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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b72beda3310bf6d2a2899d9cd71677f673f946f686bed02c0921c538bb726a2
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314644
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eea5a653f18e4551950efbb571f4edd6bf71506d2ee0667bd68a663d15ba1527
|
| 3 |
size 341314644
|
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:b5a1cfb017bdf79c8378c7120f121b550d7ab035980da59631c319adea8c4470
|
| 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": 2.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 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": 11.123,
|
| 2522 |
"eval_steps_per_second": 2.781,
|
| 2523 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2524 |
}
|
| 2525 |
],
|
| 2526 |
"logging_steps": 1,
|
|
@@ -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": 6.
|
| 2553 |
"train_batch_size": 8,
|
| 2554 |
"trial_name": null,
|
| 2555 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.048121690750122,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
| 4 |
+
"epoch": 0.49674014281279105,
|
| 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": 11.123,
|
| 2522 |
"eval_steps_per_second": 2.781,
|
| 2523 |
"step": 350
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.43588947531822414,
|
| 2527 |
+
"grad_norm": 15.027310371398926,
|
| 2528 |
+
"learning_rate": 3.844650207332562e-06,
|
| 2529 |
+
"loss": 8.233,
|
| 2530 |
+
"step": 351
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.43713132567525614,
|
| 2534 |
+
"grad_norm": 19.14738655090332,
|
| 2535 |
+
"learning_rate": 3.691267552111183e-06,
|
| 2536 |
+
"loss": 9.2654,
|
| 2537 |
+
"step": 352
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.4383731760322881,
|
| 2541 |
+
"grad_norm": 15.403022766113281,
|
| 2542 |
+
"learning_rate": 3.54088980417534e-06,
|
| 2543 |
+
"loss": 10.5999,
|
| 2544 |
+
"step": 353
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.4396150263893201,
|
| 2548 |
+
"grad_norm": 18.61003875732422,
|
| 2549 |
+
"learning_rate": 3.393526721321616e-06,
|
| 2550 |
+
"loss": 9.8252,
|
| 2551 |
+
"step": 354
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.44085687674635204,
|
| 2555 |
+
"grad_norm": 13.475218772888184,
|
| 2556 |
+
"learning_rate": 3.249187865729264e-06,
|
| 2557 |
+
"loss": 9.2884,
|
| 2558 |
+
"step": 355
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.44209872710338405,
|
| 2562 |
+
"grad_norm": 19.1926326751709,
|
| 2563 |
+
"learning_rate": 3.1078826033397843e-06,
|
| 2564 |
+
"loss": 9.26,
|
| 2565 |
+
"step": 356
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.443340577460416,
|
| 2569 |
+
"grad_norm": 20.699216842651367,
|
| 2570 |
+
"learning_rate": 2.9696201032491434e-06,
|
| 2571 |
+
"loss": 10.9862,
|
| 2572 |
+
"step": 357
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.444582427817448,
|
| 2576 |
+
"grad_norm": 19.927446365356445,
|
| 2577 |
+
"learning_rate": 2.8344093371128424e-06,
|
| 2578 |
+
"loss": 9.4867,
|
| 2579 |
+
"step": 358
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.44582427817447995,
|
| 2583 |
+
"grad_norm": 21.07493019104004,
|
| 2584 |
+
"learning_rate": 2.70225907856374e-06,
|
| 2585 |
+
"loss": 9.6272,
|
| 2586 |
+
"step": 359
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.44706612853151195,
|
| 2590 |
+
"grad_norm": 16.262590408325195,
|
| 2591 |
+
"learning_rate": 2.573177902642726e-06,
|
| 2592 |
+
"loss": 10.6436,
|
| 2593 |
+
"step": 360
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.44830797888854396,
|
| 2597 |
+
"grad_norm": 21.369077682495117,
|
| 2598 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 2599 |
+
"loss": 10.3394,
|
| 2600 |
+
"step": 361
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.4495498292455759,
|
| 2604 |
+
"grad_norm": 16.705074310302734,
|
| 2605 |
+
"learning_rate": 2.324256102563188e-06,
|
| 2606 |
+
"loss": 9.6329,
|
| 2607 |
+
"step": 362
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.4507916796026079,
|
| 2611 |
+
"grad_norm": 15.450797080993652,
|
| 2612 |
+
"learning_rate": 2.204431630583548e-06,
|
| 2613 |
+
"loss": 10.0546,
|
| 2614 |
+
"step": 363
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.45203352995963986,
|
| 2618 |
+
"grad_norm": 16.599008560180664,
|
| 2619 |
+
"learning_rate": 2.087708544541689e-06,
|
| 2620 |
+
"loss": 9.6695,
|
| 2621 |
+
"step": 364
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.45327538031667186,
|
| 2625 |
+
"grad_norm": 16.34769630432129,
|
| 2626 |
+
"learning_rate": 1.974094418431388e-06,
|
| 2627 |
+
"loss": 10.1314,
|
| 2628 |
+
"step": 365
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.4545172306737038,
|
| 2632 |
+
"grad_norm": 16.282516479492188,
|
| 2633 |
+
"learning_rate": 1.8635966245104664e-06,
|
| 2634 |
+
"loss": 9.1614,
|
| 2635 |
+
"step": 366
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.4557590810307358,
|
| 2639 |
+
"grad_norm": 18.261295318603516,
|
| 2640 |
+
"learning_rate": 1.7562223328224325e-06,
|
| 2641 |
+
"loss": 9.074,
|
| 2642 |
+
"step": 367
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.45700093138776776,
|
| 2646 |
+
"grad_norm": 19.71063995361328,
|
| 2647 |
+
"learning_rate": 1.6519785107311891e-06,
|
| 2648 |
+
"loss": 8.8432,
|
| 2649 |
+
"step": 368
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.45824278174479977,
|
| 2653 |
+
"grad_norm": 17.528982162475586,
|
| 2654 |
+
"learning_rate": 1.5508719224689717e-06,
|
| 2655 |
+
"loss": 9.3226,
|
| 2656 |
+
"step": 369
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.4594846321018317,
|
| 2660 |
+
"grad_norm": 16.943256378173828,
|
| 2661 |
+
"learning_rate": 1.4529091286973995e-06,
|
| 2662 |
+
"loss": 10.2064,
|
| 2663 |
+
"step": 370
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.4607264824588637,
|
| 2667 |
+
"grad_norm": 20.56031608581543,
|
| 2668 |
+
"learning_rate": 1.358096486081778e-06,
|
| 2669 |
+
"loss": 8.7829,
|
| 2670 |
+
"step": 371
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.46196833281589567,
|
| 2674 |
+
"grad_norm": 20.230304718017578,
|
| 2675 |
+
"learning_rate": 1.2664401468786114e-06,
|
| 2676 |
+
"loss": 8.5434,
|
| 2677 |
+
"step": 372
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.46321018317292767,
|
| 2681 |
+
"grad_norm": 17.898807525634766,
|
| 2682 |
+
"learning_rate": 1.1779460585363944e-06,
|
| 2683 |
+
"loss": 8.5721,
|
| 2684 |
+
"step": 373
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.4644520335299596,
|
| 2688 |
+
"grad_norm": 15.209033012390137,
|
| 2689 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 2690 |
+
"loss": 8.1153,
|
| 2691 |
+
"step": 374
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.4656938838869916,
|
| 2695 |
+
"grad_norm": 17.540138244628906,
|
| 2696 |
+
"learning_rate": 1.0104673978866164e-06,
|
| 2697 |
+
"loss": 8.8329,
|
| 2698 |
+
"step": 375
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.46693573424402357,
|
| 2702 |
+
"grad_norm": 15.526618957519531,
|
| 2703 |
+
"learning_rate": 9.314936930293283e-07,
|
| 2704 |
+
"loss": 7.4237,
|
| 2705 |
+
"step": 376
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.4681775846010556,
|
| 2709 |
+
"grad_norm": 17.168128967285156,
|
| 2710 |
+
"learning_rate": 8.557039732283944e-07,
|
| 2711 |
+
"loss": 7.8179,
|
| 2712 |
+
"step": 377
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.4694194349580876,
|
| 2716 |
+
"grad_norm": 17.137134552001953,
|
| 2717 |
+
"learning_rate": 7.83103156370113e-07,
|
| 2718 |
+
"loss": 7.7716,
|
| 2719 |
+
"step": 378
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.4706612853151195,
|
| 2723 |
+
"grad_norm": 17.559314727783203,
|
| 2724 |
+
"learning_rate": 7.136959534174592e-07,
|
| 2725 |
+
"loss": 7.84,
|
| 2726 |
+
"step": 379
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.47190313567215153,
|
| 2730 |
+
"grad_norm": 19.409400939941406,
|
| 2731 |
+
"learning_rate": 6.474868681043578e-07,
|
| 2732 |
+
"loss": 8.8171,
|
| 2733 |
+
"step": 380
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.4731449860291835,
|
| 2737 |
+
"grad_norm": 17.776226043701172,
|
| 2738 |
+
"learning_rate": 5.844801966434832e-07,
|
| 2739 |
+
"loss": 6.3879,
|
| 2740 |
+
"step": 381
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.4743868363862155,
|
| 2744 |
+
"grad_norm": 20.530086517333984,
|
| 2745 |
+
"learning_rate": 5.246800274474439e-07,
|
| 2746 |
+
"loss": 8.0121,
|
| 2747 |
+
"step": 382
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.47562868674324743,
|
| 2751 |
+
"grad_norm": 22.164968490600586,
|
| 2752 |
+
"learning_rate": 4.680902408635335e-07,
|
| 2753 |
+
"loss": 8.6691,
|
| 2754 |
+
"step": 383
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.47687053710027943,
|
| 2758 |
+
"grad_norm": 18.76708984375,
|
| 2759 |
+
"learning_rate": 4.1471450892189846e-07,
|
| 2760 |
+
"loss": 9.7888,
|
| 2761 |
+
"step": 384
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.4781123874573114,
|
| 2765 |
+
"grad_norm": 14.858979225158691,
|
| 2766 |
+
"learning_rate": 3.6455629509730136e-07,
|
| 2767 |
+
"loss": 6.9336,
|
| 2768 |
+
"step": 385
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.4793542378143434,
|
| 2772 |
+
"grad_norm": 18.082876205444336,
|
| 2773 |
+
"learning_rate": 3.1761885408435054e-07,
|
| 2774 |
+
"loss": 8.7338,
|
| 2775 |
+
"step": 386
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.48059608817137534,
|
| 2779 |
+
"grad_norm": 17.755693435668945,
|
| 2780 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 2781 |
+
"loss": 8.0284,
|
| 2782 |
+
"step": 387
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.48183793852840734,
|
| 2786 |
+
"grad_norm": 17.65026092529297,
|
| 2787 |
+
"learning_rate": 2.334182641175686e-07,
|
| 2788 |
+
"loss": 6.9463,
|
| 2789 |
+
"step": 388
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.4830797888854393,
|
| 2793 |
+
"grad_norm": 20.45888900756836,
|
| 2794 |
+
"learning_rate": 1.9616057881935436e-07,
|
| 2795 |
+
"loss": 9.4778,
|
| 2796 |
+
"step": 389
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.4843216392424713,
|
| 2800 |
+
"grad_norm": 21.550186157226562,
|
| 2801 |
+
"learning_rate": 1.6213459328950352e-07,
|
| 2802 |
+
"loss": 7.7903,
|
| 2803 |
+
"step": 390
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.48556348959950324,
|
| 2807 |
+
"grad_norm": 14.524604797363281,
|
| 2808 |
+
"learning_rate": 1.3134251542544774e-07,
|
| 2809 |
+
"loss": 7.0378,
|
| 2810 |
+
"step": 391
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.48680533995653524,
|
| 2814 |
+
"grad_norm": 12.841784477233887,
|
| 2815 |
+
"learning_rate": 1.0378634328099269e-07,
|
| 2816 |
+
"loss": 5.0816,
|
| 2817 |
+
"step": 392
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.4880471903135672,
|
| 2821 |
+
"grad_norm": 16.81376075744629,
|
| 2822 |
+
"learning_rate": 7.946786493666647e-08,
|
| 2823 |
+
"loss": 6.5177,
|
| 2824 |
+
"step": 393
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.4892890406705992,
|
| 2828 |
+
"grad_norm": 17.302547454833984,
|
| 2829 |
+
"learning_rate": 5.838865838366792e-08,
|
| 2830 |
+
"loss": 8.2668,
|
| 2831 |
+
"step": 394
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.49053089102763114,
|
| 2835 |
+
"grad_norm": 17.527498245239258,
|
| 2836 |
+
"learning_rate": 4.055009142152067e-08,
|
| 2837 |
+
"loss": 6.6197,
|
| 2838 |
+
"step": 395
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.49177274138466315,
|
| 2842 |
+
"grad_norm": 15.597641944885254,
|
| 2843 |
+
"learning_rate": 2.595332156925534e-08,
|
| 2844 |
+
"loss": 5.887,
|
| 2845 |
+
"step": 396
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.49301459174169515,
|
| 2849 |
+
"grad_norm": 17.199445724487305,
|
| 2850 |
+
"learning_rate": 1.4599295990352924e-08,
|
| 2851 |
+
"loss": 6.9099,
|
| 2852 |
+
"step": 397
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.4942564420987271,
|
| 2856 |
+
"grad_norm": 16.837100982666016,
|
| 2857 |
+
"learning_rate": 6.488751431266149e-09,
|
| 2858 |
+
"loss": 6.7667,
|
| 2859 |
+
"step": 398
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.4954982924557591,
|
| 2863 |
+
"grad_norm": 18.93360710144043,
|
| 2864 |
+
"learning_rate": 1.622214173602199e-09,
|
| 2865 |
+
"loss": 5.3912,
|
| 2866 |
+
"step": 399
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.49674014281279105,
|
| 2870 |
+
"grad_norm": 19.71845245361328,
|
| 2871 |
+
"learning_rate": 0.0,
|
| 2872 |
+
"loss": 6.4788,
|
| 2873 |
+
"step": 400
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.49674014281279105,
|
| 2877 |
+
"eval_loss": 2.048121690750122,
|
| 2878 |
+
"eval_runtime": 121.8292,
|
| 2879 |
+
"eval_samples_per_second": 11.13,
|
| 2880 |
+
"eval_steps_per_second": 2.783,
|
| 2881 |
+
"step": 400
|
| 2882 |
}
|
| 2883 |
],
|
| 2884 |
"logging_steps": 1,
|
|
|
|
| 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": 6.997580263949599e+17,
|
| 2911 |
"train_batch_size": 8,
|
| 2912 |
"trial_name": null,
|
| 2913 |
"trial_params": null
|