Commit
•
7f9042d
1
Parent(s):
311485d
Training in progress, step 4000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +365 -5
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Feb09_10-25-55_5414a9461c91/1675939283.9214077/events.out.tfevents.1675939283.5414a9461c91.351.1 +3 -0
- runs/Feb09_10-25-55_5414a9461c91/events.out.tfevents.1675939283.5414a9461c91.351.0 +3 -0
- training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38535e6c225fedc50533b886bfd54b9a622c67e22d7200e25392219b114ec183
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e39e01e5f4c4c5c56c4c737e55174fa27102738a2a31ad9abaea988d95c5076
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68a848aa7b2c67556e67ae63d728ec54a37d250974833764149f6f889e5db0d3
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:768c536c5cefd4a4a3a1c722218d4a55287b59d738fd22efac7a8db1091c7245
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2526,11 +2526,371 @@
|
|
| 2526 |
"eval_samples_per_second": 0.211,
|
| 2527 |
"eval_steps_per_second": 0.211,
|
| 2528 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2529 |
}
|
| 2530 |
],
|
| 2531 |
-
"max_steps":
|
| 2532 |
-
"num_train_epochs":
|
| 2533 |
-
"total_flos":
|
| 2534 |
"trial_name": null,
|
| 2535 |
"trial_params": null
|
| 2536 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.903464431019603,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2526 |
"eval_samples_per_second": 0.211,
|
| 2527 |
"eval_steps_per_second": 0.211,
|
| 2528 |
"step": 3500
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 6.94,
|
| 2532 |
+
"learning_rate": 0.00015593561368209256,
|
| 2533 |
+
"loss": 0.1147,
|
| 2534 |
+
"step": 3510
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 6.95,
|
| 2538 |
+
"learning_rate": 0.00015492957746478874,
|
| 2539 |
+
"loss": 0.0879,
|
| 2540 |
+
"step": 3520
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 6.97,
|
| 2544 |
+
"learning_rate": 0.0001539235412474849,
|
| 2545 |
+
"loss": 0.095,
|
| 2546 |
+
"step": 3530
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 6.99,
|
| 2550 |
+
"learning_rate": 0.00015291750503018109,
|
| 2551 |
+
"loss": 0.1277,
|
| 2552 |
+
"step": 3540
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 7.02,
|
| 2556 |
+
"learning_rate": 0.00015191146881287726,
|
| 2557 |
+
"loss": 0.1332,
|
| 2558 |
+
"step": 3550
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 7.04,
|
| 2562 |
+
"learning_rate": 0.00015090543259557344,
|
| 2563 |
+
"loss": 0.1055,
|
| 2564 |
+
"step": 3560
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 7.06,
|
| 2568 |
+
"learning_rate": 0.00014989939637826964,
|
| 2569 |
+
"loss": 0.1114,
|
| 2570 |
+
"step": 3570
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 7.07,
|
| 2574 |
+
"learning_rate": 0.00014889336016096582,
|
| 2575 |
+
"loss": 0.0983,
|
| 2576 |
+
"step": 3580
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 7.09,
|
| 2580 |
+
"learning_rate": 0.00014788732394366196,
|
| 2581 |
+
"loss": 0.0823,
|
| 2582 |
+
"step": 3590
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 7.11,
|
| 2586 |
+
"learning_rate": 0.00014688128772635814,
|
| 2587 |
+
"loss": 0.0949,
|
| 2588 |
+
"step": 3600
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 7.11,
|
| 2592 |
+
"eval_loss": 0.9529324769973755,
|
| 2593 |
+
"eval_rouge1": 0.1603205128205128,
|
| 2594 |
+
"eval_rouge2": 0.09454545454545453,
|
| 2595 |
+
"eval_rougeL": 0.16115384615384615,
|
| 2596 |
+
"eval_rougeLsum": 0.15993589743589742,
|
| 2597 |
+
"eval_runtime": 96.2453,
|
| 2598 |
+
"eval_samples_per_second": 0.208,
|
| 2599 |
+
"eval_steps_per_second": 0.208,
|
| 2600 |
+
"step": 3600
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 7.13,
|
| 2604 |
+
"learning_rate": 0.00014587525150905434,
|
| 2605 |
+
"loss": 0.0698,
|
| 2606 |
+
"step": 3610
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 7.15,
|
| 2610 |
+
"learning_rate": 0.00014486921529175052,
|
| 2611 |
+
"loss": 0.0694,
|
| 2612 |
+
"step": 3620
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 7.17,
|
| 2616 |
+
"learning_rate": 0.0001438631790744467,
|
| 2617 |
+
"loss": 0.1078,
|
| 2618 |
+
"step": 3630
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 7.19,
|
| 2622 |
+
"learning_rate": 0.00014285714285714284,
|
| 2623 |
+
"loss": 0.1292,
|
| 2624 |
+
"step": 3640
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 7.21,
|
| 2628 |
+
"learning_rate": 0.00014185110663983904,
|
| 2629 |
+
"loss": 0.1175,
|
| 2630 |
+
"step": 3650
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 7.23,
|
| 2634 |
+
"learning_rate": 0.00014084507042253522,
|
| 2635 |
+
"loss": 0.1168,
|
| 2636 |
+
"step": 3660
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 7.25,
|
| 2640 |
+
"learning_rate": 0.0001398390342052314,
|
| 2641 |
+
"loss": 0.0948,
|
| 2642 |
+
"step": 3670
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 7.27,
|
| 2646 |
+
"learning_rate": 0.00013883299798792757,
|
| 2647 |
+
"loss": 0.1314,
|
| 2648 |
+
"step": 3680
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 7.29,
|
| 2652 |
+
"learning_rate": 0.00013782696177062375,
|
| 2653 |
+
"loss": 0.1068,
|
| 2654 |
+
"step": 3690
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 7.31,
|
| 2658 |
+
"learning_rate": 0.00013682092555331992,
|
| 2659 |
+
"loss": 0.1059,
|
| 2660 |
+
"step": 3700
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 7.31,
|
| 2664 |
+
"eval_loss": 0.9520353078842163,
|
| 2665 |
+
"eval_rouge1": 0.13832167832167833,
|
| 2666 |
+
"eval_rouge2": 0.0977272727272727,
|
| 2667 |
+
"eval_rougeL": 0.14185314685314687,
|
| 2668 |
+
"eval_rougeLsum": 0.13999999999999999,
|
| 2669 |
+
"eval_runtime": 91.3536,
|
| 2670 |
+
"eval_samples_per_second": 0.219,
|
| 2671 |
+
"eval_steps_per_second": 0.219,
|
| 2672 |
+
"step": 3700
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 7.33,
|
| 2676 |
+
"learning_rate": 0.0001358148893360161,
|
| 2677 |
+
"loss": 0.0945,
|
| 2678 |
+
"step": 3710
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 7.35,
|
| 2682 |
+
"learning_rate": 0.00013480885311871227,
|
| 2683 |
+
"loss": 0.1298,
|
| 2684 |
+
"step": 3720
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 7.37,
|
| 2688 |
+
"learning_rate": 0.00013380281690140845,
|
| 2689 |
+
"loss": 0.0972,
|
| 2690 |
+
"step": 3730
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 7.39,
|
| 2694 |
+
"learning_rate": 0.00013279678068410465,
|
| 2695 |
+
"loss": 0.1007,
|
| 2696 |
+
"step": 3740
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 7.41,
|
| 2700 |
+
"learning_rate": 0.0001317907444668008,
|
| 2701 |
+
"loss": 0.1194,
|
| 2702 |
+
"step": 3750
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 7.43,
|
| 2706 |
+
"learning_rate": 0.00013078470824949697,
|
| 2707 |
+
"loss": 0.1416,
|
| 2708 |
+
"step": 3760
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 7.45,
|
| 2712 |
+
"learning_rate": 0.00012977867203219315,
|
| 2713 |
+
"loss": 0.1112,
|
| 2714 |
+
"step": 3770
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 7.47,
|
| 2718 |
+
"learning_rate": 0.00012877263581488935,
|
| 2719 |
+
"loss": 0.1232,
|
| 2720 |
+
"step": 3780
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 7.49,
|
| 2724 |
+
"learning_rate": 0.00012776659959758553,
|
| 2725 |
+
"loss": 0.1053,
|
| 2726 |
+
"step": 3790
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 7.51,
|
| 2730 |
+
"learning_rate": 0.0001267605633802817,
|
| 2731 |
+
"loss": 0.1482,
|
| 2732 |
+
"step": 3800
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 7.51,
|
| 2736 |
+
"eval_loss": 0.9513714909553528,
|
| 2737 |
+
"eval_rouge1": 0.21115384615384616,
|
| 2738 |
+
"eval_rouge2": 0.12045454545454545,
|
| 2739 |
+
"eval_rougeL": 0.20999999999999996,
|
| 2740 |
+
"eval_rougeLsum": 0.20730769230769228,
|
| 2741 |
+
"eval_runtime": 90.7686,
|
| 2742 |
+
"eval_samples_per_second": 0.22,
|
| 2743 |
+
"eval_steps_per_second": 0.22,
|
| 2744 |
+
"step": 3800
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 7.53,
|
| 2748 |
+
"learning_rate": 0.00012575452716297785,
|
| 2749 |
+
"loss": 0.1281,
|
| 2750 |
+
"step": 3810
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 7.55,
|
| 2754 |
+
"learning_rate": 0.00012474849094567405,
|
| 2755 |
+
"loss": 0.1547,
|
| 2756 |
+
"step": 3820
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 7.57,
|
| 2760 |
+
"learning_rate": 0.00012374245472837023,
|
| 2761 |
+
"loss": 0.1283,
|
| 2762 |
+
"step": 3830
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 7.59,
|
| 2766 |
+
"learning_rate": 0.0001227364185110664,
|
| 2767 |
+
"loss": 0.174,
|
| 2768 |
+
"step": 3840
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 7.61,
|
| 2772 |
+
"learning_rate": 0.00012173038229376258,
|
| 2773 |
+
"loss": 0.0827,
|
| 2774 |
+
"step": 3850
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 7.63,
|
| 2778 |
+
"learning_rate": 0.00012072434607645876,
|
| 2779 |
+
"loss": 0.1174,
|
| 2780 |
+
"step": 3860
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 7.65,
|
| 2784 |
+
"learning_rate": 0.00011971830985915493,
|
| 2785 |
+
"loss": 0.0914,
|
| 2786 |
+
"step": 3870
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 7.67,
|
| 2790 |
+
"learning_rate": 0.0001187122736418511,
|
| 2791 |
+
"loss": 0.1205,
|
| 2792 |
+
"step": 3880
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 7.69,
|
| 2796 |
+
"learning_rate": 0.00011770623742454728,
|
| 2797 |
+
"loss": 0.0821,
|
| 2798 |
+
"step": 3890
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 7.71,
|
| 2802 |
+
"learning_rate": 0.00011670020120724347,
|
| 2803 |
+
"loss": 0.1268,
|
| 2804 |
+
"step": 3900
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 7.71,
|
| 2808 |
+
"eval_loss": 0.938602089881897,
|
| 2809 |
+
"eval_rouge1": 0.20384615384615384,
|
| 2810 |
+
"eval_rouge2": 0.10909090909090909,
|
| 2811 |
+
"eval_rougeL": 0.20153846153846153,
|
| 2812 |
+
"eval_rougeLsum": 0.20076923076923076,
|
| 2813 |
+
"eval_runtime": 89.8217,
|
| 2814 |
+
"eval_samples_per_second": 0.223,
|
| 2815 |
+
"eval_steps_per_second": 0.223,
|
| 2816 |
+
"step": 3900
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 7.73,
|
| 2820 |
+
"learning_rate": 0.00011569416498993963,
|
| 2821 |
+
"loss": 0.0964,
|
| 2822 |
+
"step": 3910
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 7.75,
|
| 2826 |
+
"learning_rate": 0.00011468812877263582,
|
| 2827 |
+
"loss": 0.0878,
|
| 2828 |
+
"step": 3920
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 7.77,
|
| 2832 |
+
"learning_rate": 0.00011368209255533198,
|
| 2833 |
+
"loss": 0.1205,
|
| 2834 |
+
"step": 3930
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 7.79,
|
| 2838 |
+
"learning_rate": 0.00011267605633802817,
|
| 2839 |
+
"loss": 0.0916,
|
| 2840 |
+
"step": 3940
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 7.8,
|
| 2844 |
+
"learning_rate": 0.00011167002012072435,
|
| 2845 |
+
"loss": 0.1021,
|
| 2846 |
+
"step": 3950
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 7.82,
|
| 2850 |
+
"learning_rate": 0.00011066398390342052,
|
| 2851 |
+
"loss": 0.0843,
|
| 2852 |
+
"step": 3960
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 7.84,
|
| 2856 |
+
"learning_rate": 0.0001096579476861167,
|
| 2857 |
+
"loss": 0.0947,
|
| 2858 |
+
"step": 3970
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 7.86,
|
| 2862 |
+
"learning_rate": 0.00010865191146881289,
|
| 2863 |
+
"loss": 0.0884,
|
| 2864 |
+
"step": 3980
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 7.88,
|
| 2868 |
+
"learning_rate": 0.00010764587525150905,
|
| 2869 |
+
"loss": 0.0943,
|
| 2870 |
+
"step": 3990
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 7.9,
|
| 2874 |
+
"learning_rate": 0.00010663983903420524,
|
| 2875 |
+
"loss": 0.089,
|
| 2876 |
+
"step": 4000
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 7.9,
|
| 2880 |
+
"eval_loss": 0.9426229596138,
|
| 2881 |
+
"eval_rouge1": 0.15076923076923077,
|
| 2882 |
+
"eval_rouge2": 0.1181818181818182,
|
| 2883 |
+
"eval_rougeL": 0.15615384615384614,
|
| 2884 |
+
"eval_rougeLsum": 0.15384615384615383,
|
| 2885 |
+
"eval_runtime": 90.9011,
|
| 2886 |
+
"eval_samples_per_second": 0.22,
|
| 2887 |
+
"eval_steps_per_second": 0.22,
|
| 2888 |
+
"step": 4000
|
| 2889 |
}
|
| 2890 |
],
|
| 2891 |
+
"max_steps": 5060,
|
| 2892 |
+
"num_train_epochs": 10,
|
| 2893 |
+
"total_flos": 9.733899587958374e+16,
|
| 2894 |
"trial_name": null,
|
| 2895 |
"trial_params": null
|
| 2896 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8324d78149c1825be11050b4984c3538e3690b1c3af5db03801adad7507acb0
|
| 3 |
size 3643
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e39e01e5f4c4c5c56c4c737e55174fa27102738a2a31ad9abaea988d95c5076
|
| 3 |
size 2329702453
|
runs/Feb09_10-25-55_5414a9461c91/1675939283.9214077/events.out.tfevents.1675939283.5414a9461c91.351.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c113a55f8f1f9d07188df5c0217fc427fb6d5bf3a04d4e7139f2c86df2580992
|
| 3 |
+
size 5952
|
runs/Feb09_10-25-55_5414a9461c91/events.out.tfevents.1675939283.5414a9461c91.351.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acba4368ad5958bff2596e2a94cae81829d5acfc5d99f8d2a2e424dbf9a5ebb8
|
| 3 |
+
size 14428
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3643
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8324d78149c1825be11050b4984c3538e3690b1c3af5db03801adad7507acb0
|
| 3 |
size 3643
|