Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9446744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0b2fd96be9e417d5d6f304a4210773971e9997b100bc7da11bc7833c74c2e1a
|
| 3 |
size 9446744
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4879947
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04bddb6ded0a1f1787c0358fa5d9011cfb6a8d4879da9aa6640dc1a23c6261c9
|
| 3 |
size 4879947
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cca0cc36ce508f9f73602af4b17bc20b7752794b9df1c841a407fc3a8f4259e5
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1212f45ec506488b3c2a5d87d5981e35aff2ecde16f227f5da77f6a20ca2dc60
|
| 3 |
size 14917
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7196236c160a95c8aa5e1b3aea8fb1afcddeca010033d3cfc622187dfc73bcd0
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 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,
|
|
@@ -508,6 +508,506 @@
|
|
| 508 |
"mean_token_accuracy": 0.6013776436448097,
|
| 509 |
"num_tokens": 2977952.0,
|
| 510 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 511 |
}
|
| 512 |
],
|
| 513 |
"logging_steps": 10,
|
|
@@ -527,7 +1027,7 @@
|
|
| 527 |
"attributes": {}
|
| 528 |
}
|
| 529 |
},
|
| 530 |
-
"total_flos":
|
| 531 |
"train_batch_size": 2,
|
| 532 |
"trial_name": null,
|
| 533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.7186761229314422,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 508 |
"mean_token_accuracy": 0.6013776436448097,
|
| 509 |
"num_tokens": 2977952.0,
|
| 510 |
"step": 500
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"entropy": 2.0694020837545395,
|
| 514 |
+
"epoch": 0.8768536428110896,
|
| 515 |
+
"grad_norm": 0.6112110614776611,
|
| 516 |
+
"learning_rate": 0.00017964,
|
| 517 |
+
"loss": 2.1932716369628906,
|
| 518 |
+
"mean_token_accuracy": 0.6094281867146492,
|
| 519 |
+
"num_tokens": 3039858.0,
|
| 520 |
+
"step": 510
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"entropy": 2.074494983255863,
|
| 524 |
+
"epoch": 0.89404685149366,
|
| 525 |
+
"grad_norm": 0.6264903545379639,
|
| 526 |
+
"learning_rate": 0.00017924,
|
| 527 |
+
"loss": 2.1746356964111326,
|
| 528 |
+
"mean_token_accuracy": 0.6137691352516412,
|
| 529 |
+
"num_tokens": 3095095.0,
|
| 530 |
+
"step": 520
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"entropy": 2.1704643085598945,
|
| 534 |
+
"epoch": 0.9112400601762304,
|
| 535 |
+
"grad_norm": 0.5588786602020264,
|
| 536 |
+
"learning_rate": 0.00017884000000000002,
|
| 537 |
+
"loss": 2.256443977355957,
|
| 538 |
+
"mean_token_accuracy": 0.6048448126763105,
|
| 539 |
+
"num_tokens": 3154541.0,
|
| 540 |
+
"step": 530
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"entropy": 2.0287919655442237,
|
| 544 |
+
"epoch": 0.9284332688588007,
|
| 545 |
+
"grad_norm": 0.5964768528938293,
|
| 546 |
+
"learning_rate": 0.00017844,
|
| 547 |
+
"loss": 2.1472768783569336,
|
| 548 |
+
"mean_token_accuracy": 0.6183896280825139,
|
| 549 |
+
"num_tokens": 3213587.0,
|
| 550 |
+
"step": 540
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"entropy": 2.0924746826291085,
|
| 554 |
+
"epoch": 0.9456264775413712,
|
| 555 |
+
"grad_norm": 0.6021146774291992,
|
| 556 |
+
"learning_rate": 0.00017804,
|
| 557 |
+
"loss": 2.194413757324219,
|
| 558 |
+
"mean_token_accuracy": 0.6094567842781544,
|
| 559 |
+
"num_tokens": 3270420.0,
|
| 560 |
+
"step": 550
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"entropy": 2.2008628591895105,
|
| 564 |
+
"epoch": 0.9628196862239415,
|
| 565 |
+
"grad_norm": 0.5850458741188049,
|
| 566 |
+
"learning_rate": 0.00017764000000000001,
|
| 567 |
+
"loss": 2.325449752807617,
|
| 568 |
+
"mean_token_accuracy": 0.5982100035995245,
|
| 569 |
+
"num_tokens": 3329358.0,
|
| 570 |
+
"step": 560
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"entropy": 2.065661500394344,
|
| 574 |
+
"epoch": 0.9800128949065119,
|
| 575 |
+
"grad_norm": 0.5808996558189392,
|
| 576 |
+
"learning_rate": 0.00017724,
|
| 577 |
+
"loss": 2.197132873535156,
|
| 578 |
+
"mean_token_accuracy": 0.614894449710846,
|
| 579 |
+
"num_tokens": 3389408.0,
|
| 580 |
+
"step": 570
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"entropy": 2.0561472952365873,
|
| 584 |
+
"epoch": 0.9972061035890823,
|
| 585 |
+
"grad_norm": 0.5550947189331055,
|
| 586 |
+
"learning_rate": 0.00017684,
|
| 587 |
+
"loss": 2.1736166000366213,
|
| 588 |
+
"mean_token_accuracy": 0.6167749039828777,
|
| 589 |
+
"num_tokens": 3448108.0,
|
| 590 |
+
"step": 580
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"entropy": 2.017703249857023,
|
| 594 |
+
"epoch": 1.0137545669460564,
|
| 595 |
+
"grad_norm": 0.5885869860649109,
|
| 596 |
+
"learning_rate": 0.00017644,
|
| 597 |
+
"loss": 2.093535614013672,
|
| 598 |
+
"mean_token_accuracy": 0.623307110427262,
|
| 599 |
+
"num_tokens": 3510556.0,
|
| 600 |
+
"step": 590
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"entropy": 2.0724975898861886,
|
| 604 |
+
"epoch": 1.0309477756286267,
|
| 605 |
+
"grad_norm": 0.6038488745689392,
|
| 606 |
+
"learning_rate": 0.00017604,
|
| 607 |
+
"loss": 2.1512643814086916,
|
| 608 |
+
"mean_token_accuracy": 0.6218964882194996,
|
| 609 |
+
"num_tokens": 3572796.0,
|
| 610 |
+
"step": 600
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"entropy": 2.0171437337994576,
|
| 614 |
+
"epoch": 1.048140984311197,
|
| 615 |
+
"grad_norm": 0.5356580018997192,
|
| 616 |
+
"learning_rate": 0.00017564,
|
| 617 |
+
"loss": 2.1061470031738283,
|
| 618 |
+
"mean_token_accuracy": 0.6229204799979925,
|
| 619 |
+
"num_tokens": 3636040.0,
|
| 620 |
+
"step": 610
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy": 2.069349633157253,
|
| 624 |
+
"epoch": 1.0653341929937674,
|
| 625 |
+
"grad_norm": 0.6440969109535217,
|
| 626 |
+
"learning_rate": 0.00017524,
|
| 627 |
+
"loss": 2.1538244247436524,
|
| 628 |
+
"mean_token_accuracy": 0.6151916943490505,
|
| 629 |
+
"num_tokens": 3692494.0,
|
| 630 |
+
"step": 620
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"entropy": 1.9605562821030618,
|
| 634 |
+
"epoch": 1.0825274016763378,
|
| 635 |
+
"grad_norm": 0.6160545349121094,
|
| 636 |
+
"learning_rate": 0.00017484,
|
| 637 |
+
"loss": 2.036081314086914,
|
| 638 |
+
"mean_token_accuracy": 0.6326734255999327,
|
| 639 |
+
"num_tokens": 3750269.0,
|
| 640 |
+
"step": 630
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"entropy": 1.9889371052384377,
|
| 644 |
+
"epoch": 1.0997206103589083,
|
| 645 |
+
"grad_norm": 0.6164005398750305,
|
| 646 |
+
"learning_rate": 0.00017444,
|
| 647 |
+
"loss": 2.051021194458008,
|
| 648 |
+
"mean_token_accuracy": 0.6301001563668251,
|
| 649 |
+
"num_tokens": 3808993.0,
|
| 650 |
+
"step": 640
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"entropy": 2.1208505019545556,
|
| 654 |
+
"epoch": 1.1169138190414787,
|
| 655 |
+
"grad_norm": 0.5549023151397705,
|
| 656 |
+
"learning_rate": 0.00017404,
|
| 657 |
+
"loss": 2.2218536376953124,
|
| 658 |
+
"mean_token_accuracy": 0.6127480801194907,
|
| 659 |
+
"num_tokens": 3875366.0,
|
| 660 |
+
"step": 650
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"entropy": 2.0680324912071226,
|
| 664 |
+
"epoch": 1.134107027724049,
|
| 665 |
+
"grad_norm": 0.6039656400680542,
|
| 666 |
+
"learning_rate": 0.00017364,
|
| 667 |
+
"loss": 2.1767093658447267,
|
| 668 |
+
"mean_token_accuracy": 0.61400815397501,
|
| 669 |
+
"num_tokens": 3936258.0,
|
| 670 |
+
"step": 660
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"entropy": 2.072723534703255,
|
| 674 |
+
"epoch": 1.1513002364066194,
|
| 675 |
+
"grad_norm": 0.5685736536979675,
|
| 676 |
+
"learning_rate": 0.00017324000000000002,
|
| 677 |
+
"loss": 2.16034049987793,
|
| 678 |
+
"mean_token_accuracy": 0.6158209484070539,
|
| 679 |
+
"num_tokens": 3996786.0,
|
| 680 |
+
"step": 670
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"entropy": 2.0064551383256912,
|
| 684 |
+
"epoch": 1.1684934450891897,
|
| 685 |
+
"grad_norm": 0.6133168935775757,
|
| 686 |
+
"learning_rate": 0.00017284,
|
| 687 |
+
"loss": 2.0968536376953124,
|
| 688 |
+
"mean_token_accuracy": 0.6204963065683842,
|
| 689 |
+
"num_tokens": 4057237.0,
|
| 690 |
+
"step": 680
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"entropy": 1.999112318456173,
|
| 694 |
+
"epoch": 1.18568665377176,
|
| 695 |
+
"grad_norm": 0.6392707228660583,
|
| 696 |
+
"learning_rate": 0.00017244,
|
| 697 |
+
"loss": 2.1093589782714846,
|
| 698 |
+
"mean_token_accuracy": 0.6260342009365558,
|
| 699 |
+
"num_tokens": 4115641.0,
|
| 700 |
+
"step": 690
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"entropy": 1.9792790532112121,
|
| 704 |
+
"epoch": 1.2028798624543304,
|
| 705 |
+
"grad_norm": 0.5575782656669617,
|
| 706 |
+
"learning_rate": 0.00017204,
|
| 707 |
+
"loss": 2.097017288208008,
|
| 708 |
+
"mean_token_accuracy": 0.6311597619205713,
|
| 709 |
+
"num_tokens": 4179186.0,
|
| 710 |
+
"step": 700
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy": 2.0830755099654197,
|
| 714 |
+
"epoch": 1.220073071136901,
|
| 715 |
+
"grad_norm": 0.5660914182662964,
|
| 716 |
+
"learning_rate": 0.00017164,
|
| 717 |
+
"loss": 2.1811811447143556,
|
| 718 |
+
"mean_token_accuracy": 0.6163320489227772,
|
| 719 |
+
"num_tokens": 4239862.0,
|
| 720 |
+
"step": 710
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"entropy": 2.0135093346238135,
|
| 724 |
+
"epoch": 1.2372662798194713,
|
| 725 |
+
"grad_norm": 0.535127580165863,
|
| 726 |
+
"learning_rate": 0.00017124,
|
| 727 |
+
"loss": 2.1185089111328126,
|
| 728 |
+
"mean_token_accuracy": 0.6227246847003698,
|
| 729 |
+
"num_tokens": 4299020.0,
|
| 730 |
+
"step": 720
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"entropy": 2.0245131298899652,
|
| 734 |
+
"epoch": 1.2544594885020417,
|
| 735 |
+
"grad_norm": 0.5870150327682495,
|
| 736 |
+
"learning_rate": 0.00017084,
|
| 737 |
+
"loss": 2.1228567123413087,
|
| 738 |
+
"mean_token_accuracy": 0.620493221282959,
|
| 739 |
+
"num_tokens": 4357565.0,
|
| 740 |
+
"step": 730
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"entropy": 2.0833021104335785,
|
| 744 |
+
"epoch": 1.271652697184612,
|
| 745 |
+
"grad_norm": 0.6691998243331909,
|
| 746 |
+
"learning_rate": 0.00017044,
|
| 747 |
+
"loss": 2.1688915252685548,
|
| 748 |
+
"mean_token_accuracy": 0.6160433337092399,
|
| 749 |
+
"num_tokens": 4416113.0,
|
| 750 |
+
"step": 740
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"entropy": 1.9562881767749787,
|
| 754 |
+
"epoch": 1.2888459058671824,
|
| 755 |
+
"grad_norm": 0.5513840317726135,
|
| 756 |
+
"learning_rate": 0.00017004,
|
| 757 |
+
"loss": 2.038709831237793,
|
| 758 |
+
"mean_token_accuracy": 0.6274638958275318,
|
| 759 |
+
"num_tokens": 4479913.0,
|
| 760 |
+
"step": 750
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"entropy": 2.0899336978793146,
|
| 764 |
+
"epoch": 1.306039114549753,
|
| 765 |
+
"grad_norm": 0.6334884166717529,
|
| 766 |
+
"learning_rate": 0.00016964,
|
| 767 |
+
"loss": 2.1464771270751952,
|
| 768 |
+
"mean_token_accuracy": 0.6156820185482502,
|
| 769 |
+
"num_tokens": 4538630.0,
|
| 770 |
+
"step": 760
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"entropy": 2.006402041018009,
|
| 774 |
+
"epoch": 1.3232323232323233,
|
| 775 |
+
"grad_norm": 0.6608359813690186,
|
| 776 |
+
"learning_rate": 0.00016924,
|
| 777 |
+
"loss": 2.0910036087036135,
|
| 778 |
+
"mean_token_accuracy": 0.6266825262457132,
|
| 779 |
+
"num_tokens": 4596432.0,
|
| 780 |
+
"step": 770
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"entropy": 1.981143780052662,
|
| 784 |
+
"epoch": 1.3404255319148937,
|
| 785 |
+
"grad_norm": 0.6512318849563599,
|
| 786 |
+
"learning_rate": 0.00016884,
|
| 787 |
+
"loss": 2.0733022689819336,
|
| 788 |
+
"mean_token_accuracy": 0.6271612212061882,
|
| 789 |
+
"num_tokens": 4653388.0,
|
| 790 |
+
"step": 780
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"entropy": 2.046033799648285,
|
| 794 |
+
"epoch": 1.357618740597464,
|
| 795 |
+
"grad_norm": 0.657543957233429,
|
| 796 |
+
"learning_rate": 0.00016844,
|
| 797 |
+
"loss": 2.122422790527344,
|
| 798 |
+
"mean_token_accuracy": 0.6139081876724959,
|
| 799 |
+
"num_tokens": 4707749.0,
|
| 800 |
+
"step": 790
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"entropy": 2.0472232535481454,
|
| 804 |
+
"epoch": 1.3748119492800344,
|
| 805 |
+
"grad_norm": 0.5705983638763428,
|
| 806 |
+
"learning_rate": 0.00016804,
|
| 807 |
+
"loss": 2.1095462799072267,
|
| 808 |
+
"mean_token_accuracy": 0.6147159416228533,
|
| 809 |
+
"num_tokens": 4768198.0,
|
| 810 |
+
"step": 800
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"entropy": 2.0032111018896104,
|
| 814 |
+
"epoch": 1.3920051579626047,
|
| 815 |
+
"grad_norm": 0.6248787045478821,
|
| 816 |
+
"learning_rate": 0.00016764,
|
| 817 |
+
"loss": 2.06416015625,
|
| 818 |
+
"mean_token_accuracy": 0.626778207719326,
|
| 819 |
+
"num_tokens": 4830049.0,
|
| 820 |
+
"step": 810
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"entropy": 2.008875849843025,
|
| 824 |
+
"epoch": 1.409198366645175,
|
| 825 |
+
"grad_norm": 0.6245584487915039,
|
| 826 |
+
"learning_rate": 0.00016724000000000003,
|
| 827 |
+
"loss": 2.096910285949707,
|
| 828 |
+
"mean_token_accuracy": 0.626385198161006,
|
| 829 |
+
"num_tokens": 4887278.0,
|
| 830 |
+
"step": 820
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"entropy": 2.080148513615131,
|
| 834 |
+
"epoch": 1.4263915753277456,
|
| 835 |
+
"grad_norm": 0.6255568861961365,
|
| 836 |
+
"learning_rate": 0.00016684000000000002,
|
| 837 |
+
"loss": 2.1830982208251952,
|
| 838 |
+
"mean_token_accuracy": 0.6152387134730816,
|
| 839 |
+
"num_tokens": 4946401.0,
|
| 840 |
+
"step": 830
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"entropy": 1.999508222937584,
|
| 844 |
+
"epoch": 1.443584784010316,
|
| 845 |
+
"grad_norm": 0.6275898218154907,
|
| 846 |
+
"learning_rate": 0.00016644,
|
| 847 |
+
"loss": 2.1005062103271483,
|
| 848 |
+
"mean_token_accuracy": 0.6225087266415358,
|
| 849 |
+
"num_tokens": 5007769.0,
|
| 850 |
+
"step": 840
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"entropy": 1.937928880751133,
|
| 854 |
+
"epoch": 1.4607779926928863,
|
| 855 |
+
"grad_norm": 0.5719529986381531,
|
| 856 |
+
"learning_rate": 0.00016604000000000003,
|
| 857 |
+
"loss": 2.026857376098633,
|
| 858 |
+
"mean_token_accuracy": 0.6374159537255764,
|
| 859 |
+
"num_tokens": 5065155.0,
|
| 860 |
+
"step": 850
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"entropy": 2.0230891808867453,
|
| 864 |
+
"epoch": 1.4779712013754567,
|
| 865 |
+
"grad_norm": 0.6000656485557556,
|
| 866 |
+
"learning_rate": 0.00016564000000000002,
|
| 867 |
+
"loss": 2.1284557342529298,
|
| 868 |
+
"mean_token_accuracy": 0.6221452355384827,
|
| 869 |
+
"num_tokens": 5127964.0,
|
| 870 |
+
"step": 860
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"entropy": 2.0356423661112784,
|
| 874 |
+
"epoch": 1.495164410058027,
|
| 875 |
+
"grad_norm": 0.6452302932739258,
|
| 876 |
+
"learning_rate": 0.00016524,
|
| 877 |
+
"loss": 2.136619758605957,
|
| 878 |
+
"mean_token_accuracy": 0.6180427376180887,
|
| 879 |
+
"num_tokens": 5186867.0,
|
| 880 |
+
"step": 870
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"entropy": 1.980474129319191,
|
| 884 |
+
"epoch": 1.5123576187405976,
|
| 885 |
+
"grad_norm": 0.6840422749519348,
|
| 886 |
+
"learning_rate": 0.00016484000000000003,
|
| 887 |
+
"loss": 2.1068920135498046,
|
| 888 |
+
"mean_token_accuracy": 0.6276284489780665,
|
| 889 |
+
"num_tokens": 5243496.0,
|
| 890 |
+
"step": 880
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"entropy": 1.9933902084827424,
|
| 894 |
+
"epoch": 1.5295508274231677,
|
| 895 |
+
"grad_norm": 0.6497262716293335,
|
| 896 |
+
"learning_rate": 0.00016444000000000002,
|
| 897 |
+
"loss": 2.0951356887817383,
|
| 898 |
+
"mean_token_accuracy": 0.625996507704258,
|
| 899 |
+
"num_tokens": 5305224.0,
|
| 900 |
+
"step": 890
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"entropy": 1.9787120044231414,
|
| 904 |
+
"epoch": 1.5467440361057383,
|
| 905 |
+
"grad_norm": 0.5943708419799805,
|
| 906 |
+
"learning_rate": 0.00016404,
|
| 907 |
+
"loss": 2.050846481323242,
|
| 908 |
+
"mean_token_accuracy": 0.6277968011796474,
|
| 909 |
+
"num_tokens": 5362047.0,
|
| 910 |
+
"step": 900
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"entropy": 1.9207568421959877,
|
| 914 |
+
"epoch": 1.5639372447883086,
|
| 915 |
+
"grad_norm": 0.7813357710838318,
|
| 916 |
+
"learning_rate": 0.00016364000000000003,
|
| 917 |
+
"loss": 2.01483097076416,
|
| 918 |
+
"mean_token_accuracy": 0.6335461936891079,
|
| 919 |
+
"num_tokens": 5418646.0,
|
| 920 |
+
"step": 910
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"entropy": 1.991297036409378,
|
| 924 |
+
"epoch": 1.581130453470879,
|
| 925 |
+
"grad_norm": 0.6333187818527222,
|
| 926 |
+
"learning_rate": 0.00016324000000000002,
|
| 927 |
+
"loss": 2.042116165161133,
|
| 928 |
+
"mean_token_accuracy": 0.6277558326721191,
|
| 929 |
+
"num_tokens": 5474990.0,
|
| 930 |
+
"step": 920
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"entropy": 2.049289306998253,
|
| 934 |
+
"epoch": 1.5983236621534493,
|
| 935 |
+
"grad_norm": 0.6549156308174133,
|
| 936 |
+
"learning_rate": 0.00016284,
|
| 937 |
+
"loss": 2.160791778564453,
|
| 938 |
+
"mean_token_accuracy": 0.6178662430495023,
|
| 939 |
+
"num_tokens": 5536798.0,
|
| 940 |
+
"step": 930
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"entropy": 2.0044725999236106,
|
| 944 |
+
"epoch": 1.6155168708360197,
|
| 945 |
+
"grad_norm": 0.7054678201675415,
|
| 946 |
+
"learning_rate": 0.00016244000000000002,
|
| 947 |
+
"loss": 2.1012857437133787,
|
| 948 |
+
"mean_token_accuracy": 0.6249351866543293,
|
| 949 |
+
"num_tokens": 5592825.0,
|
| 950 |
+
"step": 940
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"entropy": 1.8883072763681412,
|
| 954 |
+
"epoch": 1.6327100795185903,
|
| 955 |
+
"grad_norm": 0.6150692701339722,
|
| 956 |
+
"learning_rate": 0.00016204000000000001,
|
| 957 |
+
"loss": 1.933417510986328,
|
| 958 |
+
"mean_token_accuracy": 0.6382322389632463,
|
| 959 |
+
"num_tokens": 5647293.0,
|
| 960 |
+
"step": 950
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"entropy": 1.9773345232009887,
|
| 964 |
+
"epoch": 1.6499032882011604,
|
| 965 |
+
"grad_norm": 0.6604284048080444,
|
| 966 |
+
"learning_rate": 0.00016164,
|
| 967 |
+
"loss": 2.0537574768066404,
|
| 968 |
+
"mean_token_accuracy": 0.6284147780388594,
|
| 969 |
+
"num_tokens": 5707851.0,
|
| 970 |
+
"step": 960
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"entropy": 1.9602369159460067,
|
| 974 |
+
"epoch": 1.667096496883731,
|
| 975 |
+
"grad_norm": 0.5877639055252075,
|
| 976 |
+
"learning_rate": 0.00016124000000000002,
|
| 977 |
+
"loss": 2.0338172912597656,
|
| 978 |
+
"mean_token_accuracy": 0.6378967847675086,
|
| 979 |
+
"num_tokens": 5766339.0,
|
| 980 |
+
"step": 970
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"entropy": 2.0475835338234902,
|
| 984 |
+
"epoch": 1.6842897055663013,
|
| 985 |
+
"grad_norm": 0.6029936075210571,
|
| 986 |
+
"learning_rate": 0.00016084,
|
| 987 |
+
"loss": 2.161564254760742,
|
| 988 |
+
"mean_token_accuracy": 0.6204672615975142,
|
| 989 |
+
"num_tokens": 5827901.0,
|
| 990 |
+
"step": 980
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"entropy": 1.9963667973876,
|
| 994 |
+
"epoch": 1.7014829142488717,
|
| 995 |
+
"grad_norm": 0.6379806399345398,
|
| 996 |
+
"learning_rate": 0.00016044,
|
| 997 |
+
"loss": 2.087441825866699,
|
| 998 |
+
"mean_token_accuracy": 0.6302045777440071,
|
| 999 |
+
"num_tokens": 5888724.0,
|
| 1000 |
+
"step": 990
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"entropy": 2.003598253428936,
|
| 1004 |
+
"epoch": 1.7186761229314422,
|
| 1005 |
+
"grad_norm": 0.6113580465316772,
|
| 1006 |
+
"learning_rate": 0.00016004000000000002,
|
| 1007 |
+
"loss": 2.136977195739746,
|
| 1008 |
+
"mean_token_accuracy": 0.6279609728604555,
|
| 1009 |
+
"num_tokens": 5948999.0,
|
| 1010 |
+
"step": 1000
|
| 1011 |
}
|
| 1012 |
],
|
| 1013 |
"logging_steps": 10,
|
|
|
|
| 1027 |
"attributes": {}
|
| 1028 |
}
|
| 1029 |
},
|
| 1030 |
+
"total_flos": 4.87917948502016e+16,
|
| 1031 |
"train_batch_size": 2,
|
| 1032 |
"trial_name": null,
|
| 1033 |
"trial_params": null
|