Model save
Browse files- README.md +5 -4
- all_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +509 -12
README.md
CHANGED
|
@@ -1,16 +1,17 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 3 |
-
datasets: GAIR/LIMO
|
| 4 |
library_name: transformers
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
-
|
|
|
|
| 8 |
licence: license
|
| 9 |
---
|
| 10 |
|
| 11 |
-
# Model Card for
|
| 12 |
|
| 13 |
-
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)
|
| 14 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 15 |
|
| 16 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
+
model_name: Qwen2.5-1.5B-Math-Instruct-LIMO
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Model Card for Qwen2.5-1.5B-Math-Instruct-LIMO
|
| 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
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"total_flos":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 817,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"total_flos": 40566502981632.0,
|
| 3 |
+
"train_loss": 0.25444099340545995,
|
| 4 |
+
"train_runtime": 2064.0536,
|
| 5 |
"train_samples": 817,
|
| 6 |
+
"train_samples_per_second": 22.042,
|
| 7 |
+
"train_steps_per_second": 0.345
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"total_flos":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 817,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"total_flos": 40566502981632.0,
|
| 3 |
+
"train_loss": 0.25444099340545995,
|
| 4 |
+
"train_runtime": 2064.0536,
|
| 5 |
"train_samples": 817,
|
| 6 |
+
"train_samples_per_second": 22.042,
|
| 7 |
+
"train_steps_per_second": 0.345
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 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,
|
|
@@ -506,19 +506,516 @@
|
|
| 506 |
"step": 355
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch": 4.
|
| 510 |
-
"
|
| 511 |
-
"
|
| 512 |
-
"
|
| 513 |
-
"
|
| 514 |
-
|
| 515 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 516 |
}
|
| 517 |
],
|
| 518 |
"logging_steps": 5,
|
| 519 |
-
"max_steps":
|
| 520 |
"num_input_tokens_seen": 0,
|
| 521 |
-
"num_train_epochs":
|
| 522 |
"save_steps": 200,
|
| 523 |
"stateful_callbacks": {
|
| 524 |
"TrainerControl": {
|
|
@@ -532,7 +1029,7 @@
|
|
| 532 |
"attributes": {}
|
| 533 |
}
|
| 534 |
},
|
| 535 |
-
"total_flos":
|
| 536 |
"train_batch_size": 8,
|
| 537 |
"trial_name": null,
|
| 538 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 712,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 506 |
"step": 355
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 4.044943820224719,
|
| 510 |
+
"grad_norm": 0.4074217412543327,
|
| 511 |
+
"learning_rate": 1.1585150086919896e-05,
|
| 512 |
+
"loss": 0.6009,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.101123595505618,
|
| 517 |
+
"grad_norm": 0.4271665264127198,
|
| 518 |
+
"learning_rate": 1.137632369284973e-05,
|
| 519 |
+
"loss": 0.6207,
|
| 520 |
+
"step": 365
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 4.157303370786517,
|
| 524 |
+
"grad_norm": 0.43109911858630096,
|
| 525 |
+
"learning_rate": 1.1167294115304992e-05,
|
| 526 |
+
"loss": 0.5911,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 4.213483146067416,
|
| 531 |
+
"grad_norm": 0.43839912783355806,
|
| 532 |
+
"learning_rate": 1.0958174212861062e-05,
|
| 533 |
+
"loss": 0.6011,
|
| 534 |
+
"step": 375
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 4.269662921348314,
|
| 538 |
+
"grad_norm": 0.4190687745455898,
|
| 539 |
+
"learning_rate": 1.0749076892861227e-05,
|
| 540 |
+
"loss": 0.5983,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 4.325842696629214,
|
| 545 |
+
"grad_norm": 0.4272292754884261,
|
| 546 |
+
"learning_rate": 1.0540115050456152e-05,
|
| 547 |
+
"loss": 0.6298,
|
| 548 |
+
"step": 385
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.382022471910112,
|
| 552 |
+
"grad_norm": 0.4188166195248199,
|
| 553 |
+
"learning_rate": 1.0331401507649868e-05,
|
| 554 |
+
"loss": 0.614,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.438202247191011,
|
| 559 |
+
"grad_norm": 0.46031386712411543,
|
| 560 |
+
"learning_rate": 1.012304895238529e-05,
|
| 561 |
+
"loss": 0.5934,
|
| 562 |
+
"step": 395
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 4.49438202247191,
|
| 566 |
+
"grad_norm": 0.4198160623739865,
|
| 567 |
+
"learning_rate": 9.915169877702096e-06,
|
| 568 |
+
"loss": 0.5816,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.550561797752809,
|
| 573 |
+
"grad_norm": 0.41877479862746064,
|
| 574 |
+
"learning_rate": 9.707876520999864e-06,
|
| 575 |
+
"loss": 0.6071,
|
| 576 |
+
"step": 405
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.606741573033708,
|
| 580 |
+
"grad_norm": 0.445785010864897,
|
| 581 |
+
"learning_rate": 9.501280803439204e-06,
|
| 582 |
+
"loss": 0.5816,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 4.662921348314606,
|
| 587 |
+
"grad_norm": 0.4481588101026953,
|
| 588 |
+
"learning_rate": 9.295494269513659e-06,
|
| 589 |
+
"loss": 0.6006,
|
| 590 |
+
"step": 415
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.719101123595506,
|
| 594 |
+
"grad_norm": 0.4260960071459342,
|
| 595 |
+
"learning_rate": 9.090628026824941e-06,
|
| 596 |
+
"loss": 0.6357,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.775280898876405,
|
| 601 |
+
"grad_norm": 0.4192037207998735,
|
| 602 |
+
"learning_rate": 8.886792686094096e-06,
|
| 603 |
+
"loss": 0.6006,
|
| 604 |
+
"step": 425
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.831460674157303,
|
| 608 |
+
"grad_norm": 0.43566168980415704,
|
| 609 |
+
"learning_rate": 8.684098301440903e-06,
|
| 610 |
+
"loss": 0.6267,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.887640449438202,
|
| 615 |
+
"grad_norm": 0.42117325698617175,
|
| 616 |
+
"learning_rate": 8.482654310963817e-06,
|
| 617 |
+
"loss": 0.595,
|
| 618 |
+
"step": 435
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.943820224719101,
|
| 622 |
+
"grad_norm": 0.4414097385180421,
|
| 623 |
+
"learning_rate": 8.2825694776525e-06,
|
| 624 |
+
"loss": 0.5871,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 5.0,
|
| 629 |
+
"grad_norm": 0.41448225752045526,
|
| 630 |
+
"learning_rate": 8.083951830664867e-06,
|
| 631 |
+
"loss": 0.5838,
|
| 632 |
+
"step": 445
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 5.056179775280899,
|
| 636 |
+
"grad_norm": 0.44467080989005614,
|
| 637 |
+
"learning_rate": 7.886908607000321e-06,
|
| 638 |
+
"loss": 0.5612,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.112359550561798,
|
| 643 |
+
"grad_norm": 0.48267692647228083,
|
| 644 |
+
"learning_rate": 7.691546193600702e-06,
|
| 645 |
+
"loss": 0.5438,
|
| 646 |
+
"step": 455
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 5.168539325842697,
|
| 650 |
+
"grad_norm": 0.46882770217949304,
|
| 651 |
+
"learning_rate": 7.497970069910192e-06,
|
| 652 |
+
"loss": 0.5145,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 5.224719101123595,
|
| 657 |
+
"grad_norm": 0.45016082689033277,
|
| 658 |
+
"learning_rate": 7.306284750925192e-06,
|
| 659 |
+
"loss": 0.5392,
|
| 660 |
+
"step": 465
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.280898876404494,
|
| 664 |
+
"grad_norm": 0.4904333208280953,
|
| 665 |
+
"learning_rate": 7.116593730764929e-06,
|
| 666 |
+
"loss": 0.5172,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 5.337078651685394,
|
| 671 |
+
"grad_norm": 0.5047681974857045,
|
| 672 |
+
"learning_rate": 6.928999426793234e-06,
|
| 673 |
+
"loss": 0.5408,
|
| 674 |
+
"step": 475
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.393258426966292,
|
| 678 |
+
"grad_norm": 0.46939981998911995,
|
| 679 |
+
"learning_rate": 6.743603124321712e-06,
|
| 680 |
+
"loss": 0.5408,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 5.449438202247191,
|
| 685 |
+
"grad_norm": 0.48583542280728176,
|
| 686 |
+
"learning_rate": 6.5605049219240635e-06,
|
| 687 |
+
"loss": 0.5564,
|
| 688 |
+
"step": 485
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 5.50561797752809,
|
| 692 |
+
"grad_norm": 0.445507769617856,
|
| 693 |
+
"learning_rate": 6.379803677391223e-06,
|
| 694 |
+
"loss": 0.5272,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 5.561797752808989,
|
| 699 |
+
"grad_norm": 0.48127792996455504,
|
| 700 |
+
"learning_rate": 6.201596954356362e-06,
|
| 701 |
+
"loss": 0.5221,
|
| 702 |
+
"step": 495
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 5.617977528089888,
|
| 706 |
+
"grad_norm": 0.48763800709480937,
|
| 707 |
+
"learning_rate": 6.02598096961865e-06,
|
| 708 |
+
"loss": 0.5017,
|
| 709 |
+
"step": 500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 5.674157303370786,
|
| 713 |
+
"grad_norm": 0.45141538643328166,
|
| 714 |
+
"learning_rate": 5.853050541194187e-06,
|
| 715 |
+
"loss": 0.5301,
|
| 716 |
+
"step": 505
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 5.730337078651686,
|
| 720 |
+
"grad_norm": 0.46888316703181054,
|
| 721 |
+
"learning_rate": 5.682899037122178e-06,
|
| 722 |
+
"loss": 0.5088,
|
| 723 |
+
"step": 510
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 5.786516853932584,
|
| 727 |
+
"grad_norm": 0.49578196304683,
|
| 728 |
+
"learning_rate": 5.515618325053952e-06,
|
| 729 |
+
"loss": 0.5051,
|
| 730 |
+
"step": 515
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 5.842696629213483,
|
| 734 |
+
"grad_norm": 0.4766026956952897,
|
| 735 |
+
"learning_rate": 5.351298722652064e-06,
|
| 736 |
+
"loss": 0.509,
|
| 737 |
+
"step": 520
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 5.898876404494382,
|
| 741 |
+
"grad_norm": 0.5255442360578876,
|
| 742 |
+
"learning_rate": 5.190028948826304e-06,
|
| 743 |
+
"loss": 0.5465,
|
| 744 |
+
"step": 525
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.955056179775281,
|
| 748 |
+
"grad_norm": 0.5102538127102871,
|
| 749 |
+
"learning_rate": 5.031896075832846e-06,
|
| 750 |
+
"loss": 0.5186,
|
| 751 |
+
"step": 530
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 6.01123595505618,
|
| 755 |
+
"grad_norm": 0.5022519456849229,
|
| 756 |
+
"learning_rate": 4.876985482262482e-06,
|
| 757 |
+
"loss": 0.5204,
|
| 758 |
+
"step": 535
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 6.067415730337078,
|
| 762 |
+
"grad_norm": 0.46834498920984025,
|
| 763 |
+
"learning_rate": 4.725380806943299e-06,
|
| 764 |
+
"loss": 0.4707,
|
| 765 |
+
"step": 540
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.123595505617978,
|
| 769 |
+
"grad_norm": 0.5403111606747254,
|
| 770 |
+
"learning_rate": 4.577163903782655e-06,
|
| 771 |
+
"loss": 0.4491,
|
| 772 |
+
"step": 545
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 6.179775280898877,
|
| 776 |
+
"grad_norm": 0.5964108863972761,
|
| 777 |
+
"learning_rate": 4.432414797572894e-06,
|
| 778 |
+
"loss": 0.4709,
|
| 779 |
+
"step": 550
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 6.235955056179775,
|
| 783 |
+
"grad_norm": 0.4994302712693112,
|
| 784 |
+
"learning_rate": 4.291211640784608e-06,
|
| 785 |
+
"loss": 0.4708,
|
| 786 |
+
"step": 555
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 6.292134831460674,
|
| 790 |
+
"grad_norm": 0.49243733113864285,
|
| 791 |
+
"learning_rate": 4.153630671370821e-06,
|
| 792 |
+
"loss": 0.4926,
|
| 793 |
+
"step": 560
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 6.348314606741573,
|
| 797 |
+
"grad_norm": 0.49658882787661995,
|
| 798 |
+
"learning_rate": 4.019746171604824e-06,
|
| 799 |
+
"loss": 0.502,
|
| 800 |
+
"step": 565
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 6.404494382022472,
|
| 804 |
+
"grad_norm": 0.5418840142061598,
|
| 805 |
+
"learning_rate": 3.889630427973951e-06,
|
| 806 |
+
"loss": 0.4602,
|
| 807 |
+
"step": 570
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.460674157303371,
|
| 811 |
+
"grad_norm": 0.5008443330249364,
|
| 812 |
+
"learning_rate": 3.763353692150864e-06,
|
| 813 |
+
"loss": 0.4665,
|
| 814 |
+
"step": 575
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 6.51685393258427,
|
| 818 |
+
"grad_norm": 0.48589030681678613,
|
| 819 |
+
"learning_rate": 3.6409841430635166e-06,
|
| 820 |
+
"loss": 0.4497,
|
| 821 |
+
"step": 580
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 6.573033707865169,
|
| 825 |
+
"grad_norm": 0.5820871330261026,
|
| 826 |
+
"learning_rate": 3.522587850084197e-06,
|
| 827 |
+
"loss": 0.4629,
|
| 828 |
+
"step": 585
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 6.629213483146067,
|
| 832 |
+
"grad_norm": 0.49834548702881326,
|
| 833 |
+
"learning_rate": 3.408228737357575e-06,
|
| 834 |
+
"loss": 0.483,
|
| 835 |
+
"step": 590
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 6.685393258426966,
|
| 839 |
+
"grad_norm": 0.5052799618260936,
|
| 840 |
+
"learning_rate": 3.297968549286974e-06,
|
| 841 |
+
"loss": 0.4808,
|
| 842 |
+
"step": 595
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 6.741573033707866,
|
| 846 |
+
"grad_norm": 0.492591898344833,
|
| 847 |
+
"learning_rate": 3.191866817197539e-06,
|
| 848 |
+
"loss": 0.472,
|
| 849 |
+
"step": 600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 6.797752808988764,
|
| 853 |
+
"grad_norm": 0.49032082408314204,
|
| 854 |
+
"learning_rate": 3.089980827194276e-06,
|
| 855 |
+
"loss": 0.4611,
|
| 856 |
+
"step": 605
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 6.853932584269663,
|
| 860 |
+
"grad_norm": 0.4959126643842184,
|
| 861 |
+
"learning_rate": 2.9923655892323144e-06,
|
| 862 |
+
"loss": 0.4726,
|
| 863 |
+
"step": 610
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 6.910112359550562,
|
| 867 |
+
"grad_norm": 0.5335774103596451,
|
| 868 |
+
"learning_rate": 2.8990738074161196e-06,
|
| 869 |
+
"loss": 0.4792,
|
| 870 |
+
"step": 615
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 6.966292134831461,
|
| 874 |
+
"grad_norm": 0.5201706543464556,
|
| 875 |
+
"learning_rate": 2.8101558515436506e-06,
|
| 876 |
+
"loss": 0.4711,
|
| 877 |
+
"step": 620
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 7.022471910112359,
|
| 881 |
+
"grad_norm": 0.4623475019520009,
|
| 882 |
+
"learning_rate": 2.725659729910878e-06,
|
| 883 |
+
"loss": 0.4545,
|
| 884 |
+
"step": 625
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 7.078651685393258,
|
| 888 |
+
"grad_norm": 0.4834608390252829,
|
| 889 |
+
"learning_rate": 2.645631063391285e-06,
|
| 890 |
+
"loss": 0.443,
|
| 891 |
+
"step": 630
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 7.134831460674158,
|
| 895 |
+
"grad_norm": 0.5359592571307704,
|
| 896 |
+
"learning_rate": 2.570113060804401e-06,
|
| 897 |
+
"loss": 0.441,
|
| 898 |
+
"step": 635
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 7.191011235955056,
|
| 902 |
+
"grad_norm": 0.5433362481606256,
|
| 903 |
+
"learning_rate": 2.4991464955866314e-06,
|
| 904 |
+
"loss": 0.4264,
|
| 905 |
+
"step": 640
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 7.247191011235955,
|
| 909 |
+
"grad_norm": 0.5225953610583668,
|
| 910 |
+
"learning_rate": 2.432769683776995e-06,
|
| 911 |
+
"loss": 0.4145,
|
| 912 |
+
"step": 645
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 7.303370786516854,
|
| 916 |
+
"grad_norm": 0.5205000317985969,
|
| 917 |
+
"learning_rate": 2.371018463329651e-06,
|
| 918 |
+
"loss": 0.435,
|
| 919 |
+
"step": 650
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 7.359550561797753,
|
| 923 |
+
"grad_norm": 0.5007819526288158,
|
| 924 |
+
"learning_rate": 2.3139261747643925e-06,
|
| 925 |
+
"loss": 0.41,
|
| 926 |
+
"step": 655
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 7.415730337078652,
|
| 930 |
+
"grad_norm": 0.518942310039327,
|
| 931 |
+
"learning_rate": 2.261523643165532e-06,
|
| 932 |
+
"loss": 0.4502,
|
| 933 |
+
"step": 660
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 7.47191011235955,
|
| 937 |
+
"grad_norm": 0.49873700284836797,
|
| 938 |
+
"learning_rate": 2.2138391615389306e-06,
|
| 939 |
+
"loss": 0.4324,
|
| 940 |
+
"step": 665
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 7.52808988764045,
|
| 944 |
+
"grad_norm": 0.5208414783528387,
|
| 945 |
+
"learning_rate": 2.1708984755361205e-06,
|
| 946 |
+
"loss": 0.4449,
|
| 947 |
+
"step": 670
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 7.584269662921348,
|
| 951 |
+
"grad_norm": 0.5791900845785815,
|
| 952 |
+
"learning_rate": 2.1327247695538015e-06,
|
| 953 |
+
"loss": 0.4484,
|
| 954 |
+
"step": 675
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 7.640449438202247,
|
| 958 |
+
"grad_norm": 0.5438940813210439,
|
| 959 |
+
"learning_rate": 2.0993386542161944e-06,
|
| 960 |
+
"loss": 0.4685,
|
| 961 |
+
"step": 680
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 7.696629213483146,
|
| 965 |
+
"grad_norm": 0.5127534158556458,
|
| 966 |
+
"learning_rate": 2.070758155247017e-06,
|
| 967 |
+
"loss": 0.4339,
|
| 968 |
+
"step": 685
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 7.752808988764045,
|
| 972 |
+
"grad_norm": 0.5415209164546988,
|
| 973 |
+
"learning_rate": 2.0469987037371005e-06,
|
| 974 |
+
"loss": 0.4103,
|
| 975 |
+
"step": 690
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 7.808988764044944,
|
| 979 |
+
"grad_norm": 0.5136419675345572,
|
| 980 |
+
"learning_rate": 2.028073127812876e-06,
|
| 981 |
+
"loss": 0.4169,
|
| 982 |
+
"step": 695
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 7.865168539325842,
|
| 986 |
+
"grad_norm": 0.5319921953080505,
|
| 987 |
+
"learning_rate": 2.013991645710262e-06,
|
| 988 |
+
"loss": 0.4286,
|
| 989 |
+
"step": 700
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 7.921348314606742,
|
| 993 |
+
"grad_norm": 0.5733506841186511,
|
| 994 |
+
"learning_rate": 2.0047618602576594e-06,
|
| 995 |
+
"loss": 0.4505,
|
| 996 |
+
"step": 705
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 7.97752808988764,
|
| 1000 |
+
"grad_norm": 0.5142139821667071,
|
| 1001 |
+
"learning_rate": 2.0003887547710647e-06,
|
| 1002 |
+
"loss": 0.4202,
|
| 1003 |
+
"step": 710
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 8.0,
|
| 1007 |
+
"step": 712,
|
| 1008 |
+
"total_flos": 40566502981632.0,
|
| 1009 |
+
"train_loss": 0.25444099340545995,
|
| 1010 |
+
"train_runtime": 2064.0536,
|
| 1011 |
+
"train_samples_per_second": 22.042,
|
| 1012 |
+
"train_steps_per_second": 0.345
|
| 1013 |
}
|
| 1014 |
],
|
| 1015 |
"logging_steps": 5,
|
| 1016 |
+
"max_steps": 712,
|
| 1017 |
"num_input_tokens_seen": 0,
|
| 1018 |
+
"num_train_epochs": 8,
|
| 1019 |
"save_steps": 200,
|
| 1020 |
"stateful_callbacks": {
|
| 1021 |
"TrainerControl": {
|
|
|
|
| 1029 |
"attributes": {}
|
| 1030 |
}
|
| 1031 |
},
|
| 1032 |
+
"total_flos": 40566502981632.0,
|
| 1033 |
"train_batch_size": 8,
|
| 1034 |
"trial_name": null,
|
| 1035 |
"trial_params": null
|