Model save
Browse files- README.md +9 -9
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +9 -9
- eval_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +593 -665
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
-
base_model: codellama/
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# codellama-7b-sft-lora-func-names
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [codellama/
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -44,17 +44,17 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
-
- training_steps:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
+
base_model: codellama/CodeLlama-7b-Instruct-hf
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
|
|
| 13 |
|
| 14 |
# codellama-7b-sft-lora-func-names
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7084
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- training_steps: 900
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.7541 | 0.01 | 180 | 0.7222 |
|
| 54 |
+
| 0.7126 | 0.01 | 360 | 0.7118 |
|
| 55 |
+
| 0.7342 | 0.02 | 540 | 0.7100 |
|
| 56 |
+
| 0.7216 | 0.03 | 720 | 0.7083 |
|
| 57 |
+
| 0.7171 | 0.04 | 900 | 0.7084 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "codellama/
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -16,10 +16,10 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
| 19 |
"q_proj",
|
| 20 |
-
"k_proj",
|
| 21 |
"o_proj",
|
| 22 |
-
"
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
"q_proj",
|
|
|
|
| 21 |
"o_proj",
|
| 22 |
+
"k_proj"
|
| 23 |
],
|
| 24 |
"task_type": "CAUSAL_LM"
|
| 25 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 536906096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dd35e68b814416647cebfb59b1a3eb02805721bcd06f0fd64b38a515eeb3965
|
| 3 |
size 536906096
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime": 117.
|
| 5 |
"eval_samples": 2000,
|
| 6 |
-
"eval_samples_per_second": 16.
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples":
|
| 11 |
-
"train_samples_per_second": 0.
|
| 12 |
"train_steps_per_second": 0.041
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.04,
|
| 3 |
+
"eval_loss": 0.70841383934021,
|
| 4 |
+
"eval_runtime": 117.6726,
|
| 5 |
"eval_samples": 2000,
|
| 6 |
+
"eval_samples_per_second": 16.996,
|
| 7 |
+
"eval_steps_per_second": 4.249,
|
| 8 |
+
"train_loss": 0.7602509791321225,
|
| 9 |
+
"train_runtime": 22175.0023,
|
| 10 |
+
"train_samples": 405813,
|
| 11 |
+
"train_samples_per_second": 0.649,
|
| 12 |
"train_steps_per_second": 0.041
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime": 117.
|
| 5 |
"eval_samples": 2000,
|
| 6 |
-
"eval_samples_per_second": 16.
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.04,
|
| 3 |
+
"eval_loss": 0.70841383934021,
|
| 4 |
+
"eval_runtime": 117.6726,
|
| 5 |
"eval_samples": 2000,
|
| 6 |
+
"eval_samples_per_second": 16.996,
|
| 7 |
+
"eval_steps_per_second": 4.249
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 0.
|
| 7 |
"train_steps_per_second": 0.041
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.04,
|
| 3 |
+
"train_loss": 0.7602509791321225,
|
| 4 |
+
"train_runtime": 22175.0023,
|
| 5 |
+
"train_samples": 405813,
|
| 6 |
+
"train_samples_per_second": 0.649,
|
| 7 |
"train_steps_per_second": 0.041
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1226 +1,1154 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"learning_rate": 4.
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 2.
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 4.
|
| 26 |
-
"loss": 1.
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 6.
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 8.
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 1.
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 1.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 1.
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 35
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 1.
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 40
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 45
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 2.
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 50
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 2.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 55
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 2.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 60
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 2.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 65
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 70
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate": 3.
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 75
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"learning_rate": 3.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 80
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
-
"learning_rate": 3.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 85
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 90
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"learning_rate": 3.
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 95
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"learning_rate": 3.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 100
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate": 3.
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 105
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"learning_rate": 3.
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 110
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"learning_rate": 3.
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 115
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"learning_rate": 3.
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 120
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"learning_rate": 3.
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 125
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
-
"learning_rate": 3.
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 130
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"learning_rate": 3.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 135
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"learning_rate": 3.
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 140
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 0.
|
| 187 |
-
"learning_rate": 3.
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 145
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 0.
|
| 193 |
-
"learning_rate": 3.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 150
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 0.
|
| 199 |
-
"learning_rate": 3.
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 155
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"learning_rate": 3.
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 160
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 0.
|
| 211 |
-
"learning_rate": 3.
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 165
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 0.
|
| 217 |
-
"learning_rate": 3.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 170
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"learning_rate": 3.
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 175
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch": 0.
|
| 229 |
-
"learning_rate": 3.
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 180
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 0.
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
|
|
|
|
|
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch": 0.
|
| 241 |
-
"learning_rate": 3.
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch": 0.
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
-
"eval_steps_per_second": 4.233,
|
| 251 |
-
"step": 192
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch": 0.
|
| 255 |
-
"learning_rate": 3.
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 195
|
| 258 |
},
|
| 259 |
{
|
| 260 |
-
"epoch": 0.
|
| 261 |
-
"learning_rate": 3.
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 200
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch": 0.
|
| 267 |
-
"learning_rate": 3.
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 205
|
| 270 |
},
|
| 271 |
{
|
| 272 |
-
"epoch": 0.
|
| 273 |
-
"learning_rate": 3.
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 210
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch": 0.
|
| 279 |
-
"learning_rate": 3.
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 215
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch": 0.
|
| 285 |
-
"learning_rate": 3.
|
| 286 |
-
"loss": 0.
|
| 287 |
"step": 220
|
| 288 |
},
|
| 289 |
{
|
| 290 |
-
"epoch": 0.
|
| 291 |
-
"learning_rate": 3.
|
| 292 |
-
"loss": 0.
|
| 293 |
"step": 225
|
| 294 |
},
|
| 295 |
{
|
| 296 |
-
"epoch": 0.
|
| 297 |
-
"learning_rate": 3.
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 230
|
| 300 |
},
|
| 301 |
{
|
| 302 |
-
"epoch": 0.
|
| 303 |
-
"learning_rate": 3.
|
| 304 |
-
"loss": 0.
|
| 305 |
"step": 235
|
| 306 |
},
|
| 307 |
{
|
| 308 |
-
"epoch": 0.
|
| 309 |
-
"learning_rate": 3.
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 240
|
| 312 |
},
|
| 313 |
{
|
| 314 |
-
"epoch": 0.
|
| 315 |
-
"learning_rate": 3.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 245
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 0.
|
| 321 |
-
"learning_rate": 3.
|
| 322 |
-
"loss": 0.
|
| 323 |
"step": 250
|
| 324 |
},
|
| 325 |
{
|
| 326 |
-
"epoch": 0.
|
| 327 |
-
"learning_rate": 3.
|
| 328 |
-
"loss": 0.
|
| 329 |
"step": 255
|
| 330 |
},
|
| 331 |
{
|
| 332 |
-
"epoch": 0.
|
| 333 |
-
"learning_rate": 3.
|
| 334 |
-
"loss": 0.
|
| 335 |
"step": 260
|
| 336 |
},
|
| 337 |
{
|
| 338 |
-
"epoch": 0.
|
| 339 |
-
"learning_rate": 3.
|
| 340 |
-
"loss": 0.
|
| 341 |
"step": 265
|
| 342 |
},
|
| 343 |
{
|
| 344 |
-
"epoch": 0.
|
| 345 |
-
"learning_rate": 3.
|
| 346 |
-
"loss": 0.
|
| 347 |
"step": 270
|
| 348 |
},
|
| 349 |
{
|
| 350 |
-
"epoch": 0.
|
| 351 |
-
"learning_rate": 3.
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 275
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch": 0.
|
| 357 |
-
"learning_rate": 3.
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 280
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 0.
|
| 363 |
-
"learning_rate": 3.
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 285
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch": 0.
|
| 369 |
-
"learning_rate": 3.
|
| 370 |
-
"loss": 0.
|
| 371 |
"step": 290
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch": 0.
|
| 375 |
-
"learning_rate": 3.
|
| 376 |
-
"loss": 0.
|
| 377 |
"step": 295
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 0.
|
| 381 |
-
"learning_rate": 3.
|
| 382 |
-
"loss": 0.
|
| 383 |
"step": 300
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"epoch": 0.
|
| 387 |
-
"learning_rate": 3.
|
| 388 |
-
"loss": 0.
|
| 389 |
"step": 305
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch": 0.
|
| 393 |
-
"learning_rate": 3.
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 310
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch": 0.
|
| 399 |
-
"learning_rate": 3.
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 315
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"learning_rate": 3.
|
| 406 |
-
"loss": 0.
|
| 407 |
"step": 320
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch": 0.
|
| 411 |
-
"learning_rate": 3.
|
| 412 |
-
"loss": 0.
|
| 413 |
"step": 325
|
| 414 |
},
|
| 415 |
{
|
| 416 |
-
"epoch": 0.
|
| 417 |
-
"learning_rate": 3.
|
| 418 |
-
"loss": 0.
|
| 419 |
"step": 330
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"epoch": 0.
|
| 423 |
-
"learning_rate": 3.
|
| 424 |
-
"loss": 0.
|
| 425 |
"step": 335
|
| 426 |
},
|
| 427 |
{
|
| 428 |
-
"epoch": 0.
|
| 429 |
-
"learning_rate": 3.
|
| 430 |
-
"loss": 0.
|
| 431 |
"step": 340
|
| 432 |
},
|
| 433 |
{
|
| 434 |
-
"epoch": 0.
|
| 435 |
-
"learning_rate": 3.
|
| 436 |
-
"loss": 0.
|
| 437 |
"step": 345
|
| 438 |
},
|
| 439 |
{
|
| 440 |
-
"epoch": 0.
|
| 441 |
-
"learning_rate": 3.
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 350
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch": 0.
|
| 447 |
-
"learning_rate": 3.
|
| 448 |
-
"loss": 0.
|
| 449 |
"step": 355
|
| 450 |
},
|
| 451 |
{
|
| 452 |
-
"epoch": 0.
|
| 453 |
-
"learning_rate": 3.
|
| 454 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 455 |
"step": 360
|
| 456 |
},
|
| 457 |
{
|
| 458 |
-
"epoch": 0.
|
| 459 |
-
"learning_rate":
|
| 460 |
-
"loss": 0.
|
| 461 |
"step": 365
|
| 462 |
},
|
| 463 |
{
|
| 464 |
-
"epoch": 0.
|
| 465 |
-
"learning_rate":
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 370
|
| 468 |
},
|
| 469 |
{
|
| 470 |
-
"epoch": 0.
|
| 471 |
-
"learning_rate":
|
| 472 |
-
"loss": 0.
|
| 473 |
"step": 375
|
| 474 |
},
|
| 475 |
{
|
| 476 |
-
"epoch": 0.
|
| 477 |
-
"learning_rate":
|
| 478 |
-
"loss": 0.
|
| 479 |
"step": 380
|
| 480 |
},
|
| 481 |
{
|
| 482 |
-
"epoch": 0.
|
| 483 |
-
"
|
| 484 |
-
"
|
| 485 |
-
"eval_samples_per_second": 16.975,
|
| 486 |
-
"eval_steps_per_second": 4.244,
|
| 487 |
-
"step": 384
|
| 488 |
-
},
|
| 489 |
-
{
|
| 490 |
-
"epoch": 0.62,
|
| 491 |
-
"learning_rate": 2.9936954888047478e-05,
|
| 492 |
-
"loss": 0.6363,
|
| 493 |
"step": 385
|
| 494 |
},
|
| 495 |
{
|
| 496 |
-
"epoch": 0.
|
| 497 |
-
"learning_rate": 2.
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 390
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch": 0.
|
| 503 |
-
"learning_rate": 2.
|
| 504 |
-
"loss": 0.
|
| 505 |
"step": 395
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch": 0.
|
| 509 |
-
"learning_rate": 2.
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 400
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch": 0.
|
| 515 |
-
"learning_rate": 2.
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 405
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch": 0.
|
| 521 |
-
"learning_rate": 2.
|
| 522 |
-
"loss": 0.
|
| 523 |
"step": 410
|
| 524 |
},
|
| 525 |
{
|
| 526 |
-
"epoch": 0.
|
| 527 |
-
"learning_rate": 2.
|
| 528 |
-
"loss": 0.
|
| 529 |
"step": 415
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch": 0.
|
| 533 |
-
"learning_rate": 2.
|
| 534 |
-
"loss": 0.
|
| 535 |
"step": 420
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch": 0.
|
| 539 |
-
"learning_rate": 2.
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 425
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch": 0.
|
| 545 |
-
"learning_rate": 2.
|
| 546 |
-
"loss": 0.
|
| 547 |
"step": 430
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch": 0.
|
| 551 |
-
"learning_rate": 2.
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 435
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch": 0.
|
| 557 |
-
"learning_rate": 2.
|
| 558 |
-
"loss": 0.
|
| 559 |
"step": 440
|
| 560 |
},
|
| 561 |
{
|
| 562 |
-
"epoch": 0.
|
| 563 |
-
"learning_rate": 2.
|
| 564 |
-
"loss": 0.
|
| 565 |
"step": 445
|
| 566 |
},
|
| 567 |
{
|
| 568 |
-
"epoch": 0.
|
| 569 |
-
"learning_rate": 2.
|
| 570 |
-
"loss": 0.
|
| 571 |
"step": 450
|
| 572 |
},
|
| 573 |
{
|
| 574 |
-
"epoch": 0.
|
| 575 |
-
"learning_rate": 2.
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 455
|
| 578 |
},
|
| 579 |
{
|
| 580 |
-
"epoch": 0.
|
| 581 |
-
"learning_rate": 2.
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 460
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch": 0.
|
| 587 |
-
"learning_rate": 2.
|
| 588 |
-
"loss": 0.
|
| 589 |
"step": 465
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch": 0.
|
| 593 |
-
"learning_rate": 2.
|
| 594 |
-
"loss": 0.
|
| 595 |
"step": 470
|
| 596 |
},
|
| 597 |
{
|
| 598 |
-
"epoch": 0.
|
| 599 |
-
"learning_rate": 2.
|
| 600 |
-
"loss": 0.
|
| 601 |
"step": 475
|
| 602 |
},
|
| 603 |
{
|
| 604 |
-
"epoch": 0.
|
| 605 |
-
"learning_rate": 2.
|
| 606 |
-
"loss": 0.
|
| 607 |
"step": 480
|
| 608 |
},
|
| 609 |
{
|
| 610 |
-
"epoch": 0.
|
| 611 |
-
"learning_rate": 2.
|
| 612 |
-
"loss": 0.
|
| 613 |
"step": 485
|
| 614 |
},
|
| 615 |
{
|
| 616 |
-
"epoch": 0.
|
| 617 |
-
"learning_rate": 2.
|
| 618 |
-
"loss": 0.
|
| 619 |
"step": 490
|
| 620 |
},
|
| 621 |
{
|
| 622 |
-
"epoch": 0.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 495
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch": 0.
|
| 629 |
-
"learning_rate":
|
| 630 |
-
"loss": 0.
|
| 631 |
"step": 500
|
| 632 |
},
|
| 633 |
{
|
| 634 |
-
"epoch": 0.
|
| 635 |
-
"learning_rate":
|
| 636 |
-
"loss": 0.
|
| 637 |
"step": 505
|
| 638 |
},
|
| 639 |
{
|
| 640 |
-
"epoch": 0.
|
| 641 |
-
"learning_rate":
|
| 642 |
-
"loss": 0.
|
| 643 |
"step": 510
|
| 644 |
},
|
| 645 |
{
|
| 646 |
-
"epoch": 0.
|
| 647 |
-
"learning_rate":
|
| 648 |
-
"loss": 0.
|
| 649 |
"step": 515
|
| 650 |
},
|
| 651 |
{
|
| 652 |
-
"epoch": 0.
|
| 653 |
-
"learning_rate":
|
| 654 |
-
"loss": 0.
|
| 655 |
"step": 520
|
| 656 |
},
|
| 657 |
{
|
| 658 |
-
"epoch": 0.
|
| 659 |
-
"learning_rate":
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 525
|
| 662 |
},
|
| 663 |
{
|
| 664 |
-
"epoch": 0.
|
| 665 |
-
"learning_rate": 1.
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 530
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch": 0.
|
| 671 |
-
"learning_rate": 1.
|
| 672 |
-
"loss": 0.
|
| 673 |
"step": 535
|
| 674 |
},
|
| 675 |
{
|
| 676 |
-
"epoch": 0.
|
| 677 |
-
"learning_rate": 1.
|
| 678 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 679 |
"step": 540
|
| 680 |
},
|
| 681 |
{
|
| 682 |
-
"epoch": 0.
|
| 683 |
-
"learning_rate": 1.
|
| 684 |
-
"loss": 0.
|
| 685 |
"step": 545
|
| 686 |
},
|
| 687 |
{
|
| 688 |
-
"epoch": 0.
|
| 689 |
-
"learning_rate": 1.
|
| 690 |
-
"loss": 0.
|
| 691 |
"step": 550
|
| 692 |
},
|
| 693 |
{
|
| 694 |
-
"epoch": 0.
|
| 695 |
-
"learning_rate": 1.
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 555
|
| 698 |
},
|
| 699 |
{
|
| 700 |
-
"epoch": 0.
|
| 701 |
-
"learning_rate": 1.
|
| 702 |
-
"loss": 0.
|
| 703 |
"step": 560
|
| 704 |
},
|
| 705 |
{
|
| 706 |
-
"epoch": 0.
|
| 707 |
-
"learning_rate": 1.
|
| 708 |
-
"loss": 0.
|
| 709 |
"step": 565
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 0.
|
| 713 |
-
"learning_rate": 1.
|
| 714 |
-
"loss": 0.
|
| 715 |
"step": 570
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch": 0.
|
| 719 |
-
"learning_rate": 1.
|
| 720 |
-
"loss": 0.
|
| 721 |
"step": 575
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch": 0.
|
| 725 |
-
"
|
| 726 |
-
"
|
| 727 |
-
"eval_samples_per_second": 16.955,
|
| 728 |
-
"eval_steps_per_second": 4.239,
|
| 729 |
-
"step": 576
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 0.93,
|
| 733 |
-
"learning_rate": 1.6240944911997765e-05,
|
| 734 |
-
"loss": 0.5815,
|
| 735 |
"step": 580
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch": 0.
|
| 739 |
-
"learning_rate": 1.
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 585
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"epoch": 0.
|
| 745 |
-
"learning_rate": 1.
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 590
|
| 748 |
},
|
| 749 |
{
|
| 750 |
-
"epoch": 0.
|
| 751 |
-
"learning_rate": 1.
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 595
|
| 754 |
},
|
| 755 |
{
|
| 756 |
-
"epoch": 0.
|
| 757 |
-
"learning_rate": 1.
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 600
|
| 760 |
},
|
| 761 |
{
|
| 762 |
-
"epoch": 0.
|
| 763 |
-
"learning_rate": 1.
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 605
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch": 0.
|
| 769 |
-
"learning_rate": 1.
|
| 770 |
-
"loss": 0.
|
| 771 |
"step": 610
|
| 772 |
},
|
| 773 |
{
|
| 774 |
-
"epoch": 0.
|
| 775 |
-
"learning_rate": 1.
|
| 776 |
-
"loss": 0.
|
| 777 |
"step": 615
|
| 778 |
},
|
| 779 |
{
|
| 780 |
-
"epoch": 0.
|
| 781 |
-
"learning_rate": 1.
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 620
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch":
|
| 787 |
-
"learning_rate": 1.
|
| 788 |
-
"loss": 0.
|
| 789 |
"step": 625
|
| 790 |
},
|
| 791 |
{
|
| 792 |
-
"epoch":
|
| 793 |
-
"learning_rate": 1.
|
| 794 |
-
"loss": 0.
|
| 795 |
"step": 630
|
| 796 |
},
|
| 797 |
{
|
| 798 |
-
"epoch":
|
| 799 |
-
"learning_rate":
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 635
|
| 802 |
},
|
| 803 |
{
|
| 804 |
-
"epoch":
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 640
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch":
|
| 811 |
-
"learning_rate":
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 645
|
| 814 |
},
|
| 815 |
{
|
| 816 |
-
"epoch":
|
| 817 |
-
"learning_rate":
|
| 818 |
-
"loss": 0.
|
| 819 |
"step": 650
|
| 820 |
},
|
| 821 |
{
|
| 822 |
-
"epoch":
|
| 823 |
-
"learning_rate":
|
| 824 |
-
"loss": 0.
|
| 825 |
"step": 655
|
| 826 |
},
|
| 827 |
{
|
| 828 |
-
"epoch":
|
| 829 |
-
"learning_rate":
|
| 830 |
-
"loss": 0.
|
| 831 |
"step": 660
|
| 832 |
},
|
| 833 |
{
|
| 834 |
-
"epoch":
|
| 835 |
-
"learning_rate":
|
| 836 |
-
"loss": 0.
|
| 837 |
"step": 665
|
| 838 |
},
|
| 839 |
{
|
| 840 |
-
"epoch":
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 670
|
| 844 |
},
|
| 845 |
{
|
| 846 |
-
"epoch":
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 675
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch":
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 680
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch":
|
| 859 |
-
"learning_rate":
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 685
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch":
|
| 865 |
-
"learning_rate":
|
| 866 |
-
"loss": 0.
|
| 867 |
"step": 690
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch":
|
| 871 |
-
"learning_rate":
|
| 872 |
-
"loss": 0.
|
| 873 |
"step": 695
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch":
|
| 877 |
-
"learning_rate":
|
| 878 |
-
"loss": 0.
|
| 879 |
"step": 700
|
| 880 |
},
|
| 881 |
{
|
| 882 |
-
"epoch":
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 705
|
| 886 |
},
|
| 887 |
{
|
| 888 |
-
"epoch":
|
| 889 |
-
"learning_rate":
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 710
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch":
|
| 895 |
-
"learning_rate":
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 715
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch":
|
| 901 |
-
"learning_rate":
|
| 902 |
-
"loss": 0.
|
| 903 |
"step": 720
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch":
|
| 907 |
-
"
|
| 908 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 909 |
"step": 725
|
| 910 |
},
|
| 911 |
{
|
| 912 |
-
"epoch":
|
| 913 |
-
"learning_rate":
|
| 914 |
-
"loss": 0.
|
| 915 |
"step": 730
|
| 916 |
},
|
| 917 |
{
|
| 918 |
-
"epoch":
|
| 919 |
-
"learning_rate":
|
| 920 |
-
"loss": 0.
|
| 921 |
"step": 735
|
| 922 |
},
|
| 923 |
{
|
| 924 |
-
"epoch":
|
| 925 |
-
"learning_rate":
|
| 926 |
-
"loss": 0.
|
| 927 |
"step": 740
|
| 928 |
},
|
| 929 |
{
|
| 930 |
-
"epoch":
|
| 931 |
-
"learning_rate":
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 745
|
| 934 |
},
|
| 935 |
{
|
| 936 |
-
"epoch":
|
| 937 |
-
"learning_rate":
|
| 938 |
-
"loss": 0.
|
| 939 |
"step": 750
|
| 940 |
},
|
| 941 |
{
|
| 942 |
-
"epoch":
|
| 943 |
-
"learning_rate":
|
| 944 |
-
"loss": 0.
|
| 945 |
"step": 755
|
| 946 |
},
|
| 947 |
{
|
| 948 |
-
"epoch":
|
| 949 |
-
"learning_rate":
|
| 950 |
-
"loss": 0.
|
| 951 |
"step": 760
|
| 952 |
},
|
| 953 |
{
|
| 954 |
-
"epoch":
|
| 955 |
-
"learning_rate":
|
| 956 |
-
"loss": 0.
|
| 957 |
"step": 765
|
| 958 |
},
|
| 959 |
{
|
| 960 |
-
"epoch":
|
| 961 |
-
"
|
| 962 |
-
"
|
| 963 |
-
"eval_samples_per_second": 16.965,
|
| 964 |
-
"eval_steps_per_second": 4.241,
|
| 965 |
-
"step": 768
|
| 966 |
-
},
|
| 967 |
-
{
|
| 968 |
-
"epoch": 1.23,
|
| 969 |
-
"learning_rate": 4.586027414062839e-06,
|
| 970 |
-
"loss": 0.5603,
|
| 971 |
"step": 770
|
| 972 |
},
|
| 973 |
{
|
| 974 |
-
"epoch":
|
| 975 |
-
"learning_rate":
|
| 976 |
-
"loss": 0.
|
| 977 |
"step": 775
|
| 978 |
},
|
| 979 |
{
|
| 980 |
-
"epoch":
|
| 981 |
-
"learning_rate":
|
| 982 |
-
"loss": 0.
|
| 983 |
"step": 780
|
| 984 |
},
|
| 985 |
{
|
| 986 |
-
"epoch":
|
| 987 |
-
"learning_rate":
|
| 988 |
-
"loss": 0.
|
| 989 |
"step": 785
|
| 990 |
},
|
| 991 |
{
|
| 992 |
-
"epoch":
|
| 993 |
-
"learning_rate":
|
| 994 |
-
"loss": 0.
|
| 995 |
"step": 790
|
| 996 |
},
|
| 997 |
{
|
| 998 |
-
"epoch":
|
| 999 |
-
"learning_rate":
|
| 1000 |
-
"loss": 0.
|
| 1001 |
"step": 795
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
-
"epoch":
|
| 1005 |
-
"learning_rate":
|
| 1006 |
-
"loss": 0.
|
| 1007 |
"step": 800
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch":
|
| 1011 |
-
"learning_rate":
|
| 1012 |
-
"loss": 0.
|
| 1013 |
"step": 805
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch":
|
| 1017 |
-
"learning_rate":
|
| 1018 |
-
"loss": 0.
|
| 1019 |
"step": 810
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch":
|
| 1023 |
-
"learning_rate":
|
| 1024 |
-
"loss": 0.
|
| 1025 |
"step": 815
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch":
|
| 1029 |
-
"learning_rate":
|
| 1030 |
-
"loss": 0.
|
| 1031 |
"step": 820
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch":
|
| 1035 |
-
"learning_rate":
|
| 1036 |
-
"loss": 0.
|
| 1037 |
"step": 825
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch":
|
| 1041 |
-
"learning_rate":
|
| 1042 |
-
"loss": 0.
|
| 1043 |
"step": 830
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch":
|
| 1047 |
-
"learning_rate":
|
| 1048 |
-
"loss": 0.
|
| 1049 |
"step": 835
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
-
"epoch":
|
| 1053 |
-
"learning_rate":
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"step": 840
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
-
"epoch":
|
| 1059 |
-
"learning_rate":
|
| 1060 |
-
"loss": 0.
|
| 1061 |
"step": 845
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
-
"epoch":
|
| 1065 |
-
"learning_rate":
|
| 1066 |
-
"loss": 0.
|
| 1067 |
"step": 850
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
-
"epoch":
|
| 1071 |
-
"learning_rate":
|
| 1072 |
-
"loss": 0.
|
| 1073 |
"step": 855
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
-
"epoch":
|
| 1077 |
-
"learning_rate":
|
| 1078 |
-
"loss": 0.
|
| 1079 |
"step": 860
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
-
"epoch":
|
| 1083 |
-
"learning_rate": 1.
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 865
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
-
"epoch":
|
| 1089 |
-
"learning_rate": 1.
|
| 1090 |
-
"loss": 0.
|
| 1091 |
"step": 870
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
-
"epoch":
|
| 1095 |
-
"learning_rate": 9.
|
| 1096 |
-
"loss": 0.
|
| 1097 |
"step": 875
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
-
"epoch":
|
| 1101 |
-
"learning_rate":
|
| 1102 |
-
"loss": 0.
|
| 1103 |
"step": 880
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
-
"epoch":
|
| 1107 |
-
"learning_rate":
|
| 1108 |
-
"loss": 0.
|
| 1109 |
"step": 885
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
-
"epoch":
|
| 1113 |
-
"learning_rate":
|
| 1114 |
-
"loss": 0.
|
| 1115 |
"step": 890
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
-
"epoch":
|
| 1119 |
-
"learning_rate":
|
| 1120 |
-
"loss": 0.
|
| 1121 |
"step": 895
|
| 1122 |
},
|
| 1123 |
{
|
| 1124 |
-
"epoch":
|
| 1125 |
-
"learning_rate": 4.740798576013328e-07,
|
| 1126 |
-
"loss": 0.5472,
|
| 1127 |
-
"step": 900
|
| 1128 |
-
},
|
| 1129 |
-
{
|
| 1130 |
-
"epoch": 1.45,
|
| 1131 |
-
"learning_rate": 3.9861140110209806e-07,
|
| 1132 |
-
"loss": 0.5339,
|
| 1133 |
-
"step": 905
|
| 1134 |
-
},
|
| 1135 |
-
{
|
| 1136 |
-
"epoch": 1.46,
|
| 1137 |
-
"learning_rate": 3.296216337916458e-07,
|
| 1138 |
-
"loss": 0.536,
|
| 1139 |
-
"step": 910
|
| 1140 |
-
},
|
| 1141 |
-
{
|
| 1142 |
-
"epoch": 1.46,
|
| 1143 |
-
"learning_rate": 2.671333583024205e-07,
|
| 1144 |
-
"loss": 0.5434,
|
| 1145 |
-
"step": 915
|
| 1146 |
-
},
|
| 1147 |
-
{
|
| 1148 |
-
"epoch": 1.47,
|
| 1149 |
-
"learning_rate": 2.111672283811106e-07,
|
| 1150 |
-
"loss": 0.5483,
|
| 1151 |
-
"step": 920
|
| 1152 |
-
},
|
| 1153 |
-
{
|
| 1154 |
-
"epoch": 1.48,
|
| 1155 |
-
"learning_rate": 1.6174174206212922e-07,
|
| 1156 |
-
"loss": 0.5437,
|
| 1157 |
-
"step": 925
|
| 1158 |
-
},
|
| 1159 |
-
{
|
| 1160 |
-
"epoch": 1.49,
|
| 1161 |
-
"learning_rate": 1.1887323555360708e-07,
|
| 1162 |
-
"loss": 0.5446,
|
| 1163 |
-
"step": 930
|
| 1164 |
-
},
|
| 1165 |
-
{
|
| 1166 |
-
"epoch": 1.5,
|
| 1167 |
-
"learning_rate": 8.25758778379293e-08,
|
| 1168 |
-
"loss": 0.5457,
|
| 1169 |
-
"step": 935
|
| 1170 |
-
},
|
| 1171 |
-
{
|
| 1172 |
-
"epoch": 1.5,
|
| 1173 |
-
"learning_rate": 5.286166598855502e-08,
|
| 1174 |
-
"loss": 0.5429,
|
| 1175 |
-
"step": 940
|
| 1176 |
-
},
|
| 1177 |
-
{
|
| 1178 |
-
"epoch": 1.51,
|
| 1179 |
-
"learning_rate": 2.974042120473808e-08,
|
| 1180 |
-
"loss": 0.5405,
|
| 1181 |
-
"step": 945
|
| 1182 |
-
},
|
| 1183 |
-
{
|
| 1184 |
-
"epoch": 1.52,
|
| 1185 |
-
"learning_rate": 1.3219785565399268e-08,
|
| 1186 |
-
"loss": 0.5388,
|
| 1187 |
-
"step": 950
|
| 1188 |
-
},
|
| 1189 |
-
{
|
| 1190 |
-
"epoch": 1.53,
|
| 1191 |
-
"learning_rate": 3.305219503249024e-09,
|
| 1192 |
-
"loss": 0.5402,
|
| 1193 |
-
"step": 955
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 1.54,
|
| 1197 |
"learning_rate": 0.0,
|
| 1198 |
-
"loss": 0.
|
| 1199 |
-
"step":
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
-
"epoch":
|
| 1203 |
-
"eval_loss": 0.
|
| 1204 |
-
"eval_runtime": 117.
|
| 1205 |
-
"eval_samples_per_second": 16.
|
| 1206 |
-
"eval_steps_per_second": 4.
|
| 1207 |
-
"step":
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
-
"epoch":
|
| 1211 |
-
"step":
|
| 1212 |
-
"total_flos": 1.
|
| 1213 |
-
"train_loss": 0.
|
| 1214 |
-
"train_runtime":
|
| 1215 |
-
"train_samples_per_second": 0.
|
| 1216 |
"train_steps_per_second": 0.041
|
| 1217 |
}
|
| 1218 |
],
|
| 1219 |
"logging_steps": 5,
|
| 1220 |
-
"max_steps":
|
| 1221 |
-
"num_train_epochs":
|
| 1222 |
-
"save_steps":
|
| 1223 |
-
"total_flos": 1.
|
| 1224 |
"trial_name": null,
|
| 1225 |
"trial_params": null
|
| 1226 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03548406174226743,
|
| 5 |
+
"eval_steps": 180,
|
| 6 |
+
"global_step": 900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 4.444444444444445e-07,
|
| 14 |
+
"loss": 1.4612,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 2.222222222222222e-06,
|
| 20 |
+
"loss": 1.4717,
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 4.444444444444444e-06,
|
| 26 |
+
"loss": 1.4887,
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.0,
|
| 31 |
+
"learning_rate": 6.666666666666667e-06,
|
| 32 |
+
"loss": 1.4126,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.0,
|
| 37 |
+
"learning_rate": 8.888888888888888e-06,
|
| 38 |
+
"loss": 1.2639,
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.0,
|
| 43 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 44 |
+
"loss": 1.1005,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.0,
|
| 49 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 50 |
+
"loss": 1.0341,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.0,
|
| 55 |
+
"learning_rate": 1.555555555555556e-05,
|
| 56 |
+
"loss": 1.0016,
|
| 57 |
"step": 35
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.0,
|
| 61 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 62 |
+
"loss": 0.9879,
|
| 63 |
"step": 40
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.0,
|
| 67 |
+
"learning_rate": 2e-05,
|
| 68 |
+
"loss": 0.947,
|
| 69 |
"step": 45
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.0,
|
| 73 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 74 |
+
"loss": 0.9558,
|
| 75 |
"step": 50
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.0,
|
| 79 |
+
"learning_rate": 2.444444444444445e-05,
|
| 80 |
+
"loss": 0.9208,
|
| 81 |
"step": 55
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.0,
|
| 85 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 86 |
+
"loss": 0.9096,
|
| 87 |
"step": 60
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.0,
|
| 91 |
+
"learning_rate": 2.888888888888889e-05,
|
| 92 |
+
"loss": 0.8924,
|
| 93 |
"step": 65
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.0,
|
| 97 |
+
"learning_rate": 3.111111111111112e-05,
|
| 98 |
+
"loss": 0.8883,
|
| 99 |
"step": 70
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.0,
|
| 103 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 104 |
+
"loss": 0.879,
|
| 105 |
"step": 75
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.0,
|
| 109 |
+
"learning_rate": 3.555555555555555e-05,
|
| 110 |
+
"loss": 0.8643,
|
| 111 |
"step": 80
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.0,
|
| 115 |
+
"learning_rate": 3.777777777777778e-05,
|
| 116 |
+
"loss": 0.8491,
|
| 117 |
"step": 85
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.0,
|
| 121 |
+
"learning_rate": 4e-05,
|
| 122 |
+
"loss": 0.8485,
|
| 123 |
"step": 90
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.0,
|
| 127 |
+
"learning_rate": 3.999623940897003e-05,
|
| 128 |
+
"loss": 0.8734,
|
| 129 |
"step": 95
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.0,
|
| 133 |
+
"learning_rate": 3.998495905008461e-05,
|
| 134 |
+
"loss": 0.8522,
|
| 135 |
"step": 100
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.0,
|
| 139 |
+
"learning_rate": 3.996616316542537e-05,
|
| 140 |
+
"loss": 0.8434,
|
| 141 |
"step": 105
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.0,
|
| 145 |
+
"learning_rate": 3.993985882335584e-05,
|
| 146 |
+
"loss": 0.8312,
|
| 147 |
"step": 110
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.0,
|
| 151 |
+
"learning_rate": 3.9906055915863316e-05,
|
| 152 |
+
"loss": 0.8248,
|
| 153 |
"step": 115
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.0,
|
| 157 |
+
"learning_rate": 3.9864767154838864e-05,
|
| 158 |
+
"loss": 0.8387,
|
| 159 |
"step": 120
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.0,
|
| 163 |
+
"learning_rate": 3.9816008067296905e-05,
|
| 164 |
+
"loss": 0.8191,
|
| 165 |
"step": 125
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.01,
|
| 169 |
+
"learning_rate": 3.9759796989536185e-05,
|
| 170 |
+
"loss": 0.8047,
|
| 171 |
"step": 130
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.01,
|
| 175 |
+
"learning_rate": 3.9696155060244166e-05,
|
| 176 |
+
"loss": 0.7999,
|
| 177 |
"step": 135
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.01,
|
| 181 |
+
"learning_rate": 3.9625106212547696e-05,
|
| 182 |
+
"loss": 0.7841,
|
| 183 |
"step": 140
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 0.01,
|
| 187 |
+
"learning_rate": 3.9546677165012714e-05,
|
| 188 |
+
"loss": 0.7546,
|
| 189 |
"step": 145
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.01,
|
| 193 |
+
"learning_rate": 3.946089741159648e-05,
|
| 194 |
+
"loss": 0.7539,
|
| 195 |
"step": 150
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.01,
|
| 199 |
+
"learning_rate": 3.9367799210556124e-05,
|
| 200 |
+
"loss": 0.7346,
|
| 201 |
"step": 155
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.01,
|
| 205 |
+
"learning_rate": 3.926741757231761e-05,
|
| 206 |
+
"loss": 0.7315,
|
| 207 |
"step": 160
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 0.01,
|
| 211 |
+
"learning_rate": 3.915979024630978e-05,
|
| 212 |
+
"loss": 0.744,
|
| 213 |
"step": 165
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 0.01,
|
| 217 |
+
"learning_rate": 3.904495770676831e-05,
|
| 218 |
+
"loss": 0.7298,
|
| 219 |
"step": 170
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.01,
|
| 223 |
+
"learning_rate": 3.892296313751502e-05,
|
| 224 |
+
"loss": 0.7385,
|
| 225 |
"step": 175
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 0.01,
|
| 229 |
+
"learning_rate": 3.879385241571817e-05,
|
| 230 |
+
"loss": 0.7541,
|
| 231 |
"step": 180
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 0.01,
|
| 235 |
+
"eval_loss": 0.7222402691841125,
|
| 236 |
+
"eval_runtime": 118.1542,
|
| 237 |
+
"eval_samples_per_second": 16.927,
|
| 238 |
+
"eval_steps_per_second": 4.232,
|
| 239 |
+
"step": 180
|
| 240 |
},
|
| 241 |
{
|
| 242 |
+
"epoch": 0.01,
|
| 243 |
+
"learning_rate": 3.865767409464002e-05,
|
| 244 |
+
"loss": 0.7311,
|
| 245 |
+
"step": 185
|
| 246 |
},
|
| 247 |
{
|
| 248 |
+
"epoch": 0.01,
|
| 249 |
+
"learning_rate": 3.8514479385377813e-05,
|
| 250 |
+
"loss": 0.7376,
|
| 251 |
+
"step": 190
|
|
|
|
|
|
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 0.01,
|
| 255 |
+
"learning_rate": 3.8364322137605484e-05,
|
| 256 |
+
"loss": 0.727,
|
| 257 |
"step": 195
|
| 258 |
},
|
| 259 |
{
|
| 260 |
+
"epoch": 0.01,
|
| 261 |
+
"learning_rate": 3.8207258819322936e-05,
|
| 262 |
+
"loss": 0.739,
|
| 263 |
"step": 200
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"epoch": 0.01,
|
| 267 |
+
"learning_rate": 3.804334849562076e-05,
|
| 268 |
+
"loss": 0.741,
|
| 269 |
"step": 205
|
| 270 |
},
|
| 271 |
{
|
| 272 |
+
"epoch": 0.01,
|
| 273 |
+
"learning_rate": 3.787265280646825e-05,
|
| 274 |
+
"loss": 0.7216,
|
| 275 |
"step": 210
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.01,
|
| 279 |
+
"learning_rate": 3.7695235943533155e-05,
|
| 280 |
+
"loss": 0.7115,
|
| 281 |
"step": 215
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 0.01,
|
| 285 |
+
"learning_rate": 3.7511164626041823e-05,
|
| 286 |
+
"loss": 0.731,
|
| 287 |
"step": 220
|
| 288 |
},
|
| 289 |
{
|
| 290 |
+
"epoch": 0.01,
|
| 291 |
+
"learning_rate": 3.732050807568878e-05,
|
| 292 |
+
"loss": 0.7185,
|
| 293 |
"step": 225
|
| 294 |
},
|
| 295 |
{
|
| 296 |
+
"epoch": 0.01,
|
| 297 |
+
"learning_rate": 3.7123337990605335e-05,
|
| 298 |
+
"loss": 0.729,
|
| 299 |
"step": 230
|
| 300 |
},
|
| 301 |
{
|
| 302 |
+
"epoch": 0.01,
|
| 303 |
+
"learning_rate": 3.691972851839682e-05,
|
| 304 |
+
"loss": 0.7485,
|
| 305 |
"step": 235
|
| 306 |
},
|
| 307 |
{
|
| 308 |
+
"epoch": 0.01,
|
| 309 |
+
"learning_rate": 3.6709756228258735e-05,
|
| 310 |
+
"loss": 0.7344,
|
| 311 |
"step": 240
|
| 312 |
},
|
| 313 |
{
|
| 314 |
+
"epoch": 0.01,
|
| 315 |
+
"learning_rate": 3.649350008218214e-05,
|
| 316 |
+
"loss": 0.7527,
|
| 317 |
"step": 245
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.01,
|
| 321 |
+
"learning_rate": 3.6271041405259354e-05,
|
| 322 |
+
"loss": 0.7381,
|
| 323 |
"step": 250
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 0.01,
|
| 327 |
+
"learning_rate": 3.604246385510088e-05,
|
| 328 |
+
"loss": 0.7512,
|
| 329 |
"step": 255
|
| 330 |
},
|
| 331 |
{
|
| 332 |
+
"epoch": 0.01,
|
| 333 |
+
"learning_rate": 3.580785339037519e-05,
|
| 334 |
+
"loss": 0.7368,
|
| 335 |
"step": 260
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 0.01,
|
| 339 |
+
"learning_rate": 3.5567298238483206e-05,
|
| 340 |
+
"loss": 0.7228,
|
| 341 |
"step": 265
|
| 342 |
},
|
| 343 |
{
|
| 344 |
+
"epoch": 0.01,
|
| 345 |
+
"learning_rate": 3.532088886237956e-05,
|
| 346 |
+
"loss": 0.7361,
|
| 347 |
"step": 270
|
| 348 |
},
|
| 349 |
{
|
| 350 |
+
"epoch": 0.01,
|
| 351 |
+
"learning_rate": 3.506871792655321e-05,
|
| 352 |
+
"loss": 0.727,
|
| 353 |
"step": 275
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 0.01,
|
| 357 |
+
"learning_rate": 3.48108802621801e-05,
|
| 358 |
+
"loss": 0.7198,
|
| 359 |
"step": 280
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.01,
|
| 363 |
+
"learning_rate": 3.4547472831460976e-05,
|
| 364 |
+
"loss": 0.736,
|
| 365 |
"step": 285
|
| 366 |
},
|
| 367 |
{
|
| 368 |
+
"epoch": 0.01,
|
| 369 |
+
"learning_rate": 3.4278594691157985e-05,
|
| 370 |
+
"loss": 0.7552,
|
| 371 |
"step": 290
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 0.01,
|
| 375 |
+
"learning_rate": 3.400434695534337e-05,
|
| 376 |
+
"loss": 0.7316,
|
| 377 |
"step": 295
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 0.01,
|
| 381 |
+
"learning_rate": 3.372483275737468e-05,
|
| 382 |
+
"loss": 0.7235,
|
| 383 |
"step": 300
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"epoch": 0.01,
|
| 387 |
+
"learning_rate": 3.3440157211110454e-05,
|
| 388 |
+
"loss": 0.7189,
|
| 389 |
"step": 305
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 0.01,
|
| 393 |
+
"learning_rate": 3.315042737138128e-05,
|
| 394 |
+
"loss": 0.7358,
|
| 395 |
"step": 310
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 0.01,
|
| 399 |
+
"learning_rate": 3.285575219373079e-05,
|
| 400 |
+
"loss": 0.7252,
|
| 401 |
"step": 315
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 0.01,
|
| 405 |
+
"learning_rate": 3.255624249344198e-05,
|
| 406 |
+
"loss": 0.7157,
|
| 407 |
"step": 320
|
| 408 |
},
|
| 409 |
{
|
| 410 |
+
"epoch": 0.01,
|
| 411 |
+
"learning_rate": 3.2252010903864057e-05,
|
| 412 |
+
"loss": 0.7175,
|
| 413 |
"step": 325
|
| 414 |
},
|
| 415 |
{
|
| 416 |
+
"epoch": 0.01,
|
| 417 |
+
"learning_rate": 3.194317183405573e-05,
|
| 418 |
+
"loss": 0.7417,
|
| 419 |
"step": 330
|
| 420 |
},
|
| 421 |
{
|
| 422 |
+
"epoch": 0.01,
|
| 423 |
+
"learning_rate": 3.1629841425760534e-05,
|
| 424 |
+
"loss": 0.736,
|
| 425 |
"step": 335
|
| 426 |
},
|
| 427 |
{
|
| 428 |
+
"epoch": 0.01,
|
| 429 |
+
"learning_rate": 3.1312137509730776e-05,
|
| 430 |
+
"loss": 0.7194,
|
| 431 |
"step": 340
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"epoch": 0.01,
|
| 435 |
+
"learning_rate": 3.0990179561416124e-05,
|
| 436 |
+
"loss": 0.7222,
|
| 437 |
"step": 345
|
| 438 |
},
|
| 439 |
{
|
| 440 |
+
"epoch": 0.01,
|
| 441 |
+
"learning_rate": 3.066408865603383e-05,
|
| 442 |
+
"loss": 0.7196,
|
| 443 |
"step": 350
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 0.01,
|
| 447 |
+
"learning_rate": 3.0333987423037262e-05,
|
| 448 |
+
"loss": 0.714,
|
| 449 |
"step": 355
|
| 450 |
},
|
| 451 |
{
|
| 452 |
+
"epoch": 0.01,
|
| 453 |
+
"learning_rate": 3.0000000000000004e-05,
|
| 454 |
+
"loss": 0.7126,
|
| 455 |
+
"step": 360
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.01,
|
| 459 |
+
"eval_loss": 0.7118021249771118,
|
| 460 |
+
"eval_runtime": 117.7706,
|
| 461 |
+
"eval_samples_per_second": 16.982,
|
| 462 |
+
"eval_steps_per_second": 4.246,
|
| 463 |
"step": 360
|
| 464 |
},
|
| 465 |
{
|
| 466 |
+
"epoch": 0.01,
|
| 467 |
+
"learning_rate": 2.9662251985932773e-05,
|
| 468 |
+
"loss": 0.7159,
|
| 469 |
"step": 365
|
| 470 |
},
|
| 471 |
{
|
| 472 |
+
"epoch": 0.01,
|
| 473 |
+
"learning_rate": 2.9320870394050783e-05,
|
| 474 |
+
"loss": 0.7249,
|
| 475 |
"step": 370
|
| 476 |
},
|
| 477 |
{
|
| 478 |
+
"epoch": 0.01,
|
| 479 |
+
"learning_rate": 2.897598360400925e-05,
|
| 480 |
+
"loss": 0.7182,
|
| 481 |
"step": 375
|
| 482 |
},
|
| 483 |
{
|
| 484 |
+
"epoch": 0.01,
|
| 485 |
+
"learning_rate": 2.8627721313625073e-05,
|
| 486 |
+
"loss": 0.7083,
|
| 487 |
"step": 380
|
| 488 |
},
|
| 489 |
{
|
| 490 |
+
"epoch": 0.02,
|
| 491 |
+
"learning_rate": 2.8276214490102788e-05,
|
| 492 |
+
"loss": 0.7238,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 493 |
"step": 385
|
| 494 |
},
|
| 495 |
{
|
| 496 |
+
"epoch": 0.02,
|
| 497 |
+
"learning_rate": 2.792159532078314e-05,
|
| 498 |
+
"loss": 0.7137,
|
| 499 |
"step": 390
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 0.02,
|
| 503 |
+
"learning_rate": 2.7563997163432853e-05,
|
| 504 |
+
"loss": 0.7182,
|
| 505 |
"step": 395
|
| 506 |
},
|
| 507 |
{
|
| 508 |
+
"epoch": 0.02,
|
| 509 |
+
"learning_rate": 2.720355449609421e-05,
|
| 510 |
+
"loss": 0.7285,
|
| 511 |
"step": 400
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 0.02,
|
| 515 |
+
"learning_rate": 2.684040286651338e-05,
|
| 516 |
+
"loss": 0.6988,
|
| 517 |
"step": 405
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 0.02,
|
| 521 |
+
"learning_rate": 2.6474678841166426e-05,
|
| 522 |
+
"loss": 0.7217,
|
| 523 |
"step": 410
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"epoch": 0.02,
|
| 527 |
+
"learning_rate": 2.6106519953902268e-05,
|
| 528 |
+
"loss": 0.7185,
|
| 529 |
"step": 415
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 0.02,
|
| 533 |
+
"learning_rate": 2.5736064654221808e-05,
|
| 534 |
+
"loss": 0.7303,
|
| 535 |
"step": 420
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 0.02,
|
| 539 |
+
"learning_rate": 2.536345225521275e-05,
|
| 540 |
+
"loss": 0.7134,
|
| 541 |
"step": 425
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 0.02,
|
| 545 |
+
"learning_rate": 2.4988822881159627e-05,
|
| 546 |
+
"loss": 0.7215,
|
| 547 |
"step": 430
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 0.02,
|
| 551 |
+
"learning_rate": 2.4612317414848804e-05,
|
| 552 |
+
"loss": 0.7219,
|
| 553 |
"step": 435
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 0.02,
|
| 557 |
+
"learning_rate": 2.423407744458822e-05,
|
| 558 |
+
"loss": 0.7253,
|
| 559 |
"step": 440
|
| 560 |
},
|
| 561 |
{
|
| 562 |
+
"epoch": 0.02,
|
| 563 |
+
"learning_rate": 2.3854245210961798e-05,
|
| 564 |
+
"loss": 0.7251,
|
| 565 |
"step": 445
|
| 566 |
},
|
| 567 |
{
|
| 568 |
+
"epoch": 0.02,
|
| 569 |
+
"learning_rate": 2.3472963553338614e-05,
|
| 570 |
+
"loss": 0.7259,
|
| 571 |
"step": 450
|
| 572 |
},
|
| 573 |
{
|
| 574 |
+
"epoch": 0.02,
|
| 575 |
+
"learning_rate": 2.3090375856156813e-05,
|
| 576 |
+
"loss": 0.7412,
|
| 577 |
"step": 455
|
| 578 |
},
|
| 579 |
{
|
| 580 |
+
"epoch": 0.02,
|
| 581 |
+
"learning_rate": 2.2706625995002626e-05,
|
| 582 |
+
"loss": 0.7316,
|
| 583 |
"step": 460
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 0.02,
|
| 587 |
+
"learning_rate": 2.2321858282504606e-05,
|
| 588 |
+
"loss": 0.7166,
|
| 589 |
"step": 465
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 0.02,
|
| 593 |
+
"learning_rate": 2.1936217414063584e-05,
|
| 594 |
+
"loss": 0.7453,
|
| 595 |
"step": 470
|
| 596 |
},
|
| 597 |
{
|
| 598 |
+
"epoch": 0.02,
|
| 599 |
+
"learning_rate": 2.154984841343862e-05,
|
| 600 |
+
"loss": 0.7135,
|
| 601 |
"step": 475
|
| 602 |
},
|
| 603 |
{
|
| 604 |
+
"epoch": 0.02,
|
| 605 |
+
"learning_rate": 2.1162896578209517e-05,
|
| 606 |
+
"loss": 0.712,
|
| 607 |
"step": 480
|
| 608 |
},
|
| 609 |
{
|
| 610 |
+
"epoch": 0.02,
|
| 611 |
+
"learning_rate": 2.077550742513634e-05,
|
| 612 |
+
"loss": 0.7185,
|
| 613 |
"step": 485
|
| 614 |
},
|
| 615 |
{
|
| 616 |
+
"epoch": 0.02,
|
| 617 |
+
"learning_rate": 2.038782663543649e-05,
|
| 618 |
+
"loss": 0.7366,
|
| 619 |
"step": 490
|
| 620 |
},
|
| 621 |
{
|
| 622 |
+
"epoch": 0.02,
|
| 623 |
+
"learning_rate": 2e-05,
|
| 624 |
+
"loss": 0.7302,
|
| 625 |
"step": 495
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 0.02,
|
| 629 |
+
"learning_rate": 1.9612173364563517e-05,
|
| 630 |
+
"loss": 0.7393,
|
| 631 |
"step": 500
|
| 632 |
},
|
| 633 |
{
|
| 634 |
+
"epoch": 0.02,
|
| 635 |
+
"learning_rate": 1.9224492574863663e-05,
|
| 636 |
+
"loss": 0.7296,
|
| 637 |
"step": 505
|
| 638 |
},
|
| 639 |
{
|
| 640 |
+
"epoch": 0.02,
|
| 641 |
+
"learning_rate": 1.8837103421790486e-05,
|
| 642 |
+
"loss": 0.7109,
|
| 643 |
"step": 510
|
| 644 |
},
|
| 645 |
{
|
| 646 |
+
"epoch": 0.02,
|
| 647 |
+
"learning_rate": 1.8450151586561386e-05,
|
| 648 |
+
"loss": 0.7092,
|
| 649 |
"step": 515
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"epoch": 0.02,
|
| 653 |
+
"learning_rate": 1.806378258593642e-05,
|
| 654 |
+
"loss": 0.7381,
|
| 655 |
"step": 520
|
| 656 |
},
|
| 657 |
{
|
| 658 |
+
"epoch": 0.02,
|
| 659 |
+
"learning_rate": 1.7678141717495394e-05,
|
| 660 |
+
"loss": 0.733,
|
| 661 |
"step": 525
|
| 662 |
},
|
| 663 |
{
|
| 664 |
+
"epoch": 0.02,
|
| 665 |
+
"learning_rate": 1.7293374004997384e-05,
|
| 666 |
+
"loss": 0.7068,
|
| 667 |
"step": 530
|
| 668 |
},
|
| 669 |
{
|
| 670 |
+
"epoch": 0.02,
|
| 671 |
+
"learning_rate": 1.6909624143843193e-05,
|
| 672 |
+
"loss": 0.7062,
|
| 673 |
"step": 535
|
| 674 |
},
|
| 675 |
{
|
| 676 |
+
"epoch": 0.02,
|
| 677 |
+
"learning_rate": 1.6527036446661396e-05,
|
| 678 |
+
"loss": 0.7342,
|
| 679 |
+
"step": 540
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.02,
|
| 683 |
+
"eval_loss": 0.7100361585617065,
|
| 684 |
+
"eval_runtime": 117.785,
|
| 685 |
+
"eval_samples_per_second": 16.98,
|
| 686 |
+
"eval_steps_per_second": 4.245,
|
| 687 |
"step": 540
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 0.02,
|
| 691 |
+
"learning_rate": 1.6145754789038205e-05,
|
| 692 |
+
"loss": 0.7193,
|
| 693 |
"step": 545
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 0.02,
|
| 697 |
+
"learning_rate": 1.5765922555411793e-05,
|
| 698 |
+
"loss": 0.7087,
|
| 699 |
"step": 550
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"epoch": 0.02,
|
| 703 |
+
"learning_rate": 1.53876825851512e-05,
|
| 704 |
+
"loss": 0.7228,
|
| 705 |
"step": 555
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"epoch": 0.02,
|
| 709 |
+
"learning_rate": 1.5011177118840376e-05,
|
| 710 |
+
"loss": 0.7254,
|
| 711 |
"step": 560
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 0.02,
|
| 715 |
+
"learning_rate": 1.4636547744787251e-05,
|
| 716 |
+
"loss": 0.732,
|
| 717 |
"step": 565
|
| 718 |
},
|
| 719 |
{
|
| 720 |
+
"epoch": 0.02,
|
| 721 |
+
"learning_rate": 1.4263935345778202e-05,
|
| 722 |
+
"loss": 0.7186,
|
| 723 |
"step": 570
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 0.02,
|
| 727 |
+
"learning_rate": 1.389348004609774e-05,
|
| 728 |
+
"loss": 0.7091,
|
| 729 |
"step": 575
|
| 730 |
},
|
| 731 |
{
|
| 732 |
+
"epoch": 0.02,
|
| 733 |
+
"learning_rate": 1.3525321158833582e-05,
|
| 734 |
+
"loss": 0.7278,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 735 |
"step": 580
|
| 736 |
},
|
| 737 |
{
|
| 738 |
+
"epoch": 0.02,
|
| 739 |
+
"learning_rate": 1.3159597133486628e-05,
|
| 740 |
+
"loss": 0.7088,
|
| 741 |
"step": 585
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 0.02,
|
| 745 |
+
"learning_rate": 1.2796445503905797e-05,
|
| 746 |
+
"loss": 0.7188,
|
| 747 |
"step": 590
|
| 748 |
},
|
| 749 |
{
|
| 750 |
+
"epoch": 0.02,
|
| 751 |
+
"learning_rate": 1.2436002836567154e-05,
|
| 752 |
+
"loss": 0.7311,
|
| 753 |
"step": 595
|
| 754 |
},
|
| 755 |
{
|
| 756 |
+
"epoch": 0.02,
|
| 757 |
+
"learning_rate": 1.2078404679216864e-05,
|
| 758 |
+
"loss": 0.727,
|
| 759 |
"step": 600
|
| 760 |
},
|
| 761 |
{
|
| 762 |
+
"epoch": 0.02,
|
| 763 |
+
"learning_rate": 1.1723785509897219e-05,
|
| 764 |
+
"loss": 0.7089,
|
| 765 |
"step": 605
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 0.02,
|
| 769 |
+
"learning_rate": 1.1372278686374935e-05,
|
| 770 |
+
"loss": 0.7108,
|
| 771 |
"step": 610
|
| 772 |
},
|
| 773 |
{
|
| 774 |
+
"epoch": 0.02,
|
| 775 |
+
"learning_rate": 1.1024016395990758e-05,
|
| 776 |
+
"loss": 0.7189,
|
| 777 |
"step": 615
|
| 778 |
},
|
| 779 |
{
|
| 780 |
+
"epoch": 0.02,
|
| 781 |
+
"learning_rate": 1.067912960594923e-05,
|
| 782 |
+
"loss": 0.717,
|
| 783 |
"step": 620
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 0.02,
|
| 787 |
+
"learning_rate": 1.033774801406723e-05,
|
| 788 |
+
"loss": 0.713,
|
| 789 |
"step": 625
|
| 790 |
},
|
| 791 |
{
|
| 792 |
+
"epoch": 0.02,
|
| 793 |
+
"learning_rate": 1.0000000000000006e-05,
|
| 794 |
+
"loss": 0.7217,
|
| 795 |
"step": 630
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 0.03,
|
| 799 |
+
"learning_rate": 9.666012576962743e-06,
|
| 800 |
+
"loss": 0.7099,
|
| 801 |
"step": 635
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 0.03,
|
| 805 |
+
"learning_rate": 9.33591134396618e-06,
|
| 806 |
+
"loss": 0.6947,
|
| 807 |
"step": 640
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 0.03,
|
| 811 |
+
"learning_rate": 9.009820438583881e-06,
|
| 812 |
+
"loss": 0.7051,
|
| 813 |
"step": 645
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 0.03,
|
| 817 |
+
"learning_rate": 8.687862490269232e-06,
|
| 818 |
+
"loss": 0.7244,
|
| 819 |
"step": 650
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 0.03,
|
| 823 |
+
"learning_rate": 8.370158574239466e-06,
|
| 824 |
+
"loss": 0.7233,
|
| 825 |
"step": 655
|
| 826 |
},
|
| 827 |
{
|
| 828 |
+
"epoch": 0.03,
|
| 829 |
+
"learning_rate": 8.056828165944282e-06,
|
| 830 |
+
"loss": 0.712,
|
| 831 |
"step": 660
|
| 832 |
},
|
| 833 |
{
|
| 834 |
+
"epoch": 0.03,
|
| 835 |
+
"learning_rate": 7.747989096135943e-06,
|
| 836 |
+
"loss": 0.7236,
|
| 837 |
"step": 665
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 0.03,
|
| 841 |
+
"learning_rate": 7.443757506558033e-06,
|
| 842 |
+
"loss": 0.7134,
|
| 843 |
"step": 670
|
| 844 |
},
|
| 845 |
{
|
| 846 |
+
"epoch": 0.03,
|
| 847 |
+
"learning_rate": 7.1442478062692135e-06,
|
| 848 |
+
"loss": 0.714,
|
| 849 |
"step": 675
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 0.03,
|
| 853 |
+
"learning_rate": 6.84957262861873e-06,
|
| 854 |
+
"loss": 0.7058,
|
| 855 |
"step": 680
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 0.03,
|
| 859 |
+
"learning_rate": 6.559842788889552e-06,
|
| 860 |
+
"loss": 0.7265,
|
| 861 |
"step": 685
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 0.03,
|
| 865 |
+
"learning_rate": 6.275167242625331e-06,
|
| 866 |
+
"loss": 0.7119,
|
| 867 |
"step": 690
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 0.03,
|
| 871 |
+
"learning_rate": 5.9956530446566305e-06,
|
| 872 |
+
"loss": 0.7263,
|
| 873 |
"step": 695
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 0.03,
|
| 877 |
+
"learning_rate": 5.721405308842023e-06,
|
| 878 |
+
"loss": 0.7274,
|
| 879 |
"step": 700
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 0.03,
|
| 883 |
+
"learning_rate": 5.452527168539026e-06,
|
| 884 |
+
"loss": 0.7166,
|
| 885 |
"step": 705
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 0.03,
|
| 889 |
+
"learning_rate": 5.189119737819912e-06,
|
| 890 |
+
"loss": 0.713,
|
| 891 |
"step": 710
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 0.03,
|
| 895 |
+
"learning_rate": 4.9312820734467855e-06,
|
| 896 |
+
"loss": 0.7253,
|
| 897 |
"step": 715
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 0.03,
|
| 901 |
+
"learning_rate": 4.679111137620442e-06,
|
| 902 |
+
"loss": 0.7216,
|
| 903 |
"step": 720
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 0.03,
|
| 907 |
+
"eval_loss": 0.708259105682373,
|
| 908 |
+
"eval_runtime": 117.7068,
|
| 909 |
+
"eval_samples_per_second": 16.991,
|
| 910 |
+
"eval_steps_per_second": 4.248,
|
| 911 |
+
"step": 720
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.03,
|
| 915 |
+
"learning_rate": 4.4327017615168e-06,
|
| 916 |
+
"loss": 0.7165,
|
| 917 |
"step": 725
|
| 918 |
},
|
| 919 |
{
|
| 920 |
+
"epoch": 0.03,
|
| 921 |
+
"learning_rate": 4.1921466096248164e-06,
|
| 922 |
+
"loss": 0.7303,
|
| 923 |
"step": 730
|
| 924 |
},
|
| 925 |
{
|
| 926 |
+
"epoch": 0.03,
|
| 927 |
+
"learning_rate": 3.957536144899123e-06,
|
| 928 |
+
"loss": 0.7198,
|
| 929 |
"step": 735
|
| 930 |
},
|
| 931 |
{
|
| 932 |
+
"epoch": 0.03,
|
| 933 |
+
"learning_rate": 3.7289585947406504e-06,
|
| 934 |
+
"loss": 0.7186,
|
| 935 |
"step": 740
|
| 936 |
},
|
| 937 |
{
|
| 938 |
+
"epoch": 0.03,
|
| 939 |
+
"learning_rate": 3.5064999178178648e-06,
|
| 940 |
+
"loss": 0.7438,
|
| 941 |
"step": 745
|
| 942 |
},
|
| 943 |
{
|
| 944 |
+
"epoch": 0.03,
|
| 945 |
+
"learning_rate": 3.290243771741275e-06,
|
| 946 |
+
"loss": 0.7191,
|
| 947 |
"step": 750
|
| 948 |
},
|
| 949 |
{
|
| 950 |
+
"epoch": 0.03,
|
| 951 |
+
"learning_rate": 3.0802714816031787e-06,
|
| 952 |
+
"loss": 0.7132,
|
| 953 |
"step": 755
|
| 954 |
},
|
| 955 |
{
|
| 956 |
+
"epoch": 0.03,
|
| 957 |
+
"learning_rate": 2.876662009394673e-06,
|
| 958 |
+
"loss": 0.7278,
|
| 959 |
"step": 760
|
| 960 |
},
|
| 961 |
{
|
| 962 |
+
"epoch": 0.03,
|
| 963 |
+
"learning_rate": 2.679491924311226e-06,
|
| 964 |
+
"loss": 0.7085,
|
| 965 |
"step": 765
|
| 966 |
},
|
| 967 |
{
|
| 968 |
+
"epoch": 0.03,
|
| 969 |
+
"learning_rate": 2.488835373958185e-06,
|
| 970 |
+
"loss": 0.7115,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 971 |
"step": 770
|
| 972 |
},
|
| 973 |
{
|
| 974 |
+
"epoch": 0.03,
|
| 975 |
+
"learning_rate": 2.304764056466844e-06,
|
| 976 |
+
"loss": 0.7118,
|
| 977 |
"step": 775
|
| 978 |
},
|
| 979 |
{
|
| 980 |
+
"epoch": 0.03,
|
| 981 |
+
"learning_rate": 2.127347193531757e-06,
|
| 982 |
+
"loss": 0.7121,
|
| 983 |
"step": 780
|
| 984 |
},
|
| 985 |
{
|
| 986 |
+
"epoch": 0.03,
|
| 987 |
+
"learning_rate": 1.9566515043792455e-06,
|
| 988 |
+
"loss": 0.7174,
|
| 989 |
"step": 785
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 0.03,
|
| 993 |
+
"learning_rate": 1.792741180677069e-06,
|
| 994 |
+
"loss": 0.6913,
|
| 995 |
"step": 790
|
| 996 |
},
|
| 997 |
{
|
| 998 |
+
"epoch": 0.03,
|
| 999 |
+
"learning_rate": 1.6356778623945223e-06,
|
| 1000 |
+
"loss": 0.7038,
|
| 1001 |
"step": 795
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 0.03,
|
| 1005 |
+
"learning_rate": 1.4855206146221934e-06,
|
| 1006 |
+
"loss": 0.7156,
|
| 1007 |
"step": 800
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 0.03,
|
| 1011 |
+
"learning_rate": 1.3423259053599891e-06,
|
| 1012 |
+
"loss": 0.7113,
|
| 1013 |
"step": 805
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 0.03,
|
| 1017 |
+
"learning_rate": 1.2061475842818337e-06,
|
| 1018 |
+
"loss": 0.727,
|
| 1019 |
"step": 810
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 0.03,
|
| 1023 |
+
"learning_rate": 1.0770368624849947e-06,
|
| 1024 |
+
"loss": 0.7186,
|
| 1025 |
"step": 815
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 0.03,
|
| 1029 |
+
"learning_rate": 9.550422932316938e-07,
|
| 1030 |
+
"loss": 0.7088,
|
| 1031 |
"step": 820
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
+
"epoch": 0.03,
|
| 1035 |
+
"learning_rate": 8.402097536902221e-07,
|
| 1036 |
+
"loss": 0.7125,
|
| 1037 |
"step": 825
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 0.03,
|
| 1041 |
+
"learning_rate": 7.325824276823934e-07,
|
| 1042 |
+
"loss": 0.7076,
|
| 1043 |
"step": 830
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 0.03,
|
| 1047 |
+
"learning_rate": 6.322007894438842e-07,
|
| 1048 |
+
"loss": 0.7099,
|
| 1049 |
"step": 835
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
+
"epoch": 0.03,
|
| 1053 |
+
"learning_rate": 5.391025884035239e-07,
|
| 1054 |
+
"loss": 0.7238,
|
| 1055 |
"step": 840
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 0.03,
|
| 1059 |
+
"learning_rate": 4.533228349872887e-07,
|
| 1060 |
+
"loss": 0.7241,
|
| 1061 |
"step": 845
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
+
"epoch": 0.03,
|
| 1065 |
+
"learning_rate": 3.748937874523062e-07,
|
| 1066 |
+
"loss": 0.7248,
|
| 1067 |
"step": 850
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"epoch": 0.03,
|
| 1071 |
+
"learning_rate": 3.038449397558396e-07,
|
| 1072 |
+
"loss": 0.7083,
|
| 1073 |
"step": 855
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
+
"epoch": 0.03,
|
| 1077 |
+
"learning_rate": 2.402030104638198e-07,
|
| 1078 |
+
"loss": 0.7167,
|
| 1079 |
"step": 860
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
+
"epoch": 0.03,
|
| 1083 |
+
"learning_rate": 1.839919327030937e-07,
|
| 1084 |
+
"loss": 0.7277,
|
| 1085 |
"step": 865
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
+
"epoch": 0.03,
|
| 1089 |
+
"learning_rate": 1.3523284516113955e-07,
|
| 1090 |
+
"loss": 0.7075,
|
| 1091 |
"step": 870
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
+
"epoch": 0.03,
|
| 1095 |
+
"learning_rate": 9.394408413668343e-08,
|
| 1096 |
+
"loss": 0.7134,
|
| 1097 |
"step": 875
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
+
"epoch": 0.03,
|
| 1101 |
+
"learning_rate": 6.014117664415953e-08,
|
| 1102 |
+
"loss": 0.7147,
|
| 1103 |
"step": 880
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
+
"epoch": 0.03,
|
| 1107 |
+
"learning_rate": 3.383683457463649e-08,
|
| 1108 |
+
"loss": 0.7287,
|
| 1109 |
"step": 885
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
+
"epoch": 0.04,
|
| 1113 |
+
"learning_rate": 1.5040949915399173e-08,
|
| 1114 |
+
"loss": 0.7152,
|
| 1115 |
"step": 890
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
+
"epoch": 0.04,
|
| 1119 |
+
"learning_rate": 3.760591029973171e-09,
|
| 1120 |
+
"loss": 0.7195,
|
| 1121 |
"step": 895
|
| 1122 |
},
|
| 1123 |
{
|
| 1124 |
+
"epoch": 0.04,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1125 |
"learning_rate": 0.0,
|
| 1126 |
+
"loss": 0.7171,
|
| 1127 |
+
"step": 900
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
+
"epoch": 0.04,
|
| 1131 |
+
"eval_loss": 0.7084137797355652,
|
| 1132 |
+
"eval_runtime": 117.7342,
|
| 1133 |
+
"eval_samples_per_second": 16.987,
|
| 1134 |
+
"eval_steps_per_second": 4.247,
|
| 1135 |
+
"step": 900
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 0.04,
|
| 1139 |
+
"step": 900,
|
| 1140 |
+
"total_flos": 1.1929120479106826e+18,
|
| 1141 |
+
"train_loss": 0.7602509791321225,
|
| 1142 |
+
"train_runtime": 22175.0023,
|
| 1143 |
+
"train_samples_per_second": 0.649,
|
| 1144 |
"train_steps_per_second": 0.041
|
| 1145 |
}
|
| 1146 |
],
|
| 1147 |
"logging_steps": 5,
|
| 1148 |
+
"max_steps": 900,
|
| 1149 |
+
"num_train_epochs": 1,
|
| 1150 |
+
"save_steps": 180,
|
| 1151 |
+
"total_flos": 1.1929120479106826e+18,
|
| 1152 |
"trial_name": null,
|
| 1153 |
"trial_params": null
|
| 1154 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f65537292be9c1a03c759b840c2f8b9421e85df46af77ce90fdb8f69e1b17890
|
| 3 |
size 4728
|