Training in progress, epoch 3, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
|
@@ -909,6 +909,36 @@ You can finetune this model on your own dataset.
|
|
| 909 |
| 1.8915 | 5300 | 2.0528 | - | - | - |
|
| 910 |
| 1.9293 | 5406 | 2.4979 | - | - | - |
|
| 911 |
| 1.9672 | 5512 | 2.6698 | - | - | - |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 912 |
|
| 913 |
|
| 914 |
### Framework Versions
|
|
|
|
| 909 |
| 1.8915 | 5300 | 2.0528 | - | - | - |
|
| 910 |
| 1.9293 | 5406 | 2.4979 | - | - | - |
|
| 911 |
| 1.9672 | 5512 | 2.6698 | - | - | - |
|
| 912 |
+
| 2.0050 | 5618 | 3.2147 | - | - | - |
|
| 913 |
+
| 2.0428 | 5724 | 2.4885 | - | - | - |
|
| 914 |
+
| 2.0807 | 5830 | 2.5061 | - | - | - |
|
| 915 |
+
| 2.1010 | 5887 | - | 1.4211 | 2.3481 | 1.8698 |
|
| 916 |
+
| 2.1185 | 5936 | 2.285 | - | - | - |
|
| 917 |
+
| 2.1563 | 6042 | 2.6148 | - | - | - |
|
| 918 |
+
| 2.1941 | 6148 | 2.4811 | - | - | - |
|
| 919 |
+
| 2.2320 | 6254 | 2.0681 | - | - | - |
|
| 920 |
+
| 2.2698 | 6360 | 2.4426 | - | - | - |
|
| 921 |
+
| 2.3076 | 6466 | 2.5273 | - | - | - |
|
| 922 |
+
| 2.3455 | 6572 | 2.1097 | - | - | - |
|
| 923 |
+
| 2.3833 | 6678 | 2.8945 | - | - | - |
|
| 924 |
+
| 2.4011 | 6728 | - | 1.3394 | 2.6094 | 1.8919 |
|
| 925 |
+
| 2.4211 | 6784 | 2.2264 | - | - | - |
|
| 926 |
+
| 2.4590 | 6890 | 2.5986 | - | - | - |
|
| 927 |
+
| 2.4968 | 6996 | 2.3359 | - | - | - |
|
| 928 |
+
| 2.5346 | 7102 | 1.857 | - | - | - |
|
| 929 |
+
| 2.5724 | 7208 | 2.0381 | - | - | - |
|
| 930 |
+
| 2.6103 | 7314 | 2.0267 | - | - | - |
|
| 931 |
+
| 2.6481 | 7420 | 2.0914 | - | - | - |
|
| 932 |
+
| 2.6859 | 7526 | 1.9207 | - | - | - |
|
| 933 |
+
| 2.7013 | 7569 | - | 1.2556 | 2.2631 | 1.7135 |
|
| 934 |
+
| 2.7238 | 7632 | 2.034 | - | - | - |
|
| 935 |
+
| 2.7616 | 7738 | 2.2729 | - | - | - |
|
| 936 |
+
| 2.7994 | 7844 | 1.936 | - | - | - |
|
| 937 |
+
| 2.8373 | 7950 | 2.1102 | - | - | - |
|
| 938 |
+
| 2.8751 | 8056 | 1.6607 | - | - | - |
|
| 939 |
+
| 2.9129 | 8162 | 1.9579 | - | - | - |
|
| 940 |
+
| 2.9507 | 8268 | 2.4587 | - | - | - |
|
| 941 |
+
| 2.9886 | 8374 | 2.78 | - | - | - |
|
| 942 |
|
| 943 |
|
| 944 |
### Framework Versions
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1130520122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d9cebfb9a7e7e64a849e1dc8b049ade66359af20bc5e5427afbd57e05b40900
|
| 3 |
size 1130520122
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 565251810
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f34180c7a5cfade436f788a1c7db68ba2b2b8f1b0ab5e9c255945f7eb66fc4b5
|
| 3 |
size 565251810
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bb4a8ca87963bbe30445f59452f5ad16501c0976db609eeadd04b352fae8489
|
| 3 |
size 14244
|
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:a2a7cf6f0bbd2aeaecb5ee82eab7e9d52a1b4ca5b1640948aa8f69d7015a851c
|
| 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":
|
| 5 |
"eval_steps": 841,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -515,6 +515,267 @@
|
|
| 515 |
"learning_rate": 6.3209786741211076e-06,
|
| 516 |
"loss": 2.6698,
|
| 517 |
"step": 5512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 518 |
}
|
| 519 |
],
|
| 520 |
"logging_steps": 106,
|
|
@@ -529,7 +790,7 @@
|
|
| 529 |
"should_evaluate": false,
|
| 530 |
"should_log": false,
|
| 531 |
"should_save": true,
|
| 532 |
-
"should_training_stop":
|
| 533 |
},
|
| 534 |
"attributes": {}
|
| 535 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 841,
|
| 6 |
+
"global_step": 8406,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 515 |
"learning_rate": 6.3209786741211076e-06,
|
| 516 |
"loss": 2.6698,
|
| 517 |
"step": 5512
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.0049964311206283,
|
| 521 |
+
"grad_norm": 25.162227630615234,
|
| 522 |
+
"learning_rate": 4.89963760685911e-06,
|
| 523 |
+
"loss": 3.2147,
|
| 524 |
+
"step": 5618
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.0428265524625266,
|
| 528 |
+
"grad_norm": 5.108881950378418,
|
| 529 |
+
"learning_rate": 3.60612086314475e-06,
|
| 530 |
+
"loss": 2.4885,
|
| 531 |
+
"step": 5724
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.0806566738044254,
|
| 535 |
+
"grad_norm": 18.789485931396484,
|
| 536 |
+
"learning_rate": 2.4728463164579917e-06,
|
| 537 |
+
"loss": 2.5061,
|
| 538 |
+
"step": 5830
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.1009992862241256,
|
| 542 |
+
"eval_nli-pairs_loss": 1.8698406219482422,
|
| 543 |
+
"eval_nli-pairs_runtime": 6.3174,
|
| 544 |
+
"eval_nli-pairs_samples_per_second": 118.72,
|
| 545 |
+
"eval_nli-pairs_steps_per_second": 6.648,
|
| 546 |
+
"step": 5887
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.1009992862241256,
|
| 550 |
+
"eval_scitail-pairs-pos_loss": 1.4210681915283203,
|
| 551 |
+
"eval_scitail-pairs-pos_runtime": 7.5787,
|
| 552 |
+
"eval_scitail-pairs-pos_samples_per_second": 98.961,
|
| 553 |
+
"eval_scitail-pairs-pos_steps_per_second": 5.542,
|
| 554 |
+
"step": 5887
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.1009992862241256,
|
| 558 |
+
"eval_qnli-contrastive_loss": 2.348076105117798,
|
| 559 |
+
"eval_qnli-contrastive_runtime": 2.4643,
|
| 560 |
+
"eval_qnli-contrastive_samples_per_second": 304.346,
|
| 561 |
+
"eval_qnli-contrastive_steps_per_second": 17.043,
|
| 562 |
+
"step": 5887
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.118486795146324,
|
| 566 |
+
"grad_norm": 24.064834594726562,
|
| 567 |
+
"learning_rate": 1.5282158804586934e-06,
|
| 568 |
+
"loss": 2.285,
|
| 569 |
+
"step": 5936
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.1563169164882225,
|
| 573 |
+
"grad_norm": 17.475284576416016,
|
| 574 |
+
"learning_rate": 7.95903705565364e-07,
|
| 575 |
+
"loss": 2.6148,
|
| 576 |
+
"step": 6042
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.1941470378301213,
|
| 580 |
+
"grad_norm": 30.337942123413086,
|
| 581 |
+
"learning_rate": 2.942628618475518e-07,
|
| 582 |
+
"loss": 2.4811,
|
| 583 |
+
"step": 6148
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.23197715917202,
|
| 587 |
+
"grad_norm": 39.4644775390625,
|
| 588 |
+
"learning_rate": 3.586537783372812e-08,
|
| 589 |
+
"loss": 2.0681,
|
| 590 |
+
"step": 6254
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.2698072805139184,
|
| 594 |
+
"grad_norm": 23.357696533203125,
|
| 595 |
+
"learning_rate": 1.9972812837304454e-05,
|
| 596 |
+
"loss": 2.4426,
|
| 597 |
+
"step": 6360
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.3076374018558172,
|
| 601 |
+
"grad_norm": 45.85642623901367,
|
| 602 |
+
"learning_rate": 1.973498424932629e-05,
|
| 603 |
+
"loss": 2.5273,
|
| 604 |
+
"step": 6466
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.345467523197716,
|
| 608 |
+
"grad_norm": 5.410664081573486,
|
| 609 |
+
"learning_rate": 1.925208877931819e-05,
|
| 610 |
+
"loss": 2.1097,
|
| 611 |
+
"step": 6572
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.3832976445396143,
|
| 615 |
+
"grad_norm": 69.4088134765625,
|
| 616 |
+
"learning_rate": 1.8537319199499876e-05,
|
| 617 |
+
"loss": 2.8945,
|
| 618 |
+
"step": 6678
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.401142041399001,
|
| 622 |
+
"eval_nli-pairs_loss": 1.8918577432632446,
|
| 623 |
+
"eval_nli-pairs_runtime": 6.2206,
|
| 624 |
+
"eval_nli-pairs_samples_per_second": 120.567,
|
| 625 |
+
"eval_nli-pairs_steps_per_second": 6.752,
|
| 626 |
+
"step": 6728
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.401142041399001,
|
| 630 |
+
"eval_scitail-pairs-pos_loss": 1.3393586874008179,
|
| 631 |
+
"eval_scitail-pairs-pos_runtime": 7.6528,
|
| 632 |
+
"eval_scitail-pairs-pos_samples_per_second": 98.003,
|
| 633 |
+
"eval_scitail-pairs-pos_steps_per_second": 5.488,
|
| 634 |
+
"step": 6728
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.401142041399001,
|
| 638 |
+
"eval_qnli-contrastive_loss": 2.6094088554382324,
|
| 639 |
+
"eval_qnli-contrastive_runtime": 2.479,
|
| 640 |
+
"eval_qnli-contrastive_samples_per_second": 302.543,
|
| 641 |
+
"eval_qnli-contrastive_steps_per_second": 16.942,
|
| 642 |
+
"step": 6728
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.421127765881513,
|
| 646 |
+
"grad_norm": 16.983625411987305,
|
| 647 |
+
"learning_rate": 1.760858893072075e-05,
|
| 648 |
+
"loss": 2.2264,
|
| 649 |
+
"step": 6784
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.458957887223412,
|
| 653 |
+
"grad_norm": 32.24399948120117,
|
| 654 |
+
"learning_rate": 1.6489173636397294e-05,
|
| 655 |
+
"loss": 2.5986,
|
| 656 |
+
"step": 6890
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.4967880085653107,
|
| 660 |
+
"grad_norm": 27.440216064453125,
|
| 661 |
+
"learning_rate": 1.5207127892211873e-05,
|
| 662 |
+
"loss": 2.3359,
|
| 663 |
+
"step": 6996
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.534618129907209,
|
| 667 |
+
"grad_norm": 5.935887813568115,
|
| 668 |
+
"learning_rate": 1.3794582087610502e-05,
|
| 669 |
+
"loss": 1.857,
|
| 670 |
+
"step": 7102
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.572448251249108,
|
| 674 |
+
"grad_norm": 11.255595207214355,
|
| 675 |
+
"learning_rate": 1.228693718002246e-05,
|
| 676 |
+
"loss": 2.0381,
|
| 677 |
+
"step": 7208
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.6102783725910066,
|
| 681 |
+
"grad_norm": 20.442119598388672,
|
| 682 |
+
"learning_rate": 1.072197748271959e-05,
|
| 683 |
+
"loss": 2.0267,
|
| 684 |
+
"step": 7314
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.648108493932905,
|
| 688 |
+
"grad_norm": 16.118242263793945,
|
| 689 |
+
"learning_rate": 9.138923721459728e-06,
|
| 690 |
+
"loss": 2.0914,
|
| 691 |
+
"step": 7420
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.6859386152748037,
|
| 695 |
+
"grad_norm": 4.989729881286621,
|
| 696 |
+
"learning_rate": 7.577450092030369e-06,
|
| 697 |
+
"loss": 1.9207,
|
| 698 |
+
"step": 7526
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.7012847965738755,
|
| 702 |
+
"eval_nli-pairs_loss": 1.7135257720947266,
|
| 703 |
+
"eval_nli-pairs_runtime": 6.2852,
|
| 704 |
+
"eval_nli-pairs_samples_per_second": 119.329,
|
| 705 |
+
"eval_nli-pairs_steps_per_second": 6.682,
|
| 706 |
+
"step": 7569
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.7012847965738755,
|
| 710 |
+
"eval_scitail-pairs-pos_loss": 1.2556273937225342,
|
| 711 |
+
"eval_scitail-pairs-pos_runtime": 7.7379,
|
| 712 |
+
"eval_scitail-pairs-pos_samples_per_second": 96.926,
|
| 713 |
+
"eval_scitail-pairs-pos_steps_per_second": 5.428,
|
| 714 |
+
"step": 7569
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.7012847965738755,
|
| 718 |
+
"eval_qnli-contrastive_loss": 2.2631449699401855,
|
| 719 |
+
"eval_qnli-contrastive_runtime": 2.4746,
|
| 720 |
+
"eval_qnli-contrastive_samples_per_second": 303.074,
|
| 721 |
+
"eval_qnli-contrastive_steps_per_second": 16.972,
|
| 722 |
+
"step": 7569
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.7237687366167025,
|
| 726 |
+
"grad_norm": 18.30848503112793,
|
| 727 |
+
"learning_rate": 6.076689953011623e-06,
|
| 728 |
+
"loss": 2.034,
|
| 729 |
+
"step": 7632
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.7615988579586013,
|
| 733 |
+
"grad_norm": 6.111113548278809,
|
| 734 |
+
"learning_rate": 4.674255072899656e-06,
|
| 735 |
+
"loss": 2.2729,
|
| 736 |
+
"step": 7738
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.7994289793004996,
|
| 740 |
+
"grad_norm": 24.842626571655273,
|
| 741 |
+
"learning_rate": 3.405293011034734e-06,
|
| 742 |
+
"loss": 1.936,
|
| 743 |
+
"step": 7844
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 2.8372591006423984,
|
| 747 |
+
"grad_norm": 35.68688201904297,
|
| 748 |
+
"learning_rate": 2.30160625607605e-06,
|
| 749 |
+
"loss": 2.1102,
|
| 750 |
+
"step": 7950
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.8750892219842967,
|
| 754 |
+
"grad_norm": 2.0094401836395264,
|
| 755 |
+
"learning_rate": 1.3908551980089656e-06,
|
| 756 |
+
"loss": 1.6607,
|
| 757 |
+
"step": 8056
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 2.9129193433261955,
|
| 761 |
+
"grad_norm": 27.046804428100586,
|
| 762 |
+
"learning_rate": 6.958649086507996e-07,
|
| 763 |
+
"loss": 1.9579,
|
| 764 |
+
"step": 8162
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.9507494646680943,
|
| 768 |
+
"grad_norm": 5.009235858917236,
|
| 769 |
+
"learning_rate": 2.340531039914673e-07,
|
| 770 |
+
"loss": 2.4587,
|
| 771 |
+
"step": 8268
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.988579586009993,
|
| 775 |
+
"grad_norm": 19.040987014770508,
|
| 776 |
+
"learning_rate": 1.69936246694824e-08,
|
| 777 |
+
"loss": 2.78,
|
| 778 |
+
"step": 8374
|
| 779 |
}
|
| 780 |
],
|
| 781 |
"logging_steps": 106,
|
|
|
|
| 790 |
"should_evaluate": false,
|
| 791 |
"should_log": false,
|
| 792 |
"should_save": true,
|
| 793 |
+
"should_training_stop": true
|
| 794 |
},
|
| 795 |
"attributes": {}
|
| 796 |
}
|