Kerem P
commited on
Commit
·
f18fc82
1
Parent(s):
23ed661
End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- train_results.json +5 -5
- trainer_state.json +642 -66
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 1916,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 5743,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_f1": 0.0,
|
| 4 |
+
"eval_loss": 0.34448280930519104,
|
| 5 |
+
"eval_runtime": 20.531,
|
| 6 |
"eval_samples": 1916,
|
| 7 |
+
"eval_samples_per_second": 93.322,
|
| 8 |
+
"eval_steps_per_second": 1.461,
|
| 9 |
+
"train_loss": 0.3510875488058106,
|
| 10 |
+
"train_runtime": 3949.5247,
|
| 11 |
"train_samples": 5743,
|
| 12 |
+
"train_samples_per_second": 14.541,
|
| 13 |
+
"train_steps_per_second": 0.909
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 1916,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_f1": 0.0,
|
| 4 |
+
"eval_loss": 0.34448280930519104,
|
| 5 |
+
"eval_runtime": 20.531,
|
| 6 |
"eval_samples": 1916,
|
| 7 |
+
"eval_samples_per_second": 93.322,
|
| 8 |
+
"eval_steps_per_second": 1.461
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 5743,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.3510875488058106,
|
| 4 |
+
"train_runtime": 3949.5247,
|
| 5 |
"train_samples": 5743,
|
| 6 |
+
"train_samples_per_second": 14.541,
|
| 7 |
+
"train_steps_per_second": 0.909
|
| 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,
|
|
@@ -531,123 +531,699 @@
|
|
| 531 |
"step": 1500
|
| 532 |
},
|
| 533 |
{
|
| 534 |
-
"epoch":
|
| 535 |
-
"learning_rate":
|
| 536 |
-
"loss":
|
| 537 |
"step": 1520
|
| 538 |
},
|
| 539 |
{
|
| 540 |
-
"epoch":
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss":
|
| 543 |
"step": 1540
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"epoch":
|
| 547 |
-
"learning_rate":
|
| 548 |
-
"loss":
|
| 549 |
"step": 1560
|
| 550 |
},
|
| 551 |
{
|
| 552 |
-
"epoch":
|
| 553 |
-
"learning_rate":
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 1580
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch":
|
| 559 |
-
"learning_rate":
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 1600
|
| 562 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 563 |
{
|
| 564 |
"epoch": 9.0,
|
| 565 |
-
"eval_f1": 0.
|
| 566 |
-
"eval_loss":
|
| 567 |
-
"eval_runtime":
|
| 568 |
-
"eval_samples_per_second":
|
| 569 |
-
"eval_steps_per_second": 1.
|
| 570 |
-
"step":
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 9.03,
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 9.14,
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 0.
|
| 582 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 9.25,
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 0.
|
| 588 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 9.36,
|
| 592 |
-
"learning_rate":
|
| 593 |
-
"loss": 0.
|
| 594 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 9.47,
|
| 598 |
-
"learning_rate":
|
| 599 |
-
"loss": 0.
|
| 600 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 601 |
},
|
| 602 |
{
|
| 603 |
"epoch": 9.58,
|
| 604 |
-
"learning_rate":
|
| 605 |
-
"loss": 0.
|
| 606 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 9.69,
|
| 610 |
-
"learning_rate":
|
| 611 |
-
"loss": 0.
|
| 612 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 9.81,
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
-
"step":
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch": 9.
|
| 622 |
-
"learning_rate":
|
| 623 |
-
"loss": 0.
|
| 624 |
-
"step":
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"epoch": 9.
|
| 628 |
-
"
|
| 629 |
-
"
|
| 630 |
-
"
|
| 631 |
-
"eval_samples_per_second": 83.672,
|
| 632 |
-
"eval_steps_per_second": 1.31,
|
| 633 |
-
"step": 1790
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 9.97,
|
| 637 |
-
"
|
| 638 |
-
"
|
| 639 |
-
"
|
| 640 |
-
|
| 641 |
-
|
| 642 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 643 |
}
|
| 644 |
],
|
| 645 |
"logging_steps": 20,
|
| 646 |
-
"max_steps":
|
| 647 |
"num_input_tokens_seen": 0,
|
| 648 |
"num_train_epochs": 10,
|
| 649 |
"save_steps": 500,
|
| 650 |
-
"total_flos":
|
| 651 |
"train_batch_size": 2,
|
| 652 |
"trial_name": null,
|
| 653 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3590,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 531 |
"step": 1500
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 4.23,
|
| 535 |
+
"learning_rate": 0.001,
|
| 536 |
+
"loss": 18.7223,
|
| 537 |
"step": 1520
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 4.29,
|
| 541 |
+
"learning_rate": 0.001,
|
| 542 |
+
"loss": 5.5701,
|
| 543 |
"step": 1540
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 4.35,
|
| 547 |
+
"learning_rate": 0.001,
|
| 548 |
+
"loss": 1.2935,
|
| 549 |
"step": 1560
|
| 550 |
},
|
| 551 |
{
|
| 552 |
+
"epoch": 4.4,
|
| 553 |
+
"learning_rate": 0.001,
|
| 554 |
+
"loss": 0.6161,
|
| 555 |
"step": 1580
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 4.46,
|
| 559 |
+
"learning_rate": 0.001,
|
| 560 |
+
"loss": 0.757,
|
| 561 |
"step": 1600
|
| 562 |
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.51,
|
| 565 |
+
"learning_rate": 0.001,
|
| 566 |
+
"loss": 0.6241,
|
| 567 |
+
"step": 1620
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.57,
|
| 571 |
+
"learning_rate": 0.001,
|
| 572 |
+
"loss": 0.5211,
|
| 573 |
+
"step": 1640
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 4.62,
|
| 577 |
+
"learning_rate": 0.001,
|
| 578 |
+
"loss": 0.4467,
|
| 579 |
+
"step": 1660
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.68,
|
| 583 |
+
"learning_rate": 0.001,
|
| 584 |
+
"loss": 0.424,
|
| 585 |
+
"step": 1680
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.74,
|
| 589 |
+
"learning_rate": 0.001,
|
| 590 |
+
"loss": 0.3741,
|
| 591 |
+
"step": 1700
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 4.79,
|
| 595 |
+
"learning_rate": 0.001,
|
| 596 |
+
"loss": 0.3276,
|
| 597 |
+
"step": 1720
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.85,
|
| 601 |
+
"learning_rate": 0.001,
|
| 602 |
+
"loss": 0.3692,
|
| 603 |
+
"step": 1740
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 4.9,
|
| 607 |
+
"learning_rate": 0.001,
|
| 608 |
+
"loss": 0.3626,
|
| 609 |
+
"step": 1760
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.96,
|
| 613 |
+
"learning_rate": 0.001,
|
| 614 |
+
"loss": 0.3698,
|
| 615 |
+
"step": 1780
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 5.0,
|
| 619 |
+
"eval_f1": 0.0,
|
| 620 |
+
"eval_loss": 0.3513816297054291,
|
| 621 |
+
"eval_runtime": 20.8512,
|
| 622 |
+
"eval_samples_per_second": 91.889,
|
| 623 |
+
"eval_steps_per_second": 1.439,
|
| 624 |
+
"step": 1795
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 5.01,
|
| 628 |
+
"learning_rate": 0.001,
|
| 629 |
+
"loss": 0.3672,
|
| 630 |
+
"step": 1800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 5.07,
|
| 634 |
+
"learning_rate": 0.001,
|
| 635 |
+
"loss": 0.3879,
|
| 636 |
+
"step": 1820
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 5.13,
|
| 640 |
+
"learning_rate": 0.001,
|
| 641 |
+
"loss": 0.458,
|
| 642 |
+
"step": 1840
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 5.18,
|
| 646 |
+
"learning_rate": 0.001,
|
| 647 |
+
"loss": 0.3949,
|
| 648 |
+
"step": 1860
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 5.24,
|
| 652 |
+
"learning_rate": 0.001,
|
| 653 |
+
"loss": 0.372,
|
| 654 |
+
"step": 1880
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 5.29,
|
| 658 |
+
"learning_rate": 0.001,
|
| 659 |
+
"loss": 0.3578,
|
| 660 |
+
"step": 1900
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 5.35,
|
| 664 |
+
"learning_rate": 0.001,
|
| 665 |
+
"loss": 0.3906,
|
| 666 |
+
"step": 1920
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 5.4,
|
| 670 |
+
"learning_rate": 0.001,
|
| 671 |
+
"loss": 0.3888,
|
| 672 |
+
"step": 1940
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 5.46,
|
| 676 |
+
"learning_rate": 0.001,
|
| 677 |
+
"loss": 0.4049,
|
| 678 |
+
"step": 1960
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 5.52,
|
| 682 |
+
"learning_rate": 0.001,
|
| 683 |
+
"loss": 0.3692,
|
| 684 |
+
"step": 1980
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 5.57,
|
| 688 |
+
"learning_rate": 0.001,
|
| 689 |
+
"loss": 0.3299,
|
| 690 |
+
"step": 2000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 5.63,
|
| 694 |
+
"learning_rate": 0.001,
|
| 695 |
+
"loss": 0.3714,
|
| 696 |
+
"step": 2020
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 5.68,
|
| 700 |
+
"learning_rate": 0.001,
|
| 701 |
+
"loss": 0.3423,
|
| 702 |
+
"step": 2040
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 5.74,
|
| 706 |
+
"learning_rate": 0.001,
|
| 707 |
+
"loss": 0.3534,
|
| 708 |
+
"step": 2060
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 5.79,
|
| 712 |
+
"learning_rate": 0.001,
|
| 713 |
+
"loss": 0.3426,
|
| 714 |
+
"step": 2080
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 5.85,
|
| 718 |
+
"learning_rate": 0.001,
|
| 719 |
+
"loss": 0.3684,
|
| 720 |
+
"step": 2100
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.91,
|
| 724 |
+
"learning_rate": 0.001,
|
| 725 |
+
"loss": 0.3472,
|
| 726 |
+
"step": 2120
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 5.96,
|
| 730 |
+
"learning_rate": 0.001,
|
| 731 |
+
"loss": 0.299,
|
| 732 |
+
"step": 2140
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 6.0,
|
| 736 |
+
"eval_f1": 0.0,
|
| 737 |
+
"eval_loss": 0.3469391465187073,
|
| 738 |
+
"eval_runtime": 20.5335,
|
| 739 |
+
"eval_samples_per_second": 93.311,
|
| 740 |
+
"eval_steps_per_second": 1.461,
|
| 741 |
+
"step": 2154
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.02,
|
| 745 |
+
"learning_rate": 0.001,
|
| 746 |
+
"loss": 0.3336,
|
| 747 |
+
"step": 2160
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 6.07,
|
| 751 |
+
"learning_rate": 0.001,
|
| 752 |
+
"loss": 0.4366,
|
| 753 |
+
"step": 2180
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 6.13,
|
| 757 |
+
"learning_rate": 0.001,
|
| 758 |
+
"loss": 0.3709,
|
| 759 |
+
"step": 2200
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 6.18,
|
| 763 |
+
"learning_rate": 0.001,
|
| 764 |
+
"loss": 0.3357,
|
| 765 |
+
"step": 2220
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.24,
|
| 769 |
+
"learning_rate": 0.001,
|
| 770 |
+
"loss": 0.4034,
|
| 771 |
+
"step": 2240
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 6.3,
|
| 775 |
+
"learning_rate": 0.001,
|
| 776 |
+
"loss": 0.3868,
|
| 777 |
+
"step": 2260
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 6.35,
|
| 781 |
+
"learning_rate": 0.001,
|
| 782 |
+
"loss": 0.3328,
|
| 783 |
+
"step": 2280
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.41,
|
| 787 |
+
"learning_rate": 0.001,
|
| 788 |
+
"loss": 0.3974,
|
| 789 |
+
"step": 2300
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.46,
|
| 793 |
+
"learning_rate": 0.001,
|
| 794 |
+
"loss": 0.3707,
|
| 795 |
+
"step": 2320
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 6.52,
|
| 799 |
+
"learning_rate": 0.001,
|
| 800 |
+
"loss": 0.3753,
|
| 801 |
+
"step": 2340
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 6.57,
|
| 805 |
+
"learning_rate": 0.001,
|
| 806 |
+
"loss": 0.3255,
|
| 807 |
+
"step": 2360
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 6.63,
|
| 811 |
+
"learning_rate": 0.001,
|
| 812 |
+
"loss": 0.4284,
|
| 813 |
+
"step": 2380
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 6.69,
|
| 817 |
+
"learning_rate": 0.001,
|
| 818 |
+
"loss": 0.3699,
|
| 819 |
+
"step": 2400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 6.74,
|
| 823 |
+
"learning_rate": 0.001,
|
| 824 |
+
"loss": 0.3705,
|
| 825 |
+
"step": 2420
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 6.8,
|
| 829 |
+
"learning_rate": 0.001,
|
| 830 |
+
"loss": 0.2841,
|
| 831 |
+
"step": 2440
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 6.85,
|
| 835 |
+
"learning_rate": 0.001,
|
| 836 |
+
"loss": 0.2687,
|
| 837 |
+
"step": 2460
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 6.91,
|
| 841 |
+
"learning_rate": 0.001,
|
| 842 |
+
"loss": 0.3294,
|
| 843 |
+
"step": 2480
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 6.96,
|
| 847 |
+
"learning_rate": 0.001,
|
| 848 |
+
"loss": 0.3531,
|
| 849 |
+
"step": 2500
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 7.0,
|
| 853 |
+
"eval_f1": 0.0,
|
| 854 |
+
"eval_loss": 0.3420043885707855,
|
| 855 |
+
"eval_runtime": 20.5195,
|
| 856 |
+
"eval_samples_per_second": 93.374,
|
| 857 |
+
"eval_steps_per_second": 1.462,
|
| 858 |
+
"step": 2513
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 7.02,
|
| 862 |
+
"learning_rate": 0.001,
|
| 863 |
+
"loss": 0.3396,
|
| 864 |
+
"step": 2520
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 7.08,
|
| 868 |
+
"learning_rate": 0.001,
|
| 869 |
+
"loss": 0.3824,
|
| 870 |
+
"step": 2540
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 7.13,
|
| 874 |
+
"learning_rate": 0.001,
|
| 875 |
+
"loss": 0.2518,
|
| 876 |
+
"step": 2560
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 7.19,
|
| 880 |
+
"learning_rate": 0.001,
|
| 881 |
+
"loss": 0.3822,
|
| 882 |
+
"step": 2580
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 7.24,
|
| 886 |
+
"learning_rate": 0.001,
|
| 887 |
+
"loss": 0.3969,
|
| 888 |
+
"step": 2600
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 7.3,
|
| 892 |
+
"learning_rate": 0.001,
|
| 893 |
+
"loss": 0.2551,
|
| 894 |
+
"step": 2620
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 7.35,
|
| 898 |
+
"learning_rate": 0.001,
|
| 899 |
+
"loss": 0.3387,
|
| 900 |
+
"step": 2640
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 7.41,
|
| 904 |
+
"learning_rate": 0.001,
|
| 905 |
+
"loss": 0.3761,
|
| 906 |
+
"step": 2660
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 7.47,
|
| 910 |
+
"learning_rate": 0.001,
|
| 911 |
+
"loss": 0.3899,
|
| 912 |
+
"step": 2680
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 7.52,
|
| 916 |
+
"learning_rate": 0.001,
|
| 917 |
+
"loss": 0.3691,
|
| 918 |
+
"step": 2700
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 7.58,
|
| 922 |
+
"learning_rate": 0.001,
|
| 923 |
+
"loss": 0.3172,
|
| 924 |
+
"step": 2720
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 7.63,
|
| 928 |
+
"learning_rate": 0.001,
|
| 929 |
+
"loss": 0.3358,
|
| 930 |
+
"step": 2740
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 7.69,
|
| 934 |
+
"learning_rate": 0.001,
|
| 935 |
+
"loss": 0.3459,
|
| 936 |
+
"step": 2760
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 7.74,
|
| 940 |
+
"learning_rate": 0.001,
|
| 941 |
+
"loss": 0.3347,
|
| 942 |
+
"step": 2780
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 7.8,
|
| 946 |
+
"learning_rate": 0.001,
|
| 947 |
+
"loss": 0.3459,
|
| 948 |
+
"step": 2800
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 7.86,
|
| 952 |
+
"learning_rate": 0.001,
|
| 953 |
+
"loss": 0.3797,
|
| 954 |
+
"step": 2820
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 7.91,
|
| 958 |
+
"learning_rate": 0.001,
|
| 959 |
+
"loss": 0.3721,
|
| 960 |
+
"step": 2840
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 7.97,
|
| 964 |
+
"learning_rate": 0.001,
|
| 965 |
+
"loss": 0.3892,
|
| 966 |
+
"step": 2860
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 8.0,
|
| 970 |
+
"eval_f1": 0.0,
|
| 971 |
+
"eval_loss": 0.34283891320228577,
|
| 972 |
+
"eval_runtime": 20.5477,
|
| 973 |
+
"eval_samples_per_second": 93.247,
|
| 974 |
+
"eval_steps_per_second": 1.46,
|
| 975 |
+
"step": 2872
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 8.02,
|
| 979 |
+
"learning_rate": 0.001,
|
| 980 |
+
"loss": 0.3234,
|
| 981 |
+
"step": 2880
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 8.08,
|
| 985 |
+
"learning_rate": 0.001,
|
| 986 |
+
"loss": 0.3979,
|
| 987 |
+
"step": 2900
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 8.13,
|
| 991 |
+
"learning_rate": 0.001,
|
| 992 |
+
"loss": 0.4032,
|
| 993 |
+
"step": 2920
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 8.19,
|
| 997 |
+
"learning_rate": 0.001,
|
| 998 |
+
"loss": 0.3787,
|
| 999 |
+
"step": 2940
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 8.25,
|
| 1003 |
+
"learning_rate": 0.001,
|
| 1004 |
+
"loss": 0.3144,
|
| 1005 |
+
"step": 2960
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 8.3,
|
| 1009 |
+
"learning_rate": 0.001,
|
| 1010 |
+
"loss": 0.4071,
|
| 1011 |
+
"step": 2980
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 8.36,
|
| 1015 |
+
"learning_rate": 0.001,
|
| 1016 |
+
"loss": 0.3192,
|
| 1017 |
+
"step": 3000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 8.41,
|
| 1021 |
+
"learning_rate": 0.001,
|
| 1022 |
+
"loss": 0.3194,
|
| 1023 |
+
"step": 3020
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 8.47,
|
| 1027 |
+
"learning_rate": 0.001,
|
| 1028 |
+
"loss": 0.3468,
|
| 1029 |
+
"step": 3040
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 8.52,
|
| 1033 |
+
"learning_rate": 0.001,
|
| 1034 |
+
"loss": 0.325,
|
| 1035 |
+
"step": 3060
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 8.58,
|
| 1039 |
+
"learning_rate": 0.001,
|
| 1040 |
+
"loss": 0.3631,
|
| 1041 |
+
"step": 3080
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 8.64,
|
| 1045 |
+
"learning_rate": 0.001,
|
| 1046 |
+
"loss": 0.3464,
|
| 1047 |
+
"step": 3100
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 8.69,
|
| 1051 |
+
"learning_rate": 0.001,
|
| 1052 |
+
"loss": 0.3378,
|
| 1053 |
+
"step": 3120
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 8.75,
|
| 1057 |
+
"learning_rate": 0.001,
|
| 1058 |
+
"loss": 0.3808,
|
| 1059 |
+
"step": 3140
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 8.8,
|
| 1063 |
+
"learning_rate": 0.001,
|
| 1064 |
+
"loss": 0.3668,
|
| 1065 |
+
"step": 3160
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 8.86,
|
| 1069 |
+
"learning_rate": 0.001,
|
| 1070 |
+
"loss": 0.3045,
|
| 1071 |
+
"step": 3180
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 8.91,
|
| 1075 |
+
"learning_rate": 0.001,
|
| 1076 |
+
"loss": 0.2805,
|
| 1077 |
+
"step": 3200
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 8.97,
|
| 1081 |
+
"learning_rate": 0.001,
|
| 1082 |
+
"loss": 0.3706,
|
| 1083 |
+
"step": 3220
|
| 1084 |
+
},
|
| 1085 |
{
|
| 1086 |
"epoch": 9.0,
|
| 1087 |
+
"eval_f1": 0.0,
|
| 1088 |
+
"eval_loss": 0.3420598804950714,
|
| 1089 |
+
"eval_runtime": 20.5266,
|
| 1090 |
+
"eval_samples_per_second": 93.342,
|
| 1091 |
+
"eval_steps_per_second": 1.462,
|
| 1092 |
+
"step": 3231
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 9.03,
|
| 1096 |
+
"learning_rate": 0.001,
|
| 1097 |
+
"loss": 0.3502,
|
| 1098 |
+
"step": 3240
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 9.08,
|
| 1102 |
+
"learning_rate": 0.001,
|
| 1103 |
+
"loss": 0.3414,
|
| 1104 |
+
"step": 3260
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
"epoch": 9.14,
|
| 1108 |
+
"learning_rate": 0.001,
|
| 1109 |
+
"loss": 0.4037,
|
| 1110 |
+
"step": 3280
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 9.19,
|
| 1114 |
+
"learning_rate": 0.001,
|
| 1115 |
+
"loss": 0.3548,
|
| 1116 |
+
"step": 3300
|
| 1117 |
},
|
| 1118 |
{
|
| 1119 |
"epoch": 9.25,
|
| 1120 |
+
"learning_rate": 0.001,
|
| 1121 |
+
"loss": 0.3426,
|
| 1122 |
+
"step": 3320
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 9.3,
|
| 1126 |
+
"learning_rate": 0.001,
|
| 1127 |
+
"loss": 0.3614,
|
| 1128 |
+
"step": 3340
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
"epoch": 9.36,
|
| 1132 |
+
"learning_rate": 0.001,
|
| 1133 |
+
"loss": 0.2505,
|
| 1134 |
+
"step": 3360
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 9.42,
|
| 1138 |
+
"learning_rate": 0.001,
|
| 1139 |
+
"loss": 0.402,
|
| 1140 |
+
"step": 3380
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 9.47,
|
| 1144 |
+
"learning_rate": 0.001,
|
| 1145 |
+
"loss": 0.3029,
|
| 1146 |
+
"step": 3400
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 9.53,
|
| 1150 |
+
"learning_rate": 0.001,
|
| 1151 |
+
"loss": 0.2799,
|
| 1152 |
+
"step": 3420
|
| 1153 |
},
|
| 1154 |
{
|
| 1155 |
"epoch": 9.58,
|
| 1156 |
+
"learning_rate": 0.001,
|
| 1157 |
+
"loss": 0.3046,
|
| 1158 |
+
"step": 3440
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 9.64,
|
| 1162 |
+
"learning_rate": 0.001,
|
| 1163 |
+
"loss": 0.3707,
|
| 1164 |
+
"step": 3460
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 9.69,
|
| 1168 |
+
"learning_rate": 0.001,
|
| 1169 |
+
"loss": 0.3417,
|
| 1170 |
+
"step": 3480
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 9.75,
|
| 1174 |
+
"learning_rate": 0.001,
|
| 1175 |
+
"loss": 0.3826,
|
| 1176 |
+
"step": 3500
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
"epoch": 9.81,
|
| 1180 |
+
"learning_rate": 0.001,
|
| 1181 |
+
"loss": 0.3658,
|
| 1182 |
+
"step": 3520
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
+
"epoch": 9.86,
|
| 1186 |
+
"learning_rate": 0.001,
|
| 1187 |
+
"loss": 0.3185,
|
| 1188 |
+
"step": 3540
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
+
"epoch": 9.92,
|
| 1192 |
+
"learning_rate": 0.001,
|
| 1193 |
+
"loss": 0.3596,
|
| 1194 |
+
"step": 3560
|
|
|
|
|
|
|
|
|
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 9.97,
|
| 1198 |
+
"learning_rate": 0.001,
|
| 1199 |
+
"loss": 0.3863,
|
| 1200 |
+
"step": 3580
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 10.0,
|
| 1204 |
+
"eval_f1": 0.0,
|
| 1205 |
+
"eval_loss": 0.34448280930519104,
|
| 1206 |
+
"eval_runtime": 20.4875,
|
| 1207 |
+
"eval_samples_per_second": 93.52,
|
| 1208 |
+
"eval_steps_per_second": 1.464,
|
| 1209 |
+
"step": 3590
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 10.0,
|
| 1213 |
+
"step": 3590,
|
| 1214 |
+
"total_flos": 3792562624069632.0,
|
| 1215 |
+
"train_loss": 0.3510875488058106,
|
| 1216 |
+
"train_runtime": 3949.5247,
|
| 1217 |
+
"train_samples_per_second": 14.541,
|
| 1218 |
+
"train_steps_per_second": 0.909
|
| 1219 |
}
|
| 1220 |
],
|
| 1221 |
"logging_steps": 20,
|
| 1222 |
+
"max_steps": 3590,
|
| 1223 |
"num_input_tokens_seen": 0,
|
| 1224 |
"num_train_epochs": 10,
|
| 1225 |
"save_steps": 500,
|
| 1226 |
+
"total_flos": 3792562624069632.0,
|
| 1227 |
"train_batch_size": 2,
|
| 1228 |
"trial_name": null,
|
| 1229 |
"trial_params": null
|