Model save
Browse files- README.md +6 -10
- adapter_model.safetensors +1 -1
- all_results.json +7 -12
- runs/Sep13_10-58-16_nova.cs.ucla.edu/events.out.tfevents.1726250443.nova.cs.ucla.edu.3841631.0 +2 -2
- train_results.json +7 -7
- trainer_state.json +750 -1024
README.md
CHANGED
|
@@ -1,11 +1,8 @@
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Meta-Llama-3-8B
|
| 3 |
-
datasets:
|
| 4 |
-
- yihanwang617/WizardLM_70k_processed_indicator_4k
|
| 5 |
library_name: peft
|
| 6 |
license: llama3
|
| 7 |
tags:
|
| 8 |
-
- alignment-handbook
|
| 9 |
- trl
|
| 10 |
- sft
|
| 11 |
- generated_from_trainer
|
|
@@ -19,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# llama-3-qlora-wizard-processed-indicator-0.6
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -58,11 +55,10 @@ The following hyperparameters were used during training:
|
|
| 58 |
|
| 59 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 60 |
|:-------------:|:------:|:----:|:---------------:|
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.6769 | 0.9208 | 1000 | 0.6736 |
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Meta-Llama-3-8B
|
|
|
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
license: llama3
|
| 5 |
tags:
|
|
|
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
|
|
|
| 16 |
|
| 17 |
# llama-3-qlora-wizard-processed-indicator-0.6
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6755
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.7113 | 0.2225 | 200 | 0.7031 |
|
| 59 |
+
| 0.7181 | 0.4450 | 400 | 0.6872 |
|
| 60 |
+
| 0.7171 | 0.6675 | 600 | 0.6786 |
|
| 61 |
+
| 0.7031 | 0.8900 | 800 | 0.6755 |
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2185327392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34a0efa90ffde337347f3f32136cedf3032bbd193eae327b6b54888c0ddd64c9
|
| 3 |
size 2185327392
|
all_results.json
CHANGED
|
@@ -1,14 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"train_loss": 0.7253576234998405,
|
| 10 |
-
"train_runtime": 22925.9932,
|
| 11 |
-
"train_samples": 69499,
|
| 12 |
-
"train_samples_per_second": 3.031,
|
| 13 |
-
"train_steps_per_second": 0.047
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.9990265609790016,
|
| 3 |
+
"total_flos": 3899966689378304.0,
|
| 4 |
+
"train_loss": 0.7223505903458542,
|
| 5 |
+
"train_runtime": 18859.9671,
|
| 6 |
+
"train_samples": 57523,
|
| 7 |
+
"train_samples_per_second": 3.05,
|
| 8 |
+
"train_steps_per_second": 0.048
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
runs/Sep13_10-58-16_nova.cs.ucla.edu/events.out.tfevents.1726250443.nova.cs.ucla.edu.3841631.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a83773b0cb18d97a6926fd2857398ff7b2a33d0e47fecbc05b79017399d75046
|
| 3 |
+
size 44262
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples":
|
| 7 |
-
"train_samples_per_second": 3.
|
| 8 |
-
"train_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.9990265609790016,
|
| 3 |
+
"total_flos": 3899966689378304.0,
|
| 4 |
+
"train_loss": 0.7223505903458542,
|
| 5 |
+
"train_runtime": 18859.9671,
|
| 6 |
+
"train_samples": 57523,
|
| 7 |
+
"train_samples_per_second": 3.05,
|
| 8 |
+
"train_steps_per_second": 0.048
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1595 +1,1321 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 200,
|
| 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.
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 0.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 0.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 0.
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate": 0.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch": 0.
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate": 0.
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch": 0.
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 0.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 0.
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate": 0.
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch": 0.
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate": 0.
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch": 0.
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 0.
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate": 0.
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch": 0.
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate": 0.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate": 0.
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate": 0.
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch": 0.
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate": 0.
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch": 0.
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate": 0.
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 190
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch": 0.
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate": 0.
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 195
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 0.
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate": 0.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 200
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 0.
|
| 300 |
-
"eval_loss": 0.
|
| 301 |
-
"eval_runtime":
|
| 302 |
-
"eval_samples_per_second": 10.
|
| 303 |
-
"eval_steps_per_second": 0.
|
| 304 |
"step": 200
|
| 305 |
},
|
| 306 |
{
|
| 307 |
-
"epoch": 0.
|
| 308 |
-
"grad_norm": 0.
|
| 309 |
-
"learning_rate": 0.
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 205
|
| 312 |
},
|
| 313 |
{
|
| 314 |
-
"epoch": 0.
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
-
"learning_rate": 0.
|
| 317 |
-
"loss": 0.
|
| 318 |
"step": 210
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch": 0.
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
-
"learning_rate": 0.
|
| 324 |
-
"loss": 0.
|
| 325 |
"step": 215
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch": 0.
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 220
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch": 0.
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 225
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch": 0.
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
-
"learning_rate": 0.
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 230
|
| 347 |
},
|
| 348 |
{
|
| 349 |
-
"epoch": 0.
|
| 350 |
-
"grad_norm": 0.
|
| 351 |
-
"learning_rate": 0.
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 235
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch": 0.
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 240
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch": 0.
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
-
"learning_rate": 0.
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 245
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch": 0.
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
-
"learning_rate": 0.
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 250
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch": 0.
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
-
"learning_rate": 0.
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 255
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 0.
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
-
"learning_rate": 0.
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 260
|
| 389 |
},
|
| 390 |
{
|
| 391 |
-
"epoch": 0.
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
-
"learning_rate": 0.
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 265
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch": 0.
|
| 399 |
-
"grad_norm": 0.
|
| 400 |
-
"learning_rate": 0.
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 270
|
| 403 |
},
|
| 404 |
{
|
| 405 |
-
"epoch": 0.
|
| 406 |
-
"grad_norm": 0.
|
| 407 |
-
"learning_rate": 0.
|
| 408 |
-
"loss": 0.
|
| 409 |
"step": 275
|
| 410 |
},
|
| 411 |
{
|
| 412 |
-
"epoch": 0.
|
| 413 |
-
"grad_norm": 0.
|
| 414 |
-
"learning_rate": 0.
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 280
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"epoch": 0.
|
| 420 |
-
"grad_norm": 0.
|
| 421 |
-
"learning_rate": 0.
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 285
|
| 424 |
},
|
| 425 |
{
|
| 426 |
-
"epoch": 0.
|
| 427 |
-
"grad_norm": 0.
|
| 428 |
-
"learning_rate": 0.
|
| 429 |
-
"loss": 0.
|
| 430 |
"step": 290
|
| 431 |
},
|
| 432 |
{
|
| 433 |
-
"epoch": 0.
|
| 434 |
-
"grad_norm": 0.
|
| 435 |
-
"learning_rate": 0.
|
| 436 |
-
"loss": 0.
|
| 437 |
"step": 295
|
| 438 |
},
|
| 439 |
{
|
| 440 |
-
"epoch": 0.
|
| 441 |
-
"grad_norm": 0.
|
| 442 |
-
"learning_rate": 0.
|
| 443 |
-
"loss": 0.
|
| 444 |
"step": 300
|
| 445 |
},
|
| 446 |
{
|
| 447 |
-
"epoch": 0.
|
| 448 |
-
"grad_norm": 0.
|
| 449 |
-
"learning_rate": 0.
|
| 450 |
-
"loss": 0.
|
| 451 |
"step": 305
|
| 452 |
},
|
| 453 |
{
|
| 454 |
-
"epoch": 0.
|
| 455 |
-
"grad_norm": 0.
|
| 456 |
-
"learning_rate": 0.
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 310
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch": 0.
|
| 462 |
-
"grad_norm": 0.
|
| 463 |
-
"learning_rate": 0.
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 315
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch": 0.
|
| 469 |
-
"grad_norm": 0.
|
| 470 |
-
"learning_rate": 0.
|
| 471 |
-
"loss": 0.
|
| 472 |
"step": 320
|
| 473 |
},
|
| 474 |
{
|
| 475 |
-
"epoch": 0.
|
| 476 |
-
"grad_norm": 0.
|
| 477 |
-
"learning_rate": 0.
|
| 478 |
-
"loss": 0.
|
| 479 |
"step": 325
|
| 480 |
},
|
| 481 |
{
|
| 482 |
-
"epoch": 0.
|
| 483 |
-
"grad_norm": 0.
|
| 484 |
-
"learning_rate": 0.
|
| 485 |
-
"loss": 0.
|
| 486 |
"step": 330
|
| 487 |
},
|
| 488 |
{
|
| 489 |
-
"epoch": 0.
|
| 490 |
-
"grad_norm": 0.
|
| 491 |
-
"learning_rate": 0.
|
| 492 |
-
"loss": 0.
|
| 493 |
"step": 335
|
| 494 |
},
|
| 495 |
{
|
| 496 |
-
"epoch": 0.
|
| 497 |
-
"grad_norm": 0.
|
| 498 |
-
"learning_rate": 0.
|
| 499 |
-
"loss": 0.
|
| 500 |
"step": 340
|
| 501 |
},
|
| 502 |
{
|
| 503 |
-
"epoch": 0.
|
| 504 |
-
"grad_norm": 0.
|
| 505 |
-
"learning_rate": 0.
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 345
|
| 508 |
},
|
| 509 |
{
|
| 510 |
-
"epoch": 0.
|
| 511 |
-
"grad_norm": 0.
|
| 512 |
-
"learning_rate": 0.
|
| 513 |
-
"loss": 0.
|
| 514 |
"step": 350
|
| 515 |
},
|
| 516 |
{
|
| 517 |
-
"epoch": 0.
|
| 518 |
-
"grad_norm": 0.
|
| 519 |
-
"learning_rate": 0.
|
| 520 |
-
"loss": 0.
|
| 521 |
"step": 355
|
| 522 |
},
|
| 523 |
{
|
| 524 |
-
"epoch": 0.
|
| 525 |
-
"grad_norm": 0.
|
| 526 |
-
"learning_rate": 0.
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 360
|
| 529 |
},
|
| 530 |
{
|
| 531 |
-
"epoch": 0.
|
| 532 |
-
"grad_norm": 0.
|
| 533 |
-
"learning_rate": 0.
|
| 534 |
-
"loss": 0.
|
| 535 |
"step": 365
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch": 0.
|
| 539 |
-
"grad_norm": 0.
|
| 540 |
-
"learning_rate": 0.
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 370
|
| 543 |
},
|
| 544 |
{
|
| 545 |
-
"epoch": 0.
|
| 546 |
-
"grad_norm": 0.
|
| 547 |
-
"learning_rate": 0.
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 375
|
| 550 |
},
|
| 551 |
{
|
| 552 |
-
"epoch": 0.
|
| 553 |
-
"grad_norm": 0.
|
| 554 |
-
"learning_rate": 0.
|
| 555 |
-
"loss": 0.
|
| 556 |
"step": 380
|
| 557 |
},
|
| 558 |
{
|
| 559 |
-
"epoch": 0.
|
| 560 |
-
"grad_norm": 0.
|
| 561 |
-
"learning_rate": 0.
|
| 562 |
-
"loss": 0.
|
| 563 |
"step": 385
|
| 564 |
},
|
| 565 |
{
|
| 566 |
-
"epoch": 0.
|
| 567 |
-
"grad_norm": 0.
|
| 568 |
-
"learning_rate": 0.
|
| 569 |
-
"loss": 0.
|
| 570 |
"step": 390
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"epoch": 0.
|
| 574 |
-
"grad_norm": 0.
|
| 575 |
-
"learning_rate": 0.
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 395
|
| 578 |
},
|
| 579 |
{
|
| 580 |
-
"epoch": 0.
|
| 581 |
-
"grad_norm": 0.
|
| 582 |
-
"learning_rate": 0.
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 400
|
| 585 |
},
|
| 586 |
{
|
| 587 |
-
"epoch": 0.
|
| 588 |
-
"eval_loss": 0.
|
| 589 |
-
"eval_runtime":
|
| 590 |
-
"eval_samples_per_second": 10.
|
| 591 |
-
"eval_steps_per_second": 0.
|
| 592 |
"step": 400
|
| 593 |
},
|
| 594 |
{
|
| 595 |
-
"epoch": 0.
|
| 596 |
-
"grad_norm": 0.
|
| 597 |
-
"learning_rate": 0.
|
| 598 |
-
"loss": 0.
|
| 599 |
"step": 405
|
| 600 |
},
|
| 601 |
{
|
| 602 |
-
"epoch": 0.
|
| 603 |
-
"grad_norm": 0.
|
| 604 |
-
"learning_rate": 0.
|
| 605 |
-
"loss": 0.
|
| 606 |
"step": 410
|
| 607 |
},
|
| 608 |
{
|
| 609 |
-
"epoch": 0.
|
| 610 |
-
"grad_norm": 0.
|
| 611 |
-
"learning_rate": 0.
|
| 612 |
-
"loss": 0.
|
| 613 |
"step": 415
|
| 614 |
},
|
| 615 |
{
|
| 616 |
-
"epoch": 0.
|
| 617 |
-
"grad_norm": 0.
|
| 618 |
-
"learning_rate": 0.
|
| 619 |
-
"loss": 0.
|
| 620 |
"step": 420
|
| 621 |
},
|
| 622 |
{
|
| 623 |
-
"epoch": 0.
|
| 624 |
-
"grad_norm": 0.
|
| 625 |
-
"learning_rate": 0.
|
| 626 |
-
"loss": 0.
|
| 627 |
"step": 425
|
| 628 |
},
|
| 629 |
{
|
| 630 |
-
"epoch": 0.
|
| 631 |
-
"grad_norm": 0.
|
| 632 |
-
"learning_rate": 0.
|
| 633 |
-
"loss": 0.
|
| 634 |
"step": 430
|
| 635 |
},
|
| 636 |
{
|
| 637 |
-
"epoch": 0.
|
| 638 |
-
"grad_norm": 0.
|
| 639 |
-
"learning_rate": 0.
|
| 640 |
-
"loss": 0.
|
| 641 |
"step": 435
|
| 642 |
},
|
| 643 |
{
|
| 644 |
-
"epoch": 0.
|
| 645 |
-
"grad_norm": 0.
|
| 646 |
-
"learning_rate": 0.
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 440
|
| 649 |
},
|
| 650 |
{
|
| 651 |
-
"epoch": 0.
|
| 652 |
-
"grad_norm": 0.
|
| 653 |
-
"learning_rate": 0.
|
| 654 |
-
"loss": 0.
|
| 655 |
"step": 445
|
| 656 |
},
|
| 657 |
{
|
| 658 |
-
"epoch": 0.
|
| 659 |
-
"grad_norm": 0.
|
| 660 |
-
"learning_rate": 0.
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 450
|
| 663 |
},
|
| 664 |
{
|
| 665 |
-
"epoch": 0.
|
| 666 |
-
"grad_norm": 0.
|
| 667 |
-
"learning_rate": 0.
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 455
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch": 0.
|
| 673 |
-
"grad_norm": 0.
|
| 674 |
-
"learning_rate": 0.
|
| 675 |
-
"loss": 0.
|
| 676 |
"step": 460
|
| 677 |
},
|
| 678 |
{
|
| 679 |
-
"epoch": 0.
|
| 680 |
-
"grad_norm": 0.
|
| 681 |
-
"learning_rate": 0.
|
| 682 |
-
"loss": 0.
|
| 683 |
"step": 465
|
| 684 |
},
|
| 685 |
{
|
| 686 |
-
"epoch": 0.
|
| 687 |
-
"grad_norm": 0.
|
| 688 |
-
"learning_rate": 0.
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 470
|
| 691 |
},
|
| 692 |
{
|
| 693 |
-
"epoch": 0.
|
| 694 |
-
"grad_norm": 0.
|
| 695 |
-
"learning_rate": 0.
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 475
|
| 698 |
},
|
| 699 |
{
|
| 700 |
-
"epoch": 0.
|
| 701 |
-
"grad_norm": 0.
|
| 702 |
-
"learning_rate": 0.
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 480
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch": 0.
|
| 708 |
-
"grad_norm": 0.
|
| 709 |
-
"learning_rate": 0.
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 485
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch": 0.
|
| 715 |
-
"grad_norm": 0.
|
| 716 |
-
"learning_rate": 0.
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 490
|
| 719 |
},
|
| 720 |
{
|
| 721 |
-
"epoch": 0.
|
| 722 |
-
"grad_norm": 0.
|
| 723 |
-
"learning_rate":
|
| 724 |
-
"loss": 0.
|
| 725 |
"step": 495
|
| 726 |
},
|
| 727 |
{
|
| 728 |
-
"epoch": 0.
|
| 729 |
-
"grad_norm": 0.
|
| 730 |
-
"learning_rate":
|
| 731 |
-
"loss": 0.
|
| 732 |
"step": 500
|
| 733 |
},
|
| 734 |
{
|
| 735 |
-
"epoch": 0.
|
| 736 |
-
"grad_norm": 0.
|
| 737 |
-
"learning_rate":
|
| 738 |
-
"loss": 0.
|
| 739 |
"step": 505
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch": 0.
|
| 743 |
-
"grad_norm": 0.
|
| 744 |
-
"learning_rate":
|
| 745 |
-
"loss": 0.
|
| 746 |
"step": 510
|
| 747 |
},
|
| 748 |
{
|
| 749 |
-
"epoch": 0.
|
| 750 |
-
"grad_norm": 0.
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 515
|
| 754 |
},
|
| 755 |
{
|
| 756 |
-
"epoch": 0.
|
| 757 |
-
"grad_norm": 0.
|
| 758 |
-
"learning_rate":
|
| 759 |
-
"loss": 0.
|
| 760 |
"step": 520
|
| 761 |
},
|
| 762 |
{
|
| 763 |
-
"epoch": 0.
|
| 764 |
-
"grad_norm": 0.
|
| 765 |
-
"learning_rate":
|
| 766 |
-
"loss": 0.
|
| 767 |
"step": 525
|
| 768 |
},
|
| 769 |
{
|
| 770 |
-
"epoch": 0.
|
| 771 |
-
"grad_norm": 0.
|
| 772 |
-
"learning_rate":
|
| 773 |
-
"loss": 0.
|
| 774 |
"step": 530
|
| 775 |
},
|
| 776 |
{
|
| 777 |
-
"epoch": 0.
|
| 778 |
-
"grad_norm": 0.
|
| 779 |
-
"learning_rate":
|
| 780 |
-
"loss": 0.
|
| 781 |
"step": 535
|
| 782 |
},
|
| 783 |
{
|
| 784 |
-
"epoch": 0.
|
| 785 |
-
"grad_norm": 0.
|
| 786 |
-
"learning_rate":
|
| 787 |
-
"loss": 0.
|
| 788 |
"step": 540
|
| 789 |
},
|
| 790 |
{
|
| 791 |
-
"epoch": 0.
|
| 792 |
-
"grad_norm": 0.
|
| 793 |
-
"learning_rate":
|
| 794 |
-
"loss": 0.
|
| 795 |
"step": 545
|
| 796 |
},
|
| 797 |
{
|
| 798 |
-
"epoch": 0.
|
| 799 |
-
"grad_norm": 0.
|
| 800 |
-
"learning_rate":
|
| 801 |
-
"loss": 0.
|
| 802 |
"step": 550
|
| 803 |
},
|
| 804 |
{
|
| 805 |
-
"epoch": 0.
|
| 806 |
-
"grad_norm": 0.
|
| 807 |
-
"learning_rate":
|
| 808 |
-
"loss": 0.
|
| 809 |
"step": 555
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch": 0.
|
| 813 |
-
"grad_norm": 0.
|
| 814 |
-
"learning_rate":
|
| 815 |
-
"loss": 0.
|
| 816 |
"step": 560
|
| 817 |
},
|
| 818 |
{
|
| 819 |
-
"epoch": 0.
|
| 820 |
-
"grad_norm": 0.
|
| 821 |
-
"learning_rate":
|
| 822 |
-
"loss": 0.
|
| 823 |
"step": 565
|
| 824 |
},
|
| 825 |
{
|
| 826 |
-
"epoch": 0.
|
| 827 |
-
"grad_norm": 0.
|
| 828 |
-
"learning_rate":
|
| 829 |
-
"loss": 0.
|
| 830 |
"step": 570
|
| 831 |
},
|
| 832 |
{
|
| 833 |
-
"epoch": 0.
|
| 834 |
-
"grad_norm": 0.
|
| 835 |
-
"learning_rate":
|
| 836 |
-
"loss": 0.
|
| 837 |
"step": 575
|
| 838 |
},
|
| 839 |
{
|
| 840 |
-
"epoch": 0.
|
| 841 |
-
"grad_norm": 0.
|
| 842 |
-
"learning_rate":
|
| 843 |
-
"loss": 0.
|
| 844 |
"step": 580
|
| 845 |
},
|
| 846 |
{
|
| 847 |
-
"epoch": 0.
|
| 848 |
-
"grad_norm": 0.
|
| 849 |
-
"learning_rate":
|
| 850 |
-
"loss": 0.
|
| 851 |
"step": 585
|
| 852 |
},
|
| 853 |
{
|
| 854 |
-
"epoch": 0.
|
| 855 |
-
"grad_norm": 0.
|
| 856 |
-
"learning_rate":
|
| 857 |
-
"loss": 0.
|
| 858 |
"step": 590
|
| 859 |
},
|
| 860 |
{
|
| 861 |
-
"epoch": 0.
|
| 862 |
-
"grad_norm": 0.
|
| 863 |
-
"learning_rate":
|
| 864 |
-
"loss": 0.
|
| 865 |
"step": 595
|
| 866 |
},
|
| 867 |
{
|
| 868 |
-
"epoch": 0.
|
| 869 |
-
"grad_norm": 0.
|
| 870 |
-
"learning_rate":
|
| 871 |
-
"loss": 0.
|
| 872 |
"step": 600
|
| 873 |
},
|
| 874 |
{
|
| 875 |
-
"epoch": 0.
|
| 876 |
-
"eval_loss": 0.
|
| 877 |
-
"eval_runtime":
|
| 878 |
-
"eval_samples_per_second": 10.
|
| 879 |
-
"eval_steps_per_second": 0.
|
| 880 |
"step": 600
|
| 881 |
},
|
| 882 |
{
|
| 883 |
-
"epoch": 0.
|
| 884 |
-
"grad_norm": 0.
|
| 885 |
-
"learning_rate":
|
| 886 |
-
"loss": 0.
|
| 887 |
"step": 605
|
| 888 |
},
|
| 889 |
{
|
| 890 |
-
"epoch": 0.
|
| 891 |
-
"grad_norm": 0.
|
| 892 |
-
"learning_rate":
|
| 893 |
"loss": 0.6991,
|
| 894 |
"step": 610
|
| 895 |
},
|
| 896 |
{
|
| 897 |
-
"epoch": 0.
|
| 898 |
-
"grad_norm": 0.
|
| 899 |
-
"learning_rate":
|
| 900 |
-
"loss": 0.
|
| 901 |
"step": 615
|
| 902 |
},
|
| 903 |
{
|
| 904 |
-
"epoch": 0.
|
| 905 |
-
"grad_norm": 0.
|
| 906 |
-
"learning_rate":
|
| 907 |
-
"loss": 0.
|
| 908 |
"step": 620
|
| 909 |
},
|
| 910 |
{
|
| 911 |
-
"epoch": 0.
|
| 912 |
-
"grad_norm": 0.
|
| 913 |
-
"learning_rate":
|
| 914 |
-
"loss": 0.
|
| 915 |
"step": 625
|
| 916 |
},
|
| 917 |
{
|
| 918 |
-
"epoch": 0.
|
| 919 |
-
"grad_norm": 0.
|
| 920 |
-
"learning_rate":
|
| 921 |
-
"loss": 0.
|
| 922 |
"step": 630
|
| 923 |
},
|
| 924 |
{
|
| 925 |
-
"epoch": 0.
|
| 926 |
-
"grad_norm": 0.
|
| 927 |
-
"learning_rate":
|
| 928 |
-
"loss": 0.
|
| 929 |
"step": 635
|
| 930 |
},
|
| 931 |
{
|
| 932 |
-
"epoch": 0.
|
| 933 |
-
"grad_norm": 0.
|
| 934 |
-
"learning_rate":
|
| 935 |
-
"loss": 0.
|
| 936 |
"step": 640
|
| 937 |
},
|
| 938 |
{
|
| 939 |
-
"epoch": 0.
|
| 940 |
-
"grad_norm": 0.
|
| 941 |
-
"learning_rate":
|
| 942 |
-
"loss": 0.
|
| 943 |
"step": 645
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch": 0.
|
| 947 |
-
"grad_norm": 0.
|
| 948 |
-
"learning_rate":
|
| 949 |
-
"loss": 0.
|
| 950 |
"step": 650
|
| 951 |
},
|
| 952 |
{
|
| 953 |
-
"epoch": 0.
|
| 954 |
-
"grad_norm": 0.
|
| 955 |
-
"learning_rate":
|
| 956 |
-
"loss": 0.
|
| 957 |
"step": 655
|
| 958 |
},
|
| 959 |
{
|
| 960 |
-
"epoch": 0.
|
| 961 |
-
"grad_norm": 0.
|
| 962 |
-
"learning_rate":
|
| 963 |
-
"loss": 0.
|
| 964 |
"step": 660
|
| 965 |
},
|
| 966 |
{
|
| 967 |
-
"epoch": 0.
|
| 968 |
-
"grad_norm": 0.
|
| 969 |
-
"learning_rate":
|
| 970 |
-
"loss": 0.
|
| 971 |
"step": 665
|
| 972 |
},
|
| 973 |
{
|
| 974 |
-
"epoch": 0.
|
| 975 |
-
"grad_norm": 0.
|
| 976 |
-
"learning_rate":
|
| 977 |
-
"loss": 0.
|
| 978 |
"step": 670
|
| 979 |
},
|
| 980 |
{
|
| 981 |
-
"epoch": 0.
|
| 982 |
-
"grad_norm": 0.
|
| 983 |
-
"learning_rate":
|
| 984 |
-
"loss": 0.
|
| 985 |
"step": 675
|
| 986 |
},
|
| 987 |
{
|
| 988 |
-
"epoch": 0.
|
| 989 |
-
"grad_norm": 0.
|
| 990 |
-
"learning_rate":
|
| 991 |
-
"loss": 0.
|
| 992 |
"step": 680
|
| 993 |
},
|
| 994 |
{
|
| 995 |
-
"epoch": 0.
|
| 996 |
-
"grad_norm": 0.
|
| 997 |
-
"learning_rate":
|
| 998 |
-
"loss": 0.
|
| 999 |
"step": 685
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
-
"epoch": 0.
|
| 1003 |
-
"grad_norm": 0.
|
| 1004 |
-
"learning_rate":
|
| 1005 |
-
"loss": 0.
|
| 1006 |
"step": 690
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
-
"epoch": 0.
|
| 1010 |
-
"grad_norm": 0.
|
| 1011 |
-
"learning_rate":
|
| 1012 |
-
"loss": 0.
|
| 1013 |
"step": 695
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch": 0.
|
| 1017 |
-
"grad_norm": 0.
|
| 1018 |
-
"learning_rate":
|
| 1019 |
-
"loss": 0.
|
| 1020 |
"step": 700
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
-
"epoch": 0.
|
| 1024 |
-
"grad_norm": 0.
|
| 1025 |
-
"learning_rate":
|
| 1026 |
-
"loss": 0.
|
| 1027 |
"step": 705
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
-
"epoch": 0.
|
| 1031 |
-
"grad_norm": 0.
|
| 1032 |
-
"learning_rate":
|
| 1033 |
-
"loss": 0.
|
| 1034 |
"step": 710
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
-
"epoch": 0.
|
| 1038 |
-
"grad_norm": 0.
|
| 1039 |
-
"learning_rate":
|
| 1040 |
-
"loss": 0.
|
| 1041 |
"step": 715
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
-
"epoch": 0.
|
| 1045 |
-
"grad_norm": 0.
|
| 1046 |
-
"learning_rate":
|
| 1047 |
-
"loss": 0.
|
| 1048 |
"step": 720
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
-
"epoch": 0.
|
| 1052 |
-
"grad_norm": 0.
|
| 1053 |
-
"learning_rate":
|
| 1054 |
-
"loss": 0.
|
| 1055 |
"step": 725
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
-
"epoch": 0.
|
| 1059 |
-
"grad_norm": 0.
|
| 1060 |
-
"learning_rate":
|
| 1061 |
-
"loss": 0.
|
| 1062 |
"step": 730
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
-
"epoch": 0.
|
| 1066 |
-
"grad_norm": 0.
|
| 1067 |
-
"learning_rate":
|
| 1068 |
-
"loss": 0.
|
| 1069 |
"step": 735
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
-
"epoch": 0.
|
| 1073 |
-
"grad_norm": 0.
|
| 1074 |
-
"learning_rate":
|
| 1075 |
-
"loss": 0.
|
| 1076 |
"step": 740
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
-
"epoch": 0.
|
| 1080 |
-
"grad_norm": 0.
|
| 1081 |
-
"learning_rate":
|
| 1082 |
-
"loss": 0.
|
| 1083 |
"step": 745
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch": 0.
|
| 1087 |
-
"grad_norm": 0.
|
| 1088 |
-
"learning_rate":
|
| 1089 |
-
"loss": 0.
|
| 1090 |
"step": 750
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
-
"epoch": 0.
|
| 1094 |
-
"grad_norm": 0.
|
| 1095 |
-
"learning_rate":
|
| 1096 |
-
"loss": 0.
|
| 1097 |
"step": 755
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
-
"epoch": 0.
|
| 1101 |
-
"grad_norm": 0.
|
| 1102 |
-
"learning_rate":
|
| 1103 |
-
"loss": 0.
|
| 1104 |
"step": 760
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
-
"epoch": 0.
|
| 1108 |
-
"grad_norm": 0.
|
| 1109 |
-
"learning_rate":
|
| 1110 |
-
"loss": 0.
|
| 1111 |
"step": 765
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
-
"epoch": 0.
|
| 1115 |
-
"grad_norm": 0.
|
| 1116 |
-
"learning_rate":
|
| 1117 |
-
"loss": 0.
|
| 1118 |
"step": 770
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
-
"epoch": 0.
|
| 1122 |
-
"grad_norm": 0.
|
| 1123 |
-
"learning_rate":
|
| 1124 |
-
"loss": 0.
|
| 1125 |
"step": 775
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
-
"epoch": 0.
|
| 1129 |
-
"grad_norm": 0.
|
| 1130 |
-
"learning_rate":
|
| 1131 |
-
"loss": 0.
|
| 1132 |
"step": 780
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
-
"epoch": 0.
|
| 1136 |
-
"grad_norm": 0.
|
| 1137 |
-
"learning_rate":
|
| 1138 |
-
"loss": 0.
|
| 1139 |
"step": 785
|
| 1140 |
},
|
| 1141 |
{
|
| 1142 |
-
"epoch": 0.
|
| 1143 |
-
"grad_norm": 0.
|
| 1144 |
-
"learning_rate":
|
| 1145 |
-
"loss": 0.
|
| 1146 |
"step": 790
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
-
"epoch": 0.
|
| 1150 |
-
"grad_norm": 0.
|
| 1151 |
-
"learning_rate":
|
| 1152 |
-
"loss": 0.
|
| 1153 |
"step": 795
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch": 0.
|
| 1157 |
-
"grad_norm": 0.
|
| 1158 |
-
"learning_rate":
|
| 1159 |
-
"loss": 0.
|
| 1160 |
"step": 800
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
-
"epoch": 0.
|
| 1164 |
-
"eval_loss": 0.
|
| 1165 |
-
"eval_runtime":
|
| 1166 |
-
"eval_samples_per_second": 10.
|
| 1167 |
-
"eval_steps_per_second": 0.
|
| 1168 |
"step": 800
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
-
"epoch": 0.
|
| 1172 |
-
"grad_norm": 0.
|
| 1173 |
-
"learning_rate":
|
| 1174 |
-
"loss": 0.
|
| 1175 |
"step": 805
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
-
"epoch": 0.
|
| 1179 |
-
"grad_norm": 0.
|
| 1180 |
-
"learning_rate":
|
| 1181 |
-
"loss": 0.
|
| 1182 |
"step": 810
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
-
"epoch": 0.
|
| 1186 |
-
"grad_norm": 0.
|
| 1187 |
-
"learning_rate":
|
| 1188 |
-
"loss": 0.
|
| 1189 |
"step": 815
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
-
"epoch": 0.
|
| 1193 |
-
"grad_norm": 0.
|
| 1194 |
-
"learning_rate":
|
| 1195 |
-
"loss": 0.
|
| 1196 |
"step": 820
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
-
"epoch": 0.
|
| 1200 |
-
"grad_norm": 0.
|
| 1201 |
-
"learning_rate":
|
| 1202 |
-
"loss": 0.
|
| 1203 |
"step": 825
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
-
"epoch": 0.
|
| 1207 |
-
"grad_norm": 0.
|
| 1208 |
-
"learning_rate": 3.
|
| 1209 |
-
"loss": 0.
|
| 1210 |
"step": 830
|
| 1211 |
},
|
| 1212 |
{
|
| 1213 |
-
"epoch": 0.
|
| 1214 |
-
"grad_norm": 0.
|
| 1215 |
-
"learning_rate":
|
| 1216 |
-
"loss": 0.
|
| 1217 |
"step": 835
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
-
"epoch": 0.
|
| 1221 |
-
"grad_norm": 0.
|
| 1222 |
-
"learning_rate": 2.
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"step": 840
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
-
"epoch": 0.
|
| 1228 |
-
"grad_norm": 0.
|
| 1229 |
-
"learning_rate": 2.
|
| 1230 |
-
"loss": 0.
|
| 1231 |
"step": 845
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
-
"epoch": 0.
|
| 1235 |
-
"grad_norm": 0.
|
| 1236 |
-
"learning_rate":
|
| 1237 |
-
"loss": 0.
|
| 1238 |
"step": 850
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
-
"epoch": 0.
|
| 1242 |
-
"grad_norm": 0.
|
| 1243 |
-
"learning_rate":
|
| 1244 |
-
"loss": 0.
|
| 1245 |
"step": 855
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
-
"epoch": 0.
|
| 1249 |
-
"grad_norm": 0.
|
| 1250 |
-
"learning_rate":
|
| 1251 |
-
"loss": 0.
|
| 1252 |
"step": 860
|
| 1253 |
},
|
| 1254 |
{
|
| 1255 |
-
"epoch": 0.
|
| 1256 |
-
"grad_norm": 0.
|
| 1257 |
-
"learning_rate":
|
| 1258 |
-
"loss": 0.
|
| 1259 |
"step": 865
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
-
"epoch": 0.
|
| 1263 |
-
"grad_norm": 0.
|
| 1264 |
-
"learning_rate":
|
| 1265 |
-
"loss": 0.
|
| 1266 |
"step": 870
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
-
"epoch": 0.
|
| 1270 |
-
"grad_norm": 0.
|
| 1271 |
-
"learning_rate":
|
| 1272 |
-
"loss": 0.
|
| 1273 |
"step": 875
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
-
"epoch": 0.
|
| 1277 |
-
"grad_norm": 0.
|
| 1278 |
-
"learning_rate": 2.
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"step": 880
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
-
"epoch": 0.
|
| 1284 |
-
"grad_norm": 0.
|
| 1285 |
-
"learning_rate":
|
| 1286 |
-
"loss": 0.
|
| 1287 |
"step": 885
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch": 0.
|
| 1291 |
-
"grad_norm": 0.
|
| 1292 |
-
"learning_rate":
|
| 1293 |
-
"loss": 0.
|
| 1294 |
"step": 890
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
-
"epoch": 0.
|
| 1298 |
-
"grad_norm": 0.
|
| 1299 |
-
"learning_rate":
|
| 1300 |
-
"loss": 0.
|
| 1301 |
"step": 895
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
-
"epoch": 0.
|
| 1305 |
-
"
|
| 1306 |
-
"
|
| 1307 |
-
"
|
| 1308 |
-
"
|
| 1309 |
-
|
| 1310 |
-
|
| 1311 |
-
"epoch": 0.8333333333333334,
|
| 1312 |
-
"grad_norm": 0.11954867056661006,
|
| 1313 |
-
"learning_rate": 1.6464309923166033e-05,
|
| 1314 |
-
"loss": 0.7045,
|
| 1315 |
-
"step": 905
|
| 1316 |
-
},
|
| 1317 |
-
{
|
| 1318 |
-
"epoch": 0.8379373848987108,
|
| 1319 |
-
"grad_norm": 0.13365725863804348,
|
| 1320 |
-
"learning_rate": 1.5591337696771246e-05,
|
| 1321 |
-
"loss": 0.7313,
|
| 1322 |
-
"step": 910
|
| 1323 |
-
},
|
| 1324 |
-
{
|
| 1325 |
-
"epoch": 0.8425414364640884,
|
| 1326 |
-
"grad_norm": 0.13259625682339735,
|
| 1327 |
-
"learning_rate": 1.4740184141144664e-05,
|
| 1328 |
-
"loss": 0.7099,
|
| 1329 |
-
"step": 915
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 0.8471454880294659,
|
| 1333 |
-
"grad_norm": 0.14145923503935914,
|
| 1334 |
-
"learning_rate": 1.391106926971496e-05,
|
| 1335 |
-
"loss": 0.6952,
|
| 1336 |
-
"step": 920
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 0.8517495395948435,
|
| 1340 |
-
"grad_norm": 0.14338379016355754,
|
| 1341 |
-
"learning_rate": 1.3104207399163815e-05,
|
| 1342 |
-
"loss": 0.6856,
|
| 1343 |
-
"step": 925
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 0.856353591160221,
|
| 1347 |
-
"grad_norm": 0.14829983664793228,
|
| 1348 |
-
"learning_rate": 1.2319807094027492e-05,
|
| 1349 |
-
"loss": 0.7156,
|
| 1350 |
-
"step": 930
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 0.8609576427255985,
|
| 1354 |
-
"grad_norm": 0.12075075754668071,
|
| 1355 |
-
"learning_rate": 1.1558071112785296e-05,
|
| 1356 |
-
"loss": 0.6929,
|
| 1357 |
-
"step": 935
|
| 1358 |
-
},
|
| 1359 |
-
{
|
| 1360 |
-
"epoch": 0.8655616942909761,
|
| 1361 |
-
"grad_norm": 0.12950812269617865,
|
| 1362 |
-
"learning_rate": 1.0819196355448801e-05,
|
| 1363 |
-
"loss": 0.7045,
|
| 1364 |
-
"step": 940
|
| 1365 |
-
},
|
| 1366 |
-
{
|
| 1367 |
-
"epoch": 0.8701657458563536,
|
| 1368 |
-
"grad_norm": 0.1348184333941541,
|
| 1369 |
-
"learning_rate": 1.0103373812665551e-05,
|
| 1370 |
-
"loss": 0.6891,
|
| 1371 |
-
"step": 945
|
| 1372 |
-
},
|
| 1373 |
-
{
|
| 1374 |
-
"epoch": 0.8747697974217311,
|
| 1375 |
-
"grad_norm": 0.12025879421103704,
|
| 1376 |
-
"learning_rate": 9.410788516350077e-06,
|
| 1377 |
-
"loss": 0.6829,
|
| 1378 |
-
"step": 950
|
| 1379 |
-
},
|
| 1380 |
-
{
|
| 1381 |
-
"epoch": 0.8793738489871087,
|
| 1382 |
-
"grad_norm": 0.1332253794557465,
|
| 1383 |
-
"learning_rate": 8.741619491855291e-06,
|
| 1384 |
-
"loss": 0.7057,
|
| 1385 |
-
"step": 955
|
| 1386 |
-
},
|
| 1387 |
-
{
|
| 1388 |
-
"epoch": 0.8839779005524862,
|
| 1389 |
-
"grad_norm": 0.1219486531845245,
|
| 1390 |
-
"learning_rate": 8.096039711696545e-06,
|
| 1391 |
-
"loss": 0.701,
|
| 1392 |
-
"step": 960
|
| 1393 |
-
},
|
| 1394 |
-
{
|
| 1395 |
-
"epoch": 0.8885819521178637,
|
| 1396 |
-
"grad_norm": 0.13660210114125856,
|
| 1397 |
-
"learning_rate": 7.474216050840122e-06,
|
| 1398 |
-
"loss": 0.7016,
|
| 1399 |
-
"step": 965
|
| 1400 |
-
},
|
| 1401 |
-
{
|
| 1402 |
-
"epoch": 0.8931860036832413,
|
| 1403 |
-
"grad_norm": 0.11517510371236951,
|
| 1404 |
-
"learning_rate": 6.876309243568058e-06,
|
| 1405 |
-
"loss": 0.6961,
|
| 1406 |
-
"step": 970
|
| 1407 |
-
},
|
| 1408 |
-
{
|
| 1409 |
-
"epoch": 0.8977900552486188,
|
| 1410 |
-
"grad_norm": 0.14163517493869995,
|
| 1411 |
-
"learning_rate": 6.302473841930134e-06,
|
| 1412 |
-
"loss": 0.7082,
|
| 1413 |
-
"step": 975
|
| 1414 |
-
},
|
| 1415 |
-
{
|
| 1416 |
-
"epoch": 0.9023941068139963,
|
| 1417 |
-
"grad_norm": 0.14904472118298337,
|
| 1418 |
-
"learning_rate": 5.752858175793951e-06,
|
| 1419 |
-
"loss": 0.7017,
|
| 1420 |
-
"step": 980
|
| 1421 |
-
},
|
| 1422 |
-
{
|
| 1423 |
-
"epoch": 0.9069981583793738,
|
| 1424 |
-
"grad_norm": 0.13222086336141328,
|
| 1425 |
-
"learning_rate": 5.2276043145033425e-06,
|
| 1426 |
-
"loss": 0.6951,
|
| 1427 |
-
"step": 985
|
| 1428 |
-
},
|
| 1429 |
-
{
|
| 1430 |
-
"epoch": 0.9116022099447514,
|
| 1431 |
-
"grad_norm": 0.12747716652913677,
|
| 1432 |
-
"learning_rate": 4.726848030155129e-06,
|
| 1433 |
-
"loss": 0.727,
|
| 1434 |
-
"step": 990
|
| 1435 |
-
},
|
| 1436 |
-
{
|
| 1437 |
-
"epoch": 0.916206261510129,
|
| 1438 |
-
"grad_norm": 0.142369192844187,
|
| 1439 |
-
"learning_rate": 4.2507187625035135e-06,
|
| 1440 |
-
"loss": 0.7112,
|
| 1441 |
-
"step": 995
|
| 1442 |
-
},
|
| 1443 |
-
{
|
| 1444 |
-
"epoch": 0.9208103130755064,
|
| 1445 |
-
"grad_norm": 0.12916678602655413,
|
| 1446 |
-
"learning_rate": 3.7993395855014936e-06,
|
| 1447 |
-
"loss": 0.6769,
|
| 1448 |
-
"step": 1000
|
| 1449 |
-
},
|
| 1450 |
-
{
|
| 1451 |
-
"epoch": 0.9208103130755064,
|
| 1452 |
-
"eval_loss": 0.6735966205596924,
|
| 1453 |
-
"eval_runtime": 47.6678,
|
| 1454 |
-
"eval_samples_per_second": 10.489,
|
| 1455 |
-
"eval_steps_per_second": 0.671,
|
| 1456 |
-
"step": 1000
|
| 1457 |
-
},
|
| 1458 |
-
{
|
| 1459 |
-
"epoch": 0.925414364640884,
|
| 1460 |
-
"grad_norm": 0.1315541461105031,
|
| 1461 |
-
"learning_rate": 3.372827175487536e-06,
|
| 1462 |
-
"loss": 0.7239,
|
| 1463 |
-
"step": 1005
|
| 1464 |
-
},
|
| 1465 |
-
{
|
| 1466 |
-
"epoch": 0.9300184162062615,
|
| 1467 |
-
"grad_norm": 0.12551668481359965,
|
| 1468 |
-
"learning_rate": 2.9712917810261644e-06,
|
| 1469 |
-
"loss": 0.707,
|
| 1470 |
-
"step": 1010
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"epoch": 0.934622467771639,
|
| 1474 |
-
"grad_norm": 0.13010659142747308,
|
| 1475 |
-
"learning_rate": 2.5948371944099713e-06,
|
| 1476 |
-
"loss": 0.7066,
|
| 1477 |
-
"step": 1015
|
| 1478 |
-
},
|
| 1479 |
-
{
|
| 1480 |
-
"epoch": 0.9392265193370166,
|
| 1481 |
-
"grad_norm": 0.1374733909690572,
|
| 1482 |
-
"learning_rate": 2.2435607248304623e-06,
|
| 1483 |
-
"loss": 0.6981,
|
| 1484 |
-
"step": 1020
|
| 1485 |
-
},
|
| 1486 |
-
{
|
| 1487 |
-
"epoch": 0.9438305709023941,
|
| 1488 |
-
"grad_norm": 0.1557801553309302,
|
| 1489 |
-
"learning_rate": 1.91755317322474e-06,
|
| 1490 |
-
"loss": 0.6994,
|
| 1491 |
-
"step": 1025
|
| 1492 |
-
},
|
| 1493 |
-
{
|
| 1494 |
-
"epoch": 0.9484346224677717,
|
| 1495 |
-
"grad_norm": 0.1264138943615379,
|
| 1496 |
-
"learning_rate": 1.6168988088045678e-06,
|
| 1497 |
-
"loss": 0.704,
|
| 1498 |
-
"step": 1030
|
| 1499 |
-
},
|
| 1500 |
-
{
|
| 1501 |
-
"epoch": 0.9530386740331491,
|
| 1502 |
-
"grad_norm": 0.10632950484964579,
|
| 1503 |
-
"learning_rate": 1.341675347273652e-06,
|
| 1504 |
-
"loss": 0.677,
|
| 1505 |
-
"step": 1035
|
| 1506 |
-
},
|
| 1507 |
-
{
|
| 1508 |
-
"epoch": 0.9576427255985267,
|
| 1509 |
-
"grad_norm": 0.1230994587161385,
|
| 1510 |
-
"learning_rate": 1.0919539307391314e-06,
|
| 1511 |
-
"loss": 0.6891,
|
| 1512 |
-
"step": 1040
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 0.9622467771639043,
|
| 1516 |
-
"grad_norm": 0.1356286737876717,
|
| 1517 |
-
"learning_rate": 8.67799109322076e-07,
|
| 1518 |
-
"loss": 0.6993,
|
| 1519 |
-
"step": 1045
|
| 1520 |
-
},
|
| 1521 |
-
{
|
| 1522 |
-
"epoch": 0.9668508287292817,
|
| 1523 |
-
"grad_norm": 0.1544804686351126,
|
| 1524 |
-
"learning_rate": 6.692688244720358e-07,
|
| 1525 |
-
"loss": 0.6888,
|
| 1526 |
-
"step": 1050
|
| 1527 |
-
},
|
| 1528 |
-
{
|
| 1529 |
-
"epoch": 0.9714548802946593,
|
| 1530 |
-
"grad_norm": 0.1409581730070821,
|
| 1531 |
-
"learning_rate": 4.964143939898746e-07,
|
| 1532 |
-
"loss": 0.7092,
|
| 1533 |
-
"step": 1055
|
| 1534 |
-
},
|
| 1535 |
-
{
|
| 1536 |
-
"epoch": 0.9760589318600368,
|
| 1537 |
-
"grad_norm": 0.13126265245760058,
|
| 1538 |
-
"learning_rate": 3.49280498762683e-07,
|
| 1539 |
-
"loss": 0.7008,
|
| 1540 |
-
"step": 1060
|
| 1541 |
-
},
|
| 1542 |
-
{
|
| 1543 |
-
"epoch": 0.9806629834254144,
|
| 1544 |
-
"grad_norm": 0.13981476492383843,
|
| 1545 |
-
"learning_rate": 2.2790517121428212e-07,
|
| 1546 |
-
"loss": 0.682,
|
| 1547 |
-
"step": 1065
|
| 1548 |
-
},
|
| 1549 |
-
{
|
| 1550 |
-
"epoch": 0.9852670349907919,
|
| 1551 |
-
"grad_norm": 0.11466302388077335,
|
| 1552 |
-
"learning_rate": 1.323197854742775e-07,
|
| 1553 |
-
"loss": 0.7008,
|
| 1554 |
-
"step": 1070
|
| 1555 |
-
},
|
| 1556 |
-
{
|
| 1557 |
-
"epoch": 0.9898710865561694,
|
| 1558 |
-
"grad_norm": 0.14514253246885966,
|
| 1559 |
-
"learning_rate": 6.254904926820126e-08,
|
| 1560 |
-
"loss": 0.7039,
|
| 1561 |
-
"step": 1075
|
| 1562 |
-
},
|
| 1563 |
-
{
|
| 1564 |
-
"epoch": 0.994475138121547,
|
| 1565 |
-
"grad_norm": 0.12201481168818025,
|
| 1566 |
-
"learning_rate": 1.8610997530876807e-08,
|
| 1567 |
-
"loss": 0.696,
|
| 1568 |
-
"step": 1080
|
| 1569 |
-
},
|
| 1570 |
-
{
|
| 1571 |
-
"epoch": 0.9990791896869244,
|
| 1572 |
-
"grad_norm": 0.13117233881672566,
|
| 1573 |
-
"learning_rate": 5.169877445809767e-10,
|
| 1574 |
-
"loss": 0.6881,
|
| 1575 |
-
"step": 1085
|
| 1576 |
-
},
|
| 1577 |
-
{
|
| 1578 |
-
"epoch": 1.0,
|
| 1579 |
-
"step": 1086,
|
| 1580 |
-
"total_flos": 4801486812086272.0,
|
| 1581 |
-
"train_loss": 0.7253576234998405,
|
| 1582 |
-
"train_runtime": 22925.9932,
|
| 1583 |
-
"train_samples_per_second": 3.031,
|
| 1584 |
-
"train_steps_per_second": 0.047
|
| 1585 |
}
|
| 1586 |
],
|
| 1587 |
"logging_steps": 5,
|
| 1588 |
-
"max_steps":
|
| 1589 |
"num_input_tokens_seen": 0,
|
| 1590 |
"num_train_epochs": 1,
|
| 1591 |
"save_steps": 100,
|
| 1592 |
-
"total_flos":
|
| 1593 |
"train_batch_size": 2,
|
| 1594 |
"trial_name": null,
|
| 1595 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9990265609790016,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 898,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.001112501738283966,
|
| 13 |
+
"grad_norm": 0.6684414708991117,
|
| 14 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 15 |
+
"loss": 1.1751,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.00556250869141983,
|
| 20 |
+
"grad_norm": 0.7639609960034875,
|
| 21 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 22 |
+
"loss": 1.282,
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.01112501738283966,
|
| 27 |
+
"grad_norm": 0.8970088039778137,
|
| 28 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 29 |
+
"loss": 1.276,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.016687526074259492,
|
| 34 |
+
"grad_norm": 0.5983155959810567,
|
| 35 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 36 |
+
"loss": 1.2166,
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.02225003476567932,
|
| 41 |
+
"grad_norm": 0.9387996319771594,
|
| 42 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 43 |
+
"loss": 1.0526,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.027812543457099152,
|
| 48 |
+
"grad_norm": 0.3387344315023908,
|
| 49 |
+
"learning_rate": 5.555555555555556e-05,
|
| 50 |
+
"loss": 0.9608,
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.033375052148518984,
|
| 55 |
+
"grad_norm": 0.23890923775202408,
|
| 56 |
+
"learning_rate": 6.666666666666667e-05,
|
| 57 |
+
"loss": 0.911,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.03893756083993881,
|
| 62 |
+
"grad_norm": 0.22798914076978022,
|
| 63 |
+
"learning_rate": 7.777777777777778e-05,
|
| 64 |
+
"loss": 0.8445,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.04450006953135864,
|
| 69 |
+
"grad_norm": 0.31587333267646156,
|
| 70 |
+
"learning_rate": 8.888888888888889e-05,
|
| 71 |
+
"loss": 0.8105,
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.05006257822277847,
|
| 76 |
+
"grad_norm": 0.19505366669382362,
|
| 77 |
+
"learning_rate": 0.0001,
|
| 78 |
+
"loss": 0.8265,
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.055625086914198305,
|
| 83 |
+
"grad_norm": 0.20253125415926881,
|
| 84 |
+
"learning_rate": 0.00011111111111111112,
|
| 85 |
+
"loss": 0.7973,
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.061187595605618136,
|
| 90 |
+
"grad_norm": 0.19874800607368992,
|
| 91 |
+
"learning_rate": 0.00012222222222222224,
|
| 92 |
+
"loss": 0.7554,
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.06675010429703797,
|
| 97 |
+
"grad_norm": 0.1603617233155014,
|
| 98 |
+
"learning_rate": 0.00013333333333333334,
|
| 99 |
+
"loss": 0.7737,
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.0723126129884578,
|
| 104 |
+
"grad_norm": 0.182313382422268,
|
| 105 |
+
"learning_rate": 0.00014444444444444444,
|
| 106 |
+
"loss": 0.7744,
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.07787512167987762,
|
| 111 |
+
"grad_norm": 0.1404552378108098,
|
| 112 |
+
"learning_rate": 0.00015555555555555556,
|
| 113 |
+
"loss": 0.7995,
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.08343763037129745,
|
| 118 |
+
"grad_norm": 0.15330163912523168,
|
| 119 |
+
"learning_rate": 0.0001666666666666667,
|
| 120 |
+
"loss": 0.7854,
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.08900013906271728,
|
| 125 |
+
"grad_norm": 0.15880144560375917,
|
| 126 |
+
"learning_rate": 0.00017777777777777779,
|
| 127 |
+
"loss": 0.7572,
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.09456264775413711,
|
| 132 |
+
"grad_norm": 0.17526658243677723,
|
| 133 |
+
"learning_rate": 0.00018888888888888888,
|
| 134 |
+
"loss": 0.7421,
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.10012515644555695,
|
| 139 |
+
"grad_norm": 0.1756854246552801,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.7569,
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.10568766513697678,
|
| 146 |
+
"grad_norm": 0.13988463897936598,
|
| 147 |
+
"learning_rate": 0.00019998110384864614,
|
| 148 |
+
"loss": 0.7271,
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.11125017382839661,
|
| 153 |
+
"grad_norm": 0.14983210481706255,
|
| 154 |
+
"learning_rate": 0.0001999244225358753,
|
| 155 |
+
"loss": 0.7444,
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.11681268251981644,
|
| 160 |
+
"grad_norm": 0.14861727909266345,
|
| 161 |
+
"learning_rate": 0.00019982997748286082,
|
| 162 |
+
"loss": 0.7783,
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.12237519121123627,
|
| 167 |
+
"grad_norm": 0.17979168387360328,
|
| 168 |
+
"learning_rate": 0.00019969780438256293,
|
| 169 |
+
"loss": 0.7651,
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.1279376999026561,
|
| 174 |
+
"grad_norm": 0.16202080618298298,
|
| 175 |
+
"learning_rate": 0.00019952795318623986,
|
| 176 |
+
"loss": 0.719,
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.13350020859407594,
|
| 181 |
+
"grad_norm": 0.13085394814942794,
|
| 182 |
+
"learning_rate": 0.0001993204880845699,
|
| 183 |
+
"loss": 0.7044,
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.13906271728549577,
|
| 188 |
+
"grad_norm": 0.1369700622873931,
|
| 189 |
+
"learning_rate": 0.00019907548748339222,
|
| 190 |
+
"loss": 0.7166,
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.1446252259769156,
|
| 195 |
+
"grad_norm": 0.12798471944493164,
|
| 196 |
+
"learning_rate": 0.0001987930439740757,
|
| 197 |
+
"loss": 0.7302,
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.15018773466833543,
|
| 202 |
+
"grad_norm": 0.16062970178106098,
|
| 203 |
+
"learning_rate": 0.0001984732642985263,
|
| 204 |
+
"loss": 0.7477,
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.15575024335975524,
|
| 209 |
+
"grad_norm": 0.12776472354551027,
|
| 210 |
+
"learning_rate": 0.0001981162693088471,
|
| 211 |
+
"loss": 0.7445,
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.16131275205117507,
|
| 216 |
+
"grad_norm": 0.13554426042598045,
|
| 217 |
+
"learning_rate": 0.00019772219392166519,
|
| 218 |
+
"loss": 0.7252,
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.1668752607425949,
|
| 223 |
+
"grad_norm": 0.13347482010697612,
|
| 224 |
+
"learning_rate": 0.00019729118706714375,
|
| 225 |
+
"loss": 0.7254,
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.17243776943401473,
|
| 230 |
+
"grad_norm": 0.134631392605464,
|
| 231 |
+
"learning_rate": 0.000196823411632698,
|
| 232 |
+
"loss": 0.7184,
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.17800027812543456,
|
| 237 |
+
"grad_norm": 0.1504769169328635,
|
| 238 |
+
"learning_rate": 0.00019631904440143612,
|
| 239 |
+
"loss": 0.7259,
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.1835627868168544,
|
| 244 |
+
"grad_norm": 0.13782774235003004,
|
| 245 |
+
"learning_rate": 0.00019577827598534885,
|
| 246 |
+
"loss": 0.7367,
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.18912529550827423,
|
| 251 |
+
"grad_norm": 0.1363344338061366,
|
| 252 |
+
"learning_rate": 0.00019520131075327298,
|
| 253 |
+
"loss": 0.722,
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.19468780419969406,
|
| 258 |
+
"grad_norm": 0.14621350415121373,
|
| 259 |
+
"learning_rate": 0.00019458836675365556,
|
| 260 |
+
"loss": 0.73,
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.2002503128911139,
|
| 265 |
+
"grad_norm": 0.15278741364826062,
|
| 266 |
+
"learning_rate": 0.00019393967563214833,
|
| 267 |
+
"loss": 0.6995,
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.20581282158253372,
|
| 272 |
+
"grad_norm": 0.13331150727297583,
|
| 273 |
+
"learning_rate": 0.00019325548254406352,
|
| 274 |
+
"loss": 0.7487,
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.21137533027395355,
|
| 279 |
+
"grad_norm": 0.1412877661682615,
|
| 280 |
+
"learning_rate": 0.00019253604606172417,
|
| 281 |
+
"loss": 0.7359,
|
| 282 |
"step": 190
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 0.2169378389653734,
|
| 286 |
+
"grad_norm": 0.15015640302548008,
|
| 287 |
+
"learning_rate": 0.0001917816380767434,
|
| 288 |
+
"loss": 0.7014,
|
| 289 |
"step": 195
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.22250034765679322,
|
| 293 |
+
"grad_norm": 0.13131810843452316,
|
| 294 |
+
"learning_rate": 0.0001909925436972706,
|
| 295 |
+
"loss": 0.7113,
|
| 296 |
"step": 200
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.22250034765679322,
|
| 300 |
+
"eval_loss": 0.7031363844871521,
|
| 301 |
+
"eval_runtime": 38.8569,
|
| 302 |
+
"eval_samples_per_second": 10.474,
|
| 303 |
+
"eval_steps_per_second": 0.669,
|
| 304 |
"step": 200
|
| 305 |
},
|
| 306 |
{
|
| 307 |
+
"epoch": 0.22806285634821305,
|
| 308 |
+
"grad_norm": 0.14737211911767406,
|
| 309 |
+
"learning_rate": 0.0001901690611402423,
|
| 310 |
+
"loss": 0.7264,
|
| 311 |
"step": 205
|
| 312 |
},
|
| 313 |
{
|
| 314 |
+
"epoch": 0.23362536503963288,
|
| 315 |
+
"grad_norm": 0.1357323208908195,
|
| 316 |
+
"learning_rate": 0.00018931150161867916,
|
| 317 |
+
"loss": 0.7366,
|
| 318 |
"step": 210
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 0.2391878737310527,
|
| 322 |
+
"grad_norm": 0.13993345760253112,
|
| 323 |
+
"learning_rate": 0.0001884201892240715,
|
| 324 |
+
"loss": 0.7117,
|
| 325 |
"step": 215
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 0.24475038242247255,
|
| 329 |
+
"grad_norm": 0.1369219623281007,
|
| 330 |
+
"learning_rate": 0.00018749546080389757,
|
| 331 |
+
"loss": 0.7197,
|
| 332 |
"step": 220
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 0.2503128911138924,
|
| 336 |
+
"grad_norm": 0.15142549765891067,
|
| 337 |
+
"learning_rate": 0.00018653766583432113,
|
| 338 |
+
"loss": 0.7402,
|
| 339 |
"step": 225
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 0.2558753998053122,
|
| 343 |
+
"grad_norm": 0.1268630478080886,
|
| 344 |
+
"learning_rate": 0.0001855471662881164,
|
| 345 |
+
"loss": 0.7061,
|
| 346 |
"step": 230
|
| 347 |
},
|
| 348 |
{
|
| 349 |
+
"epoch": 0.26143790849673204,
|
| 350 |
+
"grad_norm": 0.15250219181797606,
|
| 351 |
+
"learning_rate": 0.0001845243364978702,
|
| 352 |
+
"loss": 0.6856,
|
| 353 |
"step": 235
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 0.2670004171881519,
|
| 357 |
+
"grad_norm": 0.12578511590375505,
|
| 358 |
+
"learning_rate": 0.00018346956301451304,
|
| 359 |
+
"loss": 0.6933,
|
| 360 |
"step": 240
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 0.2725629258795717,
|
| 364 |
+
"grad_norm": 0.12595811486114722,
|
| 365 |
+
"learning_rate": 0.00018238324446123266,
|
| 366 |
+
"loss": 0.7216,
|
| 367 |
"step": 245
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 0.27812543457099154,
|
| 371 |
+
"grad_norm": 0.1372248567648991,
|
| 372 |
+
"learning_rate": 0.00018126579138282503,
|
| 373 |
+
"loss": 0.7092,
|
| 374 |
"step": 250
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.28368794326241137,
|
| 378 |
+
"grad_norm": 0.1268675904703008,
|
| 379 |
+
"learning_rate": 0.0001801176260905402,
|
| 380 |
+
"loss": 0.6885,
|
| 381 |
"step": 255
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 0.2892504519538312,
|
| 385 |
+
"grad_norm": 0.15050289967108632,
|
| 386 |
+
"learning_rate": 0.00017893918250248104,
|
| 387 |
+
"loss": 0.7095,
|
| 388 |
"step": 260
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 0.29481296064525103,
|
| 392 |
+
"grad_norm": 0.13336034584149736,
|
| 393 |
+
"learning_rate": 0.00017773090597961554,
|
| 394 |
+
"loss": 0.6966,
|
| 395 |
"step": 265
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 0.30037546933667086,
|
| 399 |
+
"grad_norm": 0.158284438999716,
|
| 400 |
+
"learning_rate": 0.00017649325315746478,
|
| 401 |
+
"loss": 0.7275,
|
| 402 |
"step": 270
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 0.3059379780280907,
|
| 406 |
+
"grad_norm": 0.14579684984990443,
|
| 407 |
+
"learning_rate": 0.00017522669177352977,
|
| 408 |
+
"loss": 0.7206,
|
| 409 |
"step": 275
|
| 410 |
},
|
| 411 |
{
|
| 412 |
+
"epoch": 0.31150048671951047,
|
| 413 |
+
"grad_norm": 0.12269074197800435,
|
| 414 |
+
"learning_rate": 0.0001739317004905227,
|
| 415 |
+
"loss": 0.697,
|
| 416 |
"step": 280
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 0.3170629954109303,
|
| 420 |
+
"grad_norm": 0.13835017103100894,
|
| 421 |
+
"learning_rate": 0.00017260876871546936,
|
| 422 |
+
"loss": 0.7174,
|
| 423 |
"step": 285
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"epoch": 0.32262550410235014,
|
| 427 |
+
"grad_norm": 0.14300200863185467,
|
| 428 |
+
"learning_rate": 0.00017125839641475072,
|
| 429 |
+
"loss": 0.726,
|
| 430 |
"step": 290
|
| 431 |
},
|
| 432 |
{
|
| 433 |
+
"epoch": 0.32818801279376997,
|
| 434 |
+
"grad_norm": 0.12914092926857734,
|
| 435 |
+
"learning_rate": 0.0001698810939251543,
|
| 436 |
+
"loss": 0.6991,
|
| 437 |
"step": 295
|
| 438 |
},
|
| 439 |
{
|
| 440 |
+
"epoch": 0.3337505214851898,
|
| 441 |
+
"grad_norm": 0.1293105805311886,
|
| 442 |
+
"learning_rate": 0.00016847738176100632,
|
| 443 |
+
"loss": 0.7264,
|
| 444 |
"step": 300
|
| 445 |
},
|
| 446 |
{
|
| 447 |
+
"epoch": 0.33931303017660963,
|
| 448 |
+
"grad_norm": 0.1263743857475521,
|
| 449 |
+
"learning_rate": 0.00016704779041745686,
|
| 450 |
+
"loss": 0.6938,
|
| 451 |
"step": 305
|
| 452 |
},
|
| 453 |
{
|
| 454 |
+
"epoch": 0.34487553886802946,
|
| 455 |
+
"grad_norm": 0.16556508393117347,
|
| 456 |
+
"learning_rate": 0.000165592860169994,
|
| 457 |
+
"loss": 0.7251,
|
| 458 |
"step": 310
|
| 459 |
},
|
| 460 |
{
|
| 461 |
+
"epoch": 0.3504380475594493,
|
| 462 |
+
"grad_norm": 0.13892185415083144,
|
| 463 |
+
"learning_rate": 0.00016411314087026106,
|
| 464 |
+
"loss": 0.7439,
|
| 465 |
"step": 315
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 0.3560005562508691,
|
| 469 |
+
"grad_norm": 0.1427616131100252,
|
| 470 |
+
"learning_rate": 0.00016260919173825508,
|
| 471 |
+
"loss": 0.6905,
|
| 472 |
"step": 320
|
| 473 |
},
|
| 474 |
{
|
| 475 |
+
"epoch": 0.36156306494228896,
|
| 476 |
+
"grad_norm": 0.1187614399483276,
|
| 477 |
+
"learning_rate": 0.00016108158115098444,
|
| 478 |
+
"loss": 0.681,
|
| 479 |
"step": 325
|
| 480 |
},
|
| 481 |
{
|
| 482 |
+
"epoch": 0.3671255736337088,
|
| 483 |
+
"grad_norm": 0.1428657673910464,
|
| 484 |
+
"learning_rate": 0.0001595308864276666,
|
| 485 |
+
"loss": 0.705,
|
| 486 |
"step": 330
|
| 487 |
},
|
| 488 |
{
|
| 489 |
+
"epoch": 0.3726880823251286,
|
| 490 |
+
"grad_norm": 0.14224088322242012,
|
| 491 |
+
"learning_rate": 0.00015795769361154547,
|
| 492 |
+
"loss": 0.7139,
|
| 493 |
"step": 335
|
| 494 |
},
|
| 495 |
{
|
| 496 |
+
"epoch": 0.37825059101654845,
|
| 497 |
+
"grad_norm": 0.1456871215491553,
|
| 498 |
+
"learning_rate": 0.00015636259724841222,
|
| 499 |
+
"loss": 0.7292,
|
| 500 |
"step": 340
|
| 501 |
},
|
| 502 |
{
|
| 503 |
+
"epoch": 0.3838130997079683,
|
| 504 |
+
"grad_norm": 0.13983468342540284,
|
| 505 |
+
"learning_rate": 0.00015474620016191294,
|
| 506 |
+
"loss": 0.7222,
|
| 507 |
"step": 345
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 0.3893756083993881,
|
| 511 |
+
"grad_norm": 0.14315721096194434,
|
| 512 |
+
"learning_rate": 0.00015310911322572753,
|
| 513 |
+
"loss": 0.7112,
|
| 514 |
"step": 350
|
| 515 |
},
|
| 516 |
{
|
| 517 |
+
"epoch": 0.39493811709080795,
|
| 518 |
+
"grad_norm": 0.12717703522604246,
|
| 519 |
+
"learning_rate": 0.00015145195513270644,
|
| 520 |
+
"loss": 0.7018,
|
| 521 |
"step": 355
|
| 522 |
},
|
| 523 |
{
|
| 524 |
+
"epoch": 0.4005006257822278,
|
| 525 |
+
"grad_norm": 0.1405738893906113,
|
| 526 |
+
"learning_rate": 0.0001497753521610526,
|
| 527 |
+
"loss": 0.708,
|
| 528 |
"step": 360
|
| 529 |
},
|
| 530 |
{
|
| 531 |
+
"epoch": 0.4060631344736476,
|
| 532 |
+
"grad_norm": 0.12649904699680478,
|
| 533 |
+
"learning_rate": 0.00014807993793763619,
|
| 534 |
+
"loss": 0.6728,
|
| 535 |
"step": 365
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 0.41162564316506745,
|
| 539 |
+
"grad_norm": 0.1366397886559032,
|
| 540 |
+
"learning_rate": 0.00014636635319853275,
|
| 541 |
+
"loss": 0.6855,
|
| 542 |
"step": 370
|
| 543 |
},
|
| 544 |
{
|
| 545 |
+
"epoch": 0.4171881518564873,
|
| 546 |
+
"grad_norm": 0.1348575434185503,
|
| 547 |
+
"learning_rate": 0.00014463524554687399,
|
| 548 |
+
"loss": 0.6969,
|
| 549 |
"step": 375
|
| 550 |
},
|
| 551 |
{
|
| 552 |
+
"epoch": 0.4227506605479071,
|
| 553 |
+
"grad_norm": 0.13467406560845768,
|
| 554 |
+
"learning_rate": 0.0001428872692081038,
|
| 555 |
+
"loss": 0.7179,
|
| 556 |
"step": 380
|
| 557 |
},
|
| 558 |
{
|
| 559 |
+
"epoch": 0.42831316923932694,
|
| 560 |
+
"grad_norm": 0.13474764353512392,
|
| 561 |
+
"learning_rate": 0.00014112308478273145,
|
| 562 |
+
"loss": 0.6853,
|
| 563 |
"step": 385
|
| 564 |
},
|
| 565 |
{
|
| 566 |
+
"epoch": 0.4338756779307468,
|
| 567 |
+
"grad_norm": 0.12908327147450624,
|
| 568 |
+
"learning_rate": 0.00013934335899667527,
|
| 569 |
+
"loss": 0.7131,
|
| 570 |
"step": 390
|
| 571 |
},
|
| 572 |
{
|
| 573 |
+
"epoch": 0.4394381866221666,
|
| 574 |
+
"grad_norm": 0.12215743992138174,
|
| 575 |
+
"learning_rate": 0.00013754876444929166,
|
| 576 |
+
"loss": 0.6748,
|
| 577 |
"step": 395
|
| 578 |
},
|
| 579 |
{
|
| 580 |
+
"epoch": 0.44500069531358644,
|
| 581 |
+
"grad_norm": 0.12646747341185763,
|
| 582 |
+
"learning_rate": 0.0001357399793591844,
|
| 583 |
+
"loss": 0.7181,
|
| 584 |
"step": 400
|
| 585 |
},
|
| 586 |
{
|
| 587 |
+
"epoch": 0.44500069531358644,
|
| 588 |
+
"eval_loss": 0.6872018575668335,
|
| 589 |
+
"eval_runtime": 38.1286,
|
| 590 |
+
"eval_samples_per_second": 10.674,
|
| 591 |
+
"eval_steps_per_second": 0.682,
|
| 592 |
"step": 400
|
| 593 |
},
|
| 594 |
{
|
| 595 |
+
"epoch": 0.45056320400500627,
|
| 596 |
+
"grad_norm": 0.13122165542663003,
|
| 597 |
+
"learning_rate": 0.00013391768730789002,
|
| 598 |
+
"loss": 0.7121,
|
| 599 |
"step": 405
|
| 600 |
},
|
| 601 |
{
|
| 602 |
+
"epoch": 0.4561257126964261,
|
| 603 |
+
"grad_norm": 0.12302514176584399,
|
| 604 |
+
"learning_rate": 0.00013208257698153677,
|
| 605 |
+
"loss": 0.7122,
|
| 606 |
"step": 410
|
| 607 |
},
|
| 608 |
{
|
| 609 |
+
"epoch": 0.46168822138784593,
|
| 610 |
+
"grad_norm": 0.14440204630512954,
|
| 611 |
+
"learning_rate": 0.00013023534191057426,
|
| 612 |
+
"loss": 0.7239,
|
| 613 |
"step": 415
|
| 614 |
},
|
| 615 |
{
|
| 616 |
+
"epoch": 0.46725073007926576,
|
| 617 |
+
"grad_norm": 0.13547988803582495,
|
| 618 |
+
"learning_rate": 0.0001283766802076722,
|
| 619 |
+
"loss": 0.7206,
|
| 620 |
"step": 420
|
| 621 |
},
|
| 622 |
{
|
| 623 |
+
"epoch": 0.4728132387706856,
|
| 624 |
+
"grad_norm": 0.13999737919216407,
|
| 625 |
+
"learning_rate": 0.00012650729430388764,
|
| 626 |
+
"loss": 0.6826,
|
| 627 |
"step": 425
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 0.4783757474621054,
|
| 631 |
+
"grad_norm": 0.13048583251685064,
|
| 632 |
+
"learning_rate": 0.00012462789068320017,
|
| 633 |
+
"loss": 0.6926,
|
| 634 |
"step": 430
|
| 635 |
},
|
| 636 |
{
|
| 637 |
+
"epoch": 0.48393825615352526,
|
| 638 |
+
"grad_norm": 0.1496684308590174,
|
| 639 |
+
"learning_rate": 0.00012273917961551513,
|
| 640 |
+
"loss": 0.7342,
|
| 641 |
"step": 435
|
| 642 |
},
|
| 643 |
{
|
| 644 |
+
"epoch": 0.4895007648449451,
|
| 645 |
+
"grad_norm": 0.14327740803897993,
|
| 646 |
+
"learning_rate": 0.00012084187488823657,
|
| 647 |
+
"loss": 0.6966,
|
| 648 |
"step": 440
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 0.4950632735363649,
|
| 652 |
+
"grad_norm": 0.14722640475177795,
|
| 653 |
+
"learning_rate": 0.00011893669353651031,
|
| 654 |
+
"loss": 0.7045,
|
| 655 |
"step": 445
|
| 656 |
},
|
| 657 |
{
|
| 658 |
+
"epoch": 0.5006257822277848,
|
| 659 |
+
"grad_norm": 0.13182498566362877,
|
| 660 |
+
"learning_rate": 0.00011702435557223987,
|
| 661 |
+
"loss": 0.7205,
|
| 662 |
"step": 450
|
| 663 |
},
|
| 664 |
{
|
| 665 |
+
"epoch": 0.5061882909192046,
|
| 666 |
+
"grad_norm": 0.14649854622775277,
|
| 667 |
+
"learning_rate": 0.00011510558371197753,
|
| 668 |
+
"loss": 0.6972,
|
| 669 |
"step": 455
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 0.5117507996106244,
|
| 673 |
+
"grad_norm": 0.14603995632853023,
|
| 674 |
+
"learning_rate": 0.00011318110310379301,
|
| 675 |
+
"loss": 0.7455,
|
| 676 |
"step": 460
|
| 677 |
},
|
| 678 |
{
|
| 679 |
+
"epoch": 0.5173133083020443,
|
| 680 |
+
"grad_norm": 0.1413104318676706,
|
| 681 |
+
"learning_rate": 0.0001112516410532233,
|
| 682 |
+
"loss": 0.6917,
|
| 683 |
"step": 465
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 0.5228758169934641,
|
| 687 |
+
"grad_norm": 0.1319527122221744,
|
| 688 |
+
"learning_rate": 0.00010931792674840718,
|
| 689 |
+
"loss": 0.6855,
|
| 690 |
"step": 470
|
| 691 |
},
|
| 692 |
{
|
| 693 |
+
"epoch": 0.5284383256848839,
|
| 694 |
+
"grad_norm": 0.1245675456499167,
|
| 695 |
+
"learning_rate": 0.0001073806909845082,
|
| 696 |
+
"loss": 0.7028,
|
| 697 |
"step": 475
|
| 698 |
},
|
| 699 |
{
|
| 700 |
+
"epoch": 0.5340008343763037,
|
| 701 |
+
"grad_norm": 0.11698601668007995,
|
| 702 |
+
"learning_rate": 0.00010544066588753044,
|
| 703 |
+
"loss": 0.6933,
|
| 704 |
"step": 480
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 0.5395633430677236,
|
| 708 |
+
"grad_norm": 0.12677292396669446,
|
| 709 |
+
"learning_rate": 0.00010349858463763113,
|
| 710 |
+
"loss": 0.683,
|
| 711 |
"step": 485
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 0.5451258517591434,
|
| 715 |
+
"grad_norm": 0.13456238683420088,
|
| 716 |
+
"learning_rate": 0.0001015551811920351,
|
| 717 |
+
"loss": 0.7006,
|
| 718 |
"step": 490
|
| 719 |
},
|
| 720 |
{
|
| 721 |
+
"epoch": 0.5506883604505632,
|
| 722 |
+
"grad_norm": 0.15227986749806005,
|
| 723 |
+
"learning_rate": 9.961119000765531e-05,
|
| 724 |
+
"loss": 0.6894,
|
| 725 |
"step": 495
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 0.5562508691419831,
|
| 729 |
+
"grad_norm": 0.12847199230412348,
|
| 730 |
+
"learning_rate": 9.766734576352478e-05,
|
| 731 |
+
"loss": 0.6964,
|
| 732 |
"step": 500
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 0.5618133778334029,
|
| 736 |
+
"grad_norm": 0.13064877508080042,
|
| 737 |
+
"learning_rate": 9.572438308314446e-05,
|
| 738 |
+
"loss": 0.6885,
|
| 739 |
"step": 505
|
| 740 |
},
|
| 741 |
{
|
| 742 |
+
"epoch": 0.5673758865248227,
|
| 743 |
+
"grad_norm": 0.1372527364951275,
|
| 744 |
+
"learning_rate": 9.378303625685195e-05,
|
| 745 |
+
"loss": 0.7056,
|
| 746 |
"step": 510
|
| 747 |
},
|
| 748 |
{
|
| 749 |
+
"epoch": 0.5729383952162426,
|
| 750 |
+
"grad_norm": 0.13318320240144188,
|
| 751 |
+
"learning_rate": 9.18440389643165e-05,
|
| 752 |
+
"loss": 0.6792,
|
| 753 |
"step": 515
|
| 754 |
},
|
| 755 |
{
|
| 756 |
+
"epoch": 0.5785009039076624,
|
| 757 |
+
"grad_norm": 0.1389287540275015,
|
| 758 |
+
"learning_rate": 8.990812399726435e-05,
|
| 759 |
+
"loss": 0.6955,
|
| 760 |
"step": 520
|
| 761 |
},
|
| 762 |
{
|
| 763 |
+
"epoch": 0.5840634125990822,
|
| 764 |
+
"grad_norm": 0.15589038738911026,
|
| 765 |
+
"learning_rate": 8.797602298254004e-05,
|
| 766 |
+
"loss": 0.6995,
|
| 767 |
"step": 525
|
| 768 |
},
|
| 769 |
{
|
| 770 |
+
"epoch": 0.5896259212905021,
|
| 771 |
+
"grad_norm": 0.13296983699316012,
|
| 772 |
+
"learning_rate": 8.604846610560771e-05,
|
| 773 |
+
"loss": 0.6707,
|
| 774 |
"step": 530
|
| 775 |
},
|
| 776 |
{
|
| 777 |
+
"epoch": 0.5951884299819219,
|
| 778 |
+
"grad_norm": 0.12114356841208347,
|
| 779 |
+
"learning_rate": 8.412618183459708e-05,
|
| 780 |
+
"loss": 0.7015,
|
| 781 |
"step": 535
|
| 782 |
},
|
| 783 |
{
|
| 784 |
+
"epoch": 0.6007509386733417,
|
| 785 |
+
"grad_norm": 0.12351709388346521,
|
| 786 |
+
"learning_rate": 8.220989664499878e-05,
|
| 787 |
+
"loss": 0.7006,
|
| 788 |
"step": 540
|
| 789 |
},
|
| 790 |
{
|
| 791 |
+
"epoch": 0.6063134473647616,
|
| 792 |
+
"grad_norm": 0.1233117181776912,
|
| 793 |
+
"learning_rate": 8.030033474511249e-05,
|
| 794 |
+
"loss": 0.7061,
|
| 795 |
"step": 545
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 0.6118759560561814,
|
| 799 |
+
"grad_norm": 0.14966743246815337,
|
| 800 |
+
"learning_rate": 7.839821780235168e-05,
|
| 801 |
+
"loss": 0.7383,
|
| 802 |
"step": 550
|
| 803 |
},
|
| 804 |
{
|
| 805 |
+
"epoch": 0.6174384647476012,
|
| 806 |
+
"grad_norm": 0.13689976425741557,
|
| 807 |
+
"learning_rate": 7.650426467050926e-05,
|
| 808 |
+
"loss": 0.7083,
|
| 809 |
"step": 555
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 0.6230009734390209,
|
| 813 |
+
"grad_norm": 0.1540376322278511,
|
| 814 |
+
"learning_rate": 7.461919111808595e-05,
|
| 815 |
+
"loss": 0.6991,
|
| 816 |
"step": 560
|
| 817 |
},
|
| 818 |
{
|
| 819 |
+
"epoch": 0.6285634821304408,
|
| 820 |
+
"grad_norm": 0.15818277915085305,
|
| 821 |
+
"learning_rate": 7.274370955778498e-05,
|
| 822 |
+
"loss": 0.7147,
|
| 823 |
"step": 565
|
| 824 |
},
|
| 825 |
{
|
| 826 |
+
"epoch": 0.6341259908218606,
|
| 827 |
+
"grad_norm": 0.13733946492240742,
|
| 828 |
+
"learning_rate": 7.087852877727481e-05,
|
| 829 |
+
"loss": 0.7043,
|
| 830 |
"step": 570
|
| 831 |
},
|
| 832 |
{
|
| 833 |
+
"epoch": 0.6396884995132804,
|
| 834 |
+
"grad_norm": 0.12905771101166952,
|
| 835 |
+
"learning_rate": 6.902435367132208e-05,
|
| 836 |
+
"loss": 0.6952,
|
| 837 |
"step": 575
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 0.6452510082047003,
|
| 841 |
+
"grad_norm": 0.14917864740623707,
|
| 842 |
+
"learning_rate": 6.718188497539554e-05,
|
| 843 |
+
"loss": 0.6894,
|
| 844 |
"step": 580
|
| 845 |
},
|
| 846 |
{
|
| 847 |
+
"epoch": 0.6508135168961201,
|
| 848 |
+
"grad_norm": 0.17034610159423622,
|
| 849 |
+
"learning_rate": 6.535181900084206e-05,
|
| 850 |
+
"loss": 0.6906,
|
| 851 |
"step": 585
|
| 852 |
},
|
| 853 |
{
|
| 854 |
+
"epoch": 0.6563760255875399,
|
| 855 |
+
"grad_norm": 0.14577692793179953,
|
| 856 |
+
"learning_rate": 6.35348473717345e-05,
|
| 857 |
+
"loss": 0.6822,
|
| 858 |
"step": 590
|
| 859 |
},
|
| 860 |
{
|
| 861 |
+
"epoch": 0.6619385342789598,
|
| 862 |
+
"grad_norm": 0.1400663188779511,
|
| 863 |
+
"learning_rate": 6.173165676349103e-05,
|
| 864 |
+
"loss": 0.702,
|
| 865 |
"step": 595
|
| 866 |
},
|
| 867 |
{
|
| 868 |
+
"epoch": 0.6675010429703796,
|
| 869 |
+
"grad_norm": 0.13477519960817833,
|
| 870 |
+
"learning_rate": 5.9942928643364724e-05,
|
| 871 |
+
"loss": 0.7171,
|
| 872 |
"step": 600
|
| 873 |
},
|
| 874 |
{
|
| 875 |
+
"epoch": 0.6675010429703796,
|
| 876 |
+
"eval_loss": 0.6785927414894104,
|
| 877 |
+
"eval_runtime": 38.1279,
|
| 878 |
+
"eval_samples_per_second": 10.675,
|
| 879 |
+
"eval_steps_per_second": 0.682,
|
| 880 |
"step": 600
|
| 881 |
},
|
| 882 |
{
|
| 883 |
+
"epoch": 0.6730635516617994,
|
| 884 |
+
"grad_norm": 0.13058646321017944,
|
| 885 |
+
"learning_rate": 5.816933901290136e-05,
|
| 886 |
+
"loss": 0.6959,
|
| 887 |
"step": 605
|
| 888 |
},
|
| 889 |
{
|
| 890 |
+
"epoch": 0.6786260603532193,
|
| 891 |
+
"grad_norm": 0.14039443258781562,
|
| 892 |
+
"learning_rate": 5.6411558152462894e-05,
|
| 893 |
"loss": 0.6991,
|
| 894 |
"step": 610
|
| 895 |
},
|
| 896 |
{
|
| 897 |
+
"epoch": 0.6841885690446391,
|
| 898 |
+
"grad_norm": 0.1435099198472092,
|
| 899 |
+
"learning_rate": 5.4670250367913023e-05,
|
| 900 |
+
"loss": 0.7008,
|
| 901 |
"step": 615
|
| 902 |
},
|
| 903 |
{
|
| 904 |
+
"epoch": 0.6897510777360589,
|
| 905 |
+
"grad_norm": 0.1251912516827599,
|
| 906 |
+
"learning_rate": 5.2946073739560706e-05,
|
| 907 |
+
"loss": 0.6828,
|
| 908 |
"step": 620
|
| 909 |
},
|
| 910 |
{
|
| 911 |
+
"epoch": 0.6953135864274788,
|
| 912 |
+
"grad_norm": 0.12907022711465035,
|
| 913 |
+
"learning_rate": 5.1239679873456634e-05,
|
| 914 |
+
"loss": 0.6811,
|
| 915 |
"step": 625
|
| 916 |
},
|
| 917 |
{
|
| 918 |
+
"epoch": 0.7008760951188986,
|
| 919 |
+
"grad_norm": 0.13237387347735238,
|
| 920 |
+
"learning_rate": 4.955171365513603e-05,
|
| 921 |
+
"loss": 0.7235,
|
| 922 |
"step": 630
|
| 923 |
},
|
| 924 |
{
|
| 925 |
+
"epoch": 0.7064386038103184,
|
| 926 |
+
"grad_norm": 0.12376618467656812,
|
| 927 |
+
"learning_rate": 4.7882813005901696e-05,
|
| 928 |
+
"loss": 0.687,
|
| 929 |
"step": 635
|
| 930 |
},
|
| 931 |
{
|
| 932 |
+
"epoch": 0.7120011125017383,
|
| 933 |
+
"grad_norm": 0.1456941018180003,
|
| 934 |
+
"learning_rate": 4.623360864173893e-05,
|
| 935 |
+
"loss": 0.6813,
|
| 936 |
"step": 640
|
| 937 |
},
|
| 938 |
{
|
| 939 |
+
"epoch": 0.7175636211931581,
|
| 940 |
+
"grad_norm": 0.17032008806579718,
|
| 941 |
+
"learning_rate": 4.460472383495331e-05,
|
| 942 |
+
"loss": 0.6795,
|
| 943 |
"step": 645
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 0.7231261298845779,
|
| 947 |
+
"grad_norm": 0.12579166198761085,
|
| 948 |
+
"learning_rate": 4.2996774178621736e-05,
|
| 949 |
+
"loss": 0.6835,
|
| 950 |
"step": 650
|
| 951 |
},
|
| 952 |
{
|
| 953 |
+
"epoch": 0.7286886385759977,
|
| 954 |
+
"grad_norm": 0.14450683290791613,
|
| 955 |
+
"learning_rate": 4.141036735394574e-05,
|
| 956 |
+
"loss": 0.6862,
|
| 957 |
"step": 655
|
| 958 |
},
|
| 959 |
{
|
| 960 |
+
"epoch": 0.7342511472674176,
|
| 961 |
+
"grad_norm": 0.17119446089706108,
|
| 962 |
+
"learning_rate": 3.984610290059467e-05,
|
| 963 |
+
"loss": 0.7112,
|
| 964 |
"step": 660
|
| 965 |
},
|
| 966 |
{
|
| 967 |
+
"epoch": 0.7398136559588374,
|
| 968 |
+
"grad_norm": 0.14950992219628134,
|
| 969 |
+
"learning_rate": 3.830457199012585e-05,
|
| 970 |
+
"loss": 0.7259,
|
| 971 |
"step": 665
|
| 972 |
},
|
| 973 |
{
|
| 974 |
+
"epoch": 0.7453761646502572,
|
| 975 |
+
"grad_norm": 0.14485285236277412,
|
| 976 |
+
"learning_rate": 3.678635720256737e-05,
|
| 977 |
+
"loss": 0.6944,
|
| 978 |
"step": 670
|
| 979 |
},
|
| 980 |
{
|
| 981 |
+
"epoch": 0.7509386733416771,
|
| 982 |
+
"grad_norm": 0.13749155498971605,
|
| 983 |
+
"learning_rate": 3.529203230624747e-05,
|
| 984 |
+
"loss": 0.6758,
|
| 985 |
"step": 675
|
| 986 |
},
|
| 987 |
{
|
| 988 |
+
"epoch": 0.7565011820330969,
|
| 989 |
+
"grad_norm": 0.12869094791923574,
|
| 990 |
+
"learning_rate": 3.3822162040954354e-05,
|
| 991 |
+
"loss": 0.701,
|
| 992 |
"step": 680
|
| 993 |
},
|
| 994 |
{
|
| 995 |
+
"epoch": 0.7620636907245167,
|
| 996 |
+
"grad_norm": 0.12906896257797407,
|
| 997 |
+
"learning_rate": 3.237730190450816e-05,
|
| 998 |
+
"loss": 0.7059,
|
| 999 |
"step": 685
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 0.7676261994159366,
|
| 1003 |
+
"grad_norm": 0.15164612968237504,
|
| 1004 |
+
"learning_rate": 3.0957997942825336e-05,
|
| 1005 |
+
"loss": 0.6925,
|
| 1006 |
"step": 690
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
+
"epoch": 0.7731887081073564,
|
| 1010 |
+
"grad_norm": 0.15092417362430902,
|
| 1011 |
+
"learning_rate": 2.9564786543555388e-05,
|
| 1012 |
+
"loss": 0.704,
|
| 1013 |
"step": 695
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 0.7787512167987762,
|
| 1017 |
+
"grad_norm": 0.12028807778273494,
|
| 1018 |
+
"learning_rate": 2.819819423336775e-05,
|
| 1019 |
+
"loss": 0.6615,
|
| 1020 |
"step": 700
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
+
"epoch": 0.7843137254901961,
|
| 1024 |
+
"grad_norm": 0.11668516511159772,
|
| 1025 |
+
"learning_rate": 2.6858737478965035e-05,
|
| 1026 |
+
"loss": 0.6761,
|
| 1027 |
"step": 705
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
+
"epoch": 0.7898762341816159,
|
| 1031 |
+
"grad_norm": 0.12013736025525155,
|
| 1032 |
+
"learning_rate": 2.5546922491898495e-05,
|
| 1033 |
+
"loss": 0.6812,
|
| 1034 |
"step": 710
|
| 1035 |
},
|
| 1036 |
{
|
| 1037 |
+
"epoch": 0.7954387428730357,
|
| 1038 |
+
"grad_norm": 0.11406481330250699,
|
| 1039 |
+
"learning_rate": 2.4263245037258995e-05,
|
| 1040 |
+
"loss": 0.6653,
|
| 1041 |
"step": 715
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
+
"epoch": 0.8010012515644556,
|
| 1045 |
+
"grad_norm": 0.14003374126540685,
|
| 1046 |
+
"learning_rate": 2.300819024631603e-05,
|
| 1047 |
+
"loss": 0.7079,
|
| 1048 |
"step": 720
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
+
"epoch": 0.8065637602558754,
|
| 1052 |
+
"grad_norm": 0.14609209804734563,
|
| 1053 |
+
"learning_rate": 2.178223243317532e-05,
|
| 1054 |
+
"loss": 0.7126,
|
| 1055 |
"step": 725
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 0.8121262689472952,
|
| 1059 |
+
"grad_norm": 0.1412723606655406,
|
| 1060 |
+
"learning_rate": 2.058583491552465e-05,
|
| 1061 |
+
"loss": 0.6805,
|
| 1062 |
"step": 730
|
| 1063 |
},
|
| 1064 |
{
|
| 1065 |
+
"epoch": 0.8176887776387151,
|
| 1066 |
+
"grad_norm": 0.13559476815952162,
|
| 1067 |
+
"learning_rate": 1.941944983953552e-05,
|
| 1068 |
+
"loss": 0.6687,
|
| 1069 |
"step": 735
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
+
"epoch": 0.8232512863301349,
|
| 1073 |
+
"grad_norm": 0.1212687591445283,
|
| 1074 |
+
"learning_rate": 1.8283518008986567e-05,
|
| 1075 |
+
"loss": 0.6949,
|
| 1076 |
"step": 740
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
+
"epoch": 0.8288137950215547,
|
| 1080 |
+
"grad_norm": 0.13418537722622348,
|
| 1081 |
+
"learning_rate": 1.7178468718673714e-05,
|
| 1082 |
+
"loss": 0.6947,
|
| 1083 |
"step": 745
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
+
"epoch": 0.8343763037129746,
|
| 1087 |
+
"grad_norm": 0.14626468131094617,
|
| 1088 |
+
"learning_rate": 1.6104719592169902e-05,
|
| 1089 |
+
"loss": 0.6974,
|
| 1090 |
"step": 750
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
+
"epoch": 0.8399388124043944,
|
| 1094 |
+
"grad_norm": 0.1505968834590085,
|
| 1095 |
+
"learning_rate": 1.5062676423995247e-05,
|
| 1096 |
+
"loss": 0.6699,
|
| 1097 |
"step": 755
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
+
"epoch": 0.8455013210958142,
|
| 1101 |
+
"grad_norm": 0.13840692663705956,
|
| 1102 |
+
"learning_rate": 1.4052733026258281e-05,
|
| 1103 |
+
"loss": 0.6775,
|
| 1104 |
"step": 760
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
+
"epoch": 0.851063829787234,
|
| 1108 |
+
"grad_norm": 0.15338747206444608,
|
| 1109 |
+
"learning_rate": 1.3075271079825036e-05,
|
| 1110 |
+
"loss": 0.6855,
|
| 1111 |
"step": 765
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
+
"epoch": 0.8566263384786539,
|
| 1115 |
+
"grad_norm": 0.15087298168068788,
|
| 1116 |
+
"learning_rate": 1.2130659990073146e-05,
|
| 1117 |
+
"loss": 0.7074,
|
| 1118 |
"step": 770
|
| 1119 |
},
|
| 1120 |
{
|
| 1121 |
+
"epoch": 0.8621888471700737,
|
| 1122 |
+
"grad_norm": 0.15260125382082407,
|
| 1123 |
+
"learning_rate": 1.1219256747285045e-05,
|
| 1124 |
+
"loss": 0.6559,
|
| 1125 |
"step": 775
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
+
"epoch": 0.8677513558614935,
|
| 1129 |
+
"grad_norm": 0.13676984708600298,
|
| 1130 |
+
"learning_rate": 1.0341405791733183e-05,
|
| 1131 |
+
"loss": 0.7018,
|
| 1132 |
"step": 780
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
+
"epoch": 0.8733138645529134,
|
| 1136 |
+
"grad_norm": 0.12792881953620902,
|
| 1137 |
+
"learning_rate": 9.49743888350798e-06,
|
| 1138 |
+
"loss": 0.6758,
|
| 1139 |
"step": 785
|
| 1140 |
},
|
| 1141 |
{
|
| 1142 |
+
"epoch": 0.8788763732443332,
|
| 1143 |
+
"grad_norm": 0.13024278184248392,
|
| 1144 |
+
"learning_rate": 8.687674977138116e-06,
|
| 1145 |
+
"loss": 0.703,
|
| 1146 |
"step": 790
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
+
"epoch": 0.884438881935753,
|
| 1150 |
+
"grad_norm": 0.15819074719833112,
|
| 1151 |
+
"learning_rate": 7.912420101050367e-06,
|
| 1152 |
+
"loss": 0.7026,
|
| 1153 |
"step": 795
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 0.8900013906271729,
|
| 1157 |
+
"grad_norm": 0.1363306447853743,
|
| 1158 |
+
"learning_rate": 7.171967241914224e-06,
|
| 1159 |
+
"loss": 0.7031,
|
| 1160 |
"step": 800
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
+
"epoch": 0.8900013906271729,
|
| 1164 |
+
"eval_loss": 0.6755391955375671,
|
| 1165 |
+
"eval_runtime": 38.1439,
|
| 1166 |
+
"eval_samples_per_second": 10.67,
|
| 1167 |
+
"eval_steps_per_second": 0.682,
|
| 1168 |
"step": 800
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
+
"epoch": 0.8955638993185927,
|
| 1172 |
+
"grad_norm": 0.11599580684218645,
|
| 1173 |
+
"learning_rate": 6.4665962339156005e-06,
|
| 1174 |
+
"loss": 0.6559,
|
| 1175 |
"step": 805
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
+
"epoch": 0.9011264080100125,
|
| 1179 |
+
"grad_norm": 0.14301150354946243,
|
| 1180 |
+
"learning_rate": 5.7965736530010916e-06,
|
| 1181 |
+
"loss": 0.7436,
|
| 1182 |
"step": 810
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
+
"epoch": 0.9066889167014324,
|
| 1186 |
+
"grad_norm": 0.1454357862013425,
|
| 1187 |
+
"learning_rate": 5.162152716132662e-06,
|
| 1188 |
+
"loss": 0.6851,
|
| 1189 |
"step": 815
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
+
"epoch": 0.9122514253928522,
|
| 1193 |
+
"grad_norm": 0.1296885702439703,
|
| 1194 |
+
"learning_rate": 4.563573185591219e-06,
|
| 1195 |
+
"loss": 0.6799,
|
| 1196 |
"step": 820
|
| 1197 |
},
|
| 1198 |
{
|
| 1199 |
+
"epoch": 0.917813934084272,
|
| 1200 |
+
"grad_norm": 0.13649350003605498,
|
| 1201 |
+
"learning_rate": 4.0010612783648925e-06,
|
| 1202 |
+
"loss": 0.6954,
|
| 1203 |
"step": 825
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
+
"epoch": 0.9233764427756919,
|
| 1207 |
+
"grad_norm": 0.11566680964002608,
|
| 1208 |
+
"learning_rate": 3.4748295806564356e-06,
|
| 1209 |
+
"loss": 0.6931,
|
| 1210 |
"step": 830
|
| 1211 |
},
|
| 1212 |
{
|
| 1213 |
+
"epoch": 0.9289389514671117,
|
| 1214 |
+
"grad_norm": 0.1376951533333156,
|
| 1215 |
+
"learning_rate": 2.9850769675419774e-06,
|
| 1216 |
+
"loss": 0.7094,
|
| 1217 |
"step": 835
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
+
"epoch": 0.9345014601585315,
|
| 1221 |
+
"grad_norm": 0.13815883208860893,
|
| 1222 |
+
"learning_rate": 2.5319885278115906e-06,
|
| 1223 |
+
"loss": 0.6814,
|
| 1224 |
"step": 840
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
+
"epoch": 0.9400639688499514,
|
| 1228 |
+
"grad_norm": 0.12898446369151903,
|
| 1229 |
+
"learning_rate": 2.115735494019966e-06,
|
| 1230 |
+
"loss": 0.7252,
|
| 1231 |
"step": 845
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
+
"epoch": 0.9456264775413712,
|
| 1235 |
+
"grad_norm": 0.14801072441410335,
|
| 1236 |
+
"learning_rate": 1.7364751777736332e-06,
|
| 1237 |
+
"loss": 0.6701,
|
| 1238 |
"step": 850
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
+
"epoch": 0.951188986232791,
|
| 1242 |
+
"grad_norm": 0.1489167549426156,
|
| 1243 |
+
"learning_rate": 1.394350910279385e-06,
|
| 1244 |
+
"loss": 0.6852,
|
| 1245 |
"step": 855
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
+
"epoch": 0.9567514949242109,
|
| 1249 |
+
"grad_norm": 0.150107558255733,
|
| 1250 |
+
"learning_rate": 1.089491988176017e-06,
|
| 1251 |
+
"loss": 0.7177,
|
| 1252 |
"step": 860
|
| 1253 |
},
|
| 1254 |
{
|
| 1255 |
+
"epoch": 0.9623140036156307,
|
| 1256 |
+
"grad_norm": 0.1462660934588179,
|
| 1257 |
+
"learning_rate": 8.220136246701926e-07,
|
| 1258 |
+
"loss": 0.6665,
|
| 1259 |
"step": 865
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
+
"epoch": 0.9678765123070505,
|
| 1263 |
+
"grad_norm": 0.13216262862731915,
|
| 1264 |
+
"learning_rate": 5.920169059947411e-07,
|
| 1265 |
+
"loss": 0.666,
|
| 1266 |
"step": 870
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
+
"epoch": 0.9734390209984704,
|
| 1270 |
+
"grad_norm": 0.1497443816075182,
|
| 1271 |
+
"learning_rate": 3.9958875320580404e-07,
|
| 1272 |
+
"loss": 0.6902,
|
| 1273 |
"step": 875
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
+
"epoch": 0.9790015296898902,
|
| 1277 |
+
"grad_norm": 0.1329859440152703,
|
| 1278 |
+
"learning_rate": 2.448018893333681e-07,
|
| 1279 |
+
"loss": 0.6959,
|
| 1280 |
"step": 880
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
+
"epoch": 0.98456403838131,
|
| 1284 |
+
"grad_norm": 0.14839381526763562,
|
| 1285 |
+
"learning_rate": 1.277148118975835e-07,
|
| 1286 |
+
"loss": 0.6884,
|
| 1287 |
"step": 885
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 0.9901265470727298,
|
| 1291 |
+
"grad_norm": 0.14357565386768453,
|
| 1292 |
+
"learning_rate": 4.837177080119215e-08,
|
| 1293 |
+
"loss": 0.6961,
|
| 1294 |
"step": 890
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
+
"epoch": 0.9956890557641497,
|
| 1298 |
+
"grad_norm": 0.12423764687193309,
|
| 1299 |
+
"learning_rate": 6.8027516064606e-09,
|
| 1300 |
+
"loss": 0.6802,
|
| 1301 |
"step": 895
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
+
"epoch": 0.9990265609790016,
|
| 1305 |
+
"step": 898,
|
| 1306 |
+
"total_flos": 3899966689378304.0,
|
| 1307 |
+
"train_loss": 0.7223505903458542,
|
| 1308 |
+
"train_runtime": 18859.9671,
|
| 1309 |
+
"train_samples_per_second": 3.05,
|
| 1310 |
+
"train_steps_per_second": 0.048
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1311 |
}
|
| 1312 |
],
|
| 1313 |
"logging_steps": 5,
|
| 1314 |
+
"max_steps": 898,
|
| 1315 |
"num_input_tokens_seen": 0,
|
| 1316 |
"num_train_epochs": 1,
|
| 1317 |
"save_steps": 100,
|
| 1318 |
+
"total_flos": 3899966689378304.0,
|
| 1319 |
"train_batch_size": 2,
|
| 1320 |
"trial_name": null,
|
| 1321 |
"trial_params": null
|