Model save
Browse files- README.md +2 -4
- all_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +214 -214
README.md
CHANGED
|
@@ -1,11 +1,9 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
-
datasets: flyingbugs/OpenR1-Math-220k-pruned-keep-0.5-end-start-0.5
|
| 4 |
library_name: transformers
|
| 5 |
model_name: Qwen2.5-1.5B-Open-R1-Distill-eos-epic
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
-
- open-r1
|
| 9 |
- trl
|
| 10 |
- sft
|
| 11 |
licence: license
|
|
@@ -13,7 +11,7 @@ licence: license
|
|
| 13 |
|
| 14 |
# Model Card for Qwen2.5-1.5B-Open-R1-Distill-eos-epic
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct)
|
| 17 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 18 |
|
| 19 |
## Quick start
|
|
@@ -29,7 +27,7 @@ print(output["generated_text"])
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/
|
| 33 |
|
| 34 |
|
| 35 |
This model was trained with SFT.
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: Qwen2.5-1.5B-Open-R1-Distill-eos-epic
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
licence: license
|
|
|
|
| 11 |
|
| 12 |
# Model Card for Qwen2.5-1.5B-Open-R1-Distill-eos-epic
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jjh233/huggingface/runs/c9f8aax3)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 962656789856256.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 93733,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 962656789856256.0,
|
| 3 |
+
"train_loss": 0.5394951967578946,
|
| 4 |
+
"train_runtime": 11008.0222,
|
| 5 |
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 6.123,
|
| 7 |
+
"train_steps_per_second": 0.048
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"total_flos": 962656789856256.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 93733,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"total_flos": 962656789856256.0,
|
| 3 |
+
"train_loss": 0.5394951967578946,
|
| 4 |
+
"train_runtime": 11008.0222,
|
| 5 |
"train_samples": 93733,
|
| 6 |
+
"train_samples_per_second": 6.123,
|
| 7 |
+
"train_steps_per_second": 0.048
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -11,747 +11,747 @@
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.028409090909090908,
|
| 14 |
-
"grad_norm":
|
| 15 |
"learning_rate": 7.4074074074074075e-06,
|
| 16 |
-
"loss":
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.056818181818181816,
|
| 21 |
-
"grad_norm": 1.
|
| 22 |
"learning_rate": 1.6666666666666667e-05,
|
| 23 |
-
"loss":
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.08522727272727272,
|
| 28 |
-
"grad_norm": 0.
|
| 29 |
"learning_rate": 2.5925925925925925e-05,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 15
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.11363636363636363,
|
| 35 |
-
"grad_norm": 0.
|
| 36 |
"learning_rate": 3.518518518518519e-05,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.14204545454545456,
|
| 42 |
-
"grad_norm": 0.
|
| 43 |
"learning_rate": 4.4444444444444447e-05,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.17045454545454544,
|
| 49 |
-
"grad_norm": 0.
|
| 50 |
"learning_rate": 4.99982305792533e-05,
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 30
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.19886363636363635,
|
| 56 |
-
"grad_norm": 0.
|
| 57 |
"learning_rate": 4.997832779179051e-05,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 35
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.22727272727272727,
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
"learning_rate": 4.993633006948142e-05,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 40
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.2556818181818182,
|
| 70 |
-
"grad_norm": 0.
|
| 71 |
"learning_rate": 4.987227869373036e-05,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 45
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.2840909090909091,
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
"learning_rate": 4.9786236623445434e-05,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 50
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.3125,
|
| 84 |
-
"grad_norm": 0.
|
| 85 |
"learning_rate": 4.967828843315348e-05,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 55
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.3409090909090909,
|
| 91 |
-
"grad_norm": 0.
|
| 92 |
"learning_rate": 4.954854022986805e-05,
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 60
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.3693181818181818,
|
| 98 |
-
"grad_norm": 0.
|
| 99 |
"learning_rate": 4.939711954879211e-05,
|
| 100 |
-
"loss": 0.
|
| 101 |
"step": 65
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.3977272727272727,
|
| 105 |
-
"grad_norm": 0.
|
| 106 |
"learning_rate": 4.922417522795821e-05,
|
| 107 |
-
"loss": 0.
|
| 108 |
"step": 70
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.42613636363636365,
|
| 112 |
-
"grad_norm": 0.
|
| 113 |
"learning_rate": 4.902987726192893e-05,
|
| 114 |
-
"loss": 0.
|
| 115 |
"step": 75
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.45454545454545453,
|
| 119 |
-
"grad_norm": 0.
|
| 120 |
"learning_rate": 4.881441663470182e-05,
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 80
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.48295454545454547,
|
| 126 |
-
"grad_norm": 0.
|
| 127 |
"learning_rate": 4.857800513198288e-05,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 85
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.5113636363636364,
|
| 133 |
-
"grad_norm": 0.
|
| 134 |
"learning_rate": 4.832087513301302e-05,
|
| 135 |
-
"loss": 0.
|
| 136 |
"step": 90
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.5397727272727273,
|
| 140 |
-
"grad_norm": 0.
|
| 141 |
"learning_rate": 4.804327938215235e-05,
|
| 142 |
-
"loss": 0.
|
| 143 |
"step": 95
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.5681818181818182,
|
| 147 |
-
"grad_norm": 0.
|
| 148 |
"learning_rate": 4.7745490740446676e-05,
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 100
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.5965909090909091,
|
| 154 |
-
"grad_norm": 0.
|
| 155 |
"learning_rate": 4.742780191742036e-05,
|
| 156 |
-
"loss": 0.
|
| 157 |
"step": 105
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.625,
|
| 161 |
-
"grad_norm": 0.
|
| 162 |
"learning_rate": 4.7090525183359297e-05,
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 110
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.6534090909090909,
|
| 168 |
-
"grad_norm": 0.
|
| 169 |
"learning_rate": 4.6733992062366766e-05,
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 115
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.6818181818181818,
|
| 175 |
-
"grad_norm": 0.
|
| 176 |
"learning_rate": 4.635855300649382e-05,
|
| 177 |
-
"loss": 0.
|
| 178 |
"step": 120
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.7102272727272727,
|
| 182 |
-
"grad_norm": 0.
|
| 183 |
"learning_rate": 4.596457705126459e-05,
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 125
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.7386363636363636,
|
| 189 |
-
"grad_norm": 0.
|
| 190 |
"learning_rate": 4.555245145293509e-05,
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 130
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.7670454545454546,
|
| 196 |
-
"grad_norm": 0.
|
| 197 |
"learning_rate": 4.512258130784199e-05,
|
| 198 |
-
"loss": 0.
|
| 199 |
"step": 135
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.7954545454545454,
|
| 203 |
-
"grad_norm": 0.
|
| 204 |
"learning_rate": 4.4675389154215744e-05,
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 140
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.8238636363636364,
|
| 210 |
-
"grad_norm": 0.
|
| 211 |
"learning_rate": 4.4211314556849136e-05,
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 145
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.8522727272727273,
|
| 217 |
-
"grad_norm": 0.
|
| 218 |
"learning_rate": 4.373081367502981e-05,
|
| 219 |
-
"loss": 0.
|
| 220 |
"step": 150
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.8806818181818182,
|
| 224 |
-
"grad_norm": 0.
|
| 225 |
"learning_rate": 4.323435881416124e-05,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 155
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.9090909090909091,
|
| 231 |
-
"grad_norm": 0.
|
| 232 |
"learning_rate": 4.272243796151305e-05,
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 160
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.9375,
|
| 238 |
-
"grad_norm": 0.
|
| 239 |
"learning_rate": 4.219555430655693e-05,
|
| 240 |
-
"loss": 0.
|
| 241 |
"step": 165
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.9659090909090909,
|
| 245 |
-
"grad_norm": 0.
|
| 246 |
"learning_rate": 4.165422574635959e-05,
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 170
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.9943181818181818,
|
| 252 |
-
"grad_norm": 0.
|
| 253 |
"learning_rate": 4.1098984376519e-05,
|
| 254 |
-
"loss": 0.
|
| 255 |
"step": 175
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.0227272727272727,
|
| 259 |
-
"grad_norm": 0.
|
| 260 |
"learning_rate": 4.053037596814432e-05,
|
| 261 |
-
"loss": 0.
|
| 262 |
"step": 180
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.0511363636363635,
|
| 266 |
-
"grad_norm": 0.
|
| 267 |
"learning_rate": 3.9948959431393454e-05,
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 185
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0795454545454546,
|
| 273 |
-
"grad_norm": 0.
|
| 274 |
"learning_rate": 3.935530626609582e-05,
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 190
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.1079545454545454,
|
| 280 |
-
"grad_norm": 0.
|
| 281 |
"learning_rate": 3.875e-05,
|
| 282 |
-
"loss": 0.
|
| 283 |
"step": 195
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.1363636363636362,
|
| 287 |
-
"grad_norm": 0.
|
| 288 |
"learning_rate": 3.813363561519876e-05,
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 200
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.1647727272727273,
|
| 294 |
-
"grad_norm": 0.
|
| 295 |
"learning_rate": 3.750681896329504e-05,
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 205
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.1931818181818181,
|
| 301 |
-
"grad_norm": 0.
|
| 302 |
"learning_rate": 3.687016616988379e-05,
|
| 303 |
-
"loss": 0.
|
| 304 |
"step": 210
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.2215909090909092,
|
| 308 |
-
"grad_norm": 0.
|
| 309 |
"learning_rate": 3.6224303028935106e-05,
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 215
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.25,
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
"learning_rate": 3.556986438767389e-05,
|
| 317 |
-
"loss": 0.
|
| 318 |
"step": 220
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.2784090909090908,
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
"learning_rate": 3.490749352256063e-05,
|
| 324 |
-
"loss": 0.
|
| 325 |
"step": 225
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.3068181818181819,
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
"learning_rate": 3.4237841506986744e-05,
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 230
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.3352272727272727,
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
"learning_rate": 3.356156657130596e-05,
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 235
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.3636363636363638,
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
"learning_rate": 3.287933345583085e-05,
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 240
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.3920454545454546,
|
| 350 |
-
"grad_norm": 0.
|
| 351 |
"learning_rate": 3.219181275743034e-05,
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 245
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.4204545454545454,
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
"learning_rate": 3.1499680270370706e-05,
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 250
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.4488636363636362,
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
"learning_rate": 3.0803616322047654e-05,
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 255
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.4772727272727273,
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
"learning_rate": 3.0104305104262698e-05,
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 260
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.5056818181818183,
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
"learning_rate": 2.940243400070103e-05,
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 265
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.5340909090909092,
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
"learning_rate": 2.8698692911271897e-05,
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 270
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.5625,
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
"learning_rate": 2.7993773573975728e-05,
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 275
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.5909090909090908,
|
| 399 |
-
"grad_norm": 0.
|
| 400 |
"learning_rate": 2.7288368884964475e-05,
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 280
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.6193181818181817,
|
| 406 |
-
"grad_norm": 0.
|
| 407 |
"learning_rate": 2.658317221746361e-05,
|
| 408 |
-
"loss": 0.
|
| 409 |
"step": 285
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.6477272727272727,
|
| 413 |
-
"grad_norm": 0.
|
| 414 |
"learning_rate": 2.5878876740225116e-05,
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 290
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.6761363636363638,
|
| 420 |
-
"grad_norm": 0.
|
| 421 |
"learning_rate": 2.5176174736181536e-05,
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 295
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.7045454545454546,
|
| 427 |
-
"grad_norm": 0.
|
| 428 |
"learning_rate": 2.4475756921970653e-05,
|
| 429 |
-
"loss": 0.
|
| 430 |
"step": 300
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 1.7329545454545454,
|
| 434 |
-
"grad_norm": 0.
|
| 435 |
"learning_rate": 2.377831176899986e-05,
|
| 436 |
-
"loss": 0.
|
| 437 |
"step": 305
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.7613636363636362,
|
| 441 |
-
"grad_norm": 0.
|
| 442 |
"learning_rate": 2.3084524826717317e-05,
|
| 443 |
-
"loss": 0.
|
| 444 |
"step": 310
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.7897727272727273,
|
| 448 |
-
"grad_norm": 0.
|
| 449 |
"learning_rate": 2.23950780487554e-05,
|
| 450 |
-
"loss": 0.
|
| 451 |
"step": 315
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.8181818181818183,
|
| 455 |
-
"grad_norm": 0.
|
| 456 |
"learning_rate": 2.171064912260849e-05,
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 320
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.8465909090909092,
|
| 462 |
-
"grad_norm": 0.
|
| 463 |
"learning_rate": 2.103191080350419e-05,
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 325
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.875,
|
| 469 |
-
"grad_norm": 0.
|
| 470 |
"learning_rate": 2.0359530253122738e-05,
|
| 471 |
-
"loss": 0.
|
| 472 |
"step": 330
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.9034090909090908,
|
| 476 |
-
"grad_norm": 0.
|
| 477 |
"learning_rate": 1.9694168383814492e-05,
|
| 478 |
-
"loss": 0.
|
| 479 |
"step": 335
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.9318181818181817,
|
| 483 |
-
"grad_norm": 0.
|
| 484 |
"learning_rate": 1.9036479208960127e-05,
|
| 485 |
-
"loss": 0.
|
| 486 |
"step": 340
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.9602272727272727,
|
| 490 |
-
"grad_norm": 0.
|
| 491 |
"learning_rate": 1.838710920011227e-05,
|
| 492 |
-
"loss": 0.
|
| 493 |
"step": 345
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.9886363636363638,
|
| 497 |
-
"grad_norm": 0.
|
| 498 |
"learning_rate": 1.7746696651550143e-05,
|
| 499 |
-
"loss": 0.
|
| 500 |
"step": 350
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.0170454545454546,
|
| 504 |
-
"grad_norm": 0.
|
| 505 |
"learning_rate": 1.7115871052872204e-05,
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 355
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 2.0454545454545454,
|
| 511 |
-
"grad_norm": 0.
|
| 512 |
"learning_rate": 1.6495252470243134e-05,
|
| 513 |
-
"loss": 0.
|
| 514 |
"step": 360
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 2.0738636363636362,
|
| 518 |
-
"grad_norm": 0.
|
| 519 |
"learning_rate": 1.5885450936903586e-05,
|
| 520 |
-
"loss": 0.
|
| 521 |
"step": 365
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 2.102272727272727,
|
| 525 |
-
"grad_norm": 0.
|
| 526 |
"learning_rate": 1.528706585354177e-05,
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 370
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 2.1306818181818183,
|
| 532 |
-
"grad_norm": 0.
|
| 533 |
"learning_rate": 1.4700685399116238e-05,
|
| 534 |
-
"loss": 0.
|
| 535 |
"step": 375
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 2.159090909090909,
|
| 539 |
-
"grad_norm": 0.
|
| 540 |
"learning_rate": 1.412688595270887e-05,
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 380
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 2.1875,
|
| 546 |
-
"grad_norm": 0.
|
| 547 |
"learning_rate": 1.3566231526976714e-05,
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 385
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 2.215909090909091,
|
| 553 |
-
"grad_norm": 0.
|
| 554 |
"learning_rate": 1.3019273213759081e-05,
|
| 555 |
-
"loss": 0.
|
| 556 |
"step": 390
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 2.2443181818181817,
|
| 560 |
-
"grad_norm": 0.
|
| 561 |
"learning_rate": 1.2486548642385274e-05,
|
| 562 |
-
"loss": 0.
|
| 563 |
"step": 395
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 2.2727272727272725,
|
| 567 |
-
"grad_norm": 0.
|
| 568 |
"learning_rate": 1.1968581451215065e-05,
|
| 569 |
-
"loss": 0.
|
| 570 |
"step": 400
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 2.3011363636363638,
|
| 574 |
-
"grad_norm": 0.
|
| 575 |
"learning_rate": 1.1465880772931601e-05,
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 405
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 2.3295454545454546,
|
| 581 |
-
"grad_norm": 0.
|
| 582 |
"learning_rate": 1.0978940734092554e-05,
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 410
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 2.3579545454545454,
|
| 588 |
-
"grad_norm": 0.
|
| 589 |
"learning_rate": 1.050823996943144e-05,
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 415
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 2.3863636363636362,
|
| 595 |
-
"grad_norm": 0.
|
| 596 |
"learning_rate": 1.0054241151386492e-05,
|
| 597 |
-
"loss": 0.
|
| 598 |
"step": 420
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 2.4147727272727275,
|
| 602 |
-
"grad_norm": 0.
|
| 603 |
"learning_rate": 9.617390535319684e-06,
|
| 604 |
-
"loss": 0.
|
| 605 |
"step": 425
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 2.4431818181818183,
|
| 609 |
-
"grad_norm": 0.
|
| 610 |
"learning_rate": 9.198117520872698e-06,
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 430
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 2.471590909090909,
|
| 616 |
-
"grad_norm": 0.
|
| 617 |
"learning_rate": 8.796834229891206e-06,
|
| 618 |
-
"loss": 0.
|
| 619 |
"step": 435
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 2.5,
|
| 623 |
-
"grad_norm": 0.
|
| 624 |
"learning_rate": 8.413935101332198e-06,
|
| 625 |
-
"loss": 0.
|
| 626 |
"step": 440
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 2.528409090909091,
|
| 630 |
-
"grad_norm": 0.
|
| 631 |
"learning_rate": 8.049796503552626e-06,
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 445
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 2.5568181818181817,
|
| 637 |
-
"grad_norm": 0.
|
| 638 |
"learning_rate": 7.704776364360454e-06,
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 450
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 2.5852272727272725,
|
| 644 |
-
"grad_norm": 0.
|
| 645 |
"learning_rate": 7.379213819191676e-06,
|
| 646 |
-
"loss": 0.
|
| 647 |
"step": 455
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 2.6136363636363638,
|
| 651 |
-
"grad_norm": 0.
|
| 652 |
"learning_rate": 7.07342887775922e-06,
|
| 653 |
-
"loss": 0.
|
| 654 |
"step": 460
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 2.6420454545454546,
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
"learning_rate": 6.787722109501379e-06,
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 465
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 2.6704545454545454,
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
"learning_rate": 6.522374348138882e-06,
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 470
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 2.6988636363636362,
|
| 672 |
-
"grad_norm": 0.
|
| 673 |
"learning_rate": 6.277646415631148e-06,
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 475
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 2.7272727272727275,
|
| 679 |
-
"grad_norm": 0.
|
| 680 |
"learning_rate": 6.053778865802907e-06,
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 480
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 2.7556818181818183,
|
| 686 |
-
"grad_norm": 0.
|
| 687 |
"learning_rate": 5.850991747893292e-06,
|
| 688 |
-
"loss": 0.
|
| 689 |
"step": 485
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 2.784090909090909,
|
| 693 |
-
"grad_norm": 0.
|
| 694 |
"learning_rate": 5.669484390259793e-06,
|
| 695 |
-
"loss": 0.
|
| 696 |
"step": 490
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 2.8125,
|
| 700 |
-
"grad_norm": 0.
|
| 701 |
"learning_rate": 5.509435204449666e-06,
|
| 702 |
-
"loss": 0.
|
| 703 |
"step": 495
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 2.840909090909091,
|
| 707 |
-
"grad_norm": 0.
|
| 708 |
"learning_rate": 5.37100150983139e-06,
|
| 709 |
-
"loss": 0.
|
| 710 |
"step": 500
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 2.8693181818181817,
|
| 714 |
-
"grad_norm": 0.
|
| 715 |
"learning_rate": 5.254319378958563e-06,
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 505
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 2.8977272727272725,
|
| 721 |
-
"grad_norm": 0.
|
| 722 |
"learning_rate": 5.159503503818199e-06,
|
| 723 |
-
"loss": 0.
|
| 724 |
"step": 510
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"epoch": 2.9261363636363638,
|
| 728 |
-
"grad_norm": 0.
|
| 729 |
"learning_rate": 5.086647083094966e-06,
|
| 730 |
-
"loss": 0.
|
| 731 |
"step": 515
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 2.9545454545454546,
|
| 735 |
-
"grad_norm": 0.
|
| 736 |
"learning_rate": 5.03582173056209e-06,
|
| 737 |
-
"loss": 0.
|
| 738 |
"step": 520
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 2.9829545454545454,
|
| 742 |
-
"grad_norm": 0.
|
| 743 |
"learning_rate": 5.00707740468904e-06,
|
| 744 |
-
"loss": 0.
|
| 745 |
"step": 525
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 3.0,
|
| 749 |
"step": 528,
|
| 750 |
"total_flos": 962656789856256.0,
|
| 751 |
-
"train_loss": 0.
|
| 752 |
-
"train_runtime":
|
| 753 |
-
"train_samples_per_second":
|
| 754 |
-
"train_steps_per_second":
|
| 755 |
}
|
| 756 |
],
|
| 757 |
"logging_steps": 5,
|
|
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.028409090909090908,
|
| 14 |
+
"grad_norm": 10.896637192000782,
|
| 15 |
"learning_rate": 7.4074074074074075e-06,
|
| 16 |
+
"loss": 1.6734,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.056818181818181816,
|
| 21 |
+
"grad_norm": 1.5163857276357569,
|
| 22 |
"learning_rate": 1.6666666666666667e-05,
|
| 23 |
+
"loss": 1.2095,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.08522727272727272,
|
| 28 |
+
"grad_norm": 0.6030083388420293,
|
| 29 |
"learning_rate": 2.5925925925925925e-05,
|
| 30 |
+
"loss": 0.8954,
|
| 31 |
"step": 15
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.11363636363636363,
|
| 35 |
+
"grad_norm": 0.4146436929136456,
|
| 36 |
"learning_rate": 3.518518518518519e-05,
|
| 37 |
+
"loss": 0.7715,
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.14204545454545456,
|
| 42 |
+
"grad_norm": 0.2636145188710264,
|
| 43 |
"learning_rate": 4.4444444444444447e-05,
|
| 44 |
+
"loss": 0.7127,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.17045454545454544,
|
| 49 |
+
"grad_norm": 0.2023043123134589,
|
| 50 |
"learning_rate": 4.99982305792533e-05,
|
| 51 |
+
"loss": 0.6778,
|
| 52 |
"step": 30
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.19886363636363635,
|
| 56 |
+
"grad_norm": 0.16510970301238276,
|
| 57 |
"learning_rate": 4.997832779179051e-05,
|
| 58 |
+
"loss": 0.6409,
|
| 59 |
"step": 35
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.22727272727272727,
|
| 63 |
+
"grad_norm": 0.13082269602718508,
|
| 64 |
"learning_rate": 4.993633006948142e-05,
|
| 65 |
+
"loss": 0.6336,
|
| 66 |
"step": 40
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.2556818181818182,
|
| 70 |
+
"grad_norm": 0.14831898432802543,
|
| 71 |
"learning_rate": 4.987227869373036e-05,
|
| 72 |
+
"loss": 0.6166,
|
| 73 |
"step": 45
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.2840909090909091,
|
| 77 |
+
"grad_norm": 0.10897233346547917,
|
| 78 |
"learning_rate": 4.9786236623445434e-05,
|
| 79 |
+
"loss": 0.6118,
|
| 80 |
"step": 50
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.3125,
|
| 84 |
+
"grad_norm": 0.11184138744287996,
|
| 85 |
"learning_rate": 4.967828843315348e-05,
|
| 86 |
+
"loss": 0.5983,
|
| 87 |
"step": 55
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.3409090909090909,
|
| 91 |
+
"grad_norm": 0.11134807726458239,
|
| 92 |
"learning_rate": 4.954854022986805e-05,
|
| 93 |
+
"loss": 0.5891,
|
| 94 |
"step": 60
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.3693181818181818,
|
| 98 |
+
"grad_norm": 0.09921365604301072,
|
| 99 |
"learning_rate": 4.939711954879211e-05,
|
| 100 |
+
"loss": 0.5876,
|
| 101 |
"step": 65
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.3977272727272727,
|
| 105 |
+
"grad_norm": 0.1055432451773935,
|
| 106 |
"learning_rate": 4.922417522795821e-05,
|
| 107 |
+
"loss": 0.5801,
|
| 108 |
"step": 70
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.42613636363636365,
|
| 112 |
+
"grad_norm": 0.09914093623755263,
|
| 113 |
"learning_rate": 4.902987726192893e-05,
|
| 114 |
+
"loss": 0.5781,
|
| 115 |
"step": 75
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.45454545454545453,
|
| 119 |
+
"grad_norm": 0.08828127246038743,
|
| 120 |
"learning_rate": 4.881441663470182e-05,
|
| 121 |
+
"loss": 0.5649,
|
| 122 |
"step": 80
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.48295454545454547,
|
| 126 |
+
"grad_norm": 0.10055317591789738,
|
| 127 |
"learning_rate": 4.857800513198288e-05,
|
| 128 |
+
"loss": 0.5625,
|
| 129 |
"step": 85
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.5113636363636364,
|
| 133 |
+
"grad_norm": 0.08874927350125936,
|
| 134 |
"learning_rate": 4.832087513301302e-05,
|
| 135 |
+
"loss": 0.5631,
|
| 136 |
"step": 90
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.5397727272727273,
|
| 140 |
+
"grad_norm": 0.1118239441455913,
|
| 141 |
"learning_rate": 4.804327938215235e-05,
|
| 142 |
+
"loss": 0.5591,
|
| 143 |
"step": 95
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.5681818181818182,
|
| 147 |
+
"grad_norm": 0.09351012207556161,
|
| 148 |
"learning_rate": 4.7745490740446676e-05,
|
| 149 |
+
"loss": 0.5566,
|
| 150 |
"step": 100
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.5965909090909091,
|
| 154 |
+
"grad_norm": 0.10852517138960499,
|
| 155 |
"learning_rate": 4.742780191742036e-05,
|
| 156 |
+
"loss": 0.5607,
|
| 157 |
"step": 105
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.625,
|
| 161 |
+
"grad_norm": 0.11702640688817323,
|
| 162 |
"learning_rate": 4.7090525183359297e-05,
|
| 163 |
+
"loss": 0.5539,
|
| 164 |
"step": 110
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.6534090909090909,
|
| 168 |
+
"grad_norm": 0.09785419980049836,
|
| 169 |
"learning_rate": 4.6733992062366766e-05,
|
| 170 |
+
"loss": 0.5419,
|
| 171 |
"step": 115
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.6818181818181818,
|
| 175 |
+
"grad_norm": 0.10711167883214251,
|
| 176 |
"learning_rate": 4.635855300649382e-05,
|
| 177 |
+
"loss": 0.5445,
|
| 178 |
"step": 120
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.7102272727272727,
|
| 182 |
+
"grad_norm": 0.10796834846017456,
|
| 183 |
"learning_rate": 4.596457705126459e-05,
|
| 184 |
+
"loss": 0.5448,
|
| 185 |
"step": 125
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.7386363636363636,
|
| 189 |
+
"grad_norm": 0.11744855439211235,
|
| 190 |
"learning_rate": 4.555245145293509e-05,
|
| 191 |
+
"loss": 0.5411,
|
| 192 |
"step": 130
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.7670454545454546,
|
| 196 |
+
"grad_norm": 0.11356156360640139,
|
| 197 |
"learning_rate": 4.512258130784199e-05,
|
| 198 |
+
"loss": 0.5434,
|
| 199 |
"step": 135
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.7954545454545454,
|
| 203 |
+
"grad_norm": 0.12169855888778969,
|
| 204 |
"learning_rate": 4.4675389154215744e-05,
|
| 205 |
+
"loss": 0.5421,
|
| 206 |
"step": 140
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.8238636363636364,
|
| 210 |
+
"grad_norm": 0.10341006801601364,
|
| 211 |
"learning_rate": 4.4211314556849136e-05,
|
| 212 |
+
"loss": 0.5355,
|
| 213 |
"step": 145
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.8522727272727273,
|
| 217 |
+
"grad_norm": 0.10759924912275785,
|
| 218 |
"learning_rate": 4.373081367502981e-05,
|
| 219 |
+
"loss": 0.5326,
|
| 220 |
"step": 150
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.8806818181818182,
|
| 224 |
+
"grad_norm": 0.10861205860545389,
|
| 225 |
"learning_rate": 4.323435881416124e-05,
|
| 226 |
+
"loss": 0.537,
|
| 227 |
"step": 155
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.9090909090909091,
|
| 231 |
+
"grad_norm": 0.09957047692339929,
|
| 232 |
"learning_rate": 4.272243796151305e-05,
|
| 233 |
+
"loss": 0.533,
|
| 234 |
"step": 160
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.9375,
|
| 238 |
+
"grad_norm": 0.12359375999999637,
|
| 239 |
"learning_rate": 4.219555430655693e-05,
|
| 240 |
+
"loss": 0.5351,
|
| 241 |
"step": 165
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.9659090909090909,
|
| 245 |
+
"grad_norm": 0.09258501782228747,
|
| 246 |
"learning_rate": 4.165422574635959e-05,
|
| 247 |
+
"loss": 0.5317,
|
| 248 |
"step": 170
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.9943181818181818,
|
| 252 |
+
"grad_norm": 0.11203309080231412,
|
| 253 |
"learning_rate": 4.1098984376519e-05,
|
| 254 |
+
"loss": 0.5292,
|
| 255 |
"step": 175
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.0227272727272727,
|
| 259 |
+
"grad_norm": 0.08337277679519309,
|
| 260 |
"learning_rate": 4.053037596814432e-05,
|
| 261 |
+
"loss": 0.5205,
|
| 262 |
"step": 180
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 1.0511363636363635,
|
| 266 |
+
"grad_norm": 0.08922972769023695,
|
| 267 |
"learning_rate": 3.9948959431393454e-05,
|
| 268 |
+
"loss": 0.5107,
|
| 269 |
"step": 185
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0795454545454546,
|
| 273 |
+
"grad_norm": 0.09256444997193415,
|
| 274 |
"learning_rate": 3.935530626609582e-05,
|
| 275 |
+
"loss": 0.5091,
|
| 276 |
"step": 190
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.1079545454545454,
|
| 280 |
+
"grad_norm": 0.08761092083420882,
|
| 281 |
"learning_rate": 3.875e-05,
|
| 282 |
+
"loss": 0.5118,
|
| 283 |
"step": 195
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 1.1363636363636362,
|
| 287 |
+
"grad_norm": 0.09766222638240604,
|
| 288 |
"learning_rate": 3.813363561519876e-05,
|
| 289 |
+
"loss": 0.5086,
|
| 290 |
"step": 200
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.1647727272727273,
|
| 294 |
+
"grad_norm": 0.08469321954291688,
|
| 295 |
"learning_rate": 3.750681896329504e-05,
|
| 296 |
+
"loss": 0.5106,
|
| 297 |
"step": 205
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.1931818181818181,
|
| 301 |
+
"grad_norm": 0.0961560094422636,
|
| 302 |
"learning_rate": 3.687016616988379e-05,
|
| 303 |
+
"loss": 0.51,
|
| 304 |
"step": 210
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.2215909090909092,
|
| 308 |
+
"grad_norm": 0.0862194194928744,
|
| 309 |
"learning_rate": 3.6224303028935106e-05,
|
| 310 |
+
"loss": 0.5103,
|
| 311 |
"step": 215
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 1.25,
|
| 315 |
+
"grad_norm": 0.07956278803606433,
|
| 316 |
"learning_rate": 3.556986438767389e-05,
|
| 317 |
+
"loss": 0.5037,
|
| 318 |
"step": 220
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 1.2784090909090908,
|
| 322 |
+
"grad_norm": 0.0903181198584574,
|
| 323 |
"learning_rate": 3.490749352256063e-05,
|
| 324 |
+
"loss": 0.509,
|
| 325 |
"step": 225
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.3068181818181819,
|
| 329 |
+
"grad_norm": 0.0944984329203277,
|
| 330 |
"learning_rate": 3.4237841506986744e-05,
|
| 331 |
+
"loss": 0.5027,
|
| 332 |
"step": 230
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.3352272727272727,
|
| 336 |
+
"grad_norm": 0.08882033124741437,
|
| 337 |
"learning_rate": 3.356156657130596e-05,
|
| 338 |
+
"loss": 0.4961,
|
| 339 |
"step": 235
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.3636363636363638,
|
| 343 |
+
"grad_norm": 0.09550461777333721,
|
| 344 |
"learning_rate": 3.287933345583085e-05,
|
| 345 |
+
"loss": 0.5069,
|
| 346 |
"step": 240
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.3920454545454546,
|
| 350 |
+
"grad_norm": 0.08946536218539883,
|
| 351 |
"learning_rate": 3.219181275743034e-05,
|
| 352 |
+
"loss": 0.5086,
|
| 353 |
"step": 245
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.4204545454545454,
|
| 357 |
+
"grad_norm": 0.09325584287334789,
|
| 358 |
"learning_rate": 3.1499680270370706e-05,
|
| 359 |
+
"loss": 0.5044,
|
| 360 |
"step": 250
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.4488636363636362,
|
| 364 |
+
"grad_norm": 0.08223842512135068,
|
| 365 |
"learning_rate": 3.0803616322047654e-05,
|
| 366 |
+
"loss": 0.5052,
|
| 367 |
"step": 255
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.4772727272727273,
|
| 371 |
+
"grad_norm": 0.08270798846301625,
|
| 372 |
"learning_rate": 3.0104305104262698e-05,
|
| 373 |
+
"loss": 0.4985,
|
| 374 |
"step": 260
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.5056818181818183,
|
| 378 |
+
"grad_norm": 0.08262838460793459,
|
| 379 |
"learning_rate": 2.940243400070103e-05,
|
| 380 |
+
"loss": 0.4994,
|
| 381 |
"step": 265
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.5340909090909092,
|
| 385 |
+
"grad_norm": 0.09058860519349171,
|
| 386 |
"learning_rate": 2.8698692911271897e-05,
|
| 387 |
+
"loss": 0.5023,
|
| 388 |
"step": 270
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.5625,
|
| 392 |
+
"grad_norm": 0.09371800013120092,
|
| 393 |
"learning_rate": 2.7993773573975728e-05,
|
| 394 |
+
"loss": 0.4992,
|
| 395 |
"step": 275
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.5909090909090908,
|
| 399 |
+
"grad_norm": 0.08456948817551574,
|
| 400 |
"learning_rate": 2.7288368884964475e-05,
|
| 401 |
+
"loss": 0.503,
|
| 402 |
"step": 280
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 1.6193181818181817,
|
| 406 |
+
"grad_norm": 0.09101003159864386,
|
| 407 |
"learning_rate": 2.658317221746361e-05,
|
| 408 |
+
"loss": 0.4954,
|
| 409 |
"step": 285
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 1.6477272727272727,
|
| 413 |
+
"grad_norm": 0.08160457721074796,
|
| 414 |
"learning_rate": 2.5878876740225116e-05,
|
| 415 |
+
"loss": 0.4986,
|
| 416 |
"step": 290
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 1.6761363636363638,
|
| 420 |
+
"grad_norm": 0.08078176783826871,
|
| 421 |
"learning_rate": 2.5176174736181536e-05,
|
| 422 |
+
"loss": 0.4971,
|
| 423 |
"step": 295
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 1.7045454545454546,
|
| 427 |
+
"grad_norm": 0.08864892274469409,
|
| 428 |
"learning_rate": 2.4475756921970653e-05,
|
| 429 |
+
"loss": 0.4988,
|
| 430 |
"step": 300
|
| 431 |
},
|
| 432 |
{
|
| 433 |
"epoch": 1.7329545454545454,
|
| 434 |
+
"grad_norm": 0.09144520680898066,
|
| 435 |
"learning_rate": 2.377831176899986e-05,
|
| 436 |
+
"loss": 0.4987,
|
| 437 |
"step": 305
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.7613636363636362,
|
| 441 |
+
"grad_norm": 0.0913519780551606,
|
| 442 |
"learning_rate": 2.3084524826717317e-05,
|
| 443 |
+
"loss": 0.4962,
|
| 444 |
"step": 310
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 1.7897727272727273,
|
| 448 |
+
"grad_norm": 0.08330604163992984,
|
| 449 |
"learning_rate": 2.23950780487554e-05,
|
| 450 |
+
"loss": 0.5021,
|
| 451 |
"step": 315
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 1.8181818181818183,
|
| 455 |
+
"grad_norm": 0.08280936051442833,
|
| 456 |
"learning_rate": 2.171064912260849e-05,
|
| 457 |
+
"loss": 0.4983,
|
| 458 |
"step": 320
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 1.8465909090909092,
|
| 462 |
+
"grad_norm": 0.07571686269473353,
|
| 463 |
"learning_rate": 2.103191080350419e-05,
|
| 464 |
+
"loss": 0.499,
|
| 465 |
"step": 325
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.875,
|
| 469 |
+
"grad_norm": 0.08525336953750823,
|
| 470 |
"learning_rate": 2.0359530253122738e-05,
|
| 471 |
+
"loss": 0.4923,
|
| 472 |
"step": 330
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.9034090909090908,
|
| 476 |
+
"grad_norm": 0.10358699532249785,
|
| 477 |
"learning_rate": 1.9694168383814492e-05,
|
| 478 |
+
"loss": 0.5043,
|
| 479 |
"step": 335
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.9318181818181817,
|
| 483 |
+
"grad_norm": 0.08301020877209554,
|
| 484 |
"learning_rate": 1.9036479208960127e-05,
|
| 485 |
+
"loss": 0.4946,
|
| 486 |
"step": 340
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.9602272727272727,
|
| 490 |
+
"grad_norm": 0.08553632563551307,
|
| 491 |
"learning_rate": 1.838710920011227e-05,
|
| 492 |
+
"loss": 0.4969,
|
| 493 |
"step": 345
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.9886363636363638,
|
| 497 |
+
"grad_norm": 0.08303295503235186,
|
| 498 |
"learning_rate": 1.7746696651550143e-05,
|
| 499 |
+
"loss": 0.4997,
|
| 500 |
"step": 350
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 2.0170454545454546,
|
| 504 |
+
"grad_norm": 0.08033143740448973,
|
| 505 |
"learning_rate": 1.7115871052872204e-05,
|
| 506 |
+
"loss": 0.4867,
|
| 507 |
"step": 355
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 2.0454545454545454,
|
| 511 |
+
"grad_norm": 0.08063264186240293,
|
| 512 |
"learning_rate": 1.6495252470243134e-05,
|
| 513 |
+
"loss": 0.487,
|
| 514 |
"step": 360
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 2.0738636363636362,
|
| 518 |
+
"grad_norm": 0.07841584895617655,
|
| 519 |
"learning_rate": 1.5885450936903586e-05,
|
| 520 |
+
"loss": 0.4837,
|
| 521 |
"step": 365
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 2.102272727272727,
|
| 525 |
+
"grad_norm": 0.07460661702402475,
|
| 526 |
"learning_rate": 1.528706585354177e-05,
|
| 527 |
+
"loss": 0.4788,
|
| 528 |
"step": 370
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 2.1306818181818183,
|
| 532 |
+
"grad_norm": 0.08030048639361652,
|
| 533 |
"learning_rate": 1.4700685399116238e-05,
|
| 534 |
+
"loss": 0.4803,
|
| 535 |
"step": 375
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 2.159090909090909,
|
| 539 |
+
"grad_norm": 0.07655857860636041,
|
| 540 |
"learning_rate": 1.412688595270887e-05,
|
| 541 |
+
"loss": 0.4782,
|
| 542 |
"step": 380
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 2.1875,
|
| 546 |
+
"grad_norm": 0.0741239677057519,
|
| 547 |
"learning_rate": 1.3566231526976714e-05,
|
| 548 |
+
"loss": 0.4833,
|
| 549 |
"step": 385
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 2.215909090909091,
|
| 553 |
+
"grad_norm": 0.07552080480637674,
|
| 554 |
"learning_rate": 1.3019273213759081e-05,
|
| 555 |
+
"loss": 0.4817,
|
| 556 |
"step": 390
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 2.2443181818181817,
|
| 560 |
+
"grad_norm": 0.087506481602976,
|
| 561 |
"learning_rate": 1.2486548642385274e-05,
|
| 562 |
+
"loss": 0.4855,
|
| 563 |
"step": 395
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 2.2727272727272725,
|
| 567 |
+
"grad_norm": 0.07825929401017973,
|
| 568 |
"learning_rate": 1.1968581451215065e-05,
|
| 569 |
+
"loss": 0.4783,
|
| 570 |
"step": 400
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 2.3011363636363638,
|
| 574 |
+
"grad_norm": 0.07347633398325569,
|
| 575 |
"learning_rate": 1.1465880772931601e-05,
|
| 576 |
+
"loss": 0.484,
|
| 577 |
"step": 405
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 2.3295454545454546,
|
| 581 |
+
"grad_norm": 0.07075822069959536,
|
| 582 |
"learning_rate": 1.0978940734092554e-05,
|
| 583 |
+
"loss": 0.478,
|
| 584 |
"step": 410
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 2.3579545454545454,
|
| 588 |
+
"grad_norm": 0.07267042198965988,
|
| 589 |
"learning_rate": 1.050823996943144e-05,
|
| 590 |
+
"loss": 0.4783,
|
| 591 |
"step": 415
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 2.3863636363636362,
|
| 595 |
+
"grad_norm": 0.07341626200460101,
|
| 596 |
"learning_rate": 1.0054241151386492e-05,
|
| 597 |
+
"loss": 0.4756,
|
| 598 |
"step": 420
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 2.4147727272727275,
|
| 602 |
+
"grad_norm": 0.0706063205931748,
|
| 603 |
"learning_rate": 9.617390535319684e-06,
|
| 604 |
+
"loss": 0.4772,
|
| 605 |
"step": 425
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 2.4431818181818183,
|
| 609 |
+
"grad_norm": 0.06987948971233222,
|
| 610 |
"learning_rate": 9.198117520872698e-06,
|
| 611 |
+
"loss": 0.477,
|
| 612 |
"step": 430
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 2.471590909090909,
|
| 616 |
+
"grad_norm": 0.07780450930302736,
|
| 617 |
"learning_rate": 8.796834229891206e-06,
|
| 618 |
+
"loss": 0.4819,
|
| 619 |
"step": 435
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 2.5,
|
| 623 |
+
"grad_norm": 0.07385728736608703,
|
| 624 |
"learning_rate": 8.413935101332198e-06,
|
| 625 |
+
"loss": 0.476,
|
| 626 |
"step": 440
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 2.528409090909091,
|
| 630 |
+
"grad_norm": 0.06912845080364564,
|
| 631 |
"learning_rate": 8.049796503552626e-06,
|
| 632 |
+
"loss": 0.4776,
|
| 633 |
"step": 445
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 2.5568181818181817,
|
| 637 |
+
"grad_norm": 0.07115097048034667,
|
| 638 |
"learning_rate": 7.704776364360454e-06,
|
| 639 |
+
"loss": 0.4806,
|
| 640 |
"step": 450
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 2.5852272727272725,
|
| 644 |
+
"grad_norm": 0.0719603929691263,
|
| 645 |
"learning_rate": 7.379213819191676e-06,
|
| 646 |
+
"loss": 0.4805,
|
| 647 |
"step": 455
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 2.6136363636363638,
|
| 651 |
+
"grad_norm": 0.06733281311431526,
|
| 652 |
"learning_rate": 7.07342887775922e-06,
|
| 653 |
+
"loss": 0.4771,
|
| 654 |
"step": 460
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 2.6420454545454546,
|
| 658 |
+
"grad_norm": 0.06812256929077086,
|
| 659 |
"learning_rate": 6.787722109501379e-06,
|
| 660 |
+
"loss": 0.4769,
|
| 661 |
"step": 465
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 2.6704545454545454,
|
| 665 |
+
"grad_norm": 0.06945313043383605,
|
| 666 |
"learning_rate": 6.522374348138882e-06,
|
| 667 |
+
"loss": 0.4791,
|
| 668 |
"step": 470
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 2.6988636363636362,
|
| 672 |
+
"grad_norm": 0.07082851639261782,
|
| 673 |
"learning_rate": 6.277646415631148e-06,
|
| 674 |
+
"loss": 0.4785,
|
| 675 |
"step": 475
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 2.7272727272727275,
|
| 679 |
+
"grad_norm": 0.07019381014525443,
|
| 680 |
"learning_rate": 6.053778865802907e-06,
|
| 681 |
+
"loss": 0.4787,
|
| 682 |
"step": 480
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 2.7556818181818183,
|
| 686 |
+
"grad_norm": 0.06814585572621572,
|
| 687 |
"learning_rate": 5.850991747893292e-06,
|
| 688 |
+
"loss": 0.4788,
|
| 689 |
"step": 485
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 2.784090909090909,
|
| 693 |
+
"grad_norm": 0.06724675412918013,
|
| 694 |
"learning_rate": 5.669484390259793e-06,
|
| 695 |
+
"loss": 0.4744,
|
| 696 |
"step": 490
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 2.8125,
|
| 700 |
+
"grad_norm": 0.06951904971525688,
|
| 701 |
"learning_rate": 5.509435204449666e-06,
|
| 702 |
+
"loss": 0.4852,
|
| 703 |
"step": 495
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 2.840909090909091,
|
| 707 |
+
"grad_norm": 0.06771580623936355,
|
| 708 |
"learning_rate": 5.37100150983139e-06,
|
| 709 |
+
"loss": 0.4748,
|
| 710 |
"step": 500
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 2.8693181818181817,
|
| 714 |
+
"grad_norm": 0.06692159909264785,
|
| 715 |
"learning_rate": 5.254319378958563e-06,
|
| 716 |
+
"loss": 0.475,
|
| 717 |
"step": 505
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 2.8977272727272725,
|
| 721 |
+
"grad_norm": 0.06940269513307211,
|
| 722 |
"learning_rate": 5.159503503818199e-06,
|
| 723 |
+
"loss": 0.4809,
|
| 724 |
"step": 510
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"epoch": 2.9261363636363638,
|
| 728 |
+
"grad_norm": 0.06707771857169355,
|
| 729 |
"learning_rate": 5.086647083094966e-06,
|
| 730 |
+
"loss": 0.4793,
|
| 731 |
"step": 515
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 2.9545454545454546,
|
| 735 |
+
"grad_norm": 0.06794955106454185,
|
| 736 |
"learning_rate": 5.03582173056209e-06,
|
| 737 |
+
"loss": 0.4781,
|
| 738 |
"step": 520
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 2.9829545454545454,
|
| 742 |
+
"grad_norm": 0.06951889463364248,
|
| 743 |
"learning_rate": 5.00707740468904e-06,
|
| 744 |
+
"loss": 0.4807,
|
| 745 |
"step": 525
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 3.0,
|
| 749 |
"step": 528,
|
| 750 |
"total_flos": 962656789856256.0,
|
| 751 |
+
"train_loss": 0.5394951967578946,
|
| 752 |
+
"train_runtime": 11008.0222,
|
| 753 |
+
"train_samples_per_second": 6.123,
|
| 754 |
+
"train_steps_per_second": 0.048
|
| 755 |
}
|
| 756 |
],
|
| 757 |
"logging_steps": 5,
|