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 191968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6373405c3b7c7600badd6498a3e066774e0c57029c515cb64512f41dd48d3903
|
| 3 |
size 191968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 253144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51d13d3160f1ba0241753affc9ac14d41be7161cdab70d44b1a83196f196a7e3
|
| 3 |
size 253144
|
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 sha256:5f681b5837dad30af7ed1e1f99dde6084a3e968786b6c9ef1e4b3c7c26041ca9
|
| 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": 10.
|
| 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": 218.003,
|
| 2522 |
"eval_steps_per_second": 54.501,
|
| 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":
|
| 2553 |
"train_batch_size": 8,
|
| 2554 |
"trial_name": null,
|
| 2555 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 10.268507957458496,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
| 4 |
+
"epoch": 0.3472222222222222,
|
| 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": 218.003,
|
| 2522 |
"eval_steps_per_second": 54.501,
|
| 2523 |
"step": 350
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.3046875,
|
| 2527 |
+
"grad_norm": 0.203641876578331,
|
| 2528 |
+
"learning_rate": 3.844650207332562e-06,
|
| 2529 |
+
"loss": 10.319,
|
| 2530 |
+
"step": 351
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.3055555555555556,
|
| 2534 |
+
"grad_norm": 0.15488123893737793,
|
| 2535 |
+
"learning_rate": 3.691267552111183e-06,
|
| 2536 |
+
"loss": 10.3176,
|
| 2537 |
+
"step": 352
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.3064236111111111,
|
| 2541 |
+
"grad_norm": 0.11736272275447845,
|
| 2542 |
+
"learning_rate": 3.54088980417534e-06,
|
| 2543 |
+
"loss": 10.3076,
|
| 2544 |
+
"step": 353
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.3072916666666667,
|
| 2548 |
+
"grad_norm": 0.11099082976579666,
|
| 2549 |
+
"learning_rate": 3.393526721321616e-06,
|
| 2550 |
+
"loss": 10.3029,
|
| 2551 |
+
"step": 354
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.3081597222222222,
|
| 2555 |
+
"grad_norm": 0.10357703268527985,
|
| 2556 |
+
"learning_rate": 3.249187865729264e-06,
|
| 2557 |
+
"loss": 10.3033,
|
| 2558 |
+
"step": 355
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.3090277777777778,
|
| 2562 |
+
"grad_norm": 0.10490359365940094,
|
| 2563 |
+
"learning_rate": 3.1078826033397843e-06,
|
| 2564 |
+
"loss": 10.2954,
|
| 2565 |
+
"step": 356
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.3098958333333333,
|
| 2569 |
+
"grad_norm": 0.10956919193267822,
|
| 2570 |
+
"learning_rate": 2.9696201032491434e-06,
|
| 2571 |
+
"loss": 10.2854,
|
| 2572 |
+
"step": 357
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.3107638888888889,
|
| 2576 |
+
"grad_norm": 0.10499009490013123,
|
| 2577 |
+
"learning_rate": 2.8344093371128424e-06,
|
| 2578 |
+
"loss": 10.2853,
|
| 2579 |
+
"step": 358
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.3116319444444444,
|
| 2583 |
+
"grad_norm": 0.10610862076282501,
|
| 2584 |
+
"learning_rate": 2.70225907856374e-06,
|
| 2585 |
+
"loss": 10.2744,
|
| 2586 |
+
"step": 359
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.3125,
|
| 2590 |
+
"grad_norm": 0.11454145610332489,
|
| 2591 |
+
"learning_rate": 2.573177902642726e-06,
|
| 2592 |
+
"loss": 10.2665,
|
| 2593 |
+
"step": 360
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.3133680555555556,
|
| 2597 |
+
"grad_norm": 0.10325542837381363,
|
| 2598 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 2599 |
+
"loss": 10.2665,
|
| 2600 |
+
"step": 361
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.3142361111111111,
|
| 2604 |
+
"grad_norm": 0.08684834092855453,
|
| 2605 |
+
"learning_rate": 2.324256102563188e-06,
|
| 2606 |
+
"loss": 10.272,
|
| 2607 |
+
"step": 362
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.3151041666666667,
|
| 2611 |
+
"grad_norm": 0.09154251217842102,
|
| 2612 |
+
"learning_rate": 2.204431630583548e-06,
|
| 2613 |
+
"loss": 10.2674,
|
| 2614 |
+
"step": 363
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.3159722222222222,
|
| 2618 |
+
"grad_norm": 0.08357816189527512,
|
| 2619 |
+
"learning_rate": 2.087708544541689e-06,
|
| 2620 |
+
"loss": 10.2681,
|
| 2621 |
+
"step": 364
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.3168402777777778,
|
| 2625 |
+
"grad_norm": 0.08111364394426346,
|
| 2626 |
+
"learning_rate": 1.974094418431388e-06,
|
| 2627 |
+
"loss": 10.2695,
|
| 2628 |
+
"step": 365
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.3177083333333333,
|
| 2632 |
+
"grad_norm": 0.0831846222281456,
|
| 2633 |
+
"learning_rate": 1.8635966245104664e-06,
|
| 2634 |
+
"loss": 10.2692,
|
| 2635 |
+
"step": 366
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.3185763888888889,
|
| 2639 |
+
"grad_norm": 0.08490800857543945,
|
| 2640 |
+
"learning_rate": 1.7562223328224325e-06,
|
| 2641 |
+
"loss": 10.2708,
|
| 2642 |
+
"step": 367
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.3194444444444444,
|
| 2646 |
+
"grad_norm": 0.06859968602657318,
|
| 2647 |
+
"learning_rate": 1.6519785107311891e-06,
|
| 2648 |
+
"loss": 10.2675,
|
| 2649 |
+
"step": 368
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.3203125,
|
| 2653 |
+
"grad_norm": 0.07412555068731308,
|
| 2654 |
+
"learning_rate": 1.5508719224689717e-06,
|
| 2655 |
+
"loss": 10.2658,
|
| 2656 |
+
"step": 369
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.3211805555555556,
|
| 2660 |
+
"grad_norm": 0.08164600282907486,
|
| 2661 |
+
"learning_rate": 1.4529091286973995e-06,
|
| 2662 |
+
"loss": 10.269,
|
| 2663 |
+
"step": 370
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.3220486111111111,
|
| 2667 |
+
"grad_norm": 0.08098141849040985,
|
| 2668 |
+
"learning_rate": 1.358096486081778e-06,
|
| 2669 |
+
"loss": 10.2648,
|
| 2670 |
+
"step": 371
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.3229166666666667,
|
| 2674 |
+
"grad_norm": 0.06871629506349564,
|
| 2675 |
+
"learning_rate": 1.2664401468786114e-06,
|
| 2676 |
+
"loss": 10.2708,
|
| 2677 |
+
"step": 372
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.3237847222222222,
|
| 2681 |
+
"grad_norm": 0.088385209441185,
|
| 2682 |
+
"learning_rate": 1.1779460585363944e-06,
|
| 2683 |
+
"loss": 10.2678,
|
| 2684 |
+
"step": 373
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.3246527777777778,
|
| 2688 |
+
"grad_norm": 0.07745223492383957,
|
| 2689 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 2690 |
+
"loss": 10.266,
|
| 2691 |
+
"step": 374
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.3255208333333333,
|
| 2695 |
+
"grad_norm": 0.07550082355737686,
|
| 2696 |
+
"learning_rate": 1.0104673978866164e-06,
|
| 2697 |
+
"loss": 10.2686,
|
| 2698 |
+
"step": 375
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.3263888888888889,
|
| 2702 |
+
"grad_norm": 0.07686543464660645,
|
| 2703 |
+
"learning_rate": 9.314936930293283e-07,
|
| 2704 |
+
"loss": 10.2672,
|
| 2705 |
+
"step": 376
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.3272569444444444,
|
| 2709 |
+
"grad_norm": 0.08065584301948547,
|
| 2710 |
+
"learning_rate": 8.557039732283944e-07,
|
| 2711 |
+
"loss": 10.2674,
|
| 2712 |
+
"step": 377
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.328125,
|
| 2716 |
+
"grad_norm": 0.06920608133077621,
|
| 2717 |
+
"learning_rate": 7.83103156370113e-07,
|
| 2718 |
+
"loss": 10.2662,
|
| 2719 |
+
"step": 378
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.3289930555555556,
|
| 2723 |
+
"grad_norm": 0.07387682795524597,
|
| 2724 |
+
"learning_rate": 7.136959534174592e-07,
|
| 2725 |
+
"loss": 10.2655,
|
| 2726 |
+
"step": 379
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.3298611111111111,
|
| 2730 |
+
"grad_norm": 0.08137144893407822,
|
| 2731 |
+
"learning_rate": 6.474868681043578e-07,
|
| 2732 |
+
"loss": 10.2659,
|
| 2733 |
+
"step": 380
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.3307291666666667,
|
| 2737 |
+
"grad_norm": 0.07337526977062225,
|
| 2738 |
+
"learning_rate": 5.844801966434832e-07,
|
| 2739 |
+
"loss": 10.2667,
|
| 2740 |
+
"step": 381
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.3315972222222222,
|
| 2744 |
+
"grad_norm": 0.07363461703062057,
|
| 2745 |
+
"learning_rate": 5.246800274474439e-07,
|
| 2746 |
+
"loss": 10.2668,
|
| 2747 |
+
"step": 382
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.3324652777777778,
|
| 2751 |
+
"grad_norm": 0.08539921045303345,
|
| 2752 |
+
"learning_rate": 4.680902408635335e-07,
|
| 2753 |
+
"loss": 10.2616,
|
| 2754 |
+
"step": 383
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.3333333333333333,
|
| 2758 |
+
"grad_norm": 0.07690860331058502,
|
| 2759 |
+
"learning_rate": 4.1471450892189846e-07,
|
| 2760 |
+
"loss": 10.2657,
|
| 2761 |
+
"step": 384
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.3342013888888889,
|
| 2765 |
+
"grad_norm": 0.082105353474617,
|
| 2766 |
+
"learning_rate": 3.6455629509730136e-07,
|
| 2767 |
+
"loss": 10.2667,
|
| 2768 |
+
"step": 385
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.3350694444444444,
|
| 2772 |
+
"grad_norm": 0.07633727043867111,
|
| 2773 |
+
"learning_rate": 3.1761885408435054e-07,
|
| 2774 |
+
"loss": 10.2706,
|
| 2775 |
+
"step": 386
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.3359375,
|
| 2779 |
+
"grad_norm": 0.08272045850753784,
|
| 2780 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 2781 |
+
"loss": 10.2652,
|
| 2782 |
+
"step": 387
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.3368055555555556,
|
| 2786 |
+
"grad_norm": 0.07836596667766571,
|
| 2787 |
+
"learning_rate": 2.334182641175686e-07,
|
| 2788 |
+
"loss": 10.265,
|
| 2789 |
+
"step": 388
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.3376736111111111,
|
| 2793 |
+
"grad_norm": 0.07885283976793289,
|
| 2794 |
+
"learning_rate": 1.9616057881935436e-07,
|
| 2795 |
+
"loss": 10.266,
|
| 2796 |
+
"step": 389
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.3385416666666667,
|
| 2800 |
+
"grad_norm": 0.08755853027105331,
|
| 2801 |
+
"learning_rate": 1.6213459328950352e-07,
|
| 2802 |
+
"loss": 10.2633,
|
| 2803 |
+
"step": 390
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.3394097222222222,
|
| 2807 |
+
"grad_norm": 0.09107019752264023,
|
| 2808 |
+
"learning_rate": 1.3134251542544774e-07,
|
| 2809 |
+
"loss": 10.2691,
|
| 2810 |
+
"step": 391
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.3402777777777778,
|
| 2814 |
+
"grad_norm": 0.10855327546596527,
|
| 2815 |
+
"learning_rate": 1.0378634328099269e-07,
|
| 2816 |
+
"loss": 10.2641,
|
| 2817 |
+
"step": 392
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.3411458333333333,
|
| 2821 |
+
"grad_norm": 0.0946725383400917,
|
| 2822 |
+
"learning_rate": 7.946786493666647e-08,
|
| 2823 |
+
"loss": 10.2628,
|
| 2824 |
+
"step": 393
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.3420138888888889,
|
| 2828 |
+
"grad_norm": 0.10138517618179321,
|
| 2829 |
+
"learning_rate": 5.838865838366792e-08,
|
| 2830 |
+
"loss": 10.265,
|
| 2831 |
+
"step": 394
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.3428819444444444,
|
| 2835 |
+
"grad_norm": 0.08748935163021088,
|
| 2836 |
+
"learning_rate": 4.055009142152067e-08,
|
| 2837 |
+
"loss": 10.2632,
|
| 2838 |
+
"step": 395
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.34375,
|
| 2842 |
+
"grad_norm": 0.09347328543663025,
|
| 2843 |
+
"learning_rate": 2.595332156925534e-08,
|
| 2844 |
+
"loss": 10.2627,
|
| 2845 |
+
"step": 396
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.3446180555555556,
|
| 2849 |
+
"grad_norm": 0.1317155361175537,
|
| 2850 |
+
"learning_rate": 1.4599295990352924e-08,
|
| 2851 |
+
"loss": 10.2702,
|
| 2852 |
+
"step": 397
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.3454861111111111,
|
| 2856 |
+
"grad_norm": 0.1449960321187973,
|
| 2857 |
+
"learning_rate": 6.488751431266149e-09,
|
| 2858 |
+
"loss": 10.268,
|
| 2859 |
+
"step": 398
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.3463541666666667,
|
| 2863 |
+
"grad_norm": 0.12930181622505188,
|
| 2864 |
+
"learning_rate": 1.622214173602199e-09,
|
| 2865 |
+
"loss": 10.2639,
|
| 2866 |
+
"step": 399
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.3472222222222222,
|
| 2870 |
+
"grad_norm": 0.1722465306520462,
|
| 2871 |
+
"learning_rate": 0.0,
|
| 2872 |
+
"loss": 10.261,
|
| 2873 |
+
"step": 400
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.3472222222222222,
|
| 2877 |
+
"eval_loss": 10.268507957458496,
|
| 2878 |
+
"eval_runtime": 9.2056,
|
| 2879 |
+
"eval_samples_per_second": 210.742,
|
| 2880 |
+
"eval_steps_per_second": 52.685,
|
| 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": 44620264243200.0,
|
| 2911 |
"train_batch_size": 8,
|
| 2912 |
"trial_name": null,
|
| 2913 |
"trial_params": null
|