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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:151c9a6c043af174215252f74e976d839e04775cc8f15e0a57791c185438bd0f
|
3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 170920532
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5173804b1e5050209c934f3da5a1df264d57506afda07cf932118eb3c88e2a2
|
3 |
size 170920532
|
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 sha256:998dbcc7517e2ea40f5bca505faaaf954ad30ed6e9368c648577affe98a6d7a4
|
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": 1.6479060649871826,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-350",
|
4 |
-
"epoch": 0.
|
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": 13.012,
|
2522 |
"eval_steps_per_second": 3.266,
|
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":
|
2553 |
"train_batch_size": 8,
|
2554 |
"trial_name": null,
|
2555 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.6479060649871826,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-350",
|
4 |
+
"epoch": 0.9090909090909091,
|
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": 13.012,
|
2522 |
"eval_steps_per_second": 3.266,
|
2523 |
"step": 350
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 0.7977272727272727,
|
2527 |
+
"grad_norm": 0.3698289394378662,
|
2528 |
+
"learning_rate": 3.844650207332562e-06,
|
2529 |
+
"loss": 1.8769,
|
2530 |
+
"step": 351
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 0.8,
|
2534 |
+
"grad_norm": 0.47637778520584106,
|
2535 |
+
"learning_rate": 3.691267552111183e-06,
|
2536 |
+
"loss": 1.9414,
|
2537 |
+
"step": 352
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 0.8022727272727272,
|
2541 |
+
"grad_norm": 0.5020650029182434,
|
2542 |
+
"learning_rate": 3.54088980417534e-06,
|
2543 |
+
"loss": 1.8797,
|
2544 |
+
"step": 353
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 0.8045454545454546,
|
2548 |
+
"grad_norm": 0.5514700412750244,
|
2549 |
+
"learning_rate": 3.393526721321616e-06,
|
2550 |
+
"loss": 1.8749,
|
2551 |
+
"step": 354
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 0.8068181818181818,
|
2555 |
+
"grad_norm": 0.5742571353912354,
|
2556 |
+
"learning_rate": 3.249187865729264e-06,
|
2557 |
+
"loss": 1.7711,
|
2558 |
+
"step": 355
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 0.8090909090909091,
|
2562 |
+
"grad_norm": 0.5958347320556641,
|
2563 |
+
"learning_rate": 3.1078826033397843e-06,
|
2564 |
+
"loss": 1.7989,
|
2565 |
+
"step": 356
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 0.8113636363636364,
|
2569 |
+
"grad_norm": 0.5803319811820984,
|
2570 |
+
"learning_rate": 2.9696201032491434e-06,
|
2571 |
+
"loss": 1.5927,
|
2572 |
+
"step": 357
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 0.8136363636363636,
|
2576 |
+
"grad_norm": 0.7168722748756409,
|
2577 |
+
"learning_rate": 2.8344093371128424e-06,
|
2578 |
+
"loss": 1.6328,
|
2579 |
+
"step": 358
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 0.8159090909090909,
|
2583 |
+
"grad_norm": 0.6790624856948853,
|
2584 |
+
"learning_rate": 2.70225907856374e-06,
|
2585 |
+
"loss": 1.6932,
|
2586 |
+
"step": 359
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 0.8181818181818182,
|
2590 |
+
"grad_norm": 0.7426336407661438,
|
2591 |
+
"learning_rate": 2.573177902642726e-06,
|
2592 |
+
"loss": 1.859,
|
2593 |
+
"step": 360
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 0.8204545454545454,
|
2597 |
+
"grad_norm": 0.7567765712738037,
|
2598 |
+
"learning_rate": 2.4471741852423237e-06,
|
2599 |
+
"loss": 1.5385,
|
2600 |
+
"step": 361
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 0.8227272727272728,
|
2604 |
+
"grad_norm": 0.7817090153694153,
|
2605 |
+
"learning_rate": 2.324256102563188e-06,
|
2606 |
+
"loss": 1.6779,
|
2607 |
+
"step": 362
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 0.825,
|
2611 |
+
"grad_norm": 0.8798091411590576,
|
2612 |
+
"learning_rate": 2.204431630583548e-06,
|
2613 |
+
"loss": 1.5295,
|
2614 |
+
"step": 363
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 0.8272727272727273,
|
2618 |
+
"grad_norm": 0.8708153963088989,
|
2619 |
+
"learning_rate": 2.087708544541689e-06,
|
2620 |
+
"loss": 1.6753,
|
2621 |
+
"step": 364
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 0.8295454545454546,
|
2625 |
+
"grad_norm": 0.8136506080627441,
|
2626 |
+
"learning_rate": 1.974094418431388e-06,
|
2627 |
+
"loss": 1.6369,
|
2628 |
+
"step": 365
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 0.8318181818181818,
|
2632 |
+
"grad_norm": 0.906902015209198,
|
2633 |
+
"learning_rate": 1.8635966245104664e-06,
|
2634 |
+
"loss": 1.6952,
|
2635 |
+
"step": 366
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 0.8340909090909091,
|
2639 |
+
"grad_norm": 0.9133580327033997,
|
2640 |
+
"learning_rate": 1.7562223328224325e-06,
|
2641 |
+
"loss": 1.8168,
|
2642 |
+
"step": 367
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 0.8363636363636363,
|
2646 |
+
"grad_norm": 0.9204378724098206,
|
2647 |
+
"learning_rate": 1.6519785107311891e-06,
|
2648 |
+
"loss": 1.7356,
|
2649 |
+
"step": 368
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 0.8386363636363636,
|
2653 |
+
"grad_norm": 0.9639214873313904,
|
2654 |
+
"learning_rate": 1.5508719224689717e-06,
|
2655 |
+
"loss": 1.6889,
|
2656 |
+
"step": 369
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 0.8409090909090909,
|
2660 |
+
"grad_norm": 1.0332034826278687,
|
2661 |
+
"learning_rate": 1.4529091286973995e-06,
|
2662 |
+
"loss": 1.5004,
|
2663 |
+
"step": 370
|
2664 |
+
},
|
2665 |
+
{
|
2666 |
+
"epoch": 0.8431818181818181,
|
2667 |
+
"grad_norm": 0.986321210861206,
|
2668 |
+
"learning_rate": 1.358096486081778e-06,
|
2669 |
+
"loss": 1.6841,
|
2670 |
+
"step": 371
|
2671 |
+
},
|
2672 |
+
{
|
2673 |
+
"epoch": 0.8454545454545455,
|
2674 |
+
"grad_norm": 1.020476222038269,
|
2675 |
+
"learning_rate": 1.2664401468786114e-06,
|
2676 |
+
"loss": 1.6094,
|
2677 |
+
"step": 372
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 0.8477272727272728,
|
2681 |
+
"grad_norm": 1.0801876783370972,
|
2682 |
+
"learning_rate": 1.1779460585363944e-06,
|
2683 |
+
"loss": 1.5441,
|
2684 |
+
"step": 373
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 0.85,
|
2688 |
+
"grad_norm": 1.1377614736557007,
|
2689 |
+
"learning_rate": 1.0926199633097157e-06,
|
2690 |
+
"loss": 1.45,
|
2691 |
+
"step": 374
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 0.8522727272727273,
|
2695 |
+
"grad_norm": 1.1650811433792114,
|
2696 |
+
"learning_rate": 1.0104673978866164e-06,
|
2697 |
+
"loss": 1.5581,
|
2698 |
+
"step": 375
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 0.8545454545454545,
|
2702 |
+
"grad_norm": 1.099685788154602,
|
2703 |
+
"learning_rate": 9.314936930293283e-07,
|
2704 |
+
"loss": 1.6638,
|
2705 |
+
"step": 376
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 0.8568181818181818,
|
2709 |
+
"grad_norm": 1.6271238327026367,
|
2710 |
+
"learning_rate": 8.557039732283944e-07,
|
2711 |
+
"loss": 1.5905,
|
2712 |
+
"step": 377
|
2713 |
+
},
|
2714 |
+
{
|
2715 |
+
"epoch": 0.8590909090909091,
|
2716 |
+
"grad_norm": 1.6747556924819946,
|
2717 |
+
"learning_rate": 7.83103156370113e-07,
|
2718 |
+
"loss": 1.6473,
|
2719 |
+
"step": 378
|
2720 |
+
},
|
2721 |
+
{
|
2722 |
+
"epoch": 0.8613636363636363,
|
2723 |
+
"grad_norm": 1.1051077842712402,
|
2724 |
+
"learning_rate": 7.136959534174592e-07,
|
2725 |
+
"loss": 1.6016,
|
2726 |
+
"step": 379
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 0.8636363636363636,
|
2730 |
+
"grad_norm": 1.4238884449005127,
|
2731 |
+
"learning_rate": 6.474868681043578e-07,
|
2732 |
+
"loss": 1.5379,
|
2733 |
+
"step": 380
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 0.865909090909091,
|
2737 |
+
"grad_norm": 1.5626180171966553,
|
2738 |
+
"learning_rate": 5.844801966434832e-07,
|
2739 |
+
"loss": 1.4908,
|
2740 |
+
"step": 381
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 0.8681818181818182,
|
2744 |
+
"grad_norm": 1.586370825767517,
|
2745 |
+
"learning_rate": 5.246800274474439e-07,
|
2746 |
+
"loss": 1.6281,
|
2747 |
+
"step": 382
|
2748 |
+
},
|
2749 |
+
{
|
2750 |
+
"epoch": 0.8704545454545455,
|
2751 |
+
"grad_norm": 1.4967386722564697,
|
2752 |
+
"learning_rate": 4.680902408635335e-07,
|
2753 |
+
"loss": 1.3998,
|
2754 |
+
"step": 383
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 0.8727272727272727,
|
2758 |
+
"grad_norm": 1.4333577156066895,
|
2759 |
+
"learning_rate": 4.1471450892189846e-07,
|
2760 |
+
"loss": 1.4366,
|
2761 |
+
"step": 384
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 0.875,
|
2765 |
+
"grad_norm": 1.4822272062301636,
|
2766 |
+
"learning_rate": 3.6455629509730136e-07,
|
2767 |
+
"loss": 1.4206,
|
2768 |
+
"step": 385
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 0.8772727272727273,
|
2772 |
+
"grad_norm": 1.463018536567688,
|
2773 |
+
"learning_rate": 3.1761885408435054e-07,
|
2774 |
+
"loss": 1.286,
|
2775 |
+
"step": 386
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 0.8795454545454545,
|
2779 |
+
"grad_norm": 1.9729580879211426,
|
2780 |
+
"learning_rate": 2.7390523158633554e-07,
|
2781 |
+
"loss": 1.7124,
|
2782 |
+
"step": 387
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 0.8818181818181818,
|
2786 |
+
"grad_norm": 1.8522109985351562,
|
2787 |
+
"learning_rate": 2.334182641175686e-07,
|
2788 |
+
"loss": 1.3835,
|
2789 |
+
"step": 388
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.884090909090909,
|
2793 |
+
"grad_norm": 1.4895251989364624,
|
2794 |
+
"learning_rate": 1.9616057881935436e-07,
|
2795 |
+
"loss": 1.2827,
|
2796 |
+
"step": 389
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 0.8863636363636364,
|
2800 |
+
"grad_norm": 1.7748496532440186,
|
2801 |
+
"learning_rate": 1.6213459328950352e-07,
|
2802 |
+
"loss": 1.3755,
|
2803 |
+
"step": 390
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 0.8886363636363637,
|
2807 |
+
"grad_norm": 1.7273297309875488,
|
2808 |
+
"learning_rate": 1.3134251542544774e-07,
|
2809 |
+
"loss": 1.206,
|
2810 |
+
"step": 391
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 0.8909090909090909,
|
2814 |
+
"grad_norm": 2.185232639312744,
|
2815 |
+
"learning_rate": 1.0378634328099269e-07,
|
2816 |
+
"loss": 1.4596,
|
2817 |
+
"step": 392
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 0.8931818181818182,
|
2821 |
+
"grad_norm": 2.2152626514434814,
|
2822 |
+
"learning_rate": 7.946786493666647e-08,
|
2823 |
+
"loss": 1.5451,
|
2824 |
+
"step": 393
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 0.8954545454545455,
|
2828 |
+
"grad_norm": 2.496037721633911,
|
2829 |
+
"learning_rate": 5.838865838366792e-08,
|
2830 |
+
"loss": 1.6552,
|
2831 |
+
"step": 394
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 0.8977272727272727,
|
2835 |
+
"grad_norm": 2.770740270614624,
|
2836 |
+
"learning_rate": 4.055009142152067e-08,
|
2837 |
+
"loss": 1.5272,
|
2838 |
+
"step": 395
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 0.9,
|
2842 |
+
"grad_norm": 2.5166406631469727,
|
2843 |
+
"learning_rate": 2.595332156925534e-08,
|
2844 |
+
"loss": 1.8477,
|
2845 |
+
"step": 396
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 0.9022727272727272,
|
2849 |
+
"grad_norm": 3.1613364219665527,
|
2850 |
+
"learning_rate": 1.4599295990352924e-08,
|
2851 |
+
"loss": 1.6615,
|
2852 |
+
"step": 397
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 0.9045454545454545,
|
2856 |
+
"grad_norm": 3.1120591163635254,
|
2857 |
+
"learning_rate": 6.488751431266149e-09,
|
2858 |
+
"loss": 1.4356,
|
2859 |
+
"step": 398
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 0.9068181818181819,
|
2863 |
+
"grad_norm": 4.566768169403076,
|
2864 |
+
"learning_rate": 1.622214173602199e-09,
|
2865 |
+
"loss": 1.6896,
|
2866 |
+
"step": 399
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 0.9090909090909091,
|
2870 |
+
"grad_norm": 7.5620036125183105,
|
2871 |
+
"learning_rate": 0.0,
|
2872 |
+
"loss": 2.4552,
|
2873 |
+
"step": 400
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 0.9090909090909091,
|
2877 |
+
"eval_loss": 1.6492966413497925,
|
2878 |
+
"eval_runtime": 57.2439,
|
2879 |
+
"eval_samples_per_second": 12.945,
|
2880 |
+
"eval_steps_per_second": 3.249,
|
2881 |
+
"step": 400
|
2882 |
}
|
2883 |
],
|
2884 |
"logging_steps": 1,
|
|
|
2893 |
"early_stopping_threshold": 0.0
|
2894 |
},
|
2895 |
"attributes": {
|
2896 |
+
"early_stopping_patience_counter": 1
|
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": 6.020304348968387e+17,
|
2911 |
"train_batch_size": 8,
|
2912 |
"trial_name": null,
|
2913 |
"trial_params": null
|