[mid-backup] slot 5 update latest checkpoint-1243
Browse files
slots/5/latest/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -367,38 +367,94 @@
|
|
| 367 |
"step": 1000
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch": 0.
|
| 371 |
-
"grad_norm":
|
| 372 |
-
"learning_rate": 4.
|
| 373 |
-
"loss":
|
| 374 |
"step": 1020
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch": 0.
|
| 378 |
-
"grad_norm":
|
| 379 |
-
"learning_rate": 4.
|
| 380 |
-
"loss":
|
| 381 |
"step": 1040
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 0.
|
| 385 |
-
"grad_norm":
|
| 386 |
-
"learning_rate": 4.
|
| 387 |
-
"loss":
|
| 388 |
"step": 1060
|
| 389 |
},
|
| 390 |
{
|
| 391 |
-
"epoch": 0.
|
| 392 |
-
"grad_norm":
|
| 393 |
-
"learning_rate": 4.
|
| 394 |
-
"loss":
|
| 395 |
"step": 1080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 396 |
}
|
| 397 |
],
|
| 398 |
"logging_steps": 20,
|
| 399 |
-
"max_steps":
|
| 400 |
"num_input_tokens_seen": 0,
|
| 401 |
-
"num_train_epochs":
|
| 402 |
"save_steps": 1000000000,
|
| 403 |
"stateful_callbacks": {
|
| 404 |
"TrainerControl": {
|
|
@@ -412,7 +468,7 @@
|
|
| 412 |
"attributes": {}
|
| 413 |
}
|
| 414 |
},
|
| 415 |
-
"total_flos":
|
| 416 |
"train_batch_size": 1,
|
| 417 |
"trial_name": null,
|
| 418 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5031688403688758,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1243,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 367 |
"step": 1000
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 0.11327237077267444,
|
| 371 |
+
"grad_norm": 426.9232482910156,
|
| 372 |
+
"learning_rate": 4.9749156515129356e-05,
|
| 373 |
+
"loss": 494.6495768229167,
|
| 374 |
"step": 1020
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.11549339765057001,
|
| 378 |
+
"grad_norm": 472.5828552246094,
|
| 379 |
+
"learning_rate": 4.9739200960461216e-05,
|
| 380 |
+
"loss": 419.9888671875,
|
| 381 |
"step": 1040
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 0.11771442452846559,
|
| 385 |
+
"grad_norm": 744.5155029296875,
|
| 386 |
+
"learning_rate": 4.972905270727243e-05,
|
| 387 |
+
"loss": 383.80888671875,
|
| 388 |
"step": 1060
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 0.11993545140636117,
|
| 392 |
+
"grad_norm": 360.4026794433594,
|
| 393 |
+
"learning_rate": 4.9718711834609744e-05,
|
| 394 |
+
"loss": 363.4324462890625,
|
| 395 |
"step": 1080
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.44528215961847417,
|
| 399 |
+
"grad_norm": 277.2105407714844,
|
| 400 |
+
"learning_rate": 2.6398680901162493e-05,
|
| 401 |
+
"loss": 326.2257568359375,
|
| 402 |
+
"step": 1100
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4533781988842646,
|
| 406 |
+
"grad_norm": 280.0869445800781,
|
| 407 |
+
"learning_rate": 2.5708249369176603e-05,
|
| 408 |
+
"loss": 315.2998779296875,
|
| 409 |
+
"step": 1120
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.461474238150055,
|
| 413 |
+
"grad_norm": 319.7271423339844,
|
| 414 |
+
"learning_rate": 2.5017276685017228e-05,
|
| 415 |
+
"loss": 308.6649169921875,
|
| 416 |
+
"step": 1140
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.46957027741584545,
|
| 420 |
+
"grad_norm": 326.30511474609375,
|
| 421 |
+
"learning_rate": 2.4326290800259233e-05,
|
| 422 |
+
"loss": 299.4122314453125,
|
| 423 |
+
"step": 1160
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4776663166816359,
|
| 427 |
+
"grad_norm": 281.5859680175781,
|
| 428 |
+
"learning_rate": 2.3635819676563654e-05,
|
| 429 |
+
"loss": 293.6065673828125,
|
| 430 |
+
"step": 1180
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.48576235594742634,
|
| 434 |
+
"grad_norm": 249.5887908935547,
|
| 435 |
+
"learning_rate": 2.2946390882278e-05,
|
| 436 |
+
"loss": 288.6381103515625,
|
| 437 |
+
"step": 1200
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.4938583952132168,
|
| 441 |
+
"grad_norm": 256.4424133300781,
|
| 442 |
+
"learning_rate": 2.225853118933701e-05,
|
| 443 |
+
"loss": 281.87607421875,
|
| 444 |
+
"step": 1220
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5019544344790072,
|
| 448 |
+
"grad_norm": 238.34730529785156,
|
| 449 |
+
"learning_rate": 2.1572766170772005e-05,
|
| 450 |
+
"loss": 280.4020263671875,
|
| 451 |
+
"step": 1240
|
| 452 |
}
|
| 453 |
],
|
| 454 |
"logging_steps": 20,
|
| 455 |
+
"max_steps": 2273,
|
| 456 |
"num_input_tokens_seen": 0,
|
| 457 |
+
"num_train_epochs": 1,
|
| 458 |
"save_steps": 1000000000,
|
| 459 |
"stateful_callbacks": {
|
| 460 |
"TrainerControl": {
|
|
|
|
| 468 |
"attributes": {}
|
| 469 |
}
|
| 470 |
},
|
| 471 |
+
"total_flos": 8958922567778304.0,
|
| 472 |
"train_batch_size": 1,
|
| 473 |
"trial_name": null,
|
| 474 |
"trial_params": null
|