sizhkhy commited on
Commit
abdeb96
·
verified ·
1 Parent(s): cb0bd09
README.md CHANGED
@@ -1,25 +1,25 @@
1
  ---
2
  library_name: peft
3
  license: other
4
- base_model: unsloth/Llama-3.2-3B-Instruct
5
  tags:
6
  - llama-factory
7
  - lora
8
  - unsloth
9
  - generated_from_trainer
10
  model-index:
11
- - name: llm3br256
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # llm3br256
19
 
20
  This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the brasingh_publicis_f5f dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0205
23
 
24
  ## Model description
25
 
@@ -40,101 +40,17 @@ More information needed
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0001
42
  - train_batch_size: 4
43
- - eval_batch_size: 4
44
  - seed: 42
45
  - gradient_accumulation_steps: 8
46
  - total_train_batch_size: 32
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: cosine
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 5.0
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:------:|:----:|:---------------:|
56
- | 0.1038 | 0.0606 | 5 | 0.0979 |
57
- | 0.0759 | 0.1212 | 10 | 0.0765 |
58
- | 0.069 | 0.1818 | 15 | 0.0683 |
59
- | 0.0729 | 0.2424 | 20 | 0.0620 |
60
- | 0.0545 | 0.3030 | 25 | 0.0571 |
61
- | 0.0589 | 0.3636 | 30 | 0.0528 |
62
- | 0.0461 | 0.4242 | 35 | 0.0501 |
63
- | 0.0522 | 0.4848 | 40 | 0.0493 |
64
- | 0.052 | 0.5455 | 45 | 0.0483 |
65
- | 0.0459 | 0.6061 | 50 | 0.0458 |
66
- | 0.0363 | 0.6667 | 55 | 0.0434 |
67
- | 0.0553 | 0.7273 | 60 | 0.0418 |
68
- | 0.0444 | 0.7879 | 65 | 0.0403 |
69
- | 0.0469 | 0.8485 | 70 | 0.0397 |
70
- | 0.0417 | 0.9091 | 75 | 0.0386 |
71
- | 0.0388 | 0.9697 | 80 | 0.0372 |
72
- | 0.0309 | 1.0303 | 85 | 0.0358 |
73
- | 0.0487 | 1.0909 | 90 | 0.0354 |
74
- | 0.0348 | 1.1515 | 95 | 0.0340 |
75
- | 0.0308 | 1.2121 | 100 | 0.0334 |
76
- | 0.0318 | 1.2727 | 105 | 0.0330 |
77
- | 0.028 | 1.3333 | 110 | 0.0322 |
78
- | 0.0311 | 1.3939 | 115 | 0.0321 |
79
- | 0.0382 | 1.4545 | 120 | 0.0315 |
80
- | 0.0316 | 1.5152 | 125 | 0.0304 |
81
- | 0.0278 | 1.5758 | 130 | 0.0299 |
82
- | 0.0285 | 1.6364 | 135 | 0.0292 |
83
- | 0.0257 | 1.6970 | 140 | 0.0285 |
84
- | 0.0244 | 1.7576 | 145 | 0.0281 |
85
- | 0.0256 | 1.8182 | 150 | 0.0278 |
86
- | 0.0338 | 1.8788 | 155 | 0.0270 |
87
- | 0.0309 | 1.9394 | 160 | 0.0262 |
88
- | 0.0378 | 2.0 | 165 | 0.0261 |
89
- | 0.0275 | 2.0606 | 170 | 0.0263 |
90
- | 0.0225 | 2.1212 | 175 | 0.0259 |
91
- | 0.0232 | 2.1818 | 180 | 0.0256 |
92
- | 0.0193 | 2.2424 | 185 | 0.0255 |
93
- | 0.0251 | 2.3030 | 190 | 0.0253 |
94
- | 0.0228 | 2.3636 | 195 | 0.0249 |
95
- | 0.0195 | 2.4242 | 200 | 0.0249 |
96
- | 0.0219 | 2.4848 | 205 | 0.0241 |
97
- | 0.0184 | 2.5455 | 210 | 0.0238 |
98
- | 0.0199 | 2.6061 | 215 | 0.0236 |
99
- | 0.023 | 2.6667 | 220 | 0.0232 |
100
- | 0.0227 | 2.7273 | 225 | 0.0234 |
101
- | 0.0206 | 2.7879 | 230 | 0.0230 |
102
- | 0.0217 | 2.8485 | 235 | 0.0225 |
103
- | 0.0186 | 2.9091 | 240 | 0.0224 |
104
- | 0.0201 | 2.9697 | 245 | 0.0220 |
105
- | 0.0147 | 3.0303 | 250 | 0.0220 |
106
- | 0.0142 | 3.0909 | 255 | 0.0226 |
107
- | 0.0149 | 3.1515 | 260 | 0.0218 |
108
- | 0.0151 | 3.2121 | 265 | 0.0215 |
109
- | 0.0174 | 3.2727 | 270 | 0.0217 |
110
- | 0.0172 | 3.3333 | 275 | 0.0213 |
111
- | 0.017 | 3.3939 | 280 | 0.0211 |
112
- | 0.0223 | 3.4545 | 285 | 0.0212 |
113
- | 0.0144 | 3.5152 | 290 | 0.0211 |
114
- | 0.0125 | 3.5758 | 295 | 0.0208 |
115
- | 0.0163 | 3.6364 | 300 | 0.0207 |
116
- | 0.015 | 3.6970 | 305 | 0.0207 |
117
- | 0.0154 | 3.7576 | 310 | 0.0206 |
118
- | 0.0186 | 3.8182 | 315 | 0.0203 |
119
- | 0.0135 | 3.8788 | 320 | 0.0202 |
120
- | 0.0159 | 3.9394 | 325 | 0.0201 |
121
- | 0.0211 | 4.0 | 330 | 0.0200 |
122
- | 0.0134 | 4.0606 | 335 | 0.0202 |
123
- | 0.0113 | 4.1212 | 340 | 0.0206 |
124
- | 0.0117 | 4.1818 | 345 | 0.0208 |
125
- | 0.0108 | 4.2424 | 350 | 0.0209 |
126
- | 0.012 | 4.3030 | 355 | 0.0207 |
127
- | 0.0111 | 4.3636 | 360 | 0.0206 |
128
- | 0.0118 | 4.4242 | 365 | 0.0205 |
129
- | 0.0099 | 4.4848 | 370 | 0.0206 |
130
- | 0.0118 | 4.5455 | 375 | 0.0206 |
131
- | 0.0119 | 4.6061 | 380 | 0.0206 |
132
- | 0.0114 | 4.6667 | 385 | 0.0206 |
133
- | 0.0109 | 4.7273 | 390 | 0.0206 |
134
- | 0.0124 | 4.7879 | 395 | 0.0205 |
135
- | 0.0111 | 4.8485 | 400 | 0.0206 |
136
- | 0.012 | 4.9091 | 405 | 0.0206 |
137
- | 0.0104 | 4.9697 | 410 | 0.0205 |
138
 
139
 
140
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
  license: other
4
+ base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
5
  tags:
6
  - llama-factory
7
  - lora
8
  - unsloth
9
  - generated_from_trainer
10
  model-index:
11
+ - name: nova_v1.5
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ # nova_v1.5
19
 
20
  This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the brasingh_publicis_f5f dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0421
23
 
24
  ## Model description
25
 
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 0.0001
42
  - train_batch_size: 4
43
+ - eval_batch_size: 48
44
  - seed: 42
45
  - gradient_accumulation_steps: 8
46
  - total_train_batch_size: 32
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: cosine
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 1
51
 
52
  ### Training results
53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,11 +20,11 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "gate_proj",
24
- "up_proj",
25
  "o_proj",
26
- "q_proj",
 
27
  "k_proj",
 
28
  "v_proj",
29
  "down_proj"
30
  ],
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "o_proj",
24
+ "up_proj",
25
+ "gate_proj",
26
  "k_proj",
27
+ "q_proj",
28
  "v_proj",
29
  "down_proj"
30
  ],
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d9e21e8d743b135412f1e3ec2c11e1ffaf214421bd6cbe51c4d8c4f604bffaa
3
  size 1556140392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4df28160aa2cacaeceebeac4b0ff96d4e2e2078aa9e6967cff0bfbe22f87ba
3
  size 1556140392
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "epoch": 4.96969696969697,
3
- "eval_loss": 0.020535212010145187,
4
- "eval_runtime": 6.2115,
5
- "eval_samples_per_second": 8.05,
6
- "eval_steps_per_second": 2.093,
7
- "total_flos": 6.27193584892674e+17,
8
- "train_loss": 0.027697906577278202,
9
- "train_runtime": 5078.5288,
10
- "train_samples_per_second": 2.598,
11
- "train_steps_per_second": 0.081
12
  }
 
1
  {
2
+ "epoch": 0.6956521739130435,
3
+ "eval_loss": 0.04214267060160637,
4
+ "eval_runtime": 3.45,
5
+ "eval_samples_per_second": 2.899,
6
+ "eval_steps_per_second": 0.29,
7
+ "total_flos": 3880733380509696.0,
8
+ "train_loss": 0.029286871664226055,
9
+ "train_runtime": 89.5279,
10
+ "train_samples_per_second": 1.005,
11
+ "train_steps_per_second": 0.022
12
  }
checkpoint-2/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
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-2/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
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": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 256,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "up_proj",
25
+ "gate_proj",
26
+ "k_proj",
27
+ "q_proj",
28
+ "v_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-2/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4df28160aa2cacaeceebeac4b0ff96d4e2e2078aa9e6967cff0bfbe22f87ba
3
+ size 1556140392
checkpoint-2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53fb6d10cbaa854c82563ee8ed18f38a15c9dea553f5fcc0fe2e41f2a5ca3cec
3
+ size 3112505578
checkpoint-2/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e773b5b1002096a721bb04ea3f59bac7a8cfca1a8a8e35452232b57d0216bf2
3
+ size 14308
checkpoint-2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a5aa6cab52bdf0942e6b057dccc7ca9a8b45ae6da834a9bf34a445647b8991
3
+ size 1064
checkpoint-2/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
checkpoint-2/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-2/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-2/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6956521739130435,
5
+ "eval_steps": 50,
6
+ "global_step": 2,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.34782608695652173,
13
+ "grad_norm": 0.07414738088846207,
14
+ "learning_rate": 0.0001,
15
+ "loss": 0.0288,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.6956521739130435,
20
+ "grad_norm": 0.06888309866189957,
21
+ "learning_rate": 0.0,
22
+ "loss": 0.0298,
23
+ "step": 2
24
+ }
25
+ ],
26
+ "logging_steps": 1,
27
+ "max_steps": 2,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 1,
30
+ "save_steps": 100,
31
+ "stateful_callbacks": {
32
+ "EarlyStoppingCallback": {
33
+ "args": {
34
+ "early_stopping_patience": 5,
35
+ "early_stopping_threshold": 0.0
36
+ },
37
+ "attributes": {
38
+ "early_stopping_patience_counter": 0
39
+ }
40
+ },
41
+ "TrainerControl": {
42
+ "args": {
43
+ "should_epoch_stop": false,
44
+ "should_evaluate": false,
45
+ "should_log": false,
46
+ "should_save": true,
47
+ "should_training_stop": true
48
+ },
49
+ "attributes": {}
50
+ }
51
+ },
52
+ "total_flos": 3880733380509696.0,
53
+ "train_batch_size": 4,
54
+ "trial_name": null,
55
+ "trial_params": null
56
+ }
checkpoint-2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b07d6117d888dc51d19e06cb48a53cb20d5edb3faef27e7da7fca291d4a00d
3
+ size 5496
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 4.96969696969697,
3
- "eval_loss": 0.020535212010145187,
4
- "eval_runtime": 6.2115,
5
- "eval_samples_per_second": 8.05,
6
- "eval_steps_per_second": 2.093
7
  }
 
1
  {
2
+ "epoch": 0.6956521739130435,
3
+ "eval_loss": 0.04214267060160637,
4
+ "eval_runtime": 3.45,
5
+ "eval_samples_per_second": 2.899,
6
+ "eval_steps_per_second": 0.29
7
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.96969696969697,
3
- "total_flos": 6.27193584892674e+17,
4
- "train_loss": 0.027697906577278202,
5
- "train_runtime": 5078.5288,
6
- "train_samples_per_second": 2.598,
7
- "train_steps_per_second": 0.081
8
  }
 
1
  {
2
+ "epoch": 0.6956521739130435,
3
+ "total_flos": 3880733380509696.0,
4
+ "train_loss": 0.029286871664226055,
5
+ "train_runtime": 89.5279,
6
+ "train_samples_per_second": 1.005,
7
+ "train_steps_per_second": 0.022
8
  }
trainer_log.jsonl CHANGED
@@ -1,493 +1,3 @@
1
- {"current_steps": 1, "total_steps": 410, "loss": 0.103, "lr": 2.4390243902439027e-06, "epoch": 0.012121212121212121, "percentage": 0.24, "elapsed_time": "0:00:21", "remaining_time": "2:27:24"}
2
- {"current_steps": 2, "total_steps": 410, "loss": 0.11, "lr": 4.8780487804878055e-06, "epoch": 0.024242424242424242, "percentage": 0.49, "elapsed_time": "0:00:39", "remaining_time": "2:15:54"}
3
- {"current_steps": 3, "total_steps": 410, "loss": 0.1104, "lr": 7.317073170731707e-06, "epoch": 0.03636363636363636, "percentage": 0.73, "elapsed_time": "0:00:55", "remaining_time": "2:05:28"}
4
- {"current_steps": 4, "total_steps": 410, "loss": 0.1076, "lr": 9.756097560975611e-06, "epoch": 0.048484848484848485, "percentage": 0.98, "elapsed_time": "0:01:06", "remaining_time": "1:51:59"}
5
- {"current_steps": 5, "total_steps": 410, "loss": 0.1038, "lr": 1.2195121951219513e-05, "epoch": 0.06060606060606061, "percentage": 1.22, "elapsed_time": "0:01:17", "remaining_time": "1:44:23"}
6
- {"current_steps": 5, "total_steps": 410, "eval_loss": 0.09789121896028519, "epoch": 0.06060606060606061, "percentage": 1.22, "elapsed_time": "0:01:25", "remaining_time": "1:55:20"}
7
- {"current_steps": 6, "total_steps": 410, "loss": 0.0995, "lr": 1.4634146341463415e-05, "epoch": 0.07272727272727272, "percentage": 1.46, "elapsed_time": "0:01:35", "remaining_time": "1:47:37"}
8
- {"current_steps": 7, "total_steps": 410, "loss": 0.0833, "lr": 1.707317073170732e-05, "epoch": 0.08484848484848485, "percentage": 1.71, "elapsed_time": "0:01:47", "remaining_time": "1:42:40"}
9
- {"current_steps": 8, "total_steps": 410, "loss": 0.0756, "lr": 1.9512195121951222e-05, "epoch": 0.09696969696969697, "percentage": 1.95, "elapsed_time": "0:01:58", "remaining_time": "1:39:19"}
10
- {"current_steps": 9, "total_steps": 410, "loss": 0.0681, "lr": 2.1951219512195124e-05, "epoch": 0.10909090909090909, "percentage": 2.2, "elapsed_time": "0:02:08", "remaining_time": "1:35:14"}
11
- {"current_steps": 10, "total_steps": 410, "loss": 0.0759, "lr": 2.4390243902439026e-05, "epoch": 0.12121212121212122, "percentage": 2.44, "elapsed_time": "0:02:18", "remaining_time": "1:32:15"}
12
- {"current_steps": 10, "total_steps": 410, "eval_loss": 0.07647334039211273, "epoch": 0.12121212121212122, "percentage": 2.44, "elapsed_time": "0:02:24", "remaining_time": "1:36:24"}
13
- {"current_steps": 11, "total_steps": 410, "loss": 0.0757, "lr": 2.682926829268293e-05, "epoch": 0.13333333333333333, "percentage": 2.68, "elapsed_time": "0:02:35", "remaining_time": "1:33:43"}
14
- {"current_steps": 12, "total_steps": 410, "loss": 0.0733, "lr": 2.926829268292683e-05, "epoch": 0.14545454545454545, "percentage": 2.93, "elapsed_time": "0:02:45", "remaining_time": "1:31:37"}
15
- {"current_steps": 13, "total_steps": 410, "loss": 0.0751, "lr": 3.170731707317073e-05, "epoch": 0.15757575757575756, "percentage": 3.17, "elapsed_time": "0:02:57", "remaining_time": "1:30:10"}
16
- {"current_steps": 14, "total_steps": 410, "loss": 0.0784, "lr": 3.414634146341464e-05, "epoch": 0.1696969696969697, "percentage": 3.41, "elapsed_time": "0:03:08", "remaining_time": "1:28:59"}
17
- {"current_steps": 15, "total_steps": 410, "loss": 0.069, "lr": 3.6585365853658535e-05, "epoch": 0.18181818181818182, "percentage": 3.66, "elapsed_time": "0:03:19", "remaining_time": "1:27:29"}
18
- {"current_steps": 15, "total_steps": 410, "eval_loss": 0.06831522285938263, "epoch": 0.18181818181818182, "percentage": 3.66, "elapsed_time": "0:03:25", "remaining_time": "1:30:12"}
19
- {"current_steps": 16, "total_steps": 410, "loss": 0.0691, "lr": 3.9024390243902444e-05, "epoch": 0.19393939393939394, "percentage": 3.9, "elapsed_time": "0:03:37", "remaining_time": "1:29:16"}
20
- {"current_steps": 17, "total_steps": 410, "loss": 0.0813, "lr": 4.146341463414634e-05, "epoch": 0.20606060606060606, "percentage": 4.15, "elapsed_time": "0:03:47", "remaining_time": "1:27:40"}
21
- {"current_steps": 18, "total_steps": 410, "loss": 0.065, "lr": 4.390243902439025e-05, "epoch": 0.21818181818181817, "percentage": 4.39, "elapsed_time": "0:03:57", "remaining_time": "1:26:13"}
22
- {"current_steps": 19, "total_steps": 410, "loss": 0.0617, "lr": 4.634146341463415e-05, "epoch": 0.23030303030303031, "percentage": 4.63, "elapsed_time": "0:04:08", "remaining_time": "1:25:15"}
23
- {"current_steps": 20, "total_steps": 410, "loss": 0.0729, "lr": 4.878048780487805e-05, "epoch": 0.24242424242424243, "percentage": 4.88, "elapsed_time": "0:04:19", "remaining_time": "1:24:16"}
24
- {"current_steps": 20, "total_steps": 410, "eval_loss": 0.062009546905756, "epoch": 0.24242424242424243, "percentage": 4.88, "elapsed_time": "0:04:25", "remaining_time": "1:26:18"}
25
- {"current_steps": 21, "total_steps": 410, "loss": 0.0602, "lr": 5.121951219512195e-05, "epoch": 0.2545454545454545, "percentage": 5.12, "elapsed_time": "0:04:35", "remaining_time": "1:25:06"}
26
- {"current_steps": 22, "total_steps": 410, "loss": 0.0772, "lr": 5.365853658536586e-05, "epoch": 0.26666666666666666, "percentage": 5.37, "elapsed_time": "0:04:49", "remaining_time": "1:25:14"}
27
- {"current_steps": 23, "total_steps": 410, "loss": 0.0584, "lr": 5.6097560975609764e-05, "epoch": 0.2787878787878788, "percentage": 5.61, "elapsed_time": "0:05:02", "remaining_time": "1:24:58"}
28
- {"current_steps": 24, "total_steps": 410, "loss": 0.0568, "lr": 5.853658536585366e-05, "epoch": 0.2909090909090909, "percentage": 5.85, "elapsed_time": "0:05:13", "remaining_time": "1:24:07"}
29
- {"current_steps": 25, "total_steps": 410, "loss": 0.0545, "lr": 6.097560975609756e-05, "epoch": 0.30303030303030304, "percentage": 6.1, "elapsed_time": "0:05:26", "remaining_time": "1:23:51"}
30
- {"current_steps": 25, "total_steps": 410, "eval_loss": 0.057142239063978195, "epoch": 0.30303030303030304, "percentage": 6.1, "elapsed_time": "0:05:32", "remaining_time": "1:25:27"}
31
- {"current_steps": 26, "total_steps": 410, "loss": 0.0591, "lr": 6.341463414634146e-05, "epoch": 0.3151515151515151, "percentage": 6.34, "elapsed_time": "0:05:44", "remaining_time": "1:24:54"}
32
- {"current_steps": 27, "total_steps": 410, "loss": 0.0836, "lr": 6.585365853658538e-05, "epoch": 0.32727272727272727, "percentage": 6.59, "elapsed_time": "0:05:55", "remaining_time": "1:23:56"}
33
- {"current_steps": 28, "total_steps": 410, "loss": 0.0574, "lr": 6.829268292682928e-05, "epoch": 0.3393939393939394, "percentage": 6.83, "elapsed_time": "0:06:06", "remaining_time": "1:23:15"}
34
- {"current_steps": 29, "total_steps": 410, "loss": 0.0506, "lr": 7.073170731707317e-05, "epoch": 0.3515151515151515, "percentage": 7.07, "elapsed_time": "0:06:19", "remaining_time": "1:23:09"}
35
- {"current_steps": 30, "total_steps": 410, "loss": 0.0589, "lr": 7.317073170731707e-05, "epoch": 0.36363636363636365, "percentage": 7.32, "elapsed_time": "0:06:31", "remaining_time": "1:22:33"}
36
- {"current_steps": 30, "total_steps": 410, "eval_loss": 0.05275052413344383, "epoch": 0.36363636363636365, "percentage": 7.32, "elapsed_time": "0:06:37", "remaining_time": "1:23:51"}
37
- {"current_steps": 31, "total_steps": 410, "loss": 0.0536, "lr": 7.560975609756099e-05, "epoch": 0.37575757575757573, "percentage": 7.56, "elapsed_time": "0:06:45", "remaining_time": "1:22:41"}
38
- {"current_steps": 32, "total_steps": 410, "loss": 0.0454, "lr": 7.804878048780489e-05, "epoch": 0.3878787878787879, "percentage": 7.8, "elapsed_time": "0:06:56", "remaining_time": "1:22:00"}
39
- {"current_steps": 33, "total_steps": 410, "loss": 0.0727, "lr": 8.048780487804879e-05, "epoch": 0.4, "percentage": 8.05, "elapsed_time": "0:07:07", "remaining_time": "1:21:23"}
40
- {"current_steps": 34, "total_steps": 410, "loss": 0.0557, "lr": 8.292682926829268e-05, "epoch": 0.4121212121212121, "percentage": 8.29, "elapsed_time": "0:07:19", "remaining_time": "1:20:57"}
41
- {"current_steps": 35, "total_steps": 410, "loss": 0.0461, "lr": 8.53658536585366e-05, "epoch": 0.42424242424242425, "percentage": 8.54, "elapsed_time": "0:07:30", "remaining_time": "1:20:29"}
42
- {"current_steps": 35, "total_steps": 410, "eval_loss": 0.05005570873618126, "epoch": 0.42424242424242425, "percentage": 8.54, "elapsed_time": "0:07:36", "remaining_time": "1:21:36"}
43
- {"current_steps": 36, "total_steps": 410, "loss": 0.0627, "lr": 8.78048780487805e-05, "epoch": 0.43636363636363634, "percentage": 8.78, "elapsed_time": "0:07:46", "remaining_time": "1:20:42"}
44
- {"current_steps": 37, "total_steps": 410, "loss": 0.0527, "lr": 9.02439024390244e-05, "epoch": 0.4484848484848485, "percentage": 9.02, "elapsed_time": "0:07:57", "remaining_time": "1:20:14"}
45
- {"current_steps": 38, "total_steps": 410, "loss": 0.0509, "lr": 9.26829268292683e-05, "epoch": 0.46060606060606063, "percentage": 9.27, "elapsed_time": "0:08:07", "remaining_time": "1:19:33"}
46
- {"current_steps": 39, "total_steps": 410, "loss": 0.0488, "lr": 9.51219512195122e-05, "epoch": 0.4727272727272727, "percentage": 9.51, "elapsed_time": "0:08:19", "remaining_time": "1:19:15"}
47
- {"current_steps": 40, "total_steps": 410, "loss": 0.0522, "lr": 9.75609756097561e-05, "epoch": 0.48484848484848486, "percentage": 9.76, "elapsed_time": "0:08:30", "remaining_time": "1:18:44"}
48
- {"current_steps": 40, "total_steps": 410, "eval_loss": 0.049276672303676605, "epoch": 0.48484848484848486, "percentage": 9.76, "elapsed_time": "0:08:37", "remaining_time": "1:19:42"}
49
- {"current_steps": 41, "total_steps": 410, "loss": 0.0463, "lr": 0.0001, "epoch": 0.49696969696969695, "percentage": 10.0, "elapsed_time": "0:08:48", "remaining_time": "1:19:18"}
50
- {"current_steps": 42, "total_steps": 410, "loss": 0.0433, "lr": 9.999818789066165e-05, "epoch": 0.509090909090909, "percentage": 10.24, "elapsed_time": "0:08:59", "remaining_time": "1:18:43"}
51
- {"current_steps": 43, "total_steps": 410, "loss": 0.0393, "lr": 9.999275169399614e-05, "epoch": 0.5212121212121212, "percentage": 10.49, "elapsed_time": "0:09:09", "remaining_time": "1:18:08"}
52
- {"current_steps": 44, "total_steps": 410, "loss": 0.044, "lr": 9.998369180404283e-05, "epoch": 0.5333333333333333, "percentage": 10.73, "elapsed_time": "0:09:19", "remaining_time": "1:17:33"}
53
- {"current_steps": 45, "total_steps": 410, "loss": 0.052, "lr": 9.997100887750215e-05, "epoch": 0.5454545454545454, "percentage": 10.98, "elapsed_time": "0:09:30", "remaining_time": "1:17:05"}
54
- {"current_steps": 45, "total_steps": 410, "eval_loss": 0.04825693741440773, "epoch": 0.5454545454545454, "percentage": 10.98, "elapsed_time": "0:09:36", "remaining_time": "1:17:55"}
55
- {"current_steps": 46, "total_steps": 410, "loss": 0.0436, "lr": 9.995470383368808e-05, "epoch": 0.5575757575757576, "percentage": 11.22, "elapsed_time": "0:09:46", "remaining_time": "1:17:24"}
56
- {"current_steps": 47, "total_steps": 410, "loss": 0.0431, "lr": 9.99347778544615e-05, "epoch": 0.5696969696969697, "percentage": 11.46, "elapsed_time": "0:09:57", "remaining_time": "1:16:55"}
57
- {"current_steps": 48, "total_steps": 410, "loss": 0.0526, "lr": 9.991123238414455e-05, "epoch": 0.5818181818181818, "percentage": 11.71, "elapsed_time": "0:10:08", "remaining_time": "1:16:31"}
58
- {"current_steps": 49, "total_steps": 410, "loss": 0.0447, "lr": 9.98840691294159e-05, "epoch": 0.593939393939394, "percentage": 11.95, "elapsed_time": "0:10:19", "remaining_time": "1:16:06"}
59
- {"current_steps": 50, "total_steps": 410, "loss": 0.0459, "lr": 9.985329005918702e-05, "epoch": 0.6060606060606061, "percentage": 12.2, "elapsed_time": "0:10:32", "remaining_time": "1:15:55"}
60
- {"current_steps": 50, "total_steps": 410, "eval_loss": 0.045825447887182236, "epoch": 0.6060606060606061, "percentage": 12.2, "elapsed_time": "0:10:38", "remaining_time": "1:16:39"}
61
- {"current_steps": 51, "total_steps": 410, "loss": 0.0417, "lr": 9.981889740445958e-05, "epoch": 0.6181818181818182, "percentage": 12.44, "elapsed_time": "0:10:55", "remaining_time": "1:16:55"}
62
- {"current_steps": 52, "total_steps": 410, "loss": 0.0446, "lr": 9.978089365816357e-05, "epoch": 0.6303030303030303, "percentage": 12.68, "elapsed_time": "0:11:06", "remaining_time": "1:16:25"}
63
- {"current_steps": 53, "total_steps": 410, "loss": 0.0451, "lr": 9.973928157497674e-05, "epoch": 0.6424242424242425, "percentage": 12.93, "elapsed_time": "0:11:18", "remaining_time": "1:16:07"}
64
- {"current_steps": 54, "total_steps": 410, "loss": 0.0416, "lr": 9.969406417112489e-05, "epoch": 0.6545454545454545, "percentage": 13.17, "elapsed_time": "0:11:27", "remaining_time": "1:15:29"}
65
- {"current_steps": 55, "total_steps": 410, "loss": 0.0363, "lr": 9.964524472416319e-05, "epoch": 0.6666666666666666, "percentage": 13.41, "elapsed_time": "0:11:37", "remaining_time": "1:15:05"}
66
- {"current_steps": 55, "total_steps": 410, "eval_loss": 0.0433911457657814, "epoch": 0.6666666666666666, "percentage": 13.41, "elapsed_time": "0:11:44", "remaining_time": "1:15:45"}
67
- {"current_steps": 56, "total_steps": 410, "loss": 0.0457, "lr": 9.95928267727387e-05, "epoch": 0.6787878787878788, "percentage": 13.66, "elapsed_time": "0:11:54", "remaining_time": "1:15:18"}
68
- {"current_steps": 57, "total_steps": 410, "loss": 0.0367, "lr": 9.953681411633376e-05, "epoch": 0.6909090909090909, "percentage": 13.9, "elapsed_time": "0:12:04", "remaining_time": "1:14:49"}
69
- {"current_steps": 58, "total_steps": 410, "loss": 0.0428, "lr": 9.947721081499068e-05, "epoch": 0.703030303030303, "percentage": 14.15, "elapsed_time": "0:12:16", "remaining_time": "1:14:30"}
70
- {"current_steps": 59, "total_steps": 410, "loss": 0.0456, "lr": 9.941402118901744e-05, "epoch": 0.7151515151515152, "percentage": 14.39, "elapsed_time": "0:12:27", "remaining_time": "1:14:04"}
71
- {"current_steps": 60, "total_steps": 410, "loss": 0.0553, "lr": 9.934724981867446e-05, "epoch": 0.7272727272727273, "percentage": 14.63, "elapsed_time": "0:12:37", "remaining_time": "1:13:37"}
72
- {"current_steps": 60, "total_steps": 410, "eval_loss": 0.04182567819952965, "epoch": 0.7272727272727273, "percentage": 14.63, "elapsed_time": "0:12:43", "remaining_time": "1:14:14"}
73
- {"current_steps": 61, "total_steps": 410, "loss": 0.0443, "lr": 9.927690154384273e-05, "epoch": 0.7393939393939394, "percentage": 14.88, "elapsed_time": "0:12:52", "remaining_time": "1:13:40"}
74
- {"current_steps": 62, "total_steps": 410, "loss": 0.0423, "lr": 9.920298146367286e-05, "epoch": 0.7515151515151515, "percentage": 15.12, "elapsed_time": "0:13:01", "remaining_time": "1:13:07"}
75
- {"current_steps": 63, "total_steps": 410, "loss": 0.0469, "lr": 9.912549493621554e-05, "epoch": 0.7636363636363637, "percentage": 15.37, "elapsed_time": "0:13:12", "remaining_time": "1:12:44"}
76
- {"current_steps": 64, "total_steps": 410, "loss": 0.0428, "lr": 9.904444757803321e-05, "epoch": 0.7757575757575758, "percentage": 15.61, "elapsed_time": "0:13:24", "remaining_time": "1:12:29"}
77
- {"current_steps": 65, "total_steps": 410, "loss": 0.0444, "lr": 9.895984526379281e-05, "epoch": 0.7878787878787878, "percentage": 15.85, "elapsed_time": "0:13:36", "remaining_time": "1:12:16"}
78
- {"current_steps": 65, "total_steps": 410, "eval_loss": 0.0403163880109787, "epoch": 0.7878787878787878, "percentage": 15.85, "elapsed_time": "0:13:43", "remaining_time": "1:12:49"}
79
- {"current_steps": 66, "total_steps": 410, "loss": 0.0389, "lr": 9.887169412584011e-05, "epoch": 0.8, "percentage": 16.1, "elapsed_time": "0:13:55", "remaining_time": "1:12:36"}
80
- {"current_steps": 67, "total_steps": 410, "loss": 0.0397, "lr": 9.878000055375512e-05, "epoch": 0.8121212121212121, "percentage": 16.34, "elapsed_time": "0:14:07", "remaining_time": "1:12:16"}
81
- {"current_steps": 68, "total_steps": 410, "loss": 0.0387, "lr": 9.868477119388896e-05, "epoch": 0.8242424242424242, "percentage": 16.59, "elapsed_time": "0:14:18", "remaining_time": "1:11:55"}
82
- {"current_steps": 69, "total_steps": 410, "loss": 0.0344, "lr": 9.858601294888213e-05, "epoch": 0.8363636363636363, "percentage": 16.83, "elapsed_time": "0:14:29", "remaining_time": "1:11:36"}
83
- {"current_steps": 70, "total_steps": 410, "loss": 0.0469, "lr": 9.848373297716414e-05, "epoch": 0.8484848484848485, "percentage": 17.07, "elapsed_time": "0:14:40", "remaining_time": "1:11:16"}
84
- {"current_steps": 70, "total_steps": 410, "eval_loss": 0.03973233327269554, "epoch": 0.8484848484848485, "percentage": 17.07, "elapsed_time": "0:14:46", "remaining_time": "1:11:46"}
85
- {"current_steps": 71, "total_steps": 410, "loss": 0.0388, "lr": 9.837793869243468e-05, "epoch": 0.8606060606060606, "percentage": 17.32, "elapsed_time": "0:14:55", "remaining_time": "1:11:15"}
86
- {"current_steps": 72, "total_steps": 410, "loss": 0.0415, "lr": 9.82686377631262e-05, "epoch": 0.8727272727272727, "percentage": 17.56, "elapsed_time": "0:15:06", "remaining_time": "1:10:55"}
87
- {"current_steps": 73, "total_steps": 410, "loss": 0.037, "lr": 9.815583811184808e-05, "epoch": 0.8848484848484849, "percentage": 17.8, "elapsed_time": "0:15:16", "remaining_time": "1:10:30"}
88
- {"current_steps": 74, "total_steps": 410, "loss": 0.0408, "lr": 9.803954791481239e-05, "epoch": 0.896969696969697, "percentage": 18.05, "elapsed_time": "0:15:26", "remaining_time": "1:10:07"}
89
- {"current_steps": 75, "total_steps": 410, "loss": 0.0417, "lr": 9.791977560124119e-05, "epoch": 0.9090909090909091, "percentage": 18.29, "elapsed_time": "0:15:37", "remaining_time": "1:09:45"}
90
- {"current_steps": 75, "total_steps": 410, "eval_loss": 0.038558006286621094, "epoch": 0.9090909090909091, "percentage": 18.29, "elapsed_time": "0:15:43", "remaining_time": "1:10:13"}
91
- {"current_steps": 76, "total_steps": 410, "loss": 0.0427, "lr": 9.779652985275562e-05, "epoch": 0.9212121212121213, "percentage": 18.54, "elapsed_time": "0:15:53", "remaining_time": "1:09:49"}
92
- {"current_steps": 77, "total_steps": 410, "loss": 0.0312, "lr": 9.766981960274653e-05, "epoch": 0.9333333333333333, "percentage": 18.78, "elapsed_time": "0:16:05", "remaining_time": "1:09:36"}
93
- {"current_steps": 78, "total_steps": 410, "loss": 0.0424, "lr": 9.753965403572703e-05, "epoch": 0.9454545454545454, "percentage": 19.02, "elapsed_time": "0:16:17", "remaining_time": "1:09:20"}
94
- {"current_steps": 79, "total_steps": 410, "loss": 0.0368, "lr": 9.740604258666668e-05, "epoch": 0.9575757575757575, "percentage": 19.27, "elapsed_time": "0:16:29", "remaining_time": "1:09:04"}
95
- {"current_steps": 80, "total_steps": 410, "loss": 0.0388, "lr": 9.726899494030768e-05, "epoch": 0.9696969696969697, "percentage": 19.51, "elapsed_time": "0:16:40", "remaining_time": "1:08:45"}
96
- {"current_steps": 80, "total_steps": 410, "eval_loss": 0.037164073437452316, "epoch": 0.9696969696969697, "percentage": 19.51, "elapsed_time": "0:16:46", "remaining_time": "1:09:11"}
97
- {"current_steps": 81, "total_steps": 410, "loss": 0.0367, "lr": 9.71285210304628e-05, "epoch": 0.9818181818181818, "percentage": 19.76, "elapsed_time": "0:16:59", "remaining_time": "1:09:02"}
98
- {"current_steps": 82, "total_steps": 410, "loss": 0.0399, "lr": 9.698463103929542e-05, "epoch": 0.9939393939393939, "percentage": 20.0, "elapsed_time": "0:17:09", "remaining_time": "1:08:36"}
99
- {"current_steps": 83, "total_steps": 410, "loss": 0.0545, "lr": 9.683733539658139e-05, "epoch": 1.006060606060606, "percentage": 20.24, "elapsed_time": "0:17:19", "remaining_time": "1:08:14"}
100
- {"current_steps": 84, "total_steps": 410, "loss": 0.048, "lr": 9.66866447789531e-05, "epoch": 1.018181818181818, "percentage": 20.49, "elapsed_time": "0:17:29", "remaining_time": "1:07:53"}
101
- {"current_steps": 85, "total_steps": 410, "loss": 0.0309, "lr": 9.653257010912559e-05, "epoch": 1.0303030303030303, "percentage": 20.73, "elapsed_time": "0:17:39", "remaining_time": "1:07:29"}
102
- {"current_steps": 85, "total_steps": 410, "eval_loss": 0.03581343591213226, "epoch": 1.0303030303030303, "percentage": 20.73, "elapsed_time": "0:17:45", "remaining_time": "1:07:53"}
103
- {"current_steps": 86, "total_steps": 410, "loss": 0.0659, "lr": 9.637512255510475e-05, "epoch": 1.0424242424242425, "percentage": 20.98, "elapsed_time": "0:17:54", "remaining_time": "1:07:27"}
104
- {"current_steps": 87, "total_steps": 410, "loss": 0.0502, "lr": 9.621431352937789e-05, "epoch": 1.0545454545454545, "percentage": 21.22, "elapsed_time": "0:18:04", "remaining_time": "1:07:05"}
105
- {"current_steps": 88, "total_steps": 410, "loss": 0.0318, "lr": 9.605015468808651e-05, "epoch": 1.0666666666666667, "percentage": 21.46, "elapsed_time": "0:18:14", "remaining_time": "1:06:43"}
106
- {"current_steps": 89, "total_steps": 410, "loss": 0.0446, "lr": 9.58826579301814e-05, "epoch": 1.0787878787878789, "percentage": 21.71, "elapsed_time": "0:18:26", "remaining_time": "1:06:29"}
107
- {"current_steps": 90, "total_steps": 410, "loss": 0.0487, "lr": 9.571183539656011e-05, "epoch": 1.0909090909090908, "percentage": 21.95, "elapsed_time": "0:18:38", "remaining_time": "1:06:16"}
108
- {"current_steps": 90, "total_steps": 410, "eval_loss": 0.0354202575981617, "epoch": 1.0909090909090908, "percentage": 21.95, "elapsed_time": "0:18:44", "remaining_time": "1:06:38"}
109
- {"current_steps": 91, "total_steps": 410, "loss": 0.0403, "lr": 9.553769946918697e-05, "epoch": 1.103030303030303, "percentage": 22.2, "elapsed_time": "0:18:54", "remaining_time": "1:06:16"}
110
- {"current_steps": 92, "total_steps": 410, "loss": 0.032, "lr": 9.536026277019561e-05, "epoch": 1.1151515151515152, "percentage": 22.44, "elapsed_time": "0:19:05", "remaining_time": "1:05:59"}
111
- {"current_steps": 93, "total_steps": 410, "loss": 0.0366, "lr": 9.517953816097396e-05, "epoch": 1.1272727272727272, "percentage": 22.68, "elapsed_time": "0:19:13", "remaining_time": "1:05:33"}
112
- {"current_steps": 94, "total_steps": 410, "loss": 0.0383, "lr": 9.499553874123212e-05, "epoch": 1.1393939393939394, "percentage": 22.93, "elapsed_time": "0:19:25", "remaining_time": "1:05:19"}
113
- {"current_steps": 95, "total_steps": 410, "loss": 0.0348, "lr": 9.480827784805278e-05, "epoch": 1.1515151515151516, "percentage": 23.17, "elapsed_time": "0:19:34", "remaining_time": "1:04:55"}
114
- {"current_steps": 95, "total_steps": 410, "eval_loss": 0.034031517803668976, "epoch": 1.1515151515151516, "percentage": 23.17, "elapsed_time": "0:19:41", "remaining_time": "1:05:16"}
115
- {"current_steps": 96, "total_steps": 410, "loss": 0.0322, "lr": 9.461776905492446e-05, "epoch": 1.1636363636363636, "percentage": 23.41, "elapsed_time": "0:19:53", "remaining_time": "1:05:03"}
116
- {"current_steps": 97, "total_steps": 410, "loss": 0.0302, "lr": 9.442402617075765e-05, "epoch": 1.1757575757575758, "percentage": 23.66, "elapsed_time": "0:20:05", "remaining_time": "1:04:50"}
117
- {"current_steps": 98, "total_steps": 410, "loss": 0.0305, "lr": 9.422706323888397e-05, "epoch": 1.187878787878788, "percentage": 23.9, "elapsed_time": "0:20:14", "remaining_time": "1:04:26"}
118
- {"current_steps": 99, "total_steps": 410, "loss": 0.0384, "lr": 9.402689453603815e-05, "epoch": 1.2, "percentage": 24.15, "elapsed_time": "0:20:25", "remaining_time": "1:04:09"}
119
- {"current_steps": 100, "total_steps": 410, "loss": 0.0308, "lr": 9.382353457132317e-05, "epoch": 1.2121212121212122, "percentage": 24.39, "elapsed_time": "0:20:37", "remaining_time": "1:03:55"}
120
- {"current_steps": 100, "total_steps": 410, "eval_loss": 0.03338392823934555, "epoch": 1.2121212121212122, "percentage": 24.39, "elapsed_time": "0:20:43", "remaining_time": "1:04:14"}
121
- {"current_steps": 101, "total_steps": 410, "loss": 0.0341, "lr": 9.361699808515876e-05, "epoch": 1.2242424242424241, "percentage": 24.63, "elapsed_time": "0:20:59", "remaining_time": "1:04:13"}
122
- {"current_steps": 102, "total_steps": 410, "loss": 0.0346, "lr": 9.340730004821266e-05, "epoch": 1.2363636363636363, "percentage": 24.88, "elapsed_time": "0:21:08", "remaining_time": "1:03:50"}
123
- {"current_steps": 103, "total_steps": 410, "loss": 0.0408, "lr": 9.31944556603157e-05, "epoch": 1.2484848484848485, "percentage": 25.12, "elapsed_time": "0:21:20", "remaining_time": "1:03:37"}
124
- {"current_steps": 104, "total_steps": 410, "loss": 0.0332, "lr": 9.297848034936006e-05, "epoch": 1.2606060606060607, "percentage": 25.37, "elapsed_time": "0:21:31", "remaining_time": "1:03:18"}
125
- {"current_steps": 105, "total_steps": 410, "loss": 0.0318, "lr": 9.275938977018081e-05, "epoch": 1.2727272727272727, "percentage": 25.61, "elapsed_time": "0:21:42", "remaining_time": "1:03:03"}
126
- {"current_steps": 105, "total_steps": 410, "eval_loss": 0.03301350772380829, "epoch": 1.2727272727272727, "percentage": 25.61, "elapsed_time": "0:21:48", "remaining_time": "1:03:21"}
127
- {"current_steps": 106, "total_steps": 410, "loss": 0.0339, "lr": 9.253719980342135e-05, "epoch": 1.284848484848485, "percentage": 25.85, "elapsed_time": "0:21:59", "remaining_time": "1:03:04"}
128
- {"current_steps": 107, "total_steps": 410, "loss": 0.0336, "lr": 9.231192655438221e-05, "epoch": 1.2969696969696969, "percentage": 26.1, "elapsed_time": "0:22:08", "remaining_time": "1:02:43"}
129
- {"current_steps": 108, "total_steps": 410, "loss": 0.0324, "lr": 9.208358635185373e-05, "epoch": 1.309090909090909, "percentage": 26.34, "elapsed_time": "0:22:19", "remaining_time": "1:02:25"}
130
- {"current_steps": 109, "total_steps": 410, "loss": 0.0332, "lr": 9.185219574693242e-05, "epoch": 1.3212121212121213, "percentage": 26.59, "elapsed_time": "0:22:27", "remaining_time": "1:02:01"}
131
- {"current_steps": 110, "total_steps": 410, "loss": 0.028, "lr": 9.161777151182136e-05, "epoch": 1.3333333333333333, "percentage": 26.83, "elapsed_time": "0:22:38", "remaining_time": "1:01:43"}
132
- {"current_steps": 110, "total_steps": 410, "eval_loss": 0.03218723088502884, "epoch": 1.3333333333333333, "percentage": 26.83, "elapsed_time": "0:22:44", "remaining_time": "1:02:00"}
133
- {"current_steps": 111, "total_steps": 410, "loss": 0.0346, "lr": 9.138033063861436e-05, "epoch": 1.3454545454545455, "percentage": 27.07, "elapsed_time": "0:22:56", "remaining_time": "1:01:48"}
134
- {"current_steps": 112, "total_steps": 410, "loss": 0.0283, "lr": 9.113989033806434e-05, "epoch": 1.3575757575757577, "percentage": 27.32, "elapsed_time": "0:23:08", "remaining_time": "1:01:35"}
135
- {"current_steps": 113, "total_steps": 410, "loss": 0.0246, "lr": 9.089646803833589e-05, "epoch": 1.3696969696969696, "percentage": 27.56, "elapsed_time": "0:23:21", "remaining_time": "1:01:23"}
136
- {"current_steps": 114, "total_steps": 410, "loss": 0.0317, "lr": 9.065008138374189e-05, "epoch": 1.3818181818181818, "percentage": 27.8, "elapsed_time": "0:23:32", "remaining_time": "1:01:07"}
137
- {"current_steps": 115, "total_steps": 410, "loss": 0.0311, "lr": 9.040074823346465e-05, "epoch": 1.393939393939394, "percentage": 28.05, "elapsed_time": "0:23:43", "remaining_time": "1:00:51"}
138
- {"current_steps": 115, "total_steps": 410, "eval_loss": 0.032092493027448654, "epoch": 1.393939393939394, "percentage": 28.05, "elapsed_time": "0:23:49", "remaining_time": "1:01:07"}
139
- {"current_steps": 116, "total_steps": 410, "loss": 0.0389, "lr": 9.014848666026138e-05, "epoch": 1.406060606060606, "percentage": 28.29, "elapsed_time": "0:24:00", "remaining_time": "1:00:52"}
140
- {"current_steps": 117, "total_steps": 410, "loss": 0.0287, "lr": 8.989331494915417e-05, "epoch": 1.4181818181818182, "percentage": 28.54, "elapsed_time": "0:24:13", "remaining_time": "1:00:39"}
141
- {"current_steps": 118, "total_steps": 410, "loss": 0.0265, "lr": 8.963525159610465e-05, "epoch": 1.4303030303030302, "percentage": 28.78, "elapsed_time": "0:24:23", "remaining_time": "1:00:22"}
142
- {"current_steps": 119, "total_steps": 410, "loss": 0.0262, "lr": 8.937431530667328e-05, "epoch": 1.4424242424242424, "percentage": 29.02, "elapsed_time": "0:24:33", "remaining_time": "1:00:02"}
143
- {"current_steps": 120, "total_steps": 410, "loss": 0.0382, "lr": 8.911052499466357e-05, "epoch": 1.4545454545454546, "percentage": 29.27, "elapsed_time": "0:24:41", "remaining_time": "0:59:40"}
144
- {"current_steps": 120, "total_steps": 410, "eval_loss": 0.031465690582990646, "epoch": 1.4545454545454546, "percentage": 29.27, "elapsed_time": "0:24:47", "remaining_time": "0:59:55"}
145
- {"current_steps": 121, "total_steps": 410, "loss": 0.0336, "lr": 8.884389978075098e-05, "epoch": 1.4666666666666668, "percentage": 29.51, "elapsed_time": "0:24:57", "remaining_time": "0:59:36"}
146
- {"current_steps": 122, "total_steps": 410, "loss": 0.0267, "lr": 8.857445899109715e-05, "epoch": 1.4787878787878788, "percentage": 29.76, "elapsed_time": "0:25:10", "remaining_time": "0:59:25"}
147
- {"current_steps": 123, "total_steps": 410, "loss": 0.0258, "lr": 8.83022221559489e-05, "epoch": 1.490909090909091, "percentage": 30.0, "elapsed_time": "0:25:22", "remaining_time": "0:59:13"}
148
- {"current_steps": 124, "total_steps": 410, "loss": 0.0344, "lr": 8.80272090082227e-05, "epoch": 1.503030303030303, "percentage": 30.24, "elapsed_time": "0:25:34", "remaining_time": "0:58:59"}
149
- {"current_steps": 125, "total_steps": 410, "loss": 0.0316, "lr": 8.774943948207426e-05, "epoch": 1.5151515151515151, "percentage": 30.49, "elapsed_time": "0:25:44", "remaining_time": "0:58:41"}
150
- {"current_steps": 125, "total_steps": 410, "eval_loss": 0.030392121523618698, "epoch": 1.5151515151515151, "percentage": 30.49, "elapsed_time": "0:25:50", "remaining_time": "0:58:56"}
151
- {"current_steps": 126, "total_steps": 410, "loss": 0.0279, "lr": 8.746893371145366e-05, "epoch": 1.5272727272727273, "percentage": 30.73, "elapsed_time": "0:26:03", "remaining_time": "0:58:43"}
152
- {"current_steps": 127, "total_steps": 410, "loss": 0.0292, "lr": 8.718571202864598e-05, "epoch": 1.5393939393939395, "percentage": 30.98, "elapsed_time": "0:26:12", "remaining_time": "0:58:24"}
153
- {"current_steps": 128, "total_steps": 410, "loss": 0.0296, "lr": 8.689979496279746e-05, "epoch": 1.5515151515151515, "percentage": 31.22, "elapsed_time": "0:26:20", "remaining_time": "0:58:02"}
154
- {"current_steps": 129, "total_steps": 410, "loss": 0.0286, "lr": 8.661120323842751e-05, "epoch": 1.5636363636363635, "percentage": 31.46, "elapsed_time": "0:26:33", "remaining_time": "0:57:50"}
155
- {"current_steps": 130, "total_steps": 410, "loss": 0.0278, "lr": 8.631995777392645e-05, "epoch": 1.5757575757575757, "percentage": 31.71, "elapsed_time": "0:26:43", "remaining_time": "0:57:34"}
156
- {"current_steps": 130, "total_steps": 410, "eval_loss": 0.029901880770921707, "epoch": 1.5757575757575757, "percentage": 31.71, "elapsed_time": "0:26:50", "remaining_time": "0:57:47"}
157
- {"current_steps": 131, "total_steps": 410, "loss": 0.0277, "lr": 8.602607968003935e-05, "epoch": 1.587878787878788, "percentage": 31.95, "elapsed_time": "0:27:02", "remaining_time": "0:57:34"}
158
- {"current_steps": 132, "total_steps": 410, "loss": 0.023, "lr": 8.572959025833573e-05, "epoch": 1.6, "percentage": 32.2, "elapsed_time": "0:27:15", "remaining_time": "0:57:24"}
159
- {"current_steps": 133, "total_steps": 410, "loss": 0.0253, "lr": 8.543051099966558e-05, "epoch": 1.612121212121212, "percentage": 32.44, "elapsed_time": "0:27:29", "remaining_time": "0:57:15"}
160
- {"current_steps": 134, "total_steps": 410, "loss": 0.0249, "lr": 8.512886358260162e-05, "epoch": 1.6242424242424243, "percentage": 32.68, "elapsed_time": "0:27:40", "remaining_time": "0:57:00"}
161
- {"current_steps": 135, "total_steps": 410, "loss": 0.0285, "lr": 8.482466987186785e-05, "epoch": 1.6363636363636362, "percentage": 32.93, "elapsed_time": "0:27:50", "remaining_time": "0:56:43"}
162
- {"current_steps": 135, "total_steps": 410, "eval_loss": 0.029229959473013878, "epoch": 1.6363636363636362, "percentage": 32.93, "elapsed_time": "0:27:56", "remaining_time": "0:56:55"}
163
- {"current_steps": 136, "total_steps": 410, "loss": 0.0268, "lr": 8.451795191675488e-05, "epoch": 1.6484848484848484, "percentage": 33.17, "elapsed_time": "0:28:09", "remaining_time": "0:56:42"}
164
- {"current_steps": 137, "total_steps": 410, "loss": 0.0351, "lr": 8.420873194952152e-05, "epoch": 1.6606060606060606, "percentage": 33.41, "elapsed_time": "0:28:20", "remaining_time": "0:56:27"}
165
- {"current_steps": 138, "total_steps": 410, "loss": 0.0309, "lr": 8.389703238378339e-05, "epoch": 1.6727272727272728, "percentage": 33.66, "elapsed_time": "0:28:32", "remaining_time": "0:56:14"}
166
- {"current_steps": 139, "total_steps": 410, "loss": 0.0244, "lr": 8.358287581288822e-05, "epoch": 1.6848484848484848, "percentage": 33.9, "elapsed_time": "0:28:43", "remaining_time": "0:56:00"}
167
- {"current_steps": 140, "total_steps": 410, "loss": 0.0257, "lr": 8.326628500827826e-05, "epoch": 1.696969696969697, "percentage": 34.15, "elapsed_time": "0:28:53", "remaining_time": "0:55:42"}
168
- {"current_steps": 140, "total_steps": 410, "eval_loss": 0.02854442596435547, "epoch": 1.696969696969697, "percentage": 34.15, "elapsed_time": "0:28:59", "remaining_time": "0:55:54"}
169
- {"current_steps": 141, "total_steps": 410, "loss": 0.0301, "lr": 8.294728291783966e-05, "epoch": 1.709090909090909, "percentage": 34.39, "elapsed_time": "0:29:10", "remaining_time": "0:55:39"}
170
- {"current_steps": 142, "total_steps": 410, "loss": 0.0254, "lr": 8.262589266423908e-05, "epoch": 1.7212121212121212, "percentage": 34.63, "elapsed_time": "0:29:21", "remaining_time": "0:55:24"}
171
- {"current_steps": 143, "total_steps": 410, "loss": 0.0338, "lr": 8.230213754324773e-05, "epoch": 1.7333333333333334, "percentage": 34.88, "elapsed_time": "0:29:33", "remaining_time": "0:55:11"}
172
- {"current_steps": 144, "total_steps": 410, "loss": 0.0265, "lr": 8.197604102205271e-05, "epoch": 1.7454545454545456, "percentage": 35.12, "elapsed_time": "0:29:44", "remaining_time": "0:54:55"}
173
- {"current_steps": 145, "total_steps": 410, "loss": 0.0244, "lr": 8.16476267375561e-05, "epoch": 1.7575757575757576, "percentage": 35.37, "elapsed_time": "0:29:54", "remaining_time": "0:54:39"}
174
- {"current_steps": 145, "total_steps": 410, "eval_loss": 0.028112677857279778, "epoch": 1.7575757575757576, "percentage": 35.37, "elapsed_time": "0:30:00", "remaining_time": "0:54:50"}
175
- {"current_steps": 146, "total_steps": 410, "loss": 0.0351, "lr": 8.131691849466153e-05, "epoch": 1.7696969696969695, "percentage": 35.61, "elapsed_time": "0:30:10", "remaining_time": "0:54:33"}
176
- {"current_steps": 147, "total_steps": 410, "loss": 0.0318, "lr": 8.098394026454885e-05, "epoch": 1.7818181818181817, "percentage": 35.85, "elapsed_time": "0:30:19", "remaining_time": "0:54:15"}
177
- {"current_steps": 148, "total_steps": 410, "loss": 0.0258, "lr": 8.064871618293646e-05, "epoch": 1.793939393939394, "percentage": 36.1, "elapsed_time": "0:30:31", "remaining_time": "0:54:01"}
178
- {"current_steps": 149, "total_steps": 410, "loss": 0.0322, "lr": 8.03112705483319e-05, "epoch": 1.8060606060606061, "percentage": 36.34, "elapsed_time": "0:30:41", "remaining_time": "0:53:45"}
179
- {"current_steps": 150, "total_steps": 410, "loss": 0.0256, "lr": 7.997162782027061e-05, "epoch": 1.8181818181818183, "percentage": 36.59, "elapsed_time": "0:30:52", "remaining_time": "0:53:30"}
180
- {"current_steps": 150, "total_steps": 410, "eval_loss": 0.027805332094430923, "epoch": 1.8181818181818183, "percentage": 36.59, "elapsed_time": "0:30:58", "remaining_time": "0:53:41"}
181
- {"current_steps": 151, "total_steps": 410, "loss": 0.0265, "lr": 7.962981261754294e-05, "epoch": 1.8303030303030303, "percentage": 36.83, "elapsed_time": "0:31:16", "remaining_time": "0:53:39"}
182
- {"current_steps": 152, "total_steps": 410, "loss": 0.0302, "lr": 7.928584971640974e-05, "epoch": 1.8424242424242423, "percentage": 37.07, "elapsed_time": "0:31:28", "remaining_time": "0:53:26"}
183
- {"current_steps": 153, "total_steps": 410, "loss": 0.0331, "lr": 7.893976404880643e-05, "epoch": 1.8545454545454545, "percentage": 37.32, "elapsed_time": "0:31:39", "remaining_time": "0:53:10"}
184
- {"current_steps": 154, "total_steps": 410, "loss": 0.0245, "lr": 7.859158070053577e-05, "epoch": 1.8666666666666667, "percentage": 37.56, "elapsed_time": "0:31:50", "remaining_time": "0:52:55"}
185
- {"current_steps": 155, "total_steps": 410, "loss": 0.0338, "lr": 7.824132490944967e-05, "epoch": 1.878787878787879, "percentage": 37.8, "elapsed_time": "0:32:02", "remaining_time": "0:52:42"}
186
- {"current_steps": 155, "total_steps": 410, "eval_loss": 0.027029650285840034, "epoch": 1.878787878787879, "percentage": 37.8, "elapsed_time": "0:32:08", "remaining_time": "0:52:52"}
187
- {"current_steps": 156, "total_steps": 410, "loss": 0.0241, "lr": 7.788902206361973e-05, "epoch": 1.8909090909090909, "percentage": 38.05, "elapsed_time": "0:32:20", "remaining_time": "0:52:38"}
188
- {"current_steps": 157, "total_steps": 410, "loss": 0.0301, "lr": 7.7534697699497e-05, "epoch": 1.903030303030303, "percentage": 38.29, "elapsed_time": "0:32:29", "remaining_time": "0:52:21"}
189
- {"current_steps": 158, "total_steps": 410, "loss": 0.0274, "lr": 7.717837750006106e-05, "epoch": 1.915151515151515, "percentage": 38.54, "elapsed_time": "0:32:43", "remaining_time": "0:52:11"}
190
- {"current_steps": 159, "total_steps": 410, "loss": 0.026, "lr": 7.682008729295833e-05, "epoch": 1.9272727272727272, "percentage": 38.78, "elapsed_time": "0:32:52", "remaining_time": "0:51:53"}
191
- {"current_steps": 160, "total_steps": 410, "loss": 0.0309, "lr": 7.645985304863003e-05, "epoch": 1.9393939393939394, "percentage": 39.02, "elapsed_time": "0:33:03", "remaining_time": "0:51:38"}
192
- {"current_steps": 160, "total_steps": 410, "eval_loss": 0.02624826692044735, "epoch": 1.9393939393939394, "percentage": 39.02, "elapsed_time": "0:33:09", "remaining_time": "0:51:48"}
193
- {"current_steps": 161, "total_steps": 410, "loss": 0.0275, "lr": 7.609770087842969e-05, "epoch": 1.9515151515151516, "percentage": 39.27, "elapsed_time": "0:33:18", "remaining_time": "0:51:30"}
194
- {"current_steps": 162, "total_steps": 410, "loss": 0.0263, "lr": 7.573365703273046e-05, "epoch": 1.9636363636363636, "percentage": 39.51, "elapsed_time": "0:33:28", "remaining_time": "0:51:15"}
195
- {"current_steps": 163, "total_steps": 410, "loss": 0.0293, "lr": 7.536774789902246e-05, "epoch": 1.9757575757575756, "percentage": 39.76, "elapsed_time": "0:33:39", "remaining_time": "0:50:59"}
196
- {"current_steps": 164, "total_steps": 410, "loss": 0.0292, "lr": 7.500000000000001e-05, "epoch": 1.9878787878787878, "percentage": 40.0, "elapsed_time": "0:33:51", "remaining_time": "0:50:46"}
197
- {"current_steps": 165, "total_steps": 410, "loss": 0.0378, "lr": 7.463043999163919e-05, "epoch": 2.0, "percentage": 40.24, "elapsed_time": "0:34:02", "remaining_time": "0:50:32"}
198
- {"current_steps": 165, "total_steps": 410, "eval_loss": 0.02608395926654339, "epoch": 2.0, "percentage": 40.24, "elapsed_time": "0:34:08", "remaining_time": "0:50:41"}
199
- {"current_steps": 166, "total_steps": 410, "loss": 0.024, "lr": 7.425909466126568e-05, "epoch": 2.012121212121212, "percentage": 40.49, "elapsed_time": "0:34:17", "remaining_time": "0:50:23"}
200
- {"current_steps": 167, "total_steps": 410, "loss": 0.0238, "lr": 7.388599092561315e-05, "epoch": 2.0242424242424244, "percentage": 40.73, "elapsed_time": "0:34:28", "remaining_time": "0:50:10"}
201
- {"current_steps": 168, "total_steps": 410, "loss": 0.0218, "lr": 7.351115582887211e-05, "epoch": 2.036363636363636, "percentage": 40.98, "elapsed_time": "0:34:38", "remaining_time": "0:49:53"}
202
- {"current_steps": 169, "total_steps": 410, "loss": 0.0199, "lr": 7.313461654072973e-05, "epoch": 2.0484848484848484, "percentage": 41.22, "elapsed_time": "0:34:50", "remaining_time": "0:49:40"}
203
- {"current_steps": 170, "total_steps": 410, "loss": 0.0275, "lr": 7.275640035440045e-05, "epoch": 2.0606060606060606, "percentage": 41.46, "elapsed_time": "0:35:01", "remaining_time": "0:49:27"}
204
- {"current_steps": 170, "total_steps": 410, "eval_loss": 0.026318900287151337, "epoch": 2.0606060606060606, "percentage": 41.46, "elapsed_time": "0:35:07", "remaining_time": "0:49:35"}
205
- {"current_steps": 171, "total_steps": 410, "loss": 0.0256, "lr": 7.237653468464756e-05, "epoch": 2.0727272727272728, "percentage": 41.71, "elapsed_time": "0:35:20", "remaining_time": "0:49:23"}
206
- {"current_steps": 172, "total_steps": 410, "loss": 0.0226, "lr": 7.199504706579617e-05, "epoch": 2.084848484848485, "percentage": 41.95, "elapsed_time": "0:35:32", "remaining_time": "0:49:10"}
207
- {"current_steps": 173, "total_steps": 410, "loss": 0.0188, "lr": 7.161196514973734e-05, "epoch": 2.096969696969697, "percentage": 42.2, "elapsed_time": "0:35:43", "remaining_time": "0:48:55"}
208
- {"current_steps": 174, "total_steps": 410, "loss": 0.0232, "lr": 7.12273167039238e-05, "epoch": 2.109090909090909, "percentage": 42.44, "elapsed_time": "0:35:53", "remaining_time": "0:48:40"}
209
- {"current_steps": 175, "total_steps": 410, "loss": 0.0225, "lr": 7.084112960935716e-05, "epoch": 2.121212121212121, "percentage": 42.68, "elapsed_time": "0:36:02", "remaining_time": "0:48:24"}
210
- {"current_steps": 175, "total_steps": 410, "eval_loss": 0.025883661583065987, "epoch": 2.121212121212121, "percentage": 42.68, "elapsed_time": "0:36:09", "remaining_time": "0:48:32"}
211
- {"current_steps": 176, "total_steps": 410, "loss": 0.0248, "lr": 7.045343185856701e-05, "epoch": 2.1333333333333333, "percentage": 42.93, "elapsed_time": "0:36:20", "remaining_time": "0:48:19"}
212
- {"current_steps": 177, "total_steps": 410, "loss": 0.0244, "lr": 7.006425155358195e-05, "epoch": 2.1454545454545455, "percentage": 43.17, "elapsed_time": "0:36:32", "remaining_time": "0:48:06"}
213
- {"current_steps": 178, "total_steps": 410, "loss": 0.0242, "lr": 6.967361690389258e-05, "epoch": 2.1575757575757577, "percentage": 43.41, "elapsed_time": "0:36:43", "remaining_time": "0:47:51"}
214
- {"current_steps": 179, "total_steps": 410, "loss": 0.0246, "lr": 6.92815562244068e-05, "epoch": 2.16969696969697, "percentage": 43.66, "elapsed_time": "0:36:55", "remaining_time": "0:47:38"}
215
- {"current_steps": 180, "total_steps": 410, "loss": 0.0232, "lr": 6.88880979333973e-05, "epoch": 2.1818181818181817, "percentage": 43.9, "elapsed_time": "0:37:04", "remaining_time": "0:47:22"}
216
- {"current_steps": 180, "total_steps": 410, "eval_loss": 0.025616060942411423, "epoch": 2.1818181818181817, "percentage": 43.9, "elapsed_time": "0:37:10", "remaining_time": "0:47:30"}
217
- {"current_steps": 181, "total_steps": 410, "loss": 0.0251, "lr": 6.849327055044183e-05, "epoch": 2.193939393939394, "percentage": 44.15, "elapsed_time": "0:37:22", "remaining_time": "0:47:17"}
218
- {"current_steps": 182, "total_steps": 410, "loss": 0.022, "lr": 6.809710269435589e-05, "epoch": 2.206060606060606, "percentage": 44.39, "elapsed_time": "0:37:34", "remaining_time": "0:47:04"}
219
- {"current_steps": 183, "total_steps": 410, "loss": 0.0234, "lr": 6.769962308111839e-05, "epoch": 2.2181818181818183, "percentage": 44.63, "elapsed_time": "0:37:44", "remaining_time": "0:46:49"}
220
- {"current_steps": 184, "total_steps": 410, "loss": 0.0221, "lr": 6.730086052179004e-05, "epoch": 2.2303030303030305, "percentage": 44.88, "elapsed_time": "0:37:57", "remaining_time": "0:46:37"}
221
- {"current_steps": 185, "total_steps": 410, "loss": 0.0193, "lr": 6.690084392042513e-05, "epoch": 2.242424242424242, "percentage": 45.12, "elapsed_time": "0:38:08", "remaining_time": "0:46:23"}
222
- {"current_steps": 185, "total_steps": 410, "eval_loss": 0.025547849014401436, "epoch": 2.242424242424242, "percentage": 45.12, "elapsed_time": "0:38:14", "remaining_time": "0:46:30"}
223
- {"current_steps": 186, "total_steps": 410, "loss": 0.0217, "lr": 6.649960227197647e-05, "epoch": 2.2545454545454544, "percentage": 45.37, "elapsed_time": "0:38:26", "remaining_time": "0:46:18"}
224
- {"current_steps": 187, "total_steps": 410, "loss": 0.0239, "lr": 6.609716466019356e-05, "epoch": 2.2666666666666666, "percentage": 45.61, "elapsed_time": "0:38:36", "remaining_time": "0:46:02"}
225
- {"current_steps": 188, "total_steps": 410, "loss": 0.0232, "lr": 6.569356025551454e-05, "epoch": 2.278787878787879, "percentage": 45.85, "elapsed_time": "0:38:47", "remaining_time": "0:45:48"}
226
- {"current_steps": 189, "total_steps": 410, "loss": 0.02, "lr": 6.528881831295188e-05, "epoch": 2.290909090909091, "percentage": 46.1, "elapsed_time": "0:38:56", "remaining_time": "0:45:31"}
227
- {"current_steps": 190, "total_steps": 410, "loss": 0.0251, "lr": 6.488296816997173e-05, "epoch": 2.303030303030303, "percentage": 46.34, "elapsed_time": "0:39:06", "remaining_time": "0:45:17"}
228
- {"current_steps": 190, "total_steps": 410, "eval_loss": 0.02527759224176407, "epoch": 2.303030303030303, "percentage": 46.34, "elapsed_time": "0:39:12", "remaining_time": "0:45:24"}
229
- {"current_steps": 191, "total_steps": 410, "loss": 0.0243, "lr": 6.447603924436744e-05, "epoch": 2.315151515151515, "percentage": 46.59, "elapsed_time": "0:39:24", "remaining_time": "0:45:10"}
230
- {"current_steps": 192, "total_steps": 410, "loss": 0.0204, "lr": 6.406806103212725e-05, "epoch": 2.327272727272727, "percentage": 46.83, "elapsed_time": "0:39:36", "remaining_time": "0:44:58"}
231
- {"current_steps": 193, "total_steps": 410, "loss": 0.0232, "lr": 6.36590631052963e-05, "epoch": 2.3393939393939394, "percentage": 47.07, "elapsed_time": "0:39:45", "remaining_time": "0:44:42"}
232
- {"current_steps": 194, "total_steps": 410, "loss": 0.0324, "lr": 6.32490751098331e-05, "epoch": 2.3515151515151516, "percentage": 47.32, "elapsed_time": "0:39:55", "remaining_time": "0:44:26"}
233
- {"current_steps": 195, "total_steps": 410, "loss": 0.0228, "lr": 6.283812676346063e-05, "epoch": 2.3636363636363638, "percentage": 47.56, "elapsed_time": "0:40:07", "remaining_time": "0:44:14"}
234
- {"current_steps": 195, "total_steps": 410, "eval_loss": 0.024870626628398895, "epoch": 2.3636363636363638, "percentage": 47.56, "elapsed_time": "0:40:13", "remaining_time": "0:44:20"}
235
- {"current_steps": 196, "total_steps": 410, "loss": 0.0231, "lr": 6.242624785351236e-05, "epoch": 2.375757575757576, "percentage": 47.8, "elapsed_time": "0:40:24", "remaining_time": "0:44:06"}
236
- {"current_steps": 197, "total_steps": 410, "loss": 0.0193, "lr": 6.201346823477303e-05, "epoch": 2.3878787878787877, "percentage": 48.05, "elapsed_time": "0:40:36", "remaining_time": "0:43:54"}
237
- {"current_steps": 198, "total_steps": 410, "loss": 0.0227, "lr": 6.159981782731474e-05, "epoch": 2.4, "percentage": 48.29, "elapsed_time": "0:40:49", "remaining_time": "0:43:42"}
238
- {"current_steps": 199, "total_steps": 410, "loss": 0.0224, "lr": 6.118532661432812e-05, "epoch": 2.412121212121212, "percentage": 48.54, "elapsed_time": "0:41:00", "remaining_time": "0:43:28"}
239
- {"current_steps": 200, "total_steps": 410, "loss": 0.0195, "lr": 6.0770024639949074e-05, "epoch": 2.4242424242424243, "percentage": 48.78, "elapsed_time": "0:41:09", "remaining_time": "0:43:12"}
240
- {"current_steps": 200, "total_steps": 410, "eval_loss": 0.024939175695180893, "epoch": 2.4242424242424243, "percentage": 48.78, "elapsed_time": "0:41:15", "remaining_time": "0:43:19"}
241
- {"current_steps": 201, "total_steps": 410, "loss": 0.0198, "lr": 6.0353942007081046e-05, "epoch": 2.4363636363636365, "percentage": 49.02, "elapsed_time": "0:41:34", "remaining_time": "0:43:13"}
242
- {"current_steps": 202, "total_steps": 410, "loss": 0.0184, "lr": 5.993710887521302e-05, "epoch": 2.4484848484848483, "percentage": 49.27, "elapsed_time": "0:41:46", "remaining_time": "0:43:01"}
243
- {"current_steps": 203, "total_steps": 410, "loss": 0.0207, "lr": 5.951955545823342e-05, "epoch": 2.4606060606060605, "percentage": 49.51, "elapsed_time": "0:41:57", "remaining_time": "0:42:47"}
244
- {"current_steps": 204, "total_steps": 410, "loss": 0.0217, "lr": 5.9101312022240106e-05, "epoch": 2.4727272727272727, "percentage": 49.76, "elapsed_time": "0:42:09", "remaining_time": "0:42:34"}
245
- {"current_steps": 205, "total_steps": 410, "loss": 0.0219, "lr": 5.868240888334653e-05, "epoch": 2.484848484848485, "percentage": 50.0, "elapsed_time": "0:42:18", "remaining_time": "0:42:18"}
246
- {"current_steps": 205, "total_steps": 410, "eval_loss": 0.024136777967214584, "epoch": 2.484848484848485, "percentage": 50.0, "elapsed_time": "0:42:25", "remaining_time": "0:42:25"}
247
- {"current_steps": 206, "total_steps": 410, "loss": 0.0231, "lr": 5.826287640548425e-05, "epoch": 2.496969696969697, "percentage": 50.24, "elapsed_time": "0:42:36", "remaining_time": "0:42:11"}
248
- {"current_steps": 207, "total_steps": 410, "loss": 0.0243, "lr": 5.784274499820214e-05, "epoch": 2.509090909090909, "percentage": 50.49, "elapsed_time": "0:42:45", "remaining_time": "0:41:55"}
249
- {"current_steps": 208, "total_steps": 410, "loss": 0.0241, "lr": 5.742204511446203e-05, "epoch": 2.5212121212121215, "percentage": 50.73, "elapsed_time": "0:42:54", "remaining_time": "0:41:40"}
250
- {"current_steps": 209, "total_steps": 410, "loss": 0.0217, "lr": 5.700080724843147e-05, "epoch": 2.533333333333333, "percentage": 50.98, "elapsed_time": "0:43:05", "remaining_time": "0:41:26"}
251
- {"current_steps": 210, "total_steps": 410, "loss": 0.0184, "lr": 5.657906193327325e-05, "epoch": 2.5454545454545454, "percentage": 51.22, "elapsed_time": "0:43:16", "remaining_time": "0:41:12"}
252
- {"current_steps": 210, "total_steps": 410, "eval_loss": 0.023839673027396202, "epoch": 2.5454545454545454, "percentage": 51.22, "elapsed_time": "0:43:22", "remaining_time": "0:41:18"}
253
- {"current_steps": 211, "total_steps": 410, "loss": 0.0233, "lr": 5.6156839738932343e-05, "epoch": 2.5575757575757576, "percentage": 51.46, "elapsed_time": "0:43:31", "remaining_time": "0:41:03"}
254
- {"current_steps": 212, "total_steps": 410, "loss": 0.0419, "lr": 5.573417126992003e-05, "epoch": 2.56969696969697, "percentage": 51.71, "elapsed_time": "0:43:43", "remaining_time": "0:40:50"}
255
- {"current_steps": 213, "total_steps": 410, "loss": 0.0208, "lr": 5.531108716309547e-05, "epoch": 2.581818181818182, "percentage": 51.95, "elapsed_time": "0:43:52", "remaining_time": "0:40:35"}
256
- {"current_steps": 214, "total_steps": 410, "loss": 0.0356, "lr": 5.4887618085445094e-05, "epoch": 2.5939393939393938, "percentage": 52.2, "elapsed_time": "0:44:02", "remaining_time": "0:40:20"}
257
- {"current_steps": 215, "total_steps": 410, "loss": 0.0199, "lr": 5.446379473185972e-05, "epoch": 2.606060606060606, "percentage": 52.44, "elapsed_time": "0:44:14", "remaining_time": "0:40:07"}
258
- {"current_steps": 215, "total_steps": 410, "eval_loss": 0.023647097870707512, "epoch": 2.606060606060606, "percentage": 52.44, "elapsed_time": "0:44:20", "remaining_time": "0:40:13"}
259
- {"current_steps": 216, "total_steps": 410, "loss": 0.0185, "lr": 5.4039647822909624e-05, "epoch": 2.618181818181818, "percentage": 52.68, "elapsed_time": "0:44:32", "remaining_time": "0:40:00"}
260
- {"current_steps": 217, "total_steps": 410, "loss": 0.0212, "lr": 5.361520810261779e-05, "epoch": 2.6303030303030304, "percentage": 52.93, "elapsed_time": "0:44:43", "remaining_time": "0:39:46"}
261
- {"current_steps": 218, "total_steps": 410, "loss": 0.0208, "lr": 5.319050633623142e-05, "epoch": 2.6424242424242426, "percentage": 53.17, "elapsed_time": "0:44:54", "remaining_time": "0:39:32"}
262
- {"current_steps": 219, "total_steps": 410, "loss": 0.0343, "lr": 5.2765573307992036e-05, "epoch": 2.6545454545454543, "percentage": 53.41, "elapsed_time": "0:45:05", "remaining_time": "0:39:19"}
263
- {"current_steps": 220, "total_steps": 410, "loss": 0.023, "lr": 5.234043981890394e-05, "epoch": 2.6666666666666665, "percentage": 53.66, "elapsed_time": "0:45:14", "remaining_time": "0:39:04"}
264
- {"current_steps": 220, "total_steps": 410, "eval_loss": 0.02315612882375717, "epoch": 2.6666666666666665, "percentage": 53.66, "elapsed_time": "0:45:21", "remaining_time": "0:39:10"}
265
- {"current_steps": 221, "total_steps": 410, "loss": 0.0208, "lr": 5.191513668450178e-05, "epoch": 2.6787878787878787, "percentage": 53.9, "elapsed_time": "0:45:33", "remaining_time": "0:38:57"}
266
- {"current_steps": 222, "total_steps": 410, "loss": 0.0178, "lr": 5.14896947326168e-05, "epoch": 2.690909090909091, "percentage": 54.15, "elapsed_time": "0:45:46", "remaining_time": "0:38:45"}
267
- {"current_steps": 223, "total_steps": 410, "loss": 0.019, "lr": 5.1064144801142374e-05, "epoch": 2.703030303030303, "percentage": 54.39, "elapsed_time": "0:45:56", "remaining_time": "0:38:31"}
268
- {"current_steps": 224, "total_steps": 410, "loss": 0.0184, "lr": 5.0638517735798696e-05, "epoch": 2.7151515151515153, "percentage": 54.63, "elapsed_time": "0:46:09", "remaining_time": "0:38:19"}
269
- {"current_steps": 225, "total_steps": 410, "loss": 0.0227, "lr": 5.021284438789694e-05, "epoch": 2.7272727272727275, "percentage": 54.88, "elapsed_time": "0:46:18", "remaining_time": "0:38:04"}
270
- {"current_steps": 225, "total_steps": 410, "eval_loss": 0.023449590429663658, "epoch": 2.7272727272727275, "percentage": 54.88, "elapsed_time": "0:46:25", "remaining_time": "0:38:10"}
271
- {"current_steps": 226, "total_steps": 410, "loss": 0.0205, "lr": 4.9787155612103074e-05, "epoch": 2.7393939393939393, "percentage": 55.12, "elapsed_time": "0:46:36", "remaining_time": "0:37:56"}
272
- {"current_steps": 227, "total_steps": 410, "loss": 0.0171, "lr": 4.936148226420132e-05, "epoch": 2.7515151515151515, "percentage": 55.37, "elapsed_time": "0:46:47", "remaining_time": "0:37:43"}
273
- {"current_steps": 228, "total_steps": 410, "loss": 0.0197, "lr": 4.893585519885764e-05, "epoch": 2.7636363636363637, "percentage": 55.61, "elapsed_time": "0:47:01", "remaining_time": "0:37:32"}
274
- {"current_steps": 229, "total_steps": 410, "loss": 0.0204, "lr": 4.851030526738321e-05, "epoch": 2.775757575757576, "percentage": 55.85, "elapsed_time": "0:47:12", "remaining_time": "0:37:18"}
275
- {"current_steps": 230, "total_steps": 410, "loss": 0.0206, "lr": 4.8084863315498234e-05, "epoch": 2.787878787878788, "percentage": 56.1, "elapsed_time": "0:47:22", "remaining_time": "0:37:04"}
276
- {"current_steps": 230, "total_steps": 410, "eval_loss": 0.022967081516981125, "epoch": 2.787878787878788, "percentage": 56.1, "elapsed_time": "0:47:28", "remaining_time": "0:37:09"}
277
- {"current_steps": 231, "total_steps": 410, "loss": 0.0197, "lr": 4.765956018109607e-05, "epoch": 2.8, "percentage": 56.34, "elapsed_time": "0:47:40", "remaining_time": "0:36:56"}
278
- {"current_steps": 232, "total_steps": 410, "loss": 0.0213, "lr": 4.723442669200798e-05, "epoch": 2.812121212121212, "percentage": 56.59, "elapsed_time": "0:47:52", "remaining_time": "0:36:43"}
279
- {"current_steps": 233, "total_steps": 410, "loss": 0.0237, "lr": 4.680949366376858e-05, "epoch": 2.824242424242424, "percentage": 56.83, "elapsed_time": "0:48:03", "remaining_time": "0:36:30"}
280
- {"current_steps": 234, "total_steps": 410, "loss": 0.0235, "lr": 4.638479189738224e-05, "epoch": 2.8363636363636364, "percentage": 57.07, "elapsed_time": "0:48:15", "remaining_time": "0:36:18"}
281
- {"current_steps": 235, "total_steps": 410, "loss": 0.0217, "lr": 4.5960352177090395e-05, "epoch": 2.8484848484848486, "percentage": 57.32, "elapsed_time": "0:48:25", "remaining_time": "0:36:03"}
282
- {"current_steps": 235, "total_steps": 410, "eval_loss": 0.022518714889883995, "epoch": 2.8484848484848486, "percentage": 57.32, "elapsed_time": "0:48:31", "remaining_time": "0:36:08"}
283
- {"current_steps": 236, "total_steps": 410, "loss": 0.0189, "lr": 4.5536205268140294e-05, "epoch": 2.8606060606060604, "percentage": 57.56, "elapsed_time": "0:48:42", "remaining_time": "0:35:54"}
284
- {"current_steps": 237, "total_steps": 410, "loss": 0.0166, "lr": 4.511238191455491e-05, "epoch": 2.8727272727272726, "percentage": 57.8, "elapsed_time": "0:48:53", "remaining_time": "0:35:41"}
285
- {"current_steps": 238, "total_steps": 410, "loss": 0.0183, "lr": 4.468891283690454e-05, "epoch": 2.8848484848484848, "percentage": 58.05, "elapsed_time": "0:49:04", "remaining_time": "0:35:27"}
286
- {"current_steps": 239, "total_steps": 410, "loss": 0.0221, "lr": 4.4265828730079987e-05, "epoch": 2.896969696969697, "percentage": 58.29, "elapsed_time": "0:49:14", "remaining_time": "0:35:14"}
287
- {"current_steps": 240, "total_steps": 410, "loss": 0.0186, "lr": 4.3843160261067655e-05, "epoch": 2.909090909090909, "percentage": 58.54, "elapsed_time": "0:49:26", "remaining_time": "0:35:00"}
288
- {"current_steps": 240, "total_steps": 410, "eval_loss": 0.022352781146764755, "epoch": 2.909090909090909, "percentage": 58.54, "elapsed_time": "0:49:32", "remaining_time": "0:35:05"}
289
- {"current_steps": 241, "total_steps": 410, "loss": 0.0181, "lr": 4.342093806672678e-05, "epoch": 2.9212121212121214, "percentage": 58.78, "elapsed_time": "0:49:43", "remaining_time": "0:34:52"}
290
- {"current_steps": 242, "total_steps": 410, "loss": 0.0203, "lr": 4.2999192751568564e-05, "epoch": 2.9333333333333336, "percentage": 59.02, "elapsed_time": "0:49:52", "remaining_time": "0:34:37"}
291
- {"current_steps": 243, "total_steps": 410, "loss": 0.0181, "lr": 4.2577954885537986e-05, "epoch": 2.9454545454545453, "percentage": 59.27, "elapsed_time": "0:50:04", "remaining_time": "0:34:25"}
292
- {"current_steps": 244, "total_steps": 410, "loss": 0.0191, "lr": 4.215725500179787e-05, "epoch": 2.9575757575757575, "percentage": 59.51, "elapsed_time": "0:50:14", "remaining_time": "0:34:11"}
293
- {"current_steps": 245, "total_steps": 410, "loss": 0.0201, "lr": 4.1737123594515756e-05, "epoch": 2.9696969696969697, "percentage": 59.76, "elapsed_time": "0:50:23", "remaining_time": "0:33:56"}
294
- {"current_steps": 245, "total_steps": 410, "eval_loss": 0.02198323793709278, "epoch": 2.9696969696969697, "percentage": 59.76, "elapsed_time": "0:50:30", "remaining_time": "0:34:00"}
295
- {"current_steps": 246, "total_steps": 410, "loss": 0.0191, "lr": 4.131759111665349e-05, "epoch": 2.981818181818182, "percentage": 60.0, "elapsed_time": "0:50:41", "remaining_time": "0:33:47"}
296
- {"current_steps": 247, "total_steps": 410, "loss": 0.0185, "lr": 4.089868797775989e-05, "epoch": 2.993939393939394, "percentage": 60.24, "elapsed_time": "0:50:50", "remaining_time": "0:33:33"}
297
- {"current_steps": 248, "total_steps": 410, "loss": 0.0301, "lr": 4.0480444541766576e-05, "epoch": 3.006060606060606, "percentage": 60.49, "elapsed_time": "0:50:59", "remaining_time": "0:33:18"}
298
- {"current_steps": 249, "total_steps": 410, "loss": 0.0188, "lr": 4.0062891124787e-05, "epoch": 3.018181818181818, "percentage": 60.73, "elapsed_time": "0:51:11", "remaining_time": "0:33:06"}
299
- {"current_steps": 250, "total_steps": 410, "loss": 0.0147, "lr": 3.964605799291897e-05, "epoch": 3.0303030303030303, "percentage": 60.98, "elapsed_time": "0:51:22", "remaining_time": "0:32:52"}
300
- {"current_steps": 250, "total_steps": 410, "eval_loss": 0.021969465538859367, "epoch": 3.0303030303030303, "percentage": 60.98, "elapsed_time": "0:51:28", "remaining_time": "0:32:56"}
301
- {"current_steps": 251, "total_steps": 410, "loss": 0.0178, "lr": 3.922997536005094e-05, "epoch": 3.0424242424242425, "percentage": 61.22, "elapsed_time": "0:51:47", "remaining_time": "0:32:48"}
302
- {"current_steps": 252, "total_steps": 410, "loss": 0.0157, "lr": 3.8814673385671894e-05, "epoch": 3.0545454545454547, "percentage": 61.46, "elapsed_time": "0:51:58", "remaining_time": "0:32:35"}
303
- {"current_steps": 253, "total_steps": 410, "loss": 0.0161, "lr": 3.840018217268527e-05, "epoch": 3.066666666666667, "percentage": 61.71, "elapsed_time": "0:52:06", "remaining_time": "0:32:20"}
304
- {"current_steps": 254, "total_steps": 410, "loss": 0.0161, "lr": 3.7986531765226964e-05, "epoch": 3.0787878787878786, "percentage": 61.95, "elapsed_time": "0:52:18", "remaining_time": "0:32:07"}
305
- {"current_steps": 255, "total_steps": 410, "loss": 0.0142, "lr": 3.757375214648764e-05, "epoch": 3.090909090909091, "percentage": 62.2, "elapsed_time": "0:52:29", "remaining_time": "0:31:54"}
306
- {"current_steps": 255, "total_steps": 410, "eval_loss": 0.022621195763349533, "epoch": 3.090909090909091, "percentage": 62.2, "elapsed_time": "0:52:36", "remaining_time": "0:31:58"}
307
- {"current_steps": 256, "total_steps": 410, "loss": 0.0167, "lr": 3.716187323653939e-05, "epoch": 3.103030303030303, "percentage": 62.44, "elapsed_time": "0:52:46", "remaining_time": "0:31:44"}
308
- {"current_steps": 257, "total_steps": 410, "loss": 0.0168, "lr": 3.675092489016693e-05, "epoch": 3.1151515151515152, "percentage": 62.68, "elapsed_time": "0:52:55", "remaining_time": "0:31:30"}
309
- {"current_steps": 258, "total_steps": 410, "loss": 0.017, "lr": 3.634093689470371e-05, "epoch": 3.1272727272727274, "percentage": 62.93, "elapsed_time": "0:53:06", "remaining_time": "0:31:17"}
310
- {"current_steps": 259, "total_steps": 410, "loss": 0.016, "lr": 3.5931938967872766e-05, "epoch": 3.1393939393939396, "percentage": 63.17, "elapsed_time": "0:53:15", "remaining_time": "0:31:03"}
311
- {"current_steps": 260, "total_steps": 410, "loss": 0.0149, "lr": 3.5523960755632574e-05, "epoch": 3.1515151515151514, "percentage": 63.41, "elapsed_time": "0:53:26", "remaining_time": "0:30:49"}
312
- {"current_steps": 260, "total_steps": 410, "eval_loss": 0.021824924275279045, "epoch": 3.1515151515151514, "percentage": 63.41, "elapsed_time": "0:53:32", "remaining_time": "0:30:53"}
313
- {"current_steps": 261, "total_steps": 410, "loss": 0.0127, "lr": 3.5117031830028274e-05, "epoch": 3.1636363636363636, "percentage": 63.66, "elapsed_time": "0:53:45", "remaining_time": "0:30:41"}
314
- {"current_steps": 262, "total_steps": 410, "loss": 0.015, "lr": 3.471118168704811e-05, "epoch": 3.175757575757576, "percentage": 63.9, "elapsed_time": "0:53:56", "remaining_time": "0:30:28"}
315
- {"current_steps": 263, "total_steps": 410, "loss": 0.0154, "lr": 3.4306439744485454e-05, "epoch": 3.187878787878788, "percentage": 64.15, "elapsed_time": "0:54:08", "remaining_time": "0:30:15"}
316
- {"current_steps": 264, "total_steps": 410, "loss": 0.0167, "lr": 3.390283533980646e-05, "epoch": 3.2, "percentage": 64.39, "elapsed_time": "0:54:19", "remaining_time": "0:30:02"}
317
- {"current_steps": 265, "total_steps": 410, "loss": 0.0151, "lr": 3.350039772802354e-05, "epoch": 3.212121212121212, "percentage": 64.63, "elapsed_time": "0:54:32", "remaining_time": "0:29:50"}
318
- {"current_steps": 265, "total_steps": 410, "eval_loss": 0.02153392694890499, "epoch": 3.212121212121212, "percentage": 64.63, "elapsed_time": "0:54:38", "remaining_time": "0:29:53"}
319
- {"current_steps": 266, "total_steps": 410, "loss": 0.0171, "lr": 3.309915607957487e-05, "epoch": 3.224242424242424, "percentage": 64.88, "elapsed_time": "0:54:48", "remaining_time": "0:29:40"}
320
- {"current_steps": 267, "total_steps": 410, "loss": 0.0158, "lr": 3.269913947820998e-05, "epoch": 3.2363636363636363, "percentage": 65.12, "elapsed_time": "0:54:58", "remaining_time": "0:29:26"}
321
- {"current_steps": 268, "total_steps": 410, "loss": 0.0156, "lr": 3.2300376918881624e-05, "epoch": 3.2484848484848485, "percentage": 65.37, "elapsed_time": "0:55:10", "remaining_time": "0:29:13"}
322
- {"current_steps": 269, "total_steps": 410, "loss": 0.0134, "lr": 3.1902897305644095e-05, "epoch": 3.2606060606060607, "percentage": 65.61, "elapsed_time": "0:55:19", "remaining_time": "0:29:00"}
323
- {"current_steps": 270, "total_steps": 410, "loss": 0.0174, "lr": 3.1506729449558184e-05, "epoch": 3.2727272727272725, "percentage": 65.85, "elapsed_time": "0:55:30", "remaining_time": "0:28:46"}
324
- {"current_steps": 270, "total_steps": 410, "eval_loss": 0.021679332479834557, "epoch": 3.2727272727272725, "percentage": 65.85, "elapsed_time": "0:55:36", "remaining_time": "0:28:50"}
325
- {"current_steps": 271, "total_steps": 410, "loss": 0.018, "lr": 3.1111902066602724e-05, "epoch": 3.2848484848484847, "percentage": 66.1, "elapsed_time": "0:55:49", "remaining_time": "0:28:37"}
326
- {"current_steps": 272, "total_steps": 410, "loss": 0.016, "lr": 3.071844377559323e-05, "epoch": 3.296969696969697, "percentage": 66.34, "elapsed_time": "0:55:59", "remaining_time": "0:28:24"}
327
- {"current_steps": 273, "total_steps": 410, "loss": 0.014, "lr": 3.0326383096107426e-05, "epoch": 3.309090909090909, "percentage": 66.59, "elapsed_time": "0:56:08", "remaining_time": "0:28:10"}
328
- {"current_steps": 274, "total_steps": 410, "loss": 0.0169, "lr": 2.9935748446418066e-05, "epoch": 3.3212121212121213, "percentage": 66.83, "elapsed_time": "0:56:21", "remaining_time": "0:27:58"}
329
- {"current_steps": 275, "total_steps": 410, "loss": 0.0172, "lr": 2.9546568141433006e-05, "epoch": 3.3333333333333335, "percentage": 67.07, "elapsed_time": "0:56:33", "remaining_time": "0:27:45"}
330
- {"current_steps": 275, "total_steps": 410, "eval_loss": 0.021324800327420235, "epoch": 3.3333333333333335, "percentage": 67.07, "elapsed_time": "0:56:39", "remaining_time": "0:27:48"}
331
- {"current_steps": 276, "total_steps": 410, "loss": 0.0141, "lr": 2.915887039064287e-05, "epoch": 3.3454545454545457, "percentage": 67.32, "elapsed_time": "0:56:51", "remaining_time": "0:27:36"}
332
- {"current_steps": 277, "total_steps": 410, "loss": 0.0126, "lr": 2.8772683296076196e-05, "epoch": 3.3575757575757574, "percentage": 67.56, "elapsed_time": "0:57:01", "remaining_time": "0:27:22"}
333
- {"current_steps": 278, "total_steps": 410, "loss": 0.0376, "lr": 2.8388034850262646e-05, "epoch": 3.3696969696969696, "percentage": 67.8, "elapsed_time": "0:57:14", "remaining_time": "0:27:10"}
334
- {"current_steps": 279, "total_steps": 410, "loss": 0.017, "lr": 2.8004952934203838e-05, "epoch": 3.381818181818182, "percentage": 68.05, "elapsed_time": "0:57:26", "remaining_time": "0:26:58"}
335
- {"current_steps": 280, "total_steps": 410, "loss": 0.017, "lr": 2.762346531535246e-05, "epoch": 3.393939393939394, "percentage": 68.29, "elapsed_time": "0:57:38", "remaining_time": "0:26:45"}
336
- {"current_steps": 280, "total_steps": 410, "eval_loss": 0.02108747698366642, "epoch": 3.393939393939394, "percentage": 68.29, "elapsed_time": "0:57:44", "remaining_time": "0:26:48"}
337
- {"current_steps": 281, "total_steps": 410, "loss": 0.014, "lr": 2.7243599645599576e-05, "epoch": 3.4060606060606062, "percentage": 68.54, "elapsed_time": "0:57:59", "remaining_time": "0:26:37"}
338
- {"current_steps": 282, "total_steps": 410, "loss": 0.0158, "lr": 2.6865383459270265e-05, "epoch": 3.418181818181818, "percentage": 68.78, "elapsed_time": "0:58:11", "remaining_time": "0:26:24"}
339
- {"current_steps": 283, "total_steps": 410, "loss": 0.017, "lr": 2.6488844171127903e-05, "epoch": 3.43030303030303, "percentage": 69.02, "elapsed_time": "0:58:23", "remaining_time": "0:26:12"}
340
- {"current_steps": 284, "total_steps": 410, "loss": 0.0124, "lr": 2.6114009074386846e-05, "epoch": 3.4424242424242424, "percentage": 69.27, "elapsed_time": "0:58:33", "remaining_time": "0:25:58"}
341
- {"current_steps": 285, "total_steps": 410, "loss": 0.0223, "lr": 2.574090533873431e-05, "epoch": 3.4545454545454546, "percentage": 69.51, "elapsed_time": "0:58:44", "remaining_time": "0:25:46"}
342
- {"current_steps": 285, "total_steps": 410, "eval_loss": 0.021236957982182503, "epoch": 3.4545454545454546, "percentage": 69.51, "elapsed_time": "0:58:51", "remaining_time": "0:25:48"}
343
- {"current_steps": 286, "total_steps": 410, "loss": 0.0132, "lr": 2.5369560008360828e-05, "epoch": 3.466666666666667, "percentage": 69.76, "elapsed_time": "0:59:00", "remaining_time": "0:25:35"}
344
- {"current_steps": 287, "total_steps": 410, "loss": 0.0132, "lr": 2.500000000000001e-05, "epoch": 3.4787878787878785, "percentage": 70.0, "elapsed_time": "0:59:11", "remaining_time": "0:25:22"}
345
- {"current_steps": 288, "total_steps": 410, "loss": 0.0136, "lr": 2.4632252100977566e-05, "epoch": 3.4909090909090907, "percentage": 70.24, "elapsed_time": "0:59:24", "remaining_time": "0:25:09"}
346
- {"current_steps": 289, "total_steps": 410, "loss": 0.0157, "lr": 2.4266342967269552e-05, "epoch": 3.503030303030303, "percentage": 70.49, "elapsed_time": "0:59:36", "remaining_time": "0:24:57"}
347
- {"current_steps": 290, "total_steps": 410, "loss": 0.0144, "lr": 2.3902299121570333e-05, "epoch": 3.515151515151515, "percentage": 70.73, "elapsed_time": "0:59:45", "remaining_time": "0:24:43"}
348
- {"current_steps": 290, "total_steps": 410, "eval_loss": 0.02107882872223854, "epoch": 3.515151515151515, "percentage": 70.73, "elapsed_time": "0:59:52", "remaining_time": "0:24:46"}
349
- {"current_steps": 291, "total_steps": 410, "loss": 0.0131, "lr": 2.354014695136997e-05, "epoch": 3.5272727272727273, "percentage": 70.98, "elapsed_time": "1:00:05", "remaining_time": "0:24:34"}
350
- {"current_steps": 292, "total_steps": 410, "loss": 0.0151, "lr": 2.317991270704167e-05, "epoch": 3.5393939393939395, "percentage": 71.22, "elapsed_time": "1:00:15", "remaining_time": "0:24:21"}
351
- {"current_steps": 293, "total_steps": 410, "loss": 0.0125, "lr": 2.282162249993895e-05, "epoch": 3.5515151515151517, "percentage": 71.46, "elapsed_time": "1:00:25", "remaining_time": "0:24:07"}
352
- {"current_steps": 294, "total_steps": 410, "loss": 0.0162, "lr": 2.246530230050301e-05, "epoch": 3.5636363636363635, "percentage": 71.71, "elapsed_time": "1:00:35", "remaining_time": "0:23:54"}
353
- {"current_steps": 295, "total_steps": 410, "loss": 0.0125, "lr": 2.211097793638029e-05, "epoch": 3.5757575757575757, "percentage": 71.95, "elapsed_time": "1:00:44", "remaining_time": "0:23:40"}
354
- {"current_steps": 295, "total_steps": 410, "eval_loss": 0.020796656608581543, "epoch": 3.5757575757575757, "percentage": 71.95, "elapsed_time": "1:00:50", "remaining_time": "0:23:43"}
355
- {"current_steps": 296, "total_steps": 410, "loss": 0.0111, "lr": 2.175867509055033e-05, "epoch": 3.587878787878788, "percentage": 72.2, "elapsed_time": "1:01:01", "remaining_time": "0:23:30"}
356
- {"current_steps": 297, "total_steps": 410, "loss": 0.0165, "lr": 2.1408419299464245e-05, "epoch": 3.6, "percentage": 72.44, "elapsed_time": "1:01:09", "remaining_time": "0:23:16"}
357
- {"current_steps": 298, "total_steps": 410, "loss": 0.0139, "lr": 2.106023595119358e-05, "epoch": 3.6121212121212123, "percentage": 72.68, "elapsed_time": "1:01:21", "remaining_time": "0:23:03"}
358
- {"current_steps": 299, "total_steps": 410, "loss": 0.0148, "lr": 2.071415028359026e-05, "epoch": 3.624242424242424, "percentage": 72.93, "elapsed_time": "1:01:32", "remaining_time": "0:22:50"}
359
- {"current_steps": 300, "total_steps": 410, "loss": 0.0163, "lr": 2.0370187382457068e-05, "epoch": 3.6363636363636362, "percentage": 73.17, "elapsed_time": "1:01:44", "remaining_time": "0:22:38"}
360
- {"current_steps": 300, "total_steps": 410, "eval_loss": 0.02069205790758133, "epoch": 3.6363636363636362, "percentage": 73.17, "elapsed_time": "1:01:51", "remaining_time": "0:22:40"}
361
- {"current_steps": 301, "total_steps": 410, "loss": 0.0143, "lr": 2.0028372179729403e-05, "epoch": 3.6484848484848484, "percentage": 73.41, "elapsed_time": "1:02:08", "remaining_time": "0:22:30"}
362
- {"current_steps": 302, "total_steps": 410, "loss": 0.0168, "lr": 1.9688729451668114e-05, "epoch": 3.6606060606060606, "percentage": 73.66, "elapsed_time": "1:02:18", "remaining_time": "0:22:16"}
363
- {"current_steps": 303, "total_steps": 410, "loss": 0.0129, "lr": 1.935128381706355e-05, "epoch": 3.672727272727273, "percentage": 73.9, "elapsed_time": "1:02:29", "remaining_time": "0:22:04"}
364
- {"current_steps": 304, "total_steps": 410, "loss": 0.0194, "lr": 1.901605973545116e-05, "epoch": 3.6848484848484846, "percentage": 74.15, "elapsed_time": "1:02:43", "remaining_time": "0:21:52"}
365
- {"current_steps": 305, "total_steps": 410, "loss": 0.015, "lr": 1.868308150533847e-05, "epoch": 3.6969696969696972, "percentage": 74.39, "elapsed_time": "1:02:54", "remaining_time": "0:21:39"}
366
- {"current_steps": 305, "total_steps": 410, "eval_loss": 0.020683376118540764, "epoch": 3.6969696969696972, "percentage": 74.39, "elapsed_time": "1:03:00", "remaining_time": "0:21:41"}
367
- {"current_steps": 306, "total_steps": 410, "loss": 0.0147, "lr": 1.8352373262443916e-05, "epoch": 3.709090909090909, "percentage": 74.63, "elapsed_time": "1:03:11", "remaining_time": "0:21:28"}
368
- {"current_steps": 307, "total_steps": 410, "loss": 0.0157, "lr": 1.8023958977947304e-05, "epoch": 3.721212121212121, "percentage": 74.88, "elapsed_time": "1:03:21", "remaining_time": "0:21:15"}
369
- {"current_steps": 308, "total_steps": 410, "loss": 0.0152, "lr": 1.7697862456752273e-05, "epoch": 3.7333333333333334, "percentage": 75.12, "elapsed_time": "1:03:32", "remaining_time": "0:21:02"}
370
- {"current_steps": 309, "total_steps": 410, "loss": 0.0172, "lr": 1.7374107335760936e-05, "epoch": 3.7454545454545456, "percentage": 75.37, "elapsed_time": "1:03:41", "remaining_time": "0:20:49"}
371
- {"current_steps": 310, "total_steps": 410, "loss": 0.0154, "lr": 1.7052717082160346e-05, "epoch": 3.757575757575758, "percentage": 75.61, "elapsed_time": "1:03:53", "remaining_time": "0:20:36"}
372
- {"current_steps": 310, "total_steps": 410, "eval_loss": 0.02056981809437275, "epoch": 3.757575757575758, "percentage": 75.61, "elapsed_time": "1:03:59", "remaining_time": "0:20:38"}
373
- {"current_steps": 311, "total_steps": 410, "loss": 0.015, "lr": 1.673371499172174e-05, "epoch": 3.7696969696969695, "percentage": 75.85, "elapsed_time": "1:04:09", "remaining_time": "0:20:25"}
374
- {"current_steps": 312, "total_steps": 410, "loss": 0.017, "lr": 1.6417124187111775e-05, "epoch": 3.7818181818181817, "percentage": 76.1, "elapsed_time": "1:04:20", "remaining_time": "0:20:12"}
375
- {"current_steps": 313, "total_steps": 410, "loss": 0.0145, "lr": 1.610296761621662e-05, "epoch": 3.793939393939394, "percentage": 76.34, "elapsed_time": "1:04:30", "remaining_time": "0:19:59"}
376
- {"current_steps": 314, "total_steps": 410, "loss": 0.0228, "lr": 1.5791268050478486e-05, "epoch": 3.806060606060606, "percentage": 76.59, "elapsed_time": "1:04:40", "remaining_time": "0:19:46"}
377
- {"current_steps": 315, "total_steps": 410, "loss": 0.0186, "lr": 1.5482048083245114e-05, "epoch": 3.8181818181818183, "percentage": 76.83, "elapsed_time": "1:04:53", "remaining_time": "0:19:34"}
378
- {"current_steps": 315, "total_steps": 410, "eval_loss": 0.02028246596455574, "epoch": 3.8181818181818183, "percentage": 76.83, "elapsed_time": "1:04:59", "remaining_time": "0:19:36"}
379
- {"current_steps": 316, "total_steps": 410, "loss": 0.0159, "lr": 1.517533012813217e-05, "epoch": 3.83030303030303, "percentage": 77.07, "elapsed_time": "1:05:12", "remaining_time": "0:19:23"}
380
- {"current_steps": 317, "total_steps": 410, "loss": 0.0123, "lr": 1.4871136417398406e-05, "epoch": 3.8424242424242423, "percentage": 77.32, "elapsed_time": "1:05:24", "remaining_time": "0:19:11"}
381
- {"current_steps": 318, "total_steps": 410, "loss": 0.0137, "lr": 1.4569489000334436e-05, "epoch": 3.8545454545454545, "percentage": 77.56, "elapsed_time": "1:05:35", "remaining_time": "0:18:58"}
382
- {"current_steps": 319, "total_steps": 410, "loss": 0.0159, "lr": 1.427040974166427e-05, "epoch": 3.8666666666666667, "percentage": 77.8, "elapsed_time": "1:05:44", "remaining_time": "0:18:45"}
383
- {"current_steps": 320, "total_steps": 410, "loss": 0.0135, "lr": 1.3973920319960655e-05, "epoch": 3.878787878787879, "percentage": 78.05, "elapsed_time": "1:05:53", "remaining_time": "0:18:31"}
384
- {"current_steps": 320, "total_steps": 410, "eval_loss": 0.020162392407655716, "epoch": 3.878787878787879, "percentage": 78.05, "elapsed_time": "1:05:59", "remaining_time": "0:18:33"}
385
- {"current_steps": 321, "total_steps": 410, "loss": 0.0148, "lr": 1.3680042226073552e-05, "epoch": 3.8909090909090907, "percentage": 78.29, "elapsed_time": "1:06:09", "remaining_time": "0:18:20"}
386
- {"current_steps": 322, "total_steps": 410, "loss": 0.0141, "lr": 1.3388796761572492e-05, "epoch": 3.9030303030303033, "percentage": 78.54, "elapsed_time": "1:06:20", "remaining_time": "0:18:07"}
387
- {"current_steps": 323, "total_steps": 410, "loss": 0.0132, "lr": 1.310020503720254e-05, "epoch": 3.915151515151515, "percentage": 78.78, "elapsed_time": "1:06:32", "remaining_time": "0:17:55"}
388
- {"current_steps": 324, "total_steps": 410, "loss": 0.0161, "lr": 1.2814287971354022e-05, "epoch": 3.9272727272727272, "percentage": 79.02, "elapsed_time": "1:06:41", "remaining_time": "0:17:42"}
389
- {"current_steps": 325, "total_steps": 410, "loss": 0.0159, "lr": 1.253106628854635e-05, "epoch": 3.9393939393939394, "percentage": 79.27, "elapsed_time": "1:06:52", "remaining_time": "0:17:29"}
390
- {"current_steps": 325, "total_steps": 410, "eval_loss": 0.020128030329942703, "epoch": 3.9393939393939394, "percentage": 79.27, "elapsed_time": "1:06:58", "remaining_time": "0:17:30"}
391
- {"current_steps": 326, "total_steps": 410, "loss": 0.0142, "lr": 1.2250560517925746e-05, "epoch": 3.9515151515151516, "percentage": 79.51, "elapsed_time": "1:07:07", "remaining_time": "0:17:17"}
392
- {"current_steps": 327, "total_steps": 410, "loss": 0.0155, "lr": 1.1972790991777311e-05, "epoch": 3.963636363636364, "percentage": 79.76, "elapsed_time": "1:07:19", "remaining_time": "0:17:05"}
393
- {"current_steps": 328, "total_steps": 410, "loss": 0.0142, "lr": 1.1697777844051105e-05, "epoch": 3.9757575757575756, "percentage": 80.0, "elapsed_time": "1:07:31", "remaining_time": "0:16:52"}
394
- {"current_steps": 329, "total_steps": 410, "loss": 0.0147, "lr": 1.1425541008902851e-05, "epoch": 3.987878787878788, "percentage": 80.24, "elapsed_time": "1:07:41", "remaining_time": "0:16:39"}
395
- {"current_steps": 330, "total_steps": 410, "loss": 0.0211, "lr": 1.1156100219249022e-05, "epoch": 4.0, "percentage": 80.49, "elapsed_time": "1:07:52", "remaining_time": "0:16:27"}
396
- {"current_steps": 330, "total_steps": 410, "eval_loss": 0.01995450258255005, "epoch": 4.0, "percentage": 80.49, "elapsed_time": "1:07:58", "remaining_time": "0:16:28"}
397
- {"current_steps": 331, "total_steps": 410, "loss": 0.0133, "lr": 1.0889475005336446e-05, "epoch": 4.012121212121212, "percentage": 80.73, "elapsed_time": "1:08:07", "remaining_time": "0:16:15"}
398
- {"current_steps": 332, "total_steps": 410, "loss": 0.013, "lr": 1.0625684693326727e-05, "epoch": 4.024242424242424, "percentage": 80.98, "elapsed_time": "1:08:19", "remaining_time": "0:16:03"}
399
- {"current_steps": 333, "total_steps": 410, "loss": 0.0132, "lr": 1.036474840389537e-05, "epoch": 4.036363636363636, "percentage": 81.22, "elapsed_time": "1:08:28", "remaining_time": "0:15:50"}
400
- {"current_steps": 334, "total_steps": 410, "loss": 0.0121, "lr": 1.0106685050845838e-05, "epoch": 4.048484848484849, "percentage": 81.46, "elapsed_time": "1:08:38", "remaining_time": "0:15:37"}
401
- {"current_steps": 335, "total_steps": 410, "loss": 0.0134, "lr": 9.851513339738628e-06, "epoch": 4.0606060606060606, "percentage": 81.71, "elapsed_time": "1:08:49", "remaining_time": "0:15:24"}
402
- {"current_steps": 335, "total_steps": 410, "eval_loss": 0.0202109944075346, "epoch": 4.0606060606060606, "percentage": 81.71, "elapsed_time": "1:08:55", "remaining_time": "0:15:25"}
403
- {"current_steps": 336, "total_steps": 410, "loss": 0.0121, "lr": 9.599251766535345e-06, "epoch": 4.072727272727272, "percentage": 81.95, "elapsed_time": "1:09:07", "remaining_time": "0:15:13"}
404
- {"current_steps": 337, "total_steps": 410, "loss": 0.0126, "lr": 9.349918616258114e-06, "epoch": 4.084848484848485, "percentage": 82.2, "elapsed_time": "1:09:16", "remaining_time": "0:15:00"}
405
- {"current_steps": 338, "total_steps": 410, "loss": 0.0122, "lr": 9.103531961664118e-06, "epoch": 4.096969696969697, "percentage": 82.44, "elapsed_time": "1:09:27", "remaining_time": "0:14:47"}
406
- {"current_steps": 339, "total_steps": 410, "loss": 0.0155, "lr": 8.860109661935674e-06, "epoch": 4.109090909090909, "percentage": 82.68, "elapsed_time": "1:09:40", "remaining_time": "0:14:35"}
407
- {"current_steps": 340, "total_steps": 410, "loss": 0.0113, "lr": 8.619669361385663e-06, "epoch": 4.121212121212121, "percentage": 82.93, "elapsed_time": "1:09:50", "remaining_time": "0:14:22"}
408
- {"current_steps": 340, "total_steps": 410, "eval_loss": 0.020561667159199715, "epoch": 4.121212121212121, "percentage": 82.93, "elapsed_time": "1:09:56", "remaining_time": "0:14:24"}
409
- {"current_steps": 341, "total_steps": 410, "loss": 0.0127, "lr": 8.38222848817864e-06, "epoch": 4.133333333333334, "percentage": 83.17, "elapsed_time": "1:10:07", "remaining_time": "0:14:11"}
410
- {"current_steps": 342, "total_steps": 410, "loss": 0.0121, "lr": 8.14780425306758e-06, "epoch": 4.1454545454545455, "percentage": 83.41, "elapsed_time": "1:10:15", "remaining_time": "0:13:58"}
411
- {"current_steps": 343, "total_steps": 410, "loss": 0.0109, "lr": 7.91641364814628e-06, "epoch": 4.157575757575757, "percentage": 83.66, "elapsed_time": "1:10:26", "remaining_time": "0:13:45"}
412
- {"current_steps": 344, "total_steps": 410, "loss": 0.0108, "lr": 7.688073445617799e-06, "epoch": 4.16969696969697, "percentage": 83.9, "elapsed_time": "1:10:35", "remaining_time": "0:13:32"}
413
- {"current_steps": 345, "total_steps": 410, "loss": 0.0117, "lr": 7.462800196578662e-06, "epoch": 4.181818181818182, "percentage": 84.15, "elapsed_time": "1:10:46", "remaining_time": "0:13:19"}
414
- {"current_steps": 345, "total_steps": 410, "eval_loss": 0.0208114180713892, "epoch": 4.181818181818182, "percentage": 84.15, "elapsed_time": "1:10:52", "remaining_time": "0:13:21"}
415
- {"current_steps": 346, "total_steps": 410, "loss": 0.013, "lr": 7.240610229819195e-06, "epoch": 4.193939393939394, "percentage": 84.39, "elapsed_time": "1:11:05", "remaining_time": "0:13:09"}
416
- {"current_steps": 347, "total_steps": 410, "loss": 0.0108, "lr": 7.0215196506399515e-06, "epoch": 4.206060606060606, "percentage": 84.63, "elapsed_time": "1:11:18", "remaining_time": "0:12:56"}
417
- {"current_steps": 348, "total_steps": 410, "loss": 0.0103, "lr": 6.8055443396842945e-06, "epoch": 4.218181818181818, "percentage": 84.88, "elapsed_time": "1:11:30", "remaining_time": "0:12:44"}
418
- {"current_steps": 349, "total_steps": 410, "loss": 0.0138, "lr": 6.592699951787362e-06, "epoch": 4.2303030303030305, "percentage": 85.12, "elapsed_time": "1:11:41", "remaining_time": "0:12:31"}
419
- {"current_steps": 350, "total_steps": 410, "loss": 0.0108, "lr": 6.3830019148412525e-06, "epoch": 4.242424242424242, "percentage": 85.37, "elapsed_time": "1:11:53", "remaining_time": "0:12:19"}
420
- {"current_steps": 350, "total_steps": 410, "eval_loss": 0.020906535908579826, "epoch": 4.242424242424242, "percentage": 85.37, "elapsed_time": "1:11:59", "remaining_time": "0:12:20"}
421
- {"current_steps": 351, "total_steps": 410, "loss": 0.0144, "lr": 6.17646542867682e-06, "epoch": 4.254545454545455, "percentage": 85.61, "elapsed_time": "1:12:16", "remaining_time": "0:12:08"}
422
- {"current_steps": 352, "total_steps": 410, "loss": 0.0107, "lr": 5.973105463961865e-06, "epoch": 4.266666666666667, "percentage": 85.85, "elapsed_time": "1:12:28", "remaining_time": "0:11:56"}
423
- {"current_steps": 353, "total_steps": 410, "loss": 0.0139, "lr": 5.772936761116027e-06, "epoch": 4.278787878787879, "percentage": 86.1, "elapsed_time": "1:12:37", "remaining_time": "0:11:43"}
424
- {"current_steps": 354, "total_steps": 410, "loss": 0.0126, "lr": 5.575973829242364e-06, "epoch": 4.290909090909091, "percentage": 86.34, "elapsed_time": "1:12:47", "remaining_time": "0:11:30"}
425
- {"current_steps": 355, "total_steps": 410, "loss": 0.012, "lr": 5.382230945075556e-06, "epoch": 4.303030303030303, "percentage": 86.59, "elapsed_time": "1:12:58", "remaining_time": "0:11:18"}
426
- {"current_steps": 355, "total_steps": 410, "eval_loss": 0.020746439695358276, "epoch": 4.303030303030303, "percentage": 86.59, "elapsed_time": "1:13:04", "remaining_time": "0:11:19"}
427
- {"current_steps": 356, "total_steps": 410, "loss": 0.0099, "lr": 5.191722151947226e-06, "epoch": 4.315151515151515, "percentage": 86.83, "elapsed_time": "1:13:16", "remaining_time": "0:11:06"}
428
- {"current_steps": 357, "total_steps": 410, "loss": 0.0143, "lr": 5.004461258767873e-06, "epoch": 4.327272727272727, "percentage": 87.07, "elapsed_time": "1:13:28", "remaining_time": "0:10:54"}
429
- {"current_steps": 358, "total_steps": 410, "loss": 0.0126, "lr": 4.820461839026047e-06, "epoch": 4.33939393939394, "percentage": 87.32, "elapsed_time": "1:13:39", "remaining_time": "0:10:41"}
430
- {"current_steps": 359, "total_steps": 410, "loss": 0.0115, "lr": 4.639737229804403e-06, "epoch": 4.351515151515152, "percentage": 87.56, "elapsed_time": "1:13:51", "remaining_time": "0:10:29"}
431
- {"current_steps": 360, "total_steps": 410, "loss": 0.0111, "lr": 4.462300530813024e-06, "epoch": 4.363636363636363, "percentage": 87.8, "elapsed_time": "1:14:01", "remaining_time": "0:10:16"}
432
- {"current_steps": 360, "total_steps": 410, "eval_loss": 0.020565090700984, "epoch": 4.363636363636363, "percentage": 87.8, "elapsed_time": "1:14:07", "remaining_time": "0:10:17"}
433
- {"current_steps": 361, "total_steps": 410, "loss": 0.0114, "lr": 4.2881646034398925e-06, "epoch": 4.375757575757576, "percentage": 88.05, "elapsed_time": "1:14:18", "remaining_time": "0:10:05"}
434
- {"current_steps": 362, "total_steps": 410, "loss": 0.0113, "lr": 4.117342069818603e-06, "epoch": 4.387878787878788, "percentage": 88.29, "elapsed_time": "1:14:27", "remaining_time": "0:09:52"}
435
- {"current_steps": 363, "total_steps": 410, "loss": 0.0115, "lr": 3.949845311913492e-06, "epoch": 4.4, "percentage": 88.54, "elapsed_time": "1:14:37", "remaining_time": "0:09:39"}
436
- {"current_steps": 364, "total_steps": 410, "loss": 0.0098, "lr": 3.7856864706221185e-06, "epoch": 4.412121212121212, "percentage": 88.78, "elapsed_time": "1:14:51", "remaining_time": "0:09:27"}
437
- {"current_steps": 365, "total_steps": 410, "loss": 0.0118, "lr": 3.6248774448952695e-06, "epoch": 4.424242424242424, "percentage": 89.02, "elapsed_time": "1:15:00", "remaining_time": "0:09:14"}
438
- {"current_steps": 365, "total_steps": 410, "eval_loss": 0.02050224132835865, "epoch": 4.424242424242424, "percentage": 89.02, "elapsed_time": "1:15:07", "remaining_time": "0:09:15"}
439
- {"current_steps": 366, "total_steps": 410, "loss": 0.0111, "lr": 3.467429890874424e-06, "epoch": 4.4363636363636365, "percentage": 89.27, "elapsed_time": "1:15:21", "remaining_time": "0:09:03"}
440
- {"current_steps": 367, "total_steps": 410, "loss": 0.0122, "lr": 3.3133552210468875e-06, "epoch": 4.448484848484848, "percentage": 89.51, "elapsed_time": "1:15:30", "remaining_time": "0:08:50"}
441
- {"current_steps": 368, "total_steps": 410, "loss": 0.0136, "lr": 3.162664603418608e-06, "epoch": 4.460606060606061, "percentage": 89.76, "elapsed_time": "1:15:42", "remaining_time": "0:08:38"}
442
- {"current_steps": 369, "total_steps": 410, "loss": 0.0116, "lr": 3.0153689607045845e-06, "epoch": 4.472727272727273, "percentage": 90.0, "elapsed_time": "1:15:56", "remaining_time": "0:08:26"}
443
- {"current_steps": 370, "total_steps": 410, "loss": 0.0099, "lr": 2.871478969537206e-06, "epoch": 4.484848484848484, "percentage": 90.24, "elapsed_time": "1:16:09", "remaining_time": "0:08:13"}
444
- {"current_steps": 370, "total_steps": 410, "eval_loss": 0.02058413252234459, "epoch": 4.484848484848484, "percentage": 90.24, "elapsed_time": "1:16:15", "remaining_time": "0:08:14"}
445
- {"current_steps": 371, "total_steps": 410, "loss": 0.0212, "lr": 2.731005059692332e-06, "epoch": 4.496969696969697, "percentage": 90.49, "elapsed_time": "1:16:26", "remaining_time": "0:08:02"}
446
- {"current_steps": 372, "total_steps": 410, "loss": 0.0275, "lr": 2.5939574133333312e-06, "epoch": 4.509090909090909, "percentage": 90.73, "elapsed_time": "1:16:37", "remaining_time": "0:07:49"}
447
- {"current_steps": 373, "total_steps": 410, "loss": 0.0104, "lr": 2.4603459642729863e-06, "epoch": 4.5212121212121215, "percentage": 90.98, "elapsed_time": "1:16:50", "remaining_time": "0:07:37"}
448
- {"current_steps": 374, "total_steps": 410, "loss": 0.0099, "lr": 2.330180397253473e-06, "epoch": 4.533333333333333, "percentage": 91.22, "elapsed_time": "1:17:01", "remaining_time": "0:07:24"}
449
- {"current_steps": 375, "total_steps": 410, "loss": 0.0118, "lr": 2.203470147244385e-06, "epoch": 4.545454545454545, "percentage": 91.46, "elapsed_time": "1:17:11", "remaining_time": "0:07:12"}
450
- {"current_steps": 375, "total_steps": 410, "eval_loss": 0.020584262907505035, "epoch": 4.545454545454545, "percentage": 91.46, "elapsed_time": "1:17:17", "remaining_time": "0:07:12"}
451
- {"current_steps": 376, "total_steps": 410, "loss": 0.0104, "lr": 2.0802243987588066e-06, "epoch": 4.557575757575758, "percentage": 91.71, "elapsed_time": "1:17:28", "remaining_time": "0:07:00"}
452
- {"current_steps": 377, "total_steps": 410, "loss": 0.0121, "lr": 1.9604520851876198e-06, "epoch": 4.569696969696969, "percentage": 91.95, "elapsed_time": "1:17:40", "remaining_time": "0:06:47"}
453
- {"current_steps": 378, "total_steps": 410, "loss": 0.0113, "lr": 1.8441618881519184e-06, "epoch": 4.581818181818182, "percentage": 92.2, "elapsed_time": "1:17:50", "remaining_time": "0:06:35"}
454
- {"current_steps": 379, "total_steps": 410, "loss": 0.0105, "lr": 1.7313622368738014e-06, "epoch": 4.593939393939394, "percentage": 92.44, "elapsed_time": "1:18:00", "remaining_time": "0:06:22"}
455
- {"current_steps": 380, "total_steps": 410, "loss": 0.0119, "lr": 1.6220613075653202e-06, "epoch": 4.606060606060606, "percentage": 92.68, "elapsed_time": "1:18:11", "remaining_time": "0:06:10"}
456
- {"current_steps": 380, "total_steps": 410, "eval_loss": 0.02056843228638172, "epoch": 4.606060606060606, "percentage": 92.68, "elapsed_time": "1:18:17", "remaining_time": "0:06:10"}
457
- {"current_steps": 381, "total_steps": 410, "loss": 0.0098, "lr": 1.51626702283586e-06, "epoch": 4.618181818181818, "percentage": 92.93, "elapsed_time": "1:18:28", "remaining_time": "0:05:58"}
458
- {"current_steps": 382, "total_steps": 410, "loss": 0.0116, "lr": 1.4139870511178766e-06, "epoch": 4.63030303030303, "percentage": 93.17, "elapsed_time": "1:18:39", "remaining_time": "0:05:45"}
459
- {"current_steps": 383, "total_steps": 410, "loss": 0.0101, "lr": 1.3152288061110518e-06, "epoch": 4.642424242424243, "percentage": 93.41, "elapsed_time": "1:18:51", "remaining_time": "0:05:33"}
460
- {"current_steps": 384, "total_steps": 410, "loss": 0.0113, "lr": 1.2199994462448904e-06, "epoch": 4.654545454545454, "percentage": 93.66, "elapsed_time": "1:19:03", "remaining_time": "0:05:21"}
461
- {"current_steps": 385, "total_steps": 410, "loss": 0.0114, "lr": 1.128305874159896e-06, "epoch": 4.666666666666667, "percentage": 93.9, "elapsed_time": "1:19:13", "remaining_time": "0:05:08"}
462
- {"current_steps": 385, "total_steps": 410, "eval_loss": 0.02059413306415081, "epoch": 4.666666666666667, "percentage": 93.9, "elapsed_time": "1:19:19", "remaining_time": "0:05:09"}
463
- {"current_steps": 386, "total_steps": 410, "loss": 0.0106, "lr": 1.040154736207194e-06, "epoch": 4.678787878787879, "percentage": 94.15, "elapsed_time": "1:19:29", "remaining_time": "0:04:56"}
464
- {"current_steps": 387, "total_steps": 410, "loss": 0.0122, "lr": 9.555524219667989e-07, "epoch": 4.690909090909091, "percentage": 94.39, "elapsed_time": "1:19:39", "remaining_time": "0:04:44"}
465
- {"current_steps": 388, "total_steps": 410, "loss": 0.0097, "lr": 8.745050637844532e-07, "epoch": 4.703030303030303, "percentage": 94.63, "elapsed_time": "1:19:50", "remaining_time": "0:04:31"}
466
- {"current_steps": 389, "total_steps": 410, "loss": 0.0121, "lr": 7.970185363271431e-07, "epoch": 4.715151515151515, "percentage": 94.88, "elapsed_time": "1:20:01", "remaining_time": "0:04:19"}
467
- {"current_steps": 390, "total_steps": 410, "loss": 0.0109, "lr": 7.230984561572729e-07, "epoch": 4.7272727272727275, "percentage": 95.12, "elapsed_time": "1:20:14", "remaining_time": "0:04:06"}
468
- {"current_steps": 390, "total_steps": 410, "eval_loss": 0.020591916516423225, "epoch": 4.7272727272727275, "percentage": 95.12, "elapsed_time": "1:20:20", "remaining_time": "0:04:07"}
469
- {"current_steps": 391, "total_steps": 410, "loss": 0.0165, "lr": 6.527501813255344e-07, "epoch": 4.739393939393939, "percentage": 95.37, "elapsed_time": "1:20:31", "remaining_time": "0:03:54"}
470
- {"current_steps": 392, "total_steps": 410, "loss": 0.0096, "lr": 5.859788109825793e-07, "epoch": 4.751515151515152, "percentage": 95.61, "elapsed_time": "1:20:47", "remaining_time": "0:03:42"}
471
- {"current_steps": 393, "total_steps": 410, "loss": 0.0129, "lr": 5.227891850093314e-07, "epoch": 4.763636363636364, "percentage": 95.85, "elapsed_time": "1:20:58", "remaining_time": "0:03:30"}
472
- {"current_steps": 394, "total_steps": 410, "loss": 0.0122, "lr": 4.6318588366625616e-07, "epoch": 4.775757575757575, "percentage": 96.1, "elapsed_time": "1:21:10", "remaining_time": "0:03:17"}
473
- {"current_steps": 395, "total_steps": 410, "loss": 0.0124, "lr": 4.071732272613149e-07, "epoch": 4.787878787878788, "percentage": 96.34, "elapsed_time": "1:21:19", "remaining_time": "0:03:05"}
474
- {"current_steps": 395, "total_steps": 410, "eval_loss": 0.020531287416815758, "epoch": 4.787878787878788, "percentage": 96.34, "elapsed_time": "1:21:25", "remaining_time": "0:03:05"}
475
- {"current_steps": 396, "total_steps": 410, "loss": 0.0112, "lr": 3.5475527583681e-07, "epoch": 4.8, "percentage": 96.59, "elapsed_time": "1:21:33", "remaining_time": "0:02:53"}
476
- {"current_steps": 397, "total_steps": 410, "loss": 0.0102, "lr": 3.059358288751202e-07, "epoch": 4.8121212121212125, "percentage": 96.83, "elapsed_time": "1:21:44", "remaining_time": "0:02:40"}
477
- {"current_steps": 398, "total_steps": 410, "loss": 0.0119, "lr": 2.6071842502326527e-07, "epoch": 4.824242424242424, "percentage": 97.07, "elapsed_time": "1:21:57", "remaining_time": "0:02:28"}
478
- {"current_steps": 399, "total_steps": 410, "loss": 0.0117, "lr": 2.1910634183644474e-07, "epoch": 4.836363636363636, "percentage": 97.32, "elapsed_time": "1:22:09", "remaining_time": "0:02:15"}
479
- {"current_steps": 400, "total_steps": 410, "loss": 0.0111, "lr": 1.811025955404333e-07, "epoch": 4.848484848484849, "percentage": 97.56, "elapsed_time": "1:22:20", "remaining_time": "0:02:03"}
480
- {"current_steps": 400, "total_steps": 410, "eval_loss": 0.020571600645780563, "epoch": 4.848484848484849, "percentage": 97.56, "elapsed_time": "1:22:26", "remaining_time": "0:02:03"}
481
- {"current_steps": 401, "total_steps": 410, "loss": 0.0141, "lr": 1.4670994081297795e-07, "epoch": 4.86060606060606, "percentage": 97.8, "elapsed_time": "1:22:43", "remaining_time": "0:01:51"}
482
- {"current_steps": 402, "total_steps": 410, "loss": 0.0113, "lr": 1.1593087058410779e-07, "epoch": 4.872727272727273, "percentage": 98.05, "elapsed_time": "1:22:55", "remaining_time": "0:01:39"}
483
- {"current_steps": 403, "total_steps": 410, "loss": 0.0104, "lr": 8.876761585545068e-08, "epoch": 4.884848484848485, "percentage": 98.29, "elapsed_time": "1:23:03", "remaining_time": "0:01:26"}
484
- {"current_steps": 404, "total_steps": 410, "loss": 0.0122, "lr": 6.522214553850159e-08, "epoch": 4.8969696969696965, "percentage": 98.54, "elapsed_time": "1:23:16", "remaining_time": "0:01:14"}
485
- {"current_steps": 405, "total_steps": 410, "loss": 0.012, "lr": 4.529616631193112e-08, "epoch": 4.909090909090909, "percentage": 98.78, "elapsed_time": "1:23:27", "remaining_time": "0:01:01"}
486
- {"current_steps": 405, "total_steps": 410, "eval_loss": 0.020557112991809845, "epoch": 4.909090909090909, "percentage": 98.78, "elapsed_time": "1:23:33", "remaining_time": "0:01:01"}
487
- {"current_steps": 406, "total_steps": 410, "loss": 0.0115, "lr": 2.899112249786229e-08, "epoch": 4.921212121212121, "percentage": 99.02, "elapsed_time": "1:23:41", "remaining_time": "0:00:49"}
488
- {"current_steps": 407, "total_steps": 410, "loss": 0.0125, "lr": 1.6308195957182027e-08, "epoch": 4.933333333333334, "percentage": 99.27, "elapsed_time": "1:23:53", "remaining_time": "0:00:37"}
489
- {"current_steps": 408, "total_steps": 410, "loss": 0.0123, "lr": 7.248306003865279e-09, "epoch": 4.945454545454545, "percentage": 99.51, "elapsed_time": "1:24:02", "remaining_time": "0:00:24"}
490
- {"current_steps": 409, "total_steps": 410, "loss": 0.0117, "lr": 1.8121093383671738e-09, "epoch": 4.957575757575757, "percentage": 99.76, "elapsed_time": "1:24:12", "remaining_time": "0:00:12"}
491
- {"current_steps": 410, "total_steps": 410, "loss": 0.0104, "lr": 0.0, "epoch": 4.96969696969697, "percentage": 100.0, "elapsed_time": "1:24:24", "remaining_time": "0:00:00"}
492
- {"current_steps": 410, "total_steps": 410, "eval_loss": 0.020535213872790337, "epoch": 4.96969696969697, "percentage": 100.0, "elapsed_time": "1:24:30", "remaining_time": "0:00:00"}
493
- {"current_steps": 410, "total_steps": 410, "epoch": 4.96969696969697, "percentage": 100.0, "elapsed_time": "1:24:37", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 2, "loss": 0.0288, "lr": 0.0001, "epoch": 0.34782608695652173, "percentage": 50.0, "elapsed_time": "0:00:52", "remaining_time": "0:00:52"}
2
+ {"current_steps": 2, "total_steps": 2, "loss": 0.0298, "lr": 0.0, "epoch": 0.6956521739130435, "percentage": 100.0, "elapsed_time": "0:01:22", "remaining_time": "0:00:00"}
3
+ {"current_steps": 2, "total_steps": 2, "epoch": 0.6956521739130435, "percentage": 100.0, "elapsed_time": "0:01:28", "remaining_time": "0:00:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
trainer_state.json CHANGED
@@ -1,3555 +1,52 @@
1
  {
2
- "best_metric": 0.020535213872790337,
3
- "best_model_checkpoint": "/home/paperspace/Data/models/brasingh_publicis_f5f/llm3br256/checkpoint-410",
4
- "epoch": 4.96969696969697,
5
- "eval_steps": 5,
6
- "global_step": 410,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.012121212121212121,
13
- "grad_norm": 0.17719489336013794,
14
- "learning_rate": 2.4390243902439027e-06,
15
- "loss": 0.103,
16
- "step": 1
17
- },
18
- {
19
- "epoch": 0.024242424242424242,
20
- "grad_norm": 0.1567779779434204,
21
- "learning_rate": 4.8780487804878055e-06,
22
- "loss": 0.11,
23
- "step": 2
24
- },
25
- {
26
- "epoch": 0.03636363636363636,
27
- "grad_norm": 0.1601039469242096,
28
- "learning_rate": 7.317073170731707e-06,
29
- "loss": 0.1104,
30
- "step": 3
31
- },
32
- {
33
- "epoch": 0.048484848484848485,
34
- "grad_norm": 0.16313816606998444,
35
- "learning_rate": 9.756097560975611e-06,
36
- "loss": 0.1076,
37
- "step": 4
38
- },
39
- {
40
- "epoch": 0.06060606060606061,
41
- "grad_norm": 0.15266162157058716,
42
- "learning_rate": 1.2195121951219513e-05,
43
- "loss": 0.1038,
44
- "step": 5
45
- },
46
- {
47
- "epoch": 0.06060606060606061,
48
- "eval_loss": 0.09789121896028519,
49
- "eval_runtime": 8.116,
50
- "eval_samples_per_second": 6.161,
51
- "eval_steps_per_second": 1.602,
52
- "step": 5
53
- },
54
- {
55
- "epoch": 0.07272727272727272,
56
- "grad_norm": 0.1329907476902008,
57
- "learning_rate": 1.4634146341463415e-05,
58
- "loss": 0.0995,
59
- "step": 6
60
- },
61
- {
62
- "epoch": 0.08484848484848485,
63
- "grad_norm": 0.09588994085788727,
64
- "learning_rate": 1.707317073170732e-05,
65
- "loss": 0.0833,
66
- "step": 7
67
- },
68
- {
69
- "epoch": 0.09696969696969697,
70
- "grad_norm": 0.07421080023050308,
71
- "learning_rate": 1.9512195121951222e-05,
72
- "loss": 0.0756,
73
- "step": 8
74
- },
75
- {
76
- "epoch": 0.10909090909090909,
77
- "grad_norm": 0.0636032298207283,
78
- "learning_rate": 2.1951219512195124e-05,
79
- "loss": 0.0681,
80
- "step": 9
81
- },
82
- {
83
- "epoch": 0.12121212121212122,
84
- "grad_norm": 0.07186830043792725,
85
- "learning_rate": 2.4390243902439026e-05,
86
- "loss": 0.0759,
87
- "step": 10
88
- },
89
- {
90
- "epoch": 0.12121212121212122,
91
- "eval_loss": 0.07647334039211273,
92
- "eval_runtime": 6.2195,
93
- "eval_samples_per_second": 8.039,
94
- "eval_steps_per_second": 2.09,
95
- "step": 10
96
- },
97
- {
98
- "epoch": 0.13333333333333333,
99
- "grad_norm": 0.07592587172985077,
100
- "learning_rate": 2.682926829268293e-05,
101
- "loss": 0.0757,
102
- "step": 11
103
- },
104
- {
105
- "epoch": 0.14545454545454545,
106
- "grad_norm": 0.057555243372917175,
107
- "learning_rate": 2.926829268292683e-05,
108
- "loss": 0.0733,
109
- "step": 12
110
- },
111
- {
112
- "epoch": 0.15757575757575756,
113
- "grad_norm": 0.04685232415795326,
114
- "learning_rate": 3.170731707317073e-05,
115
- "loss": 0.0751,
116
- "step": 13
117
- },
118
- {
119
- "epoch": 0.1696969696969697,
120
- "grad_norm": 0.04220229387283325,
121
- "learning_rate": 3.414634146341464e-05,
122
- "loss": 0.0784,
123
- "step": 14
124
- },
125
- {
126
- "epoch": 0.18181818181818182,
127
- "grad_norm": 0.050287775695323944,
128
- "learning_rate": 3.6585365853658535e-05,
129
- "loss": 0.069,
130
- "step": 15
131
- },
132
- {
133
- "epoch": 0.18181818181818182,
134
- "eval_loss": 0.06831522285938263,
135
- "eval_runtime": 6.1929,
136
- "eval_samples_per_second": 8.074,
137
- "eval_steps_per_second": 2.099,
138
- "step": 15
139
- },
140
- {
141
- "epoch": 0.19393939393939394,
142
- "grad_norm": 0.04325024411082268,
143
- "learning_rate": 3.9024390243902444e-05,
144
- "loss": 0.0691,
145
- "step": 16
146
- },
147
- {
148
- "epoch": 0.20606060606060606,
149
- "grad_norm": 0.037937626242637634,
150
- "learning_rate": 4.146341463414634e-05,
151
- "loss": 0.0813,
152
- "step": 17
153
- },
154
- {
155
- "epoch": 0.21818181818181817,
156
- "grad_norm": 0.03867847099900246,
157
- "learning_rate": 4.390243902439025e-05,
158
- "loss": 0.065,
159
- "step": 18
160
- },
161
- {
162
- "epoch": 0.23030303030303031,
163
- "grad_norm": 0.03792285919189453,
164
- "learning_rate": 4.634146341463415e-05,
165
- "loss": 0.0617,
166
- "step": 19
167
- },
168
- {
169
- "epoch": 0.24242424242424243,
170
- "grad_norm": 0.03528020903468132,
171
- "learning_rate": 4.878048780487805e-05,
172
- "loss": 0.0729,
173
- "step": 20
174
- },
175
- {
176
- "epoch": 0.24242424242424243,
177
- "eval_loss": 0.062009546905756,
178
- "eval_runtime": 6.1891,
179
- "eval_samples_per_second": 8.079,
180
- "eval_steps_per_second": 2.1,
181
- "step": 20
182
- },
183
- {
184
- "epoch": 0.2545454545454545,
185
- "grad_norm": 0.031467072665691376,
186
- "learning_rate": 5.121951219512195e-05,
187
- "loss": 0.0602,
188
- "step": 21
189
- },
190
- {
191
- "epoch": 0.26666666666666666,
192
- "grad_norm": 0.03714953735470772,
193
- "learning_rate": 5.365853658536586e-05,
194
- "loss": 0.0772,
195
- "step": 22
196
- },
197
- {
198
- "epoch": 0.2787878787878788,
199
- "grad_norm": 0.03779144585132599,
200
- "learning_rate": 5.6097560975609764e-05,
201
- "loss": 0.0584,
202
- "step": 23
203
- },
204
- {
205
- "epoch": 0.2909090909090909,
206
- "grad_norm": 0.030055589973926544,
207
- "learning_rate": 5.853658536585366e-05,
208
- "loss": 0.0568,
209
- "step": 24
210
- },
211
- {
212
- "epoch": 0.30303030303030304,
213
- "grad_norm": 0.029797468334436417,
214
- "learning_rate": 6.097560975609756e-05,
215
- "loss": 0.0545,
216
- "step": 25
217
- },
218
- {
219
- "epoch": 0.30303030303030304,
220
- "eval_loss": 0.057142239063978195,
221
- "eval_runtime": 6.2052,
222
- "eval_samples_per_second": 8.058,
223
- "eval_steps_per_second": 2.095,
224
- "step": 25
225
- },
226
- {
227
- "epoch": 0.3151515151515151,
228
- "grad_norm": 0.029303744435310364,
229
- "learning_rate": 6.341463414634146e-05,
230
- "loss": 0.0591,
231
- "step": 26
232
- },
233
- {
234
- "epoch": 0.32727272727272727,
235
- "grad_norm": 0.03735222667455673,
236
- "learning_rate": 6.585365853658538e-05,
237
- "loss": 0.0836,
238
- "step": 27
239
- },
240
- {
241
- "epoch": 0.3393939393939394,
242
- "grad_norm": 0.02950606681406498,
243
- "learning_rate": 6.829268292682928e-05,
244
- "loss": 0.0574,
245
- "step": 28
246
- },
247
- {
248
- "epoch": 0.3515151515151515,
249
- "grad_norm": 0.02479255013167858,
250
- "learning_rate": 7.073170731707317e-05,
251
- "loss": 0.0506,
252
- "step": 29
253
- },
254
- {
255
- "epoch": 0.36363636363636365,
256
- "grad_norm": 0.030447915196418762,
257
- "learning_rate": 7.317073170731707e-05,
258
- "loss": 0.0589,
259
- "step": 30
260
- },
261
- {
262
- "epoch": 0.36363636363636365,
263
- "eval_loss": 0.05275052413344383,
264
- "eval_runtime": 6.1946,
265
- "eval_samples_per_second": 8.072,
266
- "eval_steps_per_second": 2.099,
267
- "step": 30
268
- },
269
- {
270
- "epoch": 0.37575757575757573,
271
- "grad_norm": 0.029138660058379173,
272
- "learning_rate": 7.560975609756099e-05,
273
- "loss": 0.0536,
274
- "step": 31
275
- },
276
- {
277
- "epoch": 0.3878787878787879,
278
- "grad_norm": 0.029026566073298454,
279
- "learning_rate": 7.804878048780489e-05,
280
- "loss": 0.0454,
281
- "step": 32
282
- },
283
- {
284
- "epoch": 0.4,
285
- "grad_norm": 0.03538930043578148,
286
- "learning_rate": 8.048780487804879e-05,
287
- "loss": 0.0727,
288
- "step": 33
289
- },
290
- {
291
- "epoch": 0.4121212121212121,
292
- "grad_norm": 0.028354594483971596,
293
- "learning_rate": 8.292682926829268e-05,
294
- "loss": 0.0557,
295
- "step": 34
296
- },
297
- {
298
- "epoch": 0.42424242424242425,
299
- "grad_norm": 0.02743169106543064,
300
- "learning_rate": 8.53658536585366e-05,
301
- "loss": 0.0461,
302
- "step": 35
303
- },
304
- {
305
- "epoch": 0.42424242424242425,
306
- "eval_loss": 0.05005570873618126,
307
- "eval_runtime": 6.192,
308
- "eval_samples_per_second": 8.075,
309
- "eval_steps_per_second": 2.099,
310
- "step": 35
311
- },
312
- {
313
- "epoch": 0.43636363636363634,
314
- "grad_norm": 0.03530753031373024,
315
- "learning_rate": 8.78048780487805e-05,
316
- "loss": 0.0627,
317
- "step": 36
318
- },
319
- {
320
- "epoch": 0.4484848484848485,
321
- "grad_norm": 0.02797996811568737,
322
- "learning_rate": 9.02439024390244e-05,
323
- "loss": 0.0527,
324
- "step": 37
325
- },
326
- {
327
- "epoch": 0.46060606060606063,
328
- "grad_norm": 0.022809529677033424,
329
- "learning_rate": 9.26829268292683e-05,
330
- "loss": 0.0509,
331
- "step": 38
332
- },
333
- {
334
- "epoch": 0.4727272727272727,
335
- "grad_norm": 0.02468150481581688,
336
- "learning_rate": 9.51219512195122e-05,
337
- "loss": 0.0488,
338
- "step": 39
339
- },
340
- {
341
- "epoch": 0.48484848484848486,
342
- "grad_norm": 0.030917035415768623,
343
- "learning_rate": 9.75609756097561e-05,
344
- "loss": 0.0522,
345
- "step": 40
346
- },
347
- {
348
- "epoch": 0.48484848484848486,
349
- "eval_loss": 0.049276672303676605,
350
- "eval_runtime": 6.1874,
351
- "eval_samples_per_second": 8.081,
352
- "eval_steps_per_second": 2.101,
353
- "step": 40
354
- },
355
- {
356
- "epoch": 0.49696969696969695,
357
- "grad_norm": 0.026523206382989883,
358
- "learning_rate": 0.0001,
359
- "loss": 0.0463,
360
- "step": 41
361
- },
362
- {
363
- "epoch": 0.509090909090909,
364
- "grad_norm": 0.028745442628860474,
365
- "learning_rate": 9.999818789066165e-05,
366
- "loss": 0.0433,
367
- "step": 42
368
- },
369
- {
370
- "epoch": 0.5212121212121212,
371
- "grad_norm": 0.026402153074741364,
372
- "learning_rate": 9.999275169399614e-05,
373
- "loss": 0.0393,
374
- "step": 43
375
- },
376
- {
377
- "epoch": 0.5333333333333333,
378
- "grad_norm": 0.02671145275235176,
379
- "learning_rate": 9.998369180404283e-05,
380
- "loss": 0.044,
381
- "step": 44
382
- },
383
- {
384
- "epoch": 0.5454545454545454,
385
- "grad_norm": 0.034986190497875214,
386
- "learning_rate": 9.997100887750215e-05,
387
- "loss": 0.052,
388
- "step": 45
389
- },
390
- {
391
- "epoch": 0.5454545454545454,
392
- "eval_loss": 0.04825693741440773,
393
- "eval_runtime": 6.1973,
394
- "eval_samples_per_second": 8.068,
395
- "eval_steps_per_second": 2.098,
396
- "step": 45
397
- },
398
- {
399
- "epoch": 0.5575757575757576,
400
- "grad_norm": 0.029590139165520668,
401
- "learning_rate": 9.995470383368808e-05,
402
- "loss": 0.0436,
403
- "step": 46
404
- },
405
- {
406
- "epoch": 0.5696969696969697,
407
- "grad_norm": 0.03095312975347042,
408
- "learning_rate": 9.99347778544615e-05,
409
- "loss": 0.0431,
410
- "step": 47
411
- },
412
- {
413
- "epoch": 0.5818181818181818,
414
- "grad_norm": 0.030565602704882622,
415
- "learning_rate": 9.991123238414455e-05,
416
- "loss": 0.0526,
417
- "step": 48
418
- },
419
- {
420
- "epoch": 0.593939393939394,
421
- "grad_norm": 0.027898119762539864,
422
- "learning_rate": 9.98840691294159e-05,
423
- "loss": 0.0447,
424
- "step": 49
425
- },
426
- {
427
- "epoch": 0.6060606060606061,
428
- "grad_norm": 0.03219461813569069,
429
- "learning_rate": 9.985329005918702e-05,
430
- "loss": 0.0459,
431
- "step": 50
432
- },
433
- {
434
- "epoch": 0.6060606060606061,
435
- "eval_loss": 0.045825447887182236,
436
- "eval_runtime": 6.1916,
437
- "eval_samples_per_second": 8.075,
438
- "eval_steps_per_second": 2.1,
439
- "step": 50
440
- },
441
- {
442
- "epoch": 0.6181818181818182,
443
- "grad_norm": 0.02641221322119236,
444
- "learning_rate": 9.981889740445958e-05,
445
- "loss": 0.0417,
446
- "step": 51
447
- },
448
- {
449
- "epoch": 0.6303030303030303,
450
- "grad_norm": 0.028501464053988457,
451
- "learning_rate": 9.978089365816357e-05,
452
- "loss": 0.0446,
453
- "step": 52
454
- },
455
- {
456
- "epoch": 0.6424242424242425,
457
- "grad_norm": 0.0260939784348011,
458
- "learning_rate": 9.973928157497674e-05,
459
- "loss": 0.0451,
460
- "step": 53
461
- },
462
- {
463
- "epoch": 0.6545454545454545,
464
- "grad_norm": 0.029564740136265755,
465
- "learning_rate": 9.969406417112489e-05,
466
- "loss": 0.0416,
467
- "step": 54
468
- },
469
- {
470
- "epoch": 0.6666666666666666,
471
- "grad_norm": 0.027353042736649513,
472
- "learning_rate": 9.964524472416319e-05,
473
- "loss": 0.0363,
474
- "step": 55
475
- },
476
- {
477
- "epoch": 0.6666666666666666,
478
- "eval_loss": 0.0433911457657814,
479
- "eval_runtime": 6.2376,
480
- "eval_samples_per_second": 8.016,
481
- "eval_steps_per_second": 2.084,
482
- "step": 55
483
- },
484
- {
485
- "epoch": 0.6787878787878788,
486
- "grad_norm": 0.03154386952519417,
487
- "learning_rate": 9.95928267727387e-05,
488
- "loss": 0.0457,
489
- "step": 56
490
- },
491
- {
492
- "epoch": 0.6909090909090909,
493
- "grad_norm": 0.0249126385897398,
494
- "learning_rate": 9.953681411633376e-05,
495
- "loss": 0.0367,
496
- "step": 57
497
- },
498
- {
499
- "epoch": 0.703030303030303,
500
- "grad_norm": 0.02522316575050354,
501
- "learning_rate": 9.947721081499068e-05,
502
- "loss": 0.0428,
503
- "step": 58
504
- },
505
- {
506
- "epoch": 0.7151515151515152,
507
- "grad_norm": 0.028446340933442116,
508
- "learning_rate": 9.941402118901744e-05,
509
- "loss": 0.0456,
510
- "step": 59
511
- },
512
- {
513
- "epoch": 0.7272727272727273,
514
- "grad_norm": 0.0324234701693058,
515
- "learning_rate": 9.934724981867446e-05,
516
- "loss": 0.0553,
517
- "step": 60
518
- },
519
- {
520
- "epoch": 0.7272727272727273,
521
- "eval_loss": 0.04182567819952965,
522
- "eval_runtime": 6.2053,
523
- "eval_samples_per_second": 8.058,
524
- "eval_steps_per_second": 2.095,
525
- "step": 60
526
- },
527
- {
528
- "epoch": 0.7393939393939394,
529
- "grad_norm": 0.027509605512022972,
530
- "learning_rate": 9.927690154384273e-05,
531
- "loss": 0.0443,
532
- "step": 61
533
- },
534
- {
535
- "epoch": 0.7515151515151515,
536
- "grad_norm": 0.025798741728067398,
537
- "learning_rate": 9.920298146367286e-05,
538
- "loss": 0.0423,
539
- "step": 62
540
- },
541
- {
542
- "epoch": 0.7636363636363637,
543
- "grad_norm": 0.029940692707896233,
544
- "learning_rate": 9.912549493621554e-05,
545
- "loss": 0.0469,
546
- "step": 63
547
- },
548
- {
549
- "epoch": 0.7757575757575758,
550
- "grad_norm": 0.032555170357227325,
551
- "learning_rate": 9.904444757803321e-05,
552
- "loss": 0.0428,
553
- "step": 64
554
- },
555
- {
556
- "epoch": 0.7878787878787878,
557
- "grad_norm": 0.03051156736910343,
558
- "learning_rate": 9.895984526379281e-05,
559
- "loss": 0.0444,
560
- "step": 65
561
- },
562
- {
563
- "epoch": 0.7878787878787878,
564
- "eval_loss": 0.0403163880109787,
565
- "eval_runtime": 6.1935,
566
- "eval_samples_per_second": 8.073,
567
- "eval_steps_per_second": 2.099,
568
- "step": 65
569
- },
570
- {
571
- "epoch": 0.8,
572
- "grad_norm": 0.02734997309744358,
573
- "learning_rate": 9.887169412584011e-05,
574
- "loss": 0.0389,
575
- "step": 66
576
- },
577
- {
578
- "epoch": 0.8121212121212121,
579
- "grad_norm": 0.026902060955762863,
580
- "learning_rate": 9.878000055375512e-05,
581
- "loss": 0.0397,
582
- "step": 67
583
- },
584
- {
585
- "epoch": 0.8242424242424242,
586
- "grad_norm": 0.03240904584527016,
587
- "learning_rate": 9.868477119388896e-05,
588
- "loss": 0.0387,
589
- "step": 68
590
- },
591
- {
592
- "epoch": 0.8363636363636363,
593
- "grad_norm": 0.02606021985411644,
594
- "learning_rate": 9.858601294888213e-05,
595
- "loss": 0.0344,
596
- "step": 69
597
- },
598
- {
599
- "epoch": 0.8484848484848485,
600
- "grad_norm": 0.029814746230840683,
601
- "learning_rate": 9.848373297716414e-05,
602
- "loss": 0.0469,
603
- "step": 70
604
- },
605
- {
606
- "epoch": 0.8484848484848485,
607
- "eval_loss": 0.03973233327269554,
608
- "eval_runtime": 6.2308,
609
- "eval_samples_per_second": 8.025,
610
- "eval_steps_per_second": 2.086,
611
- "step": 70
612
- },
613
- {
614
- "epoch": 0.8606060606060606,
615
- "grad_norm": 0.025392569601535797,
616
- "learning_rate": 9.837793869243468e-05,
617
- "loss": 0.0388,
618
- "step": 71
619
- },
620
- {
621
- "epoch": 0.8727272727272727,
622
- "grad_norm": 0.03046100027859211,
623
- "learning_rate": 9.82686377631262e-05,
624
- "loss": 0.0415,
625
- "step": 72
626
- },
627
- {
628
- "epoch": 0.8848484848484849,
629
- "grad_norm": 0.02428356185555458,
630
- "learning_rate": 9.815583811184808e-05,
631
- "loss": 0.037,
632
- "step": 73
633
- },
634
- {
635
- "epoch": 0.896969696969697,
636
- "grad_norm": 0.029197214171290398,
637
- "learning_rate": 9.803954791481239e-05,
638
- "loss": 0.0408,
639
- "step": 74
640
- },
641
- {
642
- "epoch": 0.9090909090909091,
643
- "grad_norm": 0.027502721175551414,
644
- "learning_rate": 9.791977560124119e-05,
645
- "loss": 0.0417,
646
- "step": 75
647
- },
648
- {
649
- "epoch": 0.9090909090909091,
650
- "eval_loss": 0.038558006286621094,
651
- "eval_runtime": 6.2,
652
- "eval_samples_per_second": 8.065,
653
- "eval_steps_per_second": 2.097,
654
- "step": 75
655
- },
656
- {
657
- "epoch": 0.9212121212121213,
658
- "grad_norm": 0.030016757547855377,
659
- "learning_rate": 9.779652985275562e-05,
660
- "loss": 0.0427,
661
- "step": 76
662
- },
663
- {
664
- "epoch": 0.9333333333333333,
665
- "grad_norm": 0.029366502538323402,
666
- "learning_rate": 9.766981960274653e-05,
667
- "loss": 0.0312,
668
- "step": 77
669
- },
670
- {
671
- "epoch": 0.9454545454545454,
672
- "grad_norm": 0.02805924229323864,
673
- "learning_rate": 9.753965403572703e-05,
674
- "loss": 0.0424,
675
- "step": 78
676
- },
677
- {
678
- "epoch": 0.9575757575757575,
679
- "grad_norm": 0.027496378868818283,
680
- "learning_rate": 9.740604258666668e-05,
681
- "loss": 0.0368,
682
- "step": 79
683
- },
684
- {
685
- "epoch": 0.9696969696969697,
686
- "grad_norm": 0.02711924910545349,
687
- "learning_rate": 9.726899494030768e-05,
688
- "loss": 0.0388,
689
- "step": 80
690
- },
691
- {
692
- "epoch": 0.9696969696969697,
693
- "eval_loss": 0.037164073437452316,
694
- "eval_runtime": 6.2151,
695
- "eval_samples_per_second": 8.045,
696
- "eval_steps_per_second": 2.092,
697
- "step": 80
698
- },
699
- {
700
- "epoch": 0.9818181818181818,
701
- "grad_norm": 0.02877042628824711,
702
- "learning_rate": 9.71285210304628e-05,
703
- "loss": 0.0367,
704
- "step": 81
705
- },
706
- {
707
- "epoch": 0.9939393939393939,
708
- "grad_norm": 0.029804140329360962,
709
- "learning_rate": 9.698463103929542e-05,
710
- "loss": 0.0399,
711
- "step": 82
712
- },
713
- {
714
- "epoch": 1.006060606060606,
715
- "grad_norm": 0.04405470937490463,
716
- "learning_rate": 9.683733539658139e-05,
717
- "loss": 0.0545,
718
- "step": 83
719
- },
720
- {
721
- "epoch": 1.018181818181818,
722
- "grad_norm": 0.0315798744559288,
723
- "learning_rate": 9.66866447789531e-05,
724
- "loss": 0.048,
725
- "step": 84
726
- },
727
- {
728
- "epoch": 1.0303030303030303,
729
- "grad_norm": 0.02551027573645115,
730
- "learning_rate": 9.653257010912559e-05,
731
- "loss": 0.0309,
732
- "step": 85
733
- },
734
- {
735
- "epoch": 1.0303030303030303,
736
- "eval_loss": 0.03581343591213226,
737
- "eval_runtime": 6.2558,
738
- "eval_samples_per_second": 7.993,
739
- "eval_steps_per_second": 2.078,
740
- "step": 85
741
- },
742
- {
743
- "epoch": 1.0424242424242425,
744
- "grad_norm": 0.03550685569643974,
745
- "learning_rate": 9.637512255510475e-05,
746
- "loss": 0.0659,
747
- "step": 86
748
- },
749
- {
750
- "epoch": 1.0545454545454545,
751
- "grad_norm": 0.03085348755121231,
752
- "learning_rate": 9.621431352937789e-05,
753
- "loss": 0.0502,
754
- "step": 87
755
- },
756
- {
757
- "epoch": 1.0666666666666667,
758
- "grad_norm": 0.02470513805747032,
759
- "learning_rate": 9.605015468808651e-05,
760
- "loss": 0.0318,
761
- "step": 88
762
- },
763
- {
764
- "epoch": 1.0787878787878789,
765
- "grad_norm": 0.02803831174969673,
766
- "learning_rate": 9.58826579301814e-05,
767
- "loss": 0.0446,
768
- "step": 89
769
- },
770
- {
771
- "epoch": 1.0909090909090908,
772
- "grad_norm": 0.03941066190600395,
773
- "learning_rate": 9.571183539656011e-05,
774
- "loss": 0.0487,
775
- "step": 90
776
- },
777
- {
778
- "epoch": 1.0909090909090908,
779
- "eval_loss": 0.0354202575981617,
780
- "eval_runtime": 6.1921,
781
- "eval_samples_per_second": 8.075,
782
- "eval_steps_per_second": 2.099,
783
- "step": 90
784
- },
785
- {
786
- "epoch": 1.103030303030303,
787
- "grad_norm": 0.029008885845541954,
788
- "learning_rate": 9.553769946918697e-05,
789
- "loss": 0.0403,
790
- "step": 91
791
- },
792
- {
793
- "epoch": 1.1151515151515152,
794
- "grad_norm": 0.025633882731199265,
795
- "learning_rate": 9.536026277019561e-05,
796
- "loss": 0.032,
797
- "step": 92
798
- },
799
- {
800
- "epoch": 1.1272727272727272,
801
- "grad_norm": 0.02955947443842888,
802
- "learning_rate": 9.517953816097396e-05,
803
- "loss": 0.0366,
804
- "step": 93
805
- },
806
- {
807
- "epoch": 1.1393939393939394,
808
- "grad_norm": 0.029836708679795265,
809
- "learning_rate": 9.499553874123212e-05,
810
- "loss": 0.0383,
811
- "step": 94
812
- },
813
- {
814
- "epoch": 1.1515151515151516,
815
- "grad_norm": 0.030258659273386,
816
- "learning_rate": 9.480827784805278e-05,
817
- "loss": 0.0348,
818
- "step": 95
819
- },
820
- {
821
- "epoch": 1.1515151515151516,
822
- "eval_loss": 0.034031517803668976,
823
- "eval_runtime": 6.1911,
824
- "eval_samples_per_second": 8.076,
825
- "eval_steps_per_second": 2.1,
826
- "step": 95
827
- },
828
- {
829
- "epoch": 1.1636363636363636,
830
- "grad_norm": 0.02571636624634266,
831
- "learning_rate": 9.461776905492446e-05,
832
- "loss": 0.0322,
833
- "step": 96
834
- },
835
- {
836
- "epoch": 1.1757575757575758,
837
- "grad_norm": 0.025425300002098083,
838
- "learning_rate": 9.442402617075765e-05,
839
- "loss": 0.0302,
840
- "step": 97
841
- },
842
- {
843
- "epoch": 1.187878787878788,
844
- "grad_norm": 0.02790471538901329,
845
- "learning_rate": 9.422706323888397e-05,
846
- "loss": 0.0305,
847
- "step": 98
848
- },
849
- {
850
- "epoch": 1.2,
851
- "grad_norm": 0.031999390572309494,
852
- "learning_rate": 9.402689453603815e-05,
853
- "loss": 0.0384,
854
- "step": 99
855
- },
856
- {
857
- "epoch": 1.2121212121212122,
858
- "grad_norm": 0.02810075506567955,
859
- "learning_rate": 9.382353457132317e-05,
860
- "loss": 0.0308,
861
- "step": 100
862
- },
863
- {
864
- "epoch": 1.2121212121212122,
865
- "eval_loss": 0.03338392823934555,
866
- "eval_runtime": 6.1917,
867
- "eval_samples_per_second": 8.075,
868
- "eval_steps_per_second": 2.1,
869
- "step": 100
870
- },
871
- {
872
- "epoch": 1.2242424242424241,
873
- "grad_norm": 0.0302734412252903,
874
- "learning_rate": 9.361699808515876e-05,
875
- "loss": 0.0341,
876
- "step": 101
877
- },
878
- {
879
- "epoch": 1.2363636363636363,
880
- "grad_norm": 0.033730726689100266,
881
- "learning_rate": 9.340730004821266e-05,
882
- "loss": 0.0346,
883
- "step": 102
884
- },
885
- {
886
- "epoch": 1.2484848484848485,
887
- "grad_norm": 0.03323773667216301,
888
- "learning_rate": 9.31944556603157e-05,
889
- "loss": 0.0408,
890
- "step": 103
891
- },
892
- {
893
- "epoch": 1.2606060606060607,
894
- "grad_norm": 0.027124911546707153,
895
- "learning_rate": 9.297848034936006e-05,
896
- "loss": 0.0332,
897
- "step": 104
898
- },
899
- {
900
- "epoch": 1.2727272727272727,
901
- "grad_norm": 0.026853900402784348,
902
- "learning_rate": 9.275938977018081e-05,
903
- "loss": 0.0318,
904
- "step": 105
905
- },
906
- {
907
- "epoch": 1.2727272727272727,
908
- "eval_loss": 0.03301350772380829,
909
- "eval_runtime": 6.1968,
910
- "eval_samples_per_second": 8.069,
911
- "eval_steps_per_second": 2.098,
912
- "step": 105
913
- },
914
- {
915
- "epoch": 1.284848484848485,
916
- "grad_norm": 0.027320127934217453,
917
- "learning_rate": 9.253719980342135e-05,
918
- "loss": 0.0339,
919
- "step": 106
920
- },
921
- {
922
- "epoch": 1.2969696969696969,
923
- "grad_norm": 0.0313449464738369,
924
- "learning_rate": 9.231192655438221e-05,
925
- "loss": 0.0336,
926
- "step": 107
927
- },
928
- {
929
- "epoch": 1.309090909090909,
930
- "grad_norm": 0.029063764959573746,
931
- "learning_rate": 9.208358635185373e-05,
932
- "loss": 0.0324,
933
- "step": 108
934
- },
935
- {
936
- "epoch": 1.3212121212121213,
937
- "grad_norm": 0.03135693818330765,
938
- "learning_rate": 9.185219574693242e-05,
939
- "loss": 0.0332,
940
- "step": 109
941
- },
942
- {
943
- "epoch": 1.3333333333333333,
944
- "grad_norm": 0.0317191518843174,
945
- "learning_rate": 9.161777151182136e-05,
946
- "loss": 0.028,
947
- "step": 110
948
- },
949
- {
950
- "epoch": 1.3333333333333333,
951
- "eval_loss": 0.03218723088502884,
952
- "eval_runtime": 6.2118,
953
- "eval_samples_per_second": 8.049,
954
- "eval_steps_per_second": 2.093,
955
- "step": 110
956
- },
957
- {
958
- "epoch": 1.3454545454545455,
959
- "grad_norm": 0.031457044184207916,
960
- "learning_rate": 9.138033063861436e-05,
961
- "loss": 0.0346,
962
- "step": 111
963
- },
964
- {
965
- "epoch": 1.3575757575757577,
966
- "grad_norm": 0.031810589134693146,
967
- "learning_rate": 9.113989033806434e-05,
968
- "loss": 0.0283,
969
- "step": 112
970
- },
971
- {
972
- "epoch": 1.3696969696969696,
973
- "grad_norm": 0.030629124492406845,
974
- "learning_rate": 9.089646803833589e-05,
975
- "loss": 0.0246,
976
- "step": 113
977
- },
978
- {
979
- "epoch": 1.3818181818181818,
980
- "grad_norm": 0.030411459505558014,
981
- "learning_rate": 9.065008138374189e-05,
982
- "loss": 0.0317,
983
- "step": 114
984
- },
985
- {
986
- "epoch": 1.393939393939394,
987
- "grad_norm": 0.029815878719091415,
988
- "learning_rate": 9.040074823346465e-05,
989
- "loss": 0.0311,
990
- "step": 115
991
- },
992
- {
993
- "epoch": 1.393939393939394,
994
- "eval_loss": 0.032092493027448654,
995
- "eval_runtime": 6.1885,
996
- "eval_samples_per_second": 8.08,
997
- "eval_steps_per_second": 2.101,
998
- "step": 115
999
- },
1000
- {
1001
- "epoch": 1.406060606060606,
1002
- "grad_norm": 0.030812319368124008,
1003
- "learning_rate": 9.014848666026138e-05,
1004
- "loss": 0.0389,
1005
- "step": 116
1006
- },
1007
- {
1008
- "epoch": 1.4181818181818182,
1009
- "grad_norm": 0.02588343806564808,
1010
- "learning_rate": 8.989331494915417e-05,
1011
- "loss": 0.0287,
1012
- "step": 117
1013
- },
1014
- {
1015
- "epoch": 1.4303030303030302,
1016
- "grad_norm": 0.02780727669596672,
1017
- "learning_rate": 8.963525159610465e-05,
1018
- "loss": 0.0265,
1019
- "step": 118
1020
- },
1021
- {
1022
- "epoch": 1.4424242424242424,
1023
- "grad_norm": 0.026163380593061447,
1024
- "learning_rate": 8.937431530667328e-05,
1025
- "loss": 0.0262,
1026
- "step": 119
1027
- },
1028
- {
1029
- "epoch": 1.4545454545454546,
1030
- "grad_norm": 0.0316736213862896,
1031
- "learning_rate": 8.911052499466357e-05,
1032
- "loss": 0.0382,
1033
- "step": 120
1034
- },
1035
- {
1036
- "epoch": 1.4545454545454546,
1037
- "eval_loss": 0.031465690582990646,
1038
- "eval_runtime": 6.1922,
1039
- "eval_samples_per_second": 8.075,
1040
- "eval_steps_per_second": 2.099,
1041
- "step": 120
1042
- },
1043
- {
1044
- "epoch": 1.4666666666666668,
1045
- "grad_norm": 0.03706022724509239,
1046
- "learning_rate": 8.884389978075098e-05,
1047
- "loss": 0.0336,
1048
- "step": 121
1049
- },
1050
- {
1051
- "epoch": 1.4787878787878788,
1052
- "grad_norm": 0.027684392407536507,
1053
- "learning_rate": 8.857445899109715e-05,
1054
- "loss": 0.0267,
1055
- "step": 122
1056
- },
1057
- {
1058
- "epoch": 1.490909090909091,
1059
- "grad_norm": 0.02498454973101616,
1060
- "learning_rate": 8.83022221559489e-05,
1061
- "loss": 0.0258,
1062
- "step": 123
1063
- },
1064
- {
1065
- "epoch": 1.503030303030303,
1066
- "grad_norm": 0.03206618130207062,
1067
- "learning_rate": 8.80272090082227e-05,
1068
- "loss": 0.0344,
1069
- "step": 124
1070
- },
1071
- {
1072
- "epoch": 1.5151515151515151,
1073
- "grad_norm": 0.03329097852110863,
1074
- "learning_rate": 8.774943948207426e-05,
1075
- "loss": 0.0316,
1076
- "step": 125
1077
- },
1078
- {
1079
- "epoch": 1.5151515151515151,
1080
- "eval_loss": 0.030392121523618698,
1081
- "eval_runtime": 6.2076,
1082
- "eval_samples_per_second": 8.055,
1083
- "eval_steps_per_second": 2.094,
1084
- "step": 125
1085
- },
1086
- {
1087
- "epoch": 1.5272727272727273,
1088
- "grad_norm": 0.029471345245838165,
1089
- "learning_rate": 8.746893371145366e-05,
1090
- "loss": 0.0279,
1091
- "step": 126
1092
- },
1093
- {
1094
- "epoch": 1.5393939393939395,
1095
- "grad_norm": 0.030292104929685593,
1096
- "learning_rate": 8.718571202864598e-05,
1097
- "loss": 0.0292,
1098
- "step": 127
1099
- },
1100
- {
1101
- "epoch": 1.5515151515151515,
1102
- "grad_norm": 0.028025031089782715,
1103
- "learning_rate": 8.689979496279746e-05,
1104
- "loss": 0.0296,
1105
- "step": 128
1106
- },
1107
- {
1108
- "epoch": 1.5636363636363635,
1109
- "grad_norm": 0.027177123352885246,
1110
- "learning_rate": 8.661120323842751e-05,
1111
- "loss": 0.0286,
1112
- "step": 129
1113
- },
1114
- {
1115
- "epoch": 1.5757575757575757,
1116
- "grad_norm": 0.03291260078549385,
1117
- "learning_rate": 8.631995777392645e-05,
1118
- "loss": 0.0278,
1119
- "step": 130
1120
- },
1121
- {
1122
- "epoch": 1.5757575757575757,
1123
- "eval_loss": 0.029901880770921707,
1124
- "eval_runtime": 6.1931,
1125
- "eval_samples_per_second": 8.073,
1126
- "eval_steps_per_second": 2.099,
1127
- "step": 130
1128
- },
1129
- {
1130
- "epoch": 1.587878787878788,
1131
- "grad_norm": 0.027456866577267647,
1132
- "learning_rate": 8.602607968003935e-05,
1133
- "loss": 0.0277,
1134
- "step": 131
1135
- },
1136
- {
1137
- "epoch": 1.6,
1138
- "grad_norm": 0.02367628738284111,
1139
- "learning_rate": 8.572959025833573e-05,
1140
- "loss": 0.023,
1141
- "step": 132
1142
- },
1143
- {
1144
- "epoch": 1.612121212121212,
1145
- "grad_norm": 0.030250705778598785,
1146
- "learning_rate": 8.543051099966558e-05,
1147
- "loss": 0.0253,
1148
- "step": 133
1149
- },
1150
- {
1151
- "epoch": 1.6242424242424243,
1152
- "grad_norm": 0.02687668427824974,
1153
- "learning_rate": 8.512886358260162e-05,
1154
- "loss": 0.0249,
1155
- "step": 134
1156
- },
1157
- {
1158
- "epoch": 1.6363636363636362,
1159
- "grad_norm": 0.032938696444034576,
1160
- "learning_rate": 8.482466987186785e-05,
1161
- "loss": 0.0285,
1162
- "step": 135
1163
- },
1164
- {
1165
- "epoch": 1.6363636363636362,
1166
- "eval_loss": 0.029229959473013878,
1167
- "eval_runtime": 6.1897,
1168
- "eval_samples_per_second": 8.078,
1169
- "eval_steps_per_second": 2.1,
1170
- "step": 135
1171
- },
1172
- {
1173
- "epoch": 1.6484848484848484,
1174
- "grad_norm": 0.02894946001470089,
1175
- "learning_rate": 8.451795191675488e-05,
1176
- "loss": 0.0268,
1177
- "step": 136
1178
- },
1179
- {
1180
- "epoch": 1.6606060606060606,
1181
- "grad_norm": 0.03599061071872711,
1182
- "learning_rate": 8.420873194952152e-05,
1183
- "loss": 0.0351,
1184
- "step": 137
1185
- },
1186
- {
1187
- "epoch": 1.6727272727272728,
1188
- "grad_norm": 0.031365521252155304,
1189
- "learning_rate": 8.389703238378339e-05,
1190
- "loss": 0.0309,
1191
- "step": 138
1192
- },
1193
- {
1194
- "epoch": 1.6848484848484848,
1195
- "grad_norm": 0.024763284251093864,
1196
- "learning_rate": 8.358287581288822e-05,
1197
- "loss": 0.0244,
1198
- "step": 139
1199
- },
1200
- {
1201
- "epoch": 1.696969696969697,
1202
- "grad_norm": 0.026635024696588516,
1203
- "learning_rate": 8.326628500827826e-05,
1204
- "loss": 0.0257,
1205
- "step": 140
1206
- },
1207
- {
1208
- "epoch": 1.696969696969697,
1209
- "eval_loss": 0.02854442596435547,
1210
- "eval_runtime": 6.2016,
1211
- "eval_samples_per_second": 8.062,
1212
- "eval_steps_per_second": 2.096,
1213
- "step": 140
1214
- },
1215
- {
1216
- "epoch": 1.709090909090909,
1217
- "grad_norm": 0.03084694594144821,
1218
- "learning_rate": 8.294728291783966e-05,
1219
- "loss": 0.0301,
1220
- "step": 141
1221
- },
1222
- {
1223
- "epoch": 1.7212121212121212,
1224
- "grad_norm": 0.024888882413506508,
1225
- "learning_rate": 8.262589266423908e-05,
1226
- "loss": 0.0254,
1227
- "step": 142
1228
- },
1229
- {
1230
- "epoch": 1.7333333333333334,
1231
- "grad_norm": 0.02867315709590912,
1232
- "learning_rate": 8.230213754324773e-05,
1233
- "loss": 0.0338,
1234
- "step": 143
1235
- },
1236
- {
1237
- "epoch": 1.7454545454545456,
1238
- "grad_norm": 0.030578091740608215,
1239
- "learning_rate": 8.197604102205271e-05,
1240
- "loss": 0.0265,
1241
- "step": 144
1242
- },
1243
- {
1244
- "epoch": 1.7575757575757576,
1245
- "grad_norm": 0.025194313377141953,
1246
- "learning_rate": 8.16476267375561e-05,
1247
- "loss": 0.0244,
1248
- "step": 145
1249
- },
1250
- {
1251
- "epoch": 1.7575757575757576,
1252
- "eval_loss": 0.028112677857279778,
1253
- "eval_runtime": 6.1903,
1254
- "eval_samples_per_second": 8.077,
1255
- "eval_steps_per_second": 2.1,
1256
- "step": 145
1257
- },
1258
- {
1259
- "epoch": 1.7696969696969695,
1260
- "grad_norm": 0.03511481732130051,
1261
- "learning_rate": 8.131691849466153e-05,
1262
- "loss": 0.0351,
1263
- "step": 146
1264
- },
1265
- {
1266
- "epoch": 1.7818181818181817,
1267
- "grad_norm": 0.034265320748090744,
1268
- "learning_rate": 8.098394026454885e-05,
1269
- "loss": 0.0318,
1270
- "step": 147
1271
- },
1272
- {
1273
- "epoch": 1.793939393939394,
1274
- "grad_norm": 0.02798490971326828,
1275
- "learning_rate": 8.064871618293646e-05,
1276
- "loss": 0.0258,
1277
- "step": 148
1278
- },
1279
- {
1280
- "epoch": 1.8060606060606061,
1281
- "grad_norm": 0.031277846544981,
1282
- "learning_rate": 8.03112705483319e-05,
1283
- "loss": 0.0322,
1284
- "step": 149
1285
- },
1286
- {
1287
- "epoch": 1.8181818181818183,
1288
- "grad_norm": 0.025352105498313904,
1289
- "learning_rate": 7.997162782027061e-05,
1290
- "loss": 0.0256,
1291
- "step": 150
1292
- },
1293
- {
1294
- "epoch": 1.8181818181818183,
1295
- "eval_loss": 0.027805332094430923,
1296
- "eval_runtime": 6.1948,
1297
- "eval_samples_per_second": 8.071,
1298
- "eval_steps_per_second": 2.099,
1299
- "step": 150
1300
- },
1301
- {
1302
- "epoch": 1.8303030303030303,
1303
- "grad_norm": 0.03179726377129555,
1304
- "learning_rate": 7.962981261754294e-05,
1305
- "loss": 0.0265,
1306
- "step": 151
1307
- },
1308
- {
1309
- "epoch": 1.8424242424242423,
1310
- "grad_norm": 0.02985468879342079,
1311
- "learning_rate": 7.928584971640974e-05,
1312
- "loss": 0.0302,
1313
- "step": 152
1314
- },
1315
- {
1316
- "epoch": 1.8545454545454545,
1317
- "grad_norm": 0.031871821731328964,
1318
- "learning_rate": 7.893976404880643e-05,
1319
- "loss": 0.0331,
1320
- "step": 153
1321
- },
1322
- {
1323
- "epoch": 1.8666666666666667,
1324
- "grad_norm": 0.028416186571121216,
1325
- "learning_rate": 7.859158070053577e-05,
1326
- "loss": 0.0245,
1327
- "step": 154
1328
- },
1329
- {
1330
- "epoch": 1.878787878787879,
1331
- "grad_norm": 0.03054559975862503,
1332
- "learning_rate": 7.824132490944967e-05,
1333
- "loss": 0.0338,
1334
- "step": 155
1335
- },
1336
- {
1337
- "epoch": 1.878787878787879,
1338
- "eval_loss": 0.027029650285840034,
1339
- "eval_runtime": 6.235,
1340
- "eval_samples_per_second": 8.019,
1341
- "eval_steps_per_second": 2.085,
1342
- "step": 155
1343
- },
1344
- {
1345
- "epoch": 1.8909090909090909,
1346
- "grad_norm": 0.028330031782388687,
1347
- "learning_rate": 7.788902206361973e-05,
1348
- "loss": 0.0241,
1349
- "step": 156
1350
- },
1351
- {
1352
- "epoch": 1.903030303030303,
1353
- "grad_norm": 0.031616389751434326,
1354
- "learning_rate": 7.7534697699497e-05,
1355
- "loss": 0.0301,
1356
- "step": 157
1357
- },
1358
- {
1359
- "epoch": 1.915151515151515,
1360
- "grad_norm": 0.027048081159591675,
1361
- "learning_rate": 7.717837750006106e-05,
1362
- "loss": 0.0274,
1363
- "step": 158
1364
- },
1365
- {
1366
- "epoch": 1.9272727272727272,
1367
- "grad_norm": 0.028316281735897064,
1368
- "learning_rate": 7.682008729295833e-05,
1369
- "loss": 0.026,
1370
- "step": 159
1371
- },
1372
- {
1373
- "epoch": 1.9393939393939394,
1374
- "grad_norm": 0.02987455017864704,
1375
- "learning_rate": 7.645985304863003e-05,
1376
- "loss": 0.0309,
1377
- "step": 160
1378
- },
1379
- {
1380
- "epoch": 1.9393939393939394,
1381
- "eval_loss": 0.02624826692044735,
1382
- "eval_runtime": 6.1867,
1383
- "eval_samples_per_second": 8.082,
1384
- "eval_steps_per_second": 2.101,
1385
- "step": 160
1386
- },
1387
- {
1388
- "epoch": 1.9515151515151516,
1389
- "grad_norm": 0.02562532387673855,
1390
- "learning_rate": 7.609770087842969e-05,
1391
- "loss": 0.0275,
1392
- "step": 161
1393
- },
1394
- {
1395
- "epoch": 1.9636363636363636,
1396
- "grad_norm": 0.026776108890771866,
1397
- "learning_rate": 7.573365703273046e-05,
1398
- "loss": 0.0263,
1399
- "step": 162
1400
- },
1401
- {
1402
- "epoch": 1.9757575757575756,
1403
- "grad_norm": 0.031301844865083694,
1404
- "learning_rate": 7.536774789902246e-05,
1405
- "loss": 0.0293,
1406
- "step": 163
1407
- },
1408
- {
1409
- "epoch": 1.9878787878787878,
1410
- "grad_norm": 0.02761393040418625,
1411
- "learning_rate": 7.500000000000001e-05,
1412
- "loss": 0.0292,
1413
- "step": 164
1414
- },
1415
- {
1416
- "epoch": 2.0,
1417
- "grad_norm": 0.04325617477297783,
1418
- "learning_rate": 7.463043999163919e-05,
1419
- "loss": 0.0378,
1420
- "step": 165
1421
- },
1422
- {
1423
- "epoch": 2.0,
1424
- "eval_loss": 0.02608395926654339,
1425
- "eval_runtime": 6.2208,
1426
- "eval_samples_per_second": 8.038,
1427
- "eval_steps_per_second": 2.09,
1428
- "step": 165
1429
- },
1430
- {
1431
- "epoch": 2.012121212121212,
1432
- "grad_norm": 0.026866400614380836,
1433
- "learning_rate": 7.425909466126568e-05,
1434
- "loss": 0.024,
1435
- "step": 166
1436
- },
1437
- {
1438
- "epoch": 2.0242424242424244,
1439
- "grad_norm": 0.026734622195363045,
1440
- "learning_rate": 7.388599092561315e-05,
1441
- "loss": 0.0238,
1442
- "step": 167
1443
- },
1444
- {
1445
- "epoch": 2.036363636363636,
1446
- "grad_norm": 0.02514388971030712,
1447
- "learning_rate": 7.351115582887211e-05,
1448
- "loss": 0.0218,
1449
- "step": 168
1450
- },
1451
- {
1452
- "epoch": 2.0484848484848484,
1453
- "grad_norm": 0.02405986562371254,
1454
- "learning_rate": 7.313461654072973e-05,
1455
- "loss": 0.0199,
1456
- "step": 169
1457
- },
1458
- {
1459
- "epoch": 2.0606060606060606,
1460
- "grad_norm": 0.030505580827593803,
1461
- "learning_rate": 7.275640035440045e-05,
1462
- "loss": 0.0275,
1463
- "step": 170
1464
- },
1465
- {
1466
- "epoch": 2.0606060606060606,
1467
- "eval_loss": 0.026318900287151337,
1468
- "eval_runtime": 6.2393,
1469
- "eval_samples_per_second": 8.014,
1470
- "eval_steps_per_second": 2.084,
1471
- "step": 170
1472
- },
1473
- {
1474
- "epoch": 2.0727272727272728,
1475
- "grad_norm": 0.03722088038921356,
1476
- "learning_rate": 7.237653468464756e-05,
1477
- "loss": 0.0256,
1478
- "step": 171
1479
- },
1480
- {
1481
- "epoch": 2.084848484848485,
1482
- "grad_norm": 0.03724412992596626,
1483
- "learning_rate": 7.199504706579617e-05,
1484
- "loss": 0.0226,
1485
- "step": 172
1486
- },
1487
- {
1488
- "epoch": 2.096969696969697,
1489
- "grad_norm": 0.030355574563145638,
1490
- "learning_rate": 7.161196514973734e-05,
1491
- "loss": 0.0188,
1492
- "step": 173
1493
- },
1494
- {
1495
- "epoch": 2.109090909090909,
1496
- "grad_norm": 0.03693992272019386,
1497
- "learning_rate": 7.12273167039238e-05,
1498
- "loss": 0.0232,
1499
- "step": 174
1500
- },
1501
- {
1502
- "epoch": 2.121212121212121,
1503
- "grad_norm": 0.03164402395486832,
1504
- "learning_rate": 7.084112960935716e-05,
1505
- "loss": 0.0225,
1506
- "step": 175
1507
- },
1508
- {
1509
- "epoch": 2.121212121212121,
1510
- "eval_loss": 0.025883661583065987,
1511
- "eval_runtime": 6.2414,
1512
- "eval_samples_per_second": 8.011,
1513
- "eval_steps_per_second": 2.083,
1514
- "step": 175
1515
- },
1516
- {
1517
- "epoch": 2.1333333333333333,
1518
- "grad_norm": 0.031605158001184464,
1519
- "learning_rate": 7.045343185856701e-05,
1520
- "loss": 0.0248,
1521
- "step": 176
1522
- },
1523
- {
1524
- "epoch": 2.1454545454545455,
1525
- "grad_norm": 0.0310862734913826,
1526
- "learning_rate": 7.006425155358195e-05,
1527
- "loss": 0.0244,
1528
- "step": 177
1529
- },
1530
- {
1531
- "epoch": 2.1575757575757577,
1532
- "grad_norm": 0.031485848128795624,
1533
- "learning_rate": 6.967361690389258e-05,
1534
- "loss": 0.0242,
1535
- "step": 178
1536
- },
1537
- {
1538
- "epoch": 2.16969696969697,
1539
- "grad_norm": 0.03367177024483681,
1540
- "learning_rate": 6.92815562244068e-05,
1541
- "loss": 0.0246,
1542
- "step": 179
1543
- },
1544
- {
1545
- "epoch": 2.1818181818181817,
1546
- "grad_norm": 0.028202077373862267,
1547
- "learning_rate": 6.88880979333973e-05,
1548
- "loss": 0.0232,
1549
- "step": 180
1550
- },
1551
- {
1552
- "epoch": 2.1818181818181817,
1553
- "eval_loss": 0.025616060942411423,
1554
- "eval_runtime": 6.1872,
1555
- "eval_samples_per_second": 8.081,
1556
- "eval_steps_per_second": 2.101,
1557
- "step": 180
1558
- },
1559
- {
1560
- "epoch": 2.193939393939394,
1561
- "grad_norm": 0.03502137213945389,
1562
- "learning_rate": 6.849327055044183e-05,
1563
- "loss": 0.0251,
1564
- "step": 181
1565
- },
1566
- {
1567
- "epoch": 2.206060606060606,
1568
- "grad_norm": 0.029362250119447708,
1569
- "learning_rate": 6.809710269435589e-05,
1570
- "loss": 0.022,
1571
- "step": 182
1572
- },
1573
- {
1574
- "epoch": 2.2181818181818183,
1575
- "grad_norm": 0.033701106905937195,
1576
- "learning_rate": 6.769962308111839e-05,
1577
- "loss": 0.0234,
1578
- "step": 183
1579
- },
1580
- {
1581
- "epoch": 2.2303030303030305,
1582
- "grad_norm": 0.03379302844405174,
1583
- "learning_rate": 6.730086052179004e-05,
1584
- "loss": 0.0221,
1585
- "step": 184
1586
- },
1587
- {
1588
- "epoch": 2.242424242424242,
1589
- "grad_norm": 0.027100039646029472,
1590
- "learning_rate": 6.690084392042513e-05,
1591
- "loss": 0.0193,
1592
- "step": 185
1593
- },
1594
- {
1595
- "epoch": 2.242424242424242,
1596
- "eval_loss": 0.025547849014401436,
1597
- "eval_runtime": 6.2367,
1598
- "eval_samples_per_second": 8.017,
1599
- "eval_steps_per_second": 2.084,
1600
- "step": 185
1601
- },
1602
- {
1603
- "epoch": 2.2545454545454544,
1604
- "grad_norm": 0.03181413188576698,
1605
- "learning_rate": 6.649960227197647e-05,
1606
- "loss": 0.0217,
1607
- "step": 186
1608
- },
1609
- {
1610
- "epoch": 2.2666666666666666,
1611
- "grad_norm": 0.03648809716105461,
1612
- "learning_rate": 6.609716466019356e-05,
1613
- "loss": 0.0239,
1614
- "step": 187
1615
- },
1616
- {
1617
- "epoch": 2.278787878787879,
1618
- "grad_norm": 0.0302013847976923,
1619
- "learning_rate": 6.569356025551454e-05,
1620
- "loss": 0.0232,
1621
- "step": 188
1622
- },
1623
- {
1624
- "epoch": 2.290909090909091,
1625
- "grad_norm": 0.028094977140426636,
1626
- "learning_rate": 6.528881831295188e-05,
1627
- "loss": 0.02,
1628
- "step": 189
1629
- },
1630
- {
1631
- "epoch": 2.303030303030303,
1632
- "grad_norm": 0.03214862942695618,
1633
- "learning_rate": 6.488296816997173e-05,
1634
- "loss": 0.0251,
1635
- "step": 190
1636
- },
1637
- {
1638
- "epoch": 2.303030303030303,
1639
- "eval_loss": 0.02527759224176407,
1640
- "eval_runtime": 6.19,
1641
- "eval_samples_per_second": 8.078,
1642
- "eval_steps_per_second": 2.1,
1643
- "step": 190
1644
- },
1645
- {
1646
- "epoch": 2.315151515151515,
1647
- "grad_norm": 0.033984988927841187,
1648
- "learning_rate": 6.447603924436744e-05,
1649
- "loss": 0.0243,
1650
- "step": 191
1651
- },
1652
- {
1653
- "epoch": 2.327272727272727,
1654
- "grad_norm": 0.027719179168343544,
1655
- "learning_rate": 6.406806103212725e-05,
1656
- "loss": 0.0204,
1657
- "step": 192
1658
- },
1659
- {
1660
- "epoch": 2.3393939393939394,
1661
- "grad_norm": 0.029257657006382942,
1662
- "learning_rate": 6.36590631052963e-05,
1663
- "loss": 0.0232,
1664
- "step": 193
1665
- },
1666
- {
1667
- "epoch": 2.3515151515151516,
1668
- "grad_norm": 0.050508007407188416,
1669
- "learning_rate": 6.32490751098331e-05,
1670
- "loss": 0.0324,
1671
- "step": 194
1672
- },
1673
- {
1674
- "epoch": 2.3636363636363638,
1675
- "grad_norm": 0.029407154768705368,
1676
- "learning_rate": 6.283812676346063e-05,
1677
- "loss": 0.0228,
1678
- "step": 195
1679
- },
1680
- {
1681
- "epoch": 2.3636363636363638,
1682
- "eval_loss": 0.024870626628398895,
1683
- "eval_runtime": 6.191,
1684
- "eval_samples_per_second": 8.076,
1685
- "eval_steps_per_second": 2.1,
1686
- "step": 195
1687
- },
1688
- {
1689
- "epoch": 2.375757575757576,
1690
- "grad_norm": 0.0258539617061615,
1691
- "learning_rate": 6.242624785351236e-05,
1692
- "loss": 0.0231,
1693
- "step": 196
1694
- },
1695
- {
1696
- "epoch": 2.3878787878787877,
1697
- "grad_norm": 0.02586168795824051,
1698
- "learning_rate": 6.201346823477303e-05,
1699
- "loss": 0.0193,
1700
- "step": 197
1701
- },
1702
- {
1703
- "epoch": 2.4,
1704
- "grad_norm": 0.029741084203124046,
1705
- "learning_rate": 6.159981782731474e-05,
1706
- "loss": 0.0227,
1707
- "step": 198
1708
- },
1709
- {
1710
- "epoch": 2.412121212121212,
1711
- "grad_norm": 0.029881663620471954,
1712
- "learning_rate": 6.118532661432812e-05,
1713
- "loss": 0.0224,
1714
- "step": 199
1715
- },
1716
- {
1717
- "epoch": 2.4242424242424243,
1718
- "grad_norm": 0.027224918827414513,
1719
- "learning_rate": 6.0770024639949074e-05,
1720
- "loss": 0.0195,
1721
- "step": 200
1722
- },
1723
- {
1724
- "epoch": 2.4242424242424243,
1725
- "eval_loss": 0.024939175695180893,
1726
- "eval_runtime": 6.1942,
1727
- "eval_samples_per_second": 8.072,
1728
- "eval_steps_per_second": 2.099,
1729
- "step": 200
1730
- },
1731
- {
1732
- "epoch": 2.4363636363636365,
1733
- "grad_norm": 0.028513159602880478,
1734
- "learning_rate": 6.0353942007081046e-05,
1735
- "loss": 0.0198,
1736
- "step": 201
1737
- },
1738
- {
1739
- "epoch": 2.4484848484848483,
1740
- "grad_norm": 0.028778916224837303,
1741
- "learning_rate": 5.993710887521302e-05,
1742
- "loss": 0.0184,
1743
- "step": 202
1744
- },
1745
- {
1746
- "epoch": 2.4606060606060605,
1747
- "grad_norm": 0.03407447412610054,
1748
- "learning_rate": 5.951955545823342e-05,
1749
- "loss": 0.0207,
1750
- "step": 203
1751
- },
1752
- {
1753
- "epoch": 2.4727272727272727,
1754
- "grad_norm": 0.033413201570510864,
1755
- "learning_rate": 5.9101312022240106e-05,
1756
- "loss": 0.0217,
1757
- "step": 204
1758
- },
1759
- {
1760
- "epoch": 2.484848484848485,
1761
- "grad_norm": 0.031220227479934692,
1762
- "learning_rate": 5.868240888334653e-05,
1763
- "loss": 0.0219,
1764
- "step": 205
1765
- },
1766
- {
1767
- "epoch": 2.484848484848485,
1768
- "eval_loss": 0.024136777967214584,
1769
- "eval_runtime": 6.2,
1770
- "eval_samples_per_second": 8.065,
1771
- "eval_steps_per_second": 2.097,
1772
- "step": 205
1773
- },
1774
- {
1775
- "epoch": 2.496969696969697,
1776
- "grad_norm": 0.0299720149487257,
1777
- "learning_rate": 5.826287640548425e-05,
1778
- "loss": 0.0231,
1779
- "step": 206
1780
- },
1781
- {
1782
- "epoch": 2.509090909090909,
1783
- "grad_norm": 0.030199084430933,
1784
- "learning_rate": 5.784274499820214e-05,
1785
- "loss": 0.0243,
1786
- "step": 207
1787
- },
1788
- {
1789
- "epoch": 2.5212121212121215,
1790
- "grad_norm": 0.03225167095661163,
1791
- "learning_rate": 5.742204511446203e-05,
1792
- "loss": 0.0241,
1793
- "step": 208
1794
- },
1795
- {
1796
- "epoch": 2.533333333333333,
1797
- "grad_norm": 0.02794428914785385,
1798
- "learning_rate": 5.700080724843147e-05,
1799
- "loss": 0.0217,
1800
- "step": 209
1801
- },
1802
- {
1803
- "epoch": 2.5454545454545454,
1804
- "grad_norm": 0.026055919006466866,
1805
- "learning_rate": 5.657906193327325e-05,
1806
- "loss": 0.0184,
1807
- "step": 210
1808
- },
1809
- {
1810
- "epoch": 2.5454545454545454,
1811
- "eval_loss": 0.023839673027396202,
1812
- "eval_runtime": 6.1855,
1813
- "eval_samples_per_second": 8.083,
1814
- "eval_steps_per_second": 2.102,
1815
- "step": 210
1816
- },
1817
- {
1818
- "epoch": 2.5575757575757576,
1819
- "grad_norm": 0.03009297326207161,
1820
- "learning_rate": 5.6156839738932343e-05,
1821
- "loss": 0.0233,
1822
- "step": 211
1823
- },
1824
- {
1825
- "epoch": 2.56969696969697,
1826
- "grad_norm": 0.038690801709890366,
1827
- "learning_rate": 5.573417126992003e-05,
1828
- "loss": 0.0419,
1829
- "step": 212
1830
- },
1831
- {
1832
- "epoch": 2.581818181818182,
1833
- "grad_norm": 0.03184739127755165,
1834
- "learning_rate": 5.531108716309547e-05,
1835
- "loss": 0.0208,
1836
- "step": 213
1837
- },
1838
- {
1839
- "epoch": 2.5939393939393938,
1840
- "grad_norm": 0.04226066172122955,
1841
- "learning_rate": 5.4887618085445094e-05,
1842
- "loss": 0.0356,
1843
- "step": 214
1844
- },
1845
- {
1846
- "epoch": 2.606060606060606,
1847
- "grad_norm": 0.02787015587091446,
1848
- "learning_rate": 5.446379473185972e-05,
1849
- "loss": 0.0199,
1850
- "step": 215
1851
- },
1852
- {
1853
- "epoch": 2.606060606060606,
1854
- "eval_loss": 0.023647097870707512,
1855
- "eval_runtime": 6.1981,
1856
- "eval_samples_per_second": 8.067,
1857
- "eval_steps_per_second": 2.097,
1858
- "step": 215
1859
- },
1860
- {
1861
- "epoch": 2.618181818181818,
1862
- "grad_norm": 0.028222182765603065,
1863
- "learning_rate": 5.4039647822909624e-05,
1864
- "loss": 0.0185,
1865
- "step": 216
1866
- },
1867
- {
1868
- "epoch": 2.6303030303030304,
1869
- "grad_norm": 0.03137464076280594,
1870
- "learning_rate": 5.361520810261779e-05,
1871
- "loss": 0.0212,
1872
- "step": 217
1873
- },
1874
- {
1875
- "epoch": 2.6424242424242426,
1876
- "grad_norm": 0.028826339170336723,
1877
- "learning_rate": 5.319050633623142e-05,
1878
- "loss": 0.0208,
1879
- "step": 218
1880
- },
1881
- {
1882
- "epoch": 2.6545454545454543,
1883
- "grad_norm": 0.048953138291835785,
1884
- "learning_rate": 5.2765573307992036e-05,
1885
- "loss": 0.0343,
1886
- "step": 219
1887
- },
1888
- {
1889
- "epoch": 2.6666666666666665,
1890
- "grad_norm": 0.03138812631368637,
1891
- "learning_rate": 5.234043981890394e-05,
1892
- "loss": 0.023,
1893
- "step": 220
1894
- },
1895
- {
1896
- "epoch": 2.6666666666666665,
1897
- "eval_loss": 0.02315612882375717,
1898
- "eval_runtime": 6.1852,
1899
- "eval_samples_per_second": 8.084,
1900
- "eval_steps_per_second": 2.102,
1901
- "step": 220
1902
- },
1903
- {
1904
- "epoch": 2.6787878787878787,
1905
- "grad_norm": 0.03604348748922348,
1906
- "learning_rate": 5.191513668450178e-05,
1907
- "loss": 0.0208,
1908
- "step": 221
1909
- },
1910
- {
1911
- "epoch": 2.690909090909091,
1912
- "grad_norm": 0.028721556067466736,
1913
- "learning_rate": 5.14896947326168e-05,
1914
- "loss": 0.0178,
1915
- "step": 222
1916
- },
1917
- {
1918
- "epoch": 2.703030303030303,
1919
- "grad_norm": 0.02585718221962452,
1920
- "learning_rate": 5.1064144801142374e-05,
1921
- "loss": 0.019,
1922
- "step": 223
1923
- },
1924
- {
1925
- "epoch": 2.7151515151515153,
1926
- "grad_norm": 0.02729875221848488,
1927
- "learning_rate": 5.0638517735798696e-05,
1928
- "loss": 0.0184,
1929
- "step": 224
1930
- },
1931
- {
1932
- "epoch": 2.7272727272727275,
1933
- "grad_norm": 0.029812021180987358,
1934
- "learning_rate": 5.021284438789694e-05,
1935
- "loss": 0.0227,
1936
- "step": 225
1937
- },
1938
- {
1939
- "epoch": 2.7272727272727275,
1940
- "eval_loss": 0.023449590429663658,
1941
- "eval_runtime": 6.1841,
1942
- "eval_samples_per_second": 8.085,
1943
- "eval_steps_per_second": 2.102,
1944
- "step": 225
1945
- },
1946
- {
1947
- "epoch": 2.7393939393939393,
1948
- "grad_norm": 0.02997618354856968,
1949
- "learning_rate": 4.9787155612103074e-05,
1950
- "loss": 0.0205,
1951
- "step": 226
1952
- },
1953
- {
1954
- "epoch": 2.7515151515151515,
1955
- "grad_norm": 0.028398435562849045,
1956
- "learning_rate": 4.936148226420132e-05,
1957
- "loss": 0.0171,
1958
- "step": 227
1959
- },
1960
- {
1961
- "epoch": 2.7636363636363637,
1962
- "grad_norm": 0.030046509578824043,
1963
- "learning_rate": 4.893585519885764e-05,
1964
- "loss": 0.0197,
1965
- "step": 228
1966
- },
1967
- {
1968
- "epoch": 2.775757575757576,
1969
- "grad_norm": 0.029226917773485184,
1970
- "learning_rate": 4.851030526738321e-05,
1971
- "loss": 0.0204,
1972
- "step": 229
1973
- },
1974
- {
1975
- "epoch": 2.787878787878788,
1976
- "grad_norm": 0.03432171046733856,
1977
- "learning_rate": 4.8084863315498234e-05,
1978
- "loss": 0.0206,
1979
- "step": 230
1980
- },
1981
- {
1982
- "epoch": 2.787878787878788,
1983
- "eval_loss": 0.022967081516981125,
1984
- "eval_runtime": 6.1905,
1985
- "eval_samples_per_second": 8.077,
1986
- "eval_steps_per_second": 2.1,
1987
- "step": 230
1988
- },
1989
- {
1990
- "epoch": 2.8,
1991
- "grad_norm": 0.029804987832903862,
1992
- "learning_rate": 4.765956018109607e-05,
1993
- "loss": 0.0197,
1994
- "step": 231
1995
- },
1996
- {
1997
- "epoch": 2.812121212121212,
1998
- "grad_norm": 0.029483767226338387,
1999
- "learning_rate": 4.723442669200798e-05,
2000
- "loss": 0.0213,
2001
- "step": 232
2002
- },
2003
- {
2004
- "epoch": 2.824242424242424,
2005
- "grad_norm": 0.03142073005437851,
2006
- "learning_rate": 4.680949366376858e-05,
2007
- "loss": 0.0237,
2008
- "step": 233
2009
- },
2010
- {
2011
- "epoch": 2.8363636363636364,
2012
- "grad_norm": 0.029062366113066673,
2013
- "learning_rate": 4.638479189738224e-05,
2014
- "loss": 0.0235,
2015
- "step": 234
2016
- },
2017
- {
2018
- "epoch": 2.8484848484848486,
2019
- "grad_norm": 0.03055807389318943,
2020
- "learning_rate": 4.5960352177090395e-05,
2021
- "loss": 0.0217,
2022
- "step": 235
2023
- },
2024
- {
2025
- "epoch": 2.8484848484848486,
2026
- "eval_loss": 0.022518714889883995,
2027
- "eval_runtime": 6.1918,
2028
- "eval_samples_per_second": 8.075,
2029
- "eval_steps_per_second": 2.1,
2030
- "step": 235
2031
- },
2032
- {
2033
- "epoch": 2.8606060606060604,
2034
- "grad_norm": 0.027205798774957657,
2035
- "learning_rate": 4.5536205268140294e-05,
2036
- "loss": 0.0189,
2037
- "step": 236
2038
- },
2039
- {
2040
- "epoch": 2.8727272727272726,
2041
- "grad_norm": 0.025477448478341103,
2042
- "learning_rate": 4.511238191455491e-05,
2043
- "loss": 0.0166,
2044
- "step": 237
2045
- },
2046
- {
2047
- "epoch": 2.8848484848484848,
2048
- "grad_norm": 0.025487707927823067,
2049
- "learning_rate": 4.468891283690454e-05,
2050
- "loss": 0.0183,
2051
- "step": 238
2052
- },
2053
- {
2054
- "epoch": 2.896969696969697,
2055
- "grad_norm": 0.0332886204123497,
2056
- "learning_rate": 4.4265828730079987e-05,
2057
- "loss": 0.0221,
2058
- "step": 239
2059
- },
2060
- {
2061
- "epoch": 2.909090909090909,
2062
- "grad_norm": 0.029150154441595078,
2063
- "learning_rate": 4.3843160261067655e-05,
2064
- "loss": 0.0186,
2065
- "step": 240
2066
- },
2067
- {
2068
- "epoch": 2.909090909090909,
2069
- "eval_loss": 0.022352781146764755,
2070
- "eval_runtime": 6.1961,
2071
- "eval_samples_per_second": 8.07,
2072
- "eval_steps_per_second": 2.098,
2073
- "step": 240
2074
- },
2075
- {
2076
- "epoch": 2.9212121212121214,
2077
- "grad_norm": 0.029591498896479607,
2078
- "learning_rate": 4.342093806672678e-05,
2079
- "loss": 0.0181,
2080
- "step": 241
2081
- },
2082
- {
2083
- "epoch": 2.9333333333333336,
2084
- "grad_norm": 0.03216252475976944,
2085
- "learning_rate": 4.2999192751568564e-05,
2086
- "loss": 0.0203,
2087
- "step": 242
2088
- },
2089
- {
2090
- "epoch": 2.9454545454545453,
2091
- "grad_norm": 0.02891668863594532,
2092
- "learning_rate": 4.2577954885537986e-05,
2093
- "loss": 0.0181,
2094
- "step": 243
2095
- },
2096
- {
2097
- "epoch": 2.9575757575757575,
2098
- "grad_norm": 0.028023086488246918,
2099
- "learning_rate": 4.215725500179787e-05,
2100
- "loss": 0.0191,
2101
- "step": 244
2102
- },
2103
- {
2104
- "epoch": 2.9696969696969697,
2105
- "grad_norm": 0.03082926571369171,
2106
- "learning_rate": 4.1737123594515756e-05,
2107
- "loss": 0.0201,
2108
- "step": 245
2109
- },
2110
- {
2111
- "epoch": 2.9696969696969697,
2112
- "eval_loss": 0.02198323793709278,
2113
- "eval_runtime": 6.1948,
2114
- "eval_samples_per_second": 8.071,
2115
- "eval_steps_per_second": 2.099,
2116
- "step": 245
2117
- },
2118
- {
2119
- "epoch": 2.981818181818182,
2120
- "grad_norm": 0.0321161188185215,
2121
- "learning_rate": 4.131759111665349e-05,
2122
- "loss": 0.0191,
2123
- "step": 246
2124
- },
2125
- {
2126
- "epoch": 2.993939393939394,
2127
- "grad_norm": 0.026935642585158348,
2128
- "learning_rate": 4.089868797775989e-05,
2129
- "loss": 0.0185,
2130
- "step": 247
2131
- },
2132
- {
2133
- "epoch": 3.006060606060606,
2134
- "grad_norm": 0.05411810800433159,
2135
- "learning_rate": 4.0480444541766576e-05,
2136
- "loss": 0.0301,
2137
- "step": 248
2138
- },
2139
- {
2140
- "epoch": 3.018181818181818,
2141
- "grad_norm": 0.027184097096323967,
2142
- "learning_rate": 4.0062891124787e-05,
2143
- "loss": 0.0188,
2144
- "step": 249
2145
- },
2146
- {
2147
- "epoch": 3.0303030303030303,
2148
- "grad_norm": 0.022542983293533325,
2149
- "learning_rate": 3.964605799291897e-05,
2150
- "loss": 0.0147,
2151
- "step": 250
2152
- },
2153
- {
2154
- "epoch": 3.0303030303030303,
2155
- "eval_loss": 0.021969465538859367,
2156
- "eval_runtime": 6.1917,
2157
- "eval_samples_per_second": 8.075,
2158
- "eval_steps_per_second": 2.1,
2159
- "step": 250
2160
- },
2161
- {
2162
- "epoch": 3.0424242424242425,
2163
- "grad_norm": 0.03472661226987839,
2164
- "learning_rate": 3.922997536005094e-05,
2165
- "loss": 0.0178,
2166
- "step": 251
2167
- },
2168
- {
2169
- "epoch": 3.0545454545454547,
2170
- "grad_norm": 0.028128741309046745,
2171
- "learning_rate": 3.8814673385671894e-05,
2172
- "loss": 0.0157,
2173
- "step": 252
2174
- },
2175
- {
2176
- "epoch": 3.066666666666667,
2177
- "grad_norm": 0.03135592117905617,
2178
- "learning_rate": 3.840018217268527e-05,
2179
- "loss": 0.0161,
2180
- "step": 253
2181
- },
2182
- {
2183
- "epoch": 3.0787878787878786,
2184
- "grad_norm": 0.03661385551095009,
2185
- "learning_rate": 3.7986531765226964e-05,
2186
- "loss": 0.0161,
2187
- "step": 254
2188
- },
2189
- {
2190
- "epoch": 3.090909090909091,
2191
- "grad_norm": 0.03205974027514458,
2192
- "learning_rate": 3.757375214648764e-05,
2193
- "loss": 0.0142,
2194
- "step": 255
2195
- },
2196
- {
2197
- "epoch": 3.090909090909091,
2198
- "eval_loss": 0.022621195763349533,
2199
- "eval_runtime": 6.2467,
2200
- "eval_samples_per_second": 8.004,
2201
- "eval_steps_per_second": 2.081,
2202
- "step": 255
2203
- },
2204
- {
2205
- "epoch": 3.103030303030303,
2206
- "grad_norm": 0.037527382373809814,
2207
- "learning_rate": 3.716187323653939e-05,
2208
- "loss": 0.0167,
2209
- "step": 256
2210
- },
2211
- {
2212
- "epoch": 3.1151515151515152,
2213
- "grad_norm": 0.03540443629026413,
2214
- "learning_rate": 3.675092489016693e-05,
2215
- "loss": 0.0168,
2216
- "step": 257
2217
- },
2218
- {
2219
- "epoch": 3.1272727272727274,
2220
- "grad_norm": 0.034389954060316086,
2221
- "learning_rate": 3.634093689470371e-05,
2222
- "loss": 0.017,
2223
- "step": 258
2224
- },
2225
- {
2226
- "epoch": 3.1393939393939396,
2227
- "grad_norm": 0.033294420689344406,
2228
- "learning_rate": 3.5931938967872766e-05,
2229
- "loss": 0.016,
2230
- "step": 259
2231
- },
2232
- {
2233
- "epoch": 3.1515151515151514,
2234
- "grad_norm": 0.028759747743606567,
2235
- "learning_rate": 3.5523960755632574e-05,
2236
- "loss": 0.0149,
2237
- "step": 260
2238
- },
2239
- {
2240
- "epoch": 3.1515151515151514,
2241
- "eval_loss": 0.021824924275279045,
2242
- "eval_runtime": 6.1966,
2243
- "eval_samples_per_second": 8.069,
2244
- "eval_steps_per_second": 2.098,
2245
- "step": 260
2246
- },
2247
- {
2248
- "epoch": 3.1636363636363636,
2249
- "grad_norm": 0.02833370864391327,
2250
- "learning_rate": 3.5117031830028274e-05,
2251
- "loss": 0.0127,
2252
- "step": 261
2253
- },
2254
- {
2255
- "epoch": 3.175757575757576,
2256
- "grad_norm": 0.0286524910479784,
2257
- "learning_rate": 3.471118168704811e-05,
2258
- "loss": 0.015,
2259
- "step": 262
2260
- },
2261
- {
2262
- "epoch": 3.187878787878788,
2263
- "grad_norm": 0.02769540622830391,
2264
- "learning_rate": 3.4306439744485454e-05,
2265
- "loss": 0.0154,
2266
- "step": 263
2267
- },
2268
- {
2269
- "epoch": 3.2,
2270
- "grad_norm": 0.03221355006098747,
2271
- "learning_rate": 3.390283533980646e-05,
2272
- "loss": 0.0167,
2273
- "step": 264
2274
- },
2275
- {
2276
- "epoch": 3.212121212121212,
2277
- "grad_norm": 0.026392612606287003,
2278
- "learning_rate": 3.350039772802354e-05,
2279
- "loss": 0.0151,
2280
- "step": 265
2281
- },
2282
- {
2283
- "epoch": 3.212121212121212,
2284
- "eval_loss": 0.02153392694890499,
2285
- "eval_runtime": 6.1848,
2286
- "eval_samples_per_second": 8.084,
2287
- "eval_steps_per_second": 2.102,
2288
- "step": 265
2289
- },
2290
- {
2291
- "epoch": 3.224242424242424,
2292
- "grad_norm": 0.03104759193956852,
2293
- "learning_rate": 3.309915607957487e-05,
2294
- "loss": 0.0171,
2295
- "step": 266
2296
- },
2297
- {
2298
- "epoch": 3.2363636363636363,
2299
- "grad_norm": 0.028836429119110107,
2300
- "learning_rate": 3.269913947820998e-05,
2301
- "loss": 0.0158,
2302
- "step": 267
2303
- },
2304
- {
2305
- "epoch": 3.2484848484848485,
2306
- "grad_norm": 0.032903432846069336,
2307
- "learning_rate": 3.2300376918881624e-05,
2308
- "loss": 0.0156,
2309
- "step": 268
2310
- },
2311
- {
2312
- "epoch": 3.2606060606060607,
2313
- "grad_norm": 0.030551951378583908,
2314
- "learning_rate": 3.1902897305644095e-05,
2315
- "loss": 0.0134,
2316
- "step": 269
2317
- },
2318
- {
2319
- "epoch": 3.2727272727272725,
2320
- "grad_norm": 0.030059080570936203,
2321
- "learning_rate": 3.1506729449558184e-05,
2322
- "loss": 0.0174,
2323
- "step": 270
2324
- },
2325
- {
2326
- "epoch": 3.2727272727272725,
2327
- "eval_loss": 0.021679332479834557,
2328
- "eval_runtime": 6.1964,
2329
- "eval_samples_per_second": 8.069,
2330
- "eval_steps_per_second": 2.098,
2331
- "step": 270
2332
- },
2333
- {
2334
- "epoch": 3.2848484848484847,
2335
- "grad_norm": 0.030379703268408775,
2336
- "learning_rate": 3.1111902066602724e-05,
2337
- "loss": 0.018,
2338
- "step": 271
2339
- },
2340
- {
2341
- "epoch": 3.296969696969697,
2342
- "grad_norm": 0.02761555276811123,
2343
- "learning_rate": 3.071844377559323e-05,
2344
- "loss": 0.016,
2345
- "step": 272
2346
- },
2347
- {
2348
- "epoch": 3.309090909090909,
2349
- "grad_norm": 0.026775086298584938,
2350
- "learning_rate": 3.0326383096107426e-05,
2351
- "loss": 0.014,
2352
- "step": 273
2353
- },
2354
- {
2355
- "epoch": 3.3212121212121213,
2356
- "grad_norm": 0.03328753635287285,
2357
- "learning_rate": 2.9935748446418066e-05,
2358
- "loss": 0.0169,
2359
- "step": 274
2360
- },
2361
- {
2362
- "epoch": 3.3333333333333335,
2363
- "grad_norm": 0.03564237430691719,
2364
- "learning_rate": 2.9546568141433006e-05,
2365
- "loss": 0.0172,
2366
- "step": 275
2367
- },
2368
- {
2369
- "epoch": 3.3333333333333335,
2370
- "eval_loss": 0.021324800327420235,
2371
- "eval_runtime": 6.1942,
2372
- "eval_samples_per_second": 8.072,
2373
- "eval_steps_per_second": 2.099,
2374
- "step": 275
2375
- },
2376
- {
2377
- "epoch": 3.3454545454545457,
2378
- "grad_norm": 0.028079047799110413,
2379
- "learning_rate": 2.915887039064287e-05,
2380
- "loss": 0.0141,
2381
- "step": 276
2382
- },
2383
- {
2384
- "epoch": 3.3575757575757574,
2385
- "grad_norm": 0.02460673451423645,
2386
- "learning_rate": 2.8772683296076196e-05,
2387
- "loss": 0.0126,
2388
- "step": 277
2389
- },
2390
- {
2391
- "epoch": 3.3696969696969696,
2392
- "grad_norm": 0.04345537722110748,
2393
- "learning_rate": 2.8388034850262646e-05,
2394
- "loss": 0.0376,
2395
- "step": 278
2396
- },
2397
- {
2398
- "epoch": 3.381818181818182,
2399
- "grad_norm": 0.0306687094271183,
2400
- "learning_rate": 2.8004952934203838e-05,
2401
- "loss": 0.017,
2402
- "step": 279
2403
- },
2404
- {
2405
- "epoch": 3.393939393939394,
2406
- "grad_norm": 0.033993735909461975,
2407
- "learning_rate": 2.762346531535246e-05,
2408
- "loss": 0.017,
2409
- "step": 280
2410
- },
2411
- {
2412
- "epoch": 3.393939393939394,
2413
- "eval_loss": 0.02108747698366642,
2414
- "eval_runtime": 6.2236,
2415
- "eval_samples_per_second": 8.034,
2416
- "eval_steps_per_second": 2.089,
2417
- "step": 280
2418
- },
2419
- {
2420
- "epoch": 3.4060606060606062,
2421
- "grad_norm": 0.02444186620414257,
2422
- "learning_rate": 2.7243599645599576e-05,
2423
- "loss": 0.014,
2424
- "step": 281
2425
- },
2426
- {
2427
- "epoch": 3.418181818181818,
2428
- "grad_norm": 0.028384167701005936,
2429
- "learning_rate": 2.6865383459270265e-05,
2430
- "loss": 0.0158,
2431
- "step": 282
2432
- },
2433
- {
2434
- "epoch": 3.43030303030303,
2435
- "grad_norm": 0.03162846714258194,
2436
- "learning_rate": 2.6488844171127903e-05,
2437
- "loss": 0.017,
2438
- "step": 283
2439
- },
2440
- {
2441
- "epoch": 3.4424242424242424,
2442
- "grad_norm": 0.027297567576169968,
2443
- "learning_rate": 2.6114009074386846e-05,
2444
- "loss": 0.0124,
2445
- "step": 284
2446
- },
2447
- {
2448
- "epoch": 3.4545454545454546,
2449
- "grad_norm": 0.03545952960848808,
2450
- "learning_rate": 2.574090533873431e-05,
2451
- "loss": 0.0223,
2452
- "step": 285
2453
- },
2454
- {
2455
- "epoch": 3.4545454545454546,
2456
- "eval_loss": 0.021236957982182503,
2457
- "eval_runtime": 6.1899,
2458
- "eval_samples_per_second": 8.078,
2459
- "eval_steps_per_second": 2.1,
2460
- "step": 285
2461
- },
2462
- {
2463
- "epoch": 3.466666666666667,
2464
- "grad_norm": 0.024587715044617653,
2465
- "learning_rate": 2.5369560008360828e-05,
2466
- "loss": 0.0132,
2467
- "step": 286
2468
- },
2469
- {
2470
- "epoch": 3.4787878787878785,
2471
- "grad_norm": 0.025963526219129562,
2472
- "learning_rate": 2.500000000000001e-05,
2473
- "loss": 0.0132,
2474
- "step": 287
2475
- },
2476
- {
2477
- "epoch": 3.4909090909090907,
2478
- "grad_norm": 0.03487967699766159,
2479
- "learning_rate": 2.4632252100977566e-05,
2480
- "loss": 0.0136,
2481
- "step": 288
2482
- },
2483
- {
2484
- "epoch": 3.503030303030303,
2485
- "grad_norm": 0.030390363186597824,
2486
- "learning_rate": 2.4266342967269552e-05,
2487
- "loss": 0.0157,
2488
- "step": 289
2489
- },
2490
- {
2491
- "epoch": 3.515151515151515,
2492
- "grad_norm": 0.030459538102149963,
2493
- "learning_rate": 2.3902299121570333e-05,
2494
- "loss": 0.0144,
2495
- "step": 290
2496
- },
2497
- {
2498
- "epoch": 3.515151515151515,
2499
- "eval_loss": 0.02107882872223854,
2500
- "eval_runtime": 6.2006,
2501
- "eval_samples_per_second": 8.064,
2502
- "eval_steps_per_second": 2.097,
2503
- "step": 290
2504
- },
2505
- {
2506
- "epoch": 3.5272727272727273,
2507
- "grad_norm": 0.02951274998486042,
2508
- "learning_rate": 2.354014695136997e-05,
2509
- "loss": 0.0131,
2510
- "step": 291
2511
- },
2512
- {
2513
- "epoch": 3.5393939393939395,
2514
- "grad_norm": 0.029193086549639702,
2515
- "learning_rate": 2.317991270704167e-05,
2516
- "loss": 0.0151,
2517
- "step": 292
2518
- },
2519
- {
2520
- "epoch": 3.5515151515151517,
2521
- "grad_norm": 0.02726319245994091,
2522
- "learning_rate": 2.282162249993895e-05,
2523
- "loss": 0.0125,
2524
- "step": 293
2525
- },
2526
- {
2527
- "epoch": 3.5636363636363635,
2528
- "grad_norm": 0.03212954103946686,
2529
- "learning_rate": 2.246530230050301e-05,
2530
- "loss": 0.0162,
2531
- "step": 294
2532
- },
2533
- {
2534
- "epoch": 3.5757575757575757,
2535
- "grad_norm": 0.024175025522708893,
2536
- "learning_rate": 2.211097793638029e-05,
2537
- "loss": 0.0125,
2538
- "step": 295
2539
- },
2540
- {
2541
- "epoch": 3.5757575757575757,
2542
- "eval_loss": 0.020796656608581543,
2543
- "eval_runtime": 6.1933,
2544
- "eval_samples_per_second": 8.073,
2545
- "eval_steps_per_second": 2.099,
2546
- "step": 295
2547
- },
2548
- {
2549
- "epoch": 3.587878787878788,
2550
- "grad_norm": 0.02679980918765068,
2551
- "learning_rate": 2.175867509055033e-05,
2552
- "loss": 0.0111,
2553
- "step": 296
2554
- },
2555
- {
2556
- "epoch": 3.6,
2557
- "grad_norm": 0.031121132895350456,
2558
- "learning_rate": 2.1408419299464245e-05,
2559
- "loss": 0.0165,
2560
- "step": 297
2561
- },
2562
- {
2563
- "epoch": 3.6121212121212123,
2564
- "grad_norm": 0.030764909461140633,
2565
- "learning_rate": 2.106023595119358e-05,
2566
- "loss": 0.0139,
2567
- "step": 298
2568
- },
2569
- {
2570
- "epoch": 3.624242424242424,
2571
- "grad_norm": 0.0302122812718153,
2572
- "learning_rate": 2.071415028359026e-05,
2573
- "loss": 0.0148,
2574
- "step": 299
2575
- },
2576
- {
2577
- "epoch": 3.6363636363636362,
2578
- "grad_norm": 0.029834948480129242,
2579
- "learning_rate": 2.0370187382457068e-05,
2580
- "loss": 0.0163,
2581
- "step": 300
2582
- },
2583
- {
2584
- "epoch": 3.6363636363636362,
2585
- "eval_loss": 0.02069205790758133,
2586
- "eval_runtime": 6.2054,
2587
- "eval_samples_per_second": 8.057,
2588
- "eval_steps_per_second": 2.095,
2589
- "step": 300
2590
- },
2591
- {
2592
- "epoch": 3.6484848484848484,
2593
- "grad_norm": 0.03009135089814663,
2594
- "learning_rate": 2.0028372179729403e-05,
2595
- "loss": 0.0143,
2596
- "step": 301
2597
- },
2598
- {
2599
- "epoch": 3.6606060606060606,
2600
- "grad_norm": 0.029639270156621933,
2601
- "learning_rate": 1.9688729451668114e-05,
2602
- "loss": 0.0168,
2603
- "step": 302
2604
- },
2605
- {
2606
- "epoch": 3.672727272727273,
2607
- "grad_norm": 0.026824606582522392,
2608
- "learning_rate": 1.935128381706355e-05,
2609
- "loss": 0.0129,
2610
- "step": 303
2611
- },
2612
- {
2613
- "epoch": 3.6848484848484846,
2614
- "grad_norm": 0.03427920117974281,
2615
- "learning_rate": 1.901605973545116e-05,
2616
- "loss": 0.0194,
2617
- "step": 304
2618
- },
2619
- {
2620
- "epoch": 3.6969696969696972,
2621
- "grad_norm": 0.031160475686192513,
2622
- "learning_rate": 1.868308150533847e-05,
2623
- "loss": 0.015,
2624
- "step": 305
2625
- },
2626
- {
2627
- "epoch": 3.6969696969696972,
2628
- "eval_loss": 0.020683376118540764,
2629
- "eval_runtime": 6.1876,
2630
- "eval_samples_per_second": 8.081,
2631
- "eval_steps_per_second": 2.101,
2632
- "step": 305
2633
- },
2634
- {
2635
- "epoch": 3.709090909090909,
2636
- "grad_norm": 0.033249229192733765,
2637
- "learning_rate": 1.8352373262443916e-05,
2638
- "loss": 0.0147,
2639
- "step": 306
2640
- },
2641
- {
2642
- "epoch": 3.721212121212121,
2643
- "grad_norm": 0.029073260724544525,
2644
- "learning_rate": 1.8023958977947304e-05,
2645
- "loss": 0.0157,
2646
- "step": 307
2647
- },
2648
- {
2649
- "epoch": 3.7333333333333334,
2650
- "grad_norm": 0.030520522966980934,
2651
- "learning_rate": 1.7697862456752273e-05,
2652
- "loss": 0.0152,
2653
- "step": 308
2654
- },
2655
- {
2656
- "epoch": 3.7454545454545456,
2657
- "grad_norm": 0.029693983495235443,
2658
- "learning_rate": 1.7374107335760936e-05,
2659
- "loss": 0.0172,
2660
- "step": 309
2661
- },
2662
- {
2663
- "epoch": 3.757575757575758,
2664
- "grad_norm": 0.03103681467473507,
2665
- "learning_rate": 1.7052717082160346e-05,
2666
- "loss": 0.0154,
2667
- "step": 310
2668
- },
2669
- {
2670
- "epoch": 3.757575757575758,
2671
- "eval_loss": 0.02056981809437275,
2672
- "eval_runtime": 6.1896,
2673
- "eval_samples_per_second": 8.078,
2674
- "eval_steps_per_second": 2.1,
2675
- "step": 310
2676
- },
2677
- {
2678
- "epoch": 3.7696969696969695,
2679
- "grad_norm": 0.030047744512557983,
2680
- "learning_rate": 1.673371499172174e-05,
2681
- "loss": 0.015,
2682
- "step": 311
2683
- },
2684
- {
2685
- "epoch": 3.7818181818181817,
2686
- "grad_norm": 0.03367823734879494,
2687
- "learning_rate": 1.6417124187111775e-05,
2688
- "loss": 0.017,
2689
- "step": 312
2690
- },
2691
- {
2692
- "epoch": 3.793939393939394,
2693
- "grad_norm": 0.027037424966692924,
2694
- "learning_rate": 1.610296761621662e-05,
2695
- "loss": 0.0145,
2696
- "step": 313
2697
- },
2698
- {
2699
- "epoch": 3.806060606060606,
2700
- "grad_norm": 0.030140092596411705,
2701
- "learning_rate": 1.5791268050478486e-05,
2702
- "loss": 0.0228,
2703
- "step": 314
2704
- },
2705
- {
2706
- "epoch": 3.8181818181818183,
2707
- "grad_norm": 0.031016338616609573,
2708
- "learning_rate": 1.5482048083245114e-05,
2709
- "loss": 0.0186,
2710
- "step": 315
2711
- },
2712
- {
2713
- "epoch": 3.8181818181818183,
2714
- "eval_loss": 0.02028246596455574,
2715
- "eval_runtime": 6.1869,
2716
- "eval_samples_per_second": 8.082,
2717
- "eval_steps_per_second": 2.101,
2718
- "step": 315
2719
- },
2720
- {
2721
- "epoch": 3.83030303030303,
2722
- "grad_norm": 0.02848219871520996,
2723
- "learning_rate": 1.517533012813217e-05,
2724
- "loss": 0.0159,
2725
- "step": 316
2726
- },
2727
- {
2728
- "epoch": 3.8424242424242423,
2729
- "grad_norm": 0.024206412956118584,
2730
- "learning_rate": 1.4871136417398406e-05,
2731
- "loss": 0.0123,
2732
- "step": 317
2733
- },
2734
- {
2735
- "epoch": 3.8545454545454545,
2736
- "grad_norm": 0.03030635416507721,
2737
- "learning_rate": 1.4569489000334436e-05,
2738
- "loss": 0.0137,
2739
- "step": 318
2740
- },
2741
- {
2742
- "epoch": 3.8666666666666667,
2743
- "grad_norm": 0.03156241029500961,
2744
- "learning_rate": 1.427040974166427e-05,
2745
- "loss": 0.0159,
2746
- "step": 319
2747
- },
2748
- {
2749
- "epoch": 3.878787878787879,
2750
- "grad_norm": 0.028942270204424858,
2751
- "learning_rate": 1.3973920319960655e-05,
2752
- "loss": 0.0135,
2753
- "step": 320
2754
- },
2755
- {
2756
- "epoch": 3.878787878787879,
2757
- "eval_loss": 0.020162392407655716,
2758
- "eval_runtime": 6.1914,
2759
- "eval_samples_per_second": 8.076,
2760
- "eval_steps_per_second": 2.1,
2761
- "step": 320
2762
- },
2763
- {
2764
- "epoch": 3.8909090909090907,
2765
- "grad_norm": 0.03344618156552315,
2766
- "learning_rate": 1.3680042226073552e-05,
2767
- "loss": 0.0148,
2768
- "step": 321
2769
- },
2770
- {
2771
- "epoch": 3.9030303030303033,
2772
- "grad_norm": 0.02961633913218975,
2773
- "learning_rate": 1.3388796761572492e-05,
2774
- "loss": 0.0141,
2775
- "step": 322
2776
- },
2777
- {
2778
- "epoch": 3.915151515151515,
2779
- "grad_norm": 0.030708983540534973,
2780
- "learning_rate": 1.310020503720254e-05,
2781
- "loss": 0.0132,
2782
- "step": 323
2783
- },
2784
- {
2785
- "epoch": 3.9272727272727272,
2786
- "grad_norm": 0.030072160065174103,
2787
- "learning_rate": 1.2814287971354022e-05,
2788
- "loss": 0.0161,
2789
- "step": 324
2790
- },
2791
- {
2792
- "epoch": 3.9393939393939394,
2793
- "grad_norm": 0.03028644621372223,
2794
- "learning_rate": 1.253106628854635e-05,
2795
- "loss": 0.0159,
2796
- "step": 325
2797
- },
2798
- {
2799
- "epoch": 3.9393939393939394,
2800
- "eval_loss": 0.020128030329942703,
2801
- "eval_runtime": 6.1885,
2802
- "eval_samples_per_second": 8.08,
2803
- "eval_steps_per_second": 2.101,
2804
- "step": 325
2805
- },
2806
- {
2807
- "epoch": 3.9515151515151516,
2808
- "grad_norm": 0.02972756326198578,
2809
- "learning_rate": 1.2250560517925746e-05,
2810
- "loss": 0.0142,
2811
- "step": 326
2812
- },
2813
- {
2814
- "epoch": 3.963636363636364,
2815
- "grad_norm": 0.02873014286160469,
2816
- "learning_rate": 1.1972790991777311e-05,
2817
- "loss": 0.0155,
2818
- "step": 327
2819
- },
2820
- {
2821
- "epoch": 3.9757575757575756,
2822
- "grad_norm": 0.028870223090052605,
2823
- "learning_rate": 1.1697777844051105e-05,
2824
- "loss": 0.0142,
2825
- "step": 328
2826
- },
2827
- {
2828
- "epoch": 3.987878787878788,
2829
- "grad_norm": 0.02774449624121189,
2830
- "learning_rate": 1.1425541008902851e-05,
2831
- "loss": 0.0147,
2832
- "step": 329
2833
- },
2834
- {
2835
- "epoch": 4.0,
2836
- "grad_norm": 0.04664117470383644,
2837
- "learning_rate": 1.1156100219249022e-05,
2838
- "loss": 0.0211,
2839
- "step": 330
2840
- },
2841
- {
2842
- "epoch": 4.0,
2843
- "eval_loss": 0.01995450258255005,
2844
- "eval_runtime": 6.191,
2845
- "eval_samples_per_second": 8.076,
2846
- "eval_steps_per_second": 2.1,
2847
- "step": 330
2848
- },
2849
- {
2850
- "epoch": 4.012121212121212,
2851
- "grad_norm": 0.024339957162737846,
2852
- "learning_rate": 1.0889475005336446e-05,
2853
- "loss": 0.0133,
2854
- "step": 331
2855
- },
2856
- {
2857
- "epoch": 4.024242424242424,
2858
- "grad_norm": 0.023921139538288116,
2859
- "learning_rate": 1.0625684693326727e-05,
2860
- "loss": 0.013,
2861
- "step": 332
2862
- },
2863
- {
2864
- "epoch": 4.036363636363636,
2865
- "grad_norm": 0.02364080585539341,
2866
- "learning_rate": 1.036474840389537e-05,
2867
- "loss": 0.0132,
2868
- "step": 333
2869
- },
2870
- {
2871
- "epoch": 4.048484848484849,
2872
- "grad_norm": 0.02356121875345707,
2873
- "learning_rate": 1.0106685050845838e-05,
2874
- "loss": 0.0121,
2875
- "step": 334
2876
- },
2877
- {
2878
- "epoch": 4.0606060606060606,
2879
- "grad_norm": 0.025879928842186928,
2880
- "learning_rate": 9.851513339738628e-06,
2881
- "loss": 0.0134,
2882
- "step": 335
2883
- },
2884
- {
2885
- "epoch": 4.0606060606060606,
2886
- "eval_loss": 0.0202109944075346,
2887
- "eval_runtime": 6.1925,
2888
- "eval_samples_per_second": 8.074,
2889
- "eval_steps_per_second": 2.099,
2890
- "step": 335
2891
- },
2892
- {
2893
- "epoch": 4.072727272727272,
2894
- "grad_norm": 0.02288251556456089,
2895
- "learning_rate": 9.599251766535345e-06,
2896
- "loss": 0.0121,
2897
- "step": 336
2898
- },
2899
- {
2900
- "epoch": 4.084848484848485,
2901
- "grad_norm": 0.02703404612839222,
2902
- "learning_rate": 9.349918616258114e-06,
2903
- "loss": 0.0126,
2904
- "step": 337
2905
- },
2906
- {
2907
- "epoch": 4.096969696969697,
2908
- "grad_norm": 0.025494417175650597,
2909
- "learning_rate": 9.103531961664118e-06,
2910
- "loss": 0.0122,
2911
- "step": 338
2912
- },
2913
- {
2914
- "epoch": 4.109090909090909,
2915
- "grad_norm": 0.02807869389653206,
2916
- "learning_rate": 8.860109661935674e-06,
2917
- "loss": 0.0155,
2918
- "step": 339
2919
- },
2920
- {
2921
- "epoch": 4.121212121212121,
2922
- "grad_norm": 0.027642810717225075,
2923
- "learning_rate": 8.619669361385663e-06,
2924
- "loss": 0.0113,
2925
- "step": 340
2926
- },
2927
- {
2928
- "epoch": 4.121212121212121,
2929
- "eval_loss": 0.020561667159199715,
2930
- "eval_runtime": 6.1965,
2931
- "eval_samples_per_second": 8.069,
2932
- "eval_steps_per_second": 2.098,
2933
- "step": 340
2934
- },
2935
- {
2936
- "epoch": 4.133333333333334,
2937
- "grad_norm": 0.030346019193530083,
2938
- "learning_rate": 8.38222848817864e-06,
2939
- "loss": 0.0127,
2940
- "step": 341
2941
- },
2942
- {
2943
- "epoch": 4.1454545454545455,
2944
- "grad_norm": 0.024746423587203026,
2945
- "learning_rate": 8.14780425306758e-06,
2946
- "loss": 0.0121,
2947
- "step": 342
2948
- },
2949
- {
2950
- "epoch": 4.157575757575757,
2951
- "grad_norm": 0.026435259729623795,
2952
- "learning_rate": 7.91641364814628e-06,
2953
- "loss": 0.0109,
2954
- "step": 343
2955
- },
2956
- {
2957
- "epoch": 4.16969696969697,
2958
- "grad_norm": 0.02962976135313511,
2959
- "learning_rate": 7.688073445617799e-06,
2960
- "loss": 0.0108,
2961
- "step": 344
2962
- },
2963
- {
2964
- "epoch": 4.181818181818182,
2965
- "grad_norm": 0.02813326194882393,
2966
- "learning_rate": 7.462800196578662e-06,
2967
- "loss": 0.0117,
2968
- "step": 345
2969
- },
2970
- {
2971
- "epoch": 4.181818181818182,
2972
- "eval_loss": 0.0208114180713892,
2973
- "eval_runtime": 6.1943,
2974
- "eval_samples_per_second": 8.072,
2975
- "eval_steps_per_second": 2.099,
2976
- "step": 345
2977
- },
2978
- {
2979
- "epoch": 4.193939393939394,
2980
- "grad_norm": 0.03237050771713257,
2981
- "learning_rate": 7.240610229819195e-06,
2982
- "loss": 0.013,
2983
- "step": 346
2984
- },
2985
- {
2986
- "epoch": 4.206060606060606,
2987
- "grad_norm": 0.026286713778972626,
2988
- "learning_rate": 7.0215196506399515e-06,
2989
- "loss": 0.0108,
2990
- "step": 347
2991
- },
2992
- {
2993
- "epoch": 4.218181818181818,
2994
- "grad_norm": 0.026608100160956383,
2995
- "learning_rate": 6.8055443396842945e-06,
2996
- "loss": 0.0103,
2997
- "step": 348
2998
- },
2999
- {
3000
- "epoch": 4.2303030303030305,
3001
- "grad_norm": 0.03118029236793518,
3002
- "learning_rate": 6.592699951787362e-06,
3003
- "loss": 0.0138,
3004
- "step": 349
3005
- },
3006
- {
3007
- "epoch": 4.242424242424242,
3008
- "grad_norm": 0.030633771792054176,
3009
- "learning_rate": 6.3830019148412525e-06,
3010
- "loss": 0.0108,
3011
- "step": 350
3012
- },
3013
- {
3014
- "epoch": 4.242424242424242,
3015
- "eval_loss": 0.020906535908579826,
3016
- "eval_runtime": 6.1873,
3017
- "eval_samples_per_second": 8.081,
3018
- "eval_steps_per_second": 2.101,
3019
- "step": 350
3020
- },
3021
- {
3022
- "epoch": 4.254545454545455,
3023
- "grad_norm": 0.03377068042755127,
3024
- "learning_rate": 6.17646542867682e-06,
3025
- "loss": 0.0144,
3026
- "step": 351
3027
- },
3028
- {
3029
- "epoch": 4.266666666666667,
3030
- "grad_norm": 0.027513034641742706,
3031
- "learning_rate": 5.973105463961865e-06,
3032
- "loss": 0.0107,
3033
- "step": 352
3034
- },
3035
- {
3036
- "epoch": 4.278787878787879,
3037
- "grad_norm": 0.03077622503042221,
3038
- "learning_rate": 5.772936761116027e-06,
3039
- "loss": 0.0139,
3040
- "step": 353
3041
- },
3042
- {
3043
- "epoch": 4.290909090909091,
3044
- "grad_norm": 0.026948513463139534,
3045
- "learning_rate": 5.575973829242364e-06,
3046
- "loss": 0.0126,
3047
- "step": 354
3048
- },
3049
- {
3050
- "epoch": 4.303030303030303,
3051
- "grad_norm": 0.02911302261054516,
3052
- "learning_rate": 5.382230945075556e-06,
3053
- "loss": 0.012,
3054
- "step": 355
3055
- },
3056
- {
3057
- "epoch": 4.303030303030303,
3058
- "eval_loss": 0.020746439695358276,
3059
- "eval_runtime": 6.1873,
3060
- "eval_samples_per_second": 8.081,
3061
- "eval_steps_per_second": 2.101,
3062
- "step": 355
3063
- },
3064
- {
3065
- "epoch": 4.315151515151515,
3066
- "grad_norm": 0.02364683710038662,
3067
- "learning_rate": 5.191722151947226e-06,
3068
- "loss": 0.0099,
3069
- "step": 356
3070
- },
3071
- {
3072
- "epoch": 4.327272727272727,
3073
- "grad_norm": 0.031056983396410942,
3074
- "learning_rate": 5.004461258767873e-06,
3075
- "loss": 0.0143,
3076
- "step": 357
3077
- },
3078
- {
3079
- "epoch": 4.33939393939394,
3080
- "grad_norm": 0.02985430881381035,
3081
- "learning_rate": 4.820461839026047e-06,
3082
- "loss": 0.0126,
3083
- "step": 358
3084
- },
3085
- {
3086
- "epoch": 4.351515151515152,
3087
- "grad_norm": 0.02651560679078102,
3088
- "learning_rate": 4.639737229804403e-06,
3089
- "loss": 0.0115,
3090
- "step": 359
3091
- },
3092
- {
3093
- "epoch": 4.363636363636363,
3094
- "grad_norm": 0.026479771360754967,
3095
- "learning_rate": 4.462300530813024e-06,
3096
- "loss": 0.0111,
3097
- "step": 360
3098
- },
3099
- {
3100
- "epoch": 4.363636363636363,
3101
- "eval_loss": 0.020565090700984,
3102
- "eval_runtime": 6.2012,
3103
- "eval_samples_per_second": 8.063,
3104
- "eval_steps_per_second": 2.096,
3105
- "step": 360
3106
- },
3107
- {
3108
- "epoch": 4.375757575757576,
3109
- "grad_norm": 0.02071288600564003,
3110
- "learning_rate": 4.2881646034398925e-06,
3111
- "loss": 0.0114,
3112
- "step": 361
3113
- },
3114
- {
3115
- "epoch": 4.387878787878788,
3116
- "grad_norm": 0.02533382549881935,
3117
- "learning_rate": 4.117342069818603e-06,
3118
- "loss": 0.0113,
3119
- "step": 362
3120
- },
3121
- {
3122
- "epoch": 4.4,
3123
- "grad_norm": 0.021412553265690804,
3124
- "learning_rate": 3.949845311913492e-06,
3125
- "loss": 0.0115,
3126
- "step": 363
3127
- },
3128
- {
3129
- "epoch": 4.412121212121212,
3130
- "grad_norm": 0.024555562064051628,
3131
- "learning_rate": 3.7856864706221185e-06,
3132
- "loss": 0.0098,
3133
- "step": 364
3134
- },
3135
- {
3136
- "epoch": 4.424242424242424,
3137
- "grad_norm": 0.027632344514131546,
3138
- "learning_rate": 3.6248774448952695e-06,
3139
- "loss": 0.0118,
3140
- "step": 365
3141
- },
3142
- {
3143
- "epoch": 4.424242424242424,
3144
- "eval_loss": 0.02050224132835865,
3145
- "eval_runtime": 6.1859,
3146
- "eval_samples_per_second": 8.083,
3147
- "eval_steps_per_second": 2.102,
3148
- "step": 365
3149
- },
3150
- {
3151
- "epoch": 4.4363636363636365,
3152
- "grad_norm": 0.028998758643865585,
3153
- "learning_rate": 3.467429890874424e-06,
3154
- "loss": 0.0111,
3155
- "step": 366
3156
- },
3157
- {
3158
- "epoch": 4.448484848484848,
3159
- "grad_norm": 0.027949200943112373,
3160
- "learning_rate": 3.3133552210468875e-06,
3161
- "loss": 0.0122,
3162
- "step": 367
3163
- },
3164
- {
3165
- "epoch": 4.460606060606061,
3166
- "grad_norm": 0.029877539724111557,
3167
- "learning_rate": 3.162664603418608e-06,
3168
- "loss": 0.0136,
3169
- "step": 368
3170
- },
3171
- {
3172
- "epoch": 4.472727272727273,
3173
- "grad_norm": 0.02742207795381546,
3174
- "learning_rate": 3.0153689607045845e-06,
3175
- "loss": 0.0116,
3176
- "step": 369
3177
- },
3178
- {
3179
- "epoch": 4.484848484848484,
3180
- "grad_norm": 0.02200300246477127,
3181
- "learning_rate": 2.871478969537206e-06,
3182
- "loss": 0.0099,
3183
- "step": 370
3184
- },
3185
- {
3186
- "epoch": 4.484848484848484,
3187
- "eval_loss": 0.02058413252234459,
3188
- "eval_runtime": 6.1924,
3189
- "eval_samples_per_second": 8.074,
3190
- "eval_steps_per_second": 2.099,
3191
- "step": 370
3192
- },
3193
- {
3194
- "epoch": 4.496969696969697,
3195
- "grad_norm": 0.029120702296495438,
3196
- "learning_rate": 2.731005059692332e-06,
3197
- "loss": 0.0212,
3198
- "step": 371
3199
- },
3200
- {
3201
- "epoch": 4.509090909090909,
3202
- "grad_norm": 0.030737141147255898,
3203
- "learning_rate": 2.5939574133333312e-06,
3204
- "loss": 0.0275,
3205
- "step": 372
3206
- },
3207
- {
3208
- "epoch": 4.5212121212121215,
3209
- "grad_norm": 0.02619299292564392,
3210
- "learning_rate": 2.4603459642729863e-06,
3211
- "loss": 0.0104,
3212
- "step": 373
3213
- },
3214
- {
3215
- "epoch": 4.533333333333333,
3216
- "grad_norm": 0.02171757072210312,
3217
- "learning_rate": 2.330180397253473e-06,
3218
- "loss": 0.0099,
3219
- "step": 374
3220
- },
3221
- {
3222
- "epoch": 4.545454545454545,
3223
- "grad_norm": 0.022865932434797287,
3224
- "learning_rate": 2.203470147244385e-06,
3225
- "loss": 0.0118,
3226
- "step": 375
3227
- },
3228
- {
3229
- "epoch": 4.545454545454545,
3230
- "eval_loss": 0.020584262907505035,
3231
- "eval_runtime": 6.193,
3232
- "eval_samples_per_second": 8.074,
3233
- "eval_steps_per_second": 2.099,
3234
- "step": 375
3235
- },
3236
- {
3237
- "epoch": 4.557575757575758,
3238
- "grad_norm": 0.02180948108434677,
3239
- "learning_rate": 2.0802243987588066e-06,
3240
- "loss": 0.0104,
3241
- "step": 376
3242
- },
3243
- {
3244
- "epoch": 4.569696969696969,
3245
- "grad_norm": 0.027300819754600525,
3246
- "learning_rate": 1.9604520851876198e-06,
3247
- "loss": 0.0121,
3248
- "step": 377
3249
- },
3250
- {
3251
- "epoch": 4.581818181818182,
3252
- "grad_norm": 0.027127033099532127,
3253
- "learning_rate": 1.8441618881519184e-06,
3254
- "loss": 0.0113,
3255
- "step": 378
3256
- },
3257
- {
3258
- "epoch": 4.593939393939394,
3259
- "grad_norm": 0.026878971606492996,
3260
- "learning_rate": 1.7313622368738014e-06,
3261
- "loss": 0.0105,
3262
- "step": 379
3263
- },
3264
- {
3265
- "epoch": 4.606060606060606,
3266
- "grad_norm": 0.02648119069635868,
3267
- "learning_rate": 1.6220613075653202e-06,
3268
- "loss": 0.0119,
3269
- "step": 380
3270
- },
3271
- {
3272
- "epoch": 4.606060606060606,
3273
- "eval_loss": 0.02056843228638172,
3274
- "eval_runtime": 6.1957,
3275
- "eval_samples_per_second": 8.07,
3276
- "eval_steps_per_second": 2.098,
3277
- "step": 380
3278
- },
3279
- {
3280
- "epoch": 4.618181818181818,
3281
- "grad_norm": 0.026216818019747734,
3282
- "learning_rate": 1.51626702283586e-06,
3283
- "loss": 0.0098,
3284
- "step": 381
3285
- },
3286
- {
3287
- "epoch": 4.63030303030303,
3288
- "grad_norm": 0.02351340465247631,
3289
- "learning_rate": 1.4139870511178766e-06,
3290
- "loss": 0.0116,
3291
- "step": 382
3292
- },
3293
- {
3294
- "epoch": 4.642424242424243,
3295
- "grad_norm": 0.030724933370947838,
3296
- "learning_rate": 1.3152288061110518e-06,
3297
- "loss": 0.0101,
3298
- "step": 383
3299
- },
3300
- {
3301
- "epoch": 4.654545454545454,
3302
- "grad_norm": 0.02688099816441536,
3303
- "learning_rate": 1.2199994462448904e-06,
3304
- "loss": 0.0113,
3305
- "step": 384
3306
- },
3307
- {
3308
- "epoch": 4.666666666666667,
3309
- "grad_norm": 0.02722257934510708,
3310
- "learning_rate": 1.128305874159896e-06,
3311
- "loss": 0.0114,
3312
- "step": 385
3313
- },
3314
- {
3315
- "epoch": 4.666666666666667,
3316
- "eval_loss": 0.02059413306415081,
3317
- "eval_runtime": 6.2059,
3318
- "eval_samples_per_second": 8.057,
3319
- "eval_steps_per_second": 2.095,
3320
- "step": 385
3321
- },
3322
- {
3323
- "epoch": 4.678787878787879,
3324
- "grad_norm": 0.02383565530180931,
3325
- "learning_rate": 1.040154736207194e-06,
3326
- "loss": 0.0106,
3327
- "step": 386
3328
- },
3329
- {
3330
- "epoch": 4.690909090909091,
3331
- "grad_norm": 0.028037432581186295,
3332
- "learning_rate": 9.555524219667989e-07,
3333
- "loss": 0.0122,
3334
- "step": 387
3335
- },
3336
- {
3337
- "epoch": 4.703030303030303,
3338
- "grad_norm": 0.021838784217834473,
3339
- "learning_rate": 8.745050637844532e-07,
3340
- "loss": 0.0097,
3341
- "step": 388
3342
- },
3343
- {
3344
- "epoch": 4.715151515151515,
3345
- "grad_norm": 0.030912073329091072,
3346
- "learning_rate": 7.970185363271431e-07,
3347
- "loss": 0.0121,
3348
- "step": 389
3349
- },
3350
- {
3351
- "epoch": 4.7272727272727275,
3352
- "grad_norm": 0.02470664493739605,
3353
- "learning_rate": 7.230984561572729e-07,
3354
- "loss": 0.0109,
3355
- "step": 390
3356
- },
3357
- {
3358
- "epoch": 4.7272727272727275,
3359
- "eval_loss": 0.020591916516423225,
3360
- "eval_runtime": 6.1901,
3361
- "eval_samples_per_second": 8.077,
3362
- "eval_steps_per_second": 2.1,
3363
- "step": 390
3364
- },
3365
- {
3366
- "epoch": 4.739393939393939,
3367
- "grad_norm": 0.030810924246907234,
3368
- "learning_rate": 6.527501813255344e-07,
3369
- "loss": 0.0165,
3370
- "step": 391
3371
- },
3372
- {
3373
- "epoch": 4.751515151515152,
3374
- "grad_norm": 0.025043383240699768,
3375
- "learning_rate": 5.859788109825793e-07,
3376
- "loss": 0.0096,
3377
- "step": 392
3378
- },
3379
- {
3380
- "epoch": 4.763636363636364,
3381
- "grad_norm": 0.028706299141049385,
3382
- "learning_rate": 5.227891850093314e-07,
3383
- "loss": 0.0129,
3384
- "step": 393
3385
- },
3386
- {
3387
- "epoch": 4.775757575757575,
3388
- "grad_norm": 0.0277020912617445,
3389
- "learning_rate": 4.6318588366625616e-07,
3390
- "loss": 0.0122,
3391
- "step": 394
3392
- },
3393
- {
3394
- "epoch": 4.787878787878788,
3395
- "grad_norm": 0.02909735217690468,
3396
- "learning_rate": 4.071732272613149e-07,
3397
- "loss": 0.0124,
3398
- "step": 395
3399
- },
3400
- {
3401
- "epoch": 4.787878787878788,
3402
- "eval_loss": 0.020531287416815758,
3403
- "eval_runtime": 6.1957,
3404
- "eval_samples_per_second": 8.07,
3405
- "eval_steps_per_second": 2.098,
3406
- "step": 395
3407
- },
3408
- {
3409
- "epoch": 4.8,
3410
- "grad_norm": 0.024658478796482086,
3411
- "learning_rate": 3.5475527583681e-07,
3412
- "loss": 0.0112,
3413
- "step": 396
3414
- },
3415
- {
3416
- "epoch": 4.8121212121212125,
3417
- "grad_norm": 0.023081207647919655,
3418
- "learning_rate": 3.059358288751202e-07,
3419
- "loss": 0.0102,
3420
- "step": 397
3421
- },
3422
- {
3423
- "epoch": 4.824242424242424,
3424
- "grad_norm": 0.03320831060409546,
3425
- "learning_rate": 2.6071842502326527e-07,
3426
- "loss": 0.0119,
3427
- "step": 398
3428
- },
3429
- {
3430
- "epoch": 4.836363636363636,
3431
- "grad_norm": 0.025276964530348778,
3432
- "learning_rate": 2.1910634183644474e-07,
3433
- "loss": 0.0117,
3434
- "step": 399
3435
- },
3436
- {
3437
- "epoch": 4.848484848484849,
3438
- "grad_norm": 0.02636777050793171,
3439
- "learning_rate": 1.811025955404333e-07,
3440
- "loss": 0.0111,
3441
- "step": 400
3442
- },
3443
- {
3444
- "epoch": 4.848484848484849,
3445
- "eval_loss": 0.020571600645780563,
3446
- "eval_runtime": 6.1951,
3447
- "eval_samples_per_second": 8.071,
3448
- "eval_steps_per_second": 2.098,
3449
- "step": 400
3450
- },
3451
- {
3452
- "epoch": 4.86060606060606,
3453
- "grad_norm": 0.0283295139670372,
3454
- "learning_rate": 1.4670994081297795e-07,
3455
- "loss": 0.0141,
3456
- "step": 401
3457
- },
3458
- {
3459
- "epoch": 4.872727272727273,
3460
- "grad_norm": 0.025880116969347,
3461
- "learning_rate": 1.1593087058410779e-07,
3462
- "loss": 0.0113,
3463
- "step": 402
3464
- },
3465
- {
3466
- "epoch": 4.884848484848485,
3467
- "grad_norm": 0.02684679627418518,
3468
- "learning_rate": 8.876761585545068e-08,
3469
- "loss": 0.0104,
3470
- "step": 403
3471
- },
3472
- {
3473
- "epoch": 4.8969696969696965,
3474
- "grad_norm": 0.027327047660946846,
3475
- "learning_rate": 6.522214553850159e-08,
3476
- "loss": 0.0122,
3477
- "step": 404
3478
- },
3479
- {
3480
- "epoch": 4.909090909090909,
3481
- "grad_norm": 0.033394601196050644,
3482
- "learning_rate": 4.529616631193112e-08,
3483
- "loss": 0.012,
3484
- "step": 405
3485
- },
3486
- {
3487
- "epoch": 4.909090909090909,
3488
- "eval_loss": 0.020557112991809845,
3489
- "eval_runtime": 6.1866,
3490
- "eval_samples_per_second": 8.082,
3491
- "eval_steps_per_second": 2.101,
3492
- "step": 405
3493
- },
3494
- {
3495
- "epoch": 4.921212121212121,
3496
- "grad_norm": 0.02917388454079628,
3497
- "learning_rate": 2.899112249786229e-08,
3498
- "loss": 0.0115,
3499
- "step": 406
3500
- },
3501
- {
3502
- "epoch": 4.933333333333334,
3503
- "grad_norm": 0.032552849501371384,
3504
- "learning_rate": 1.6308195957182027e-08,
3505
- "loss": 0.0125,
3506
- "step": 407
3507
- },
3508
- {
3509
- "epoch": 4.945454545454545,
3510
- "grad_norm": 0.026771927252411842,
3511
- "learning_rate": 7.248306003865279e-09,
3512
- "loss": 0.0123,
3513
- "step": 408
3514
- },
3515
- {
3516
- "epoch": 4.957575757575757,
3517
- "grad_norm": 0.024449503049254417,
3518
- "learning_rate": 1.8121093383671738e-09,
3519
- "loss": 0.0117,
3520
- "step": 409
3521
  },
3522
  {
3523
- "epoch": 4.96969696969697,
3524
- "grad_norm": 0.02603001333773136,
3525
  "learning_rate": 0.0,
3526
- "loss": 0.0104,
3527
- "step": 410
3528
- },
3529
- {
3530
- "epoch": 4.96969696969697,
3531
- "eval_loss": 0.020535213872790337,
3532
- "eval_runtime": 6.2062,
3533
- "eval_samples_per_second": 8.056,
3534
- "eval_steps_per_second": 2.095,
3535
- "step": 410
3536
  },
3537
  {
3538
- "epoch": 4.96969696969697,
3539
- "step": 410,
3540
- "total_flos": 6.27193584892674e+17,
3541
- "train_loss": 0.027697906577278202,
3542
- "train_runtime": 5078.5288,
3543
- "train_samples_per_second": 2.598,
3544
- "train_steps_per_second": 0.081
3545
  }
3546
  ],
3547
  "logging_steps": 1,
3548
- "max_steps": 410,
3549
  "num_input_tokens_seen": 0,
3550
- "num_train_epochs": 5,
3551
- "save_steps": 50,
3552
  "stateful_callbacks": {
 
 
 
 
 
 
 
 
 
3553
  "TrainerControl": {
3554
  "args": {
3555
  "should_epoch_stop": false,
@@ -3561,7 +58,7 @@
3561
  "attributes": {}
3562
  }
3563
  },
3564
- "total_flos": 6.27193584892674e+17,
3565
  "train_batch_size": 4,
3566
  "trial_name": null,
3567
  "trial_params": null
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6956521739130435,
5
+ "eval_steps": 50,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.34782608695652173,
13
+ "grad_norm": 0.07414738088846207,
14
+ "learning_rate": 0.0001,
15
+ "loss": 0.0288,
16
+ "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  },
18
  {
19
+ "epoch": 0.6956521739130435,
20
+ "grad_norm": 0.06888309866189957,
21
  "learning_rate": 0.0,
22
+ "loss": 0.0298,
23
+ "step": 2
 
 
 
 
 
 
 
 
24
  },
25
  {
26
+ "epoch": 0.6956521739130435,
27
+ "step": 2,
28
+ "total_flos": 3880733380509696.0,
29
+ "train_loss": 0.029286871664226055,
30
+ "train_runtime": 89.5279,
31
+ "train_samples_per_second": 1.005,
32
+ "train_steps_per_second": 0.022
33
  }
34
  ],
35
  "logging_steps": 1,
36
+ "max_steps": 2,
37
  "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 1,
39
+ "save_steps": 100,
40
  "stateful_callbacks": {
41
+ "EarlyStoppingCallback": {
42
+ "args": {
43
+ "early_stopping_patience": 5,
44
+ "early_stopping_threshold": 0.0
45
+ },
46
+ "attributes": {
47
+ "early_stopping_patience_counter": 0
48
+ }
49
+ },
50
  "TrainerControl": {
51
  "args": {
52
  "should_epoch_stop": false,
 
58
  "attributes": {}
59
  }
60
  },
61
+ "total_flos": 3880733380509696.0,
62
  "train_batch_size": 4,
63
  "trial_name": null,
64
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d96aa9d85c0c8aaa8150b6566c50c34edbca6adae21b4dd043144f9d0462346e
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b07d6117d888dc51d19e06cb48a53cb20d5edb3faef27e7da7fca291d4a00d
3
  size 5496
training_loss.png CHANGED