ToastyPigeon commited on
Commit
dc14b5c
1 Parent(s): bee738c

Training in progress, step 236, checkpoint

Browse files
checkpoint-236/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Mistral-Nemo-Base-2407
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 0.12.0
checkpoint-236/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Mistral-Nemo-Base-2407",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
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": 0.125,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "down_proj",
25
+ "v_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "up_proj",
29
+ "k_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-236/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc1d90a786444a935abf3d1b4329313adf9c7def226c87a283daaecb61511c0
3
+ size 912336848
checkpoint-236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3cde6b475cb786a789e2f3ec85ca0f3ff5e7435d28b29bc40122d87b048b08
3
+ size 457689812
checkpoint-236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0ae7008826c26f6e03a2dbd9b8178cff1e1e00235c606e50c53acdd201617c
3
+ size 14244
checkpoint-236/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433d294d69c754c61b49a84358ed440faf6f0c84335858e5119c485dde2fea53
3
+ size 1064
checkpoint-236/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
checkpoint-236/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-236/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-236/trainer_state.json ADDED
@@ -0,0 +1,1701 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.251063829787234,
5
+ "eval_steps": 189,
6
+ "global_step": 236,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0010638297872340426,
13
+ "grad_norm": 0.15719425678253174,
14
+ "learning_rate": 2.5e-05,
15
+ "loss": 1.9422,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0010638297872340426,
20
+ "eval_loss": 2.3947696685791016,
21
+ "eval_runtime": 228.0833,
22
+ "eval_samples_per_second": 0.403,
23
+ "eval_steps_per_second": 0.403,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.002127659574468085,
28
+ "grad_norm": 0.12337572872638702,
29
+ "learning_rate": 5e-05,
30
+ "loss": 1.8454,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0031914893617021275,
35
+ "grad_norm": 0.13498862087726593,
36
+ "learning_rate": 7.5e-05,
37
+ "loss": 2.0205,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.00425531914893617,
42
+ "grad_norm": 0.14641264081001282,
43
+ "learning_rate": 0.0001,
44
+ "loss": 2.2241,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.005319148936170213,
49
+ "grad_norm": 0.221758633852005,
50
+ "learning_rate": 0.000125,
51
+ "loss": 2.1881,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.006382978723404255,
56
+ "grad_norm": 0.16080522537231445,
57
+ "learning_rate": 0.00015,
58
+ "loss": 2.3418,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.007446808510638298,
63
+ "grad_norm": 0.200699582695961,
64
+ "learning_rate": 0.000175,
65
+ "loss": 2.2462,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.00851063829787234,
70
+ "grad_norm": 0.22244133055210114,
71
+ "learning_rate": 0.0002,
72
+ "loss": 2.1351,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.009574468085106383,
77
+ "grad_norm": 0.12635783851146698,
78
+ "learning_rate": 0.00022500000000000002,
79
+ "loss": 2.1829,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.010638297872340425,
84
+ "grad_norm": 0.23889027535915375,
85
+ "learning_rate": 0.00025,
86
+ "loss": 2.285,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.011702127659574468,
91
+ "grad_norm": 0.16700100898742676,
92
+ "learning_rate": 0.0002499993636030197,
93
+ "loss": 2.0751,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.01276595744680851,
98
+ "grad_norm": 0.13016349077224731,
99
+ "learning_rate": 0.00024999745441927886,
100
+ "loss": 2.1398,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.013829787234042552,
105
+ "grad_norm": 0.22968527674674988,
106
+ "learning_rate": 0.00024999427247037733,
107
+ "loss": 2.0359,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.014893617021276596,
112
+ "grad_norm": 0.145517960190773,
113
+ "learning_rate": 0.000249989817792315,
114
+ "loss": 1.9857,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.015957446808510637,
119
+ "grad_norm": 0.12325005978345871,
120
+ "learning_rate": 0.0002499840904354907,
121
+ "loss": 2.1137,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.01702127659574468,
126
+ "grad_norm": 0.10462953895330429,
127
+ "learning_rate": 0.0002499770904647022,
128
+ "loss": 2.1306,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.018085106382978722,
133
+ "grad_norm": 0.10856030881404877,
134
+ "learning_rate": 0.0002499688179591453,
135
+ "loss": 1.9974,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.019148936170212766,
140
+ "grad_norm": 0.12662340700626373,
141
+ "learning_rate": 0.0002499592730124128,
142
+ "loss": 2.3052,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.02021276595744681,
147
+ "grad_norm": 0.10757914185523987,
148
+ "learning_rate": 0.0002499484557324936,
149
+ "loss": 2.1465,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.02127659574468085,
154
+ "grad_norm": 0.1157526895403862,
155
+ "learning_rate": 0.0002499363662417714,
156
+ "loss": 2.2331,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.022340425531914895,
161
+ "grad_norm": 0.12368866801261902,
162
+ "learning_rate": 0.00024992300467702346,
163
+ "loss": 2.1574,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.023404255319148935,
168
+ "grad_norm": 0.10928671061992645,
169
+ "learning_rate": 0.00024990837118941874,
170
+ "loss": 2.0207,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.02446808510638298,
175
+ "grad_norm": 0.1046021580696106,
176
+ "learning_rate": 0.00024989246594451646,
177
+ "loss": 2.1064,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.02553191489361702,
182
+ "grad_norm": 0.09606686979532242,
183
+ "learning_rate": 0.0002498752891222643,
184
+ "loss": 1.9726,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.026595744680851064,
189
+ "grad_norm": 0.10333864390850067,
190
+ "learning_rate": 0.00024985684091699594,
191
+ "loss": 1.9889,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.027659574468085105,
196
+ "grad_norm": 0.09974610805511475,
197
+ "learning_rate": 0.00024983712153742936,
198
+ "loss": 2.1849,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.02872340425531915,
203
+ "grad_norm": 0.09508953243494034,
204
+ "learning_rate": 0.00024981613120666417,
205
+ "loss": 1.8267,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.029787234042553193,
210
+ "grad_norm": 0.11703687906265259,
211
+ "learning_rate": 0.0002497938701621792,
212
+ "loss": 2.1924,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.030851063829787233,
217
+ "grad_norm": 0.10372091084718704,
218
+ "learning_rate": 0.0002497703386558297,
219
+ "loss": 1.8565,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.031914893617021274,
224
+ "grad_norm": 0.10386721789836884,
225
+ "learning_rate": 0.0002497455369538447,
226
+ "loss": 2.0355,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.03297872340425532,
231
+ "grad_norm": 0.09948979318141937,
232
+ "learning_rate": 0.0002497194653368238,
233
+ "loss": 2.088,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.03404255319148936,
238
+ "grad_norm": 0.0912819355726242,
239
+ "learning_rate": 0.0002496921240997341,
240
+ "loss": 2.1658,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.035106382978723406,
245
+ "grad_norm": 0.09557418525218964,
246
+ "learning_rate": 0.0002496635135519068,
247
+ "loss": 2.1933,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.036170212765957444,
252
+ "grad_norm": 0.10222162306308746,
253
+ "learning_rate": 0.0002496336340170337,
254
+ "loss": 2.0631,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.03723404255319149,
259
+ "grad_norm": 0.08941858261823654,
260
+ "learning_rate": 0.0002496024858331637,
261
+ "loss": 1.9997,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.03829787234042553,
266
+ "grad_norm": 0.0999622568488121,
267
+ "learning_rate": 0.00024957006935269867,
268
+ "loss": 2.2196,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.039361702127659576,
273
+ "grad_norm": 0.10653268545866013,
274
+ "learning_rate": 0.0002495363849423898,
275
+ "loss": 2.1727,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.04042553191489362,
280
+ "grad_norm": 0.1327868402004242,
281
+ "learning_rate": 0.0002495014329833331,
282
+ "loss": 2.0095,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.04148936170212766,
287
+ "grad_norm": 0.08846122026443481,
288
+ "learning_rate": 0.00024946521387096557,
289
+ "loss": 1.8497,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.0425531914893617,
294
+ "grad_norm": 0.1001238003373146,
295
+ "learning_rate": 0.0002494277280150601,
296
+ "loss": 2.0145,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.043617021276595745,
301
+ "grad_norm": 0.1113252341747284,
302
+ "learning_rate": 0.0002493889758397214,
303
+ "loss": 1.7905,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.04468085106382979,
308
+ "grad_norm": 0.10579642653465271,
309
+ "learning_rate": 0.00024934895778338086,
310
+ "loss": 1.9684,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.045744680851063826,
315
+ "grad_norm": 0.09689021110534668,
316
+ "learning_rate": 0.0002493076742987917,
317
+ "loss": 1.9877,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.04680851063829787,
322
+ "grad_norm": 0.10904544591903687,
323
+ "learning_rate": 0.000249265125853024,
324
+ "loss": 1.9456,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.047872340425531915,
329
+ "grad_norm": 0.08989599347114563,
330
+ "learning_rate": 0.000249221312927459,
331
+ "loss": 1.9915,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.04893617021276596,
336
+ "grad_norm": 0.10626763105392456,
337
+ "learning_rate": 0.0002491762360177841,
338
+ "loss": 2.1049,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.05,
343
+ "grad_norm": 0.10239193588495255,
344
+ "learning_rate": 0.00024912989563398696,
345
+ "loss": 2.1835,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.05106382978723404,
350
+ "grad_norm": 0.09280844777822495,
351
+ "learning_rate": 0.00024908229230035,
352
+ "loss": 1.9502,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.052127659574468084,
357
+ "grad_norm": 0.10963878780603409,
358
+ "learning_rate": 0.00024903342655544414,
359
+ "loss": 1.9337,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.05319148936170213,
364
+ "grad_norm": 0.10434435307979584,
365
+ "learning_rate": 0.00024898329895212297,
366
+ "loss": 1.9479,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.05425531914893617,
371
+ "grad_norm": 0.11127671599388123,
372
+ "learning_rate": 0.00024893191005751636,
373
+ "loss": 2.1103,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.05531914893617021,
378
+ "grad_norm": 0.09825640171766281,
379
+ "learning_rate": 0.00024887926045302403,
380
+ "loss": 1.777,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.05638297872340425,
385
+ "grad_norm": 0.10062053054571152,
386
+ "learning_rate": 0.00024882535073430915,
387
+ "loss": 2.0612,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.0574468085106383,
392
+ "grad_norm": 0.1014753133058548,
393
+ "learning_rate": 0.00024877018151129134,
394
+ "loss": 2.015,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.05851063829787234,
399
+ "grad_norm": 0.10736796259880066,
400
+ "learning_rate": 0.00024871375340814004,
401
+ "loss": 2.1078,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.059574468085106386,
406
+ "grad_norm": 0.09837566316127777,
407
+ "learning_rate": 0.00024865606706326714,
408
+ "loss": 2.0138,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.06063829787234042,
413
+ "grad_norm": 0.10129820555448532,
414
+ "learning_rate": 0.00024859712312932014,
415
+ "loss": 1.8079,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.06170212765957447,
420
+ "grad_norm": 0.11590743064880371,
421
+ "learning_rate": 0.0002485369222731744,
422
+ "loss": 1.8639,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.0627659574468085,
427
+ "grad_norm": 0.10071361064910889,
428
+ "learning_rate": 0.0002484754651759258,
429
+ "loss": 1.9809,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.06382978723404255,
434
+ "grad_norm": 0.16242088377475739,
435
+ "learning_rate": 0.0002484127525328829,
436
+ "loss": 2.0969,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.06489361702127659,
441
+ "grad_norm": 0.09952322393655777,
442
+ "learning_rate": 0.0002483487850535594,
443
+ "loss": 1.7684,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.06595744680851064,
448
+ "grad_norm": 0.0950712263584137,
449
+ "learning_rate": 0.0002482835634616656,
450
+ "loss": 1.86,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.06702127659574468,
455
+ "grad_norm": 0.1205645427107811,
456
+ "learning_rate": 0.00024821708849510053,
457
+ "loss": 1.9127,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.06808510638297872,
462
+ "grad_norm": 0.10416848212480545,
463
+ "learning_rate": 0.00024814936090594383,
464
+ "loss": 2.1245,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.06914893617021277,
469
+ "grad_norm": 0.10299328714609146,
470
+ "learning_rate": 0.00024808038146044664,
471
+ "loss": 2.2193,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.07021276595744681,
476
+ "grad_norm": 0.10638066381216049,
477
+ "learning_rate": 0.00024801015093902333,
478
+ "loss": 1.8795,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.07127659574468086,
483
+ "grad_norm": 0.13867318630218506,
484
+ "learning_rate": 0.0002479386701362427,
485
+ "loss": 2.0245,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.07234042553191489,
490
+ "grad_norm": 0.09890972822904587,
491
+ "learning_rate": 0.00024786593986081884,
492
+ "loss": 2.1797,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.07340425531914893,
497
+ "grad_norm": 0.09402583539485931,
498
+ "learning_rate": 0.00024779196093560195,
499
+ "loss": 2.0093,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.07446808510638298,
504
+ "grad_norm": 0.10384728014469147,
505
+ "learning_rate": 0.00024771673419756926,
506
+ "loss": 1.9576,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.07553191489361702,
511
+ "grad_norm": 0.11337074637413025,
512
+ "learning_rate": 0.0002476402604978153,
513
+ "loss": 2.1267,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.07659574468085106,
518
+ "grad_norm": 0.12024985998868942,
519
+ "learning_rate": 0.00024756254070154235,
520
+ "loss": 2.1193,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.07765957446808511,
525
+ "grad_norm": 0.09909618645906448,
526
+ "learning_rate": 0.0002474835756880509,
527
+ "loss": 2.0732,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.07872340425531915,
532
+ "grad_norm": 0.10968328267335892,
533
+ "learning_rate": 0.00024740336635072915,
534
+ "loss": 1.8176,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.0797872340425532,
539
+ "grad_norm": 0.10667924582958221,
540
+ "learning_rate": 0.00024732191359704345,
541
+ "loss": 1.7713,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.08085106382978724,
546
+ "grad_norm": 0.10140973329544067,
547
+ "learning_rate": 0.0002472392183485279,
548
+ "loss": 1.9644,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.08191489361702127,
553
+ "grad_norm": 0.1087941825389862,
554
+ "learning_rate": 0.0002471552815407736,
555
+ "loss": 2.0052,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.08297872340425531,
560
+ "grad_norm": 0.1062784343957901,
561
+ "learning_rate": 0.0002470701041234185,
562
+ "loss": 1.9551,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.08404255319148936,
567
+ "grad_norm": 0.10445404797792435,
568
+ "learning_rate": 0.0002469836870601363,
569
+ "loss": 2.0273,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.0851063829787234,
574
+ "grad_norm": 0.09620675444602966,
575
+ "learning_rate": 0.000246896031328626,
576
+ "loss": 1.837,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.08617021276595745,
581
+ "grad_norm": 0.09469189494848251,
582
+ "learning_rate": 0.00024680713792060016,
583
+ "loss": 2.0745,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.08723404255319149,
588
+ "grad_norm": 0.10994596034288406,
589
+ "learning_rate": 0.00024671700784177435,
590
+ "loss": 1.8983,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.08829787234042553,
595
+ "grad_norm": 0.11240627616643906,
596
+ "learning_rate": 0.0002466256421118555,
597
+ "loss": 2.0791,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.08936170212765958,
602
+ "grad_norm": 0.11063706874847412,
603
+ "learning_rate": 0.0002465330417645301,
604
+ "loss": 1.9128,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.09042553191489362,
609
+ "grad_norm": 0.09807933121919632,
610
+ "learning_rate": 0.0002464392078474531,
611
+ "loss": 1.9822,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.09148936170212765,
616
+ "grad_norm": 0.11714861541986465,
617
+ "learning_rate": 0.0002463441414222355,
618
+ "loss": 2.149,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.0925531914893617,
623
+ "grad_norm": 0.11007135361433029,
624
+ "learning_rate": 0.0002462478435644325,
625
+ "loss": 1.7036,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.09361702127659574,
630
+ "grad_norm": 0.1519717276096344,
631
+ "learning_rate": 0.0002461503153635316,
632
+ "loss": 2.1358,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.09468085106382979,
637
+ "grad_norm": 0.10105334222316742,
638
+ "learning_rate": 0.00024605155792293995,
639
+ "loss": 1.8889,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.09574468085106383,
644
+ "grad_norm": 0.09844442456960678,
645
+ "learning_rate": 0.000245951572359972,
646
+ "loss": 2.0052,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.09680851063829787,
651
+ "grad_norm": 0.1045021116733551,
652
+ "learning_rate": 0.0002458503598058367,
653
+ "loss": 2.2272,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.09787234042553192,
658
+ "grad_norm": 0.09748804569244385,
659
+ "learning_rate": 0.0002457479214056251,
660
+ "loss": 2.2324,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.09893617021276596,
665
+ "grad_norm": 0.09661906957626343,
666
+ "learning_rate": 0.0002456442583182969,
667
+ "loss": 2.0503,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.1,
672
+ "grad_norm": 0.10234526544809341,
673
+ "learning_rate": 0.0002455393717166678,
674
+ "loss": 2.1088,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.10106382978723404,
679
+ "grad_norm": 0.10246799141168594,
680
+ "learning_rate": 0.00024543326278739566,
681
+ "loss": 2.2405,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.10212765957446808,
686
+ "grad_norm": 0.1000024825334549,
687
+ "learning_rate": 0.0002453259327309679,
688
+ "loss": 1.86,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.10319148936170212,
693
+ "grad_norm": 0.10678999125957489,
694
+ "learning_rate": 0.0002452173827616869,
695
+ "loss": 2.134,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.10425531914893617,
700
+ "grad_norm": 0.10660276561975479,
701
+ "learning_rate": 0.00024510761410765725,
702
+ "loss": 1.8102,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.10531914893617021,
707
+ "grad_norm": 0.10170196741819382,
708
+ "learning_rate": 0.00024499662801077114,
709
+ "loss": 1.9482,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.10638297872340426,
714
+ "grad_norm": 0.11082155257463455,
715
+ "learning_rate": 0.0002448844257266947,
716
+ "loss": 2.2016,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.1074468085106383,
721
+ "grad_norm": 0.09914924204349518,
722
+ "learning_rate": 0.0002447710085248535,
723
+ "loss": 1.7777,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.10851063829787234,
728
+ "grad_norm": 0.0965084433555603,
729
+ "learning_rate": 0.00024465637768841857,
730
+ "loss": 2.0662,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.10957446808510639,
735
+ "grad_norm": 0.10745298117399216,
736
+ "learning_rate": 0.0002445405345142915,
737
+ "loss": 1.8013,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.11063829787234042,
742
+ "grad_norm": 0.11509711295366287,
743
+ "learning_rate": 0.0002444234803130901,
744
+ "loss": 1.9372,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.11170212765957446,
749
+ "grad_norm": 0.09749408811330795,
750
+ "learning_rate": 0.00024430521640913323,
751
+ "loss": 2.1201,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.1127659574468085,
756
+ "grad_norm": 0.10483244061470032,
757
+ "learning_rate": 0.0002441857441404261,
758
+ "loss": 1.9827,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.11382978723404255,
763
+ "grad_norm": 0.11765095591545105,
764
+ "learning_rate": 0.00024406506485864497,
765
+ "loss": 1.8852,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.1148936170212766,
770
+ "grad_norm": 0.09942599385976791,
771
+ "learning_rate": 0.00024394317992912194,
772
+ "loss": 1.8814,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.11595744680851064,
777
+ "grad_norm": 0.1128399670124054,
778
+ "learning_rate": 0.0002438200907308295,
779
+ "loss": 1.9887,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.11702127659574468,
784
+ "grad_norm": 0.1034490242600441,
785
+ "learning_rate": 0.00024369579865636485,
786
+ "loss": 2.087,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.11808510638297873,
791
+ "grad_norm": 0.10408236086368561,
792
+ "learning_rate": 0.00024357030511193423,
793
+ "loss": 1.4333,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.11914893617021277,
798
+ "grad_norm": 0.10553466528654099,
799
+ "learning_rate": 0.00024344361151733702,
800
+ "loss": 2.1482,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.1202127659574468,
805
+ "grad_norm": 0.10812198370695114,
806
+ "learning_rate": 0.00024331571930594954,
807
+ "loss": 1.7569,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.12127659574468085,
812
+ "grad_norm": 0.3904220759868622,
813
+ "learning_rate": 0.00024318662992470896,
814
+ "loss": 2.0672,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.12234042553191489,
819
+ "grad_norm": 0.1045014038681984,
820
+ "learning_rate": 0.00024305634483409703,
821
+ "loss": 1.7733,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.12340425531914893,
826
+ "grad_norm": 0.11234873533248901,
827
+ "learning_rate": 0.00024292486550812323,
828
+ "loss": 1.8588,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.12446808510638298,
833
+ "grad_norm": 0.12042441219091415,
834
+ "learning_rate": 0.00024279219343430842,
835
+ "loss": 2.3323,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.125531914893617,
840
+ "grad_norm": 0.13395822048187256,
841
+ "learning_rate": 0.00024265833011366777,
842
+ "loss": 1.9681,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.12659574468085105,
847
+ "grad_norm": 0.13613761961460114,
848
+ "learning_rate": 0.00024252327706069407,
849
+ "loss": 1.8812,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.1276595744680851,
854
+ "grad_norm": 0.11202660948038101,
855
+ "learning_rate": 0.0002423870358033402,
856
+ "loss": 2.1017,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.12872340425531914,
861
+ "grad_norm": 0.10813065618276596,
862
+ "learning_rate": 0.00024224960788300217,
863
+ "loss": 1.6332,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.12978723404255318,
868
+ "grad_norm": 0.12841644883155823,
869
+ "learning_rate": 0.00024211099485450167,
870
+ "loss": 2.0098,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.13085106382978723,
875
+ "grad_norm": 0.10981354117393494,
876
+ "learning_rate": 0.0002419711982860681,
877
+ "loss": 2.0437,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.13191489361702127,
882
+ "grad_norm": 0.10300987213850021,
883
+ "learning_rate": 0.0002418302197593213,
884
+ "loss": 1.9898,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.13297872340425532,
889
+ "grad_norm": 0.09915132820606232,
890
+ "learning_rate": 0.00024168806086925348,
891
+ "loss": 1.7063,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.13404255319148936,
896
+ "grad_norm": 0.10637573152780533,
897
+ "learning_rate": 0.00024154472322421113,
898
+ "loss": 1.8626,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.1351063829787234,
903
+ "grad_norm": 0.10706152766942978,
904
+ "learning_rate": 0.00024140020844587667,
905
+ "loss": 2.009,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.13617021276595745,
910
+ "grad_norm": 0.10487835109233856,
911
+ "learning_rate": 0.00024125451816925058,
912
+ "loss": 2.0771,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.1372340425531915,
917
+ "grad_norm": 0.11320215463638306,
918
+ "learning_rate": 0.0002411076540426324,
919
+ "loss": 2.111,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 0.13829787234042554,
924
+ "grad_norm": 0.10687907040119171,
925
+ "learning_rate": 0.00024095961772760237,
926
+ "loss": 1.7782,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 0.13936170212765958,
931
+ "grad_norm": 0.10387088358402252,
932
+ "learning_rate": 0.0002408104108990024,
933
+ "loss": 1.947,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 0.14042553191489363,
938
+ "grad_norm": 0.11471838504076004,
939
+ "learning_rate": 0.00024066003524491752,
940
+ "loss": 2.0569,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 0.14148936170212767,
945
+ "grad_norm": 0.10412081331014633,
946
+ "learning_rate": 0.00024050849246665628,
947
+ "loss": 1.9277,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 0.1425531914893617,
952
+ "grad_norm": 0.11945554614067078,
953
+ "learning_rate": 0.00024035578427873192,
954
+ "loss": 2.0863,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 0.14361702127659576,
959
+ "grad_norm": 0.12696759402751923,
960
+ "learning_rate": 0.00024020191240884276,
961
+ "loss": 2.0757,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 0.14468085106382977,
966
+ "grad_norm": 0.11579248309135437,
967
+ "learning_rate": 0.00024004687859785265,
968
+ "loss": 1.9771,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 0.14574468085106382,
973
+ "grad_norm": 0.1291639804840088,
974
+ "learning_rate": 0.00023989068459977139,
975
+ "loss": 1.9655,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 0.14680851063829786,
980
+ "grad_norm": 0.10244561731815338,
981
+ "learning_rate": 0.0002397333321817347,
982
+ "loss": 2.0573,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 0.1478723404255319,
987
+ "grad_norm": 0.10870030522346497,
988
+ "learning_rate": 0.00023957482312398452,
989
+ "loss": 1.9953,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 0.14893617021276595,
994
+ "grad_norm": 0.11521364748477936,
995
+ "learning_rate": 0.00023941515921984855,
996
+ "loss": 1.7835,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 0.15,
1001
+ "grad_norm": 0.1189892515540123,
1002
+ "learning_rate": 0.00023925434227572013,
1003
+ "loss": 1.8137,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 0.15106382978723404,
1008
+ "grad_norm": 0.11443563550710678,
1009
+ "learning_rate": 0.00023909237411103785,
1010
+ "loss": 2.1109,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 0.15212765957446808,
1015
+ "grad_norm": 0.1882992833852768,
1016
+ "learning_rate": 0.00023892925655826476,
1017
+ "loss": 2.1079,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 0.15319148936170213,
1022
+ "grad_norm": 0.11956554651260376,
1023
+ "learning_rate": 0.0002387649914628679,
1024
+ "loss": 2.0648,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 0.15425531914893617,
1029
+ "grad_norm": 0.13715718686580658,
1030
+ "learning_rate": 0.00023859958068329725,
1031
+ "loss": 2.004,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 0.15531914893617021,
1036
+ "grad_norm": 0.1169043555855751,
1037
+ "learning_rate": 0.00023843302609096467,
1038
+ "loss": 2.1193,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 0.15638297872340426,
1043
+ "grad_norm": 0.11039727926254272,
1044
+ "learning_rate": 0.00023826532957022293,
1045
+ "loss": 1.9419,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 0.1574468085106383,
1050
+ "grad_norm": 0.11504384130239487,
1051
+ "learning_rate": 0.00023809649301834415,
1052
+ "loss": 1.9714,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 0.15851063829787235,
1057
+ "grad_norm": 0.11435811966657639,
1058
+ "learning_rate": 0.00023792651834549856,
1059
+ "loss": 1.7879,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 0.1595744680851064,
1064
+ "grad_norm": 0.27376243472099304,
1065
+ "learning_rate": 0.00023775540747473262,
1066
+ "loss": 2.0011,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 0.16063829787234044,
1071
+ "grad_norm": 0.12073350697755814,
1072
+ "learning_rate": 0.0002375831623419476,
1073
+ "loss": 1.9285,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 0.16170212765957448,
1078
+ "grad_norm": 0.11144834011793137,
1079
+ "learning_rate": 0.00023740978489587733,
1080
+ "loss": 1.9147,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 0.16276595744680852,
1085
+ "grad_norm": 0.1074347198009491,
1086
+ "learning_rate": 0.00023723527709806647,
1087
+ "loss": 2.092,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 0.16382978723404254,
1092
+ "grad_norm": 0.11253698170185089,
1093
+ "learning_rate": 0.00023705964092284805,
1094
+ "loss": 1.9452,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 0.16489361702127658,
1099
+ "grad_norm": 0.1153697595000267,
1100
+ "learning_rate": 0.00023688287835732134,
1101
+ "loss": 2.008,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 0.16595744680851063,
1106
+ "grad_norm": 0.11541475355625153,
1107
+ "learning_rate": 0.00023670499140132918,
1108
+ "loss": 1.5319,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 0.16702127659574467,
1113
+ "grad_norm": 0.11363336443901062,
1114
+ "learning_rate": 0.00023652598206743553,
1115
+ "loss": 2.1214,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 0.16808510638297872,
1120
+ "grad_norm": 0.10930821299552917,
1121
+ "learning_rate": 0.00023634585238090265,
1122
+ "loss": 1.8862,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 0.16914893617021276,
1127
+ "grad_norm": 0.13756263256072998,
1128
+ "learning_rate": 0.000236164604379668,
1129
+ "loss": 2.001,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 0.1702127659574468,
1134
+ "grad_norm": 0.11600874364376068,
1135
+ "learning_rate": 0.00023598224011432163,
1136
+ "loss": 2.0017,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 0.17127659574468085,
1141
+ "grad_norm": 0.14339403808116913,
1142
+ "learning_rate": 0.00023579876164808234,
1143
+ "loss": 1.8875,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 0.1723404255319149,
1148
+ "grad_norm": 0.11734171211719513,
1149
+ "learning_rate": 0.000235614171056775,
1150
+ "loss": 2.025,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 0.17340425531914894,
1155
+ "grad_norm": 0.16881157457828522,
1156
+ "learning_rate": 0.00023542847042880662,
1157
+ "loss": 2.1279,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 0.17446808510638298,
1162
+ "grad_norm": 0.10519936680793762,
1163
+ "learning_rate": 0.00023524166186514284,
1164
+ "loss": 1.8798,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 0.17553191489361702,
1169
+ "grad_norm": 0.11043398827314377,
1170
+ "learning_rate": 0.00023505374747928419,
1171
+ "loss": 1.9368,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 0.17659574468085107,
1176
+ "grad_norm": 0.11440404504537582,
1177
+ "learning_rate": 0.00023486472939724217,
1178
+ "loss": 1.9948,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 0.1776595744680851,
1183
+ "grad_norm": 0.11574520170688629,
1184
+ "learning_rate": 0.0002346746097575153,
1185
+ "loss": 2.1822,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 0.17872340425531916,
1190
+ "grad_norm": 0.11897675693035126,
1191
+ "learning_rate": 0.00023448339071106461,
1192
+ "loss": 1.9755,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 0.1797872340425532,
1197
+ "grad_norm": 0.116481252014637,
1198
+ "learning_rate": 0.00023429107442128974,
1199
+ "loss": 1.751,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 0.18085106382978725,
1204
+ "grad_norm": 0.11168333142995834,
1205
+ "learning_rate": 0.0002340976630640041,
1206
+ "loss": 2.1915,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 0.1819148936170213,
1211
+ "grad_norm": 0.1481730043888092,
1212
+ "learning_rate": 0.00023390315882741038,
1213
+ "loss": 1.9164,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 0.1829787234042553,
1218
+ "grad_norm": 0.10625225305557251,
1219
+ "learning_rate": 0.00023370756391207588,
1220
+ "loss": 1.8064,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 0.18404255319148935,
1225
+ "grad_norm": 0.11492953449487686,
1226
+ "learning_rate": 0.0002335108805309075,
1227
+ "loss": 2.0202,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 0.1851063829787234,
1232
+ "grad_norm": 0.11886078119277954,
1233
+ "learning_rate": 0.00023331311090912677,
1234
+ "loss": 1.994,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 0.18617021276595744,
1239
+ "grad_norm": 0.12113317847251892,
1240
+ "learning_rate": 0.0002331142572842446,
1241
+ "loss": 2.061,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 0.18723404255319148,
1246
+ "grad_norm": 0.11451803892850876,
1247
+ "learning_rate": 0.00023291432190603603,
1248
+ "loss": 2.0846,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 0.18829787234042553,
1253
+ "grad_norm": 0.13504713773727417,
1254
+ "learning_rate": 0.00023271330703651482,
1255
+ "loss": 2.0917,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 0.18936170212765957,
1260
+ "grad_norm": 0.11458391696214676,
1261
+ "learning_rate": 0.00023251121494990764,
1262
+ "loss": 1.704,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 0.19042553191489361,
1267
+ "grad_norm": 0.13398422300815582,
1268
+ "learning_rate": 0.00023230804793262873,
1269
+ "loss": 2.103,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 0.19148936170212766,
1274
+ "grad_norm": 0.11917758733034134,
1275
+ "learning_rate": 0.00023210380828325353,
1276
+ "loss": 1.7718,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 0.1925531914893617,
1281
+ "grad_norm": 0.1172708049416542,
1282
+ "learning_rate": 0.0002318984983124932,
1283
+ "loss": 2.0172,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 0.19361702127659575,
1288
+ "grad_norm": 0.1266704946756363,
1289
+ "learning_rate": 0.00023169212034316805,
1290
+ "loss": 1.9212,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 0.1946808510638298,
1295
+ "grad_norm": 0.13580508530139923,
1296
+ "learning_rate": 0.0002314846767101815,
1297
+ "loss": 2.0556,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 0.19574468085106383,
1302
+ "grad_norm": 0.1328660249710083,
1303
+ "learning_rate": 0.00023127616976049357,
1304
+ "loss": 1.9746,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 0.19680851063829788,
1309
+ "grad_norm": 0.1272975504398346,
1310
+ "learning_rate": 0.00023106660185309434,
1311
+ "loss": 1.9995,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 0.19787234042553192,
1316
+ "grad_norm": 0.11610808223485947,
1317
+ "learning_rate": 0.0002308559753589773,
1318
+ "loss": 1.9755,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 0.19893617021276597,
1323
+ "grad_norm": 0.11477465182542801,
1324
+ "learning_rate": 0.0002306442926611125,
1325
+ "loss": 1.8594,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 0.2,
1330
+ "grad_norm": 0.11912880837917328,
1331
+ "learning_rate": 0.00023043155615441963,
1332
+ "loss": 2.2537,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 0.20106382978723406,
1337
+ "grad_norm": 0.12370310723781586,
1338
+ "learning_rate": 0.00023021776824574077,
1339
+ "loss": 1.8427,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 0.20106382978723406,
1344
+ "eval_loss": 2.2439846992492676,
1345
+ "eval_runtime": 228.9331,
1346
+ "eval_samples_per_second": 0.402,
1347
+ "eval_steps_per_second": 0.402,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.20212765957446807,
1352
+ "grad_norm": 0.12219749391078949,
1353
+ "learning_rate": 0.0002300029313538133,
1354
+ "loss": 1.6372,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.20319148936170212,
1359
+ "grad_norm": 0.12997935712337494,
1360
+ "learning_rate": 0.00022978704790924264,
1361
+ "loss": 1.7587,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.20425531914893616,
1366
+ "grad_norm": 0.1191156730055809,
1367
+ "learning_rate": 0.00022957012035447445,
1368
+ "loss": 2.1128,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.2053191489361702,
1373
+ "grad_norm": 0.1545037180185318,
1374
+ "learning_rate": 0.00022935215114376723,
1375
+ "loss": 1.6692,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.20638297872340425,
1380
+ "grad_norm": 0.1366199105978012,
1381
+ "learning_rate": 0.00022913314274316455,
1382
+ "loss": 1.9685,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.2074468085106383,
1387
+ "grad_norm": 0.12138072401285172,
1388
+ "learning_rate": 0.00022891309763046697,
1389
+ "loss": 1.8484,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.20851063829787234,
1394
+ "grad_norm": 0.1285848766565323,
1395
+ "learning_rate": 0.0002286920182952042,
1396
+ "loss": 1.7935,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.20957446808510638,
1401
+ "grad_norm": 0.11619207262992859,
1402
+ "learning_rate": 0.00022846990723860686,
1403
+ "loss": 2.0731,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.21063829787234042,
1408
+ "grad_norm": 0.4214017689228058,
1409
+ "learning_rate": 0.00022824676697357814,
1410
+ "loss": 2.0675,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.21170212765957447,
1415
+ "grad_norm": 0.11827094852924347,
1416
+ "learning_rate": 0.0002280226000246654,
1417
+ "loss": 1.7509,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.2127659574468085,
1422
+ "grad_norm": 0.132975772023201,
1423
+ "learning_rate": 0.00022779740892803175,
1424
+ "loss": 1.6893,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.21382978723404256,
1429
+ "grad_norm": 0.12743262946605682,
1430
+ "learning_rate": 0.00022757119623142706,
1431
+ "loss": 1.9338,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.2148936170212766,
1436
+ "grad_norm": 0.13391292095184326,
1437
+ "learning_rate": 0.00022734396449415934,
1438
+ "loss": 2.1821,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.21595744680851064,
1443
+ "grad_norm": 0.12177909165620804,
1444
+ "learning_rate": 0.0002271157162870658,
1445
+ "loss": 1.8998,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.2170212765957447,
1450
+ "grad_norm": 0.3537590503692627,
1451
+ "learning_rate": 0.00022688645419248374,
1452
+ "loss": 1.8342,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.21808510638297873,
1457
+ "grad_norm": 0.14446629583835602,
1458
+ "learning_rate": 0.00022665618080422114,
1459
+ "loss": 1.9379,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.21914893617021278,
1464
+ "grad_norm": 0.1220061182975769,
1465
+ "learning_rate": 0.00022642489872752765,
1466
+ "loss": 1.8389,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.22021276595744682,
1471
+ "grad_norm": 0.10652719438076019,
1472
+ "learning_rate": 0.00022619261057906485,
1473
+ "loss": 1.7434,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.22127659574468084,
1478
+ "grad_norm": 0.1321529746055603,
1479
+ "learning_rate": 0.00022595931898687673,
1480
+ "loss": 2.2176,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.22234042553191488,
1485
+ "grad_norm": 0.11512637138366699,
1486
+ "learning_rate": 0.00022572502659036007,
1487
+ "loss": 1.8772,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.22340425531914893,
1492
+ "grad_norm": 0.15195037424564362,
1493
+ "learning_rate": 0.00022548973604023437,
1494
+ "loss": 2.1445,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.22446808510638297,
1499
+ "grad_norm": 0.1171952560544014,
1500
+ "learning_rate": 0.00022525344999851197,
1501
+ "loss": 2.0841,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.225531914893617,
1506
+ "grad_norm": 0.11501558870077133,
1507
+ "learning_rate": 0.00022501617113846798,
1508
+ "loss": 1.8845,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.22659574468085106,
1513
+ "grad_norm": 0.14285384118556976,
1514
+ "learning_rate": 0.00022477790214460994,
1515
+ "loss": 1.7457,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.2276595744680851,
1520
+ "grad_norm": 0.1312599778175354,
1521
+ "learning_rate": 0.0002245386457126475,
1522
+ "loss": 2.12,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.22872340425531915,
1527
+ "grad_norm": 0.12865905463695526,
1528
+ "learning_rate": 0.00022429840454946196,
1529
+ "loss": 1.9595,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.2297872340425532,
1534
+ "grad_norm": 0.18248826265335083,
1535
+ "learning_rate": 0.00022405718137307552,
1536
+ "loss": 2.0199,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.23085106382978723,
1541
+ "grad_norm": 0.129413902759552,
1542
+ "learning_rate": 0.00022381497891262066,
1543
+ "loss": 1.8833,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.23191489361702128,
1548
+ "grad_norm": 0.12320221215486526,
1549
+ "learning_rate": 0.00022357179990830923,
1550
+ "loss": 2.0043,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.23297872340425532,
1555
+ "grad_norm": 0.11922425031661987,
1556
+ "learning_rate": 0.00022332764711140127,
1557
+ "loss": 1.9641,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.23404255319148937,
1562
+ "grad_norm": 0.1320050060749054,
1563
+ "learning_rate": 0.00022308252328417426,
1564
+ "loss": 1.9602,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.2351063829787234,
1569
+ "grad_norm": 0.14773212373256683,
1570
+ "learning_rate": 0.00022283643119989154,
1571
+ "loss": 1.8785,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.23617021276595745,
1576
+ "grad_norm": 0.128052219748497,
1577
+ "learning_rate": 0.00022258937364277105,
1578
+ "loss": 1.8772,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.2372340425531915,
1583
+ "grad_norm": 0.12113828212022781,
1584
+ "learning_rate": 0.00022234135340795378,
1585
+ "loss": 2.0577,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.23829787234042554,
1590
+ "grad_norm": 0.1478564292192459,
1591
+ "learning_rate": 0.0002220923733014723,
1592
+ "loss": 1.7237,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.2393617021276596,
1597
+ "grad_norm": 0.12648318707942963,
1598
+ "learning_rate": 0.0002218424361402188,
1599
+ "loss": 1.5301,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.2404255319148936,
1604
+ "grad_norm": 0.13919681310653687,
1605
+ "learning_rate": 0.00022159154475191343,
1606
+ "loss": 1.8451,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.24148936170212765,
1611
+ "grad_norm": 0.162435844540596,
1612
+ "learning_rate": 0.00022133970197507199,
1613
+ "loss": 1.7585,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.2425531914893617,
1618
+ "grad_norm": 0.1612282693386078,
1619
+ "learning_rate": 0.0002210869106589743,
1620
+ "loss": 1.9223,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.24361702127659574,
1625
+ "grad_norm": 0.1214359775185585,
1626
+ "learning_rate": 0.0002208331736636316,
1627
+ "loss": 1.8637,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.24468085106382978,
1632
+ "grad_norm": 0.1307225078344345,
1633
+ "learning_rate": 0.0002205784938597541,
1634
+ "loss": 1.9397,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.24574468085106382,
1639
+ "grad_norm": 0.13562381267547607,
1640
+ "learning_rate": 0.00022032287412871893,
1641
+ "loss": 1.9584,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.24680851063829787,
1646
+ "grad_norm": 0.12984585762023926,
1647
+ "learning_rate": 0.00022006631736253715,
1648
+ "loss": 1.8084,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.2478723404255319,
1653
+ "grad_norm": 0.11881977319717407,
1654
+ "learning_rate": 0.00021980882646382128,
1655
+ "loss": 1.747,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.24893617021276596,
1660
+ "grad_norm": 0.13311228156089783,
1661
+ "learning_rate": 0.0002195504043457523,
1662
+ "loss": 1.9873,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.25,
1667
+ "grad_norm": 0.13149425387382507,
1668
+ "learning_rate": 0.00021929105393204675,
1669
+ "loss": 2.0715,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.251063829787234,
1674
+ "grad_norm": 0.1460556536912918,
1675
+ "learning_rate": 0.00021903077815692358,
1676
+ "loss": 1.7887,
1677
+ "step": 236
1678
+ }
1679
+ ],
1680
+ "logging_steps": 1,
1681
+ "max_steps": 944,
1682
+ "num_input_tokens_seen": 0,
1683
+ "num_train_epochs": 1,
1684
+ "save_steps": 236,
1685
+ "stateful_callbacks": {
1686
+ "TrainerControl": {
1687
+ "args": {
1688
+ "should_epoch_stop": false,
1689
+ "should_evaluate": false,
1690
+ "should_log": false,
1691
+ "should_save": true,
1692
+ "should_training_stop": false
1693
+ },
1694
+ "attributes": {}
1695
+ }
1696
+ },
1697
+ "total_flos": 5.477347754193715e+17,
1698
+ "train_batch_size": 4,
1699
+ "trial_name": null,
1700
+ "trial_params": null
1701
+ }
checkpoint-236/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f9aa142f9f5228c96795c688617203e96a2827ab2384852389683ff851c738
3
+ size 6328