Moemu commited on
Commit
ce4b83b
·
1 Parent(s): fcc1470

Upload model

Browse files
README.md CHANGED
@@ -1,3 +1,51 @@
1
- ---
2
- license: llama3
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: https://huggingface.co/FlagAlpha/Llama3-Chinese-8B-Instruct
4
+ tags:
5
+ - chinese
6
+ - lora
7
+ - llama3
8
+ library_name: peft
9
+ language:
10
+ - zh
11
+ ---
12
+
13
+ ## 模型说明
14
+
15
+ 基于 [FlagAlpha/Llama3-Chinese-8B-Instruct](https://huggingface.co/FlagAlpha/Llama3-Chinese-8B-Instruct) 微调而成的沐雪角色扮演模型,在主动对话上表现出一定的优势(固定Prompt)。使用本模型需要模型本体。
16
+
17
+ 沐雪设定可参见:[Moemu/Muice-Chatbot](https://github.com/Moemu/Muice-Chatbot?tab=readme-ov-file#沐雪人设)
18
+
19
+ 部分训练集参见:[Moemu/Muice-Dataset](https://huggingface.co/datasets/Moemu/Muice-Dataset)
20
+
21
+ ## 对话示例
22
+
23
+ ![此对话示例来自于沐雪直播间](https://img.snowy.moe/2024/image-20250126164517960.png)
24
+
25
+ ## System Prompt
26
+
27
+ 在不同任务中,模型拥有不同的System Prompt。具体参见:[Muice-Chatbot/llm/utils/auto_system_prompt.py at main · Moemu/Muice-Chatbot](https://github.com/Moemu/Muice-Chatbot/blob/main/llm/utils/auto_system_prompt.py)
28
+
29
+ ## 评估
30
+
31
+ | 模型名 | 新话题发起分数 | 直播对话性能 | 日常聊天性能 | 综合对话分数 |
32
+ | ----------------------------------------------- | -------------- | ------------ | ------------ | ------------ |
33
+ | Muice-2.3-chatglm2-6b-int4-pt-128-1e-2 | 2.80 | 4.00 | 4.33 | 3.45 |
34
+ | Muice-2.4-chatglm2-6b-int4-pt-128-1e-2 | 3.20 | 4.00 | 3.50 | 3.45 |
35
+ | Muice-2.4-Qwen2-1.5B-Instruct-GPTQ-Int4-2e-3 | 1.40 | 3.00 | 6.00 | 5.75 |
36
+ | Muice-2.5.3-Qwen2-1.5B-Instruct-GPTQ-Int4-2e-3 | 4.04 | 5.00 | 4.33 | 5.29 |
37
+ | Muice-2.6.2-Qwen-7B-Chat-Int4-5e-4 | 5.20 | 5.67 | 4.00 | 5.75 |
38
+ | Muice-2.7.0-Qwen-7B-Chat-Int4-1e-4 | 2.40 | 5.30 | 6.00 | \ |
39
+ | Muice-2.7.1-Qwen2.5-7B-Instruct-GPTQ-Int4-8e-4 | **5.40** | 4.60 | 4.50 | **6.76** |
40
+ | **Muice-2.7.1-Llama3_Chinese_8b_Instruct-8e-5** | 4.16 | **6.34** | **8.16** | 6.20 |
41
+
42
+ ## 训练参数
43
+
44
+ - learning_rate: 8e-05
45
+ - train_batch_size: 4
46
+ - eval_batch_size: 4
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - num_epochs: 5.0
51
+ - mixed_precision_training: Native AMP
adapter.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4227cf3c7906bbb3c9530b86471f42a7faa699b21cbd834c96ac987b37ed00
3
+ size 77719157
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "llama3_cn_8b_instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.01,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1782bfdd658ecd13a8aa93a2bc22e161624b7ec037c61371afdcef9138f587fa
3
+ size 83945296
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "predict_bleu-4": 66.0153542662116,
4
+ "predict_rouge-1": 73.49086416382252,
5
+ "predict_rouge-2": 66.4713481228669,
6
+ "predict_rouge-l": 71.78216040955631,
7
+ "predict_runtime": 729.4862,
8
+ "predict_samples_per_second": 0.803,
9
+ "predict_steps_per_second": 0.202,
10
+ "total_flos": 2.2102292765343744e+17,
11
+ "train_loss": 1.054027732430181,
12
+ "train_runtime": 2482.8245,
13
+ "train_samples_per_second": 5.905,
14
+ "train_steps_per_second": 1.476
15
+ }
checkpoint-3665/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/.atp/models/llama3_cn_8b_instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
checkpoint-3665/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/.atp/models/llama3_cn_8b_instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.01,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "q_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-3665/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1782bfdd658ecd13a8aa93a2bc22e161624b7ec037c61371afdcef9138f587fa
3
+ size 83945296
checkpoint-3665/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-3665/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3665/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-3665/trainer_state.json ADDED
@@ -0,0 +1,2595 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3665,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013642564802182811,
13
+ "grad_norm": 5.18676233291626,
14
+ "learning_rate": 7.999880967748602e-05,
15
+ "loss": 2.6446,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.027285129604365622,
20
+ "grad_norm": 5.224745273590088,
21
+ "learning_rate": 7.999469507332807e-05,
22
+ "loss": 2.5833,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.040927694406548434,
27
+ "grad_norm": 5.343475341796875,
28
+ "learning_rate": 7.998764179444167e-05,
29
+ "loss": 2.3323,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.054570259208731244,
34
+ "grad_norm": 3.960702657699585,
35
+ "learning_rate": 7.997765035907784e-05,
36
+ "loss": 2.2764,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.06821282401091405,
41
+ "grad_norm": 5.80894136428833,
42
+ "learning_rate": 7.99661465457664e-05,
43
+ "loss": 2.3653,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.08185538881309687,
48
+ "grad_norm": 3.9454762935638428,
49
+ "learning_rate": 7.995057481402883e-05,
50
+ "loss": 2.3655,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09549795361527967,
55
+ "grad_norm": 4.658463478088379,
56
+ "learning_rate": 7.993206764937005e-05,
57
+ "loss": 2.2008,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.10914051841746249,
62
+ "grad_norm": 7.062836647033691,
63
+ "learning_rate": 7.99106264116338e-05,
64
+ "loss": 2.4619,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.12278308321964529,
69
+ "grad_norm": 5.339938640594482,
70
+ "learning_rate": 7.988625267624962e-05,
71
+ "loss": 2.4662,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1364256480218281,
76
+ "grad_norm": 6.298858165740967,
77
+ "learning_rate": 7.9858948234117e-05,
78
+ "loss": 2.3909,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.15006821282401092,
83
+ "grad_norm": 5.622934818267822,
84
+ "learning_rate": 7.98287150914739e-05,
85
+ "loss": 2.4736,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.16371077762619374,
90
+ "grad_norm": 3.229802370071411,
91
+ "learning_rate": 7.979555546974922e-05,
92
+ "loss": 2.3796,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.17735334242837653,
97
+ "grad_norm": 5.506136894226074,
98
+ "learning_rate": 7.975947180539966e-05,
99
+ "loss": 2.2357,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.19099590723055934,
104
+ "grad_norm": 5.04240608215332,
105
+ "learning_rate": 7.972046674973065e-05,
106
+ "loss": 2.3435,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.20463847203274216,
111
+ "grad_norm": 6.470039367675781,
112
+ "learning_rate": 7.967854316870156e-05,
113
+ "loss": 2.4652,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.21828103683492497,
118
+ "grad_norm": 3.5564420223236084,
119
+ "learning_rate": 7.963370414271514e-05,
120
+ "loss": 2.2549,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.23192360163710776,
125
+ "grad_norm": 3.998383045196533,
126
+ "learning_rate": 7.958595296639115e-05,
127
+ "loss": 2.3102,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.24556616643929058,
132
+ "grad_norm": 4.615527629852295,
133
+ "learning_rate": 7.953529314832426e-05,
134
+ "loss": 2.2444,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.2592087312414734,
139
+ "grad_norm": 6.488475322723389,
140
+ "learning_rate": 7.948172841082635e-05,
141
+ "loss": 2.2928,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2728512960436562,
146
+ "grad_norm": 4.134075164794922,
147
+ "learning_rate": 7.942526268965287e-05,
148
+ "loss": 2.2113,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.286493860845839,
153
+ "grad_norm": 5.373613357543945,
154
+ "learning_rate": 7.936590013371378e-05,
155
+ "loss": 2.0795,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.30013642564802184,
160
+ "grad_norm": 5.965483665466309,
161
+ "learning_rate": 7.93036451047686e-05,
162
+ "loss": 2.3991,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.31377899045020463,
167
+ "grad_norm": 4.945356369018555,
168
+ "learning_rate": 7.923850217710604e-05,
169
+ "loss": 2.3399,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.3274215552523875,
174
+ "grad_norm": 5.210105895996094,
175
+ "learning_rate": 7.917047613720773e-05,
176
+ "loss": 2.3305,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.34106412005457026,
181
+ "grad_norm": 3.3301730155944824,
182
+ "learning_rate": 7.909957198339669e-05,
183
+ "loss": 2.2404,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.35470668485675305,
188
+ "grad_norm": 3.685528039932251,
189
+ "learning_rate": 7.902579492546998e-05,
190
+ "loss": 2.1853,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3683492496589359,
195
+ "grad_norm": 5.30728006362915,
196
+ "learning_rate": 7.894915038431595e-05,
197
+ "loss": 2.3177,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.3819918144611187,
202
+ "grad_norm": 2.644773006439209,
203
+ "learning_rate": 7.886964399151586e-05,
204
+ "loss": 2.3621,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.3956343792633015,
209
+ "grad_norm": 4.921834468841553,
210
+ "learning_rate": 7.878728158893015e-05,
211
+ "loss": 2.3687,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.4092769440654843,
216
+ "grad_norm": 3.9288289546966553,
217
+ "learning_rate": 7.870206922826921e-05,
218
+ "loss": 2.2021,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.4229195088676671,
223
+ "grad_norm": 6.143318176269531,
224
+ "learning_rate": 7.862294656001264e-05,
225
+ "loss": 2.0236,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.43656207366984995,
230
+ "grad_norm": 4.3533806800842285,
231
+ "learning_rate": 7.853233670108533e-05,
232
+ "loss": 2.4181,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.45020463847203274,
237
+ "grad_norm": 3.7804017066955566,
238
+ "learning_rate": 7.843889561656962e-05,
239
+ "loss": 2.2359,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.4638472032742155,
244
+ "grad_norm": 2.7896721363067627,
245
+ "learning_rate": 7.83426301721999e-05,
246
+ "loss": 2.2156,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.47748976807639837,
251
+ "grad_norm": 4.168877601623535,
252
+ "learning_rate": 7.824354744123498e-05,
253
+ "loss": 2.256,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.49113233287858116,
258
+ "grad_norm": 7.003695011138916,
259
+ "learning_rate": 7.814165470393832e-05,
260
+ "loss": 2.2627,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.504774897680764,
265
+ "grad_norm": 9.064947128295898,
266
+ "learning_rate": 7.803695944704313e-05,
267
+ "loss": 2.1303,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5184174624829468,
272
+ "grad_norm": 6.936222553253174,
273
+ "learning_rate": 7.79294693632023e-05,
274
+ "loss": 2.307,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5320600272851296,
279
+ "grad_norm": 4.441155433654785,
280
+ "learning_rate": 7.781919235042309e-05,
281
+ "loss": 2.2182,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5457025920873124,
286
+ "grad_norm": 7.236617088317871,
287
+ "learning_rate": 7.770613651148688e-05,
288
+ "loss": 2.2309,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5593451568894953,
293
+ "grad_norm": 4.184124946594238,
294
+ "learning_rate": 7.75903101533538e-05,
295
+ "loss": 2.0949,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.572987721691678,
300
+ "grad_norm": 2.9721992015838623,
301
+ "learning_rate": 7.747172178655232e-05,
302
+ "loss": 2.0541,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5866302864938608,
307
+ "grad_norm": 2.36011004447937,
308
+ "learning_rate": 7.735038012455398e-05,
309
+ "loss": 2.0429,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.6002728512960437,
314
+ "grad_norm": 5.892980575561523,
315
+ "learning_rate": 7.722629408313309e-05,
316
+ "loss": 2.1867,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.6139154160982264,
321
+ "grad_norm": 5.935312747955322,
322
+ "learning_rate": 7.709947277971168e-05,
323
+ "loss": 2.2556,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6275579809004093,
328
+ "grad_norm": 5.781426906585693,
329
+ "learning_rate": 7.69699255326896e-05,
330
+ "loss": 2.3728,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6412005457025921,
335
+ "grad_norm": 6.5159149169921875,
336
+ "learning_rate": 7.683766186075973e-05,
337
+ "loss": 2.4319,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.654843110504775,
342
+ "grad_norm": 3.946726083755493,
343
+ "learning_rate": 7.670269148220874e-05,
344
+ "loss": 2.2417,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6684856753069577,
349
+ "grad_norm": 5.711483001708984,
350
+ "learning_rate": 7.656502431420286e-05,
351
+ "loss": 2.1867,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6821282401091405,
356
+ "grad_norm": 1.9001113176345825,
357
+ "learning_rate": 7.64246704720593e-05,
358
+ "loss": 2.2426,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6957708049113234,
363
+ "grad_norm": 6.293882846832275,
364
+ "learning_rate": 7.628164026850302e-05,
365
+ "loss": 2.1057,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.7094133697135061,
370
+ "grad_norm": 2.980394124984741,
371
+ "learning_rate": 7.613594421290888e-05,
372
+ "loss": 2.0724,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.723055934515689,
377
+ "grad_norm": 7.354122161865234,
378
+ "learning_rate": 7.59875930105296e-05,
379
+ "loss": 2.1513,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.7366984993178718,
384
+ "grad_norm": 3.451127290725708,
385
+ "learning_rate": 7.583659756170904e-05,
386
+ "loss": 1.996,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7503410641200545,
391
+ "grad_norm": 4.8892951011657715,
392
+ "learning_rate": 7.568296896108135e-05,
393
+ "loss": 2.2927,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7639836289222374,
398
+ "grad_norm": 5.78281831741333,
399
+ "learning_rate": 7.552671849675571e-05,
400
+ "loss": 2.2445,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7776261937244202,
405
+ "grad_norm": 3.0643134117126465,
406
+ "learning_rate": 7.536785764948705e-05,
407
+ "loss": 2.1723,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.791268758526603,
412
+ "grad_norm": 5.0908732414245605,
413
+ "learning_rate": 7.520639809183234e-05,
414
+ "loss": 2.1945,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.8049113233287858,
419
+ "grad_norm": 4.066890716552734,
420
+ "learning_rate": 7.5042351687293e-05,
421
+ "loss": 2.385,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.8185538881309686,
426
+ "grad_norm": 6.034420967102051,
427
+ "learning_rate": 7.487573048944318e-05,
428
+ "loss": 1.8776,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8321964529331515,
433
+ "grad_norm": 2.5823731422424316,
434
+ "learning_rate": 7.470654674104415e-05,
435
+ "loss": 2.1586,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8458390177353342,
440
+ "grad_norm": 4.781266212463379,
441
+ "learning_rate": 7.453481287314469e-05,
442
+ "loss": 2.1229,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.859481582537517,
447
+ "grad_norm": 4.008852481842041,
448
+ "learning_rate": 7.436054150416777e-05,
449
+ "loss": 2.1562,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8731241473396999,
454
+ "grad_norm": 7.812346458435059,
455
+ "learning_rate": 7.418374543898328e-05,
456
+ "loss": 2.2563,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.8867667121418826,
461
+ "grad_norm": 5.588919639587402,
462
+ "learning_rate": 7.400443766796728e-05,
463
+ "loss": 2.0738,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.9004092769440655,
468
+ "grad_norm": 3.1923656463623047,
469
+ "learning_rate": 7.382263136604744e-05,
470
+ "loss": 1.9363,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.9140518417462483,
475
+ "grad_norm": 6.451751708984375,
476
+ "learning_rate": 7.363833989173504e-05,
477
+ "loss": 2.3014,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.927694406548431,
482
+ "grad_norm": 4.7484517097473145,
483
+ "learning_rate": 7.34515767861434e-05,
484
+ "loss": 2.1957,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9413369713506139,
489
+ "grad_norm": 4.468317031860352,
490
+ "learning_rate": 7.326235577199292e-05,
491
+ "loss": 2.4058,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9549795361527967,
496
+ "grad_norm": 4.4900078773498535,
497
+ "learning_rate": 7.307069075260283e-05,
498
+ "loss": 2.0714,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9686221009549796,
503
+ "grad_norm": 4.51573371887207,
504
+ "learning_rate": 7.287659581086957e-05,
505
+ "loss": 2.0244,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9822646657571623,
510
+ "grad_norm": 2.892160654067993,
511
+ "learning_rate": 7.268008520823203e-05,
512
+ "loss": 2.1891,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9959072305593452,
517
+ "grad_norm": 5.765126705169678,
518
+ "learning_rate": 7.248117338362371e-05,
519
+ "loss": 2.0008,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 1.009549795361528,
524
+ "grad_norm": 4.076498031616211,
525
+ "learning_rate": 7.227987495241174e-05,
526
+ "loss": 1.7823,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 1.0231923601637107,
531
+ "grad_norm": 5.407172203063965,
532
+ "learning_rate": 7.207620470532302e-05,
533
+ "loss": 1.7272,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.0368349249658937,
538
+ "grad_norm": 2.3942642211914062,
539
+ "learning_rate": 7.187017760735748e-05,
540
+ "loss": 1.7809,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 1.0504774897680764,
545
+ "grad_norm": 6.462409019470215,
546
+ "learning_rate": 7.166180879668843e-05,
547
+ "loss": 1.5226,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 1.0641200545702592,
552
+ "grad_norm": 10.609193801879883,
553
+ "learning_rate": 7.145111358355031e-05,
554
+ "loss": 1.6743,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 1.077762619372442,
559
+ "grad_norm": 5.816223621368408,
560
+ "learning_rate": 7.123810744911376e-05,
561
+ "loss": 1.3974,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 1.0914051841746248,
566
+ "grad_norm": 8.911855697631836,
567
+ "learning_rate": 7.102280604434805e-05,
568
+ "loss": 1.4882,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.1050477489768076,
573
+ "grad_norm": 8.37972640991211,
574
+ "learning_rate": 7.080522518887116e-05,
575
+ "loss": 1.8217,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.1186903137789905,
580
+ "grad_norm": 5.856902599334717,
581
+ "learning_rate": 7.058538086978738e-05,
582
+ "loss": 1.5443,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.1323328785811733,
587
+ "grad_norm": 8.661952018737793,
588
+ "learning_rate": 7.036328924051266e-05,
589
+ "loss": 1.426,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.145975443383356,
594
+ "grad_norm": 7.178607940673828,
595
+ "learning_rate": 7.013896661958766e-05,
596
+ "loss": 1.6086,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.159618008185539,
601
+ "grad_norm": 6.399686813354492,
602
+ "learning_rate": 6.991242948947879e-05,
603
+ "loss": 1.64,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.1732605729877217,
608
+ "grad_norm": 5.770147800445557,
609
+ "learning_rate": 6.968369449536705e-05,
610
+ "loss": 1.6026,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.1869031377899044,
615
+ "grad_norm": 7.86605167388916,
616
+ "learning_rate": 6.945277844392504e-05,
617
+ "loss": 1.5026,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 1.2005457025920874,
622
+ "grad_norm": 3.953367233276367,
623
+ "learning_rate": 6.921969830208212e-05,
624
+ "loss": 1.6705,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 1.21418826739427,
629
+ "grad_norm": 10.93819808959961,
630
+ "learning_rate": 6.898447119577764e-05,
631
+ "loss": 1.6982,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 1.2278308321964528,
636
+ "grad_norm": 4.714999675750732,
637
+ "learning_rate": 6.874711440870264e-05,
638
+ "loss": 1.2631,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 1.2414733969986358,
643
+ "grad_norm": 4.0259480476379395,
644
+ "learning_rate": 6.85076453810299e-05,
645
+ "loss": 1.5005,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 1.2551159618008185,
650
+ "grad_norm": 7.3578643798828125,
651
+ "learning_rate": 6.826608170813243e-05,
652
+ "loss": 1.6076,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 1.2687585266030013,
657
+ "grad_norm": 5.368468284606934,
658
+ "learning_rate": 6.802244113929075e-05,
659
+ "loss": 1.7727,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 1.2824010914051842,
664
+ "grad_norm": 7.0559916496276855,
665
+ "learning_rate": 6.777674157638862e-05,
666
+ "loss": 1.6125,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 1.296043656207367,
671
+ "grad_norm": 6.349229335784912,
672
+ "learning_rate": 6.75290010725977e-05,
673
+ "loss": 1.4289,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 1.30968622100955,
678
+ "grad_norm": 4.133677959442139,
679
+ "learning_rate": 6.727923783105111e-05,
680
+ "loss": 1.6043,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 1.3233287858117326,
685
+ "grad_norm": 5.688299655914307,
686
+ "learning_rate": 6.702747020350586e-05,
687
+ "loss": 1.6637,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 1.3369713506139154,
692
+ "grad_norm": 8.215998649597168,
693
+ "learning_rate": 6.677371668899448e-05,
694
+ "loss": 1.717,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 1.350613915416098,
699
+ "grad_norm": 6.267200946807861,
700
+ "learning_rate": 6.651799593246569e-05,
701
+ "loss": 1.572,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 1.364256480218281,
706
+ "grad_norm": 3.5424532890319824,
707
+ "learning_rate": 6.626032672341458e-05,
708
+ "loss": 1.6264,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 1.3778990450204638,
713
+ "grad_norm": 6.2543206214904785,
714
+ "learning_rate": 6.600072799450186e-05,
715
+ "loss": 1.5057,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 1.3915416098226467,
720
+ "grad_norm": 5.060370445251465,
721
+ "learning_rate": 6.573921882016284e-05,
722
+ "loss": 1.6963,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 1.4051841746248295,
727
+ "grad_norm": 7.101504325866699,
728
+ "learning_rate": 6.547581841520589e-05,
729
+ "loss": 1.3956,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 1.4188267394270122,
734
+ "grad_norm": 7.740041732788086,
735
+ "learning_rate": 6.521054613340064e-05,
736
+ "loss": 1.469,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 1.4324693042291952,
741
+ "grad_norm": 7.723188877105713,
742
+ "learning_rate": 6.494342146605581e-05,
743
+ "loss": 1.5518,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 1.446111869031378,
748
+ "grad_norm": 5.523282527923584,
749
+ "learning_rate": 6.467446404058722e-05,
750
+ "loss": 1.5123,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 1.4597544338335606,
755
+ "grad_norm": 10.065855026245117,
756
+ "learning_rate": 6.44036936190755e-05,
757
+ "loss": 1.5065,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 1.4733969986357436,
762
+ "grad_norm": 8.757994651794434,
763
+ "learning_rate": 6.413113009681411e-05,
764
+ "loss": 1.5362,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 1.4870395634379263,
769
+ "grad_norm": 10.307364463806152,
770
+ "learning_rate": 6.385679350084743e-05,
771
+ "loss": 1.7138,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 1.500682128240109,
776
+ "grad_norm": 7.119322299957275,
777
+ "learning_rate": 6.358070398849938e-05,
778
+ "loss": 1.6659,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 1.514324693042292,
783
+ "grad_norm": 12.579729080200195,
784
+ "learning_rate": 6.330288184589216e-05,
785
+ "loss": 1.6374,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 1.5279672578444747,
790
+ "grad_norm": 8.232572555541992,
791
+ "learning_rate": 6.30233474864558e-05,
792
+ "loss": 1.6296,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 1.5416098226466577,
797
+ "grad_norm": 10.136465072631836,
798
+ "learning_rate": 6.274212144942824e-05,
799
+ "loss": 1.6491,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 1.5552523874488404,
804
+ "grad_norm": 5.127601623535156,
805
+ "learning_rate": 6.245922439834612e-05,
806
+ "loss": 1.6309,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 1.5688949522510232,
811
+ "grad_norm": 6.231171607971191,
812
+ "learning_rate": 6.217467711952658e-05,
813
+ "loss": 1.5365,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 1.5825375170532059,
818
+ "grad_norm": 7.796588897705078,
819
+ "learning_rate": 6.188850052053985e-05,
820
+ "loss": 1.493,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 1.5961800818553888,
825
+ "grad_norm": 8.250170707702637,
826
+ "learning_rate": 6.160071562867316e-05,
827
+ "loss": 1.6771,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 1.6098226466575716,
832
+ "grad_norm": 4.563484191894531,
833
+ "learning_rate": 6.131134358938559e-05,
834
+ "loss": 1.5381,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 1.6234652114597545,
839
+ "grad_norm": 7.776663303375244,
840
+ "learning_rate": 6.1020405664754455e-05,
841
+ "loss": 1.4791,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 1.6371077762619373,
846
+ "grad_norm": 6.122801780700684,
847
+ "learning_rate": 6.0727923231913035e-05,
848
+ "loss": 1.5296,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 1.65075034106412,
853
+ "grad_norm": 5.5693278312683105,
854
+ "learning_rate": 6.04339177814798e-05,
855
+ "loss": 1.4165,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 1.6643929058663027,
860
+ "grad_norm": 8.107104301452637,
861
+ "learning_rate": 6.013841091597947e-05,
862
+ "loss": 1.5694,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 1.6780354706684857,
867
+ "grad_norm": 12.389050483703613,
868
+ "learning_rate": 5.9841424348255596e-05,
869
+ "loss": 1.6024,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 1.6916780354706686,
874
+ "grad_norm": 6.175624370574951,
875
+ "learning_rate": 5.954297989987526e-05,
876
+ "loss": 1.499,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 1.7053206002728514,
881
+ "grad_norm": 4.447775840759277,
882
+ "learning_rate": 5.924309949952565e-05,
883
+ "loss": 1.5177,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 1.718963165075034,
888
+ "grad_norm": 6.788479804992676,
889
+ "learning_rate": 5.8941805181402886e-05,
890
+ "loss": 1.4564,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 1.7326057298772168,
895
+ "grad_norm": 6.172934532165527,
896
+ "learning_rate": 5.8639119083592954e-05,
897
+ "loss": 1.3263,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 1.7462482946793996,
902
+ "grad_norm": 7.947272777557373,
903
+ "learning_rate": 5.833506344644507e-05,
904
+ "loss": 1.6518,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 1.7598908594815825,
909
+ "grad_norm": 5.520730018615723,
910
+ "learning_rate": 5.802966061093762e-05,
911
+ "loss": 1.4169,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 1.7735334242837655,
916
+ "grad_norm": 6.108306407928467,
917
+ "learning_rate": 5.7722933017036515e-05,
918
+ "loss": 1.4631,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 1.7871759890859482,
923
+ "grad_norm": 3.4584460258483887,
924
+ "learning_rate": 5.741490320204644e-05,
925
+ "loss": 1.5939,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 1.800818553888131,
930
+ "grad_norm": 7.870245456695557,
931
+ "learning_rate": 5.7105593798954895e-05,
932
+ "loss": 1.4775,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 1.8144611186903137,
937
+ "grad_norm": 6.256468772888184,
938
+ "learning_rate": 5.679502753476913e-05,
939
+ "loss": 1.6513,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 1.8281036834924966,
944
+ "grad_norm": 8.314029693603516,
945
+ "learning_rate": 5.648322722884635e-05,
946
+ "loss": 1.6092,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 1.8417462482946794,
951
+ "grad_norm": 7.979041576385498,
952
+ "learning_rate": 5.6170215791216926e-05,
953
+ "loss": 1.5116,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 1.8553888130968623,
958
+ "grad_norm": 7.900625228881836,
959
+ "learning_rate": 5.58560162209011e-05,
960
+ "loss": 1.3667,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 1.869031377899045,
965
+ "grad_norm": 7.304281234741211,
966
+ "learning_rate": 5.554065160421907e-05,
967
+ "loss": 1.4584,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 1.8826739427012278,
972
+ "grad_norm": 5.6456618309021,
973
+ "learning_rate": 5.522414511309472e-05,
974
+ "loss": 1.7889,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 1.8963165075034105,
979
+ "grad_norm": 5.90806770324707,
980
+ "learning_rate": 5.490652000335297e-05,
981
+ "loss": 1.5623,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 1.9099590723055935,
986
+ "grad_norm": 6.941085338592529,
987
+ "learning_rate": 5.461972027286809e-05,
988
+ "loss": 1.5508,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 1.9236016371077762,
993
+ "grad_norm": 7.18194580078125,
994
+ "learning_rate": 5.430003415054097e-05,
995
+ "loss": 1.4951,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 1.9372442019099592,
1000
+ "grad_norm": 9.118647575378418,
1001
+ "learning_rate": 5.397929731013993e-05,
1002
+ "loss": 1.601,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 1.950886766712142,
1007
+ "grad_norm": 7.178833961486816,
1008
+ "learning_rate": 5.365753331832165e-05,
1009
+ "loss": 1.5427,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 1.9645293315143246,
1014
+ "grad_norm": 5.578968524932861,
1015
+ "learning_rate": 5.3334765817214407e-05,
1016
+ "loss": 1.4017,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 1.9781718963165074,
1021
+ "grad_norm": 10.137267112731934,
1022
+ "learning_rate": 5.301101852268093e-05,
1023
+ "loss": 1.6255,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 1.9918144611186903,
1028
+ "grad_norm": 7.634779930114746,
1029
+ "learning_rate": 5.268631522257586e-05,
1030
+ "loss": 1.5628,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 2.0054570259208733,
1035
+ "grad_norm": 4.639617919921875,
1036
+ "learning_rate": 5.23606797749979e-05,
1037
+ "loss": 1.2903,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 2.019099590723056,
1042
+ "grad_norm": 9.048364639282227,
1043
+ "learning_rate": 5.2034136106536784e-05,
1044
+ "loss": 0.8694,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 2.0327421555252387,
1049
+ "grad_norm": 12.236319541931152,
1050
+ "learning_rate": 5.1706708210515225e-05,
1051
+ "loss": 1.0926,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 2.0463847203274215,
1056
+ "grad_norm": 8.067400932312012,
1057
+ "learning_rate": 5.1378420145226e-05,
1058
+ "loss": 0.9019,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 2.060027285129604,
1063
+ "grad_norm": 5.9596028327941895,
1064
+ "learning_rate": 5.104929603216422e-05,
1065
+ "loss": 0.9077,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 2.0736698499317874,
1070
+ "grad_norm": 16.68425941467285,
1071
+ "learning_rate": 5.0719360054254925e-05,
1072
+ "loss": 0.8833,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 2.08731241473397,
1077
+ "grad_norm": 10.05809497833252,
1078
+ "learning_rate": 5.0388636454076256e-05,
1079
+ "loss": 0.8182,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 2.100954979536153,
1084
+ "grad_norm": 7.299218654632568,
1085
+ "learning_rate": 5.0057149532078165e-05,
1086
+ "loss": 0.7097,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 2.1145975443383356,
1091
+ "grad_norm": 7.193046569824219,
1092
+ "learning_rate": 4.9724923644796904e-05,
1093
+ "loss": 0.8243,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 2.1282401091405183,
1098
+ "grad_norm": 6.852187633514404,
1099
+ "learning_rate": 4.939198320306537e-05,
1100
+ "loss": 0.8468,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 2.141882673942701,
1105
+ "grad_norm": 8.87316608428955,
1106
+ "learning_rate": 4.9058352670219576e-05,
1107
+ "loss": 0.8348,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 2.155525238744884,
1112
+ "grad_norm": 7.688050270080566,
1113
+ "learning_rate": 4.872405656030099e-05,
1114
+ "loss": 0.9292,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 2.169167803547067,
1119
+ "grad_norm": 9.83198356628418,
1120
+ "learning_rate": 4.83891194362555e-05,
1121
+ "loss": 0.7706,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 2.1828103683492497,
1126
+ "grad_norm": 10.323474884033203,
1127
+ "learning_rate": 4.805356590812852e-05,
1128
+ "loss": 0.8487,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 2.1964529331514324,
1133
+ "grad_norm": 8.7017183303833,
1134
+ "learning_rate": 4.771742063125674e-05,
1135
+ "loss": 0.8509,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 2.210095497953615,
1140
+ "grad_norm": 6.59673547744751,
1141
+ "learning_rate": 4.7380708304456554e-05,
1142
+ "loss": 0.8833,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 2.223738062755798,
1147
+ "grad_norm": 15.534720420837402,
1148
+ "learning_rate": 4.704345366820927e-05,
1149
+ "loss": 0.8968,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 2.237380627557981,
1154
+ "grad_norm": 11.261545181274414,
1155
+ "learning_rate": 4.670568150284323e-05,
1156
+ "loss": 0.9044,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 2.251023192360164,
1161
+ "grad_norm": 8.76096248626709,
1162
+ "learning_rate": 4.636741662671308e-05,
1163
+ "loss": 0.974,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 2.2646657571623465,
1168
+ "grad_norm": 5.140685081481934,
1169
+ "learning_rate": 4.602868389437622e-05,
1170
+ "loss": 0.8121,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 2.2783083219645293,
1175
+ "grad_norm": 9.906394004821777,
1176
+ "learning_rate": 4.568950819476648e-05,
1177
+ "loss": 1.1324,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 2.291950886766712,
1182
+ "grad_norm": 13.181589126586914,
1183
+ "learning_rate": 4.5349914449365435e-05,
1184
+ "loss": 0.8856,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 2.305593451568895,
1189
+ "grad_norm": 12.309771537780762,
1190
+ "learning_rate": 4.500992761037129e-05,
1191
+ "loss": 0.8276,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 2.319236016371078,
1196
+ "grad_norm": 10.110664367675781,
1197
+ "learning_rate": 4.4669572658865405e-05,
1198
+ "loss": 0.7492,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 2.3328785811732606,
1203
+ "grad_norm": 8.248074531555176,
1204
+ "learning_rate": 4.4328874602976786e-05,
1205
+ "loss": 0.9167,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 2.3465211459754434,
1210
+ "grad_norm": 8.356489181518555,
1211
+ "learning_rate": 4.3987858476044617e-05,
1212
+ "loss": 0.9453,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 2.360163710777626,
1217
+ "grad_norm": 5.316605091094971,
1218
+ "learning_rate": 4.364654933477886e-05,
1219
+ "loss": 0.8714,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 2.373806275579809,
1224
+ "grad_norm": 9.405285835266113,
1225
+ "learning_rate": 4.330497225741917e-05,
1226
+ "loss": 0.9251,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 2.3874488403819916,
1231
+ "grad_norm": 9.250997543334961,
1232
+ "learning_rate": 4.296315234189223e-05,
1233
+ "loss": 0.9479,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 2.4010914051841747,
1238
+ "grad_norm": 7.570913791656494,
1239
+ "learning_rate": 4.262111470396766e-05,
1240
+ "loss": 0.8346,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 2.4147339699863575,
1245
+ "grad_norm": 7.284623146057129,
1246
+ "learning_rate": 4.2278884475412585e-05,
1247
+ "loss": 0.754,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 2.42837653478854,
1252
+ "grad_norm": 8.737554550170898,
1253
+ "learning_rate": 4.193648680214505e-05,
1254
+ "loss": 0.7743,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 2.442019099590723,
1259
+ "grad_norm": 9.590819358825684,
1260
+ "learning_rate": 4.159394684238635e-05,
1261
+ "loss": 0.9273,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 2.4556616643929057,
1266
+ "grad_norm": 9.176666259765625,
1267
+ "learning_rate": 4.1251289764812495e-05,
1268
+ "loss": 1.0037,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 2.469304229195089,
1273
+ "grad_norm": 9.587228775024414,
1274
+ "learning_rate": 4.090854074670495e-05,
1275
+ "loss": 0.7728,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 2.4829467939972716,
1280
+ "grad_norm": 3.603977918624878,
1281
+ "learning_rate": 4.056572497210066e-05,
1282
+ "loss": 0.8098,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 2.4965893587994543,
1287
+ "grad_norm": 10.71971321105957,
1288
+ "learning_rate": 4.0222867629941554e-05,
1289
+ "loss": 0.8404,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 2.510231923601637,
1294
+ "grad_norm": 8.777016639709473,
1295
+ "learning_rate": 3.987999391222389e-05,
1296
+ "loss": 0.7021,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 2.52387448840382,
1301
+ "grad_norm": 9.952046394348145,
1302
+ "learning_rate": 3.953712901214707e-05,
1303
+ "loss": 0.9656,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 2.5375170532060025,
1308
+ "grad_norm": 10.772456169128418,
1309
+ "learning_rate": 3.9194298122262666e-05,
1310
+ "loss": 0.7487,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 2.5511596180081857,
1315
+ "grad_norm": 7.986364364624023,
1316
+ "learning_rate": 3.8851526432623254e-05,
1317
+ "loss": 0.8693,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 2.5648021828103684,
1322
+ "grad_norm": 8.993766784667969,
1323
+ "learning_rate": 3.850883912893158e-05,
1324
+ "loss": 0.8933,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 2.578444747612551,
1329
+ "grad_norm": 8.045419692993164,
1330
+ "learning_rate": 3.816626139069004e-05,
1331
+ "loss": 0.7098,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 2.592087312414734,
1336
+ "grad_norm": 7.299800872802734,
1337
+ "learning_rate": 3.782381838935047e-05,
1338
+ "loss": 0.8742,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 2.6057298772169166,
1343
+ "grad_norm": 8.76268482208252,
1344
+ "learning_rate": 3.748153528646472e-05,
1345
+ "loss": 0.7846,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 2.6193724420191,
1350
+ "grad_norm": 13.77757453918457,
1351
+ "learning_rate": 3.713943723183587e-05,
1352
+ "loss": 0.9032,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 2.6330150068212825,
1357
+ "grad_norm": 9.216800689697266,
1358
+ "learning_rate": 3.6797549361670257e-05,
1359
+ "loss": 0.8044,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 2.6466575716234653,
1364
+ "grad_norm": 12.811419486999512,
1365
+ "learning_rate": 3.6455896796730554e-05,
1366
+ "loss": 0.8528,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 2.660300136425648,
1371
+ "grad_norm": 8.257354736328125,
1372
+ "learning_rate": 3.611450464049005e-05,
1373
+ "loss": 0.9294,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 2.6739427012278307,
1378
+ "grad_norm": 6.599920272827148,
1379
+ "learning_rate": 3.577339797728805e-05,
1380
+ "loss": 0.9441,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 2.6875852660300135,
1385
+ "grad_norm": 10.485870361328125,
1386
+ "learning_rate": 3.5432601870486795e-05,
1387
+ "loss": 0.8572,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 2.701227830832196,
1392
+ "grad_norm": 5.167399883270264,
1393
+ "learning_rate": 3.509214136062993e-05,
1394
+ "loss": 0.9912,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 2.7148703956343794,
1399
+ "grad_norm": 9.000060081481934,
1400
+ "learning_rate": 3.475204146360254e-05,
1401
+ "loss": 0.9876,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 2.728512960436562,
1406
+ "grad_norm": 7.356120586395264,
1407
+ "learning_rate": 3.44123271687931e-05,
1408
+ "loss": 0.8796,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 2.742155525238745,
1413
+ "grad_norm": 10.706610679626465,
1414
+ "learning_rate": 3.407302343725737e-05,
1415
+ "loss": 0.8394,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 2.7557980900409276,
1420
+ "grad_norm": 6.853879928588867,
1421
+ "learning_rate": 3.3734155199884275e-05,
1422
+ "loss": 0.7603,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 2.7694406548431107,
1427
+ "grad_norm": 8.325788497924805,
1428
+ "learning_rate": 3.339574735556412e-05,
1429
+ "loss": 0.8944,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 2.7830832196452935,
1434
+ "grad_norm": 12.427726745605469,
1435
+ "learning_rate": 3.3057824769359104e-05,
1436
+ "loss": 0.9737,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 2.796725784447476,
1441
+ "grad_norm": 11.044093132019043,
1442
+ "learning_rate": 3.2720412270676275e-05,
1443
+ "loss": 0.9483,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 2.810368349249659,
1448
+ "grad_norm": 5.907009601593018,
1449
+ "learning_rate": 3.2383534651443206e-05,
1450
+ "loss": 0.9254,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 2.8240109140518417,
1455
+ "grad_norm": 5.986649036407471,
1456
+ "learning_rate": 3.204721666428631e-05,
1457
+ "loss": 0.7472,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 2.8376534788540244,
1462
+ "grad_norm": 9.0693359375,
1463
+ "learning_rate": 3.171148302071215e-05,
1464
+ "loss": 0.8689,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 2.851296043656207,
1469
+ "grad_norm": 7.178049087524414,
1470
+ "learning_rate": 3.137635838929169e-05,
1471
+ "loss": 0.7493,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 2.8649386084583903,
1476
+ "grad_norm": 8.808353424072266,
1477
+ "learning_rate": 3.1041867393847764e-05,
1478
+ "loss": 1.0867,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 2.878581173260573,
1483
+ "grad_norm": 11.312020301818848,
1484
+ "learning_rate": 3.070803461164575e-05,
1485
+ "loss": 0.9846,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 2.892223738062756,
1490
+ "grad_norm": 2.6739227771759033,
1491
+ "learning_rate": 3.0374884571587776e-05,
1492
+ "loss": 0.7862,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 2.9058663028649385,
1497
+ "grad_norm": 9.54980182647705,
1498
+ "learning_rate": 3.004244175241038e-05,
1499
+ "loss": 1.0586,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 2.9195088676671213,
1504
+ "grad_norm": 10.564549446105957,
1505
+ "learning_rate": 2.971073058088587e-05,
1506
+ "loss": 0.8757,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 2.9331514324693044,
1511
+ "grad_norm": 9.608818054199219,
1512
+ "learning_rate": 2.937977543002764e-05,
1513
+ "loss": 0.9026,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 2.946793997271487,
1518
+ "grad_norm": 4.548944473266602,
1519
+ "learning_rate": 2.9049600617299188e-05,
1520
+ "loss": 0.8864,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 2.96043656207367,
1525
+ "grad_norm": 7.556874752044678,
1526
+ "learning_rate": 2.872023040282739e-05,
1527
+ "loss": 0.8224,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 2.9740791268758526,
1532
+ "grad_norm": 9.024819374084473,
1533
+ "learning_rate": 2.8391688987620045e-05,
1534
+ "loss": 0.794,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 2.9877216916780354,
1539
+ "grad_norm": 5.675693035125732,
1540
+ "learning_rate": 2.8064000511787523e-05,
1541
+ "loss": 0.9792,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 3.001364256480218,
1546
+ "grad_norm": 6.426331520080566,
1547
+ "learning_rate": 2.77371890527691e-05,
1548
+ "loss": 0.7812,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 3.0150068212824013,
1553
+ "grad_norm": 7.24752140045166,
1554
+ "learning_rate": 2.741127862356389e-05,
1555
+ "loss": 0.496,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 3.028649386084584,
1560
+ "grad_norm": 8.4566650390625,
1561
+ "learning_rate": 2.7086293170966312e-05,
1562
+ "loss": 0.3416,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 3.0422919508867667,
1567
+ "grad_norm": 5.965997219085693,
1568
+ "learning_rate": 2.6762256573806664e-05,
1569
+ "loss": 0.3462,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 3.0559345156889495,
1574
+ "grad_norm": 10.749195098876953,
1575
+ "learning_rate": 2.6439192641196583e-05,
1576
+ "loss": 0.4756,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 3.069577080491132,
1581
+ "grad_norm": 7.666036605834961,
1582
+ "learning_rate": 2.611712511077959e-05,
1583
+ "loss": 0.357,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 3.083219645293315,
1588
+ "grad_norm": 7.038111209869385,
1589
+ "learning_rate": 2.5796077646986922e-05,
1590
+ "loss": 0.3361,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 3.096862210095498,
1595
+ "grad_norm": 10.389034271240234,
1596
+ "learning_rate": 2.5476073839298857e-05,
1597
+ "loss": 0.419,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 3.110504774897681,
1602
+ "grad_norm": 6.829967021942139,
1603
+ "learning_rate": 2.5157137200511253e-05,
1604
+ "loss": 0.4211,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 3.1241473396998636,
1609
+ "grad_norm": 4.85243558883667,
1610
+ "learning_rate": 2.4839291165008073e-05,
1611
+ "loss": 0.5248,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 3.1377899045020463,
1616
+ "grad_norm": 7.922482490539551,
1617
+ "learning_rate": 2.452255908703945e-05,
1618
+ "loss": 0.3983,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 3.151432469304229,
1623
+ "grad_norm": 4.674210071563721,
1624
+ "learning_rate": 2.420696423900567e-05,
1625
+ "loss": 0.3728,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 3.1650750341064118,
1630
+ "grad_norm": 16.18085289001465,
1631
+ "learning_rate": 2.3892529809747195e-05,
1632
+ "loss": 0.4099,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 3.178717598908595,
1637
+ "grad_norm": 10.127204895019531,
1638
+ "learning_rate": 2.35792789028409e-05,
1639
+ "loss": 0.5466,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 3.1923601637107777,
1644
+ "grad_norm": 6.371789932250977,
1645
+ "learning_rate": 2.32672345349024e-05,
1646
+ "loss": 0.3956,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 3.2060027285129604,
1651
+ "grad_norm": 6.170881748199463,
1652
+ "learning_rate": 2.2956419633894922e-05,
1653
+ "loss": 0.2686,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 3.219645293315143,
1658
+ "grad_norm": 8.651374816894531,
1659
+ "learning_rate": 2.264685703744466e-05,
1660
+ "loss": 0.3545,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 3.233287858117326,
1665
+ "grad_norm": 9.146707534790039,
1666
+ "learning_rate": 2.2338569491162688e-05,
1667
+ "loss": 0.4361,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 3.246930422919509,
1672
+ "grad_norm": 10.473475456237793,
1673
+ "learning_rate": 2.2031579646973662e-05,
1674
+ "loss": 0.4616,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 3.260572987721692,
1679
+ "grad_norm": 7.665262222290039,
1680
+ "learning_rate": 2.1725910061451582e-05,
1681
+ "loss": 0.4095,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 3.2742155525238745,
1686
+ "grad_norm": 14.176889419555664,
1687
+ "learning_rate": 2.1421583194162237e-05,
1688
+ "loss": 0.4428,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 3.2878581173260573,
1693
+ "grad_norm": 10.604450225830078,
1694
+ "learning_rate": 2.1118621406013045e-05,
1695
+ "loss": 0.4946,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 3.30150068212824,
1700
+ "grad_norm": 9.188895225524902,
1701
+ "learning_rate": 2.0817046957610073e-05,
1702
+ "loss": 0.3676,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 3.3151432469304227,
1707
+ "grad_norm": 5.148584842681885,
1708
+ "learning_rate": 2.0516882007622318e-05,
1709
+ "loss": 0.4319,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 3.328785811732606,
1714
+ "grad_norm": 10.153374671936035,
1715
+ "learning_rate": 2.0218148611153614e-05,
1716
+ "loss": 0.3973,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 3.3424283765347886,
1721
+ "grad_norm": 2.798651695251465,
1722
+ "learning_rate": 1.99208687181221e-05,
1723
+ "loss": 0.3728,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 3.3560709413369714,
1728
+ "grad_norm": 7.391672611236572,
1729
+ "learning_rate": 1.9625064171647403e-05,
1730
+ "loss": 0.4029,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 3.369713506139154,
1735
+ "grad_norm": 8.293444633483887,
1736
+ "learning_rate": 1.933075670644566e-05,
1737
+ "loss": 0.5182,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 3.383356070941337,
1742
+ "grad_norm": 12.008163452148438,
1743
+ "learning_rate": 1.903796794723261e-05,
1744
+ "loss": 0.3211,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 3.39699863574352,
1749
+ "grad_norm": 4.839990139007568,
1750
+ "learning_rate": 1.8746719407134558e-05,
1751
+ "loss": 0.3218,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 3.4106412005457027,
1756
+ "grad_norm": 5.815826892852783,
1757
+ "learning_rate": 1.8457032486107733e-05,
1758
+ "loss": 0.3561,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 3.4242837653478855,
1763
+ "grad_norm": 5.609132766723633,
1764
+ "learning_rate": 1.816892846936592e-05,
1765
+ "loss": 0.4223,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 3.437926330150068,
1770
+ "grad_norm": 6.10213041305542,
1771
+ "learning_rate": 1.7882428525816434e-05,
1772
+ "loss": 0.2911,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 3.451568894952251,
1777
+ "grad_norm": 6.413115501403809,
1778
+ "learning_rate": 1.759755370650472e-05,
1779
+ "loss": 0.3991,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 3.4652114597544337,
1784
+ "grad_norm": 10.340503692626953,
1785
+ "learning_rate": 1.7314324943067598e-05,
1786
+ "loss": 0.3823,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 3.4788540245566164,
1791
+ "grad_norm": 10.008712768554688,
1792
+ "learning_rate": 1.70327630461953e-05,
1793
+ "loss": 0.3564,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 3.4924965893587996,
1798
+ "grad_norm": 7.237100601196289,
1799
+ "learning_rate": 1.6752888704102304e-05,
1800
+ "loss": 0.4012,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 3.5061391541609823,
1805
+ "grad_norm": 7.369434833526611,
1806
+ "learning_rate": 1.6474722481007344e-05,
1807
+ "loss": 0.3622,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 3.519781718963165,
1812
+ "grad_norm": 10.581721305847168,
1813
+ "learning_rate": 1.619828481562229e-05,
1814
+ "loss": 0.3502,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 3.533424283765348,
1819
+ "grad_norm": 7.968098163604736,
1820
+ "learning_rate": 1.5923596019650517e-05,
1821
+ "loss": 0.4129,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 3.547066848567531,
1826
+ "grad_norm": 9.581936836242676,
1827
+ "learning_rate": 1.565067627629432e-05,
1828
+ "loss": 0.455,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 3.5607094133697137,
1833
+ "grad_norm": 7.407210350036621,
1834
+ "learning_rate": 1.5379545638772032e-05,
1835
+ "loss": 0.3905,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 3.5743519781718964,
1840
+ "grad_norm": 9.555901527404785,
1841
+ "learning_rate": 1.511022402884459e-05,
1842
+ "loss": 0.4603,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 3.587994542974079,
1847
+ "grad_norm": 5.677056312561035,
1848
+ "learning_rate": 1.4842731235351653e-05,
1849
+ "loss": 0.3654,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 3.601637107776262,
1854
+ "grad_norm": 8.808677673339844,
1855
+ "learning_rate": 1.4577086912757659e-05,
1856
+ "loss": 0.4481,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 3.6152796725784446,
1861
+ "grad_norm": 11.250635147094727,
1862
+ "learning_rate": 1.4313310579707697e-05,
1863
+ "loss": 0.4829,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 3.6289222373806274,
1868
+ "grad_norm": 8.87308406829834,
1869
+ "learning_rate": 1.405142161759327e-05,
1870
+ "loss": 0.3937,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 3.64256480218281,
1875
+ "grad_norm": 7.986633777618408,
1876
+ "learning_rate": 1.3791439269128274e-05,
1877
+ "loss": 0.3902,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 3.6562073669849933,
1882
+ "grad_norm": 6.5852155685424805,
1883
+ "learning_rate": 1.3533382636935092e-05,
1884
+ "loss": 0.4495,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 3.669849931787176,
1889
+ "grad_norm": 22.476903915405273,
1890
+ "learning_rate": 1.3277270682140996e-05,
1891
+ "loss": 0.4707,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 3.6834924965893587,
1896
+ "grad_norm": 6.103644371032715,
1897
+ "learning_rate": 1.3023122222984941e-05,
1898
+ "loss": 0.4189,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 3.6971350613915415,
1903
+ "grad_norm": 8.584049224853516,
1904
+ "learning_rate": 1.2770955933434906e-05,
1905
+ "loss": 0.3741,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 3.7107776261937246,
1910
+ "grad_norm": 8.539772033691406,
1911
+ "learning_rate": 1.2520790341815726e-05,
1912
+ "loss": 0.3724,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 3.7244201909959074,
1917
+ "grad_norm": 8.408806800842285,
1918
+ "learning_rate": 1.2272643829447723e-05,
1919
+ "loss": 0.4002,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 3.73806275579809,
1924
+ "grad_norm": 13.712347030639648,
1925
+ "learning_rate": 1.2026534629296168e-05,
1926
+ "loss": 0.4129,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 3.751705320600273,
1931
+ "grad_norm": 7.925304412841797,
1932
+ "learning_rate": 1.1782480824631478e-05,
1933
+ "loss": 0.3354,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 3.7653478854024556,
1938
+ "grad_norm": 6.753428936004639,
1939
+ "learning_rate": 1.154050034770057e-05,
1940
+ "loss": 0.3,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 3.7789904502046383,
1945
+ "grad_norm": 11.436506271362305,
1946
+ "learning_rate": 1.1300610978409301e-05,
1947
+ "loss": 0.4613,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 3.792633015006821,
1952
+ "grad_norm": 7.002927780151367,
1953
+ "learning_rate": 1.1062830343015998e-05,
1954
+ "loss": 0.3782,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 3.806275579809004,
1959
+ "grad_norm": 8.752483367919922,
1960
+ "learning_rate": 1.0827175912836352e-05,
1961
+ "loss": 0.3154,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 3.819918144611187,
1966
+ "grad_norm": 8.298131942749023,
1967
+ "learning_rate": 1.059366500295973e-05,
1968
+ "loss": 0.3941,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 3.8335607094133697,
1973
+ "grad_norm": 9.577731132507324,
1974
+ "learning_rate": 1.0362314770976858e-05,
1975
+ "loss": 0.4402,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 3.8472032742155524,
1980
+ "grad_norm": 8.360587120056152,
1981
+ "learning_rate": 1.0133142215719176e-05,
1982
+ "loss": 0.3588,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 3.8608458390177356,
1987
+ "grad_norm": 7.106631755828857,
1988
+ "learning_rate": 9.906164176009825e-06,
1989
+ "loss": 0.4171,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 3.8744884038199183,
1994
+ "grad_norm": 7.905004501342773,
1995
+ "learning_rate": 9.681397329426363e-06,
1996
+ "loss": 0.4008,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 3.888130968622101,
2001
+ "grad_norm": 7.430079460144043,
2002
+ "learning_rate": 9.458858191075358e-06,
2003
+ "loss": 0.2851,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 3.901773533424284,
2008
+ "grad_norm": 6.089357852935791,
2009
+ "learning_rate": 9.238563112378967e-06,
2010
+ "loss": 0.486,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 3.9154160982264665,
2015
+ "grad_norm": 10.433391571044922,
2016
+ "learning_rate": 9.02052827987339e-06,
2017
+ "loss": 0.3321,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 3.9290586630286493,
2022
+ "grad_norm": 11.072164535522461,
2023
+ "learning_rate": 8.804769714019619e-06,
2024
+ "loss": 0.2981,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 3.942701227830832,
2029
+ "grad_norm": 6.538973331451416,
2030
+ "learning_rate": 8.591303268026293e-06,
2031
+ "loss": 0.3412,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 3.956343792633015,
2036
+ "grad_norm": 6.748257637023926,
2037
+ "learning_rate": 8.380144626684829e-06,
2038
+ "loss": 0.3648,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 3.969986357435198,
2043
+ "grad_norm": 8.447965621948242,
2044
+ "learning_rate": 8.171309305216973e-06,
2045
+ "loss": 0.4028,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 3.9836289222373806,
2050
+ "grad_norm": 11.228553771972656,
2051
+ "learning_rate": 7.96481264813481e-06,
2052
+ "loss": 0.5365,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 3.9972714870395634,
2057
+ "grad_norm": 16.4576416015625,
2058
+ "learning_rate": 7.760669828113276e-06,
2059
+ "loss": 0.3312,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 4.0109140518417465,
2064
+ "grad_norm": 9.181668281555176,
2065
+ "learning_rate": 7.558895844875325e-06,
2066
+ "loss": 0.2586,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 4.024556616643929,
2071
+ "grad_norm": 6.005313873291016,
2072
+ "learning_rate": 7.359505524089843e-06,
2073
+ "loss": 0.174,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 4.038199181446112,
2078
+ "grad_norm": 9.592679977416992,
2079
+ "learning_rate": 7.162513516282236e-06,
2080
+ "loss": 0.1319,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 4.051841746248295,
2085
+ "grad_norm": 4.006359100341797,
2086
+ "learning_rate": 6.967934295758003e-06,
2087
+ "loss": 0.1098,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 4.0654843110504775,
2092
+ "grad_norm": 8.887368202209473,
2093
+ "learning_rate": 6.775782159539237e-06,
2094
+ "loss": 0.1351,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 4.07912687585266,
2099
+ "grad_norm": 4.626531600952148,
2100
+ "learning_rate": 6.586071226314046e-06,
2101
+ "loss": 0.2408,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 4.092769440654843,
2106
+ "grad_norm": 3.412660598754883,
2107
+ "learning_rate": 6.3988154353992285e-06,
2108
+ "loss": 0.1759,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 4.106412005457026,
2113
+ "grad_norm": 3.9307303428649902,
2114
+ "learning_rate": 6.214028545716071e-06,
2115
+ "loss": 0.2398,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 4.120054570259208,
2120
+ "grad_norm": 4.589839935302734,
2121
+ "learning_rate": 6.031724134779331e-06,
2122
+ "loss": 0.1491,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 4.133697135061391,
2127
+ "grad_norm": 5.797046184539795,
2128
+ "learning_rate": 5.851915597699638e-06,
2129
+ "loss": 0.1711,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 4.147339699863575,
2134
+ "grad_norm": 6.0500030517578125,
2135
+ "learning_rate": 5.674616146199277e-06,
2136
+ "loss": 0.1815,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 4.1609822646657575,
2141
+ "grad_norm": 5.424590587615967,
2142
+ "learning_rate": 5.499838807641413e-06,
2143
+ "loss": 0.2796,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 4.17462482946794,
2148
+ "grad_norm": 10.55384349822998,
2149
+ "learning_rate": 5.327596424072896e-06,
2150
+ "loss": 0.2307,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 4.188267394270123,
2155
+ "grad_norm": 11.20399284362793,
2156
+ "learning_rate": 5.157901651280672e-06,
2157
+ "loss": 0.1955,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 4.201909959072306,
2162
+ "grad_norm": 5.694499492645264,
2163
+ "learning_rate": 4.990766957861875e-06,
2164
+ "loss": 0.2332,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 4.215552523874488,
2169
+ "grad_norm": 3.623840093612671,
2170
+ "learning_rate": 4.826204624307665e-06,
2171
+ "loss": 0.1317,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 4.229195088676671,
2176
+ "grad_norm": 6.306783199310303,
2177
+ "learning_rate": 4.664226742100946e-06,
2178
+ "loss": 0.1772,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 4.242837653478854,
2183
+ "grad_norm": 5.530797004699707,
2184
+ "learning_rate": 4.504845212827848e-06,
2185
+ "loss": 0.1893,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 4.256480218281037,
2190
+ "grad_norm": 6.482370853424072,
2191
+ "learning_rate": 4.348071747303322e-06,
2192
+ "loss": 0.2459,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 4.270122783083219,
2197
+ "grad_norm": 6.513676643371582,
2198
+ "learning_rate": 4.193917864710599e-06,
2199
+ "loss": 0.1615,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 4.283765347885402,
2204
+ "grad_norm": 7.2312703132629395,
2205
+ "learning_rate": 4.042394891754846e-06,
2206
+ "loss": 0.1488,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 4.297407912687586,
2211
+ "grad_norm": 8.509649276733398,
2212
+ "learning_rate": 3.893513961830886e-06,
2213
+ "loss": 0.1507,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 4.311050477489768,
2218
+ "grad_norm": 8.615159034729004,
2219
+ "learning_rate": 3.74728601420518e-06,
2220
+ "loss": 0.1768,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 4.324693042291951,
2225
+ "grad_norm": 9.077027320861816,
2226
+ "learning_rate": 3.6037217932120272e-06,
2227
+ "loss": 0.3008,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 4.338335607094134,
2232
+ "grad_norm": 4.60724401473999,
2233
+ "learning_rate": 3.4628318474641344e-06,
2234
+ "loss": 0.1839,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 4.351978171896317,
2239
+ "grad_norm": 3.5988879203796387,
2240
+ "learning_rate": 3.3246265290775013e-06,
2241
+ "loss": 0.1681,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 4.365620736698499,
2246
+ "grad_norm": 3.6327638626098633,
2247
+ "learning_rate": 3.1891159929108074e-06,
2248
+ "loss": 0.2091,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 4.379263301500682,
2253
+ "grad_norm": 7.489198207855225,
2254
+ "learning_rate": 3.0563101958192677e-06,
2255
+ "loss": 0.175,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 4.392905866302865,
2260
+ "grad_norm": 7.076563835144043,
2261
+ "learning_rate": 2.9262188959230297e-06,
2262
+ "loss": 0.2715,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 4.406548431105048,
2267
+ "grad_norm": 4.808744430541992,
2268
+ "learning_rate": 2.7988516518901643e-06,
2269
+ "loss": 0.205,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 4.42019099590723,
2274
+ "grad_norm": 12.732096672058105,
2275
+ "learning_rate": 2.674217822234382e-06,
2276
+ "loss": 0.1804,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 4.433833560709413,
2281
+ "grad_norm": 4.898436546325684,
2282
+ "learning_rate": 2.5523265646273252e-06,
2283
+ "loss": 0.2301,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 4.447476125511596,
2288
+ "grad_norm": 3.7656116485595703,
2289
+ "learning_rate": 2.433186835225745e-06,
2290
+ "loss": 0.2665,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 4.461118690313779,
2295
+ "grad_norm": 4.772073745727539,
2296
+ "learning_rate": 2.316807388013431e-06,
2297
+ "loss": 0.1443,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 4.474761255115962,
2302
+ "grad_norm": 7.5682830810546875,
2303
+ "learning_rate": 2.203196774157972e-06,
2304
+ "loss": 0.2292,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 4.488403819918145,
2309
+ "grad_norm": 4.153563976287842,
2310
+ "learning_rate": 2.0923633413824663e-06,
2311
+ "loss": 0.1765,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 4.502046384720328,
2316
+ "grad_norm": 3.0278851985931396,
2317
+ "learning_rate": 1.98431523335215e-06,
2318
+ "loss": 0.1966,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 4.51568894952251,
2323
+ "grad_norm": 3.25349497795105,
2324
+ "learning_rate": 1.8790603890760328e-06,
2325
+ "loss": 0.2525,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 4.529331514324693,
2330
+ "grad_norm": 6.384403228759766,
2331
+ "learning_rate": 1.7766065423235624e-06,
2332
+ "loss": 0.1502,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 4.542974079126876,
2337
+ "grad_norm": 8.483981132507324,
2338
+ "learning_rate": 1.6769612210563834e-06,
2339
+ "loss": 0.2251,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 4.5566166439290585,
2344
+ "grad_norm": 5.477599620819092,
2345
+ "learning_rate": 1.5801317468751954e-06,
2346
+ "loss": 0.1724,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 4.570259208731241,
2351
+ "grad_norm": 6.450118541717529,
2352
+ "learning_rate": 1.4861252344817812e-06,
2353
+ "loss": 0.1416,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 4.583901773533424,
2358
+ "grad_norm": 8.463088035583496,
2359
+ "learning_rate": 1.3949485911562799e-06,
2360
+ "loss": 0.1507,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 4.597544338335607,
2365
+ "grad_norm": 5.667326927185059,
2366
+ "learning_rate": 1.3066085162496057e-06,
2367
+ "loss": 0.1486,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 4.61118690313779,
2372
+ "grad_norm": 8.173833847045898,
2373
+ "learning_rate": 1.2211115006912499e-06,
2374
+ "loss": 0.1823,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 4.624829467939973,
2379
+ "grad_norm": 7.300376892089844,
2380
+ "learning_rate": 1.1384638265123305e-06,
2381
+ "loss": 0.1146,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 4.638472032742156,
2386
+ "grad_norm": 5.938165664672852,
2387
+ "learning_rate": 1.0586715663840175e-06,
2388
+ "loss": 0.2206,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 4.6521145975443385,
2393
+ "grad_norm": 5.717035293579102,
2394
+ "learning_rate": 9.817405831713135e-07,
2395
+ "loss": 0.137,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 4.665757162346521,
2400
+ "grad_norm": 9.58558464050293,
2401
+ "learning_rate": 9.076765295022949e-07,
2402
+ "loss": 0.1969,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 4.679399727148704,
2407
+ "grad_norm": 5.858943462371826,
2408
+ "learning_rate": 8.364848473527698e-07,
2409
+ "loss": 0.1712,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 4.693042291950887,
2414
+ "grad_norm": 5.517107009887695,
2415
+ "learning_rate": 7.748725387928791e-07,
2416
+ "loss": 0.1606,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 4.7066848567530695,
2421
+ "grad_norm": 2.8044917583465576,
2422
+ "learning_rate": 7.09152598980536e-07,
2423
+ "loss": 0.1722,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 4.720327421555252,
2428
+ "grad_norm": 5.587821960449219,
2429
+ "learning_rate": 6.463196175536768e-07,
2430
+ "loss": 0.2592,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 4.733969986357435,
2435
+ "grad_norm": 8.284170150756836,
2436
+ "learning_rate": 5.863782112669647e-07,
2437
+ "loss": 0.2729,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 4.747612551159618,
2442
+ "grad_norm": 7.003023147583008,
2443
+ "learning_rate": 5.293327844118956e-07,
2444
+ "loss": 0.1888,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 4.7612551159618,
2449
+ "grad_norm": 1.9856537580490112,
2450
+ "learning_rate": 4.751875284932217e-07,
2451
+ "loss": 0.1367,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 4.774897680763983,
2456
+ "grad_norm": 6.205258846282959,
2457
+ "learning_rate": 4.2394642192095327e-07,
2458
+ "loss": 0.2003,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 4.788540245566167,
2463
+ "grad_norm": 5.503448009490967,
2464
+ "learning_rate": 3.7561322971803706e-07,
2465
+ "loss": 0.1503,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 4.8021828103683495,
2470
+ "grad_norm": 5.814334392547607,
2471
+ "learning_rate": 3.301915032437375e-07,
2472
+ "loss": 0.1425,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 4.815825375170532,
2477
+ "grad_norm": 7.47700309753418,
2478
+ "learning_rate": 2.8768457993266775e-07,
2479
+ "loss": 0.1265,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 4.829467939972715,
2484
+ "grad_norm": 6.920642375946045,
2485
+ "learning_rate": 2.480955830495679e-07,
2486
+ "loss": 0.2103,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 4.843110504774898,
2491
+ "grad_norm": 8.557290077209473,
2492
+ "learning_rate": 2.1142742145984442e-07,
2493
+ "loss": 0.2395,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 4.85675306957708,
2498
+ "grad_norm": 7.730421543121338,
2499
+ "learning_rate": 1.7768278941581617e-07,
2500
+ "loss": 0.1317,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 4.870395634379263,
2505
+ "grad_norm": 4.612334728240967,
2506
+ "learning_rate": 1.4686416635874445e-07,
2507
+ "loss": 0.1802,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 4.884038199181446,
2512
+ "grad_norm": 6.5652899742126465,
2513
+ "learning_rate": 1.1897381673666719e-07,
2514
+ "loss": 0.2484,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 4.897680763983629,
2519
+ "grad_norm": 8.53544807434082,
2520
+ "learning_rate": 9.40137898380078e-08,
2521
+ "loss": 0.1346,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 4.911323328785811,
2526
+ "grad_norm": 6.831415176391602,
2527
+ "learning_rate": 7.198591964099777e-08,
2528
+ "loss": 0.2097,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 4.924965893587995,
2533
+ "grad_norm": 11.197553634643555,
2534
+ "learning_rate": 5.289182467893561e-08,
2535
+ "loss": 0.1865,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 4.938608458390178,
2540
+ "grad_norm": 9.906291007995605,
2541
+ "learning_rate": 3.6732907921241956e-08,
2542
+ "loss": 0.2137,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 4.95225102319236,
2547
+ "grad_norm": 6.347635269165039,
2548
+ "learning_rate": 2.351035667038648e-08,
2549
+ "loss": 0.1699,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 4.965893587994543,
2554
+ "grad_norm": 2.5308990478515625,
2555
+ "learning_rate": 1.3225142474651009e-08,
2556
+ "loss": 0.247,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 4.979536152796726,
2561
+ "grad_norm": 8.235413551330566,
2562
+ "learning_rate": 5.878021056742178e-09,
2563
+ "loss": 0.1884,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 4.993178717598909,
2568
+ "grad_norm": 8.303121566772461,
2569
+ "learning_rate": 1.4695322582491956e-09,
2570
+ "loss": 0.186,
2571
+ "step": 3660
2572
+ }
2573
+ ],
2574
+ "logging_steps": 10,
2575
+ "max_steps": 3665,
2576
+ "num_input_tokens_seen": 0,
2577
+ "num_train_epochs": 5,
2578
+ "save_steps": 500.0,
2579
+ "stateful_callbacks": {
2580
+ "TrainerControl": {
2581
+ "args": {
2582
+ "should_epoch_stop": false,
2583
+ "should_evaluate": false,
2584
+ "should_log": false,
2585
+ "should_save": true,
2586
+ "should_training_stop": true
2587
+ },
2588
+ "attributes": {}
2589
+ }
2590
+ },
2591
+ "total_flos": 2.2102292765343744e+17,
2592
+ "train_batch_size": 4,
2593
+ "trial_name": null,
2594
+ "trial_params": null
2595
+ }
checkpoint-3665/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa89ca6dfb1c8dadc04eb97aacb2843a70e0a6ea9f28cdd1741081039e0e341
3
+ size 5368
dataset_info.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "7ps2u174_e564dc1efb": {
3
+ "columns": {
4
+ "system": "system",
5
+ "response": "output",
6
+ "prompt": "instruction"
7
+ },
8
+ "file_name": "/work/datasets/7ps2u174/train.json"
9
+ },
10
+ "7ps2u174_e564dc1efb_eval": {
11
+ "columns": {
12
+ "system": "system",
13
+ "response": "output",
14
+ "prompt": "instruction"
15
+ },
16
+ "file_name": "/work/data/7ps2u174_e564dc1efb_eval.jsonl"
17
+ }
18
+ }
error.log ADDED
The diff for this file is too large to render. See raw diff
 
generated_predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu-4": 66.0153542662116,
3
+ "predict_rouge-1": 73.49086416382252,
4
+ "predict_rouge-2": 66.4713481228669,
5
+ "predict_rouge-l": 71.78216040955631,
6
+ "predict_runtime": 729.4862,
7
+ "predict_samples_per_second": 0.803,
8
+ "predict_steps_per_second": 0.202
9
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 2.2102292765343744e+17,
4
+ "train_loss": 1.054027732430181,
5
+ "train_runtime": 2482.8245,
6
+ "train_samples_per_second": 5.905,
7
+ "train_steps_per_second": 1.476
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,367 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3665, "loss": 2.6446, "learning_rate": 7.999880967748602e-05, "epoch": 0.013642564802182811, "percentage": 0.27, "elapsed_time": "0:00:07", "remaining_time": "0:44:58", "throughput": "0.00", "total_tokens": 0}
2
+ {"current_steps": 20, "total_steps": 3665, "loss": 2.5833, "learning_rate": 7.999469507332807e-05, "epoch": 0.027285129604365622, "percentage": 0.55, "elapsed_time": "0:00:14", "remaining_time": "0:42:53", "throughput": "0.00", "total_tokens": 0}
3
+ {"current_steps": 30, "total_steps": 3665, "loss": 2.3323, "learning_rate": 7.998764179444167e-05, "epoch": 0.040927694406548434, "percentage": 0.82, "elapsed_time": "0:00:21", "remaining_time": "0:43:33", "throughput": "0.00", "total_tokens": 0}
4
+ {"current_steps": 40, "total_steps": 3665, "loss": 2.2764, "learning_rate": 7.997765035907784e-05, "epoch": 0.054570259208731244, "percentage": 1.09, "elapsed_time": "0:00:28", "remaining_time": "0:42:49", "throughput": "0.00", "total_tokens": 0}
5
+ {"current_steps": 50, "total_steps": 3665, "loss": 2.3653, "learning_rate": 7.99661465457664e-05, "epoch": 0.06821282401091405, "percentage": 1.36, "elapsed_time": "0:00:35", "remaining_time": "0:42:48", "throughput": "0.00", "total_tokens": 0}
6
+ {"current_steps": 60, "total_steps": 3665, "loss": 2.3655, "learning_rate": 7.995057481402883e-05, "epoch": 0.08185538881309687, "percentage": 1.64, "elapsed_time": "0:00:41", "remaining_time": "0:42:02", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 70, "total_steps": 3665, "loss": 2.2008, "learning_rate": 7.993206764937005e-05, "epoch": 0.09549795361527967, "percentage": 1.91, "elapsed_time": "0:00:48", "remaining_time": "0:41:18", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 80, "total_steps": 3665, "loss": 2.4619, "learning_rate": 7.99106264116338e-05, "epoch": 0.10914051841746249, "percentage": 2.18, "elapsed_time": "0:00:55", "remaining_time": "0:41:15", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 90, "total_steps": 3665, "loss": 2.4662, "learning_rate": 7.988625267624962e-05, "epoch": 0.12278308321964529, "percentage": 2.46, "elapsed_time": "0:01:01", "remaining_time": "0:40:57", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 100, "total_steps": 3665, "loss": 2.3909, "learning_rate": 7.9858948234117e-05, "epoch": 0.1364256480218281, "percentage": 2.73, "elapsed_time": "0:01:08", "remaining_time": "0:40:34", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 110, "total_steps": 3665, "loss": 2.4736, "learning_rate": 7.98287150914739e-05, "epoch": 0.15006821282401092, "percentage": 3.0, "elapsed_time": "0:01:14", "remaining_time": "0:40:07", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 120, "total_steps": 3665, "loss": 2.3796, "learning_rate": 7.979555546974922e-05, "epoch": 0.16371077762619374, "percentage": 3.27, "elapsed_time": "0:01:21", "remaining_time": "0:39:59", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 130, "total_steps": 3665, "loss": 2.2357, "learning_rate": 7.975947180539966e-05, "epoch": 0.17735334242837653, "percentage": 3.55, "elapsed_time": "0:01:27", "remaining_time": "0:39:39", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 140, "total_steps": 3665, "loss": 2.3435, "learning_rate": 7.972046674973065e-05, "epoch": 0.19099590723055934, "percentage": 3.82, "elapsed_time": "0:01:34", "remaining_time": "0:39:32", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 150, "total_steps": 3665, "loss": 2.4652, "learning_rate": 7.967854316870156e-05, "epoch": 0.20463847203274216, "percentage": 4.09, "elapsed_time": "0:01:40", "remaining_time": "0:39:20", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 160, "total_steps": 3665, "loss": 2.2549, "learning_rate": 7.963370414271514e-05, "epoch": 0.21828103683492497, "percentage": 4.37, "elapsed_time": "0:01:47", "remaining_time": "0:39:10", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 170, "total_steps": 3665, "loss": 2.3102, "learning_rate": 7.958595296639115e-05, "epoch": 0.23192360163710776, "percentage": 4.64, "elapsed_time": "0:01:54", "remaining_time": "0:39:20", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 180, "total_steps": 3665, "loss": 2.2444, "learning_rate": 7.953529314832426e-05, "epoch": 0.24556616643929058, "percentage": 4.91, "elapsed_time": "0:02:01", "remaining_time": "0:39:10", "throughput": "0.00", "total_tokens": 0}
19
+ {"current_steps": 190, "total_steps": 3665, "loss": 2.2928, "learning_rate": 7.948172841082635e-05, "epoch": 0.2592087312414734, "percentage": 5.18, "elapsed_time": "0:02:08", "remaining_time": "0:39:05", "throughput": "0.00", "total_tokens": 0}
20
+ {"current_steps": 200, "total_steps": 3665, "loss": 2.2113, "learning_rate": 7.942526268965287e-05, "epoch": 0.2728512960436562, "percentage": 5.46, "elapsed_time": "0:02:14", "remaining_time": "0:38:58", "throughput": "0.00", "total_tokens": 0}
21
+ {"current_steps": 210, "total_steps": 3665, "loss": 2.0795, "learning_rate": 7.936590013371378e-05, "epoch": 0.286493860845839, "percentage": 5.73, "elapsed_time": "0:02:23", "remaining_time": "0:39:13", "throughput": "0.00", "total_tokens": 0}
22
+ {"current_steps": 220, "total_steps": 3665, "loss": 2.3991, "learning_rate": 7.93036451047686e-05, "epoch": 0.30013642564802184, "percentage": 6.0, "elapsed_time": "0:02:29", "remaining_time": "0:39:05", "throughput": "0.00", "total_tokens": 0}
23
+ {"current_steps": 230, "total_steps": 3665, "loss": 2.3399, "learning_rate": 7.923850217710604e-05, "epoch": 0.31377899045020463, "percentage": 6.28, "elapsed_time": "0:02:36", "remaining_time": "0:38:55", "throughput": "0.00", "total_tokens": 0}
24
+ {"current_steps": 240, "total_steps": 3665, "loss": 2.3305, "learning_rate": 7.917047613720773e-05, "epoch": 0.3274215552523875, "percentage": 6.55, "elapsed_time": "0:02:42", "remaining_time": "0:38:42", "throughput": "0.00", "total_tokens": 0}
25
+ {"current_steps": 250, "total_steps": 3665, "loss": 2.2404, "learning_rate": 7.909957198339669e-05, "epoch": 0.34106412005457026, "percentage": 6.82, "elapsed_time": "0:02:49", "remaining_time": "0:38:38", "throughput": "0.00", "total_tokens": 0}
26
+ {"current_steps": 260, "total_steps": 3665, "loss": 2.1853, "learning_rate": 7.902579492546998e-05, "epoch": 0.35470668485675305, "percentage": 7.09, "elapsed_time": "0:02:55", "remaining_time": "0:38:23", "throughput": "0.00", "total_tokens": 0}
27
+ {"current_steps": 270, "total_steps": 3665, "loss": 2.3177, "learning_rate": 7.894915038431595e-05, "epoch": 0.3683492496589359, "percentage": 7.37, "elapsed_time": "0:03:02", "remaining_time": "0:38:14", "throughput": "0.00", "total_tokens": 0}
28
+ {"current_steps": 280, "total_steps": 3665, "loss": 2.3621, "learning_rate": 7.886964399151586e-05, "epoch": 0.3819918144611187, "percentage": 7.64, "elapsed_time": "0:03:09", "remaining_time": "0:38:07", "throughput": "0.00", "total_tokens": 0}
29
+ {"current_steps": 290, "total_steps": 3665, "loss": 2.3687, "learning_rate": 7.878728158893015e-05, "epoch": 0.3956343792633015, "percentage": 7.91, "elapsed_time": "0:03:15", "remaining_time": "0:37:59", "throughput": "0.00", "total_tokens": 0}
30
+ {"current_steps": 300, "total_steps": 3665, "loss": 2.2021, "learning_rate": 7.870206922826921e-05, "epoch": 0.4092769440654843, "percentage": 8.19, "elapsed_time": "0:03:22", "remaining_time": "0:37:53", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 310, "total_steps": 3665, "loss": 2.0236, "learning_rate": 7.862294656001264e-05, "epoch": 0.4229195088676671, "percentage": 8.46, "elapsed_time": "0:03:29", "remaining_time": "0:37:47", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 320, "total_steps": 3665, "loss": 2.4181, "learning_rate": 7.853233670108533e-05, "epoch": 0.43656207366984995, "percentage": 8.73, "elapsed_time": "0:03:36", "remaining_time": "0:37:41", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 330, "total_steps": 3665, "loss": 2.2359, "learning_rate": 7.843889561656962e-05, "epoch": 0.45020463847203274, "percentage": 9.0, "elapsed_time": "0:03:42", "remaining_time": "0:37:30", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 340, "total_steps": 3665, "loss": 2.2156, "learning_rate": 7.83426301721999e-05, "epoch": 0.4638472032742155, "percentage": 9.28, "elapsed_time": "0:03:49", "remaining_time": "0:37:27", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 350, "total_steps": 3665, "loss": 2.256, "learning_rate": 7.824354744123498e-05, "epoch": 0.47748976807639837, "percentage": 9.55, "elapsed_time": "0:03:56", "remaining_time": "0:37:19", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 360, "total_steps": 3665, "loss": 2.2627, "learning_rate": 7.814165470393832e-05, "epoch": 0.49113233287858116, "percentage": 9.82, "elapsed_time": "0:04:03", "remaining_time": "0:37:15", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 370, "total_steps": 3665, "loss": 2.1303, "learning_rate": 7.803695944704313e-05, "epoch": 0.504774897680764, "percentage": 10.1, "elapsed_time": "0:04:10", "remaining_time": "0:37:07", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 380, "total_steps": 3665, "loss": 2.307, "learning_rate": 7.79294693632023e-05, "epoch": 0.5184174624829468, "percentage": 10.37, "elapsed_time": "0:04:17", "remaining_time": "0:37:03", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 390, "total_steps": 3665, "loss": 2.2182, "learning_rate": 7.781919235042309e-05, "epoch": 0.5320600272851296, "percentage": 10.64, "elapsed_time": "0:04:23", "remaining_time": "0:36:53", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 400, "total_steps": 3665, "loss": 2.2309, "learning_rate": 7.770613651148688e-05, "epoch": 0.5457025920873124, "percentage": 10.91, "elapsed_time": "0:04:30", "remaining_time": "0:36:44", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 410, "total_steps": 3665, "loss": 2.0949, "learning_rate": 7.75903101533538e-05, "epoch": 0.5593451568894953, "percentage": 11.19, "elapsed_time": "0:04:36", "remaining_time": "0:36:38", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 420, "total_steps": 3665, "loss": 2.0541, "learning_rate": 7.747172178655232e-05, "epoch": 0.572987721691678, "percentage": 11.46, "elapsed_time": "0:04:44", "remaining_time": "0:36:35", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 430, "total_steps": 3665, "loss": 2.0429, "learning_rate": 7.735038012455398e-05, "epoch": 0.5866302864938608, "percentage": 11.73, "elapsed_time": "0:04:51", "remaining_time": "0:36:33", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 440, "total_steps": 3665, "loss": 2.1867, "learning_rate": 7.722629408313309e-05, "epoch": 0.6002728512960437, "percentage": 12.01, "elapsed_time": "0:04:58", "remaining_time": "0:36:27", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 450, "total_steps": 3665, "loss": 2.2556, "learning_rate": 7.709947277971168e-05, "epoch": 0.6139154160982264, "percentage": 12.28, "elapsed_time": "0:05:05", "remaining_time": "0:36:20", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 460, "total_steps": 3665, "loss": 2.3728, "learning_rate": 7.69699255326896e-05, "epoch": 0.6275579809004093, "percentage": 12.55, "elapsed_time": "0:05:11", "remaining_time": "0:36:12", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 470, "total_steps": 3665, "loss": 2.4319, "learning_rate": 7.683766186075973e-05, "epoch": 0.6412005457025921, "percentage": 12.82, "elapsed_time": "0:05:18", "remaining_time": "0:36:08", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 480, "total_steps": 3665, "loss": 2.2417, "learning_rate": 7.670269148220874e-05, "epoch": 0.654843110504775, "percentage": 13.1, "elapsed_time": "0:05:25", "remaining_time": "0:36:02", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 490, "total_steps": 3665, "loss": 2.1867, "learning_rate": 7.656502431420286e-05, "epoch": 0.6684856753069577, "percentage": 13.37, "elapsed_time": "0:05:32", "remaining_time": "0:35:56", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 500, "total_steps": 3665, "loss": 2.2426, "learning_rate": 7.64246704720593e-05, "epoch": 0.6821282401091405, "percentage": 13.64, "elapsed_time": "0:05:40", "remaining_time": "0:35:54", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 510, "total_steps": 3665, "loss": 2.1057, "learning_rate": 7.628164026850302e-05, "epoch": 0.6957708049113234, "percentage": 13.92, "elapsed_time": "0:05:47", "remaining_time": "0:35:47", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 520, "total_steps": 3665, "loss": 2.0724, "learning_rate": 7.613594421290888e-05, "epoch": 0.7094133697135061, "percentage": 14.19, "elapsed_time": "0:05:53", "remaining_time": "0:35:38", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 530, "total_steps": 3665, "loss": 2.1513, "learning_rate": 7.59875930105296e-05, "epoch": 0.723055934515689, "percentage": 14.46, "elapsed_time": "0:06:00", "remaining_time": "0:35:31", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 540, "total_steps": 3665, "loss": 1.996, "learning_rate": 7.583659756170904e-05, "epoch": 0.7366984993178718, "percentage": 14.73, "elapsed_time": "0:06:07", "remaining_time": "0:35:27", "throughput": "0.00", "total_tokens": 0}
55
+ {"current_steps": 550, "total_steps": 3665, "loss": 2.2927, "learning_rate": 7.568296896108135e-05, "epoch": 0.7503410641200545, "percentage": 15.01, "elapsed_time": "0:06:13", "remaining_time": "0:35:18", "throughput": "0.00", "total_tokens": 0}
56
+ {"current_steps": 560, "total_steps": 3665, "loss": 2.2445, "learning_rate": 7.552671849675571e-05, "epoch": 0.7639836289222374, "percentage": 15.28, "elapsed_time": "0:06:20", "remaining_time": "0:35:10", "throughput": "0.00", "total_tokens": 0}
57
+ {"current_steps": 570, "total_steps": 3665, "loss": 2.1723, "learning_rate": 7.536785764948705e-05, "epoch": 0.7776261937244202, "percentage": 15.55, "elapsed_time": "0:06:27", "remaining_time": "0:35:05", "throughput": "0.00", "total_tokens": 0}
58
+ {"current_steps": 580, "total_steps": 3665, "loss": 2.1945, "learning_rate": 7.520639809183234e-05, "epoch": 0.791268758526603, "percentage": 15.83, "elapsed_time": "0:06:34", "remaining_time": "0:34:56", "throughput": "0.00", "total_tokens": 0}
59
+ {"current_steps": 590, "total_steps": 3665, "loss": 2.385, "learning_rate": 7.5042351687293e-05, "epoch": 0.8049113233287858, "percentage": 16.1, "elapsed_time": "0:06:40", "remaining_time": "0:34:48", "throughput": "0.00", "total_tokens": 0}
60
+ {"current_steps": 600, "total_steps": 3665, "loss": 1.8776, "learning_rate": 7.487573048944318e-05, "epoch": 0.8185538881309686, "percentage": 16.37, "elapsed_time": "0:06:47", "remaining_time": "0:34:39", "throughput": "0.00", "total_tokens": 0}
61
+ {"current_steps": 610, "total_steps": 3665, "loss": 2.1586, "learning_rate": 7.470654674104415e-05, "epoch": 0.8321964529331515, "percentage": 16.64, "elapsed_time": "0:06:53", "remaining_time": "0:34:31", "throughput": "0.00", "total_tokens": 0}
62
+ {"current_steps": 620, "total_steps": 3665, "loss": 2.1229, "learning_rate": 7.453481287314469e-05, "epoch": 0.8458390177353342, "percentage": 16.92, "elapsed_time": "0:07:00", "remaining_time": "0:34:25", "throughput": "0.00", "total_tokens": 0}
63
+ {"current_steps": 630, "total_steps": 3665, "loss": 2.1562, "learning_rate": 7.436054150416777e-05, "epoch": 0.859481582537517, "percentage": 17.19, "elapsed_time": "0:07:07", "remaining_time": "0:34:18", "throughput": "0.00", "total_tokens": 0}
64
+ {"current_steps": 640, "total_steps": 3665, "loss": 2.2563, "learning_rate": 7.418374543898328e-05, "epoch": 0.8731241473396999, "percentage": 17.46, "elapsed_time": "0:07:14", "remaining_time": "0:34:12", "throughput": "0.00", "total_tokens": 0}
65
+ {"current_steps": 650, "total_steps": 3665, "loss": 2.0738, "learning_rate": 7.400443766796728e-05, "epoch": 0.8867667121418826, "percentage": 17.74, "elapsed_time": "0:07:20", "remaining_time": "0:34:04", "throughput": "0.00", "total_tokens": 0}
66
+ {"current_steps": 660, "total_steps": 3665, "loss": 1.9363, "learning_rate": 7.382263136604744e-05, "epoch": 0.9004092769440655, "percentage": 18.01, "elapsed_time": "0:07:27", "remaining_time": "0:33:57", "throughput": "0.00", "total_tokens": 0}
67
+ {"current_steps": 670, "total_steps": 3665, "loss": 2.3014, "learning_rate": 7.363833989173504e-05, "epoch": 0.9140518417462483, "percentage": 18.28, "elapsed_time": "0:07:34", "remaining_time": "0:33:49", "throughput": "0.00", "total_tokens": 0}
68
+ {"current_steps": 680, "total_steps": 3665, "loss": 2.1957, "learning_rate": 7.34515767861434e-05, "epoch": 0.927694406548431, "percentage": 18.55, "elapsed_time": "0:07:40", "remaining_time": "0:33:40", "throughput": "0.00", "total_tokens": 0}
69
+ {"current_steps": 690, "total_steps": 3665, "loss": 2.4058, "learning_rate": 7.326235577199292e-05, "epoch": 0.9413369713506139, "percentage": 18.83, "elapsed_time": "0:07:47", "remaining_time": "0:33:35", "throughput": "0.00", "total_tokens": 0}
70
+ {"current_steps": 700, "total_steps": 3665, "loss": 2.0714, "learning_rate": 7.307069075260283e-05, "epoch": 0.9549795361527967, "percentage": 19.1, "elapsed_time": "0:07:54", "remaining_time": "0:33:28", "throughput": "0.00", "total_tokens": 0}
71
+ {"current_steps": 710, "total_steps": 3665, "loss": 2.0244, "learning_rate": 7.287659581086957e-05, "epoch": 0.9686221009549796, "percentage": 19.37, "elapsed_time": "0:08:00", "remaining_time": "0:33:21", "throughput": "0.00", "total_tokens": 0}
72
+ {"current_steps": 720, "total_steps": 3665, "loss": 2.1891, "learning_rate": 7.268008520823203e-05, "epoch": 0.9822646657571623, "percentage": 19.65, "elapsed_time": "0:08:07", "remaining_time": "0:33:13", "throughput": "0.00", "total_tokens": 0}
73
+ {"current_steps": 730, "total_steps": 3665, "loss": 2.0008, "learning_rate": 7.248117338362371e-05, "epoch": 0.9959072305593452, "percentage": 19.92, "elapsed_time": "0:08:13", "remaining_time": "0:33:05", "throughput": "0.00", "total_tokens": 0}
74
+ {"current_steps": 740, "total_steps": 3665, "loss": 1.7823, "learning_rate": 7.227987495241174e-05, "epoch": 1.009549795361528, "percentage": 20.19, "elapsed_time": "0:08:20", "remaining_time": "0:33:00", "throughput": "0.00", "total_tokens": 0}
75
+ {"current_steps": 750, "total_steps": 3665, "loss": 1.7272, "learning_rate": 7.207620470532302e-05, "epoch": 1.0231923601637107, "percentage": 20.46, "elapsed_time": "0:08:27", "remaining_time": "0:32:53", "throughput": "0.00", "total_tokens": 0}
76
+ {"current_steps": 760, "total_steps": 3665, "loss": 1.7809, "learning_rate": 7.187017760735748e-05, "epoch": 1.0368349249658937, "percentage": 20.74, "elapsed_time": "0:08:35", "remaining_time": "0:32:49", "throughput": "0.00", "total_tokens": 0}
77
+ {"current_steps": 770, "total_steps": 3665, "loss": 1.5226, "learning_rate": 7.166180879668843e-05, "epoch": 1.0504774897680764, "percentage": 21.01, "elapsed_time": "0:08:41", "remaining_time": "0:32:40", "throughput": "0.00", "total_tokens": 0}
78
+ {"current_steps": 780, "total_steps": 3665, "loss": 1.6743, "learning_rate": 7.145111358355031e-05, "epoch": 1.0641200545702592, "percentage": 21.28, "elapsed_time": "0:08:48", "remaining_time": "0:32:35", "throughput": "0.00", "total_tokens": 0}
79
+ {"current_steps": 790, "total_steps": 3665, "loss": 1.3974, "learning_rate": 7.123810744911376e-05, "epoch": 1.077762619372442, "percentage": 21.56, "elapsed_time": "0:08:55", "remaining_time": "0:32:27", "throughput": "0.00", "total_tokens": 0}
80
+ {"current_steps": 800, "total_steps": 3665, "loss": 1.4882, "learning_rate": 7.102280604434805e-05, "epoch": 1.0914051841746248, "percentage": 21.83, "elapsed_time": "0:09:01", "remaining_time": "0:32:20", "throughput": "0.00", "total_tokens": 0}
81
+ {"current_steps": 810, "total_steps": 3665, "loss": 1.8217, "learning_rate": 7.080522518887116e-05, "epoch": 1.1050477489768076, "percentage": 22.1, "elapsed_time": "0:09:08", "remaining_time": "0:32:14", "throughput": "0.00", "total_tokens": 0}
82
+ {"current_steps": 820, "total_steps": 3665, "loss": 1.5443, "learning_rate": 7.058538086978738e-05, "epoch": 1.1186903137789905, "percentage": 22.37, "elapsed_time": "0:09:15", "remaining_time": "0:32:07", "throughput": "0.00", "total_tokens": 0}
83
+ {"current_steps": 830, "total_steps": 3665, "loss": 1.426, "learning_rate": 7.036328924051266e-05, "epoch": 1.1323328785811733, "percentage": 22.65, "elapsed_time": "0:09:22", "remaining_time": "0:31:59", "throughput": "0.00", "total_tokens": 0}
84
+ {"current_steps": 840, "total_steps": 3665, "loss": 1.6086, "learning_rate": 7.013896661958766e-05, "epoch": 1.145975443383356, "percentage": 22.92, "elapsed_time": "0:09:28", "remaining_time": "0:31:51", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 850, "total_steps": 3665, "loss": 1.64, "learning_rate": 6.991242948947879e-05, "epoch": 1.159618008185539, "percentage": 23.19, "elapsed_time": "0:09:34", "remaining_time": "0:31:43", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 860, "total_steps": 3665, "loss": 1.6026, "learning_rate": 6.968369449536705e-05, "epoch": 1.1732605729877217, "percentage": 23.47, "elapsed_time": "0:09:41", "remaining_time": "0:31:36", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 870, "total_steps": 3665, "loss": 1.5026, "learning_rate": 6.945277844392504e-05, "epoch": 1.1869031377899044, "percentage": 23.74, "elapsed_time": "0:09:47", "remaining_time": "0:31:29", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 880, "total_steps": 3665, "loss": 1.6705, "learning_rate": 6.921969830208212e-05, "epoch": 1.2005457025920874, "percentage": 24.01, "elapsed_time": "0:09:54", "remaining_time": "0:31:22", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 890, "total_steps": 3665, "loss": 1.6982, "learning_rate": 6.898447119577764e-05, "epoch": 1.21418826739427, "percentage": 24.28, "elapsed_time": "0:10:01", "remaining_time": "0:31:15", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 900, "total_steps": 3665, "loss": 1.2631, "learning_rate": 6.874711440870264e-05, "epoch": 1.2278308321964528, "percentage": 24.56, "elapsed_time": "0:10:08", "remaining_time": "0:31:07", "throughput": "0.00", "total_tokens": 0}
91
+ {"current_steps": 910, "total_steps": 3665, "loss": 1.5005, "learning_rate": 6.85076453810299e-05, "epoch": 1.2414733969986358, "percentage": 24.83, "elapsed_time": "0:10:15", "remaining_time": "0:31:02", "throughput": "0.00", "total_tokens": 0}
92
+ {"current_steps": 920, "total_steps": 3665, "loss": 1.6076, "learning_rate": 6.826608170813243e-05, "epoch": 1.2551159618008185, "percentage": 25.1, "elapsed_time": "0:10:21", "remaining_time": "0:30:55", "throughput": "0.00", "total_tokens": 0}
93
+ {"current_steps": 930, "total_steps": 3665, "loss": 1.7727, "learning_rate": 6.802244113929075e-05, "epoch": 1.2687585266030013, "percentage": 25.38, "elapsed_time": "0:10:28", "remaining_time": "0:30:48", "throughput": "0.00", "total_tokens": 0}
94
+ {"current_steps": 940, "total_steps": 3665, "loss": 1.6125, "learning_rate": 6.777674157638862e-05, "epoch": 1.2824010914051842, "percentage": 25.65, "elapsed_time": "0:10:35", "remaining_time": "0:30:42", "throughput": "0.00", "total_tokens": 0}
95
+ {"current_steps": 950, "total_steps": 3665, "loss": 1.4289, "learning_rate": 6.75290010725977e-05, "epoch": 1.296043656207367, "percentage": 25.92, "elapsed_time": "0:10:42", "remaining_time": "0:30:36", "throughput": "0.00", "total_tokens": 0}
96
+ {"current_steps": 960, "total_steps": 3665, "loss": 1.6043, "learning_rate": 6.727923783105111e-05, "epoch": 1.30968622100955, "percentage": 26.19, "elapsed_time": "0:10:48", "remaining_time": "0:30:28", "throughput": "0.00", "total_tokens": 0}
97
+ {"current_steps": 970, "total_steps": 3665, "loss": 1.6637, "learning_rate": 6.702747020350586e-05, "epoch": 1.3233287858117326, "percentage": 26.47, "elapsed_time": "0:10:55", "remaining_time": "0:30:22", "throughput": "0.00", "total_tokens": 0}
98
+ {"current_steps": 980, "total_steps": 3665, "loss": 1.717, "learning_rate": 6.677371668899448e-05, "epoch": 1.3369713506139154, "percentage": 26.74, "elapsed_time": "0:11:02", "remaining_time": "0:30:15", "throughput": "0.00", "total_tokens": 0}
99
+ {"current_steps": 990, "total_steps": 3665, "loss": 1.572, "learning_rate": 6.651799593246569e-05, "epoch": 1.350613915416098, "percentage": 27.01, "elapsed_time": "0:11:09", "remaining_time": "0:30:08", "throughput": "0.00", "total_tokens": 0}
100
+ {"current_steps": 1000, "total_steps": 3665, "loss": 1.6264, "learning_rate": 6.626032672341458e-05, "epoch": 1.364256480218281, "percentage": 27.29, "elapsed_time": "0:11:15", "remaining_time": "0:30:01", "throughput": "0.00", "total_tokens": 0}
101
+ {"current_steps": 1010, "total_steps": 3665, "loss": 1.5057, "learning_rate": 6.600072799450186e-05, "epoch": 1.3778990450204638, "percentage": 27.56, "elapsed_time": "0:11:22", "remaining_time": "0:29:54", "throughput": "0.00", "total_tokens": 0}
102
+ {"current_steps": 1020, "total_steps": 3665, "loss": 1.6963, "learning_rate": 6.573921882016284e-05, "epoch": 1.3915416098226467, "percentage": 27.83, "elapsed_time": "0:11:29", "remaining_time": "0:29:47", "throughput": "0.00", "total_tokens": 0}
103
+ {"current_steps": 1030, "total_steps": 3665, "loss": 1.3956, "learning_rate": 6.547581841520589e-05, "epoch": 1.4051841746248295, "percentage": 28.1, "elapsed_time": "0:11:35", "remaining_time": "0:29:40", "throughput": "0.00", "total_tokens": 0}
104
+ {"current_steps": 1040, "total_steps": 3665, "loss": 1.469, "learning_rate": 6.521054613340064e-05, "epoch": 1.4188267394270122, "percentage": 28.38, "elapsed_time": "0:11:42", "remaining_time": "0:29:32", "throughput": "0.00", "total_tokens": 0}
105
+ {"current_steps": 1050, "total_steps": 3665, "loss": 1.5518, "learning_rate": 6.494342146605581e-05, "epoch": 1.4324693042291952, "percentage": 28.65, "elapsed_time": "0:11:50", "remaining_time": "0:29:29", "throughput": "0.00", "total_tokens": 0}
106
+ {"current_steps": 1060, "total_steps": 3665, "loss": 1.5123, "learning_rate": 6.467446404058722e-05, "epoch": 1.446111869031378, "percentage": 28.92, "elapsed_time": "0:11:57", "remaining_time": "0:29:22", "throughput": "0.00", "total_tokens": 0}
107
+ {"current_steps": 1070, "total_steps": 3665, "loss": 1.5065, "learning_rate": 6.44036936190755e-05, "epoch": 1.4597544338335606, "percentage": 29.2, "elapsed_time": "0:12:03", "remaining_time": "0:29:15", "throughput": "0.00", "total_tokens": 0}
108
+ {"current_steps": 1080, "total_steps": 3665, "loss": 1.5362, "learning_rate": 6.413113009681411e-05, "epoch": 1.4733969986357436, "percentage": 29.47, "elapsed_time": "0:12:10", "remaining_time": "0:29:08", "throughput": "0.00", "total_tokens": 0}
109
+ {"current_steps": 1090, "total_steps": 3665, "loss": 1.7138, "learning_rate": 6.385679350084743e-05, "epoch": 1.4870395634379263, "percentage": 29.74, "elapsed_time": "0:12:16", "remaining_time": "0:29:00", "throughput": "0.00", "total_tokens": 0}
110
+ {"current_steps": 1100, "total_steps": 3665, "loss": 1.6659, "learning_rate": 6.358070398849938e-05, "epoch": 1.500682128240109, "percentage": 30.01, "elapsed_time": "0:12:23", "remaining_time": "0:28:53", "throughput": "0.00", "total_tokens": 0}
111
+ {"current_steps": 1110, "total_steps": 3665, "loss": 1.6374, "learning_rate": 6.330288184589216e-05, "epoch": 1.514324693042292, "percentage": 30.29, "elapsed_time": "0:12:29", "remaining_time": "0:28:46", "throughput": "0.00", "total_tokens": 0}
112
+ {"current_steps": 1120, "total_steps": 3665, "loss": 1.6296, "learning_rate": 6.30233474864558e-05, "epoch": 1.5279672578444747, "percentage": 30.56, "elapsed_time": "0:12:36", "remaining_time": "0:28:39", "throughput": "0.00", "total_tokens": 0}
113
+ {"current_steps": 1130, "total_steps": 3665, "loss": 1.6491, "learning_rate": 6.274212144942824e-05, "epoch": 1.5416098226466577, "percentage": 30.83, "elapsed_time": "0:12:43", "remaining_time": "0:28:33", "throughput": "0.00", "total_tokens": 0}
114
+ {"current_steps": 1140, "total_steps": 3665, "loss": 1.6309, "learning_rate": 6.245922439834612e-05, "epoch": 1.5552523874488404, "percentage": 31.11, "elapsed_time": "0:12:50", "remaining_time": "0:28:26", "throughput": "0.00", "total_tokens": 0}
115
+ {"current_steps": 1150, "total_steps": 3665, "loss": 1.5365, "learning_rate": 6.217467711952658e-05, "epoch": 1.5688949522510232, "percentage": 31.38, "elapsed_time": "0:12:57", "remaining_time": "0:28:20", "throughput": "0.00", "total_tokens": 0}
116
+ {"current_steps": 1160, "total_steps": 3665, "loss": 1.493, "learning_rate": 6.188850052053985e-05, "epoch": 1.5825375170532059, "percentage": 31.65, "elapsed_time": "0:13:04", "remaining_time": "0:28:13", "throughput": "0.00", "total_tokens": 0}
117
+ {"current_steps": 1170, "total_steps": 3665, "loss": 1.6771, "learning_rate": 6.160071562867316e-05, "epoch": 1.5961800818553888, "percentage": 31.92, "elapsed_time": "0:13:11", "remaining_time": "0:28:07", "throughput": "0.00", "total_tokens": 0}
118
+ {"current_steps": 1180, "total_steps": 3665, "loss": 1.5381, "learning_rate": 6.131134358938559e-05, "epoch": 1.6098226466575716, "percentage": 32.2, "elapsed_time": "0:13:18", "remaining_time": "0:28:01", "throughput": "0.00", "total_tokens": 0}
119
+ {"current_steps": 1190, "total_steps": 3665, "loss": 1.4791, "learning_rate": 6.1020405664754455e-05, "epoch": 1.6234652114597545, "percentage": 32.47, "elapsed_time": "0:13:24", "remaining_time": "0:27:54", "throughput": "0.00", "total_tokens": 0}
120
+ {"current_steps": 1200, "total_steps": 3665, "loss": 1.5296, "learning_rate": 6.0727923231913035e-05, "epoch": 1.6371077762619373, "percentage": 32.74, "elapsed_time": "0:13:32", "remaining_time": "0:27:48", "throughput": "0.00", "total_tokens": 0}
121
+ {"current_steps": 1210, "total_steps": 3665, "loss": 1.4165, "learning_rate": 6.04339177814798e-05, "epoch": 1.65075034106412, "percentage": 33.02, "elapsed_time": "0:13:39", "remaining_time": "0:27:41", "throughput": "0.00", "total_tokens": 0}
122
+ {"current_steps": 1220, "total_steps": 3665, "loss": 1.5694, "learning_rate": 6.013841091597947e-05, "epoch": 1.6643929058663027, "percentage": 33.29, "elapsed_time": "0:13:45", "remaining_time": "0:27:35", "throughput": "0.00", "total_tokens": 0}
123
+ {"current_steps": 1230, "total_steps": 3665, "loss": 1.6024, "learning_rate": 5.9841424348255596e-05, "epoch": 1.6780354706684857, "percentage": 33.56, "elapsed_time": "0:13:52", "remaining_time": "0:27:28", "throughput": "0.00", "total_tokens": 0}
124
+ {"current_steps": 1240, "total_steps": 3665, "loss": 1.499, "learning_rate": 5.954297989987526e-05, "epoch": 1.6916780354706686, "percentage": 33.83, "elapsed_time": "0:13:59", "remaining_time": "0:27:21", "throughput": "0.00", "total_tokens": 0}
125
+ {"current_steps": 1250, "total_steps": 3665, "loss": 1.5177, "learning_rate": 5.924309949952565e-05, "epoch": 1.7053206002728514, "percentage": 34.11, "elapsed_time": "0:14:06", "remaining_time": "0:27:14", "throughput": "0.00", "total_tokens": 0}
126
+ {"current_steps": 1260, "total_steps": 3665, "loss": 1.4564, "learning_rate": 5.8941805181402886e-05, "epoch": 1.718963165075034, "percentage": 34.38, "elapsed_time": "0:14:12", "remaining_time": "0:27:07", "throughput": "0.00", "total_tokens": 0}
127
+ {"current_steps": 1270, "total_steps": 3665, "loss": 1.3263, "learning_rate": 5.8639119083592954e-05, "epoch": 1.7326057298772168, "percentage": 34.65, "elapsed_time": "0:14:19", "remaining_time": "0:27:01", "throughput": "0.00", "total_tokens": 0}
128
+ {"current_steps": 1280, "total_steps": 3665, "loss": 1.6518, "learning_rate": 5.833506344644507e-05, "epoch": 1.7462482946793996, "percentage": 34.92, "elapsed_time": "0:14:26", "remaining_time": "0:26:54", "throughput": "0.00", "total_tokens": 0}
129
+ {"current_steps": 1290, "total_steps": 3665, "loss": 1.4169, "learning_rate": 5.802966061093762e-05, "epoch": 1.7598908594815825, "percentage": 35.2, "elapsed_time": "0:14:33", "remaining_time": "0:26:47", "throughput": "0.00", "total_tokens": 0}
130
+ {"current_steps": 1300, "total_steps": 3665, "loss": 1.4631, "learning_rate": 5.7722933017036515e-05, "epoch": 1.7735334242837655, "percentage": 35.47, "elapsed_time": "0:14:39", "remaining_time": "0:26:40", "throughput": "0.00", "total_tokens": 0}
131
+ {"current_steps": 1310, "total_steps": 3665, "loss": 1.5939, "learning_rate": 5.741490320204644e-05, "epoch": 1.7871759890859482, "percentage": 35.74, "elapsed_time": "0:14:47", "remaining_time": "0:26:34", "throughput": "0.00", "total_tokens": 0}
132
+ {"current_steps": 1320, "total_steps": 3665, "loss": 1.4775, "learning_rate": 5.7105593798954895e-05, "epoch": 1.800818553888131, "percentage": 36.02, "elapsed_time": "0:14:53", "remaining_time": "0:26:26", "throughput": "0.00", "total_tokens": 0}
133
+ {"current_steps": 1330, "total_steps": 3665, "loss": 1.6513, "learning_rate": 5.679502753476913e-05, "epoch": 1.8144611186903137, "percentage": 36.29, "elapsed_time": "0:15:00", "remaining_time": "0:26:20", "throughput": "0.00", "total_tokens": 0}
134
+ {"current_steps": 1340, "total_steps": 3665, "loss": 1.6092, "learning_rate": 5.648322722884635e-05, "epoch": 1.8281036834924966, "percentage": 36.56, "elapsed_time": "0:15:07", "remaining_time": "0:26:13", "throughput": "0.00", "total_tokens": 0}
135
+ {"current_steps": 1350, "total_steps": 3665, "loss": 1.5116, "learning_rate": 5.6170215791216926e-05, "epoch": 1.8417462482946794, "percentage": 36.83, "elapsed_time": "0:15:13", "remaining_time": "0:26:06", "throughput": "0.00", "total_tokens": 0}
136
+ {"current_steps": 1360, "total_steps": 3665, "loss": 1.3667, "learning_rate": 5.58560162209011e-05, "epoch": 1.8553888130968623, "percentage": 37.11, "elapsed_time": "0:15:20", "remaining_time": "0:25:59", "throughput": "0.00", "total_tokens": 0}
137
+ {"current_steps": 1370, "total_steps": 3665, "loss": 1.4584, "learning_rate": 5.554065160421907e-05, "epoch": 1.869031377899045, "percentage": 37.38, "elapsed_time": "0:15:26", "remaining_time": "0:25:52", "throughput": "0.00", "total_tokens": 0}
138
+ {"current_steps": 1380, "total_steps": 3665, "loss": 1.7889, "learning_rate": 5.522414511309472e-05, "epoch": 1.8826739427012278, "percentage": 37.65, "elapsed_time": "0:15:34", "remaining_time": "0:25:46", "throughput": "0.00", "total_tokens": 0}
139
+ {"current_steps": 1390, "total_steps": 3665, "loss": 1.5623, "learning_rate": 5.490652000335297e-05, "epoch": 1.8963165075034105, "percentage": 37.93, "elapsed_time": "0:15:40", "remaining_time": "0:25:39", "throughput": "0.00", "total_tokens": 0}
140
+ {"current_steps": 1400, "total_steps": 3665, "loss": 1.5508, "learning_rate": 5.461972027286809e-05, "epoch": 1.9099590723055935, "percentage": 38.2, "elapsed_time": "0:15:47", "remaining_time": "0:25:32", "throughput": "0.00", "total_tokens": 0}
141
+ {"current_steps": 1410, "total_steps": 3665, "loss": 1.4951, "learning_rate": 5.430003415054097e-05, "epoch": 1.9236016371077762, "percentage": 38.47, "elapsed_time": "0:15:53", "remaining_time": "0:25:25", "throughput": "0.00", "total_tokens": 0}
142
+ {"current_steps": 1420, "total_steps": 3665, "loss": 1.601, "learning_rate": 5.397929731013993e-05, "epoch": 1.9372442019099592, "percentage": 38.74, "elapsed_time": "0:16:00", "remaining_time": "0:25:18", "throughput": "0.00", "total_tokens": 0}
143
+ {"current_steps": 1430, "total_steps": 3665, "loss": 1.5427, "learning_rate": 5.365753331832165e-05, "epoch": 1.950886766712142, "percentage": 39.02, "elapsed_time": "0:16:06", "remaining_time": "0:25:10", "throughput": "0.00", "total_tokens": 0}
144
+ {"current_steps": 1440, "total_steps": 3665, "loss": 1.4017, "learning_rate": 5.3334765817214407e-05, "epoch": 1.9645293315143246, "percentage": 39.29, "elapsed_time": "0:16:13", "remaining_time": "0:25:03", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1450, "total_steps": 3665, "loss": 1.6255, "learning_rate": 5.301101852268093e-05, "epoch": 1.9781718963165074, "percentage": 39.56, "elapsed_time": "0:16:19", "remaining_time": "0:24:56", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1460, "total_steps": 3665, "loss": 1.5628, "learning_rate": 5.268631522257586e-05, "epoch": 1.9918144611186903, "percentage": 39.84, "elapsed_time": "0:16:26", "remaining_time": "0:24:50", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1470, "total_steps": 3665, "loss": 1.2903, "learning_rate": 5.23606797749979e-05, "epoch": 2.0054570259208733, "percentage": 40.11, "elapsed_time": "0:16:34", "remaining_time": "0:24:45", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1480, "total_steps": 3665, "loss": 0.8694, "learning_rate": 5.2034136106536784e-05, "epoch": 2.019099590723056, "percentage": 40.38, "elapsed_time": "0:16:41", "remaining_time": "0:24:38", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1490, "total_steps": 3665, "loss": 1.0926, "learning_rate": 5.1706708210515225e-05, "epoch": 2.0327421555252387, "percentage": 40.65, "elapsed_time": "0:16:50", "remaining_time": "0:24:34", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1500, "total_steps": 3665, "loss": 0.9019, "learning_rate": 5.1378420145226e-05, "epoch": 2.0463847203274215, "percentage": 40.93, "elapsed_time": "0:16:56", "remaining_time": "0:24:27", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 1510, "total_steps": 3665, "loss": 0.9077, "learning_rate": 5.104929603216422e-05, "epoch": 2.060027285129604, "percentage": 41.2, "elapsed_time": "0:17:03", "remaining_time": "0:24:21", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1520, "total_steps": 3665, "loss": 0.8833, "learning_rate": 5.0719360054254925e-05, "epoch": 2.0736698499317874, "percentage": 41.47, "elapsed_time": "0:17:10", "remaining_time": "0:24:14", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1530, "total_steps": 3665, "loss": 0.8182, "learning_rate": 5.0388636454076256e-05, "epoch": 2.08731241473397, "percentage": 41.75, "elapsed_time": "0:17:17", "remaining_time": "0:24:07", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1540, "total_steps": 3665, "loss": 0.7097, "learning_rate": 5.0057149532078165e-05, "epoch": 2.100954979536153, "percentage": 42.02, "elapsed_time": "0:17:23", "remaining_time": "0:24:00", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1550, "total_steps": 3665, "loss": 0.8243, "learning_rate": 4.9724923644796904e-05, "epoch": 2.1145975443383356, "percentage": 42.29, "elapsed_time": "0:17:30", "remaining_time": "0:23:53", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1560, "total_steps": 3665, "loss": 0.8468, "learning_rate": 4.939198320306537e-05, "epoch": 2.1282401091405183, "percentage": 42.56, "elapsed_time": "0:17:36", "remaining_time": "0:23:46", "throughput": "0.00", "total_tokens": 0}
157
+ {"current_steps": 1570, "total_steps": 3665, "loss": 0.8348, "learning_rate": 4.9058352670219576e-05, "epoch": 2.141882673942701, "percentage": 42.84, "elapsed_time": "0:17:43", "remaining_time": "0:23:38", "throughput": "0.00", "total_tokens": 0}
158
+ {"current_steps": 1580, "total_steps": 3665, "loss": 0.9292, "learning_rate": 4.872405656030099e-05, "epoch": 2.155525238744884, "percentage": 43.11, "elapsed_time": "0:17:51", "remaining_time": "0:23:33", "throughput": "0.00", "total_tokens": 0}
159
+ {"current_steps": 1590, "total_steps": 3665, "loss": 0.7706, "learning_rate": 4.83891194362555e-05, "epoch": 2.169167803547067, "percentage": 43.38, "elapsed_time": "0:17:57", "remaining_time": "0:23:26", "throughput": "0.00", "total_tokens": 0}
160
+ {"current_steps": 1600, "total_steps": 3665, "loss": 0.8487, "learning_rate": 4.805356590812852e-05, "epoch": 2.1828103683492497, "percentage": 43.66, "elapsed_time": "0:18:03", "remaining_time": "0:23:18", "throughput": "0.00", "total_tokens": 0}
161
+ {"current_steps": 1610, "total_steps": 3665, "loss": 0.8509, "learning_rate": 4.771742063125674e-05, "epoch": 2.1964529331514324, "percentage": 43.93, "elapsed_time": "0:18:10", "remaining_time": "0:23:12", "throughput": "0.00", "total_tokens": 0}
162
+ {"current_steps": 1620, "total_steps": 3665, "loss": 0.8833, "learning_rate": 4.7380708304456554e-05, "epoch": 2.210095497953615, "percentage": 44.2, "elapsed_time": "0:18:17", "remaining_time": "0:23:05", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1630, "total_steps": 3665, "loss": 0.8968, "learning_rate": 4.704345366820927e-05, "epoch": 2.223738062755798, "percentage": 44.47, "elapsed_time": "0:18:24", "remaining_time": "0:22:58", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1640, "total_steps": 3665, "loss": 0.9044, "learning_rate": 4.670568150284323e-05, "epoch": 2.237380627557981, "percentage": 44.75, "elapsed_time": "0:18:31", "remaining_time": "0:22:51", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1650, "total_steps": 3665, "loss": 0.974, "learning_rate": 4.636741662671308e-05, "epoch": 2.251023192360164, "percentage": 45.02, "elapsed_time": "0:18:38", "remaining_time": "0:22:45", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1660, "total_steps": 3665, "loss": 0.8121, "learning_rate": 4.602868389437622e-05, "epoch": 2.2646657571623465, "percentage": 45.29, "elapsed_time": "0:18:44", "remaining_time": "0:22:38", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1670, "total_steps": 3665, "loss": 1.1324, "learning_rate": 4.568950819476648e-05, "epoch": 2.2783083219645293, "percentage": 45.57, "elapsed_time": "0:18:51", "remaining_time": "0:22:31", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1680, "total_steps": 3665, "loss": 0.8856, "learning_rate": 4.5349914449365435e-05, "epoch": 2.291950886766712, "percentage": 45.84, "elapsed_time": "0:18:58", "remaining_time": "0:22:25", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1690, "total_steps": 3665, "loss": 0.8276, "learning_rate": 4.500992761037129e-05, "epoch": 2.305593451568895, "percentage": 46.11, "elapsed_time": "0:19:05", "remaining_time": "0:22:18", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1700, "total_steps": 3665, "loss": 0.7492, "learning_rate": 4.4669572658865405e-05, "epoch": 2.319236016371078, "percentage": 46.38, "elapsed_time": "0:19:12", "remaining_time": "0:22:11", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1710, "total_steps": 3665, "loss": 0.9167, "learning_rate": 4.4328874602976786e-05, "epoch": 2.3328785811732606, "percentage": 46.66, "elapsed_time": "0:19:18", "remaining_time": "0:22:04", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1720, "total_steps": 3665, "loss": 0.9453, "learning_rate": 4.3987858476044617e-05, "epoch": 2.3465211459754434, "percentage": 46.93, "elapsed_time": "0:19:25", "remaining_time": "0:21:58", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1730, "total_steps": 3665, "loss": 0.8714, "learning_rate": 4.364654933477886e-05, "epoch": 2.360163710777626, "percentage": 47.2, "elapsed_time": "0:19:33", "remaining_time": "0:21:52", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1740, "total_steps": 3665, "loss": 0.9251, "learning_rate": 4.330497225741917e-05, "epoch": 2.373806275579809, "percentage": 47.48, "elapsed_time": "0:19:39", "remaining_time": "0:21:45", "throughput": "0.00", "total_tokens": 0}
175
+ {"current_steps": 1750, "total_steps": 3665, "loss": 0.9479, "learning_rate": 4.296315234189223e-05, "epoch": 2.3874488403819916, "percentage": 47.75, "elapsed_time": "0:19:46", "remaining_time": "0:21:38", "throughput": "0.00", "total_tokens": 0}
176
+ {"current_steps": 1760, "total_steps": 3665, "loss": 0.8346, "learning_rate": 4.262111470396766e-05, "epoch": 2.4010914051841747, "percentage": 48.02, "elapsed_time": "0:19:53", "remaining_time": "0:21:31", "throughput": "0.00", "total_tokens": 0}
177
+ {"current_steps": 1770, "total_steps": 3665, "loss": 0.754, "learning_rate": 4.2278884475412585e-05, "epoch": 2.4147339699863575, "percentage": 48.29, "elapsed_time": "0:20:00", "remaining_time": "0:21:24", "throughput": "0.00", "total_tokens": 0}
178
+ {"current_steps": 1780, "total_steps": 3665, "loss": 0.7743, "learning_rate": 4.193648680214505e-05, "epoch": 2.42837653478854, "percentage": 48.57, "elapsed_time": "0:20:06", "remaining_time": "0:21:17", "throughput": "0.00", "total_tokens": 0}
179
+ {"current_steps": 1790, "total_steps": 3665, "loss": 0.9273, "learning_rate": 4.159394684238635e-05, "epoch": 2.442019099590723, "percentage": 48.84, "elapsed_time": "0:20:13", "remaining_time": "0:21:10", "throughput": "0.00", "total_tokens": 0}
180
+ {"current_steps": 1800, "total_steps": 3665, "loss": 1.0037, "learning_rate": 4.1251289764812495e-05, "epoch": 2.4556616643929057, "percentage": 49.11, "elapsed_time": "0:20:20", "remaining_time": "0:21:04", "throughput": "0.00", "total_tokens": 0}
181
+ {"current_steps": 1810, "total_steps": 3665, "loss": 0.7728, "learning_rate": 4.090854074670495e-05, "epoch": 2.469304229195089, "percentage": 49.39, "elapsed_time": "0:20:26", "remaining_time": "0:20:57", "throughput": "0.00", "total_tokens": 0}
182
+ {"current_steps": 1820, "total_steps": 3665, "loss": 0.8098, "learning_rate": 4.056572497210066e-05, "epoch": 2.4829467939972716, "percentage": 49.66, "elapsed_time": "0:20:33", "remaining_time": "0:20:50", "throughput": "0.00", "total_tokens": 0}
183
+ {"current_steps": 1830, "total_steps": 3665, "loss": 0.8404, "learning_rate": 4.0222867629941554e-05, "epoch": 2.4965893587994543, "percentage": 49.93, "elapsed_time": "0:20:40", "remaining_time": "0:20:43", "throughput": "0.00", "total_tokens": 0}
184
+ {"current_steps": 1840, "total_steps": 3665, "loss": 0.7021, "learning_rate": 3.987999391222389e-05, "epoch": 2.510231923601637, "percentage": 50.2, "elapsed_time": "0:20:46", "remaining_time": "0:20:36", "throughput": "0.00", "total_tokens": 0}
185
+ {"current_steps": 1850, "total_steps": 3665, "loss": 0.9656, "learning_rate": 3.953712901214707e-05, "epoch": 2.52387448840382, "percentage": 50.48, "elapsed_time": "0:20:54", "remaining_time": "0:20:30", "throughput": "0.00", "total_tokens": 0}
186
+ {"current_steps": 1860, "total_steps": 3665, "loss": 0.7487, "learning_rate": 3.9194298122262666e-05, "epoch": 2.5375170532060025, "percentage": 50.75, "elapsed_time": "0:21:00", "remaining_time": "0:20:23", "throughput": "0.00", "total_tokens": 0}
187
+ {"current_steps": 1870, "total_steps": 3665, "loss": 0.8693, "learning_rate": 3.8851526432623254e-05, "epoch": 2.5511596180081857, "percentage": 51.02, "elapsed_time": "0:21:06", "remaining_time": "0:20:16", "throughput": "0.00", "total_tokens": 0}
188
+ {"current_steps": 1880, "total_steps": 3665, "loss": 0.8933, "learning_rate": 3.850883912893158e-05, "epoch": 2.5648021828103684, "percentage": 51.3, "elapsed_time": "0:21:13", "remaining_time": "0:20:08", "throughput": "0.00", "total_tokens": 0}
189
+ {"current_steps": 1890, "total_steps": 3665, "loss": 0.7098, "learning_rate": 3.816626139069004e-05, "epoch": 2.578444747612551, "percentage": 51.57, "elapsed_time": "0:21:19", "remaining_time": "0:20:01", "throughput": "0.00", "total_tokens": 0}
190
+ {"current_steps": 1900, "total_steps": 3665, "loss": 0.8742, "learning_rate": 3.782381838935047e-05, "epoch": 2.592087312414734, "percentage": 51.84, "elapsed_time": "0:21:26", "remaining_time": "0:19:55", "throughput": "0.00", "total_tokens": 0}
191
+ {"current_steps": 1910, "total_steps": 3665, "loss": 0.7846, "learning_rate": 3.748153528646472e-05, "epoch": 2.6057298772169166, "percentage": 52.11, "elapsed_time": "0:21:33", "remaining_time": "0:19:48", "throughput": "0.00", "total_tokens": 0}
192
+ {"current_steps": 1920, "total_steps": 3665, "loss": 0.9032, "learning_rate": 3.713943723183587e-05, "epoch": 2.6193724420191, "percentage": 52.39, "elapsed_time": "0:21:39", "remaining_time": "0:19:41", "throughput": "0.00", "total_tokens": 0}
193
+ {"current_steps": 1930, "total_steps": 3665, "loss": 0.8044, "learning_rate": 3.6797549361670257e-05, "epoch": 2.6330150068212825, "percentage": 52.66, "elapsed_time": "0:21:45", "remaining_time": "0:19:34", "throughput": "0.00", "total_tokens": 0}
194
+ {"current_steps": 1940, "total_steps": 3665, "loss": 0.8528, "learning_rate": 3.6455896796730554e-05, "epoch": 2.6466575716234653, "percentage": 52.93, "elapsed_time": "0:21:52", "remaining_time": "0:19:26", "throughput": "0.00", "total_tokens": 0}
195
+ {"current_steps": 1950, "total_steps": 3665, "loss": 0.9294, "learning_rate": 3.611450464049005e-05, "epoch": 2.660300136425648, "percentage": 53.21, "elapsed_time": "0:21:58", "remaining_time": "0:19:19", "throughput": "0.00", "total_tokens": 0}
196
+ {"current_steps": 1960, "total_steps": 3665, "loss": 0.9441, "learning_rate": 3.577339797728805e-05, "epoch": 2.6739427012278307, "percentage": 53.48, "elapsed_time": "0:22:06", "remaining_time": "0:19:13", "throughput": "0.00", "total_tokens": 0}
197
+ {"current_steps": 1970, "total_steps": 3665, "loss": 0.8572, "learning_rate": 3.5432601870486795e-05, "epoch": 2.6875852660300135, "percentage": 53.75, "elapsed_time": "0:22:12", "remaining_time": "0:19:06", "throughput": "0.00", "total_tokens": 0}
198
+ {"current_steps": 1980, "total_steps": 3665, "loss": 0.9912, "learning_rate": 3.509214136062993e-05, "epoch": 2.701227830832196, "percentage": 54.02, "elapsed_time": "0:22:19", "remaining_time": "0:19:00", "throughput": "0.00", "total_tokens": 0}
199
+ {"current_steps": 1990, "total_steps": 3665, "loss": 0.9876, "learning_rate": 3.475204146360254e-05, "epoch": 2.7148703956343794, "percentage": 54.3, "elapsed_time": "0:22:26", "remaining_time": "0:18:53", "throughput": "0.00", "total_tokens": 0}
200
+ {"current_steps": 2000, "total_steps": 3665, "loss": 0.8796, "learning_rate": 3.44123271687931e-05, "epoch": 2.728512960436562, "percentage": 54.57, "elapsed_time": "0:22:33", "remaining_time": "0:18:46", "throughput": "0.00", "total_tokens": 0}
201
+ {"current_steps": 2010, "total_steps": 3665, "loss": 0.8394, "learning_rate": 3.407302343725737e-05, "epoch": 2.742155525238745, "percentage": 54.84, "elapsed_time": "0:22:39", "remaining_time": "0:18:39", "throughput": "0.00", "total_tokens": 0}
202
+ {"current_steps": 2020, "total_steps": 3665, "loss": 0.7603, "learning_rate": 3.3734155199884275e-05, "epoch": 2.7557980900409276, "percentage": 55.12, "elapsed_time": "0:22:46", "remaining_time": "0:18:32", "throughput": "0.00", "total_tokens": 0}
203
+ {"current_steps": 2030, "total_steps": 3665, "loss": 0.8944, "learning_rate": 3.339574735556412e-05, "epoch": 2.7694406548431107, "percentage": 55.39, "elapsed_time": "0:22:53", "remaining_time": "0:18:25", "throughput": "0.00", "total_tokens": 0}
204
+ {"current_steps": 2040, "total_steps": 3665, "loss": 0.9737, "learning_rate": 3.3057824769359104e-05, "epoch": 2.7830832196452935, "percentage": 55.66, "elapsed_time": "0:23:00", "remaining_time": "0:18:19", "throughput": "0.00", "total_tokens": 0}
205
+ {"current_steps": 2050, "total_steps": 3665, "loss": 0.9483, "learning_rate": 3.2720412270676275e-05, "epoch": 2.796725784447476, "percentage": 55.93, "elapsed_time": "0:23:07", "remaining_time": "0:18:12", "throughput": "0.00", "total_tokens": 0}
206
+ {"current_steps": 2060, "total_steps": 3665, "loss": 0.9254, "learning_rate": 3.2383534651443206e-05, "epoch": 2.810368349249659, "percentage": 56.21, "elapsed_time": "0:23:13", "remaining_time": "0:18:06", "throughput": "0.00", "total_tokens": 0}
207
+ {"current_steps": 2070, "total_steps": 3665, "loss": 0.7472, "learning_rate": 3.204721666428631e-05, "epoch": 2.8240109140518417, "percentage": 56.48, "elapsed_time": "0:23:20", "remaining_time": "0:17:59", "throughput": "0.00", "total_tokens": 0}
208
+ {"current_steps": 2080, "total_steps": 3665, "loss": 0.8689, "learning_rate": 3.171148302071215e-05, "epoch": 2.8376534788540244, "percentage": 56.75, "elapsed_time": "0:23:27", "remaining_time": "0:17:52", "throughput": "0.00", "total_tokens": 0}
209
+ {"current_steps": 2090, "total_steps": 3665, "loss": 0.7493, "learning_rate": 3.137635838929169e-05, "epoch": 2.851296043656207, "percentage": 57.03, "elapsed_time": "0:23:33", "remaining_time": "0:17:45", "throughput": "0.00", "total_tokens": 0}
210
+ {"current_steps": 2100, "total_steps": 3665, "loss": 1.0867, "learning_rate": 3.1041867393847764e-05, "epoch": 2.8649386084583903, "percentage": 57.3, "elapsed_time": "0:23:41", "remaining_time": "0:17:39", "throughput": "0.00", "total_tokens": 0}
211
+ {"current_steps": 2110, "total_steps": 3665, "loss": 0.9846, "learning_rate": 3.070803461164575e-05, "epoch": 2.878581173260573, "percentage": 57.57, "elapsed_time": "0:23:48", "remaining_time": "0:17:32", "throughput": "0.00", "total_tokens": 0}
212
+ {"current_steps": 2120, "total_steps": 3665, "loss": 0.7862, "learning_rate": 3.0374884571587776e-05, "epoch": 2.892223738062756, "percentage": 57.84, "elapsed_time": "0:23:55", "remaining_time": "0:17:25", "throughput": "0.00", "total_tokens": 0}
213
+ {"current_steps": 2130, "total_steps": 3665, "loss": 1.0586, "learning_rate": 3.004244175241038e-05, "epoch": 2.9058663028649385, "percentage": 58.12, "elapsed_time": "0:24:01", "remaining_time": "0:17:19", "throughput": "0.00", "total_tokens": 0}
214
+ {"current_steps": 2140, "total_steps": 3665, "loss": 0.8757, "learning_rate": 2.971073058088587e-05, "epoch": 2.9195088676671213, "percentage": 58.39, "elapsed_time": "0:24:08", "remaining_time": "0:17:12", "throughput": "0.00", "total_tokens": 0}
215
+ {"current_steps": 2150, "total_steps": 3665, "loss": 0.9026, "learning_rate": 2.937977543002764e-05, "epoch": 2.9331514324693044, "percentage": 58.66, "elapsed_time": "0:24:15", "remaining_time": "0:17:05", "throughput": "0.00", "total_tokens": 0}
216
+ {"current_steps": 2160, "total_steps": 3665, "loss": 0.8864, "learning_rate": 2.9049600617299188e-05, "epoch": 2.946793997271487, "percentage": 58.94, "elapsed_time": "0:24:22", "remaining_time": "0:16:59", "throughput": "0.00", "total_tokens": 0}
217
+ {"current_steps": 2170, "total_steps": 3665, "loss": 0.8224, "learning_rate": 2.872023040282739e-05, "epoch": 2.96043656207367, "percentage": 59.21, "elapsed_time": "0:24:29", "remaining_time": "0:16:52", "throughput": "0.00", "total_tokens": 0}
218
+ {"current_steps": 2180, "total_steps": 3665, "loss": 0.794, "learning_rate": 2.8391688987620045e-05, "epoch": 2.9740791268758526, "percentage": 59.48, "elapsed_time": "0:24:35", "remaining_time": "0:16:45", "throughput": "0.00", "total_tokens": 0}
219
+ {"current_steps": 2190, "total_steps": 3665, "loss": 0.9792, "learning_rate": 2.8064000511787523e-05, "epoch": 2.9877216916780354, "percentage": 59.75, "elapsed_time": "0:24:42", "remaining_time": "0:16:38", "throughput": "0.00", "total_tokens": 0}
220
+ {"current_steps": 2200, "total_steps": 3665, "loss": 0.7812, "learning_rate": 2.77371890527691e-05, "epoch": 3.001364256480218, "percentage": 60.03, "elapsed_time": "0:24:50", "remaining_time": "0:16:32", "throughput": "0.00", "total_tokens": 0}
221
+ {"current_steps": 2210, "total_steps": 3665, "loss": 0.496, "learning_rate": 2.741127862356389e-05, "epoch": 3.0150068212824013, "percentage": 60.3, "elapsed_time": "0:24:57", "remaining_time": "0:16:25", "throughput": "0.00", "total_tokens": 0}
222
+ {"current_steps": 2220, "total_steps": 3665, "loss": 0.3416, "learning_rate": 2.7086293170966312e-05, "epoch": 3.028649386084584, "percentage": 60.57, "elapsed_time": "0:25:03", "remaining_time": "0:16:18", "throughput": "0.00", "total_tokens": 0}
223
+ {"current_steps": 2230, "total_steps": 3665, "loss": 0.3462, "learning_rate": 2.6762256573806664e-05, "epoch": 3.0422919508867667, "percentage": 60.85, "elapsed_time": "0:25:10", "remaining_time": "0:16:11", "throughput": "0.00", "total_tokens": 0}
224
+ {"current_steps": 2240, "total_steps": 3665, "loss": 0.4756, "learning_rate": 2.6439192641196583e-05, "epoch": 3.0559345156889495, "percentage": 61.12, "elapsed_time": "0:25:17", "remaining_time": "0:16:05", "throughput": "0.00", "total_tokens": 0}
225
+ {"current_steps": 2250, "total_steps": 3665, "loss": 0.357, "learning_rate": 2.611712511077959e-05, "epoch": 3.069577080491132, "percentage": 61.39, "elapsed_time": "0:25:24", "remaining_time": "0:15:58", "throughput": "0.00", "total_tokens": 0}
226
+ {"current_steps": 2260, "total_steps": 3665, "loss": 0.3361, "learning_rate": 2.5796077646986922e-05, "epoch": 3.083219645293315, "percentage": 61.66, "elapsed_time": "0:25:31", "remaining_time": "0:15:51", "throughput": "0.00", "total_tokens": 0}
227
+ {"current_steps": 2270, "total_steps": 3665, "loss": 0.419, "learning_rate": 2.5476073839298857e-05, "epoch": 3.096862210095498, "percentage": 61.94, "elapsed_time": "0:25:37", "remaining_time": "0:15:45", "throughput": "0.00", "total_tokens": 0}
228
+ {"current_steps": 2280, "total_steps": 3665, "loss": 0.4211, "learning_rate": 2.5157137200511253e-05, "epoch": 3.110504774897681, "percentage": 62.21, "elapsed_time": "0:25:45", "remaining_time": "0:15:38", "throughput": "0.00", "total_tokens": 0}
229
+ {"current_steps": 2290, "total_steps": 3665, "loss": 0.5248, "learning_rate": 2.4839291165008073e-05, "epoch": 3.1241473396998636, "percentage": 62.48, "elapsed_time": "0:25:52", "remaining_time": "0:15:32", "throughput": "0.00", "total_tokens": 0}
230
+ {"current_steps": 2300, "total_steps": 3665, "loss": 0.3983, "learning_rate": 2.452255908703945e-05, "epoch": 3.1377899045020463, "percentage": 62.76, "elapsed_time": "0:25:59", "remaining_time": "0:15:25", "throughput": "0.00", "total_tokens": 0}
231
+ {"current_steps": 2310, "total_steps": 3665, "loss": 0.3728, "learning_rate": 2.420696423900567e-05, "epoch": 3.151432469304229, "percentage": 63.03, "elapsed_time": "0:26:07", "remaining_time": "0:15:19", "throughput": "0.00", "total_tokens": 0}
232
+ {"current_steps": 2320, "total_steps": 3665, "loss": 0.4099, "learning_rate": 2.3892529809747195e-05, "epoch": 3.1650750341064118, "percentage": 63.3, "elapsed_time": "0:26:13", "remaining_time": "0:15:12", "throughput": "0.00", "total_tokens": 0}
233
+ {"current_steps": 2330, "total_steps": 3665, "loss": 0.5466, "learning_rate": 2.35792789028409e-05, "epoch": 3.178717598908595, "percentage": 63.57, "elapsed_time": "0:26:21", "remaining_time": "0:15:06", "throughput": "0.00", "total_tokens": 0}
234
+ {"current_steps": 2340, "total_steps": 3665, "loss": 0.3956, "learning_rate": 2.32672345349024e-05, "epoch": 3.1923601637107777, "percentage": 63.85, "elapsed_time": "0:26:28", "remaining_time": "0:14:59", "throughput": "0.00", "total_tokens": 0}
235
+ {"current_steps": 2350, "total_steps": 3665, "loss": 0.2686, "learning_rate": 2.2956419633894922e-05, "epoch": 3.2060027285129604, "percentage": 64.12, "elapsed_time": "0:26:35", "remaining_time": "0:14:52", "throughput": "0.00", "total_tokens": 0}
236
+ {"current_steps": 2360, "total_steps": 3665, "loss": 0.3545, "learning_rate": 2.264685703744466e-05, "epoch": 3.219645293315143, "percentage": 64.39, "elapsed_time": "0:26:42", "remaining_time": "0:14:45", "throughput": "0.00", "total_tokens": 0}
237
+ {"current_steps": 2370, "total_steps": 3665, "loss": 0.4361, "learning_rate": 2.2338569491162688e-05, "epoch": 3.233287858117326, "percentage": 64.67, "elapsed_time": "0:26:48", "remaining_time": "0:14:39", "throughput": "0.00", "total_tokens": 0}
238
+ {"current_steps": 2380, "total_steps": 3665, "loss": 0.4616, "learning_rate": 2.2031579646973662e-05, "epoch": 3.246930422919509, "percentage": 64.94, "elapsed_time": "0:26:55", "remaining_time": "0:14:32", "throughput": "0.00", "total_tokens": 0}
239
+ {"current_steps": 2390, "total_steps": 3665, "loss": 0.4095, "learning_rate": 2.1725910061451582e-05, "epoch": 3.260572987721692, "percentage": 65.21, "elapsed_time": "0:27:03", "remaining_time": "0:14:25", "throughput": "0.00", "total_tokens": 0}
240
+ {"current_steps": 2400, "total_steps": 3665, "loss": 0.4428, "learning_rate": 2.1421583194162237e-05, "epoch": 3.2742155525238745, "percentage": 65.48, "elapsed_time": "0:27:09", "remaining_time": "0:14:19", "throughput": "0.00", "total_tokens": 0}
241
+ {"current_steps": 2410, "total_steps": 3665, "loss": 0.4946, "learning_rate": 2.1118621406013045e-05, "epoch": 3.2878581173260573, "percentage": 65.76, "elapsed_time": "0:27:16", "remaining_time": "0:14:12", "throughput": "0.00", "total_tokens": 0}
242
+ {"current_steps": 2420, "total_steps": 3665, "loss": 0.3676, "learning_rate": 2.0817046957610073e-05, "epoch": 3.30150068212824, "percentage": 66.03, "elapsed_time": "0:27:23", "remaining_time": "0:14:05", "throughput": "0.00", "total_tokens": 0}
243
+ {"current_steps": 2430, "total_steps": 3665, "loss": 0.4319, "learning_rate": 2.0516882007622318e-05, "epoch": 3.3151432469304227, "percentage": 66.3, "elapsed_time": "0:27:30", "remaining_time": "0:13:58", "throughput": "0.00", "total_tokens": 0}
244
+ {"current_steps": 2440, "total_steps": 3665, "loss": 0.3973, "learning_rate": 2.0218148611153614e-05, "epoch": 3.328785811732606, "percentage": 66.58, "elapsed_time": "0:27:36", "remaining_time": "0:13:51", "throughput": "0.00", "total_tokens": 0}
245
+ {"current_steps": 2450, "total_steps": 3665, "loss": 0.3728, "learning_rate": 1.99208687181221e-05, "epoch": 3.3424283765347886, "percentage": 66.85, "elapsed_time": "0:27:43", "remaining_time": "0:13:45", "throughput": "0.00", "total_tokens": 0}
246
+ {"current_steps": 2460, "total_steps": 3665, "loss": 0.4029, "learning_rate": 1.9625064171647403e-05, "epoch": 3.3560709413369714, "percentage": 67.12, "elapsed_time": "0:27:50", "remaining_time": "0:13:38", "throughput": "0.00", "total_tokens": 0}
247
+ {"current_steps": 2470, "total_steps": 3665, "loss": 0.5182, "learning_rate": 1.933075670644566e-05, "epoch": 3.369713506139154, "percentage": 67.39, "elapsed_time": "0:27:57", "remaining_time": "0:13:31", "throughput": "0.00", "total_tokens": 0}
248
+ {"current_steps": 2480, "total_steps": 3665, "loss": 0.3211, "learning_rate": 1.903796794723261e-05, "epoch": 3.383356070941337, "percentage": 67.67, "elapsed_time": "0:28:03", "remaining_time": "0:13:24", "throughput": "0.00", "total_tokens": 0}
249
+ {"current_steps": 2490, "total_steps": 3665, "loss": 0.3218, "learning_rate": 1.8746719407134558e-05, "epoch": 3.39699863574352, "percentage": 67.94, "elapsed_time": "0:28:09", "remaining_time": "0:13:17", "throughput": "0.00", "total_tokens": 0}
250
+ {"current_steps": 2500, "total_steps": 3665, "loss": 0.3561, "learning_rate": 1.8457032486107733e-05, "epoch": 3.4106412005457027, "percentage": 68.21, "elapsed_time": "0:28:16", "remaining_time": "0:13:10", "throughput": "0.00", "total_tokens": 0}
251
+ {"current_steps": 2510, "total_steps": 3665, "loss": 0.4223, "learning_rate": 1.816892846936592e-05, "epoch": 3.4242837653478855, "percentage": 68.49, "elapsed_time": "0:28:23", "remaining_time": "0:13:03", "throughput": "0.00", "total_tokens": 0}
252
+ {"current_steps": 2520, "total_steps": 3665, "loss": 0.2911, "learning_rate": 1.7882428525816434e-05, "epoch": 3.437926330150068, "percentage": 68.76, "elapsed_time": "0:28:29", "remaining_time": "0:12:56", "throughput": "0.00", "total_tokens": 0}
253
+ {"current_steps": 2530, "total_steps": 3665, "loss": 0.3991, "learning_rate": 1.759755370650472e-05, "epoch": 3.451568894952251, "percentage": 69.03, "elapsed_time": "0:28:36", "remaining_time": "0:12:49", "throughput": "0.00", "total_tokens": 0}
254
+ {"current_steps": 2540, "total_steps": 3665, "loss": 0.3823, "learning_rate": 1.7314324943067598e-05, "epoch": 3.4652114597544337, "percentage": 69.3, "elapsed_time": "0:28:42", "remaining_time": "0:12:43", "throughput": "0.00", "total_tokens": 0}
255
+ {"current_steps": 2550, "total_steps": 3665, "loss": 0.3564, "learning_rate": 1.70327630461953e-05, "epoch": 3.4788540245566164, "percentage": 69.58, "elapsed_time": "0:28:49", "remaining_time": "0:12:36", "throughput": "0.00", "total_tokens": 0}
256
+ {"current_steps": 2560, "total_steps": 3665, "loss": 0.4012, "learning_rate": 1.6752888704102304e-05, "epoch": 3.4924965893587996, "percentage": 69.85, "elapsed_time": "0:28:56", "remaining_time": "0:12:29", "throughput": "0.00", "total_tokens": 0}
257
+ {"current_steps": 2570, "total_steps": 3665, "loss": 0.3622, "learning_rate": 1.6474722481007344e-05, "epoch": 3.5061391541609823, "percentage": 70.12, "elapsed_time": "0:29:03", "remaining_time": "0:12:22", "throughput": "0.00", "total_tokens": 0}
258
+ {"current_steps": 2580, "total_steps": 3665, "loss": 0.3502, "learning_rate": 1.619828481562229e-05, "epoch": 3.519781718963165, "percentage": 70.4, "elapsed_time": "0:29:09", "remaining_time": "0:12:15", "throughput": "0.00", "total_tokens": 0}
259
+ {"current_steps": 2590, "total_steps": 3665, "loss": 0.4129, "learning_rate": 1.5923596019650517e-05, "epoch": 3.533424283765348, "percentage": 70.67, "elapsed_time": "0:29:16", "remaining_time": "0:12:09", "throughput": "0.00", "total_tokens": 0}
260
+ {"current_steps": 2600, "total_steps": 3665, "loss": 0.455, "learning_rate": 1.565067627629432e-05, "epoch": 3.547066848567531, "percentage": 70.94, "elapsed_time": "0:29:23", "remaining_time": "0:12:02", "throughput": "0.00", "total_tokens": 0}
261
+ {"current_steps": 2610, "total_steps": 3665, "loss": 0.3905, "learning_rate": 1.5379545638772032e-05, "epoch": 3.5607094133697137, "percentage": 71.21, "elapsed_time": "0:29:30", "remaining_time": "0:11:55", "throughput": "0.00", "total_tokens": 0}
262
+ {"current_steps": 2620, "total_steps": 3665, "loss": 0.4603, "learning_rate": 1.511022402884459e-05, "epoch": 3.5743519781718964, "percentage": 71.49, "elapsed_time": "0:29:37", "remaining_time": "0:11:48", "throughput": "0.00", "total_tokens": 0}
263
+ {"current_steps": 2630, "total_steps": 3665, "loss": 0.3654, "learning_rate": 1.4842731235351653e-05, "epoch": 3.587994542974079, "percentage": 71.76, "elapsed_time": "0:29:43", "remaining_time": "0:11:41", "throughput": "0.00", "total_tokens": 0}
264
+ {"current_steps": 2640, "total_steps": 3665, "loss": 0.4481, "learning_rate": 1.4577086912757659e-05, "epoch": 3.601637107776262, "percentage": 72.03, "elapsed_time": "0:29:49", "remaining_time": "0:11:34", "throughput": "0.00", "total_tokens": 0}
265
+ {"current_steps": 2650, "total_steps": 3665, "loss": 0.4829, "learning_rate": 1.4313310579707697e-05, "epoch": 3.6152796725784446, "percentage": 72.31, "elapsed_time": "0:29:56", "remaining_time": "0:11:28", "throughput": "0.00", "total_tokens": 0}
266
+ {"current_steps": 2660, "total_steps": 3665, "loss": 0.3937, "learning_rate": 1.405142161759327e-05, "epoch": 3.6289222373806274, "percentage": 72.58, "elapsed_time": "0:30:03", "remaining_time": "0:11:21", "throughput": "0.00", "total_tokens": 0}
267
+ {"current_steps": 2670, "total_steps": 3665, "loss": 0.3902, "learning_rate": 1.3791439269128274e-05, "epoch": 3.64256480218281, "percentage": 72.85, "elapsed_time": "0:30:10", "remaining_time": "0:11:14", "throughput": "0.00", "total_tokens": 0}
268
+ {"current_steps": 2680, "total_steps": 3665, "loss": 0.4495, "learning_rate": 1.3533382636935092e-05, "epoch": 3.6562073669849933, "percentage": 73.12, "elapsed_time": "0:30:17", "remaining_time": "0:11:07", "throughput": "0.00", "total_tokens": 0}
269
+ {"current_steps": 2690, "total_steps": 3665, "loss": 0.4707, "learning_rate": 1.3277270682140996e-05, "epoch": 3.669849931787176, "percentage": 73.4, "elapsed_time": "0:30:24", "remaining_time": "0:11:01", "throughput": "0.00", "total_tokens": 0}
270
+ {"current_steps": 2700, "total_steps": 3665, "loss": 0.4189, "learning_rate": 1.3023122222984941e-05, "epoch": 3.6834924965893587, "percentage": 73.67, "elapsed_time": "0:30:31", "remaining_time": "0:10:54", "throughput": "0.00", "total_tokens": 0}
271
+ {"current_steps": 2710, "total_steps": 3665, "loss": 0.3741, "learning_rate": 1.2770955933434906e-05, "epoch": 3.6971350613915415, "percentage": 73.94, "elapsed_time": "0:30:37", "remaining_time": "0:10:47", "throughput": "0.00", "total_tokens": 0}
272
+ {"current_steps": 2720, "total_steps": 3665, "loss": 0.3724, "learning_rate": 1.2520790341815726e-05, "epoch": 3.7107776261937246, "percentage": 74.22, "elapsed_time": "0:30:44", "remaining_time": "0:10:40", "throughput": "0.00", "total_tokens": 0}
273
+ {"current_steps": 2730, "total_steps": 3665, "loss": 0.4002, "learning_rate": 1.2272643829447723e-05, "epoch": 3.7244201909959074, "percentage": 74.49, "elapsed_time": "0:30:50", "remaining_time": "0:10:33", "throughput": "0.00", "total_tokens": 0}
274
+ {"current_steps": 2740, "total_steps": 3665, "loss": 0.4129, "learning_rate": 1.2026534629296168e-05, "epoch": 3.73806275579809, "percentage": 74.76, "elapsed_time": "0:30:57", "remaining_time": "0:10:27", "throughput": "0.00", "total_tokens": 0}
275
+ {"current_steps": 2750, "total_steps": 3665, "loss": 0.3354, "learning_rate": 1.1782480824631478e-05, "epoch": 3.751705320600273, "percentage": 75.03, "elapsed_time": "0:31:04", "remaining_time": "0:10:20", "throughput": "0.00", "total_tokens": 0}
276
+ {"current_steps": 2760, "total_steps": 3665, "loss": 0.3, "learning_rate": 1.154050034770057e-05, "epoch": 3.7653478854024556, "percentage": 75.31, "elapsed_time": "0:31:10", "remaining_time": "0:10:13", "throughput": "0.00", "total_tokens": 0}
277
+ {"current_steps": 2770, "total_steps": 3665, "loss": 0.4613, "learning_rate": 1.1300610978409301e-05, "epoch": 3.7789904502046383, "percentage": 75.58, "elapsed_time": "0:31:16", "remaining_time": "0:10:06", "throughput": "0.00", "total_tokens": 0}
278
+ {"current_steps": 2780, "total_steps": 3665, "loss": 0.3782, "learning_rate": 1.1062830343015998e-05, "epoch": 3.792633015006821, "percentage": 75.85, "elapsed_time": "0:31:23", "remaining_time": "0:09:59", "throughput": "0.00", "total_tokens": 0}
279
+ {"current_steps": 2790, "total_steps": 3665, "loss": 0.3154, "learning_rate": 1.0827175912836352e-05, "epoch": 3.806275579809004, "percentage": 76.13, "elapsed_time": "0:31:30", "remaining_time": "0:09:52", "throughput": "0.00", "total_tokens": 0}
280
+ {"current_steps": 2800, "total_steps": 3665, "loss": 0.3941, "learning_rate": 1.059366500295973e-05, "epoch": 3.819918144611187, "percentage": 76.4, "elapsed_time": "0:31:36", "remaining_time": "0:09:45", "throughput": "0.00", "total_tokens": 0}
281
+ {"current_steps": 2810, "total_steps": 3665, "loss": 0.4402, "learning_rate": 1.0362314770976858e-05, "epoch": 3.8335607094133697, "percentage": 76.67, "elapsed_time": "0:31:43", "remaining_time": "0:09:39", "throughput": "0.00", "total_tokens": 0}
282
+ {"current_steps": 2820, "total_steps": 3665, "loss": 0.3588, "learning_rate": 1.0133142215719176e-05, "epoch": 3.8472032742155524, "percentage": 76.94, "elapsed_time": "0:31:50", "remaining_time": "0:09:32", "throughput": "0.00", "total_tokens": 0}
283
+ {"current_steps": 2830, "total_steps": 3665, "loss": 0.4171, "learning_rate": 9.906164176009825e-06, "epoch": 3.8608458390177356, "percentage": 77.22, "elapsed_time": "0:31:57", "remaining_time": "0:09:25", "throughput": "0.00", "total_tokens": 0}
284
+ {"current_steps": 2840, "total_steps": 3665, "loss": 0.4008, "learning_rate": 9.681397329426363e-06, "epoch": 3.8744884038199183, "percentage": 77.49, "elapsed_time": "0:32:03", "remaining_time": "0:09:18", "throughput": "0.00", "total_tokens": 0}
285
+ {"current_steps": 2850, "total_steps": 3665, "loss": 0.2851, "learning_rate": 9.458858191075358e-06, "epoch": 3.888130968622101, "percentage": 77.76, "elapsed_time": "0:32:10", "remaining_time": "0:09:12", "throughput": "0.00", "total_tokens": 0}
286
+ {"current_steps": 2860, "total_steps": 3665, "loss": 0.486, "learning_rate": 9.238563112378967e-06, "epoch": 3.901773533424284, "percentage": 78.04, "elapsed_time": "0:32:17", "remaining_time": "0:09:05", "throughput": "0.00", "total_tokens": 0}
287
+ {"current_steps": 2870, "total_steps": 3665, "loss": 0.3321, "learning_rate": 9.02052827987339e-06, "epoch": 3.9154160982264665, "percentage": 78.31, "elapsed_time": "0:32:24", "remaining_time": "0:08:58", "throughput": "0.00", "total_tokens": 0}
288
+ {"current_steps": 2880, "total_steps": 3665, "loss": 0.2981, "learning_rate": 8.804769714019619e-06, "epoch": 3.9290586630286493, "percentage": 78.58, "elapsed_time": "0:32:30", "remaining_time": "0:08:51", "throughput": "0.00", "total_tokens": 0}
289
+ {"current_steps": 2890, "total_steps": 3665, "loss": 0.3412, "learning_rate": 8.591303268026293e-06, "epoch": 3.942701227830832, "percentage": 78.85, "elapsed_time": "0:32:37", "remaining_time": "0:08:44", "throughput": "0.00", "total_tokens": 0}
290
+ {"current_steps": 2900, "total_steps": 3665, "loss": 0.3648, "learning_rate": 8.380144626684829e-06, "epoch": 3.956343792633015, "percentage": 79.13, "elapsed_time": "0:32:43", "remaining_time": "0:08:38", "throughput": "0.00", "total_tokens": 0}
291
+ {"current_steps": 2910, "total_steps": 3665, "loss": 0.4028, "learning_rate": 8.171309305216973e-06, "epoch": 3.969986357435198, "percentage": 79.4, "elapsed_time": "0:32:50", "remaining_time": "0:08:31", "throughput": "0.00", "total_tokens": 0}
292
+ {"current_steps": 2920, "total_steps": 3665, "loss": 0.5365, "learning_rate": 7.96481264813481e-06, "epoch": 3.9836289222373806, "percentage": 79.67, "elapsed_time": "0:32:57", "remaining_time": "0:08:24", "throughput": "0.00", "total_tokens": 0}
293
+ {"current_steps": 2930, "total_steps": 3665, "loss": 0.3312, "learning_rate": 7.760669828113276e-06, "epoch": 3.9972714870395634, "percentage": 79.95, "elapsed_time": "0:33:03", "remaining_time": "0:08:17", "throughput": "0.00", "total_tokens": 0}
294
+ {"current_steps": 2940, "total_steps": 3665, "loss": 0.2586, "learning_rate": 7.558895844875325e-06, "epoch": 4.0109140518417465, "percentage": 80.22, "elapsed_time": "0:33:10", "remaining_time": "0:08:10", "throughput": "0.00", "total_tokens": 0}
295
+ {"current_steps": 2950, "total_steps": 3665, "loss": 0.174, "learning_rate": 7.359505524089843e-06, "epoch": 4.024556616643929, "percentage": 80.49, "elapsed_time": "0:33:17", "remaining_time": "0:08:04", "throughput": "0.00", "total_tokens": 0}
296
+ {"current_steps": 2960, "total_steps": 3665, "loss": 0.1319, "learning_rate": 7.162513516282236e-06, "epoch": 4.038199181446112, "percentage": 80.76, "elapsed_time": "0:33:23", "remaining_time": "0:07:57", "throughput": "0.00", "total_tokens": 0}
297
+ {"current_steps": 2970, "total_steps": 3665, "loss": 0.1098, "learning_rate": 6.967934295758003e-06, "epoch": 4.051841746248295, "percentage": 81.04, "elapsed_time": "0:33:30", "remaining_time": "0:07:50", "throughput": "0.00", "total_tokens": 0}
298
+ {"current_steps": 2980, "total_steps": 3665, "loss": 0.1351, "learning_rate": 6.775782159539237e-06, "epoch": 4.0654843110504775, "percentage": 81.31, "elapsed_time": "0:33:36", "remaining_time": "0:07:43", "throughput": "0.00", "total_tokens": 0}
299
+ {"current_steps": 2990, "total_steps": 3665, "loss": 0.2408, "learning_rate": 6.586071226314046e-06, "epoch": 4.07912687585266, "percentage": 81.58, "elapsed_time": "0:33:43", "remaining_time": "0:07:36", "throughput": "0.00", "total_tokens": 0}
300
+ {"current_steps": 3000, "total_steps": 3665, "loss": 0.1759, "learning_rate": 6.3988154353992285e-06, "epoch": 4.092769440654843, "percentage": 81.86, "elapsed_time": "0:33:50", "remaining_time": "0:07:30", "throughput": "0.00", "total_tokens": 0}
301
+ {"current_steps": 3010, "total_steps": 3665, "loss": 0.2398, "learning_rate": 6.214028545716071e-06, "epoch": 4.106412005457026, "percentage": 82.13, "elapsed_time": "0:33:57", "remaining_time": "0:07:23", "throughput": "0.00", "total_tokens": 0}
302
+ {"current_steps": 3020, "total_steps": 3665, "loss": 0.1491, "learning_rate": 6.031724134779331e-06, "epoch": 4.120054570259208, "percentage": 82.4, "elapsed_time": "0:34:04", "remaining_time": "0:07:16", "throughput": "0.00", "total_tokens": 0}
303
+ {"current_steps": 3030, "total_steps": 3665, "loss": 0.1711, "learning_rate": 5.851915597699638e-06, "epoch": 4.133697135061391, "percentage": 82.67, "elapsed_time": "0:34:10", "remaining_time": "0:07:09", "throughput": "0.00", "total_tokens": 0}
304
+ {"current_steps": 3040, "total_steps": 3665, "loss": 0.1815, "learning_rate": 5.674616146199277e-06, "epoch": 4.147339699863575, "percentage": 82.95, "elapsed_time": "0:34:17", "remaining_time": "0:07:03", "throughput": "0.00", "total_tokens": 0}
305
+ {"current_steps": 3050, "total_steps": 3665, "loss": 0.2796, "learning_rate": 5.499838807641413e-06, "epoch": 4.1609822646657575, "percentage": 83.22, "elapsed_time": "0:34:24", "remaining_time": "0:06:56", "throughput": "0.00", "total_tokens": 0}
306
+ {"current_steps": 3060, "total_steps": 3665, "loss": 0.2307, "learning_rate": 5.327596424072896e-06, "epoch": 4.17462482946794, "percentage": 83.49, "elapsed_time": "0:34:31", "remaining_time": "0:06:49", "throughput": "0.00", "total_tokens": 0}
307
+ {"current_steps": 3070, "total_steps": 3665, "loss": 0.1955, "learning_rate": 5.157901651280672e-06, "epoch": 4.188267394270123, "percentage": 83.77, "elapsed_time": "0:34:38", "remaining_time": "0:06:42", "throughput": "0.00", "total_tokens": 0}
308
+ {"current_steps": 3080, "total_steps": 3665, "loss": 0.2332, "learning_rate": 4.990766957861875e-06, "epoch": 4.201909959072306, "percentage": 84.04, "elapsed_time": "0:34:45", "remaining_time": "0:06:36", "throughput": "0.00", "total_tokens": 0}
309
+ {"current_steps": 3090, "total_steps": 3665, "loss": 0.1317, "learning_rate": 4.826204624307665e-06, "epoch": 4.215552523874488, "percentage": 84.31, "elapsed_time": "0:34:52", "remaining_time": "0:06:29", "throughput": "0.00", "total_tokens": 0}
310
+ {"current_steps": 3100, "total_steps": 3665, "loss": 0.1772, "learning_rate": 4.664226742100946e-06, "epoch": 4.229195088676671, "percentage": 84.58, "elapsed_time": "0:34:58", "remaining_time": "0:06:22", "throughput": "0.00", "total_tokens": 0}
311
+ {"current_steps": 3110, "total_steps": 3665, "loss": 0.1893, "learning_rate": 4.504845212827848e-06, "epoch": 4.242837653478854, "percentage": 84.86, "elapsed_time": "0:35:05", "remaining_time": "0:06:15", "throughput": "0.00", "total_tokens": 0}
312
+ {"current_steps": 3120, "total_steps": 3665, "loss": 0.2459, "learning_rate": 4.348071747303322e-06, "epoch": 4.256480218281037, "percentage": 85.13, "elapsed_time": "0:35:14", "remaining_time": "0:06:09", "throughput": "0.00", "total_tokens": 0}
313
+ {"current_steps": 3130, "total_steps": 3665, "loss": 0.1615, "learning_rate": 4.193917864710599e-06, "epoch": 4.270122783083219, "percentage": 85.4, "elapsed_time": "0:35:20", "remaining_time": "0:06:02", "throughput": "0.00", "total_tokens": 0}
314
+ {"current_steps": 3140, "total_steps": 3665, "loss": 0.1488, "learning_rate": 4.042394891754846e-06, "epoch": 4.283765347885402, "percentage": 85.68, "elapsed_time": "0:35:27", "remaining_time": "0:05:55", "throughput": "0.00", "total_tokens": 0}
315
+ {"current_steps": 3150, "total_steps": 3665, "loss": 0.1507, "learning_rate": 3.893513961830886e-06, "epoch": 4.297407912687586, "percentage": 85.95, "elapsed_time": "0:35:33", "remaining_time": "0:05:48", "throughput": "0.00", "total_tokens": 0}
316
+ {"current_steps": 3160, "total_steps": 3665, "loss": 0.1768, "learning_rate": 3.74728601420518e-06, "epoch": 4.311050477489768, "percentage": 86.22, "elapsed_time": "0:35:40", "remaining_time": "0:05:42", "throughput": "0.00", "total_tokens": 0}
317
+ {"current_steps": 3170, "total_steps": 3665, "loss": 0.3008, "learning_rate": 3.6037217932120272e-06, "epoch": 4.324693042291951, "percentage": 86.49, "elapsed_time": "0:35:47", "remaining_time": "0:05:35", "throughput": "0.00", "total_tokens": 0}
318
+ {"current_steps": 3180, "total_steps": 3665, "loss": 0.1839, "learning_rate": 3.4628318474641344e-06, "epoch": 4.338335607094134, "percentage": 86.77, "elapsed_time": "0:35:54", "remaining_time": "0:05:28", "throughput": "0.00", "total_tokens": 0}
319
+ {"current_steps": 3190, "total_steps": 3665, "loss": 0.1681, "learning_rate": 3.3246265290775013e-06, "epoch": 4.351978171896317, "percentage": 87.04, "elapsed_time": "0:36:00", "remaining_time": "0:05:21", "throughput": "0.00", "total_tokens": 0}
320
+ {"current_steps": 3200, "total_steps": 3665, "loss": 0.2091, "learning_rate": 3.1891159929108074e-06, "epoch": 4.365620736698499, "percentage": 87.31, "elapsed_time": "0:36:07", "remaining_time": "0:05:15", "throughput": "0.00", "total_tokens": 0}
321
+ {"current_steps": 3210, "total_steps": 3665, "loss": 0.175, "learning_rate": 3.0563101958192677e-06, "epoch": 4.379263301500682, "percentage": 87.59, "elapsed_time": "0:36:14", "remaining_time": "0:05:08", "throughput": "0.00", "total_tokens": 0}
322
+ {"current_steps": 3220, "total_steps": 3665, "loss": 0.2715, "learning_rate": 2.9262188959230297e-06, "epoch": 4.392905866302865, "percentage": 87.86, "elapsed_time": "0:36:21", "remaining_time": "0:05:01", "throughput": "0.00", "total_tokens": 0}
323
+ {"current_steps": 3230, "total_steps": 3665, "loss": 0.205, "learning_rate": 2.7988516518901643e-06, "epoch": 4.406548431105048, "percentage": 88.13, "elapsed_time": "0:36:28", "remaining_time": "0:04:54", "throughput": "0.00", "total_tokens": 0}
324
+ {"current_steps": 3240, "total_steps": 3665, "loss": 0.1804, "learning_rate": 2.674217822234382e-06, "epoch": 4.42019099590723, "percentage": 88.4, "elapsed_time": "0:36:35", "remaining_time": "0:04:47", "throughput": "0.00", "total_tokens": 0}
325
+ {"current_steps": 3250, "total_steps": 3665, "loss": 0.2301, "learning_rate": 2.5523265646273252e-06, "epoch": 4.433833560709413, "percentage": 88.68, "elapsed_time": "0:36:42", "remaining_time": "0:04:41", "throughput": "0.00", "total_tokens": 0}
326
+ {"current_steps": 3260, "total_steps": 3665, "loss": 0.2665, "learning_rate": 2.433186835225745e-06, "epoch": 4.447476125511596, "percentage": 88.95, "elapsed_time": "0:36:49", "remaining_time": "0:04:34", "throughput": "0.00", "total_tokens": 0}
327
+ {"current_steps": 3270, "total_steps": 3665, "loss": 0.1443, "learning_rate": 2.316807388013431e-06, "epoch": 4.461118690313779, "percentage": 89.22, "elapsed_time": "0:36:55", "remaining_time": "0:04:27", "throughput": "0.00", "total_tokens": 0}
328
+ {"current_steps": 3280, "total_steps": 3665, "loss": 0.2292, "learning_rate": 2.203196774157972e-06, "epoch": 4.474761255115962, "percentage": 89.5, "elapsed_time": "0:37:03", "remaining_time": "0:04:20", "throughput": "0.00", "total_tokens": 0}
329
+ {"current_steps": 3290, "total_steps": 3665, "loss": 0.1765, "learning_rate": 2.0923633413824663e-06, "epoch": 4.488403819918145, "percentage": 89.77, "elapsed_time": "0:37:09", "remaining_time": "0:04:14", "throughput": "0.00", "total_tokens": 0}
330
+ {"current_steps": 3300, "total_steps": 3665, "loss": 0.1966, "learning_rate": 1.98431523335215e-06, "epoch": 4.502046384720328, "percentage": 90.04, "elapsed_time": "0:37:16", "remaining_time": "0:04:07", "throughput": "0.00", "total_tokens": 0}
331
+ {"current_steps": 3310, "total_steps": 3665, "loss": 0.2525, "learning_rate": 1.8790603890760328e-06, "epoch": 4.51568894952251, "percentage": 90.31, "elapsed_time": "0:37:23", "remaining_time": "0:04:00", "throughput": "0.00", "total_tokens": 0}
332
+ {"current_steps": 3320, "total_steps": 3665, "loss": 0.1502, "learning_rate": 1.7766065423235624e-06, "epoch": 4.529331514324693, "percentage": 90.59, "elapsed_time": "0:37:30", "remaining_time": "0:03:53", "throughput": "0.00", "total_tokens": 0}
333
+ {"current_steps": 3330, "total_steps": 3665, "loss": 0.2251, "learning_rate": 1.6769612210563834e-06, "epoch": 4.542974079126876, "percentage": 90.86, "elapsed_time": "0:37:37", "remaining_time": "0:03:47", "throughput": "0.00", "total_tokens": 0}
334
+ {"current_steps": 3340, "total_steps": 3665, "loss": 0.1724, "learning_rate": 1.5801317468751954e-06, "epoch": 4.5566166439290585, "percentage": 91.13, "elapsed_time": "0:37:44", "remaining_time": "0:03:40", "throughput": "0.00", "total_tokens": 0}
335
+ {"current_steps": 3350, "total_steps": 3665, "loss": 0.1416, "learning_rate": 1.4861252344817812e-06, "epoch": 4.570259208731241, "percentage": 91.41, "elapsed_time": "0:37:50", "remaining_time": "0:03:33", "throughput": "0.00", "total_tokens": 0}
336
+ {"current_steps": 3360, "total_steps": 3665, "loss": 0.1507, "learning_rate": 1.3949485911562799e-06, "epoch": 4.583901773533424, "percentage": 91.68, "elapsed_time": "0:37:57", "remaining_time": "0:03:26", "throughput": "0.00", "total_tokens": 0}
337
+ {"current_steps": 3370, "total_steps": 3665, "loss": 0.1486, "learning_rate": 1.3066085162496057e-06, "epoch": 4.597544338335607, "percentage": 91.95, "elapsed_time": "0:38:03", "remaining_time": "0:03:19", "throughput": "0.00", "total_tokens": 0}
338
+ {"current_steps": 3380, "total_steps": 3665, "loss": 0.1823, "learning_rate": 1.2211115006912499e-06, "epoch": 4.61118690313779, "percentage": 92.22, "elapsed_time": "0:38:11", "remaining_time": "0:03:13", "throughput": "0.00", "total_tokens": 0}
339
+ {"current_steps": 3390, "total_steps": 3665, "loss": 0.1146, "learning_rate": 1.1384638265123305e-06, "epoch": 4.624829467939973, "percentage": 92.5, "elapsed_time": "0:38:17", "remaining_time": "0:03:06", "throughput": "0.00", "total_tokens": 0}
340
+ {"current_steps": 3400, "total_steps": 3665, "loss": 0.2206, "learning_rate": 1.0586715663840175e-06, "epoch": 4.638472032742156, "percentage": 92.77, "elapsed_time": "0:38:24", "remaining_time": "0:02:59", "throughput": "0.00", "total_tokens": 0}
341
+ {"current_steps": 3410, "total_steps": 3665, "loss": 0.137, "learning_rate": 9.817405831713135e-07, "epoch": 4.6521145975443385, "percentage": 93.04, "elapsed_time": "0:38:30", "remaining_time": "0:02:52", "throughput": "0.00", "total_tokens": 0}
342
+ {"current_steps": 3420, "total_steps": 3665, "loss": 0.1969, "learning_rate": 9.076765295022949e-07, "epoch": 4.665757162346521, "percentage": 93.32, "elapsed_time": "0:38:37", "remaining_time": "0:02:46", "throughput": "0.00", "total_tokens": 0}
343
+ {"current_steps": 3430, "total_steps": 3665, "loss": 0.1712, "learning_rate": 8.364848473527698e-07, "epoch": 4.679399727148704, "percentage": 93.59, "elapsed_time": "0:38:44", "remaining_time": "0:02:39", "throughput": "0.00", "total_tokens": 0}
344
+ {"current_steps": 3440, "total_steps": 3665, "loss": 0.1606, "learning_rate": 7.748725387928791e-07, "epoch": 4.693042291950887, "percentage": 93.86, "elapsed_time": "0:38:50", "remaining_time": "0:02:32", "throughput": "0.00", "total_tokens": 0}
345
+ {"current_steps": 3450, "total_steps": 3665, "loss": 0.1722, "learning_rate": 7.09152598980536e-07, "epoch": 4.7066848567530695, "percentage": 94.13, "elapsed_time": "0:38:57", "remaining_time": "0:02:25", "throughput": "0.00", "total_tokens": 0}
346
+ {"current_steps": 3460, "total_steps": 3665, "loss": 0.2592, "learning_rate": 6.463196175536768e-07, "epoch": 4.720327421555252, "percentage": 94.41, "elapsed_time": "0:39:04", "remaining_time": "0:02:18", "throughput": "0.00", "total_tokens": 0}
347
+ {"current_steps": 3470, "total_steps": 3665, "loss": 0.2729, "learning_rate": 5.863782112669647e-07, "epoch": 4.733969986357435, "percentage": 94.68, "elapsed_time": "0:39:11", "remaining_time": "0:02:12", "throughput": "0.00", "total_tokens": 0}
348
+ {"current_steps": 3480, "total_steps": 3665, "loss": 0.1888, "learning_rate": 5.293327844118956e-07, "epoch": 4.747612551159618, "percentage": 94.95, "elapsed_time": "0:39:18", "remaining_time": "0:02:05", "throughput": "0.00", "total_tokens": 0}
349
+ {"current_steps": 3490, "total_steps": 3665, "loss": 0.1367, "learning_rate": 4.751875284932217e-07, "epoch": 4.7612551159618, "percentage": 95.23, "elapsed_time": "0:39:24", "remaining_time": "0:01:58", "throughput": "0.00", "total_tokens": 0}
350
+ {"current_steps": 3500, "total_steps": 3665, "loss": 0.2003, "learning_rate": 4.2394642192095327e-07, "epoch": 4.774897680763983, "percentage": 95.5, "elapsed_time": "0:39:31", "remaining_time": "0:01:51", "throughput": "0.00", "total_tokens": 0}
351
+ {"current_steps": 3510, "total_steps": 3665, "loss": 0.1503, "learning_rate": 3.7561322971803706e-07, "epoch": 4.788540245566167, "percentage": 95.77, "elapsed_time": "0:39:38", "remaining_time": "0:01:45", "throughput": "0.00", "total_tokens": 0}
352
+ {"current_steps": 3520, "total_steps": 3665, "loss": 0.1425, "learning_rate": 3.301915032437375e-07, "epoch": 4.8021828103683495, "percentage": 96.04, "elapsed_time": "0:39:44", "remaining_time": "0:01:38", "throughput": "0.00", "total_tokens": 0}
353
+ {"current_steps": 3530, "total_steps": 3665, "loss": 0.1265, "learning_rate": 2.8768457993266775e-07, "epoch": 4.815825375170532, "percentage": 96.32, "elapsed_time": "0:39:51", "remaining_time": "0:01:31", "throughput": "0.00", "total_tokens": 0}
354
+ {"current_steps": 3540, "total_steps": 3665, "loss": 0.2103, "learning_rate": 2.480955830495679e-07, "epoch": 4.829467939972715, "percentage": 96.59, "elapsed_time": "0:39:57", "remaining_time": "0:01:24", "throughput": "0.00", "total_tokens": 0}
355
+ {"current_steps": 3550, "total_steps": 3665, "loss": 0.2395, "learning_rate": 2.1142742145984442e-07, "epoch": 4.843110504774898, "percentage": 96.86, "elapsed_time": "0:40:04", "remaining_time": "0:01:17", "throughput": "0.00", "total_tokens": 0}
356
+ {"current_steps": 3560, "total_steps": 3665, "loss": 0.1317, "learning_rate": 1.7768278941581617e-07, "epoch": 4.85675306957708, "percentage": 97.14, "elapsed_time": "0:40:10", "remaining_time": "0:01:11", "throughput": "0.00", "total_tokens": 0}
357
+ {"current_steps": 3570, "total_steps": 3665, "loss": 0.1802, "learning_rate": 1.4686416635874445e-07, "epoch": 4.870395634379263, "percentage": 97.41, "elapsed_time": "0:40:17", "remaining_time": "0:01:04", "throughput": "0.00", "total_tokens": 0}
358
+ {"current_steps": 3580, "total_steps": 3665, "loss": 0.2484, "learning_rate": 1.1897381673666719e-07, "epoch": 4.884038199181446, "percentage": 97.68, "elapsed_time": "0:40:24", "remaining_time": "0:00:57", "throughput": "0.00", "total_tokens": 0}
359
+ {"current_steps": 3590, "total_steps": 3665, "loss": 0.1346, "learning_rate": 9.40137898380078e-08, "epoch": 4.897680763983629, "percentage": 97.95, "elapsed_time": "0:40:30", "remaining_time": "0:00:50", "throughput": "0.00", "total_tokens": 0}
360
+ {"current_steps": 3600, "total_steps": 3665, "loss": 0.2097, "learning_rate": 7.198591964099777e-08, "epoch": 4.911323328785811, "percentage": 98.23, "elapsed_time": "0:40:37", "remaining_time": "0:00:44", "throughput": "0.00", "total_tokens": 0}
361
+ {"current_steps": 3610, "total_steps": 3665, "loss": 0.1865, "learning_rate": 5.289182467893561e-08, "epoch": 4.924965893587995, "percentage": 98.5, "elapsed_time": "0:40:43", "remaining_time": "0:00:37", "throughput": "0.00", "total_tokens": 0}
362
+ {"current_steps": 3620, "total_steps": 3665, "loss": 0.2137, "learning_rate": 3.6732907921241956e-08, "epoch": 4.938608458390178, "percentage": 98.77, "elapsed_time": "0:40:50", "remaining_time": "0:00:30", "throughput": "0.00", "total_tokens": 0}
363
+ {"current_steps": 3630, "total_steps": 3665, "loss": 0.1699, "learning_rate": 2.351035667038648e-08, "epoch": 4.95225102319236, "percentage": 99.05, "elapsed_time": "0:40:57", "remaining_time": "0:00:23", "throughput": "0.00", "total_tokens": 0}
364
+ {"current_steps": 3640, "total_steps": 3665, "loss": 0.247, "learning_rate": 1.3225142474651009e-08, "epoch": 4.965893587994543, "percentage": 99.32, "elapsed_time": "0:41:04", "remaining_time": "0:00:16", "throughput": "0.00", "total_tokens": 0}
365
+ {"current_steps": 3650, "total_steps": 3665, "loss": 0.1884, "learning_rate": 5.878021056742178e-09, "epoch": 4.979536152796726, "percentage": 99.59, "elapsed_time": "0:41:11", "remaining_time": "0:00:10", "throughput": "0.00", "total_tokens": 0}
366
+ {"current_steps": 3660, "total_steps": 3665, "loss": 0.186, "learning_rate": 1.4695322582491956e-09, "epoch": 4.993178717598909, "percentage": 99.86, "elapsed_time": "0:41:18", "remaining_time": "0:00:03", "throughput": "0.00", "total_tokens": 0}
367
+ {"current_steps": 3665, "total_steps": 3665, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:41:22", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
trainer_state.json ADDED
@@ -0,0 +1,2604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3665,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013642564802182811,
13
+ "grad_norm": 5.18676233291626,
14
+ "learning_rate": 7.999880967748602e-05,
15
+ "loss": 2.6446,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.027285129604365622,
20
+ "grad_norm": 5.224745273590088,
21
+ "learning_rate": 7.999469507332807e-05,
22
+ "loss": 2.5833,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.040927694406548434,
27
+ "grad_norm": 5.343475341796875,
28
+ "learning_rate": 7.998764179444167e-05,
29
+ "loss": 2.3323,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.054570259208731244,
34
+ "grad_norm": 3.960702657699585,
35
+ "learning_rate": 7.997765035907784e-05,
36
+ "loss": 2.2764,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.06821282401091405,
41
+ "grad_norm": 5.80894136428833,
42
+ "learning_rate": 7.99661465457664e-05,
43
+ "loss": 2.3653,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.08185538881309687,
48
+ "grad_norm": 3.9454762935638428,
49
+ "learning_rate": 7.995057481402883e-05,
50
+ "loss": 2.3655,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09549795361527967,
55
+ "grad_norm": 4.658463478088379,
56
+ "learning_rate": 7.993206764937005e-05,
57
+ "loss": 2.2008,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.10914051841746249,
62
+ "grad_norm": 7.062836647033691,
63
+ "learning_rate": 7.99106264116338e-05,
64
+ "loss": 2.4619,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.12278308321964529,
69
+ "grad_norm": 5.339938640594482,
70
+ "learning_rate": 7.988625267624962e-05,
71
+ "loss": 2.4662,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1364256480218281,
76
+ "grad_norm": 6.298858165740967,
77
+ "learning_rate": 7.9858948234117e-05,
78
+ "loss": 2.3909,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.15006821282401092,
83
+ "grad_norm": 5.622934818267822,
84
+ "learning_rate": 7.98287150914739e-05,
85
+ "loss": 2.4736,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.16371077762619374,
90
+ "grad_norm": 3.229802370071411,
91
+ "learning_rate": 7.979555546974922e-05,
92
+ "loss": 2.3796,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.17735334242837653,
97
+ "grad_norm": 5.506136894226074,
98
+ "learning_rate": 7.975947180539966e-05,
99
+ "loss": 2.2357,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.19099590723055934,
104
+ "grad_norm": 5.04240608215332,
105
+ "learning_rate": 7.972046674973065e-05,
106
+ "loss": 2.3435,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.20463847203274216,
111
+ "grad_norm": 6.470039367675781,
112
+ "learning_rate": 7.967854316870156e-05,
113
+ "loss": 2.4652,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.21828103683492497,
118
+ "grad_norm": 3.5564420223236084,
119
+ "learning_rate": 7.963370414271514e-05,
120
+ "loss": 2.2549,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.23192360163710776,
125
+ "grad_norm": 3.998383045196533,
126
+ "learning_rate": 7.958595296639115e-05,
127
+ "loss": 2.3102,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.24556616643929058,
132
+ "grad_norm": 4.615527629852295,
133
+ "learning_rate": 7.953529314832426e-05,
134
+ "loss": 2.2444,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.2592087312414734,
139
+ "grad_norm": 6.488475322723389,
140
+ "learning_rate": 7.948172841082635e-05,
141
+ "loss": 2.2928,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2728512960436562,
146
+ "grad_norm": 4.134075164794922,
147
+ "learning_rate": 7.942526268965287e-05,
148
+ "loss": 2.2113,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.286493860845839,
153
+ "grad_norm": 5.373613357543945,
154
+ "learning_rate": 7.936590013371378e-05,
155
+ "loss": 2.0795,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.30013642564802184,
160
+ "grad_norm": 5.965483665466309,
161
+ "learning_rate": 7.93036451047686e-05,
162
+ "loss": 2.3991,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.31377899045020463,
167
+ "grad_norm": 4.945356369018555,
168
+ "learning_rate": 7.923850217710604e-05,
169
+ "loss": 2.3399,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.3274215552523875,
174
+ "grad_norm": 5.210105895996094,
175
+ "learning_rate": 7.917047613720773e-05,
176
+ "loss": 2.3305,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.34106412005457026,
181
+ "grad_norm": 3.3301730155944824,
182
+ "learning_rate": 7.909957198339669e-05,
183
+ "loss": 2.2404,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.35470668485675305,
188
+ "grad_norm": 3.685528039932251,
189
+ "learning_rate": 7.902579492546998e-05,
190
+ "loss": 2.1853,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3683492496589359,
195
+ "grad_norm": 5.30728006362915,
196
+ "learning_rate": 7.894915038431595e-05,
197
+ "loss": 2.3177,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.3819918144611187,
202
+ "grad_norm": 2.644773006439209,
203
+ "learning_rate": 7.886964399151586e-05,
204
+ "loss": 2.3621,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.3956343792633015,
209
+ "grad_norm": 4.921834468841553,
210
+ "learning_rate": 7.878728158893015e-05,
211
+ "loss": 2.3687,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.4092769440654843,
216
+ "grad_norm": 3.9288289546966553,
217
+ "learning_rate": 7.870206922826921e-05,
218
+ "loss": 2.2021,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.4229195088676671,
223
+ "grad_norm": 6.143318176269531,
224
+ "learning_rate": 7.862294656001264e-05,
225
+ "loss": 2.0236,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.43656207366984995,
230
+ "grad_norm": 4.3533806800842285,
231
+ "learning_rate": 7.853233670108533e-05,
232
+ "loss": 2.4181,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.45020463847203274,
237
+ "grad_norm": 3.7804017066955566,
238
+ "learning_rate": 7.843889561656962e-05,
239
+ "loss": 2.2359,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.4638472032742155,
244
+ "grad_norm": 2.7896721363067627,
245
+ "learning_rate": 7.83426301721999e-05,
246
+ "loss": 2.2156,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.47748976807639837,
251
+ "grad_norm": 4.168877601623535,
252
+ "learning_rate": 7.824354744123498e-05,
253
+ "loss": 2.256,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.49113233287858116,
258
+ "grad_norm": 7.003695011138916,
259
+ "learning_rate": 7.814165470393832e-05,
260
+ "loss": 2.2627,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.504774897680764,
265
+ "grad_norm": 9.064947128295898,
266
+ "learning_rate": 7.803695944704313e-05,
267
+ "loss": 2.1303,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5184174624829468,
272
+ "grad_norm": 6.936222553253174,
273
+ "learning_rate": 7.79294693632023e-05,
274
+ "loss": 2.307,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5320600272851296,
279
+ "grad_norm": 4.441155433654785,
280
+ "learning_rate": 7.781919235042309e-05,
281
+ "loss": 2.2182,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5457025920873124,
286
+ "grad_norm": 7.236617088317871,
287
+ "learning_rate": 7.770613651148688e-05,
288
+ "loss": 2.2309,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5593451568894953,
293
+ "grad_norm": 4.184124946594238,
294
+ "learning_rate": 7.75903101533538e-05,
295
+ "loss": 2.0949,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.572987721691678,
300
+ "grad_norm": 2.9721992015838623,
301
+ "learning_rate": 7.747172178655232e-05,
302
+ "loss": 2.0541,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5866302864938608,
307
+ "grad_norm": 2.36011004447937,
308
+ "learning_rate": 7.735038012455398e-05,
309
+ "loss": 2.0429,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.6002728512960437,
314
+ "grad_norm": 5.892980575561523,
315
+ "learning_rate": 7.722629408313309e-05,
316
+ "loss": 2.1867,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.6139154160982264,
321
+ "grad_norm": 5.935312747955322,
322
+ "learning_rate": 7.709947277971168e-05,
323
+ "loss": 2.2556,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6275579809004093,
328
+ "grad_norm": 5.781426906585693,
329
+ "learning_rate": 7.69699255326896e-05,
330
+ "loss": 2.3728,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6412005457025921,
335
+ "grad_norm": 6.5159149169921875,
336
+ "learning_rate": 7.683766186075973e-05,
337
+ "loss": 2.4319,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.654843110504775,
342
+ "grad_norm": 3.946726083755493,
343
+ "learning_rate": 7.670269148220874e-05,
344
+ "loss": 2.2417,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6684856753069577,
349
+ "grad_norm": 5.711483001708984,
350
+ "learning_rate": 7.656502431420286e-05,
351
+ "loss": 2.1867,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6821282401091405,
356
+ "grad_norm": 1.9001113176345825,
357
+ "learning_rate": 7.64246704720593e-05,
358
+ "loss": 2.2426,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6957708049113234,
363
+ "grad_norm": 6.293882846832275,
364
+ "learning_rate": 7.628164026850302e-05,
365
+ "loss": 2.1057,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.7094133697135061,
370
+ "grad_norm": 2.980394124984741,
371
+ "learning_rate": 7.613594421290888e-05,
372
+ "loss": 2.0724,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.723055934515689,
377
+ "grad_norm": 7.354122161865234,
378
+ "learning_rate": 7.59875930105296e-05,
379
+ "loss": 2.1513,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.7366984993178718,
384
+ "grad_norm": 3.451127290725708,
385
+ "learning_rate": 7.583659756170904e-05,
386
+ "loss": 1.996,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7503410641200545,
391
+ "grad_norm": 4.8892951011657715,
392
+ "learning_rate": 7.568296896108135e-05,
393
+ "loss": 2.2927,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7639836289222374,
398
+ "grad_norm": 5.78281831741333,
399
+ "learning_rate": 7.552671849675571e-05,
400
+ "loss": 2.2445,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7776261937244202,
405
+ "grad_norm": 3.0643134117126465,
406
+ "learning_rate": 7.536785764948705e-05,
407
+ "loss": 2.1723,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.791268758526603,
412
+ "grad_norm": 5.0908732414245605,
413
+ "learning_rate": 7.520639809183234e-05,
414
+ "loss": 2.1945,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.8049113233287858,
419
+ "grad_norm": 4.066890716552734,
420
+ "learning_rate": 7.5042351687293e-05,
421
+ "loss": 2.385,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.8185538881309686,
426
+ "grad_norm": 6.034420967102051,
427
+ "learning_rate": 7.487573048944318e-05,
428
+ "loss": 1.8776,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8321964529331515,
433
+ "grad_norm": 2.5823731422424316,
434
+ "learning_rate": 7.470654674104415e-05,
435
+ "loss": 2.1586,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8458390177353342,
440
+ "grad_norm": 4.781266212463379,
441
+ "learning_rate": 7.453481287314469e-05,
442
+ "loss": 2.1229,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.859481582537517,
447
+ "grad_norm": 4.008852481842041,
448
+ "learning_rate": 7.436054150416777e-05,
449
+ "loss": 2.1562,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8731241473396999,
454
+ "grad_norm": 7.812346458435059,
455
+ "learning_rate": 7.418374543898328e-05,
456
+ "loss": 2.2563,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.8867667121418826,
461
+ "grad_norm": 5.588919639587402,
462
+ "learning_rate": 7.400443766796728e-05,
463
+ "loss": 2.0738,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.9004092769440655,
468
+ "grad_norm": 3.1923656463623047,
469
+ "learning_rate": 7.382263136604744e-05,
470
+ "loss": 1.9363,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.9140518417462483,
475
+ "grad_norm": 6.451751708984375,
476
+ "learning_rate": 7.363833989173504e-05,
477
+ "loss": 2.3014,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.927694406548431,
482
+ "grad_norm": 4.7484517097473145,
483
+ "learning_rate": 7.34515767861434e-05,
484
+ "loss": 2.1957,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9413369713506139,
489
+ "grad_norm": 4.468317031860352,
490
+ "learning_rate": 7.326235577199292e-05,
491
+ "loss": 2.4058,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9549795361527967,
496
+ "grad_norm": 4.4900078773498535,
497
+ "learning_rate": 7.307069075260283e-05,
498
+ "loss": 2.0714,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9686221009549796,
503
+ "grad_norm": 4.51573371887207,
504
+ "learning_rate": 7.287659581086957e-05,
505
+ "loss": 2.0244,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9822646657571623,
510
+ "grad_norm": 2.892160654067993,
511
+ "learning_rate": 7.268008520823203e-05,
512
+ "loss": 2.1891,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9959072305593452,
517
+ "grad_norm": 5.765126705169678,
518
+ "learning_rate": 7.248117338362371e-05,
519
+ "loss": 2.0008,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 1.009549795361528,
524
+ "grad_norm": 4.076498031616211,
525
+ "learning_rate": 7.227987495241174e-05,
526
+ "loss": 1.7823,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 1.0231923601637107,
531
+ "grad_norm": 5.407172203063965,
532
+ "learning_rate": 7.207620470532302e-05,
533
+ "loss": 1.7272,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.0368349249658937,
538
+ "grad_norm": 2.3942642211914062,
539
+ "learning_rate": 7.187017760735748e-05,
540
+ "loss": 1.7809,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 1.0504774897680764,
545
+ "grad_norm": 6.462409019470215,
546
+ "learning_rate": 7.166180879668843e-05,
547
+ "loss": 1.5226,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 1.0641200545702592,
552
+ "grad_norm": 10.609193801879883,
553
+ "learning_rate": 7.145111358355031e-05,
554
+ "loss": 1.6743,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 1.077762619372442,
559
+ "grad_norm": 5.816223621368408,
560
+ "learning_rate": 7.123810744911376e-05,
561
+ "loss": 1.3974,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 1.0914051841746248,
566
+ "grad_norm": 8.911855697631836,
567
+ "learning_rate": 7.102280604434805e-05,
568
+ "loss": 1.4882,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.1050477489768076,
573
+ "grad_norm": 8.37972640991211,
574
+ "learning_rate": 7.080522518887116e-05,
575
+ "loss": 1.8217,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.1186903137789905,
580
+ "grad_norm": 5.856902599334717,
581
+ "learning_rate": 7.058538086978738e-05,
582
+ "loss": 1.5443,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.1323328785811733,
587
+ "grad_norm": 8.661952018737793,
588
+ "learning_rate": 7.036328924051266e-05,
589
+ "loss": 1.426,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.145975443383356,
594
+ "grad_norm": 7.178607940673828,
595
+ "learning_rate": 7.013896661958766e-05,
596
+ "loss": 1.6086,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.159618008185539,
601
+ "grad_norm": 6.399686813354492,
602
+ "learning_rate": 6.991242948947879e-05,
603
+ "loss": 1.64,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.1732605729877217,
608
+ "grad_norm": 5.770147800445557,
609
+ "learning_rate": 6.968369449536705e-05,
610
+ "loss": 1.6026,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.1869031377899044,
615
+ "grad_norm": 7.86605167388916,
616
+ "learning_rate": 6.945277844392504e-05,
617
+ "loss": 1.5026,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 1.2005457025920874,
622
+ "grad_norm": 3.953367233276367,
623
+ "learning_rate": 6.921969830208212e-05,
624
+ "loss": 1.6705,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 1.21418826739427,
629
+ "grad_norm": 10.93819808959961,
630
+ "learning_rate": 6.898447119577764e-05,
631
+ "loss": 1.6982,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 1.2278308321964528,
636
+ "grad_norm": 4.714999675750732,
637
+ "learning_rate": 6.874711440870264e-05,
638
+ "loss": 1.2631,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 1.2414733969986358,
643
+ "grad_norm": 4.0259480476379395,
644
+ "learning_rate": 6.85076453810299e-05,
645
+ "loss": 1.5005,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 1.2551159618008185,
650
+ "grad_norm": 7.3578643798828125,
651
+ "learning_rate": 6.826608170813243e-05,
652
+ "loss": 1.6076,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 1.2687585266030013,
657
+ "grad_norm": 5.368468284606934,
658
+ "learning_rate": 6.802244113929075e-05,
659
+ "loss": 1.7727,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 1.2824010914051842,
664
+ "grad_norm": 7.0559916496276855,
665
+ "learning_rate": 6.777674157638862e-05,
666
+ "loss": 1.6125,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 1.296043656207367,
671
+ "grad_norm": 6.349229335784912,
672
+ "learning_rate": 6.75290010725977e-05,
673
+ "loss": 1.4289,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 1.30968622100955,
678
+ "grad_norm": 4.133677959442139,
679
+ "learning_rate": 6.727923783105111e-05,
680
+ "loss": 1.6043,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 1.3233287858117326,
685
+ "grad_norm": 5.688299655914307,
686
+ "learning_rate": 6.702747020350586e-05,
687
+ "loss": 1.6637,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 1.3369713506139154,
692
+ "grad_norm": 8.215998649597168,
693
+ "learning_rate": 6.677371668899448e-05,
694
+ "loss": 1.717,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 1.350613915416098,
699
+ "grad_norm": 6.267200946807861,
700
+ "learning_rate": 6.651799593246569e-05,
701
+ "loss": 1.572,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 1.364256480218281,
706
+ "grad_norm": 3.5424532890319824,
707
+ "learning_rate": 6.626032672341458e-05,
708
+ "loss": 1.6264,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 1.3778990450204638,
713
+ "grad_norm": 6.2543206214904785,
714
+ "learning_rate": 6.600072799450186e-05,
715
+ "loss": 1.5057,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 1.3915416098226467,
720
+ "grad_norm": 5.060370445251465,
721
+ "learning_rate": 6.573921882016284e-05,
722
+ "loss": 1.6963,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 1.4051841746248295,
727
+ "grad_norm": 7.101504325866699,
728
+ "learning_rate": 6.547581841520589e-05,
729
+ "loss": 1.3956,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 1.4188267394270122,
734
+ "grad_norm": 7.740041732788086,
735
+ "learning_rate": 6.521054613340064e-05,
736
+ "loss": 1.469,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 1.4324693042291952,
741
+ "grad_norm": 7.723188877105713,
742
+ "learning_rate": 6.494342146605581e-05,
743
+ "loss": 1.5518,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 1.446111869031378,
748
+ "grad_norm": 5.523282527923584,
749
+ "learning_rate": 6.467446404058722e-05,
750
+ "loss": 1.5123,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 1.4597544338335606,
755
+ "grad_norm": 10.065855026245117,
756
+ "learning_rate": 6.44036936190755e-05,
757
+ "loss": 1.5065,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 1.4733969986357436,
762
+ "grad_norm": 8.757994651794434,
763
+ "learning_rate": 6.413113009681411e-05,
764
+ "loss": 1.5362,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 1.4870395634379263,
769
+ "grad_norm": 10.307364463806152,
770
+ "learning_rate": 6.385679350084743e-05,
771
+ "loss": 1.7138,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 1.500682128240109,
776
+ "grad_norm": 7.119322299957275,
777
+ "learning_rate": 6.358070398849938e-05,
778
+ "loss": 1.6659,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 1.514324693042292,
783
+ "grad_norm": 12.579729080200195,
784
+ "learning_rate": 6.330288184589216e-05,
785
+ "loss": 1.6374,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 1.5279672578444747,
790
+ "grad_norm": 8.232572555541992,
791
+ "learning_rate": 6.30233474864558e-05,
792
+ "loss": 1.6296,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 1.5416098226466577,
797
+ "grad_norm": 10.136465072631836,
798
+ "learning_rate": 6.274212144942824e-05,
799
+ "loss": 1.6491,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 1.5552523874488404,
804
+ "grad_norm": 5.127601623535156,
805
+ "learning_rate": 6.245922439834612e-05,
806
+ "loss": 1.6309,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 1.5688949522510232,
811
+ "grad_norm": 6.231171607971191,
812
+ "learning_rate": 6.217467711952658e-05,
813
+ "loss": 1.5365,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 1.5825375170532059,
818
+ "grad_norm": 7.796588897705078,
819
+ "learning_rate": 6.188850052053985e-05,
820
+ "loss": 1.493,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 1.5961800818553888,
825
+ "grad_norm": 8.250170707702637,
826
+ "learning_rate": 6.160071562867316e-05,
827
+ "loss": 1.6771,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 1.6098226466575716,
832
+ "grad_norm": 4.563484191894531,
833
+ "learning_rate": 6.131134358938559e-05,
834
+ "loss": 1.5381,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 1.6234652114597545,
839
+ "grad_norm": 7.776663303375244,
840
+ "learning_rate": 6.1020405664754455e-05,
841
+ "loss": 1.4791,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 1.6371077762619373,
846
+ "grad_norm": 6.122801780700684,
847
+ "learning_rate": 6.0727923231913035e-05,
848
+ "loss": 1.5296,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 1.65075034106412,
853
+ "grad_norm": 5.5693278312683105,
854
+ "learning_rate": 6.04339177814798e-05,
855
+ "loss": 1.4165,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 1.6643929058663027,
860
+ "grad_norm": 8.107104301452637,
861
+ "learning_rate": 6.013841091597947e-05,
862
+ "loss": 1.5694,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 1.6780354706684857,
867
+ "grad_norm": 12.389050483703613,
868
+ "learning_rate": 5.9841424348255596e-05,
869
+ "loss": 1.6024,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 1.6916780354706686,
874
+ "grad_norm": 6.175624370574951,
875
+ "learning_rate": 5.954297989987526e-05,
876
+ "loss": 1.499,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 1.7053206002728514,
881
+ "grad_norm": 4.447775840759277,
882
+ "learning_rate": 5.924309949952565e-05,
883
+ "loss": 1.5177,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 1.718963165075034,
888
+ "grad_norm": 6.788479804992676,
889
+ "learning_rate": 5.8941805181402886e-05,
890
+ "loss": 1.4564,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 1.7326057298772168,
895
+ "grad_norm": 6.172934532165527,
896
+ "learning_rate": 5.8639119083592954e-05,
897
+ "loss": 1.3263,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 1.7462482946793996,
902
+ "grad_norm": 7.947272777557373,
903
+ "learning_rate": 5.833506344644507e-05,
904
+ "loss": 1.6518,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 1.7598908594815825,
909
+ "grad_norm": 5.520730018615723,
910
+ "learning_rate": 5.802966061093762e-05,
911
+ "loss": 1.4169,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 1.7735334242837655,
916
+ "grad_norm": 6.108306407928467,
917
+ "learning_rate": 5.7722933017036515e-05,
918
+ "loss": 1.4631,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 1.7871759890859482,
923
+ "grad_norm": 3.4584460258483887,
924
+ "learning_rate": 5.741490320204644e-05,
925
+ "loss": 1.5939,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 1.800818553888131,
930
+ "grad_norm": 7.870245456695557,
931
+ "learning_rate": 5.7105593798954895e-05,
932
+ "loss": 1.4775,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 1.8144611186903137,
937
+ "grad_norm": 6.256468772888184,
938
+ "learning_rate": 5.679502753476913e-05,
939
+ "loss": 1.6513,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 1.8281036834924966,
944
+ "grad_norm": 8.314029693603516,
945
+ "learning_rate": 5.648322722884635e-05,
946
+ "loss": 1.6092,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 1.8417462482946794,
951
+ "grad_norm": 7.979041576385498,
952
+ "learning_rate": 5.6170215791216926e-05,
953
+ "loss": 1.5116,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 1.8553888130968623,
958
+ "grad_norm": 7.900625228881836,
959
+ "learning_rate": 5.58560162209011e-05,
960
+ "loss": 1.3667,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 1.869031377899045,
965
+ "grad_norm": 7.304281234741211,
966
+ "learning_rate": 5.554065160421907e-05,
967
+ "loss": 1.4584,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 1.8826739427012278,
972
+ "grad_norm": 5.6456618309021,
973
+ "learning_rate": 5.522414511309472e-05,
974
+ "loss": 1.7889,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 1.8963165075034105,
979
+ "grad_norm": 5.90806770324707,
980
+ "learning_rate": 5.490652000335297e-05,
981
+ "loss": 1.5623,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 1.9099590723055935,
986
+ "grad_norm": 6.941085338592529,
987
+ "learning_rate": 5.461972027286809e-05,
988
+ "loss": 1.5508,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 1.9236016371077762,
993
+ "grad_norm": 7.18194580078125,
994
+ "learning_rate": 5.430003415054097e-05,
995
+ "loss": 1.4951,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 1.9372442019099592,
1000
+ "grad_norm": 9.118647575378418,
1001
+ "learning_rate": 5.397929731013993e-05,
1002
+ "loss": 1.601,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 1.950886766712142,
1007
+ "grad_norm": 7.178833961486816,
1008
+ "learning_rate": 5.365753331832165e-05,
1009
+ "loss": 1.5427,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 1.9645293315143246,
1014
+ "grad_norm": 5.578968524932861,
1015
+ "learning_rate": 5.3334765817214407e-05,
1016
+ "loss": 1.4017,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 1.9781718963165074,
1021
+ "grad_norm": 10.137267112731934,
1022
+ "learning_rate": 5.301101852268093e-05,
1023
+ "loss": 1.6255,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 1.9918144611186903,
1028
+ "grad_norm": 7.634779930114746,
1029
+ "learning_rate": 5.268631522257586e-05,
1030
+ "loss": 1.5628,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 2.0054570259208733,
1035
+ "grad_norm": 4.639617919921875,
1036
+ "learning_rate": 5.23606797749979e-05,
1037
+ "loss": 1.2903,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 2.019099590723056,
1042
+ "grad_norm": 9.048364639282227,
1043
+ "learning_rate": 5.2034136106536784e-05,
1044
+ "loss": 0.8694,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 2.0327421555252387,
1049
+ "grad_norm": 12.236319541931152,
1050
+ "learning_rate": 5.1706708210515225e-05,
1051
+ "loss": 1.0926,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 2.0463847203274215,
1056
+ "grad_norm": 8.067400932312012,
1057
+ "learning_rate": 5.1378420145226e-05,
1058
+ "loss": 0.9019,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 2.060027285129604,
1063
+ "grad_norm": 5.9596028327941895,
1064
+ "learning_rate": 5.104929603216422e-05,
1065
+ "loss": 0.9077,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 2.0736698499317874,
1070
+ "grad_norm": 16.68425941467285,
1071
+ "learning_rate": 5.0719360054254925e-05,
1072
+ "loss": 0.8833,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 2.08731241473397,
1077
+ "grad_norm": 10.05809497833252,
1078
+ "learning_rate": 5.0388636454076256e-05,
1079
+ "loss": 0.8182,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 2.100954979536153,
1084
+ "grad_norm": 7.299218654632568,
1085
+ "learning_rate": 5.0057149532078165e-05,
1086
+ "loss": 0.7097,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 2.1145975443383356,
1091
+ "grad_norm": 7.193046569824219,
1092
+ "learning_rate": 4.9724923644796904e-05,
1093
+ "loss": 0.8243,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 2.1282401091405183,
1098
+ "grad_norm": 6.852187633514404,
1099
+ "learning_rate": 4.939198320306537e-05,
1100
+ "loss": 0.8468,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 2.141882673942701,
1105
+ "grad_norm": 8.87316608428955,
1106
+ "learning_rate": 4.9058352670219576e-05,
1107
+ "loss": 0.8348,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 2.155525238744884,
1112
+ "grad_norm": 7.688050270080566,
1113
+ "learning_rate": 4.872405656030099e-05,
1114
+ "loss": 0.9292,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 2.169167803547067,
1119
+ "grad_norm": 9.83198356628418,
1120
+ "learning_rate": 4.83891194362555e-05,
1121
+ "loss": 0.7706,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 2.1828103683492497,
1126
+ "grad_norm": 10.323474884033203,
1127
+ "learning_rate": 4.805356590812852e-05,
1128
+ "loss": 0.8487,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 2.1964529331514324,
1133
+ "grad_norm": 8.7017183303833,
1134
+ "learning_rate": 4.771742063125674e-05,
1135
+ "loss": 0.8509,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 2.210095497953615,
1140
+ "grad_norm": 6.59673547744751,
1141
+ "learning_rate": 4.7380708304456554e-05,
1142
+ "loss": 0.8833,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 2.223738062755798,
1147
+ "grad_norm": 15.534720420837402,
1148
+ "learning_rate": 4.704345366820927e-05,
1149
+ "loss": 0.8968,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 2.237380627557981,
1154
+ "grad_norm": 11.261545181274414,
1155
+ "learning_rate": 4.670568150284323e-05,
1156
+ "loss": 0.9044,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 2.251023192360164,
1161
+ "grad_norm": 8.76096248626709,
1162
+ "learning_rate": 4.636741662671308e-05,
1163
+ "loss": 0.974,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 2.2646657571623465,
1168
+ "grad_norm": 5.140685081481934,
1169
+ "learning_rate": 4.602868389437622e-05,
1170
+ "loss": 0.8121,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 2.2783083219645293,
1175
+ "grad_norm": 9.906394004821777,
1176
+ "learning_rate": 4.568950819476648e-05,
1177
+ "loss": 1.1324,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 2.291950886766712,
1182
+ "grad_norm": 13.181589126586914,
1183
+ "learning_rate": 4.5349914449365435e-05,
1184
+ "loss": 0.8856,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 2.305593451568895,
1189
+ "grad_norm": 12.309771537780762,
1190
+ "learning_rate": 4.500992761037129e-05,
1191
+ "loss": 0.8276,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 2.319236016371078,
1196
+ "grad_norm": 10.110664367675781,
1197
+ "learning_rate": 4.4669572658865405e-05,
1198
+ "loss": 0.7492,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 2.3328785811732606,
1203
+ "grad_norm": 8.248074531555176,
1204
+ "learning_rate": 4.4328874602976786e-05,
1205
+ "loss": 0.9167,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 2.3465211459754434,
1210
+ "grad_norm": 8.356489181518555,
1211
+ "learning_rate": 4.3987858476044617e-05,
1212
+ "loss": 0.9453,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 2.360163710777626,
1217
+ "grad_norm": 5.316605091094971,
1218
+ "learning_rate": 4.364654933477886e-05,
1219
+ "loss": 0.8714,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 2.373806275579809,
1224
+ "grad_norm": 9.405285835266113,
1225
+ "learning_rate": 4.330497225741917e-05,
1226
+ "loss": 0.9251,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 2.3874488403819916,
1231
+ "grad_norm": 9.250997543334961,
1232
+ "learning_rate": 4.296315234189223e-05,
1233
+ "loss": 0.9479,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 2.4010914051841747,
1238
+ "grad_norm": 7.570913791656494,
1239
+ "learning_rate": 4.262111470396766e-05,
1240
+ "loss": 0.8346,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 2.4147339699863575,
1245
+ "grad_norm": 7.284623146057129,
1246
+ "learning_rate": 4.2278884475412585e-05,
1247
+ "loss": 0.754,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 2.42837653478854,
1252
+ "grad_norm": 8.737554550170898,
1253
+ "learning_rate": 4.193648680214505e-05,
1254
+ "loss": 0.7743,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 2.442019099590723,
1259
+ "grad_norm": 9.590819358825684,
1260
+ "learning_rate": 4.159394684238635e-05,
1261
+ "loss": 0.9273,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 2.4556616643929057,
1266
+ "grad_norm": 9.176666259765625,
1267
+ "learning_rate": 4.1251289764812495e-05,
1268
+ "loss": 1.0037,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 2.469304229195089,
1273
+ "grad_norm": 9.587228775024414,
1274
+ "learning_rate": 4.090854074670495e-05,
1275
+ "loss": 0.7728,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 2.4829467939972716,
1280
+ "grad_norm": 3.603977918624878,
1281
+ "learning_rate": 4.056572497210066e-05,
1282
+ "loss": 0.8098,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 2.4965893587994543,
1287
+ "grad_norm": 10.71971321105957,
1288
+ "learning_rate": 4.0222867629941554e-05,
1289
+ "loss": 0.8404,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 2.510231923601637,
1294
+ "grad_norm": 8.777016639709473,
1295
+ "learning_rate": 3.987999391222389e-05,
1296
+ "loss": 0.7021,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 2.52387448840382,
1301
+ "grad_norm": 9.952046394348145,
1302
+ "learning_rate": 3.953712901214707e-05,
1303
+ "loss": 0.9656,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 2.5375170532060025,
1308
+ "grad_norm": 10.772456169128418,
1309
+ "learning_rate": 3.9194298122262666e-05,
1310
+ "loss": 0.7487,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 2.5511596180081857,
1315
+ "grad_norm": 7.986364364624023,
1316
+ "learning_rate": 3.8851526432623254e-05,
1317
+ "loss": 0.8693,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 2.5648021828103684,
1322
+ "grad_norm": 8.993766784667969,
1323
+ "learning_rate": 3.850883912893158e-05,
1324
+ "loss": 0.8933,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 2.578444747612551,
1329
+ "grad_norm": 8.045419692993164,
1330
+ "learning_rate": 3.816626139069004e-05,
1331
+ "loss": 0.7098,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 2.592087312414734,
1336
+ "grad_norm": 7.299800872802734,
1337
+ "learning_rate": 3.782381838935047e-05,
1338
+ "loss": 0.8742,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 2.6057298772169166,
1343
+ "grad_norm": 8.76268482208252,
1344
+ "learning_rate": 3.748153528646472e-05,
1345
+ "loss": 0.7846,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 2.6193724420191,
1350
+ "grad_norm": 13.77757453918457,
1351
+ "learning_rate": 3.713943723183587e-05,
1352
+ "loss": 0.9032,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 2.6330150068212825,
1357
+ "grad_norm": 9.216800689697266,
1358
+ "learning_rate": 3.6797549361670257e-05,
1359
+ "loss": 0.8044,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 2.6466575716234653,
1364
+ "grad_norm": 12.811419486999512,
1365
+ "learning_rate": 3.6455896796730554e-05,
1366
+ "loss": 0.8528,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 2.660300136425648,
1371
+ "grad_norm": 8.257354736328125,
1372
+ "learning_rate": 3.611450464049005e-05,
1373
+ "loss": 0.9294,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 2.6739427012278307,
1378
+ "grad_norm": 6.599920272827148,
1379
+ "learning_rate": 3.577339797728805e-05,
1380
+ "loss": 0.9441,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 2.6875852660300135,
1385
+ "grad_norm": 10.485870361328125,
1386
+ "learning_rate": 3.5432601870486795e-05,
1387
+ "loss": 0.8572,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 2.701227830832196,
1392
+ "grad_norm": 5.167399883270264,
1393
+ "learning_rate": 3.509214136062993e-05,
1394
+ "loss": 0.9912,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 2.7148703956343794,
1399
+ "grad_norm": 9.000060081481934,
1400
+ "learning_rate": 3.475204146360254e-05,
1401
+ "loss": 0.9876,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 2.728512960436562,
1406
+ "grad_norm": 7.356120586395264,
1407
+ "learning_rate": 3.44123271687931e-05,
1408
+ "loss": 0.8796,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 2.742155525238745,
1413
+ "grad_norm": 10.706610679626465,
1414
+ "learning_rate": 3.407302343725737e-05,
1415
+ "loss": 0.8394,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 2.7557980900409276,
1420
+ "grad_norm": 6.853879928588867,
1421
+ "learning_rate": 3.3734155199884275e-05,
1422
+ "loss": 0.7603,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 2.7694406548431107,
1427
+ "grad_norm": 8.325788497924805,
1428
+ "learning_rate": 3.339574735556412e-05,
1429
+ "loss": 0.8944,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 2.7830832196452935,
1434
+ "grad_norm": 12.427726745605469,
1435
+ "learning_rate": 3.3057824769359104e-05,
1436
+ "loss": 0.9737,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 2.796725784447476,
1441
+ "grad_norm": 11.044093132019043,
1442
+ "learning_rate": 3.2720412270676275e-05,
1443
+ "loss": 0.9483,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 2.810368349249659,
1448
+ "grad_norm": 5.907009601593018,
1449
+ "learning_rate": 3.2383534651443206e-05,
1450
+ "loss": 0.9254,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 2.8240109140518417,
1455
+ "grad_norm": 5.986649036407471,
1456
+ "learning_rate": 3.204721666428631e-05,
1457
+ "loss": 0.7472,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 2.8376534788540244,
1462
+ "grad_norm": 9.0693359375,
1463
+ "learning_rate": 3.171148302071215e-05,
1464
+ "loss": 0.8689,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 2.851296043656207,
1469
+ "grad_norm": 7.178049087524414,
1470
+ "learning_rate": 3.137635838929169e-05,
1471
+ "loss": 0.7493,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 2.8649386084583903,
1476
+ "grad_norm": 8.808353424072266,
1477
+ "learning_rate": 3.1041867393847764e-05,
1478
+ "loss": 1.0867,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 2.878581173260573,
1483
+ "grad_norm": 11.312020301818848,
1484
+ "learning_rate": 3.070803461164575e-05,
1485
+ "loss": 0.9846,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 2.892223738062756,
1490
+ "grad_norm": 2.6739227771759033,
1491
+ "learning_rate": 3.0374884571587776e-05,
1492
+ "loss": 0.7862,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 2.9058663028649385,
1497
+ "grad_norm": 9.54980182647705,
1498
+ "learning_rate": 3.004244175241038e-05,
1499
+ "loss": 1.0586,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 2.9195088676671213,
1504
+ "grad_norm": 10.564549446105957,
1505
+ "learning_rate": 2.971073058088587e-05,
1506
+ "loss": 0.8757,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 2.9331514324693044,
1511
+ "grad_norm": 9.608818054199219,
1512
+ "learning_rate": 2.937977543002764e-05,
1513
+ "loss": 0.9026,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 2.946793997271487,
1518
+ "grad_norm": 4.548944473266602,
1519
+ "learning_rate": 2.9049600617299188e-05,
1520
+ "loss": 0.8864,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 2.96043656207367,
1525
+ "grad_norm": 7.556874752044678,
1526
+ "learning_rate": 2.872023040282739e-05,
1527
+ "loss": 0.8224,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 2.9740791268758526,
1532
+ "grad_norm": 9.024819374084473,
1533
+ "learning_rate": 2.8391688987620045e-05,
1534
+ "loss": 0.794,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 2.9877216916780354,
1539
+ "grad_norm": 5.675693035125732,
1540
+ "learning_rate": 2.8064000511787523e-05,
1541
+ "loss": 0.9792,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 3.001364256480218,
1546
+ "grad_norm": 6.426331520080566,
1547
+ "learning_rate": 2.77371890527691e-05,
1548
+ "loss": 0.7812,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 3.0150068212824013,
1553
+ "grad_norm": 7.24752140045166,
1554
+ "learning_rate": 2.741127862356389e-05,
1555
+ "loss": 0.496,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 3.028649386084584,
1560
+ "grad_norm": 8.4566650390625,
1561
+ "learning_rate": 2.7086293170966312e-05,
1562
+ "loss": 0.3416,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 3.0422919508867667,
1567
+ "grad_norm": 5.965997219085693,
1568
+ "learning_rate": 2.6762256573806664e-05,
1569
+ "loss": 0.3462,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 3.0559345156889495,
1574
+ "grad_norm": 10.749195098876953,
1575
+ "learning_rate": 2.6439192641196583e-05,
1576
+ "loss": 0.4756,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 3.069577080491132,
1581
+ "grad_norm": 7.666036605834961,
1582
+ "learning_rate": 2.611712511077959e-05,
1583
+ "loss": 0.357,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 3.083219645293315,
1588
+ "grad_norm": 7.038111209869385,
1589
+ "learning_rate": 2.5796077646986922e-05,
1590
+ "loss": 0.3361,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 3.096862210095498,
1595
+ "grad_norm": 10.389034271240234,
1596
+ "learning_rate": 2.5476073839298857e-05,
1597
+ "loss": 0.419,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 3.110504774897681,
1602
+ "grad_norm": 6.829967021942139,
1603
+ "learning_rate": 2.5157137200511253e-05,
1604
+ "loss": 0.4211,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 3.1241473396998636,
1609
+ "grad_norm": 4.85243558883667,
1610
+ "learning_rate": 2.4839291165008073e-05,
1611
+ "loss": 0.5248,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 3.1377899045020463,
1616
+ "grad_norm": 7.922482490539551,
1617
+ "learning_rate": 2.452255908703945e-05,
1618
+ "loss": 0.3983,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 3.151432469304229,
1623
+ "grad_norm": 4.674210071563721,
1624
+ "learning_rate": 2.420696423900567e-05,
1625
+ "loss": 0.3728,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 3.1650750341064118,
1630
+ "grad_norm": 16.18085289001465,
1631
+ "learning_rate": 2.3892529809747195e-05,
1632
+ "loss": 0.4099,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 3.178717598908595,
1637
+ "grad_norm": 10.127204895019531,
1638
+ "learning_rate": 2.35792789028409e-05,
1639
+ "loss": 0.5466,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 3.1923601637107777,
1644
+ "grad_norm": 6.371789932250977,
1645
+ "learning_rate": 2.32672345349024e-05,
1646
+ "loss": 0.3956,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 3.2060027285129604,
1651
+ "grad_norm": 6.170881748199463,
1652
+ "learning_rate": 2.2956419633894922e-05,
1653
+ "loss": 0.2686,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 3.219645293315143,
1658
+ "grad_norm": 8.651374816894531,
1659
+ "learning_rate": 2.264685703744466e-05,
1660
+ "loss": 0.3545,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 3.233287858117326,
1665
+ "grad_norm": 9.146707534790039,
1666
+ "learning_rate": 2.2338569491162688e-05,
1667
+ "loss": 0.4361,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 3.246930422919509,
1672
+ "grad_norm": 10.473475456237793,
1673
+ "learning_rate": 2.2031579646973662e-05,
1674
+ "loss": 0.4616,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 3.260572987721692,
1679
+ "grad_norm": 7.665262222290039,
1680
+ "learning_rate": 2.1725910061451582e-05,
1681
+ "loss": 0.4095,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 3.2742155525238745,
1686
+ "grad_norm": 14.176889419555664,
1687
+ "learning_rate": 2.1421583194162237e-05,
1688
+ "loss": 0.4428,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 3.2878581173260573,
1693
+ "grad_norm": 10.604450225830078,
1694
+ "learning_rate": 2.1118621406013045e-05,
1695
+ "loss": 0.4946,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 3.30150068212824,
1700
+ "grad_norm": 9.188895225524902,
1701
+ "learning_rate": 2.0817046957610073e-05,
1702
+ "loss": 0.3676,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 3.3151432469304227,
1707
+ "grad_norm": 5.148584842681885,
1708
+ "learning_rate": 2.0516882007622318e-05,
1709
+ "loss": 0.4319,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 3.328785811732606,
1714
+ "grad_norm": 10.153374671936035,
1715
+ "learning_rate": 2.0218148611153614e-05,
1716
+ "loss": 0.3973,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 3.3424283765347886,
1721
+ "grad_norm": 2.798651695251465,
1722
+ "learning_rate": 1.99208687181221e-05,
1723
+ "loss": 0.3728,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 3.3560709413369714,
1728
+ "grad_norm": 7.391672611236572,
1729
+ "learning_rate": 1.9625064171647403e-05,
1730
+ "loss": 0.4029,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 3.369713506139154,
1735
+ "grad_norm": 8.293444633483887,
1736
+ "learning_rate": 1.933075670644566e-05,
1737
+ "loss": 0.5182,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 3.383356070941337,
1742
+ "grad_norm": 12.008163452148438,
1743
+ "learning_rate": 1.903796794723261e-05,
1744
+ "loss": 0.3211,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 3.39699863574352,
1749
+ "grad_norm": 4.839990139007568,
1750
+ "learning_rate": 1.8746719407134558e-05,
1751
+ "loss": 0.3218,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 3.4106412005457027,
1756
+ "grad_norm": 5.815826892852783,
1757
+ "learning_rate": 1.8457032486107733e-05,
1758
+ "loss": 0.3561,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 3.4242837653478855,
1763
+ "grad_norm": 5.609132766723633,
1764
+ "learning_rate": 1.816892846936592e-05,
1765
+ "loss": 0.4223,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 3.437926330150068,
1770
+ "grad_norm": 6.10213041305542,
1771
+ "learning_rate": 1.7882428525816434e-05,
1772
+ "loss": 0.2911,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 3.451568894952251,
1777
+ "grad_norm": 6.413115501403809,
1778
+ "learning_rate": 1.759755370650472e-05,
1779
+ "loss": 0.3991,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 3.4652114597544337,
1784
+ "grad_norm": 10.340503692626953,
1785
+ "learning_rate": 1.7314324943067598e-05,
1786
+ "loss": 0.3823,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 3.4788540245566164,
1791
+ "grad_norm": 10.008712768554688,
1792
+ "learning_rate": 1.70327630461953e-05,
1793
+ "loss": 0.3564,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 3.4924965893587996,
1798
+ "grad_norm": 7.237100601196289,
1799
+ "learning_rate": 1.6752888704102304e-05,
1800
+ "loss": 0.4012,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 3.5061391541609823,
1805
+ "grad_norm": 7.369434833526611,
1806
+ "learning_rate": 1.6474722481007344e-05,
1807
+ "loss": 0.3622,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 3.519781718963165,
1812
+ "grad_norm": 10.581721305847168,
1813
+ "learning_rate": 1.619828481562229e-05,
1814
+ "loss": 0.3502,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 3.533424283765348,
1819
+ "grad_norm": 7.968098163604736,
1820
+ "learning_rate": 1.5923596019650517e-05,
1821
+ "loss": 0.4129,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 3.547066848567531,
1826
+ "grad_norm": 9.581936836242676,
1827
+ "learning_rate": 1.565067627629432e-05,
1828
+ "loss": 0.455,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 3.5607094133697137,
1833
+ "grad_norm": 7.407210350036621,
1834
+ "learning_rate": 1.5379545638772032e-05,
1835
+ "loss": 0.3905,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 3.5743519781718964,
1840
+ "grad_norm": 9.555901527404785,
1841
+ "learning_rate": 1.511022402884459e-05,
1842
+ "loss": 0.4603,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 3.587994542974079,
1847
+ "grad_norm": 5.677056312561035,
1848
+ "learning_rate": 1.4842731235351653e-05,
1849
+ "loss": 0.3654,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 3.601637107776262,
1854
+ "grad_norm": 8.808677673339844,
1855
+ "learning_rate": 1.4577086912757659e-05,
1856
+ "loss": 0.4481,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 3.6152796725784446,
1861
+ "grad_norm": 11.250635147094727,
1862
+ "learning_rate": 1.4313310579707697e-05,
1863
+ "loss": 0.4829,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 3.6289222373806274,
1868
+ "grad_norm": 8.87308406829834,
1869
+ "learning_rate": 1.405142161759327e-05,
1870
+ "loss": 0.3937,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 3.64256480218281,
1875
+ "grad_norm": 7.986633777618408,
1876
+ "learning_rate": 1.3791439269128274e-05,
1877
+ "loss": 0.3902,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 3.6562073669849933,
1882
+ "grad_norm": 6.5852155685424805,
1883
+ "learning_rate": 1.3533382636935092e-05,
1884
+ "loss": 0.4495,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 3.669849931787176,
1889
+ "grad_norm": 22.476903915405273,
1890
+ "learning_rate": 1.3277270682140996e-05,
1891
+ "loss": 0.4707,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 3.6834924965893587,
1896
+ "grad_norm": 6.103644371032715,
1897
+ "learning_rate": 1.3023122222984941e-05,
1898
+ "loss": 0.4189,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 3.6971350613915415,
1903
+ "grad_norm": 8.584049224853516,
1904
+ "learning_rate": 1.2770955933434906e-05,
1905
+ "loss": 0.3741,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 3.7107776261937246,
1910
+ "grad_norm": 8.539772033691406,
1911
+ "learning_rate": 1.2520790341815726e-05,
1912
+ "loss": 0.3724,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 3.7244201909959074,
1917
+ "grad_norm": 8.408806800842285,
1918
+ "learning_rate": 1.2272643829447723e-05,
1919
+ "loss": 0.4002,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 3.73806275579809,
1924
+ "grad_norm": 13.712347030639648,
1925
+ "learning_rate": 1.2026534629296168e-05,
1926
+ "loss": 0.4129,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 3.751705320600273,
1931
+ "grad_norm": 7.925304412841797,
1932
+ "learning_rate": 1.1782480824631478e-05,
1933
+ "loss": 0.3354,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 3.7653478854024556,
1938
+ "grad_norm": 6.753428936004639,
1939
+ "learning_rate": 1.154050034770057e-05,
1940
+ "loss": 0.3,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 3.7789904502046383,
1945
+ "grad_norm": 11.436506271362305,
1946
+ "learning_rate": 1.1300610978409301e-05,
1947
+ "loss": 0.4613,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 3.792633015006821,
1952
+ "grad_norm": 7.002927780151367,
1953
+ "learning_rate": 1.1062830343015998e-05,
1954
+ "loss": 0.3782,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 3.806275579809004,
1959
+ "grad_norm": 8.752483367919922,
1960
+ "learning_rate": 1.0827175912836352e-05,
1961
+ "loss": 0.3154,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 3.819918144611187,
1966
+ "grad_norm": 8.298131942749023,
1967
+ "learning_rate": 1.059366500295973e-05,
1968
+ "loss": 0.3941,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 3.8335607094133697,
1973
+ "grad_norm": 9.577731132507324,
1974
+ "learning_rate": 1.0362314770976858e-05,
1975
+ "loss": 0.4402,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 3.8472032742155524,
1980
+ "grad_norm": 8.360587120056152,
1981
+ "learning_rate": 1.0133142215719176e-05,
1982
+ "loss": 0.3588,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 3.8608458390177356,
1987
+ "grad_norm": 7.106631755828857,
1988
+ "learning_rate": 9.906164176009825e-06,
1989
+ "loss": 0.4171,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 3.8744884038199183,
1994
+ "grad_norm": 7.905004501342773,
1995
+ "learning_rate": 9.681397329426363e-06,
1996
+ "loss": 0.4008,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 3.888130968622101,
2001
+ "grad_norm": 7.430079460144043,
2002
+ "learning_rate": 9.458858191075358e-06,
2003
+ "loss": 0.2851,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 3.901773533424284,
2008
+ "grad_norm": 6.089357852935791,
2009
+ "learning_rate": 9.238563112378967e-06,
2010
+ "loss": 0.486,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 3.9154160982264665,
2015
+ "grad_norm": 10.433391571044922,
2016
+ "learning_rate": 9.02052827987339e-06,
2017
+ "loss": 0.3321,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 3.9290586630286493,
2022
+ "grad_norm": 11.072164535522461,
2023
+ "learning_rate": 8.804769714019619e-06,
2024
+ "loss": 0.2981,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 3.942701227830832,
2029
+ "grad_norm": 6.538973331451416,
2030
+ "learning_rate": 8.591303268026293e-06,
2031
+ "loss": 0.3412,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 3.956343792633015,
2036
+ "grad_norm": 6.748257637023926,
2037
+ "learning_rate": 8.380144626684829e-06,
2038
+ "loss": 0.3648,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 3.969986357435198,
2043
+ "grad_norm": 8.447965621948242,
2044
+ "learning_rate": 8.171309305216973e-06,
2045
+ "loss": 0.4028,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 3.9836289222373806,
2050
+ "grad_norm": 11.228553771972656,
2051
+ "learning_rate": 7.96481264813481e-06,
2052
+ "loss": 0.5365,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 3.9972714870395634,
2057
+ "grad_norm": 16.4576416015625,
2058
+ "learning_rate": 7.760669828113276e-06,
2059
+ "loss": 0.3312,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 4.0109140518417465,
2064
+ "grad_norm": 9.181668281555176,
2065
+ "learning_rate": 7.558895844875325e-06,
2066
+ "loss": 0.2586,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 4.024556616643929,
2071
+ "grad_norm": 6.005313873291016,
2072
+ "learning_rate": 7.359505524089843e-06,
2073
+ "loss": 0.174,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 4.038199181446112,
2078
+ "grad_norm": 9.592679977416992,
2079
+ "learning_rate": 7.162513516282236e-06,
2080
+ "loss": 0.1319,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 4.051841746248295,
2085
+ "grad_norm": 4.006359100341797,
2086
+ "learning_rate": 6.967934295758003e-06,
2087
+ "loss": 0.1098,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 4.0654843110504775,
2092
+ "grad_norm": 8.887368202209473,
2093
+ "learning_rate": 6.775782159539237e-06,
2094
+ "loss": 0.1351,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 4.07912687585266,
2099
+ "grad_norm": 4.626531600952148,
2100
+ "learning_rate": 6.586071226314046e-06,
2101
+ "loss": 0.2408,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 4.092769440654843,
2106
+ "grad_norm": 3.412660598754883,
2107
+ "learning_rate": 6.3988154353992285e-06,
2108
+ "loss": 0.1759,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 4.106412005457026,
2113
+ "grad_norm": 3.9307303428649902,
2114
+ "learning_rate": 6.214028545716071e-06,
2115
+ "loss": 0.2398,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 4.120054570259208,
2120
+ "grad_norm": 4.589839935302734,
2121
+ "learning_rate": 6.031724134779331e-06,
2122
+ "loss": 0.1491,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 4.133697135061391,
2127
+ "grad_norm": 5.797046184539795,
2128
+ "learning_rate": 5.851915597699638e-06,
2129
+ "loss": 0.1711,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 4.147339699863575,
2134
+ "grad_norm": 6.0500030517578125,
2135
+ "learning_rate": 5.674616146199277e-06,
2136
+ "loss": 0.1815,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 4.1609822646657575,
2141
+ "grad_norm": 5.424590587615967,
2142
+ "learning_rate": 5.499838807641413e-06,
2143
+ "loss": 0.2796,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 4.17462482946794,
2148
+ "grad_norm": 10.55384349822998,
2149
+ "learning_rate": 5.327596424072896e-06,
2150
+ "loss": 0.2307,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 4.188267394270123,
2155
+ "grad_norm": 11.20399284362793,
2156
+ "learning_rate": 5.157901651280672e-06,
2157
+ "loss": 0.1955,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 4.201909959072306,
2162
+ "grad_norm": 5.694499492645264,
2163
+ "learning_rate": 4.990766957861875e-06,
2164
+ "loss": 0.2332,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 4.215552523874488,
2169
+ "grad_norm": 3.623840093612671,
2170
+ "learning_rate": 4.826204624307665e-06,
2171
+ "loss": 0.1317,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 4.229195088676671,
2176
+ "grad_norm": 6.306783199310303,
2177
+ "learning_rate": 4.664226742100946e-06,
2178
+ "loss": 0.1772,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 4.242837653478854,
2183
+ "grad_norm": 5.530797004699707,
2184
+ "learning_rate": 4.504845212827848e-06,
2185
+ "loss": 0.1893,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 4.256480218281037,
2190
+ "grad_norm": 6.482370853424072,
2191
+ "learning_rate": 4.348071747303322e-06,
2192
+ "loss": 0.2459,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 4.270122783083219,
2197
+ "grad_norm": 6.513676643371582,
2198
+ "learning_rate": 4.193917864710599e-06,
2199
+ "loss": 0.1615,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 4.283765347885402,
2204
+ "grad_norm": 7.2312703132629395,
2205
+ "learning_rate": 4.042394891754846e-06,
2206
+ "loss": 0.1488,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 4.297407912687586,
2211
+ "grad_norm": 8.509649276733398,
2212
+ "learning_rate": 3.893513961830886e-06,
2213
+ "loss": 0.1507,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 4.311050477489768,
2218
+ "grad_norm": 8.615159034729004,
2219
+ "learning_rate": 3.74728601420518e-06,
2220
+ "loss": 0.1768,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 4.324693042291951,
2225
+ "grad_norm": 9.077027320861816,
2226
+ "learning_rate": 3.6037217932120272e-06,
2227
+ "loss": 0.3008,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 4.338335607094134,
2232
+ "grad_norm": 4.60724401473999,
2233
+ "learning_rate": 3.4628318474641344e-06,
2234
+ "loss": 0.1839,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 4.351978171896317,
2239
+ "grad_norm": 3.5988879203796387,
2240
+ "learning_rate": 3.3246265290775013e-06,
2241
+ "loss": 0.1681,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 4.365620736698499,
2246
+ "grad_norm": 3.6327638626098633,
2247
+ "learning_rate": 3.1891159929108074e-06,
2248
+ "loss": 0.2091,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 4.379263301500682,
2253
+ "grad_norm": 7.489198207855225,
2254
+ "learning_rate": 3.0563101958192677e-06,
2255
+ "loss": 0.175,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 4.392905866302865,
2260
+ "grad_norm": 7.076563835144043,
2261
+ "learning_rate": 2.9262188959230297e-06,
2262
+ "loss": 0.2715,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 4.406548431105048,
2267
+ "grad_norm": 4.808744430541992,
2268
+ "learning_rate": 2.7988516518901643e-06,
2269
+ "loss": 0.205,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 4.42019099590723,
2274
+ "grad_norm": 12.732096672058105,
2275
+ "learning_rate": 2.674217822234382e-06,
2276
+ "loss": 0.1804,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 4.433833560709413,
2281
+ "grad_norm": 4.898436546325684,
2282
+ "learning_rate": 2.5523265646273252e-06,
2283
+ "loss": 0.2301,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 4.447476125511596,
2288
+ "grad_norm": 3.7656116485595703,
2289
+ "learning_rate": 2.433186835225745e-06,
2290
+ "loss": 0.2665,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 4.461118690313779,
2295
+ "grad_norm": 4.772073745727539,
2296
+ "learning_rate": 2.316807388013431e-06,
2297
+ "loss": 0.1443,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 4.474761255115962,
2302
+ "grad_norm": 7.5682830810546875,
2303
+ "learning_rate": 2.203196774157972e-06,
2304
+ "loss": 0.2292,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 4.488403819918145,
2309
+ "grad_norm": 4.153563976287842,
2310
+ "learning_rate": 2.0923633413824663e-06,
2311
+ "loss": 0.1765,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 4.502046384720328,
2316
+ "grad_norm": 3.0278851985931396,
2317
+ "learning_rate": 1.98431523335215e-06,
2318
+ "loss": 0.1966,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 4.51568894952251,
2323
+ "grad_norm": 3.25349497795105,
2324
+ "learning_rate": 1.8790603890760328e-06,
2325
+ "loss": 0.2525,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 4.529331514324693,
2330
+ "grad_norm": 6.384403228759766,
2331
+ "learning_rate": 1.7766065423235624e-06,
2332
+ "loss": 0.1502,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 4.542974079126876,
2337
+ "grad_norm": 8.483981132507324,
2338
+ "learning_rate": 1.6769612210563834e-06,
2339
+ "loss": 0.2251,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 4.5566166439290585,
2344
+ "grad_norm": 5.477599620819092,
2345
+ "learning_rate": 1.5801317468751954e-06,
2346
+ "loss": 0.1724,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 4.570259208731241,
2351
+ "grad_norm": 6.450118541717529,
2352
+ "learning_rate": 1.4861252344817812e-06,
2353
+ "loss": 0.1416,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 4.583901773533424,
2358
+ "grad_norm": 8.463088035583496,
2359
+ "learning_rate": 1.3949485911562799e-06,
2360
+ "loss": 0.1507,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 4.597544338335607,
2365
+ "grad_norm": 5.667326927185059,
2366
+ "learning_rate": 1.3066085162496057e-06,
2367
+ "loss": 0.1486,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 4.61118690313779,
2372
+ "grad_norm": 8.173833847045898,
2373
+ "learning_rate": 1.2211115006912499e-06,
2374
+ "loss": 0.1823,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 4.624829467939973,
2379
+ "grad_norm": 7.300376892089844,
2380
+ "learning_rate": 1.1384638265123305e-06,
2381
+ "loss": 0.1146,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 4.638472032742156,
2386
+ "grad_norm": 5.938165664672852,
2387
+ "learning_rate": 1.0586715663840175e-06,
2388
+ "loss": 0.2206,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 4.6521145975443385,
2393
+ "grad_norm": 5.717035293579102,
2394
+ "learning_rate": 9.817405831713135e-07,
2395
+ "loss": 0.137,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 4.665757162346521,
2400
+ "grad_norm": 9.58558464050293,
2401
+ "learning_rate": 9.076765295022949e-07,
2402
+ "loss": 0.1969,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 4.679399727148704,
2407
+ "grad_norm": 5.858943462371826,
2408
+ "learning_rate": 8.364848473527698e-07,
2409
+ "loss": 0.1712,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 4.693042291950887,
2414
+ "grad_norm": 5.517107009887695,
2415
+ "learning_rate": 7.748725387928791e-07,
2416
+ "loss": 0.1606,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 4.7066848567530695,
2421
+ "grad_norm": 2.8044917583465576,
2422
+ "learning_rate": 7.09152598980536e-07,
2423
+ "loss": 0.1722,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 4.720327421555252,
2428
+ "grad_norm": 5.587821960449219,
2429
+ "learning_rate": 6.463196175536768e-07,
2430
+ "loss": 0.2592,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 4.733969986357435,
2435
+ "grad_norm": 8.284170150756836,
2436
+ "learning_rate": 5.863782112669647e-07,
2437
+ "loss": 0.2729,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 4.747612551159618,
2442
+ "grad_norm": 7.003023147583008,
2443
+ "learning_rate": 5.293327844118956e-07,
2444
+ "loss": 0.1888,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 4.7612551159618,
2449
+ "grad_norm": 1.9856537580490112,
2450
+ "learning_rate": 4.751875284932217e-07,
2451
+ "loss": 0.1367,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 4.774897680763983,
2456
+ "grad_norm": 6.205258846282959,
2457
+ "learning_rate": 4.2394642192095327e-07,
2458
+ "loss": 0.2003,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 4.788540245566167,
2463
+ "grad_norm": 5.503448009490967,
2464
+ "learning_rate": 3.7561322971803706e-07,
2465
+ "loss": 0.1503,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 4.8021828103683495,
2470
+ "grad_norm": 5.814334392547607,
2471
+ "learning_rate": 3.301915032437375e-07,
2472
+ "loss": 0.1425,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 4.815825375170532,
2477
+ "grad_norm": 7.47700309753418,
2478
+ "learning_rate": 2.8768457993266775e-07,
2479
+ "loss": 0.1265,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 4.829467939972715,
2484
+ "grad_norm": 6.920642375946045,
2485
+ "learning_rate": 2.480955830495679e-07,
2486
+ "loss": 0.2103,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 4.843110504774898,
2491
+ "grad_norm": 8.557290077209473,
2492
+ "learning_rate": 2.1142742145984442e-07,
2493
+ "loss": 0.2395,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 4.85675306957708,
2498
+ "grad_norm": 7.730421543121338,
2499
+ "learning_rate": 1.7768278941581617e-07,
2500
+ "loss": 0.1317,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 4.870395634379263,
2505
+ "grad_norm": 4.612334728240967,
2506
+ "learning_rate": 1.4686416635874445e-07,
2507
+ "loss": 0.1802,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 4.884038199181446,
2512
+ "grad_norm": 6.5652899742126465,
2513
+ "learning_rate": 1.1897381673666719e-07,
2514
+ "loss": 0.2484,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 4.897680763983629,
2519
+ "grad_norm": 8.53544807434082,
2520
+ "learning_rate": 9.40137898380078e-08,
2521
+ "loss": 0.1346,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 4.911323328785811,
2526
+ "grad_norm": 6.831415176391602,
2527
+ "learning_rate": 7.198591964099777e-08,
2528
+ "loss": 0.2097,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 4.924965893587995,
2533
+ "grad_norm": 11.197553634643555,
2534
+ "learning_rate": 5.289182467893561e-08,
2535
+ "loss": 0.1865,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 4.938608458390178,
2540
+ "grad_norm": 9.906291007995605,
2541
+ "learning_rate": 3.6732907921241956e-08,
2542
+ "loss": 0.2137,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 4.95225102319236,
2547
+ "grad_norm": 6.347635269165039,
2548
+ "learning_rate": 2.351035667038648e-08,
2549
+ "loss": 0.1699,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 4.965893587994543,
2554
+ "grad_norm": 2.5308990478515625,
2555
+ "learning_rate": 1.3225142474651009e-08,
2556
+ "loss": 0.247,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 4.979536152796726,
2561
+ "grad_norm": 8.235413551330566,
2562
+ "learning_rate": 5.878021056742178e-09,
2563
+ "loss": 0.1884,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 4.993178717598909,
2568
+ "grad_norm": 8.303121566772461,
2569
+ "learning_rate": 1.4695322582491956e-09,
2570
+ "loss": 0.186,
2571
+ "step": 3660
2572
+ },
2573
+ {
2574
+ "epoch": 5.0,
2575
+ "step": 3665,
2576
+ "total_flos": 2.2102292765343744e+17,
2577
+ "train_loss": 1.054027732430181,
2578
+ "train_runtime": 2482.8245,
2579
+ "train_samples_per_second": 5.905,
2580
+ "train_steps_per_second": 1.476
2581
+ }
2582
+ ],
2583
+ "logging_steps": 10,
2584
+ "max_steps": 3665,
2585
+ "num_input_tokens_seen": 0,
2586
+ "num_train_epochs": 5,
2587
+ "save_steps": 500.0,
2588
+ "stateful_callbacks": {
2589
+ "TrainerControl": {
2590
+ "args": {
2591
+ "should_epoch_stop": false,
2592
+ "should_evaluate": false,
2593
+ "should_log": false,
2594
+ "should_save": true,
2595
+ "should_training_stop": true
2596
+ },
2597
+ "attributes": {}
2598
+ }
2599
+ },
2600
+ "total_flos": 2.2102292765343744e+17,
2601
+ "train_batch_size": 4,
2602
+ "trial_name": null,
2603
+ "trial_params": null
2604
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa89ca6dfb1c8dadc04eb97aacb2843a70e0a6ea9f28cdd1741081039e0e341
3
+ size 5368
training_loss.png ADDED