Training in progress, step 400, 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 100690288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2500c9beb9ee7aa46cbbad3c805f223b50922c3202588818c51345f6d47e620
|
3 |
size 100690288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 51345082
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f2d5e426b93015f76a88ebb6c24948e4da837340b41204b665d19e6295c5bbc
|
3 |
size 51345082
|
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 sha256:2a8e992c9e8abb635da1ff2966b12c61e20a55f5469f6bee4c9c456d33a994d7
|
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 sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 3.102102279663086,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2521,6 +2521,364 @@
|
|
2521 |
"eval_samples_per_second": 39.984,
|
2522 |
"eval_steps_per_second": 10.039,
|
2523 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2524 |
}
|
2525 |
],
|
2526 |
"logging_steps": 1,
|
@@ -2535,7 +2893,7 @@
|
|
2535 |
"early_stopping_threshold": 0.0
|
2536 |
},
|
2537 |
"attributes": {
|
2538 |
-
"early_stopping_patience_counter":
|
2539 |
}
|
2540 |
},
|
2541 |
"TrainerControl": {
|
@@ -2544,12 +2902,12 @@
|
|
2544 |
"should_evaluate": false,
|
2545 |
"should_log": false,
|
2546 |
"should_save": true,
|
2547 |
-
"should_training_stop":
|
2548 |
},
|
2549 |
"attributes": {}
|
2550 |
}
|
2551 |
},
|
2552 |
-
"total_flos": 2.
|
2553 |
"train_batch_size": 8,
|
2554 |
"trial_name": null,
|
2555 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 3.102102279663086,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
4 |
+
"epoch": 2.867383512544803,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2521 |
"eval_samples_per_second": 39.984,
|
2522 |
"eval_steps_per_second": 10.039,
|
2523 |
"step": 350
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 2.5161290322580645,
|
2527 |
+
"grad_norm": 4.645094394683838,
|
2528 |
+
"learning_rate": 3.844650207332562e-06,
|
2529 |
+
"loss": 11.2671,
|
2530 |
+
"step": 351
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 2.5232974910394264,
|
2534 |
+
"grad_norm": 4.672591209411621,
|
2535 |
+
"learning_rate": 3.691267552111183e-06,
|
2536 |
+
"loss": 10.9598,
|
2537 |
+
"step": 352
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 2.5304659498207887,
|
2541 |
+
"grad_norm": 5.024632453918457,
|
2542 |
+
"learning_rate": 3.54088980417534e-06,
|
2543 |
+
"loss": 11.2567,
|
2544 |
+
"step": 353
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 2.5376344086021505,
|
2548 |
+
"grad_norm": 5.246298789978027,
|
2549 |
+
"learning_rate": 3.393526721321616e-06,
|
2550 |
+
"loss": 11.6305,
|
2551 |
+
"step": 354
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 2.5448028673835124,
|
2555 |
+
"grad_norm": 5.054103374481201,
|
2556 |
+
"learning_rate": 3.249187865729264e-06,
|
2557 |
+
"loss": 11.4456,
|
2558 |
+
"step": 355
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 2.5519713261648747,
|
2562 |
+
"grad_norm": 7.0485029220581055,
|
2563 |
+
"learning_rate": 3.1078826033397843e-06,
|
2564 |
+
"loss": 11.3354,
|
2565 |
+
"step": 356
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 2.5591397849462365,
|
2569 |
+
"grad_norm": 5.031679153442383,
|
2570 |
+
"learning_rate": 2.9696201032491434e-06,
|
2571 |
+
"loss": 11.0628,
|
2572 |
+
"step": 357
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 2.5663082437275984,
|
2576 |
+
"grad_norm": 5.079736232757568,
|
2577 |
+
"learning_rate": 2.8344093371128424e-06,
|
2578 |
+
"loss": 11.0878,
|
2579 |
+
"step": 358
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 2.5734767025089607,
|
2583 |
+
"grad_norm": 5.196853160858154,
|
2584 |
+
"learning_rate": 2.70225907856374e-06,
|
2585 |
+
"loss": 11.2209,
|
2586 |
+
"step": 359
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 2.5806451612903225,
|
2590 |
+
"grad_norm": 5.1173319816589355,
|
2591 |
+
"learning_rate": 2.573177902642726e-06,
|
2592 |
+
"loss": 11.2384,
|
2593 |
+
"step": 360
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 2.5878136200716844,
|
2597 |
+
"grad_norm": 5.259467124938965,
|
2598 |
+
"learning_rate": 2.4471741852423237e-06,
|
2599 |
+
"loss": 11.3273,
|
2600 |
+
"step": 361
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 2.5949820788530467,
|
2604 |
+
"grad_norm": 5.36672306060791,
|
2605 |
+
"learning_rate": 2.324256102563188e-06,
|
2606 |
+
"loss": 11.3676,
|
2607 |
+
"step": 362
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 2.6021505376344085,
|
2611 |
+
"grad_norm": 5.235705852508545,
|
2612 |
+
"learning_rate": 2.204431630583548e-06,
|
2613 |
+
"loss": 11.1298,
|
2614 |
+
"step": 363
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 2.6093189964157704,
|
2618 |
+
"grad_norm": 5.165133476257324,
|
2619 |
+
"learning_rate": 2.087708544541689e-06,
|
2620 |
+
"loss": 11.3576,
|
2621 |
+
"step": 364
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 2.6164874551971327,
|
2625 |
+
"grad_norm": 5.137039661407471,
|
2626 |
+
"learning_rate": 1.974094418431388e-06,
|
2627 |
+
"loss": 11.1176,
|
2628 |
+
"step": 365
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 2.6236559139784945,
|
2632 |
+
"grad_norm": 5.188261985778809,
|
2633 |
+
"learning_rate": 1.8635966245104664e-06,
|
2634 |
+
"loss": 11.2998,
|
2635 |
+
"step": 366
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 2.6308243727598564,
|
2639 |
+
"grad_norm": 5.379055500030518,
|
2640 |
+
"learning_rate": 1.7562223328224325e-06,
|
2641 |
+
"loss": 11.303,
|
2642 |
+
"step": 367
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 2.6379928315412187,
|
2646 |
+
"grad_norm": 5.311244010925293,
|
2647 |
+
"learning_rate": 1.6519785107311891e-06,
|
2648 |
+
"loss": 10.7059,
|
2649 |
+
"step": 368
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 2.6451612903225805,
|
2653 |
+
"grad_norm": 5.344785690307617,
|
2654 |
+
"learning_rate": 1.5508719224689717e-06,
|
2655 |
+
"loss": 11.0272,
|
2656 |
+
"step": 369
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 2.652329749103943,
|
2660 |
+
"grad_norm": 5.798556327819824,
|
2661 |
+
"learning_rate": 1.4529091286973995e-06,
|
2662 |
+
"loss": 11.0533,
|
2663 |
+
"step": 370
|
2664 |
+
},
|
2665 |
+
{
|
2666 |
+
"epoch": 2.6594982078853047,
|
2667 |
+
"grad_norm": 5.3860273361206055,
|
2668 |
+
"learning_rate": 1.358096486081778e-06,
|
2669 |
+
"loss": 11.0939,
|
2670 |
+
"step": 371
|
2671 |
+
},
|
2672 |
+
{
|
2673 |
+
"epoch": 2.6666666666666665,
|
2674 |
+
"grad_norm": 5.676300048828125,
|
2675 |
+
"learning_rate": 1.2664401468786114e-06,
|
2676 |
+
"loss": 10.8636,
|
2677 |
+
"step": 372
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 2.673835125448029,
|
2681 |
+
"grad_norm": 5.775704383850098,
|
2682 |
+
"learning_rate": 1.1779460585363944e-06,
|
2683 |
+
"loss": 10.6959,
|
2684 |
+
"step": 373
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 2.6810035842293907,
|
2688 |
+
"grad_norm": 5.730480194091797,
|
2689 |
+
"learning_rate": 1.0926199633097157e-06,
|
2690 |
+
"loss": 10.9271,
|
2691 |
+
"step": 374
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 2.688172043010753,
|
2695 |
+
"grad_norm": 5.9740705490112305,
|
2696 |
+
"learning_rate": 1.0104673978866164e-06,
|
2697 |
+
"loss": 10.717,
|
2698 |
+
"step": 375
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 2.695340501792115,
|
2702 |
+
"grad_norm": 5.873248100280762,
|
2703 |
+
"learning_rate": 9.314936930293283e-07,
|
2704 |
+
"loss": 10.4648,
|
2705 |
+
"step": 376
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 2.7025089605734767,
|
2709 |
+
"grad_norm": 5.873241901397705,
|
2710 |
+
"learning_rate": 8.557039732283944e-07,
|
2711 |
+
"loss": 11.1325,
|
2712 |
+
"step": 377
|
2713 |
+
},
|
2714 |
+
{
|
2715 |
+
"epoch": 2.709677419354839,
|
2716 |
+
"grad_norm": 6.340686798095703,
|
2717 |
+
"learning_rate": 7.83103156370113e-07,
|
2718 |
+
"loss": 10.9804,
|
2719 |
+
"step": 378
|
2720 |
+
},
|
2721 |
+
{
|
2722 |
+
"epoch": 2.716845878136201,
|
2723 |
+
"grad_norm": 6.622114658355713,
|
2724 |
+
"learning_rate": 7.136959534174592e-07,
|
2725 |
+
"loss": 10.8305,
|
2726 |
+
"step": 379
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 2.7240143369175627,
|
2730 |
+
"grad_norm": 6.919821262359619,
|
2731 |
+
"learning_rate": 6.474868681043578e-07,
|
2732 |
+
"loss": 10.4183,
|
2733 |
+
"step": 380
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 2.731182795698925,
|
2737 |
+
"grad_norm": 8.484808921813965,
|
2738 |
+
"learning_rate": 5.844801966434832e-07,
|
2739 |
+
"loss": 10.655,
|
2740 |
+
"step": 381
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 2.738351254480287,
|
2744 |
+
"grad_norm": 4.599321365356445,
|
2745 |
+
"learning_rate": 5.246800274474439e-07,
|
2746 |
+
"loss": 11.5194,
|
2747 |
+
"step": 382
|
2748 |
+
},
|
2749 |
+
{
|
2750 |
+
"epoch": 2.7455197132616487,
|
2751 |
+
"grad_norm": 6.868017196655273,
|
2752 |
+
"learning_rate": 4.680902408635335e-07,
|
2753 |
+
"loss": 11.5332,
|
2754 |
+
"step": 383
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 2.752688172043011,
|
2758 |
+
"grad_norm": 4.8199849128723145,
|
2759 |
+
"learning_rate": 4.1471450892189846e-07,
|
2760 |
+
"loss": 11.4254,
|
2761 |
+
"step": 384
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 2.759856630824373,
|
2765 |
+
"grad_norm": 4.813037395477295,
|
2766 |
+
"learning_rate": 3.6455629509730136e-07,
|
2767 |
+
"loss": 11.3249,
|
2768 |
+
"step": 385
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 2.7670250896057347,
|
2772 |
+
"grad_norm": 4.795863151550293,
|
2773 |
+
"learning_rate": 3.1761885408435054e-07,
|
2774 |
+
"loss": 11.4607,
|
2775 |
+
"step": 386
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 2.774193548387097,
|
2779 |
+
"grad_norm": 4.950782775878906,
|
2780 |
+
"learning_rate": 2.7390523158633554e-07,
|
2781 |
+
"loss": 11.2198,
|
2782 |
+
"step": 387
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 2.781362007168459,
|
2786 |
+
"grad_norm": 4.930598735809326,
|
2787 |
+
"learning_rate": 2.334182641175686e-07,
|
2788 |
+
"loss": 11.1296,
|
2789 |
+
"step": 388
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 2.7885304659498207,
|
2793 |
+
"grad_norm": 5.018906116485596,
|
2794 |
+
"learning_rate": 1.9616057881935436e-07,
|
2795 |
+
"loss": 11.3182,
|
2796 |
+
"step": 389
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 2.795698924731183,
|
2800 |
+
"grad_norm": 4.870406150817871,
|
2801 |
+
"learning_rate": 1.6213459328950352e-07,
|
2802 |
+
"loss": 11.0136,
|
2803 |
+
"step": 390
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 2.802867383512545,
|
2807 |
+
"grad_norm": 6.802547454833984,
|
2808 |
+
"learning_rate": 1.3134251542544774e-07,
|
2809 |
+
"loss": 10.8827,
|
2810 |
+
"step": 391
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 2.8100358422939067,
|
2814 |
+
"grad_norm": 5.190401554107666,
|
2815 |
+
"learning_rate": 1.0378634328099269e-07,
|
2816 |
+
"loss": 11.8161,
|
2817 |
+
"step": 392
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 2.817204301075269,
|
2821 |
+
"grad_norm": 4.945091724395752,
|
2822 |
+
"learning_rate": 7.946786493666647e-08,
|
2823 |
+
"loss": 10.9185,
|
2824 |
+
"step": 393
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 2.824372759856631,
|
2828 |
+
"grad_norm": 5.179837703704834,
|
2829 |
+
"learning_rate": 5.838865838366792e-08,
|
2830 |
+
"loss": 11.6016,
|
2831 |
+
"step": 394
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 2.8315412186379927,
|
2835 |
+
"grad_norm": 5.073259353637695,
|
2836 |
+
"learning_rate": 4.055009142152067e-08,
|
2837 |
+
"loss": 11.0547,
|
2838 |
+
"step": 395
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 2.838709677419355,
|
2842 |
+
"grad_norm": 5.382425308227539,
|
2843 |
+
"learning_rate": 2.595332156925534e-08,
|
2844 |
+
"loss": 11.2993,
|
2845 |
+
"step": 396
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 2.845878136200717,
|
2849 |
+
"grad_norm": 5.340421676635742,
|
2850 |
+
"learning_rate": 1.4599295990352924e-08,
|
2851 |
+
"loss": 11.5045,
|
2852 |
+
"step": 397
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 2.8530465949820787,
|
2856 |
+
"grad_norm": 5.080132961273193,
|
2857 |
+
"learning_rate": 6.488751431266149e-09,
|
2858 |
+
"loss": 10.8784,
|
2859 |
+
"step": 398
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 2.860215053763441,
|
2863 |
+
"grad_norm": 5.09200382232666,
|
2864 |
+
"learning_rate": 1.622214173602199e-09,
|
2865 |
+
"loss": 11.3192,
|
2866 |
+
"step": 399
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 2.867383512544803,
|
2870 |
+
"grad_norm": 5.115841865539551,
|
2871 |
+
"learning_rate": 0.0,
|
2872 |
+
"loss": 10.917,
|
2873 |
+
"step": 400
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 2.867383512544803,
|
2877 |
+
"eval_loss": 3.1046385765075684,
|
2878 |
+
"eval_runtime": 5.8845,
|
2879 |
+
"eval_samples_per_second": 39.935,
|
2880 |
+
"eval_steps_per_second": 10.026,
|
2881 |
+
"step": 400
|
2882 |
}
|
2883 |
],
|
2884 |
"logging_steps": 1,
|
|
|
2893 |
"early_stopping_threshold": 0.0
|
2894 |
},
|
2895 |
"attributes": {
|
2896 |
+
"early_stopping_patience_counter": 3
|
2897 |
}
|
2898 |
},
|
2899 |
"TrainerControl": {
|
|
|
2902 |
"should_evaluate": false,
|
2903 |
"should_log": false,
|
2904 |
"should_save": true,
|
2905 |
+
"should_training_stop": true
|
2906 |
},
|
2907 |
"attributes": {}
|
2908 |
}
|
2909 |
},
|
2910 |
+
"total_flos": 2.574999570559795e+16,
|
2911 |
"train_batch_size": 8,
|
2912 |
"trial_name": null,
|
2913 |
"trial_params": null
|