blahBlahhhJ commited on
Commit
43b6141
·
verified ·
1 Parent(s): ca86377

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: liuhaotian/llava-v1.6-mistral-7b
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
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
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": 256,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "gate_proj",
25
+ "up_proj",
26
+ "v_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "o_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 sha256:15cad6c13249ef14bc66999e41c8089789cc17aba74afbcb75fe910ce11da62c
3
+ size 708925520
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
3
+ "architectures": [
4
+ "LlavaMistralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "freeze_mm_vision_resampler": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "image_aspect_ratio": "pad",
15
+ "image_crop_resolution": 224,
16
+ "image_grid_pinpoints": [
17
+ [
18
+ 336,
19
+ 672
20
+ ],
21
+ [
22
+ 672,
23
+ 336
24
+ ],
25
+ [
26
+ 672,
27
+ 672
28
+ ],
29
+ [
30
+ 1008,
31
+ 336
32
+ ],
33
+ [
34
+ 336,
35
+ 1008
36
+ ]
37
+ ],
38
+ "image_split_resolution": 224,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 14336,
41
+ "max_position_embeddings": 32768,
42
+ "mm_hidden_size": 1024,
43
+ "mm_patch_merge_type": "flat",
44
+ "mm_projector_lr": 2e-05,
45
+ "mm_projector_type": "mlp2x_gelu",
46
+ "mm_resampler_type": null,
47
+ "mm_use_im_patch_token": false,
48
+ "mm_use_im_start_end": false,
49
+ "mm_vision_select_feature": "patch",
50
+ "mm_vision_select_layer": -2,
51
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
52
+ "mm_vision_tower_lr": 2e-06,
53
+ "model_type": "llava_llama",
54
+ "num_attention_heads": 32,
55
+ "num_hidden_layers": 32,
56
+ "num_key_value_heads": 8,
57
+ "pretraining_tp": 1,
58
+ "rms_norm_eps": 1e-05,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000.0,
61
+ "sliding_window": null,
62
+ "tie_word_embeddings": false,
63
+ "tokenizer_model_max_length": 2048,
64
+ "tokenizer_padding_side": "right",
65
+ "torch_dtype": "bfloat16",
66
+ "transformers_version": "4.39.3",
67
+ "tune_mm_mlp_adapter": false,
68
+ "tune_mm_vision_resampler": false,
69
+ "unfreeze_mm_vision_tower": true,
70
+ "use_cache": true,
71
+ "use_mm_proj": true,
72
+ "vocab_size": 32000
73
+ }
non_lora_trainables.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3885463ff88e1ef6530e61691e756c9a5698547c007d63c618d3680b7e604d53
3
+ size 41961648
trainer_state.json ADDED
@@ -0,0 +1,1773 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 249,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 3.981182133898211,
14
+ "learning_rate": 2.5e-05,
15
+ "loss": 1.365,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 4.223447168750389,
21
+ "learning_rate": 5e-05,
22
+ "loss": 1.3932,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 2.141765750699434,
28
+ "learning_rate": 7.500000000000001e-05,
29
+ "loss": 1.1306,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 2.2703951636474855,
35
+ "learning_rate": 0.0001,
36
+ "loss": 1.0787,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "grad_norm": 1.9111760478873023,
42
+ "learning_rate": 0.000125,
43
+ "loss": 1.0686,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "grad_norm": 1.3499712071563628,
49
+ "learning_rate": 0.00015000000000000001,
50
+ "loss": 1.0114,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "grad_norm": 1.0911667817060011,
56
+ "learning_rate": 0.000175,
57
+ "loss": 0.9416,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.03,
62
+ "grad_norm": 1.2496043705531406,
63
+ "learning_rate": 0.0002,
64
+ "loss": 0.9286,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.04,
69
+ "grad_norm": 1.7692075337111344,
70
+ "learning_rate": 0.00019999150370633988,
71
+ "loss": 0.9074,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.04,
76
+ "grad_norm": 0.9122071484249495,
77
+ "learning_rate": 0.00019996601626909964,
78
+ "loss": 0.8867,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.04,
83
+ "grad_norm": 0.9493702949853532,
84
+ "learning_rate": 0.00019992354201925428,
85
+ "loss": 0.8814,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.05,
90
+ "grad_norm": 0.8549355244573901,
91
+ "learning_rate": 0.0001998640881742778,
92
+ "loss": 0.8887,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05,
97
+ "grad_norm": 0.8921668257689561,
98
+ "learning_rate": 0.00019978766483691676,
99
+ "loss": 0.8542,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.06,
104
+ "grad_norm": 0.8244188073583076,
105
+ "learning_rate": 0.0001996942849934735,
106
+ "loss": 0.8412,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.06,
111
+ "grad_norm": 0.7478409595239439,
112
+ "learning_rate": 0.00019958396451159936,
113
+ "loss": 0.7793,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06,
118
+ "grad_norm": 0.758307762850361,
119
+ "learning_rate": 0.0001994567221375987,
120
+ "loss": 0.819,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.07,
125
+ "grad_norm": 0.770947644951731,
126
+ "learning_rate": 0.00019931257949324288,
127
+ "loss": 0.8447,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.07,
132
+ "grad_norm": 0.8358253752348583,
133
+ "learning_rate": 0.00019915156107209675,
134
+ "loss": 0.772,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.08,
139
+ "grad_norm": 0.7175509358752481,
140
+ "learning_rate": 0.000198973694235356,
141
+ "loss": 0.7914,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08,
146
+ "grad_norm": 0.7542707242255626,
147
+ "learning_rate": 0.00019877900920719827,
148
+ "loss": 0.7983,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.08,
153
+ "grad_norm": 0.7645202304094161,
154
+ "learning_rate": 0.00019856753906964686,
155
+ "loss": 0.7214,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.09,
160
+ "grad_norm": 0.7430521597063948,
161
+ "learning_rate": 0.0001983393197569497,
162
+ "loss": 0.8091,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.09,
167
+ "grad_norm": 0.7324090515929388,
168
+ "learning_rate": 0.00019809439004947268,
169
+ "loss": 0.7704,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.1,
174
+ "grad_norm": 0.6896844994612445,
175
+ "learning_rate": 0.00019783279156711022,
176
+ "loss": 0.7556,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.1,
181
+ "grad_norm": 0.6749132637574569,
182
+ "learning_rate": 0.0001975545687622129,
183
+ "loss": 0.7571,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.1,
188
+ "grad_norm": 0.7076244352514828,
189
+ "learning_rate": 0.00019725976891203376,
190
+ "loss": 0.8445,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.11,
195
+ "grad_norm": 0.6358516553573809,
196
+ "learning_rate": 0.00019694844211069477,
197
+ "loss": 0.7477,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.11,
202
+ "grad_norm": 0.6633797558960025,
203
+ "learning_rate": 0.00019662064126067452,
204
+ "loss": 0.7359,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.12,
209
+ "grad_norm": 0.7619604289470452,
210
+ "learning_rate": 0.00019627642206381863,
211
+ "loss": 0.7752,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.12,
216
+ "grad_norm": 0.6693105562777081,
217
+ "learning_rate": 0.00019591584301187478,
218
+ "loss": 0.7147,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.12,
223
+ "grad_norm": 0.6441185271339039,
224
+ "learning_rate": 0.00019553896537655318,
225
+ "loss": 0.7425,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.13,
230
+ "grad_norm": 0.6912959653338677,
231
+ "learning_rate": 0.0001951458531991151,
232
+ "loss": 0.7344,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.13,
237
+ "grad_norm": 0.6265627524452637,
238
+ "learning_rate": 0.00019473657327949054,
239
+ "loss": 0.7292,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.14,
244
+ "grad_norm": 0.8319948068621666,
245
+ "learning_rate": 0.00019431119516492726,
246
+ "loss": 0.7196,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.14,
251
+ "grad_norm": 0.6374074802429165,
252
+ "learning_rate": 0.00019386979113817282,
253
+ "loss": 0.7549,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.14,
258
+ "grad_norm": 0.6813527739244364,
259
+ "learning_rate": 0.0001934124362051919,
260
+ "loss": 0.7656,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.15,
265
+ "grad_norm": 1.6806360809140246,
266
+ "learning_rate": 0.00019293920808242083,
267
+ "loss": 0.7582,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.15,
272
+ "grad_norm": 0.66415983259972,
273
+ "learning_rate": 0.0001924501871835616,
274
+ "loss": 0.7754,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.16,
279
+ "grad_norm": 0.736768809075717,
280
+ "learning_rate": 0.00019194545660591752,
281
+ "loss": 0.6906,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.16,
286
+ "grad_norm": 1.013197406350164,
287
+ "learning_rate": 0.00019142510211627264,
288
+ "loss": 0.7464,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.16,
293
+ "grad_norm": 0.8455834245687115,
294
+ "learning_rate": 0.000190889212136318,
295
+ "loss": 0.7476,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.17,
300
+ "grad_norm": 0.8000760159918991,
301
+ "learning_rate": 0.00019033787772762645,
302
+ "loss": 0.7612,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.17,
307
+ "grad_norm": 0.7721776264489126,
308
+ "learning_rate": 0.00018977119257617878,
309
+ "loss": 0.7661,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.18,
314
+ "grad_norm": 0.7411505347014887,
315
+ "learning_rate": 0.00018918925297644416,
316
+ "loss": 0.7582,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.18,
321
+ "grad_norm": 0.6574055283176412,
322
+ "learning_rate": 0.00018859215781501725,
323
+ "loss": 0.693,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.18,
328
+ "grad_norm": 0.6252820250088373,
329
+ "learning_rate": 0.0001879800085538147,
330
+ "loss": 0.6709,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.19,
335
+ "grad_norm": 0.6283973563255442,
336
+ "learning_rate": 0.0001873529092128343,
337
+ "loss": 0.7499,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.19,
342
+ "grad_norm": 0.691088723538482,
343
+ "learning_rate": 0.00018671096635247914,
344
+ "loss": 0.7595,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.2,
349
+ "grad_norm": 0.6657667325476994,
350
+ "learning_rate": 0.00018605428905545032,
351
+ "loss": 0.7608,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.2,
356
+ "grad_norm": 0.6483390927552524,
357
+ "learning_rate": 0.0001853829889082109,
358
+ "loss": 0.7267,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.2,
363
+ "grad_norm": 0.5768376505606613,
364
+ "learning_rate": 0.00018469717998202462,
365
+ "loss": 0.7361,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.21,
370
+ "grad_norm": 0.5962362264080698,
371
+ "learning_rate": 0.00018399697881357212,
372
+ "loss": 0.7373,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.21,
377
+ "grad_norm": 0.6392264631697471,
378
+ "learning_rate": 0.00018328250438514836,
379
+ "loss": 0.7005,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.22,
384
+ "grad_norm": 0.6242411219574141,
385
+ "learning_rate": 0.00018255387810444448,
386
+ "loss": 0.7522,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.22,
391
+ "grad_norm": 0.5870527031664319,
392
+ "learning_rate": 0.0001818112237839174,
393
+ "loss": 0.7118,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.22,
398
+ "grad_norm": 0.6066047817906325,
399
+ "learning_rate": 0.00018105466761975109,
400
+ "loss": 0.7058,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.23,
405
+ "grad_norm": 0.6038141699713118,
406
+ "learning_rate": 0.00018028433817041236,
407
+ "loss": 0.7219,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.23,
412
+ "grad_norm": 0.5847345831142737,
413
+ "learning_rate": 0.00017950036633480556,
414
+ "loss": 0.7147,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.24,
419
+ "grad_norm": 0.6312111783082757,
420
+ "learning_rate": 0.00017870288533002938,
421
+ "loss": 0.6963,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.24,
426
+ "grad_norm": 0.5966959070900965,
427
+ "learning_rate": 0.00017789203066873998,
428
+ "loss": 0.7307,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.24,
433
+ "grad_norm": 0.5798593347176144,
434
+ "learning_rate": 0.00017706794013612364,
435
+ "loss": 0.7303,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.25,
440
+ "grad_norm": 0.6100699019983455,
441
+ "learning_rate": 0.00017623075376648376,
442
+ "loss": 0.7122,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.25,
447
+ "grad_norm": 0.6150446745513377,
448
+ "learning_rate": 0.00017538061381944524,
449
+ "loss": 0.7282,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.26,
454
+ "grad_norm": 0.5839828703861961,
455
+ "learning_rate": 0.0001745176647557809,
456
+ "loss": 0.6841,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.26,
461
+ "grad_norm": 0.5832617502478282,
462
+ "learning_rate": 0.00017364205321286394,
463
+ "loss": 0.7088,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.27,
468
+ "grad_norm": 0.6117567542213321,
469
+ "learning_rate": 0.00017275392797975032,
470
+ "loss": 0.781,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.27,
475
+ "grad_norm": 0.6332126002995662,
476
+ "learning_rate": 0.00017185343997189588,
477
+ "loss": 0.7346,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.27,
482
+ "grad_norm": 0.5617477585453899,
483
+ "learning_rate": 0.00017094074220551158,
484
+ "loss": 0.7114,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.28,
489
+ "grad_norm": 0.5820274703305921,
490
+ "learning_rate": 0.0001700159897715624,
491
+ "loss": 0.742,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.28,
496
+ "grad_norm": 0.580367538119296,
497
+ "learning_rate": 0.00016907933980941312,
498
+ "loss": 0.6663,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.29,
503
+ "grad_norm": 0.5652333172835816,
504
+ "learning_rate": 0.0001681309514801265,
505
+ "loss": 0.678,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.29,
510
+ "grad_norm": 0.5604822769679129,
511
+ "learning_rate": 0.00016717098593941752,
512
+ "loss": 0.7027,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.29,
517
+ "grad_norm": 0.5443005590527936,
518
+ "learning_rate": 0.00016619960631026888,
519
+ "loss": 0.7235,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3,
524
+ "grad_norm": 0.5648289749630883,
525
+ "learning_rate": 0.0001652169776552123,
526
+ "loss": 0.6966,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.3,
531
+ "grad_norm": 0.5511612101503145,
532
+ "learning_rate": 0.00016422326694828007,
533
+ "loss": 0.6716,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.31,
538
+ "grad_norm": 0.5652818087038983,
539
+ "learning_rate": 0.00016321864304663173,
540
+ "loss": 0.6964,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.31,
545
+ "grad_norm": 0.5873059772542137,
546
+ "learning_rate": 0.000162203276661861,
547
+ "loss": 0.7268,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.31,
552
+ "grad_norm": 0.584440156512384,
553
+ "learning_rate": 0.00016117734033098744,
554
+ "loss": 0.7183,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.32,
559
+ "grad_norm": 0.5476205992100533,
560
+ "learning_rate": 0.00016014100838713797,
561
+ "loss": 0.7063,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.32,
566
+ "grad_norm": 0.6013346658704335,
567
+ "learning_rate": 0.000159094456929923,
568
+ "loss": 0.6893,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.33,
573
+ "grad_norm": 0.5525643324311199,
574
+ "learning_rate": 0.0001580378637955128,
575
+ "loss": 0.6691,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.33,
580
+ "grad_norm": 0.5889885232500072,
581
+ "learning_rate": 0.00015697140852641834,
582
+ "loss": 0.6944,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.33,
587
+ "grad_norm": 0.6105160593879608,
588
+ "learning_rate": 0.00015589527234098247,
589
+ "loss": 0.7328,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.34,
594
+ "grad_norm": 0.580479859109292,
595
+ "learning_rate": 0.00015480963810258613,
596
+ "loss": 0.6913,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.34,
601
+ "grad_norm": 0.5618974771825274,
602
+ "learning_rate": 0.00015371469028857532,
603
+ "loss": 0.724,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.35,
608
+ "grad_norm": 0.560525959205613,
609
+ "learning_rate": 0.00015261061495891345,
610
+ "loss": 0.7048,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.35,
615
+ "grad_norm": 0.6212802766603819,
616
+ "learning_rate": 0.0001514975997245649,
617
+ "loss": 0.6858,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.35,
622
+ "grad_norm": 0.570889967163218,
623
+ "learning_rate": 0.00015037583371561535,
624
+ "loss": 0.696,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.36,
629
+ "grad_norm": 0.5568747400044114,
630
+ "learning_rate": 0.0001492455075491334,
631
+ "loss": 0.693,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.36,
636
+ "grad_norm": 0.5563715707732911,
637
+ "learning_rate": 0.00014810681329677987,
638
+ "loss": 0.6806,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.37,
643
+ "grad_norm": 0.568992451570255,
644
+ "learning_rate": 0.00014695994445216985,
645
+ "loss": 0.7074,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.37,
650
+ "grad_norm": 0.5767587218056255,
651
+ "learning_rate": 0.00014580509589799329,
652
+ "loss": 0.7094,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.37,
657
+ "grad_norm": 0.5425009774160251,
658
+ "learning_rate": 0.00014464246387289913,
659
+ "loss": 0.6781,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.38,
664
+ "grad_norm": 0.5513859545077572,
665
+ "learning_rate": 0.00014347224593814944,
666
+ "loss": 0.7234,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.38,
671
+ "grad_norm": 0.5339051729787517,
672
+ "learning_rate": 0.00014229464094404865,
673
+ "loss": 0.6931,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.39,
678
+ "grad_norm": 0.5549045365561713,
679
+ "learning_rate": 0.00014110984899615367,
680
+ "loss": 0.6962,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.39,
685
+ "grad_norm": 0.5395797162975184,
686
+ "learning_rate": 0.0001399180714212708,
687
+ "loss": 0.6832,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.39,
692
+ "grad_norm": 0.5393020282422275,
693
+ "learning_rate": 0.00013871951073324507,
694
+ "loss": 0.7212,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.4,
699
+ "grad_norm": 0.5406971945004404,
700
+ "learning_rate": 0.0001375143705985481,
701
+ "loss": 0.6878,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4,
706
+ "grad_norm": 0.5741985470318297,
707
+ "learning_rate": 0.00013630285580166945,
708
+ "loss": 0.6725,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.41,
713
+ "grad_norm": 0.6087387724460733,
714
+ "learning_rate": 0.000135085172210319,
715
+ "loss": 0.6876,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.41,
720
+ "grad_norm": 0.5202304228310284,
721
+ "learning_rate": 0.00013386152674044422,
722
+ "loss": 0.6652,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.41,
727
+ "grad_norm": 0.5660298147339341,
728
+ "learning_rate": 0.00013263212732107012,
729
+ "loss": 0.693,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.42,
734
+ "grad_norm": 0.546774134041922,
735
+ "learning_rate": 0.00013139718285896655,
736
+ "loss": 0.6464,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.42,
741
+ "grad_norm": 0.5338303600632187,
742
+ "learning_rate": 0.00013015690320314954,
743
+ "loss": 0.7009,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.43,
748
+ "grad_norm": 0.5396484507008162,
749
+ "learning_rate": 0.00012891149910922267,
750
+ "loss": 0.696,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.43,
755
+ "grad_norm": 0.5185373681304583,
756
+ "learning_rate": 0.00012766118220356408,
757
+ "loss": 0.687,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.43,
762
+ "grad_norm": 0.5102091277266492,
763
+ "learning_rate": 0.0001264061649473657,
764
+ "loss": 0.6648,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.44,
769
+ "grad_norm": 0.5727613881928513,
770
+ "learning_rate": 0.00012514666060053076,
771
+ "loss": 0.6777,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.44,
776
+ "grad_norm": 0.5165707891231989,
777
+ "learning_rate": 0.00012388288318543512,
778
+ "loss": 0.6454,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.45,
783
+ "grad_norm": 0.5463906044314786,
784
+ "learning_rate": 0.00012261504745055964,
785
+ "loss": 0.6463,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.45,
790
+ "grad_norm": 0.5150747138759594,
791
+ "learning_rate": 0.00012134336883399855,
792
+ "loss": 0.6436,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.45,
797
+ "grad_norm": 0.5268166681458911,
798
+ "learning_rate": 0.00012006806342685126,
799
+ "loss": 0.7139,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.46,
804
+ "grad_norm": 0.5797636370362743,
805
+ "learning_rate": 0.00011878934793650273,
806
+ "loss": 0.5959,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.46,
811
+ "grad_norm": 0.5168654595529651,
812
+ "learning_rate": 0.00011750743964979918,
813
+ "loss": 0.6465,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.47,
818
+ "grad_norm": 0.5586505025432532,
819
+ "learning_rate": 0.00011622255639612554,
820
+ "loss": 0.6954,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.47,
825
+ "grad_norm": 0.5733109224839272,
826
+ "learning_rate": 0.00011493491651039077,
827
+ "loss": 0.6951,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.47,
832
+ "grad_norm": 0.5798484006098489,
833
+ "learning_rate": 0.00011364473879592674,
834
+ "loss": 0.6713,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.48,
839
+ "grad_norm": 0.5558404867313713,
840
+ "learning_rate": 0.0001123522424873082,
841
+ "loss": 0.6627,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.48,
846
+ "grad_norm": 0.564370632395679,
847
+ "learning_rate": 0.000111057647213099,
848
+ "loss": 0.6582,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.49,
853
+ "grad_norm": 0.5247546019655245,
854
+ "learning_rate": 0.00010976117295853154,
855
+ "loss": 0.6274,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.49,
860
+ "grad_norm": 0.5043366815729828,
861
+ "learning_rate": 0.00010846304002812564,
862
+ "loss": 0.663,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.49,
867
+ "grad_norm": 0.5377570953262834,
868
+ "learning_rate": 0.00010716346900825299,
869
+ "loss": 0.6879,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5,
874
+ "grad_norm": 0.5316530391582156,
875
+ "learning_rate": 0.00010586268072965396,
876
+ "loss": 0.6812,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5,
881
+ "grad_norm": 0.5309847868667069,
882
+ "learning_rate": 0.00010456089622991263,
883
+ "loss": 0.6378,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.51,
888
+ "grad_norm": 0.49952898047881455,
889
+ "learning_rate": 0.00010325833671589687,
890
+ "loss": 0.7031,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.51,
895
+ "grad_norm": 0.513186855879022,
896
+ "learning_rate": 0.00010195522352616943,
897
+ "loss": 0.6346,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.51,
902
+ "grad_norm": 0.5624215177016363,
903
+ "learning_rate": 0.00010065177809337702,
904
+ "loss": 0.7014,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.52,
909
+ "grad_norm": 0.5339748834208153,
910
+ "learning_rate": 9.934822190662299e-05,
911
+ "loss": 0.7169,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.52,
916
+ "grad_norm": 0.5298864830864823,
917
+ "learning_rate": 9.80447764738306e-05,
918
+ "loss": 0.6419,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.53,
923
+ "grad_norm": 0.49790603329053645,
924
+ "learning_rate": 9.674166328410318e-05,
925
+ "loss": 0.6277,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.53,
930
+ "grad_norm": 0.5222038396293899,
931
+ "learning_rate": 9.543910377008742e-05,
932
+ "loss": 0.6617,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.53,
937
+ "grad_norm": 0.5076737199539593,
938
+ "learning_rate": 9.413731927034605e-05,
939
+ "loss": 0.6315,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.54,
944
+ "grad_norm": 0.540367448084855,
945
+ "learning_rate": 9.283653099174704e-05,
946
+ "loss": 0.637,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.54,
951
+ "grad_norm": 0.5259754962695676,
952
+ "learning_rate": 9.15369599718744e-05,
953
+ "loss": 0.6564,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.55,
958
+ "grad_norm": 0.5297038847994276,
959
+ "learning_rate": 9.023882704146848e-05,
960
+ "loss": 0.6174,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.55,
965
+ "grad_norm": 0.5175810600475641,
966
+ "learning_rate": 8.894235278690104e-05,
967
+ "loss": 0.6885,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.55,
972
+ "grad_norm": 0.49466775844805594,
973
+ "learning_rate": 8.764775751269182e-05,
974
+ "loss": 0.6264,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.56,
979
+ "grad_norm": 0.5468376014397491,
980
+ "learning_rate": 8.635526120407329e-05,
981
+ "loss": 0.6293,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.56,
986
+ "grad_norm": 0.5266499924056278,
987
+ "learning_rate": 8.506508348960924e-05,
988
+ "loss": 0.6672,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.57,
993
+ "grad_norm": 0.5125354022430374,
994
+ "learning_rate": 8.377744360387447e-05,
995
+ "loss": 0.6289,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.57,
1000
+ "grad_norm": 0.508760796232234,
1001
+ "learning_rate": 8.249256035020086e-05,
1002
+ "loss": 0.6311,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.57,
1007
+ "grad_norm": 0.5021864887346997,
1008
+ "learning_rate": 8.121065206349729e-05,
1009
+ "loss": 0.6594,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.58,
1014
+ "grad_norm": 0.5355896437675315,
1015
+ "learning_rate": 7.993193657314875e-05,
1016
+ "loss": 0.6224,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.58,
1021
+ "grad_norm": 0.5488326374985829,
1022
+ "learning_rate": 7.865663116600148e-05,
1023
+ "loss": 0.6465,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.59,
1028
+ "grad_norm": 0.6071274038365753,
1029
+ "learning_rate": 7.738495254944042e-05,
1030
+ "loss": 0.6576,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.59,
1035
+ "grad_norm": 0.5212237290379841,
1036
+ "learning_rate": 7.611711681456493e-05,
1037
+ "loss": 0.6286,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.59,
1042
+ "grad_norm": 0.5361821341032351,
1043
+ "learning_rate": 7.485333939946926e-05,
1044
+ "loss": 0.6436,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.6,
1049
+ "grad_norm": 0.5328445664549779,
1050
+ "learning_rate": 7.359383505263431e-05,
1051
+ "loss": 0.6805,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.6,
1056
+ "grad_norm": 0.5169478911375548,
1057
+ "learning_rate": 7.233881779643594e-05,
1058
+ "loss": 0.6351,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.61,
1063
+ "grad_norm": 0.4942190213678014,
1064
+ "learning_rate": 7.108850089077735e-05,
1065
+ "loss": 0.6645,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.61,
1070
+ "grad_norm": 0.4777490402143269,
1071
+ "learning_rate": 6.98430967968505e-05,
1072
+ "loss": 0.6646,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.61,
1077
+ "grad_norm": 0.5203792217543509,
1078
+ "learning_rate": 6.86028171410335e-05,
1079
+ "loss": 0.6264,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.62,
1084
+ "grad_norm": 0.5295673373178881,
1085
+ "learning_rate": 6.736787267892991e-05,
1086
+ "loss": 0.6574,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.62,
1091
+ "grad_norm": 0.5054007800089361,
1092
+ "learning_rate": 6.613847325955578e-05,
1093
+ "loss": 0.6463,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.63,
1098
+ "grad_norm": 0.5328764157075438,
1099
+ "learning_rate": 6.491482778968104e-05,
1100
+ "loss": 0.6542,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.63,
1105
+ "grad_norm": 0.518388232442327,
1106
+ "learning_rate": 6.369714419833056e-05,
1107
+ "loss": 0.6266,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.63,
1112
+ "grad_norm": 0.6119309470927382,
1113
+ "learning_rate": 6.248562940145195e-05,
1114
+ "loss": 0.6336,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.64,
1119
+ "grad_norm": 0.4963434899391007,
1120
+ "learning_rate": 6.128048926675494e-05,
1121
+ "loss": 0.6718,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.64,
1126
+ "grad_norm": 0.5095621401572632,
1127
+ "learning_rate": 6.008192857872923e-05,
1128
+ "loss": 0.637,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.65,
1133
+ "grad_norm": 0.5093440110600602,
1134
+ "learning_rate": 5.889015100384636e-05,
1135
+ "loss": 0.6307,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.65,
1140
+ "grad_norm": 0.5082532966773227,
1141
+ "learning_rate": 5.770535905595138e-05,
1142
+ "loss": 0.6382,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.65,
1147
+ "grad_norm": 0.5305244284181049,
1148
+ "learning_rate": 5.6527754061850554e-05,
1149
+ "loss": 0.6424,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.66,
1154
+ "grad_norm": 0.5234971513196092,
1155
+ "learning_rate": 5.5357536127100904e-05,
1156
+ "loss": 0.6485,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.66,
1161
+ "grad_norm": 0.5035050904882836,
1162
+ "learning_rate": 5.419490410200675e-05,
1163
+ "loss": 0.6037,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.67,
1168
+ "grad_norm": 0.4979993303718048,
1169
+ "learning_rate": 5.304005554783015e-05,
1170
+ "loss": 0.6394,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.67,
1175
+ "grad_norm": 0.4822032608918998,
1176
+ "learning_rate": 5.1893186703220165e-05,
1177
+ "loss": 0.6107,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.67,
1182
+ "grad_norm": 0.47831076024478025,
1183
+ "learning_rate": 5.0754492450866607e-05,
1184
+ "loss": 0.6171,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.68,
1189
+ "grad_norm": 0.5217479864900989,
1190
+ "learning_rate": 4.9624166284384656e-05,
1191
+ "loss": 0.6039,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.68,
1196
+ "grad_norm": 0.4966800853562241,
1197
+ "learning_rate": 4.850240027543509e-05,
1198
+ "loss": 0.6399,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.69,
1203
+ "grad_norm": 0.48803795748690887,
1204
+ "learning_rate": 4.738938504108659e-05,
1205
+ "loss": 0.6182,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.69,
1210
+ "grad_norm": 0.5080270857045189,
1211
+ "learning_rate": 4.628530971142471e-05,
1212
+ "loss": 0.6141,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.69,
1217
+ "grad_norm": 0.47913685117930593,
1218
+ "learning_rate": 4.519036189741386e-05,
1219
+ "loss": 0.6386,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.7,
1224
+ "grad_norm": 0.5026651678612354,
1225
+ "learning_rate": 4.410472765901755e-05,
1226
+ "loss": 0.6185,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.7,
1231
+ "grad_norm": 0.5224312932610757,
1232
+ "learning_rate": 4.302859147358168e-05,
1233
+ "loss": 0.5824,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.71,
1238
+ "grad_norm": 0.5178862834267116,
1239
+ "learning_rate": 4.196213620448723e-05,
1240
+ "loss": 0.6329,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.71,
1245
+ "grad_norm": 0.5323664753651522,
1246
+ "learning_rate": 4.0905543070077036e-05,
1247
+ "loss": 0.6317,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.71,
1252
+ "grad_norm": 0.5216091278689122,
1253
+ "learning_rate": 3.985899161286205e-05,
1254
+ "loss": 0.6487,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.72,
1259
+ "grad_norm": 0.4968974338551305,
1260
+ "learning_rate": 3.882265966901257e-05,
1261
+ "loss": 0.6692,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.72,
1266
+ "grad_norm": 0.4904223105734582,
1267
+ "learning_rate": 3.7796723338138995e-05,
1268
+ "loss": 0.5781,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.73,
1273
+ "grad_norm": 0.47447489519607455,
1274
+ "learning_rate": 3.6781356953368284e-05,
1275
+ "loss": 0.6254,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.73,
1280
+ "grad_norm": 0.5197591426247571,
1281
+ "learning_rate": 3.5776733051719936e-05,
1282
+ "loss": 0.6023,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.73,
1287
+ "grad_norm": 0.49832288681418657,
1288
+ "learning_rate": 3.47830223447877e-05,
1289
+ "loss": 0.6551,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.74,
1294
+ "grad_norm": 0.5129531748899837,
1295
+ "learning_rate": 3.3800393689731146e-05,
1296
+ "loss": 0.6196,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.74,
1301
+ "grad_norm": 0.5036518056972021,
1302
+ "learning_rate": 3.28290140605825e-05,
1303
+ "loss": 0.6175,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.75,
1308
+ "grad_norm": 0.480187816135646,
1309
+ "learning_rate": 3.186904851987351e-05,
1310
+ "loss": 0.5996,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.75,
1315
+ "grad_norm": 0.5242700195547425,
1316
+ "learning_rate": 3.092066019058689e-05,
1317
+ "loss": 0.61,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.76,
1322
+ "grad_norm": 0.5152846503044708,
1323
+ "learning_rate": 2.998401022843761e-05,
1324
+ "loss": 0.6404,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.76,
1329
+ "grad_norm": 0.513298219609548,
1330
+ "learning_rate": 2.9059257794488424e-05,
1331
+ "loss": 0.557,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.76,
1336
+ "grad_norm": 0.5021252812027022,
1337
+ "learning_rate": 2.8146560028104153e-05,
1338
+ "loss": 0.6634,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.77,
1343
+ "grad_norm": 0.519800671516665,
1344
+ "learning_rate": 2.724607202024969e-05,
1345
+ "loss": 0.6121,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.77,
1350
+ "grad_norm": 0.5385204988477328,
1351
+ "learning_rate": 2.6357946787136113e-05,
1352
+ "loss": 0.6334,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.78,
1357
+ "grad_norm": 0.4878184839311098,
1358
+ "learning_rate": 2.548233524421911e-05,
1359
+ "loss": 0.6267,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.78,
1364
+ "grad_norm": 0.5220934509633983,
1365
+ "learning_rate": 2.461938618055478e-05,
1366
+ "loss": 0.6391,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.78,
1371
+ "grad_norm": 0.49114273229478017,
1372
+ "learning_rate": 2.3769246233516242e-05,
1373
+ "loss": 0.5895,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.79,
1378
+ "grad_norm": 0.4886291762205353,
1379
+ "learning_rate": 2.2932059863876365e-05,
1380
+ "loss": 0.6325,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.79,
1385
+ "grad_norm": 0.4939232885896318,
1386
+ "learning_rate": 2.2107969331260048e-05,
1387
+ "loss": 0.6165,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.8,
1392
+ "grad_norm": 0.5320372697561206,
1393
+ "learning_rate": 2.1297114669970618e-05,
1394
+ "loss": 0.585,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.8,
1399
+ "grad_norm": 0.4897381232694001,
1400
+ "learning_rate": 2.049963366519446e-05,
1401
+ "loss": 0.6132,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.8,
1406
+ "grad_norm": 0.5063086712780054,
1407
+ "learning_rate": 1.971566182958765e-05,
1408
+ "loss": 0.5857,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.81,
1413
+ "grad_norm": 0.49709180074211373,
1414
+ "learning_rate": 1.8945332380248913e-05,
1415
+ "loss": 0.5934,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.81,
1420
+ "grad_norm": 0.5013514907900145,
1421
+ "learning_rate": 1.8188776216082603e-05,
1422
+ "loss": 0.6079,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.82,
1427
+ "grad_norm": 0.4846234378658167,
1428
+ "learning_rate": 1.7446121895555555e-05,
1429
+ "loss": 0.6238,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.82,
1434
+ "grad_norm": 0.5159176854303504,
1435
+ "learning_rate": 1.6717495614851652e-05,
1436
+ "loss": 0.618,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.82,
1441
+ "grad_norm": 0.48388369881041865,
1442
+ "learning_rate": 1.6003021186427893e-05,
1443
+ "loss": 0.6115,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.83,
1448
+ "grad_norm": 0.4972352579200309,
1449
+ "learning_rate": 1.5302820017975394e-05,
1450
+ "loss": 0.6129,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.83,
1455
+ "grad_norm": 0.48184028854019717,
1456
+ "learning_rate": 1.4617011091789135e-05,
1457
+ "loss": 0.6016,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.84,
1462
+ "grad_norm": 0.4693368878966723,
1463
+ "learning_rate": 1.3945710944549706e-05,
1464
+ "loss": 0.6055,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.84,
1469
+ "grad_norm": 0.49328037858750934,
1470
+ "learning_rate": 1.3289033647520877e-05,
1471
+ "loss": 0.5841,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.84,
1476
+ "grad_norm": 0.4887185175626592,
1477
+ "learning_rate": 1.2647090787165694e-05,
1478
+ "loss": 0.6118,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.85,
1483
+ "grad_norm": 0.5275529498494832,
1484
+ "learning_rate": 1.2019991446185309e-05,
1485
+ "loss": 0.6056,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.85,
1490
+ "grad_norm": 0.5139820604569797,
1491
+ "learning_rate": 1.1407842184982786e-05,
1492
+ "loss": 0.6033,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.86,
1497
+ "grad_norm": 0.5018443059475605,
1498
+ "learning_rate": 1.0810747023555878e-05,
1499
+ "loss": 0.5949,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.86,
1504
+ "grad_norm": 0.48214911033187263,
1505
+ "learning_rate": 1.0228807423821263e-05,
1506
+ "loss": 0.5889,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.86,
1511
+ "grad_norm": 0.48428681987465205,
1512
+ "learning_rate": 9.662122272373575e-06,
1513
+ "loss": 0.5819,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.87,
1518
+ "grad_norm": 0.528477861467508,
1519
+ "learning_rate": 9.110787863682002e-06,
1520
+ "loss": 0.5819,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.87,
1525
+ "grad_norm": 0.542081152492008,
1526
+ "learning_rate": 8.574897883727384e-06,
1527
+ "loss": 0.6237,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.88,
1532
+ "grad_norm": 0.5087137996746921,
1533
+ "learning_rate": 8.054543394082504e-06,
1534
+ "loss": 0.6057,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.88,
1539
+ "grad_norm": 0.504565281502016,
1540
+ "learning_rate": 7.5498128164383955e-06,
1541
+ "loss": 0.5934,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.88,
1546
+ "grad_norm": 0.4973612377357542,
1547
+ "learning_rate": 7.0607919175791796e-06,
1548
+ "loss": 0.6008,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.89,
1553
+ "grad_norm": 0.4569327819305099,
1554
+ "learning_rate": 6.587563794808127e-06,
1555
+ "loss": 0.6257,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.89,
1560
+ "grad_norm": 0.5013818574659203,
1561
+ "learning_rate": 6.130208861827202e-06,
1562
+ "loss": 0.6111,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.9,
1567
+ "grad_norm": 0.5396029754257269,
1568
+ "learning_rate": 5.688804835072748e-06,
1569
+ "loss": 0.6049,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.9,
1574
+ "grad_norm": 0.4941288037270458,
1575
+ "learning_rate": 5.263426720509468e-06,
1576
+ "loss": 0.5498,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.9,
1581
+ "grad_norm": 0.5221213240498462,
1582
+ "learning_rate": 4.8541468008849285e-06,
1583
+ "loss": 0.5939,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.91,
1588
+ "grad_norm": 0.5148521707210466,
1589
+ "learning_rate": 4.461034623446847e-06,
1590
+ "loss": 0.5773,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.91,
1595
+ "grad_norm": 0.4933400691524689,
1596
+ "learning_rate": 4.084156988125231e-06,
1597
+ "loss": 0.6078,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.92,
1602
+ "grad_norm": 0.4882090112322451,
1603
+ "learning_rate": 3.723577936181366e-06,
1604
+ "loss": 0.6044,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.92,
1609
+ "grad_norm": 0.4899230526737377,
1610
+ "learning_rate": 3.3793587393255e-06,
1611
+ "loss": 0.5841,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.92,
1616
+ "grad_norm": 0.48341263558623804,
1617
+ "learning_rate": 3.0515578893052344e-06,
1618
+ "loss": 0.5636,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.93,
1623
+ "grad_norm": 0.45580749261782566,
1624
+ "learning_rate": 2.7402310879662497e-06,
1625
+ "loss": 0.6148,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.93,
1630
+ "grad_norm": 0.5090083434022111,
1631
+ "learning_rate": 2.44543123778711e-06,
1632
+ "loss": 0.6169,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.94,
1637
+ "grad_norm": 0.4909526042662716,
1638
+ "learning_rate": 2.167208432889789e-06,
1639
+ "loss": 0.61,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.94,
1644
+ "grad_norm": 0.4915614072461919,
1645
+ "learning_rate": 1.9056099505273427e-06,
1646
+ "loss": 0.5589,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.94,
1651
+ "grad_norm": 0.4967849394301577,
1652
+ "learning_rate": 1.6606802430503166e-06,
1653
+ "loss": 0.6148,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.95,
1658
+ "grad_norm": 0.49008026008002525,
1659
+ "learning_rate": 1.43246093035313e-06,
1660
+ "loss": 0.5432,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.95,
1665
+ "grad_norm": 0.47910645199801954,
1666
+ "learning_rate": 1.2209907928017795e-06,
1667
+ "loss": 0.6306,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.96,
1672
+ "grad_norm": 0.47354206064914267,
1673
+ "learning_rate": 1.0263057646440199e-06,
1674
+ "loss": 0.6149,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.96,
1679
+ "grad_norm": 0.48080154743346765,
1680
+ "learning_rate": 8.484389279032834e-07,
1681
+ "loss": 0.6118,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.96,
1686
+ "grad_norm": 0.5000613082596329,
1687
+ "learning_rate": 6.874205067571083e-07,
1688
+ "loss": 0.6344,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.97,
1693
+ "grad_norm": 0.5161518232153531,
1694
+ "learning_rate": 5.432778624013257e-07,
1695
+ "loss": 0.6341,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.97,
1700
+ "grad_norm": 0.5360018159046693,
1701
+ "learning_rate": 4.1603548840062345e-07,
1702
+ "loss": 0.6191,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.98,
1707
+ "grad_norm": 0.5403903928320288,
1708
+ "learning_rate": 3.0571500652651907e-07,
1709
+ "loss": 0.6069,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.98,
1714
+ "grad_norm": 0.480958206210995,
1715
+ "learning_rate": 2.1233516308323264e-07,
1716
+ "loss": 0.6041,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.98,
1721
+ "grad_norm": 0.46018947114009656,
1722
+ "learning_rate": 1.359118257221903e-07,
1723
+ "loss": 0.5822,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.99,
1728
+ "grad_norm": 0.5297015912922861,
1729
+ "learning_rate": 7.645798074572552e-08,
1730
+ "loss": 0.6451,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.99,
1735
+ "grad_norm": 0.4867081187971182,
1736
+ "learning_rate": 3.3983730900377655e-08,
1737
+ "loss": 0.5977,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.0,
1742
+ "grad_norm": 0.5439247812896818,
1743
+ "learning_rate": 8.496293660120724e-09,
1744
+ "loss": 0.659,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.0,
1749
+ "grad_norm": 0.5183819113313861,
1750
+ "learning_rate": 0.0,
1751
+ "loss": 0.5523,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.0,
1756
+ "step": 249,
1757
+ "total_flos": 37334311403520.0,
1758
+ "train_loss": 0.6850855740677401,
1759
+ "train_runtime": 4182.855,
1760
+ "train_samples_per_second": 3.802,
1761
+ "train_steps_per_second": 0.06
1762
+ }
1763
+ ],
1764
+ "logging_steps": 1.0,
1765
+ "max_steps": 249,
1766
+ "num_input_tokens_seen": 0,
1767
+ "num_train_epochs": 1,
1768
+ "save_steps": 50,
1769
+ "total_flos": 37334311403520.0,
1770
+ "train_batch_size": 16,
1771
+ "trial_name": null,
1772
+ "trial_params": null
1773
+ }