Commit
•
bbec0ad
1
Parent(s):
ffc93e8
Update fine-tuned model
Browse files- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +405 -580
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -25,9 +25,9 @@
|
|
| 25 |
"target_modules": [
|
| 26 |
"down_proj",
|
| 27 |
"q_proj",
|
| 28 |
-
"gate_proj",
|
| 29 |
"o_proj",
|
| 30 |
"v_proj",
|
|
|
|
| 31 |
"k_proj",
|
| 32 |
"up_proj"
|
| 33 |
],
|
|
|
|
| 25 |
"target_modules": [
|
| 26 |
"down_proj",
|
| 27 |
"q_proj",
|
|
|
|
| 28 |
"o_proj",
|
| 29 |
"v_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
"k_proj",
|
| 32 |
"up_proj"
|
| 33 |
],
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46b069f85021f94bb703ed2c05b02548318eb279ca561a433a0a356bc2eb9683
|
| 3 |
size 159967880
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 852876198
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46f2dc32ee8401c325cca6893ca68b7e41370a6a8d26a91e4244634adbe16ac6
|
| 3 |
size 852876198
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718f79f5f61a114f9fd5e603c23b7c7433ef040e8243bd2750c219dc632bb60a
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,893 +1,718 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 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": 1.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 0.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 0.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 0.
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate": 0.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate": 0.
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 0.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate": 0.
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch":
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate": 0.
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate": 0.
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch":
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate": 0.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate": 0.
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate": 0.
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch":
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate": 0.
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate": 0.
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate": 0.
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch":
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate": 0.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 41
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 42
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
-
"learning_rate": 0.
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 43
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch":
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate": 0.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 44
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch":
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate": 0.
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 45
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate": 0.
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 46
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch":
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate": 0.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 47
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch":
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 48
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate": 0.
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 49
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch":
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
-
"learning_rate": 0.
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 50
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch":
|
| 363 |
-
"grad_norm": 0.
|
| 364 |
-
"learning_rate": 0.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 51
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch":
|
| 370 |
-
"grad_norm": 0.
|
| 371 |
-
"learning_rate": 0.
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 52
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch":
|
| 377 |
-
"grad_norm": 0.
|
| 378 |
-
"learning_rate":
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 53
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch":
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
-
"learning_rate":
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 54
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch":
|
| 391 |
-
"grad_norm": 0.
|
| 392 |
-
"learning_rate":
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 55
|
| 395 |
},
|
| 396 |
{
|
| 397 |
-
"epoch":
|
| 398 |
-
"grad_norm": 0.
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 56
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch":
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
-
"learning_rate":
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 57
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch":
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
-
"learning_rate":
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 58
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch":
|
| 419 |
-
"grad_norm": 0.
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 59
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch": 2
|
| 426 |
-
"grad_norm": 0.
|
| 427 |
-
"learning_rate":
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 60
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"grad_norm": 0.
|
| 434 |
-
"learning_rate":
|
| 435 |
-
"loss": 0.
|
| 436 |
"step": 61
|
| 437 |
},
|
| 438 |
{
|
| 439 |
-
"epoch":
|
| 440 |
-
"grad_norm": 0.
|
| 441 |
-
"learning_rate":
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 62
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch":
|
| 447 |
-
"grad_norm": 0.
|
| 448 |
-
"learning_rate":
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 63
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch":
|
| 454 |
-
"grad_norm": 0.
|
| 455 |
-
"learning_rate":
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 64
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch":
|
| 461 |
-
"grad_norm": 0.
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 65
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch":
|
| 468 |
-
"grad_norm": 0.
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 66
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch":
|
| 475 |
-
"grad_norm": 0.
|
| 476 |
-
"learning_rate":
|
| 477 |
-
"loss": 0.
|
| 478 |
"step": 67
|
| 479 |
},
|
| 480 |
{
|
| 481 |
-
"epoch":
|
| 482 |
-
"grad_norm": 0.
|
| 483 |
-
"learning_rate":
|
| 484 |
-
"loss": 0.
|
| 485 |
"step": 68
|
| 486 |
},
|
| 487 |
{
|
| 488 |
-
"epoch":
|
| 489 |
-
"grad_norm": 0.
|
| 490 |
-
"learning_rate":
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 69
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"epoch":
|
| 496 |
-
"grad_norm": 0.
|
| 497 |
-
"learning_rate":
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 70
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch":
|
| 503 |
-
"grad_norm": 0.
|
| 504 |
-
"learning_rate":
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 71
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch":
|
| 510 |
-
"grad_norm": 0.
|
| 511 |
-
"learning_rate":
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 72
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch":
|
| 517 |
-
"grad_norm": 0.
|
| 518 |
-
"learning_rate":
|
| 519 |
-
"loss": 0.
|
| 520 |
"step": 73
|
| 521 |
},
|
| 522 |
{
|
| 523 |
-
"epoch":
|
| 524 |
-
"grad_norm": 0.
|
| 525 |
-
"learning_rate":
|
| 526 |
-
"loss": 0.
|
| 527 |
"step": 74
|
| 528 |
},
|
| 529 |
{
|
| 530 |
-
"epoch":
|
| 531 |
-
"grad_norm": 0.
|
| 532 |
-
"learning_rate":
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 75
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"epoch":
|
| 538 |
-
"grad_norm": 0.
|
| 539 |
-
"learning_rate":
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 76
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch":
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
-
"learning_rate":
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 77
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch":
|
| 552 |
-
"grad_norm": 0.
|
| 553 |
-
"learning_rate":
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 78
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch":
|
| 559 |
-
"grad_norm": 0.
|
| 560 |
-
"learning_rate":
|
| 561 |
-
"loss": 0.
|
| 562 |
"step": 79
|
| 563 |
},
|
| 564 |
{
|
| 565 |
-
"epoch":
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
-
"learning_rate":
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 80
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch":
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 81
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch":
|
| 580 |
-
"grad_norm": 0.
|
| 581 |
-
"learning_rate":
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 82
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch":
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 83
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch":
|
| 594 |
-
"grad_norm": 0.
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 84
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 85
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch":
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 86
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 87
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch":
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 88
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch":
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 89
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch":
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 90
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 91
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch":
|
| 650 |
-
"grad_norm": 0.
|
| 651 |
-
"learning_rate": 3.
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 92
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch":
|
| 657 |
-
"grad_norm": 0.
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 93
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch":
|
| 664 |
-
"grad_norm": 0.
|
| 665 |
-
"learning_rate":
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 94
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch":
|
| 671 |
-
"grad_norm": 0.
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 95
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch":
|
| 678 |
-
"grad_norm": 0.
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 96
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch":
|
| 685 |
-
"grad_norm": 0.
|
| 686 |
-
"learning_rate":
|
| 687 |
-
"loss": 0.
|
| 688 |
"step": 97
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch":
|
| 692 |
-
"grad_norm": 0.
|
| 693 |
-
"learning_rate": 2.
|
| 694 |
-
"loss": 0.
|
| 695 |
"step": 98
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch":
|
| 699 |
-
"grad_norm": 0.
|
| 700 |
-
"learning_rate":
|
| 701 |
-
"loss": 0.
|
| 702 |
"step": 99
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch":
|
| 706 |
-
"grad_norm": 0.
|
| 707 |
-
"learning_rate": 2.1344844419735755e-05,
|
| 708 |
-
"loss": 0.1867,
|
| 709 |
-
"step": 100
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"epoch": 4.04,
|
| 713 |
-
"grad_norm": 0.2711721360683441,
|
| 714 |
-
"learning_rate": 1.9728836206903656e-05,
|
| 715 |
-
"loss": 0.1657,
|
| 716 |
-
"step": 101
|
| 717 |
-
},
|
| 718 |
-
{
|
| 719 |
-
"epoch": 4.08,
|
| 720 |
-
"grad_norm": 0.2831830382347107,
|
| 721 |
-
"learning_rate": 1.8169722409183097e-05,
|
| 722 |
-
"loss": 0.1692,
|
| 723 |
-
"step": 102
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 4.12,
|
| 727 |
-
"grad_norm": 0.272053599357605,
|
| 728 |
-
"learning_rate": 1.6668608091748495e-05,
|
| 729 |
-
"loss": 0.1679,
|
| 730 |
-
"step": 103
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 4.16,
|
| 734 |
-
"grad_norm": 0.27920499444007874,
|
| 735 |
-
"learning_rate": 1.522655721103291e-05,
|
| 736 |
-
"loss": 0.1843,
|
| 737 |
-
"step": 104
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 4.2,
|
| 741 |
-
"grad_norm": 0.2759131193161011,
|
| 742 |
-
"learning_rate": 1.3844591860619383e-05,
|
| 743 |
-
"loss": 0.1626,
|
| 744 |
-
"step": 105
|
| 745 |
-
},
|
| 746 |
-
{
|
| 747 |
-
"epoch": 4.24,
|
| 748 |
-
"grad_norm": 0.2894749343395233,
|
| 749 |
-
"learning_rate": 1.2523691546803873e-05,
|
| 750 |
-
"loss": 0.1762,
|
| 751 |
-
"step": 106
|
| 752 |
-
},
|
| 753 |
-
{
|
| 754 |
-
"epoch": 4.28,
|
| 755 |
-
"grad_norm": 0.2730141580104828,
|
| 756 |
-
"learning_rate": 1.1264792494342857e-05,
|
| 757 |
-
"loss": 0.1703,
|
| 758 |
-
"step": 107
|
| 759 |
-
},
|
| 760 |
-
{
|
| 761 |
-
"epoch": 4.32,
|
| 762 |
-
"grad_norm": 0.26933005452156067,
|
| 763 |
-
"learning_rate": 1.0068786982878087e-05,
|
| 764 |
-
"loss": 0.163,
|
| 765 |
-
"step": 108
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"epoch": 4.36,
|
| 769 |
-
"grad_norm": 0.2708563506603241,
|
| 770 |
-
"learning_rate": 8.936522714508678e-06,
|
| 771 |
-
"loss": 0.1679,
|
| 772 |
-
"step": 109
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"epoch": 4.4,
|
| 776 |
-
"grad_norm": 0.26494595408439636,
|
| 777 |
-
"learning_rate": 7.868802212958703e-06,
|
| 778 |
-
"loss": 0.1611,
|
| 779 |
-
"step": 110
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 4.44,
|
| 783 |
-
"grad_norm": 0.2679324746131897,
|
| 784 |
-
"learning_rate": 6.866382254766157e-06,
|
| 785 |
-
"loss": 0.1646,
|
| 786 |
-
"step": 111
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 4.48,
|
| 790 |
-
"grad_norm": 0.26407480239868164,
|
| 791 |
-
"learning_rate": 5.929973332896677e-06,
|
| 792 |
-
"loss": 0.1616,
|
| 793 |
-
"step": 112
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 4.52,
|
| 797 |
-
"grad_norm": 0.28398773074150085,
|
| 798 |
-
"learning_rate": 5.060239153161872e-06,
|
| 799 |
-
"loss": 0.1795,
|
| 800 |
-
"step": 113
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 4.5600000000000005,
|
| 804 |
-
"grad_norm": 0.26915472745895386,
|
| 805 |
-
"learning_rate": 4.257796163799455e-06,
|
| 806 |
-
"loss": 0.1616,
|
| 807 |
-
"step": 114
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 4.6,
|
| 811 |
-
"grad_norm": 0.2760821282863617,
|
| 812 |
-
"learning_rate": 3.5232131185484076e-06,
|
| 813 |
-
"loss": 0.1535,
|
| 814 |
-
"step": 115
|
| 815 |
-
},
|
| 816 |
-
{
|
| 817 |
-
"epoch": 4.64,
|
| 818 |
-
"grad_norm": 0.2624204754829407,
|
| 819 |
-
"learning_rate": 2.857010673529015e-06,
|
| 820 |
-
"loss": 0.1697,
|
| 821 |
-
"step": 116
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 4.68,
|
| 825 |
-
"grad_norm": 0.2621574103832245,
|
| 826 |
-
"learning_rate": 2.259661018213333e-06,
|
| 827 |
-
"loss": 0.1627,
|
| 828 |
-
"step": 117
|
| 829 |
-
},
|
| 830 |
-
{
|
| 831 |
-
"epoch": 4.72,
|
| 832 |
-
"grad_norm": 0.2760251760482788,
|
| 833 |
-
"learning_rate": 1.7315875407479032e-06,
|
| 834 |
-
"loss": 0.1747,
|
| 835 |
-
"step": 118
|
| 836 |
-
},
|
| 837 |
-
{
|
| 838 |
-
"epoch": 4.76,
|
| 839 |
-
"grad_norm": 0.26422515511512756,
|
| 840 |
-
"learning_rate": 1.2731645278655445e-06,
|
| 841 |
-
"loss": 0.1653,
|
| 842 |
-
"step": 119
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 4.8,
|
| 846 |
-
"grad_norm": 0.2870921790599823,
|
| 847 |
-
"learning_rate": 8.847168995992916e-07,
|
| 848 |
-
"loss": 0.1699,
|
| 849 |
-
"step": 120
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"epoch": 4.84,
|
| 853 |
-
"grad_norm": 0.2736106812953949,
|
| 854 |
-
"learning_rate": 5.665199789862907e-07,
|
| 855 |
-
"loss": 0.1688,
|
| 856 |
-
"step": 121
|
| 857 |
-
},
|
| 858 |
-
{
|
| 859 |
-
"epoch": 4.88,
|
| 860 |
-
"grad_norm": 0.27442148327827454,
|
| 861 |
-
"learning_rate": 3.1879929692498757e-07,
|
| 862 |
-
"loss": 0.1722,
|
| 863 |
-
"step": 122
|
| 864 |
-
},
|
| 865 |
-
{
|
| 866 |
-
"epoch": 4.92,
|
| 867 |
-
"grad_norm": 0.26734665036201477,
|
| 868 |
-
"learning_rate": 1.4173043232380557e-07,
|
| 869 |
-
"loss": 0.1634,
|
| 870 |
-
"step": 123
|
| 871 |
-
},
|
| 872 |
-
{
|
| 873 |
-
"epoch": 4.96,
|
| 874 |
-
"grad_norm": 0.263090580701828,
|
| 875 |
-
"learning_rate": 3.5438887654737355e-08,
|
| 876 |
-
"loss": 0.1631,
|
| 877 |
-
"step": 124
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"epoch": 5.0,
|
| 881 |
-
"grad_norm": 0.2877998650074005,
|
| 882 |
"learning_rate": 0.0,
|
| 883 |
-
"loss": 0.
|
| 884 |
-
"step":
|
| 885 |
}
|
| 886 |
],
|
| 887 |
"logging_steps": 1,
|
| 888 |
-
"max_steps":
|
| 889 |
"num_input_tokens_seen": 0,
|
| 890 |
-
"num_train_epochs":
|
| 891 |
"save_steps": 500,
|
| 892 |
"stateful_callbacks": {
|
| 893 |
"TrainerControl": {
|
|
@@ -901,7 +726,7 @@
|
|
| 901 |
"attributes": {}
|
| 902 |
}
|
| 903 |
},
|
| 904 |
-
"total_flos": 1.
|
| 905 |
"train_batch_size": 1,
|
| 906 |
"trial_name": null,
|
| 907 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 1.148179292678833,
|
| 14 |
+
"learning_rate": 4e-05,
|
| 15 |
+
"loss": 0.5675,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 1.114451289176941,
|
| 21 |
+
"learning_rate": 8e-05,
|
| 22 |
+
"loss": 0.6005,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.06,
|
| 27 |
+
"grad_norm": 0.8947972655296326,
|
| 28 |
+
"learning_rate": 0.00012,
|
| 29 |
+
"loss": 0.5333,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.08,
|
| 34 |
+
"grad_norm": 0.6874412298202515,
|
| 35 |
+
"learning_rate": 0.00016,
|
| 36 |
+
"loss": 0.5126,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.1,
|
| 41 |
+
"grad_norm": 0.6369613409042358,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.5243,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"grad_norm": 0.5632033944129944,
|
| 49 |
+
"learning_rate": 0.00019994532573409262,
|
| 50 |
+
"loss": 0.5335,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.14,
|
| 55 |
+
"grad_norm": 0.4783449172973633,
|
| 56 |
+
"learning_rate": 0.00019978136272187747,
|
| 57 |
+
"loss": 0.5066,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.16,
|
| 62 |
+
"grad_norm": 0.4505637586116791,
|
| 63 |
+
"learning_rate": 0.00019950829025450114,
|
| 64 |
+
"loss": 0.4819,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.18,
|
| 69 |
+
"grad_norm": 0.4964255690574646,
|
| 70 |
+
"learning_rate": 0.00019912640693269752,
|
| 71 |
+
"loss": 0.4949,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.2,
|
| 76 |
+
"grad_norm": 0.48732897639274597,
|
| 77 |
+
"learning_rate": 0.00019863613034027224,
|
| 78 |
+
"loss": 0.5023,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.22,
|
| 83 |
+
"grad_norm": 0.46126267313957214,
|
| 84 |
+
"learning_rate": 0.00019803799658748094,
|
| 85 |
+
"loss": 0.4869,
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.24,
|
| 90 |
+
"grad_norm": 0.4295591711997986,
|
| 91 |
+
"learning_rate": 0.0001973326597248006,
|
| 92 |
+
"loss": 0.4706,
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.26,
|
| 97 |
+
"grad_norm": 0.4603804647922516,
|
| 98 |
+
"learning_rate": 0.00019652089102773488,
|
| 99 |
+
"loss": 0.4861,
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.28,
|
| 104 |
+
"grad_norm": 0.43054094910621643,
|
| 105 |
+
"learning_rate": 0.00019560357815343577,
|
| 106 |
+
"loss": 0.5147,
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.3,
|
| 111 |
+
"grad_norm": 0.41392526030540466,
|
| 112 |
+
"learning_rate": 0.00019458172417006347,
|
| 113 |
+
"loss": 0.4657,
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.32,
|
| 118 |
+
"grad_norm": 0.3919243812561035,
|
| 119 |
+
"learning_rate": 0.0001934564464599461,
|
| 120 |
+
"loss": 0.4649,
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.34,
|
| 125 |
+
"grad_norm": 0.38946983218193054,
|
| 126 |
+
"learning_rate": 0.00019222897549773848,
|
| 127 |
+
"loss": 0.4626,
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.36,
|
| 132 |
+
"grad_norm": 0.3812195956707001,
|
| 133 |
+
"learning_rate": 0.00019090065350491626,
|
| 134 |
+
"loss": 0.4537,
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.38,
|
| 139 |
+
"grad_norm": 0.37084001302719116,
|
| 140 |
+
"learning_rate": 0.00018947293298207635,
|
| 141 |
+
"loss": 0.4489,
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.4,
|
| 146 |
+
"grad_norm": 0.40874817967414856,
|
| 147 |
+
"learning_rate": 0.0001879473751206489,
|
| 148 |
+
"loss": 0.4583,
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.42,
|
| 153 |
+
"grad_norm": 0.38442370295524597,
|
| 154 |
+
"learning_rate": 0.00018632564809575742,
|
| 155 |
+
"loss": 0.4279,
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.44,
|
| 160 |
+
"grad_norm": 0.3699128329753876,
|
| 161 |
+
"learning_rate": 0.00018460952524209355,
|
| 162 |
+
"loss": 0.4404,
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.46,
|
| 167 |
+
"grad_norm": 0.40334978699684143,
|
| 168 |
+
"learning_rate": 0.00018280088311480201,
|
| 169 |
+
"loss": 0.4448,
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.48,
|
| 174 |
+
"grad_norm": 0.3896102011203766,
|
| 175 |
+
"learning_rate": 0.00018090169943749476,
|
| 176 |
+
"loss": 0.4421,
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.5,
|
| 181 |
+
"grad_norm": 0.3784579336643219,
|
| 182 |
+
"learning_rate": 0.00017891405093963938,
|
| 183 |
+
"loss": 0.4538,
|
| 184 |
"step": 25
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.52,
|
| 188 |
+
"grad_norm": 0.3841725289821625,
|
| 189 |
+
"learning_rate": 0.00017684011108568592,
|
| 190 |
+
"loss": 0.4251,
|
| 191 |
"step": 26
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.54,
|
| 195 |
+
"grad_norm": 0.3888923227787018,
|
| 196 |
+
"learning_rate": 0.0001746821476984154,
|
| 197 |
+
"loss": 0.3996,
|
| 198 |
"step": 27
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.56,
|
| 202 |
+
"grad_norm": 0.40714430809020996,
|
| 203 |
+
"learning_rate": 0.00017244252047910892,
|
| 204 |
+
"loss": 0.4298,
|
| 205 |
"step": 28
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.58,
|
| 209 |
+
"grad_norm": 0.395693838596344,
|
| 210 |
+
"learning_rate": 0.00017012367842724887,
|
| 211 |
+
"loss": 0.4044,
|
| 212 |
"step": 29
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.6,
|
| 216 |
+
"grad_norm": 0.3896782398223877,
|
| 217 |
+
"learning_rate": 0.00016772815716257412,
|
| 218 |
+
"loss": 0.4093,
|
| 219 |
"step": 30
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.62,
|
| 223 |
+
"grad_norm": 0.3841933310031891,
|
| 224 |
+
"learning_rate": 0.00016525857615241687,
|
| 225 |
+
"loss": 0.4139,
|
| 226 |
"step": 31
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.64,
|
| 230 |
+
"grad_norm": 0.3779061436653137,
|
| 231 |
+
"learning_rate": 0.0001627176358473537,
|
| 232 |
+
"loss": 0.3962,
|
| 233 |
"step": 32
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.66,
|
| 237 |
+
"grad_norm": 0.4033326208591461,
|
| 238 |
+
"learning_rate": 0.00016010811472830252,
|
| 239 |
+
"loss": 0.3883,
|
| 240 |
"step": 33
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.68,
|
| 244 |
+
"grad_norm": 0.3781256079673767,
|
| 245 |
+
"learning_rate": 0.00015743286626829437,
|
| 246 |
+
"loss": 0.3858,
|
| 247 |
"step": 34
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.7,
|
| 251 |
+
"grad_norm": 0.37716230750083923,
|
| 252 |
+
"learning_rate": 0.00015469481581224272,
|
| 253 |
+
"loss": 0.3938,
|
| 254 |
"step": 35
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.72,
|
| 258 |
+
"grad_norm": 0.395526260137558,
|
| 259 |
+
"learning_rate": 0.00015189695737812152,
|
| 260 |
+
"loss": 0.4122,
|
| 261 |
"step": 36
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.74,
|
| 265 |
+
"grad_norm": 0.368266224861145,
|
| 266 |
+
"learning_rate": 0.00014904235038305083,
|
| 267 |
+
"loss": 0.403,
|
| 268 |
"step": 37
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.76,
|
| 272 |
+
"grad_norm": 0.37806516885757446,
|
| 273 |
+
"learning_rate": 0.0001461341162978688,
|
| 274 |
+
"loss": 0.374,
|
| 275 |
"step": 38
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.78,
|
| 279 |
+
"grad_norm": 0.37161675095558167,
|
| 280 |
+
"learning_rate": 0.00014317543523384928,
|
| 281 |
+
"loss": 0.3792,
|
| 282 |
"step": 39
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 0.8,
|
| 286 |
+
"grad_norm": 0.3814436197280884,
|
| 287 |
+
"learning_rate": 0.00014016954246529696,
|
| 288 |
+
"loss": 0.3824,
|
| 289 |
"step": 40
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.82,
|
| 293 |
+
"grad_norm": 0.3864171504974365,
|
| 294 |
+
"learning_rate": 0.00013711972489182208,
|
| 295 |
+
"loss": 0.3693,
|
| 296 |
"step": 41
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.84,
|
| 300 |
+
"grad_norm": 0.35850077867507935,
|
| 301 |
+
"learning_rate": 0.00013402931744416433,
|
| 302 |
+
"loss": 0.3623,
|
| 303 |
"step": 42
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.86,
|
| 307 |
+
"grad_norm": 0.36775171756744385,
|
| 308 |
+
"learning_rate": 0.00013090169943749476,
|
| 309 |
+
"loss": 0.3643,
|
| 310 |
"step": 43
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 0.88,
|
| 314 |
+
"grad_norm": 0.37669485807418823,
|
| 315 |
+
"learning_rate": 0.00012774029087618446,
|
| 316 |
+
"loss": 0.3756,
|
| 317 |
"step": 44
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.9,
|
| 321 |
+
"grad_norm": 0.35857564210891724,
|
| 322 |
+
"learning_rate": 0.00012454854871407994,
|
| 323 |
+
"loss": 0.3947,
|
| 324 |
"step": 45
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.92,
|
| 328 |
+
"grad_norm": 0.3690029978752136,
|
| 329 |
+
"learning_rate": 0.0001213299630743747,
|
| 330 |
+
"loss": 0.3548,
|
| 331 |
"step": 46
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.94,
|
| 335 |
+
"grad_norm": 0.3639805018901825,
|
| 336 |
+
"learning_rate": 0.000118088053433211,
|
| 337 |
+
"loss": 0.3627,
|
| 338 |
"step": 47
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.96,
|
| 342 |
+
"grad_norm": 0.37132132053375244,
|
| 343 |
+
"learning_rate": 0.0001148263647711842,
|
| 344 |
+
"loss": 0.3668,
|
| 345 |
"step": 48
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.98,
|
| 349 |
+
"grad_norm": 0.37001127004623413,
|
| 350 |
+
"learning_rate": 0.00011154846369695863,
|
| 351 |
+
"loss": 0.3687,
|
| 352 |
"step": 49
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 1.0,
|
| 356 |
+
"grad_norm": 0.3796997368335724,
|
| 357 |
+
"learning_rate": 0.00010825793454723325,
|
| 358 |
+
"loss": 0.3819,
|
| 359 |
"step": 50
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 1.02,
|
| 363 |
+
"grad_norm": 0.29557618498802185,
|
| 364 |
+
"learning_rate": 0.00010495837546732224,
|
| 365 |
+
"loss": 0.2758,
|
| 366 |
"step": 51
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 1.04,
|
| 370 |
+
"grad_norm": 0.31048524379730225,
|
| 371 |
+
"learning_rate": 0.00010165339447663587,
|
| 372 |
+
"loss": 0.2548,
|
| 373 |
"step": 52
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 1.06,
|
| 377 |
+
"grad_norm": 0.3087123930454254,
|
| 378 |
+
"learning_rate": 9.834660552336415e-05,
|
| 379 |
+
"loss": 0.2647,
|
| 380 |
"step": 53
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 1.08,
|
| 384 |
+
"grad_norm": 0.3230942487716675,
|
| 385 |
+
"learning_rate": 9.504162453267777e-05,
|
| 386 |
+
"loss": 0.2571,
|
| 387 |
"step": 54
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 1.1,
|
| 391 |
+
"grad_norm": 0.3078308701515198,
|
| 392 |
+
"learning_rate": 9.174206545276677e-05,
|
| 393 |
+
"loss": 0.247,
|
| 394 |
"step": 55
|
| 395 |
},
|
| 396 |
{
|
| 397 |
+
"epoch": 1.12,
|
| 398 |
+
"grad_norm": 0.3151338994503021,
|
| 399 |
+
"learning_rate": 8.845153630304139e-05,
|
| 400 |
+
"loss": 0.2649,
|
| 401 |
"step": 56
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 1.1400000000000001,
|
| 405 |
+
"grad_norm": 0.32113245129585266,
|
| 406 |
+
"learning_rate": 8.517363522881579e-05,
|
| 407 |
+
"loss": 0.2441,
|
| 408 |
"step": 57
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 1.16,
|
| 412 |
+
"grad_norm": 0.3001263737678528,
|
| 413 |
+
"learning_rate": 8.191194656678904e-05,
|
| 414 |
+
"loss": 0.2545,
|
| 415 |
"step": 58
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 1.18,
|
| 419 |
+
"grad_norm": 0.31521672010421753,
|
| 420 |
+
"learning_rate": 7.867003692562534e-05,
|
| 421 |
+
"loss": 0.25,
|
| 422 |
"step": 59
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 1.2,
|
| 426 |
+
"grad_norm": 0.3146115839481354,
|
| 427 |
+
"learning_rate": 7.54514512859201e-05,
|
| 428 |
+
"loss": 0.2758,
|
| 429 |
"step": 60
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 1.22,
|
| 433 |
+
"grad_norm": 0.30817195773124695,
|
| 434 |
+
"learning_rate": 7.225970912381556e-05,
|
| 435 |
+
"loss": 0.2639,
|
| 436 |
"step": 61
|
| 437 |
},
|
| 438 |
{
|
| 439 |
+
"epoch": 1.24,
|
| 440 |
+
"grad_norm": 0.3167981505393982,
|
| 441 |
+
"learning_rate": 6.909830056250527e-05,
|
| 442 |
+
"loss": 0.2523,
|
| 443 |
"step": 62
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 1.26,
|
| 447 |
+
"grad_norm": 0.33051297068595886,
|
| 448 |
+
"learning_rate": 6.59706825558357e-05,
|
| 449 |
+
"loss": 0.2478,
|
| 450 |
"step": 63
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 1.28,
|
| 454 |
+
"grad_norm": 0.32061681151390076,
|
| 455 |
+
"learning_rate": 6.28802751081779e-05,
|
| 456 |
+
"loss": 0.2292,
|
| 457 |
"step": 64
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 1.3,
|
| 461 |
+
"grad_norm": 0.32867640256881714,
|
| 462 |
+
"learning_rate": 5.983045753470308e-05,
|
| 463 |
+
"loss": 0.2506,
|
| 464 |
"step": 65
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 1.32,
|
| 468 |
+
"grad_norm": 0.32115456461906433,
|
| 469 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 470 |
+
"loss": 0.2514,
|
| 471 |
"step": 66
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 1.34,
|
| 475 |
+
"grad_norm": 0.3387518525123596,
|
| 476 |
+
"learning_rate": 5.386588370213124e-05,
|
| 477 |
+
"loss": 0.244,
|
| 478 |
"step": 67
|
| 479 |
},
|
| 480 |
{
|
| 481 |
+
"epoch": 1.3599999999999999,
|
| 482 |
+
"grad_norm": 0.32781389355659485,
|
| 483 |
+
"learning_rate": 5.095764961694922e-05,
|
| 484 |
+
"loss": 0.2424,
|
| 485 |
"step": 68
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 1.38,
|
| 489 |
+
"grad_norm": 0.3345761299133301,
|
| 490 |
+
"learning_rate": 4.810304262187852e-05,
|
| 491 |
+
"loss": 0.2513,
|
| 492 |
"step": 69
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 1.4,
|
| 496 |
+
"grad_norm": 0.3255421817302704,
|
| 497 |
+
"learning_rate": 4.530518418775733e-05,
|
| 498 |
+
"loss": 0.2456,
|
| 499 |
"step": 70
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 1.42,
|
| 503 |
+
"grad_norm": 0.3354507088661194,
|
| 504 |
+
"learning_rate": 4.256713373170564e-05,
|
| 505 |
+
"loss": 0.2457,
|
| 506 |
"step": 71
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 1.44,
|
| 510 |
+
"grad_norm": 0.3373594284057617,
|
| 511 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 512 |
+
"loss": 0.2475,
|
| 513 |
"step": 72
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 1.46,
|
| 517 |
+
"grad_norm": 0.32666316628456116,
|
| 518 |
+
"learning_rate": 3.7282364152646297e-05,
|
| 519 |
+
"loss": 0.2301,
|
| 520 |
"step": 73
|
| 521 |
},
|
| 522 |
{
|
| 523 |
+
"epoch": 1.48,
|
| 524 |
+
"grad_norm": 0.3279685974121094,
|
| 525 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 526 |
+
"loss": 0.2472,
|
| 527 |
"step": 74
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 1.5,
|
| 531 |
+
"grad_norm": 0.3301085829734802,
|
| 532 |
+
"learning_rate": 3.227184283742591e-05,
|
| 533 |
+
"loss": 0.2294,
|
| 534 |
"step": 75
|
| 535 |
},
|
| 536 |
{
|
| 537 |
+
"epoch": 1.52,
|
| 538 |
+
"grad_norm": 0.33756864070892334,
|
| 539 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 540 |
+
"loss": 0.2319,
|
| 541 |
"step": 76
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 1.54,
|
| 545 |
+
"grad_norm": 0.3326968848705292,
|
| 546 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 547 |
+
"loss": 0.2435,
|
| 548 |
"step": 77
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 1.56,
|
| 552 |
+
"grad_norm": 0.3414022624492645,
|
| 553 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 554 |
+
"loss": 0.2365,
|
| 555 |
"step": 78
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 1.58,
|
| 559 |
+
"grad_norm": 0.3446585237979889,
|
| 560 |
+
"learning_rate": 2.315988891431412e-05,
|
| 561 |
+
"loss": 0.2353,
|
| 562 |
"step": 79
|
| 563 |
},
|
| 564 |
{
|
| 565 |
+
"epoch": 1.6,
|
| 566 |
+
"grad_norm": 0.33243560791015625,
|
| 567 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 568 |
+
"loss": 0.2604,
|
| 569 |
"step": 80
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 1.62,
|
| 573 |
+
"grad_norm": 0.3418924808502197,
|
| 574 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 575 |
+
"loss": 0.2546,
|
| 576 |
"step": 81
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 1.6400000000000001,
|
| 580 |
+
"grad_norm": 0.33969858288764954,
|
| 581 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 582 |
+
"loss": 0.2546,
|
| 583 |
"step": 82
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 1.6600000000000001,
|
| 587 |
+
"grad_norm": 0.3274635076522827,
|
| 588 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 589 |
+
"loss": 0.2336,
|
| 590 |
"step": 83
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 1.6800000000000002,
|
| 594 |
+
"grad_norm": 0.3252343237400055,
|
| 595 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 596 |
+
"loss": 0.2307,
|
| 597 |
"step": 84
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 1.7,
|
| 601 |
+
"grad_norm": 0.3318844735622406,
|
| 602 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 603 |
+
"loss": 0.2273,
|
| 604 |
"step": 85
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 1.72,
|
| 608 |
+
"grad_norm": 0.3397023677825928,
|
| 609 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 610 |
+
"loss": 0.237,
|
| 611 |
"step": 86
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 1.74,
|
| 615 |
+
"grad_norm": 0.32320481538772583,
|
| 616 |
+
"learning_rate": 9.09934649508375e-06,
|
| 617 |
+
"loss": 0.24,
|
| 618 |
"step": 87
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 1.76,
|
| 622 |
+
"grad_norm": 0.34301823377609253,
|
| 623 |
+
"learning_rate": 7.771024502261526e-06,
|
| 624 |
+
"loss": 0.2447,
|
| 625 |
"step": 88
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 1.78,
|
| 629 |
+
"grad_norm": 0.33157962560653687,
|
| 630 |
+
"learning_rate": 6.543553540053926e-06,
|
| 631 |
+
"loss": 0.2512,
|
| 632 |
"step": 89
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 1.8,
|
| 636 |
+
"grad_norm": 0.33687952160835266,
|
| 637 |
+
"learning_rate": 5.418275829936537e-06,
|
| 638 |
+
"loss": 0.2538,
|
| 639 |
"step": 90
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 1.8199999999999998,
|
| 643 |
+
"grad_norm": 0.3404587209224701,
|
| 644 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 645 |
+
"loss": 0.258,
|
| 646 |
"step": 91
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 1.8399999999999999,
|
| 650 |
+
"grad_norm": 0.3458779752254486,
|
| 651 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 652 |
+
"loss": 0.2392,
|
| 653 |
"step": 92
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 1.8599999999999999,
|
| 657 |
+
"grad_norm": 0.33880794048309326,
|
| 658 |
+
"learning_rate": 2.667340275199426e-06,
|
| 659 |
+
"loss": 0.2542,
|
| 660 |
"step": 93
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 1.88,
|
| 664 |
+
"grad_norm": 0.3243839144706726,
|
| 665 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 666 |
+
"loss": 0.2371,
|
| 667 |
"step": 94
|
| 668 |
},
|
| 669 |
{
|
| 670 |
+
"epoch": 1.9,
|
| 671 |
+
"grad_norm": 0.3197105824947357,
|
| 672 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 673 |
+
"loss": 0.2237,
|
| 674 |
"step": 95
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 1.92,
|
| 678 |
+
"grad_norm": 0.32444778084754944,
|
| 679 |
+
"learning_rate": 8.735930673024806e-07,
|
| 680 |
+
"loss": 0.2331,
|
| 681 |
"step": 96
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 1.94,
|
| 685 |
+
"grad_norm": 0.3440603017807007,
|
| 686 |
+
"learning_rate": 4.917097454988584e-07,
|
| 687 |
+
"loss": 0.257,
|
| 688 |
"step": 97
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"epoch": 1.96,
|
| 692 |
+
"grad_norm": 0.3220385015010834,
|
| 693 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 694 |
+
"loss": 0.2357,
|
| 695 |
"step": 98
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 1.98,
|
| 699 |
+
"grad_norm": 0.3219694495201111,
|
| 700 |
+
"learning_rate": 5.467426590739511e-08,
|
| 701 |
+
"loss": 0.2483,
|
| 702 |
"step": 99
|
| 703 |
},
|
| 704 |
{
|
| 705 |
+
"epoch": 2.0,
|
| 706 |
+
"grad_norm": 0.3302796185016632,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 707 |
"learning_rate": 0.0,
|
| 708 |
+
"loss": 0.2355,
|
| 709 |
+
"step": 100
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
| 713 |
+
"max_steps": 100,
|
| 714 |
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 2,
|
| 716 |
"save_steps": 500,
|
| 717 |
"stateful_callbacks": {
|
| 718 |
"TrainerControl": {
|
|
|
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
+
"total_flos": 1.5112362971367014e+17,
|
| 730 |
"train_batch_size": 1,
|
| 731 |
"trial_name": null,
|
| 732 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6064c140e1d09719a126d7e9578d7002e20512f5c5414610413b50ae4ebd670f
|
| 3 |
size 5240
|