Training in progress, step 20000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1153648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4676a585cd10eaab3d2ddf739211d0bbdbb0c1b83d4d3a7abb61f7653299182a
|
| 3 |
size 1153648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2334411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebbbbfe8fc3620e8e0e2bce73131a835c3752a4ff0f9bb46d50a34c31311fd1a
|
| 3 |
size 2334411
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3cf269e4f0f154570fbcc6523fd446e1760395fbcb34930013fc17c8b888e8f
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1838e2ba3161fe9cda5ffbc1228be866f2d720c99e25c4fc0f69015d501e1608
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fc2ea16c5e587c6641bc757032060e2ffce8af5ca147fd641f2d49009e914d3
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2528,6 +2528,286 @@
|
|
| 2528 |
"learning_rate": 0.0007005716838935606,
|
| 2529 |
"loss": 5.033485107421875,
|
| 2530 |
"step": 18000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2531 |
}
|
| 2532 |
],
|
| 2533 |
"logging_steps": 50,
|
|
@@ -2547,7 +2827,7 @@
|
|
| 2547 |
"attributes": {}
|
| 2548 |
}
|
| 2549 |
},
|
| 2550 |
-
"total_flos":
|
| 2551 |
"train_batch_size": 16,
|
| 2552 |
"trial_name": null,
|
| 2553 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.409592660099531,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 20000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2528 |
"learning_rate": 0.0007005716838935606,
|
| 2529 |
"loss": 5.033485107421875,
|
| 2530 |
"step": 18000
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.36965737573982677,
|
| 2534 |
+
"grad_norm": 0.7636358737945557,
|
| 2535 |
+
"learning_rate": 0.0006990972686104094,
|
| 2536 |
+
"loss": 5.063385009765625,
|
| 2537 |
+
"step": 18050
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.37068135739007557,
|
| 2541 |
+
"grad_norm": 0.9184279441833496,
|
| 2542 |
+
"learning_rate": 0.0006976207929392135,
|
| 2543 |
+
"loss": 5.050696716308594,
|
| 2544 |
+
"step": 18100
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.3717053390403244,
|
| 2548 |
+
"grad_norm": 0.6665329933166504,
|
| 2549 |
+
"learning_rate": 0.0006961422721595038,
|
| 2550 |
+
"loss": 5.058174133300781,
|
| 2551 |
+
"step": 18150
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.37272932069057324,
|
| 2555 |
+
"grad_norm": 0.8154553174972534,
|
| 2556 |
+
"learning_rate": 0.0006946617215719751,
|
| 2557 |
+
"loss": 5.061642761230469,
|
| 2558 |
+
"step": 18200
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.37375330234082205,
|
| 2562 |
+
"grad_norm": 0.8320987224578857,
|
| 2563 |
+
"learning_rate": 0.0006931791564983277,
|
| 2564 |
+
"loss": 5.052000732421875,
|
| 2565 |
+
"step": 18250
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.37477728399107085,
|
| 2569 |
+
"grad_norm": 1.5270822048187256,
|
| 2570 |
+
"learning_rate": 0.0006916945922811096,
|
| 2571 |
+
"loss": 5.078252258300782,
|
| 2572 |
+
"step": 18300
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.3758012656413197,
|
| 2576 |
+
"grad_norm": 1.0495359897613525,
|
| 2577 |
+
"learning_rate": 0.0006902080442835571,
|
| 2578 |
+
"loss": 5.075197448730469,
|
| 2579 |
+
"step": 18350
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.3768252472915685,
|
| 2583 |
+
"grad_norm": 0.672983705997467,
|
| 2584 |
+
"learning_rate": 0.0006887195278894356,
|
| 2585 |
+
"loss": 5.053647155761719,
|
| 2586 |
+
"step": 18400
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.3778492289418174,
|
| 2590 |
+
"grad_norm": 0.670332133769989,
|
| 2591 |
+
"learning_rate": 0.0006872290585028811,
|
| 2592 |
+
"loss": 5.047108459472656,
|
| 2593 |
+
"step": 18450
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.3788732105920662,
|
| 2597 |
+
"grad_norm": 1.0029726028442383,
|
| 2598 |
+
"learning_rate": 0.0006857366515482404,
|
| 2599 |
+
"loss": 5.051429748535156,
|
| 2600 |
+
"step": 18500
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.379897192242315,
|
| 2604 |
+
"grad_norm": 1.1316640377044678,
|
| 2605 |
+
"learning_rate": 0.0006842423224699113,
|
| 2606 |
+
"loss": 5.0507901000976565,
|
| 2607 |
+
"step": 18550
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.38092117389256386,
|
| 2611 |
+
"grad_norm": 0.7852043509483337,
|
| 2612 |
+
"learning_rate": 0.0006827460867321833,
|
| 2613 |
+
"loss": 5.049589538574219,
|
| 2614 |
+
"step": 18600
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.38194515554281266,
|
| 2618 |
+
"grad_norm": 0.7164134979248047,
|
| 2619 |
+
"learning_rate": 0.0006812479598190769,
|
| 2620 |
+
"loss": 5.053612365722656,
|
| 2621 |
+
"step": 18650
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.3829691371930615,
|
| 2625 |
+
"grad_norm": 0.7085393071174622,
|
| 2626 |
+
"learning_rate": 0.0006797479572341841,
|
| 2627 |
+
"loss": 5.053797302246093,
|
| 2628 |
+
"step": 18700
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.38399311884331033,
|
| 2632 |
+
"grad_norm": 0.8508812785148621,
|
| 2633 |
+
"learning_rate": 0.0006782460945005073,
|
| 2634 |
+
"loss": 5.055107116699219,
|
| 2635 |
+
"step": 18750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.38501710049355914,
|
| 2639 |
+
"grad_norm": 1.0779728889465332,
|
| 2640 |
+
"learning_rate": 0.0006767423871602989,
|
| 2641 |
+
"loss": 5.035299377441406,
|
| 2642 |
+
"step": 18800
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.386041082143808,
|
| 2646 |
+
"grad_norm": 0.7567844986915588,
|
| 2647 |
+
"learning_rate": 0.0006752368507749007,
|
| 2648 |
+
"loss": 5.038133544921875,
|
| 2649 |
+
"step": 18850
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.3870650637940568,
|
| 2653 |
+
"grad_norm": 0.8647480010986328,
|
| 2654 |
+
"learning_rate": 0.0006737295009245825,
|
| 2655 |
+
"loss": 5.081793212890625,
|
| 2656 |
+
"step": 18900
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.3880890454443056,
|
| 2660 |
+
"grad_norm": 1.3544557094573975,
|
| 2661 |
+
"learning_rate": 0.0006722203532083809,
|
| 2662 |
+
"loss": 5.033754577636719,
|
| 2663 |
+
"step": 18950
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.3891130270945545,
|
| 2667 |
+
"grad_norm": 0.7464925050735474,
|
| 2668 |
+
"learning_rate": 0.0006707094232439385,
|
| 2669 |
+
"loss": 5.054624328613281,
|
| 2670 |
+
"step": 19000
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.3901370087448033,
|
| 2674 |
+
"grad_norm": 0.7555453181266785,
|
| 2675 |
+
"learning_rate": 0.0006691967266673411,
|
| 2676 |
+
"loss": 5.0876837158203125,
|
| 2677 |
+
"step": 19050
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.39116099039505214,
|
| 2681 |
+
"grad_norm": 0.8442673087120056,
|
| 2682 |
+
"learning_rate": 0.000667682279132957,
|
| 2683 |
+
"loss": 5.029152526855468,
|
| 2684 |
+
"step": 19100
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.39218497204530095,
|
| 2688 |
+
"grad_norm": 0.6767661571502686,
|
| 2689 |
+
"learning_rate": 0.0006661660963132745,
|
| 2690 |
+
"loss": 5.040547180175781,
|
| 2691 |
+
"step": 19150
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.39320895369554976,
|
| 2695 |
+
"grad_norm": 0.7364939451217651,
|
| 2696 |
+
"learning_rate": 0.0006646481938987392,
|
| 2697 |
+
"loss": 5.065225830078125,
|
| 2698 |
+
"step": 19200
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.3942329353457986,
|
| 2702 |
+
"grad_norm": 0.7141822576522827,
|
| 2703 |
+
"learning_rate": 0.0006631285875975932,
|
| 2704 |
+
"loss": 5.042987976074219,
|
| 2705 |
+
"step": 19250
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.3952569169960474,
|
| 2709 |
+
"grad_norm": 1.044058918952942,
|
| 2710 |
+
"learning_rate": 0.0006616072931357105,
|
| 2711 |
+
"loss": 5.053731689453125,
|
| 2712 |
+
"step": 19300
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.39628089864629623,
|
| 2716 |
+
"grad_norm": 1.265608310699463,
|
| 2717 |
+
"learning_rate": 0.0006600843262564364,
|
| 2718 |
+
"loss": 5.03171142578125,
|
| 2719 |
+
"step": 19350
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.3973048802965451,
|
| 2723 |
+
"grad_norm": 0.6321577429771423,
|
| 2724 |
+
"learning_rate": 0.0006585597027204222,
|
| 2725 |
+
"loss": 5.048243713378906,
|
| 2726 |
+
"step": 19400
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.3983288619467939,
|
| 2730 |
+
"grad_norm": 0.8778825402259827,
|
| 2731 |
+
"learning_rate": 0.0006570334383054641,
|
| 2732 |
+
"loss": 5.062862548828125,
|
| 2733 |
+
"step": 19450
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.39935284359704276,
|
| 2737 |
+
"grad_norm": 0.8101491928100586,
|
| 2738 |
+
"learning_rate": 0.0006555055488063395,
|
| 2739 |
+
"loss": 5.0427880859375,
|
| 2740 |
+
"step": 19500
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.40037682524729157,
|
| 2744 |
+
"grad_norm": 0.8631314039230347,
|
| 2745 |
+
"learning_rate": 0.0006539760500346424,
|
| 2746 |
+
"loss": 5.03111572265625,
|
| 2747 |
+
"step": 19550
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.4014008068975404,
|
| 2751 |
+
"grad_norm": 0.6848158240318298,
|
| 2752 |
+
"learning_rate": 0.0006524449578186211,
|
| 2753 |
+
"loss": 5.0429690551757815,
|
| 2754 |
+
"step": 19600
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.40242478854778924,
|
| 2758 |
+
"grad_norm": 0.6955616474151611,
|
| 2759 |
+
"learning_rate": 0.0006509122880030138,
|
| 2760 |
+
"loss": 5.026622009277344,
|
| 2761 |
+
"step": 19650
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.40344877019803804,
|
| 2765 |
+
"grad_norm": 1.1957049369812012,
|
| 2766 |
+
"learning_rate": 0.0006493780564488847,
|
| 2767 |
+
"loss": 5.060218811035156,
|
| 2768 |
+
"step": 19700
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.4044727518482869,
|
| 2772 |
+
"grad_norm": 1.0335688591003418,
|
| 2773 |
+
"learning_rate": 0.0006478422790334599,
|
| 2774 |
+
"loss": 5.05376220703125,
|
| 2775 |
+
"step": 19750
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.4054967334985357,
|
| 2779 |
+
"grad_norm": 1.0196553468704224,
|
| 2780 |
+
"learning_rate": 0.0006463049716499632,
|
| 2781 |
+
"loss": 5.0673001098632815,
|
| 2782 |
+
"step": 19800
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.4065207151487845,
|
| 2786 |
+
"grad_norm": 0.7199227809906006,
|
| 2787 |
+
"learning_rate": 0.0006447661502074513,
|
| 2788 |
+
"loss": 5.049782409667968,
|
| 2789 |
+
"step": 19850
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.4075446967990334,
|
| 2793 |
+
"grad_norm": 0.8298079371452332,
|
| 2794 |
+
"learning_rate": 0.0006432258306306493,
|
| 2795 |
+
"loss": 5.046539916992187,
|
| 2796 |
+
"step": 19900
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.4085686784492822,
|
| 2800 |
+
"grad_norm": 0.8933535218238831,
|
| 2801 |
+
"learning_rate": 0.0006416840288597865,
|
| 2802 |
+
"loss": 5.0574407958984375,
|
| 2803 |
+
"step": 19950
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.409592660099531,
|
| 2807 |
+
"grad_norm": 3.0162930488586426,
|
| 2808 |
+
"learning_rate": 0.0006401407608504303,
|
| 2809 |
+
"loss": 5.066023559570312,
|
| 2810 |
+
"step": 20000
|
| 2811 |
}
|
| 2812 |
],
|
| 2813 |
"logging_steps": 50,
|
|
|
|
| 2827 |
"attributes": {}
|
| 2828 |
}
|
| 2829 |
},
|
| 2830 |
+
"total_flos": 260655022080000.0,
|
| 2831 |
"train_batch_size": 16,
|
| 2832 |
"trial_name": null,
|
| 2833 |
"trial_params": null
|