Training in progress, step 400, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 78480072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17224b2b3a91c0e9521d45a24436b841bfe6523957efd7e7cd1dd6c5ebdc3b1b
|
| 3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157104826
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e37a68b13eabe1e8db809461fb70508ce003e5a782bb20d5ded4257e3d6e09b
|
| 3 |
size 157104826
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c902599e1e01ff9dd003b50caf7eaa257324aa8302b2cf854a158eb29295c69
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de2bfb1b87844b729adff3b7b1db70234c5ded5f2c4da917a4abb3fe4d0e1d04
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47fce9310ac087a1e60a1910546a7146b9eb3606950c9f78a8a4262e409e9fc
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3085a74797e29a3dad431860055a9066c135bf30fe41ef3edbddc1e5b4931620
|
| 3 |
size 15024
|
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 sha256:5a6bd280b1fbb3316d4d258b95b1a2fe83754ff0ca1384b0f72c1296f3c08afc
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2577,6 +2577,372 @@
|
|
| 2577 |
"eval_samples_per_second": 71.844,
|
| 2578 |
"eval_steps_per_second": 18.68,
|
| 2579 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2580 |
}
|
| 2581 |
],
|
| 2582 |
"logging_steps": 1,
|
|
@@ -2605,7 +2971,7 @@
|
|
| 2605 |
"attributes": {}
|
| 2606 |
}
|
| 2607 |
},
|
| 2608 |
-
"total_flos": 2.
|
| 2609 |
"train_batch_size": 1,
|
| 2610 |
"trial_name": null,
|
| 2611 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.7484028447256605e-08,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
| 4 |
+
"epoch": 1.339030892269092,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2577 |
"eval_samples_per_second": 71.844,
|
| 2578 |
"eval_steps_per_second": 18.68,
|
| 2579 |
"step": 350
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.175108462704511,
|
| 2583 |
+
"grad_norm": 6.101056442275876e-06,
|
| 2584 |
+
"learning_rate": 0.0001466262735086344,
|
| 2585 |
+
"loss": 0.0,
|
| 2586 |
+
"step": 351
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.1784538184099107,
|
| 2590 |
+
"grad_norm": 5.789248461951502e-06,
|
| 2591 |
+
"learning_rate": 0.00014632641266128428,
|
| 2592 |
+
"loss": 0.0,
|
| 2593 |
+
"step": 352
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.1817991741153102,
|
| 2597 |
+
"grad_norm": 5.922979653405491e-06,
|
| 2598 |
+
"learning_rate": 0.00014602606930290456,
|
| 2599 |
+
"loss": 0.0,
|
| 2600 |
+
"step": 353
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.1851445298207097,
|
| 2604 |
+
"grad_norm": 5.770634743385017e-06,
|
| 2605 |
+
"learning_rate": 0.0001457252474228511,
|
| 2606 |
+
"loss": 0.0,
|
| 2607 |
+
"step": 354
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.1884898855261095,
|
| 2611 |
+
"grad_norm": 5.891377441002987e-06,
|
| 2612 |
+
"learning_rate": 0.00014542395101683561,
|
| 2613 |
+
"loss": 0.0,
|
| 2614 |
+
"step": 355
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.1918352412315092,
|
| 2618 |
+
"grad_norm": 5.779205366707174e-06,
|
| 2619 |
+
"learning_rate": 0.00014512218408687286,
|
| 2620 |
+
"loss": 0.0,
|
| 2621 |
+
"step": 356
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.1951805969369087,
|
| 2625 |
+
"grad_norm": 6.2929498199082445e-06,
|
| 2626 |
+
"learning_rate": 0.0001448199506412274,
|
| 2627 |
+
"loss": 0.0,
|
| 2628 |
+
"step": 357
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.1985259526423082,
|
| 2632 |
+
"grad_norm": 5.800653980259085e-06,
|
| 2633 |
+
"learning_rate": 0.00014451725469436037,
|
| 2634 |
+
"loss": 0.0,
|
| 2635 |
+
"step": 358
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.201871308347708,
|
| 2639 |
+
"grad_norm": 6.026995379215805e-06,
|
| 2640 |
+
"learning_rate": 0.00014421410026687609,
|
| 2641 |
+
"loss": 0.0,
|
| 2642 |
+
"step": 359
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.2052166640531075,
|
| 2646 |
+
"grad_norm": 6.040312655386515e-06,
|
| 2647 |
+
"learning_rate": 0.00014391049138546872,
|
| 2648 |
+
"loss": 0.0,
|
| 2649 |
+
"step": 360
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.2085620197585072,
|
| 2653 |
+
"grad_norm": 6.384302650985774e-06,
|
| 2654 |
+
"learning_rate": 0.00014360643208286887,
|
| 2655 |
+
"loss": 0.0,
|
| 2656 |
+
"step": 361
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.2119073754639067,
|
| 2660 |
+
"grad_norm": 6.054286586731905e-06,
|
| 2661 |
+
"learning_rate": 0.00014330192639778986,
|
| 2662 |
+
"loss": 0.0,
|
| 2663 |
+
"step": 362
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 1.2152527311693064,
|
| 2667 |
+
"grad_norm": 5.83691962674493e-06,
|
| 2668 |
+
"learning_rate": 0.00014299697837487414,
|
| 2669 |
+
"loss": 0.0,
|
| 2670 |
+
"step": 363
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 1.218598086874706,
|
| 2674 |
+
"grad_norm": 5.789472197648138e-06,
|
| 2675 |
+
"learning_rate": 0.0001426915920646396,
|
| 2676 |
+
"loss": 0.0,
|
| 2677 |
+
"step": 364
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 1.2219434425801057,
|
| 2681 |
+
"grad_norm": 6.030274562363047e-06,
|
| 2682 |
+
"learning_rate": 0.0001423857715234258,
|
| 2683 |
+
"loss": 0.0,
|
| 2684 |
+
"step": 365
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 1.2252887982855052,
|
| 2688 |
+
"grad_norm": 6.083088010200299e-06,
|
| 2689 |
+
"learning_rate": 0.00014207952081333992,
|
| 2690 |
+
"loss": 0.0,
|
| 2691 |
+
"step": 366
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 1.228634153990905,
|
| 2695 |
+
"grad_norm": 5.530882390303304e-06,
|
| 2696 |
+
"learning_rate": 0.00014177284400220306,
|
| 2697 |
+
"loss": 0.0,
|
| 2698 |
+
"step": 367
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.2319795096963044,
|
| 2702 |
+
"grad_norm": 5.863201749889413e-06,
|
| 2703 |
+
"learning_rate": 0.00014146574516349595,
|
| 2704 |
+
"loss": 0.0,
|
| 2705 |
+
"step": 368
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 1.235324865401704,
|
| 2709 |
+
"grad_norm": 6.111798938945867e-06,
|
| 2710 |
+
"learning_rate": 0.000141158228376305,
|
| 2711 |
+
"loss": 0.0,
|
| 2712 |
+
"step": 369
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 1.2386702211071037,
|
| 2716 |
+
"grad_norm": 6.045273494237335e-06,
|
| 2717 |
+
"learning_rate": 0.00014085029772526814,
|
| 2718 |
+
"loss": 0.0,
|
| 2719 |
+
"step": 370
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.2420155768125032,
|
| 2723 |
+
"grad_norm": 6.002165719110053e-06,
|
| 2724 |
+
"learning_rate": 0.0001405419573005205,
|
| 2725 |
+
"loss": 0.0,
|
| 2726 |
+
"step": 371
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 1.245360932517903,
|
| 2730 |
+
"grad_norm": 6.039120307832491e-06,
|
| 2731 |
+
"learning_rate": 0.00014023321119764002,
|
| 2732 |
+
"loss": 0.0,
|
| 2733 |
+
"step": 372
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 1.2487062882233024,
|
| 2737 |
+
"grad_norm": 6.003551789035555e-06,
|
| 2738 |
+
"learning_rate": 0.0001399240635175932,
|
| 2739 |
+
"loss": 0.0,
|
| 2740 |
+
"step": 373
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 1.2520516439287022,
|
| 2744 |
+
"grad_norm": 5.915948804613436e-06,
|
| 2745 |
+
"learning_rate": 0.00013961451836668043,
|
| 2746 |
+
"loss": 0.0,
|
| 2747 |
+
"step": 374
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 1.2553969996341017,
|
| 2751 |
+
"grad_norm": 5.859969860466663e-06,
|
| 2752 |
+
"learning_rate": 0.00013930457985648168,
|
| 2753 |
+
"loss": 0.0,
|
| 2754 |
+
"step": 375
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.2553969996341017,
|
| 2758 |
+
"eval_loss": 1.7748938319073204e-08,
|
| 2759 |
+
"eval_runtime": 0.6961,
|
| 2760 |
+
"eval_samples_per_second": 71.824,
|
| 2761 |
+
"eval_steps_per_second": 18.674,
|
| 2762 |
+
"step": 375
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 1.2587423553395014,
|
| 2766 |
+
"grad_norm": 5.691527803719509e-06,
|
| 2767 |
+
"learning_rate": 0.00013899425210380176,
|
| 2768 |
+
"loss": 0.0,
|
| 2769 |
+
"step": 376
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 1.262087711044901,
|
| 2773 |
+
"grad_norm": 5.914226676395629e-06,
|
| 2774 |
+
"learning_rate": 0.00013868353923061563,
|
| 2775 |
+
"loss": 0.0,
|
| 2776 |
+
"step": 377
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 1.2654330667503007,
|
| 2780 |
+
"grad_norm": 5.989952114759944e-06,
|
| 2781 |
+
"learning_rate": 0.0001383724453640137,
|
| 2782 |
+
"loss": 0.0,
|
| 2783 |
+
"step": 378
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 1.2687784224557002,
|
| 2787 |
+
"grad_norm": 5.64041874895338e-06,
|
| 2788 |
+
"learning_rate": 0.00013806097463614692,
|
| 2789 |
+
"loss": 0.0,
|
| 2790 |
+
"step": 379
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 1.2721237781610997,
|
| 2794 |
+
"grad_norm": 6.035153546690708e-06,
|
| 2795 |
+
"learning_rate": 0.00013774913118417195,
|
| 2796 |
+
"loss": 0.0,
|
| 2797 |
+
"step": 380
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 1.2754691338664994,
|
| 2801 |
+
"grad_norm": 5.875488113815663e-06,
|
| 2802 |
+
"learning_rate": 0.0001374369191501963,
|
| 2803 |
+
"loss": 0.0,
|
| 2804 |
+
"step": 381
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 1.2788144895718991,
|
| 2808 |
+
"grad_norm": 6.396473509084899e-06,
|
| 2809 |
+
"learning_rate": 0.00013712434268122324,
|
| 2810 |
+
"loss": 0.0,
|
| 2811 |
+
"step": 382
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 1.2821598452772986,
|
| 2815 |
+
"grad_norm": 5.975215117359767e-06,
|
| 2816 |
+
"learning_rate": 0.00013681140592909652,
|
| 2817 |
+
"loss": 0.0,
|
| 2818 |
+
"step": 383
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 1.2855052009826982,
|
| 2822 |
+
"grad_norm": 5.922964191995561e-06,
|
| 2823 |
+
"learning_rate": 0.00013649811305044558,
|
| 2824 |
+
"loss": 0.0,
|
| 2825 |
+
"step": 384
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 1.288850556688098,
|
| 2829 |
+
"grad_norm": 5.88319653616054e-06,
|
| 2830 |
+
"learning_rate": 0.00013618446820663015,
|
| 2831 |
+
"loss": 0.0,
|
| 2832 |
+
"step": 385
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 1.2921959123934974,
|
| 2836 |
+
"grad_norm": 6.589156328118406e-06,
|
| 2837 |
+
"learning_rate": 0.00013587047556368493,
|
| 2838 |
+
"loss": 0.0,
|
| 2839 |
+
"step": 386
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 1.2955412680988971,
|
| 2843 |
+
"grad_norm": 5.7994789131043945e-06,
|
| 2844 |
+
"learning_rate": 0.00013555613929226433,
|
| 2845 |
+
"loss": 0.0,
|
| 2846 |
+
"step": 387
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 1.2988866238042966,
|
| 2850 |
+
"grad_norm": 5.76379807171179e-06,
|
| 2851 |
+
"learning_rate": 0.00013524146356758704,
|
| 2852 |
+
"loss": 0.0,
|
| 2853 |
+
"step": 388
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 1.3022319795096964,
|
| 2857 |
+
"grad_norm": 5.537129709409783e-06,
|
| 2858 |
+
"learning_rate": 0.00013492645256938068,
|
| 2859 |
+
"loss": 0.0,
|
| 2860 |
+
"step": 389
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 1.305577335215096,
|
| 2864 |
+
"grad_norm": 5.805138698633527e-06,
|
| 2865 |
+
"learning_rate": 0.00013461111048182608,
|
| 2866 |
+
"loss": 0.0,
|
| 2867 |
+
"step": 390
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 1.3089226909204954,
|
| 2871 |
+
"grad_norm": 5.993603735987563e-06,
|
| 2872 |
+
"learning_rate": 0.00013429544149350187,
|
| 2873 |
+
"loss": 0.0,
|
| 2874 |
+
"step": 391
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 1.3122680466258951,
|
| 2878 |
+
"grad_norm": 5.531137048819801e-06,
|
| 2879 |
+
"learning_rate": 0.00013397944979732872,
|
| 2880 |
+
"loss": 0.0,
|
| 2881 |
+
"step": 392
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 1.3156134023312949,
|
| 2885 |
+
"grad_norm": 5.714673534384929e-06,
|
| 2886 |
+
"learning_rate": 0.00013366313959051383,
|
| 2887 |
+
"loss": 0.0,
|
| 2888 |
+
"step": 393
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 1.3189587580366944,
|
| 2892 |
+
"grad_norm": 5.987948497931939e-06,
|
| 2893 |
+
"learning_rate": 0.000133346515074495,
|
| 2894 |
+
"loss": 0.0,
|
| 2895 |
+
"step": 394
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 1.322304113742094,
|
| 2899 |
+
"grad_norm": 6.1729906519758515e-06,
|
| 2900 |
+
"learning_rate": 0.00013302958045488493,
|
| 2901 |
+
"loss": 0.0,
|
| 2902 |
+
"step": 395
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 1.3256494694474936,
|
| 2906 |
+
"grad_norm": 5.74833165956079e-06,
|
| 2907 |
+
"learning_rate": 0.00013271233994141516,
|
| 2908 |
+
"loss": 0.0,
|
| 2909 |
+
"step": 396
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 1.3289948251528931,
|
| 2913 |
+
"grad_norm": 5.835729098180309e-06,
|
| 2914 |
+
"learning_rate": 0.0001323947977478806,
|
| 2915 |
+
"loss": 0.0,
|
| 2916 |
+
"step": 397
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 1.3323401808582929,
|
| 2920 |
+
"grad_norm": 5.932717158430023e-06,
|
| 2921 |
+
"learning_rate": 0.00013207695809208295,
|
| 2922 |
+
"loss": 0.0,
|
| 2923 |
+
"step": 398
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 1.3356855365636924,
|
| 2927 |
+
"grad_norm": 6.128618224465754e-06,
|
| 2928 |
+
"learning_rate": 0.00013175882519577526,
|
| 2929 |
+
"loss": 0.0,
|
| 2930 |
+
"step": 399
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 1.339030892269092,
|
| 2934 |
+
"grad_norm": 5.671974122378742e-06,
|
| 2935 |
+
"learning_rate": 0.00013144040328460545,
|
| 2936 |
+
"loss": 0.0,
|
| 2937 |
+
"step": 400
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 1.339030892269092,
|
| 2941 |
+
"eval_loss": 1.7484028447256605e-08,
|
| 2942 |
+
"eval_runtime": 0.6964,
|
| 2943 |
+
"eval_samples_per_second": 71.794,
|
| 2944 |
+
"eval_steps_per_second": 18.666,
|
| 2945 |
+
"step": 400
|
| 2946 |
}
|
| 2947 |
],
|
| 2948 |
"logging_steps": 1,
|
|
|
|
| 2971 |
"attributes": {}
|
| 2972 |
}
|
| 2973 |
},
|
| 2974 |
+
"total_flos": 2.518464884165837e+18,
|
| 2975 |
"train_batch_size": 1,
|
| 2976 |
"trial_name": null,
|
| 2977 |
"trial_params": null
|