Training in progress, step 400, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -20,12 +20,12 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"q_proj",
|
|
|
|
|
|
|
| 24 |
"gate_proj",
|
| 25 |
-
"down_proj",
|
| 26 |
"k_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
-
"o_proj",
|
| 29 |
"v_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
"q_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
"gate_proj",
|
|
|
|
| 28 |
"k_proj",
|
|
|
|
|
|
|
| 29 |
"v_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43ef35dda0f3a5a508eab117460ff6a331211e06b198dc6e1a315d6d8897b434
|
| 3 |
size 83945296
|
last-checkpoint/optimizer.pt
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 sha256:784499b9c57080a9aa835529570368af18b60b12be5d1a140d26af708d454530
|
| 3 |
+
size 168155346
|
last-checkpoint/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 sha256:35297f49e243ed1d027a26f9d8cc60d7b1b3d88f3cde5bada6803ecb49d4e54c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 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,
|
|
@@ -287,6 +287,286 @@
|
|
| 287 |
"learning_rate": 4.993395348466544e-05,
|
| 288 |
"loss": 0.7012,
|
| 289 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
}
|
| 291 |
],
|
| 292 |
"logging_steps": 5,
|
|
@@ -306,7 +586,7 @@
|
|
| 306 |
"attributes": {}
|
| 307 |
}
|
| 308 |
},
|
| 309 |
-
"total_flos":
|
| 310 |
"train_batch_size": 1,
|
| 311 |
"trial_name": null,
|
| 312 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.09046362608367886,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 287 |
"learning_rate": 4.993395348466544e-05,
|
| 288 |
"loss": 0.7012,
|
| 289 |
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.046362608367885416,
|
| 293 |
+
"grad_norm": 0.28732138872146606,
|
| 294 |
+
"learning_rate": 4.992718700485085e-05,
|
| 295 |
+
"loss": 0.7247,
|
| 296 |
+
"step": 205
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.047493403693931395,
|
| 300 |
+
"grad_norm": 0.2657299339771271,
|
| 301 |
+
"learning_rate": 4.99200911095478e-05,
|
| 302 |
+
"loss": 0.7247,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.04862419901997738,
|
| 307 |
+
"grad_norm": 0.30124104022979736,
|
| 308 |
+
"learning_rate": 4.991266589252933e-05,
|
| 309 |
+
"loss": 0.7001,
|
| 310 |
+
"step": 215
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.049754994346023367,
|
| 314 |
+
"grad_norm": 0.3533799946308136,
|
| 315 |
+
"learning_rate": 4.990491145192049e-05,
|
| 316 |
+
"loss": 0.7714,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.05088578967206935,
|
| 321 |
+
"grad_norm": 0.29441332817077637,
|
| 322 |
+
"learning_rate": 4.989682789019706e-05,
|
| 323 |
+
"loss": 0.7338,
|
| 324 |
+
"step": 225
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.05201658499811534,
|
| 328 |
+
"grad_norm": 0.2670339345932007,
|
| 329 |
+
"learning_rate": 4.988841531418418e-05,
|
| 330 |
+
"loss": 0.719,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.053147380324161324,
|
| 335 |
+
"grad_norm": 0.44572877883911133,
|
| 336 |
+
"learning_rate": 4.9879673835054955e-05,
|
| 337 |
+
"loss": 0.7315,
|
| 338 |
+
"step": 235
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.05427817565020731,
|
| 342 |
+
"grad_norm": 0.29553067684173584,
|
| 343 |
+
"learning_rate": 4.9870603568328985e-05,
|
| 344 |
+
"loss": 0.7495,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.055408970976253295,
|
| 349 |
+
"grad_norm": 0.26393231749534607,
|
| 350 |
+
"learning_rate": 4.986120463387084e-05,
|
| 351 |
+
"loss": 0.6637,
|
| 352 |
+
"step": 245
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.05653976630229928,
|
| 356 |
+
"grad_norm": 0.35982418060302734,
|
| 357 |
+
"learning_rate": 4.985147715588845e-05,
|
| 358 |
+
"loss": 0.7571,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.05767056162834527,
|
| 363 |
+
"grad_norm": 0.38977113366127014,
|
| 364 |
+
"learning_rate": 4.9841421262931506e-05,
|
| 365 |
+
"loss": 0.7551,
|
| 366 |
+
"step": 255
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.05880135695439125,
|
| 370 |
+
"grad_norm": 0.28935956954956055,
|
| 371 |
+
"learning_rate": 4.983103708788972e-05,
|
| 372 |
+
"loss": 0.7863,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.05993215228043724,
|
| 377 |
+
"grad_norm": 0.34443530440330505,
|
| 378 |
+
"learning_rate": 4.98203247679911e-05,
|
| 379 |
+
"loss": 0.8106,
|
| 380 |
+
"step": 265
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.061062947606483224,
|
| 384 |
+
"grad_norm": 0.4763427674770355,
|
| 385 |
+
"learning_rate": 4.980928444480011e-05,
|
| 386 |
+
"loss": 0.7729,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.06219374293252921,
|
| 391 |
+
"grad_norm": 0.2860422730445862,
|
| 392 |
+
"learning_rate": 4.9797916264215824e-05,
|
| 393 |
+
"loss": 0.7593,
|
| 394 |
+
"step": 275
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.0633245382585752,
|
| 398 |
+
"grad_norm": 0.28870680928230286,
|
| 399 |
+
"learning_rate": 4.978622037647e-05,
|
| 400 |
+
"loss": 0.7574,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.06445533358462119,
|
| 405 |
+
"grad_norm": 0.40277180075645447,
|
| 406 |
+
"learning_rate": 4.9774196936125056e-05,
|
| 407 |
+
"loss": 0.799,
|
| 408 |
+
"step": 285
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.06558612891066717,
|
| 412 |
+
"grad_norm": 0.3290288746356964,
|
| 413 |
+
"learning_rate": 4.9761846102072065e-05,
|
| 414 |
+
"loss": 0.7519,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.06671692423671316,
|
| 419 |
+
"grad_norm": 0.3139791190624237,
|
| 420 |
+
"learning_rate": 4.9749168037528635e-05,
|
| 421 |
+
"loss": 0.6837,
|
| 422 |
+
"step": 295
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.06784771956275915,
|
| 426 |
+
"grad_norm": 0.30802035331726074,
|
| 427 |
+
"learning_rate": 4.9736162910036785e-05,
|
| 428 |
+
"loss": 0.7662,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.06897851488880513,
|
| 433 |
+
"grad_norm": 0.34561124444007874,
|
| 434 |
+
"learning_rate": 4.972283089146067e-05,
|
| 435 |
+
"loss": 0.6897,
|
| 436 |
+
"step": 305
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.07010931021485112,
|
| 440 |
+
"grad_norm": 0.3372039198875427,
|
| 441 |
+
"learning_rate": 4.970917215798438e-05,
|
| 442 |
+
"loss": 0.7344,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.0712401055408971,
|
| 447 |
+
"grad_norm": 0.41160914301872253,
|
| 448 |
+
"learning_rate": 4.9695186890109567e-05,
|
| 449 |
+
"loss": 0.832,
|
| 450 |
+
"step": 315
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.07237090086694309,
|
| 454 |
+
"grad_norm": 0.2914057672023773,
|
| 455 |
+
"learning_rate": 4.968087527265306e-05,
|
| 456 |
+
"loss": 0.7113,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.07350169619298907,
|
| 461 |
+
"grad_norm": 0.3247675597667694,
|
| 462 |
+
"learning_rate": 4.966623749474445e-05,
|
| 463 |
+
"loss": 0.6996,
|
| 464 |
+
"step": 325
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.07463249151903506,
|
| 468 |
+
"grad_norm": 0.435735285282135,
|
| 469 |
+
"learning_rate": 4.9651273749823546e-05,
|
| 470 |
+
"loss": 0.8236,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.07576328684508105,
|
| 475 |
+
"grad_norm": 0.3213053047657013,
|
| 476 |
+
"learning_rate": 4.963598423563788e-05,
|
| 477 |
+
"loss": 0.7012,
|
| 478 |
+
"step": 335
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.07689408217112703,
|
| 482 |
+
"grad_norm": 0.3745056390762329,
|
| 483 |
+
"learning_rate": 4.962036915424004e-05,
|
| 484 |
+
"loss": 0.7018,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.07802487749717302,
|
| 489 |
+
"grad_norm": 0.28368842601776123,
|
| 490 |
+
"learning_rate": 4.960442871198503e-05,
|
| 491 |
+
"loss": 0.7084,
|
| 492 |
+
"step": 345
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.079155672823219,
|
| 496 |
+
"grad_norm": 0.2621799409389496,
|
| 497 |
+
"learning_rate": 4.958816311952752e-05,
|
| 498 |
+
"loss": 0.7217,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.08028646814926499,
|
| 503 |
+
"grad_norm": 0.25561287999153137,
|
| 504 |
+
"learning_rate": 4.95715725918191e-05,
|
| 505 |
+
"loss": 0.7616,
|
| 506 |
+
"step": 355
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.08141726347531097,
|
| 510 |
+
"grad_norm": 0.3495071828365326,
|
| 511 |
+
"learning_rate": 4.9554657348105385e-05,
|
| 512 |
+
"loss": 0.7061,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.08254805880135696,
|
| 517 |
+
"grad_norm": 0.3490068018436432,
|
| 518 |
+
"learning_rate": 4.953741761192317e-05,
|
| 519 |
+
"loss": 0.7809,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.08367885412740295,
|
| 524 |
+
"grad_norm": 0.39416739344596863,
|
| 525 |
+
"learning_rate": 4.9519853611097434e-05,
|
| 526 |
+
"loss": 0.7282,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.08480964945344893,
|
| 531 |
+
"grad_norm": 0.2763444185256958,
|
| 532 |
+
"learning_rate": 4.950196557773837e-05,
|
| 533 |
+
"loss": 0.7262,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.08594044477949492,
|
| 538 |
+
"grad_norm": 0.29107871651649475,
|
| 539 |
+
"learning_rate": 4.948375374823828e-05,
|
| 540 |
+
"loss": 0.7346,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.0870712401055409,
|
| 545 |
+
"grad_norm": 0.28965339064598083,
|
| 546 |
+
"learning_rate": 4.946521836326847e-05,
|
| 547 |
+
"loss": 0.6768,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.08820203543158689,
|
| 552 |
+
"grad_norm": 0.31072792410850525,
|
| 553 |
+
"learning_rate": 4.9446359667776065e-05,
|
| 554 |
+
"loss": 0.7277,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.08933283075763288,
|
| 559 |
+
"grad_norm": 0.2789427936077118,
|
| 560 |
+
"learning_rate": 4.9427177910980794e-05,
|
| 561 |
+
"loss": 0.7481,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.09046362608367886,
|
| 566 |
+
"grad_norm": 0.2573710083961487,
|
| 567 |
+
"learning_rate": 4.9407673346371644e-05,
|
| 568 |
+
"loss": 0.7077,
|
| 569 |
+
"step": 400
|
| 570 |
}
|
| 571 |
],
|
| 572 |
"logging_steps": 5,
|
|
|
|
| 586 |
"attributes": {}
|
| 587 |
}
|
| 588 |
},
|
| 589 |
+
"total_flos": 4.2708606055664845e+17,
|
| 590 |
"train_batch_size": 1,
|
| 591 |
"trial_name": null,
|
| 592 |
"trial_params": null
|
last-checkpoint/training_args.bin
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:c29b6114cee3a1eb0c6657320d373e2561ec03a011bc688ec4cc2b0b164a6831
|
| 3 |
+
size 5816
|