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 578859568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:024de3f8e2afb4251670fd08dca4001b5a22b5aa81ae8963df0898d4eaf258bf
|
| 3 |
size 578859568
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 294324692
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc5bb928545579b4a25c09020cb0ddd259af2200a0a70f135813471914ab7ec
|
| 3 |
size 294324692
|
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 sha256:404ce932a6e24aba5cc2e7fbd9a324e1334ed0f859ca94dba9e1b8e1bea61d54
|
| 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 sha256:4fe5dbedd3d0105f98d40d84fbe544af591501f8969d82c59cef4d7bb5f81712
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 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": 11.514,
|
| 2522 |
"eval_steps_per_second": 5.767,
|
| 2523 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2524 |
}
|
| 2525 |
],
|
| 2526 |
"logging_steps": 1,
|
|
@@ -2549,7 +2907,7 @@
|
|
| 2549 |
"attributes": {}
|
| 2550 |
}
|
| 2551 |
},
|
| 2552 |
-
"total_flos": 2.
|
| 2553 |
"train_batch_size": 2,
|
| 2554 |
"trial_name": null,
|
| 2555 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7006093859672546,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
| 4 |
+
"epoch": 0.011118755255349163,
|
| 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": 11.514,
|
| 2522 |
"eval_steps_per_second": 5.767,
|
| 2523 |
"step": 350
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.00975670773656889,
|
| 2527 |
+
"grad_norm": 0.1047213226556778,
|
| 2528 |
+
"learning_rate": 0.0004226366711111808,
|
| 2529 |
+
"loss": 0.942,
|
| 2530 |
+
"step": 351
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.009784504624707265,
|
| 2534 |
+
"grad_norm": 0.10103016346693039,
|
| 2535 |
+
"learning_rate": 0.00041741373548960395,
|
| 2536 |
+
"loss": 0.7983,
|
| 2537 |
+
"step": 352
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.009812301512845636,
|
| 2541 |
+
"grad_norm": 0.10744207352399826,
|
| 2542 |
+
"learning_rate": 0.00041221474770752696,
|
| 2543 |
+
"loss": 1.0167,
|
| 2544 |
+
"step": 353
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.00984009840098401,
|
| 2548 |
+
"grad_norm": 0.10127032548189163,
|
| 2549 |
+
"learning_rate": 0.0004070399214749743,
|
| 2550 |
+
"loss": 0.9075,
|
| 2551 |
+
"step": 354
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.009867895289122382,
|
| 2555 |
+
"grad_norm": 0.10049542039632797,
|
| 2556 |
+
"learning_rate": 0.000401889469508784,
|
| 2557 |
+
"loss": 0.9626,
|
| 2558 |
+
"step": 355
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.009895692177260756,
|
| 2562 |
+
"grad_norm": 0.08796097338199615,
|
| 2563 |
+
"learning_rate": 0.00039676360352386354,
|
| 2564 |
+
"loss": 0.7321,
|
| 2565 |
+
"step": 356
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.009923489065399128,
|
| 2569 |
+
"grad_norm": 0.07982050627470016,
|
| 2570 |
+
"learning_rate": 0.00039166253422448684,
|
| 2571 |
+
"loss": 0.6331,
|
| 2572 |
+
"step": 357
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.009951285953537501,
|
| 2576 |
+
"grad_norm": 0.08986510336399078,
|
| 2577 |
+
"learning_rate": 0.0003865864712956336,
|
| 2578 |
+
"loss": 0.646,
|
| 2579 |
+
"step": 358
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.009979082841675875,
|
| 2583 |
+
"grad_norm": 0.0990855023264885,
|
| 2584 |
+
"learning_rate": 0.00038153562339436853,
|
| 2585 |
+
"loss": 0.7897,
|
| 2586 |
+
"step": 359
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.010006879729814247,
|
| 2590 |
+
"grad_norm": 0.09031044691801071,
|
| 2591 |
+
"learning_rate": 0.0003765101981412665,
|
| 2592 |
+
"loss": 0.7884,
|
| 2593 |
+
"step": 360
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.01003467661795262,
|
| 2597 |
+
"grad_norm": 0.08221515268087387,
|
| 2598 |
+
"learning_rate": 0.0003715104021118764,
|
| 2599 |
+
"loss": 0.787,
|
| 2600 |
+
"step": 361
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.010062473506090993,
|
| 2604 |
+
"grad_norm": 0.09221215546131134,
|
| 2605 |
+
"learning_rate": 0.00036653644082823046,
|
| 2606 |
+
"loss": 0.7991,
|
| 2607 |
+
"step": 362
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.010090270394229366,
|
| 2611 |
+
"grad_norm": 0.08920681476593018,
|
| 2612 |
+
"learning_rate": 0.00036158851875039456,
|
| 2613 |
+
"loss": 0.9703,
|
| 2614 |
+
"step": 363
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.010118067282367738,
|
| 2618 |
+
"grad_norm": 0.09488007426261902,
|
| 2619 |
+
"learning_rate": 0.0003566668392680662,
|
| 2620 |
+
"loss": 0.759,
|
| 2621 |
+
"step": 364
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.010145864170506112,
|
| 2625 |
+
"grad_norm": 0.0824998989701271,
|
| 2626 |
+
"learning_rate": 0.0003517716046922118,
|
| 2627 |
+
"loss": 0.6603,
|
| 2628 |
+
"step": 365
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.010173661058644486,
|
| 2632 |
+
"grad_norm": 0.0937090590596199,
|
| 2633 |
+
"learning_rate": 0.00034690301624675125,
|
| 2634 |
+
"loss": 0.7799,
|
| 2635 |
+
"step": 366
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.010201457946782858,
|
| 2639 |
+
"grad_norm": 0.08511339873075485,
|
| 2640 |
+
"learning_rate": 0.00034206127406028743,
|
| 2641 |
+
"loss": 0.6858,
|
| 2642 |
+
"step": 367
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.010229254834921231,
|
| 2646 |
+
"grad_norm": 0.09240502119064331,
|
| 2647 |
+
"learning_rate": 0.0003372465771578771,
|
| 2648 |
+
"loss": 0.8179,
|
| 2649 |
+
"step": 368
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.010257051723059603,
|
| 2653 |
+
"grad_norm": 0.08915253728628159,
|
| 2654 |
+
"learning_rate": 0.000332459123452852,
|
| 2655 |
+
"loss": 0.7399,
|
| 2656 |
+
"step": 369
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.010284848611197977,
|
| 2660 |
+
"grad_norm": 0.09466725587844849,
|
| 2661 |
+
"learning_rate": 0.00032769910973868313,
|
| 2662 |
+
"loss": 0.7574,
|
| 2663 |
+
"step": 370
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.010312645499336349,
|
| 2667 |
+
"grad_norm": 0.09638349711894989,
|
| 2668 |
+
"learning_rate": 0.00032296673168089073,
|
| 2669 |
+
"loss": 0.7101,
|
| 2670 |
+
"step": 371
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.010340442387474722,
|
| 2674 |
+
"grad_norm": 0.09288477897644043,
|
| 2675 |
+
"learning_rate": 0.0003182621838090006,
|
| 2676 |
+
"loss": 0.7876,
|
| 2677 |
+
"step": 372
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.010368239275613094,
|
| 2681 |
+
"grad_norm": 0.08711199462413788,
|
| 2682 |
+
"learning_rate": 0.0003135856595085498,
|
| 2683 |
+
"loss": 0.548,
|
| 2684 |
+
"step": 373
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.010396036163751468,
|
| 2688 |
+
"grad_norm": 0.09743466973304749,
|
| 2689 |
+
"learning_rate": 0.00030893735101313535,
|
| 2690 |
+
"loss": 0.7647,
|
| 2691 |
+
"step": 374
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.010423833051889842,
|
| 2695 |
+
"grad_norm": 0.10079675167798996,
|
| 2696 |
+
"learning_rate": 0.0003043174493965136,
|
| 2697 |
+
"loss": 0.6033,
|
| 2698 |
+
"step": 375
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.010451629940028214,
|
| 2702 |
+
"grad_norm": 0.11834803968667984,
|
| 2703 |
+
"learning_rate": 0.0002997261445647453,
|
| 2704 |
+
"loss": 0.7904,
|
| 2705 |
+
"step": 376
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.010479426828166587,
|
| 2709 |
+
"grad_norm": 0.10599831491708755,
|
| 2710 |
+
"learning_rate": 0.00029516362524838847,
|
| 2711 |
+
"loss": 0.6515,
|
| 2712 |
+
"step": 377
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.01050722371630496,
|
| 2716 |
+
"grad_norm": 0.09899824112653732,
|
| 2717 |
+
"learning_rate": 0.0002906300789947421,
|
| 2718 |
+
"loss": 0.5683,
|
| 2719 |
+
"step": 378
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.010535020604443333,
|
| 2723 |
+
"grad_norm": 0.09238414466381073,
|
| 2724 |
+
"learning_rate": 0.00028612569216013674,
|
| 2725 |
+
"loss": 0.5779,
|
| 2726 |
+
"step": 379
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.010562817492581705,
|
| 2730 |
+
"grad_norm": 0.0977087989449501,
|
| 2731 |
+
"learning_rate": 0.0002816506499022725,
|
| 2732 |
+
"loss": 0.562,
|
| 2733 |
+
"step": 380
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.010590614380720079,
|
| 2737 |
+
"grad_norm": 0.09863676875829697,
|
| 2738 |
+
"learning_rate": 0.00027720513617260855,
|
| 2739 |
+
"loss": 0.6458,
|
| 2740 |
+
"step": 381
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.01061841126885845,
|
| 2744 |
+
"grad_norm": 0.11672049015760422,
|
| 2745 |
+
"learning_rate": 0.0002727893337088027,
|
| 2746 |
+
"loss": 0.7436,
|
| 2747 |
+
"step": 382
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.010646208156996824,
|
| 2751 |
+
"grad_norm": 0.10594779998064041,
|
| 2752 |
+
"learning_rate": 0.0002684034240271986,
|
| 2753 |
+
"loss": 0.6286,
|
| 2754 |
+
"step": 383
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.010674005045135198,
|
| 2758 |
+
"grad_norm": 0.11194431781768799,
|
| 2759 |
+
"learning_rate": 0.00026404758741536505,
|
| 2760 |
+
"loss": 0.6866,
|
| 2761 |
+
"step": 384
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.01070180193327357,
|
| 2765 |
+
"grad_norm": 0.10711811482906342,
|
| 2766 |
+
"learning_rate": 0.00025972200292468463,
|
| 2767 |
+
"loss": 0.5329,
|
| 2768 |
+
"step": 385
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.010729598821411944,
|
| 2772 |
+
"grad_norm": 0.112278513610363,
|
| 2773 |
+
"learning_rate": 0.00025542684836299314,
|
| 2774 |
+
"loss": 0.6123,
|
| 2775 |
+
"step": 386
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.010757395709550316,
|
| 2779 |
+
"grad_norm": 0.12985379993915558,
|
| 2780 |
+
"learning_rate": 0.0002511623002872718,
|
| 2781 |
+
"loss": 0.686,
|
| 2782 |
+
"step": 387
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.01078519259768869,
|
| 2786 |
+
"grad_norm": 0.12807150185108185,
|
| 2787 |
+
"learning_rate": 0.00024692853399638914,
|
| 2788 |
+
"loss": 0.7307,
|
| 2789 |
+
"step": 388
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.010812989485827061,
|
| 2793 |
+
"grad_norm": 0.11589968949556351,
|
| 2794 |
+
"learning_rate": 0.00024272572352389488,
|
| 2795 |
+
"loss": 0.7484,
|
| 2796 |
+
"step": 389
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.010840786373965435,
|
| 2800 |
+
"grad_norm": 0.11197637766599655,
|
| 2801 |
+
"learning_rate": 0.0002385540416308656,
|
| 2802 |
+
"loss": 0.645,
|
| 2803 |
+
"step": 390
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.010868583262103807,
|
| 2807 |
+
"grad_norm": 0.11974731087684631,
|
| 2808 |
+
"learning_rate": 0.00023441365979880524,
|
| 2809 |
+
"loss": 0.6447,
|
| 2810 |
+
"step": 391
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.01089638015024218,
|
| 2814 |
+
"grad_norm": 0.11931908875703812,
|
| 2815 |
+
"learning_rate": 0.00023030474822259396,
|
| 2816 |
+
"loss": 0.5268,
|
| 2817 |
+
"step": 392
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.010924177038380554,
|
| 2821 |
+
"grad_norm": 0.1177850067615509,
|
| 2822 |
+
"learning_rate": 0.0002262274758034931,
|
| 2823 |
+
"loss": 0.5544,
|
| 2824 |
+
"step": 393
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.010951973926518926,
|
| 2828 |
+
"grad_norm": 0.12234242260456085,
|
| 2829 |
+
"learning_rate": 0.00022218201014220264,
|
| 2830 |
+
"loss": 0.6351,
|
| 2831 |
+
"step": 394
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.0109797708146573,
|
| 2835 |
+
"grad_norm": 0.12924128770828247,
|
| 2836 |
+
"learning_rate": 0.0002181685175319702,
|
| 2837 |
+
"loss": 0.6468,
|
| 2838 |
+
"step": 395
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.011007567702795672,
|
| 2842 |
+
"grad_norm": 0.1454528272151947,
|
| 2843 |
+
"learning_rate": 0.00021418716295175765,
|
| 2844 |
+
"loss": 0.6534,
|
| 2845 |
+
"step": 396
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.011035364590934045,
|
| 2849 |
+
"grad_norm": 0.13180844485759735,
|
| 2850 |
+
"learning_rate": 0.0002102381100594577,
|
| 2851 |
+
"loss": 0.5698,
|
| 2852 |
+
"step": 397
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.011063161479072417,
|
| 2856 |
+
"grad_norm": 0.1514425277709961,
|
| 2857 |
+
"learning_rate": 0.00020632152118516778,
|
| 2858 |
+
"loss": 0.6062,
|
| 2859 |
+
"step": 398
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.011090958367210791,
|
| 2863 |
+
"grad_norm": 0.1729186773300171,
|
| 2864 |
+
"learning_rate": 0.00020243755732451564,
|
| 2865 |
+
"loss": 0.6178,
|
| 2866 |
+
"step": 399
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.011118755255349163,
|
| 2870 |
+
"grad_norm": 0.2056732028722763,
|
| 2871 |
+
"learning_rate": 0.0001985863781320435,
|
| 2872 |
+
"loss": 0.7743,
|
| 2873 |
+
"step": 400
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.011118755255349163,
|
| 2877 |
+
"eval_loss": 0.7006093859672546,
|
| 2878 |
+
"eval_runtime": 49.996,
|
| 2879 |
+
"eval_samples_per_second": 11.541,
|
| 2880 |
+
"eval_steps_per_second": 5.78,
|
| 2881 |
+
"step": 400
|
| 2882 |
}
|
| 2883 |
],
|
| 2884 |
"logging_steps": 1,
|
|
|
|
| 2907 |
"attributes": {}
|
| 2908 |
}
|
| 2909 |
},
|
| 2910 |
+
"total_flos": 2.5658179794763776e+16,
|
| 2911 |
"train_batch_size": 2,
|
| 2912 |
"trial_name": null,
|
| 2913 |
"trial_params": null
|