Training in progress, step 36000, 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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:113fb894b062b29cf117cc658db504261451a8ff8c1a0cb06fb7e28935cf14f7
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a46699af39339744e0585d58fd78b70cf3632fc84e8d7d9301d7e78f3c4dfc81
|
| 3 |
size 938825803
|
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:cadea5b42974dfb2cd316f1afeedc6d7ac097ea0c6cf0e13d2fffcae3de277b9
|
| 3 |
size 14645
|
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:f1f70882941e6b31d82263e4fc807f24daa03205e781becc1cf39b5843e1bb88
|
| 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": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2504,6 +2504,318 @@
|
|
| 2504 |
"eval_samples_per_second": 84.308,
|
| 2505 |
"eval_steps_per_second": 21.077,
|
| 2506 |
"step": 32000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2507 |
}
|
| 2508 |
],
|
| 2509 |
"logging_steps": 100,
|
|
@@ -2523,7 +2835,7 @@
|
|
| 2523 |
"attributes": {}
|
| 2524 |
}
|
| 2525 |
},
|
| 2526 |
-
"total_flos":
|
| 2527 |
"train_batch_size": 22,
|
| 2528 |
"trial_name": null,
|
| 2529 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.03636363636363636,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 36000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2504 |
"eval_samples_per_second": 84.308,
|
| 2505 |
"eval_steps_per_second": 21.077,
|
| 2506 |
"step": 32000
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 0.0009090909090909091,
|
| 2510 |
+
"grad_norm": 0.22038772702217102,
|
| 2511 |
+
"learning_rate": 0.0008054073172385756,
|
| 2512 |
+
"loss": 2.794765625,
|
| 2513 |
+
"step": 32100
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 0.0018181818181818182,
|
| 2517 |
+
"grad_norm": 0.15077297389507294,
|
| 2518 |
+
"learning_rate": 0.0008042738758196204,
|
| 2519 |
+
"loss": 2.7949072265625,
|
| 2520 |
+
"step": 32200
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 0.0027272727272727275,
|
| 2524 |
+
"grad_norm": 0.1514005959033966,
|
| 2525 |
+
"learning_rate": 0.0008031379457496854,
|
| 2526 |
+
"loss": 2.8156253051757814,
|
| 2527 |
+
"step": 32300
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"epoch": 0.0036363636363636364,
|
| 2531 |
+
"grad_norm": 0.13997957110404968,
|
| 2532 |
+
"learning_rate": 0.0008019995363195234,
|
| 2533 |
+
"loss": 2.8109649658203124,
|
| 2534 |
+
"step": 32400
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.004545454545454545,
|
| 2538 |
+
"grad_norm": 0.14847084879875183,
|
| 2539 |
+
"learning_rate": 0.0008008586568401662,
|
| 2540 |
+
"loss": 2.7742608642578124,
|
| 2541 |
+
"step": 32500
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 0.005454545454545455,
|
| 2545 |
+
"grad_norm": 0.13216467201709747,
|
| 2546 |
+
"learning_rate": 0.0007997153166428485,
|
| 2547 |
+
"loss": 2.7673321533203126,
|
| 2548 |
+
"step": 32600
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 0.006363636363636364,
|
| 2552 |
+
"grad_norm": 0.16374439001083374,
|
| 2553 |
+
"learning_rate": 0.0007985695250789306,
|
| 2554 |
+
"loss": 2.78884521484375,
|
| 2555 |
+
"step": 32700
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 0.007272727272727273,
|
| 2559 |
+
"grad_norm": 0.1394331306219101,
|
| 2560 |
+
"learning_rate": 0.0007974212915198225,
|
| 2561 |
+
"loss": 2.779542236328125,
|
| 2562 |
+
"step": 32800
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 0.008181818181818182,
|
| 2566 |
+
"grad_norm": 0.1565932035446167,
|
| 2567 |
+
"learning_rate": 0.0007962706253569077,
|
| 2568 |
+
"loss": 2.815880126953125,
|
| 2569 |
+
"step": 32900
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 0.00909090909090909,
|
| 2573 |
+
"grad_norm": 0.17284399271011353,
|
| 2574 |
+
"learning_rate": 0.0007951175360014656,
|
| 2575 |
+
"loss": 2.769788818359375,
|
| 2576 |
+
"step": 33000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.00909090909090909,
|
| 2580 |
+
"eval_loss": 3.1402082443237305,
|
| 2581 |
+
"eval_runtime": 7.4554,
|
| 2582 |
+
"eval_samples_per_second": 77.259,
|
| 2583 |
+
"eval_steps_per_second": 19.315,
|
| 2584 |
+
"step": 33000
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 0.01,
|
| 2588 |
+
"grad_norm": 0.15111324191093445,
|
| 2589 |
+
"learning_rate": 0.0007939620328845948,
|
| 2590 |
+
"loss": 2.7730609130859376,
|
| 2591 |
+
"step": 33100
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 0.01090909090909091,
|
| 2595 |
+
"grad_norm": 0.160688117146492,
|
| 2596 |
+
"learning_rate": 0.0007928041254571361,
|
| 2597 |
+
"loss": 2.787190246582031,
|
| 2598 |
+
"step": 33200
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 0.011818181818181818,
|
| 2602 |
+
"grad_norm": 0.17507240176200867,
|
| 2603 |
+
"learning_rate": 0.0007916438231895952,
|
| 2604 |
+
"loss": 2.766163330078125,
|
| 2605 |
+
"step": 33300
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 0.012727272727272728,
|
| 2609 |
+
"grad_norm": 0.15393611788749695,
|
| 2610 |
+
"learning_rate": 0.0007904811355720652,
|
| 2611 |
+
"loss": 2.7740924072265627,
|
| 2612 |
+
"step": 33400
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.013636363636363636,
|
| 2616 |
+
"grad_norm": 0.14618468284606934,
|
| 2617 |
+
"learning_rate": 0.0007893160721141486,
|
| 2618 |
+
"loss": 2.7595263671875,
|
| 2619 |
+
"step": 33500
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.014545454545454545,
|
| 2623 |
+
"grad_norm": 0.1701638251543045,
|
| 2624 |
+
"learning_rate": 0.0007881486423448802,
|
| 2625 |
+
"loss": 2.7771051025390623,
|
| 2626 |
+
"step": 33600
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.015454545454545455,
|
| 2630 |
+
"grad_norm": 0.15899600088596344,
|
| 2631 |
+
"learning_rate": 0.0007869788558126487,
|
| 2632 |
+
"loss": 2.754100646972656,
|
| 2633 |
+
"step": 33700
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 0.016363636363636365,
|
| 2637 |
+
"grad_norm": 0.14573192596435547,
|
| 2638 |
+
"learning_rate": 0.0007858067220851188,
|
| 2639 |
+
"loss": 2.7869033813476562,
|
| 2640 |
+
"step": 33800
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 0.017272727272727273,
|
| 2644 |
+
"grad_norm": 0.16796821355819702,
|
| 2645 |
+
"learning_rate": 0.0007846322507491528,
|
| 2646 |
+
"loss": 2.7748208618164063,
|
| 2647 |
+
"step": 33900
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 0.01818181818181818,
|
| 2651 |
+
"grad_norm": 0.1425439566373825,
|
| 2652 |
+
"learning_rate": 0.000783455451410732,
|
| 2653 |
+
"loss": 2.773130187988281,
|
| 2654 |
+
"step": 34000
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.01818181818181818,
|
| 2658 |
+
"eval_loss": 3.13128399848938,
|
| 2659 |
+
"eval_runtime": 7.4414,
|
| 2660 |
+
"eval_samples_per_second": 77.405,
|
| 2661 |
+
"eval_steps_per_second": 19.351,
|
| 2662 |
+
"step": 34000
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.019090909090909092,
|
| 2666 |
+
"grad_norm": 0.15474802255630493,
|
| 2667 |
+
"learning_rate": 0.000782276333694879,
|
| 2668 |
+
"loss": 2.7699960327148436,
|
| 2669 |
+
"step": 34100
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.02,
|
| 2673 |
+
"grad_norm": 0.1559676229953766,
|
| 2674 |
+
"learning_rate": 0.0007810949072455778,
|
| 2675 |
+
"loss": 2.7731719970703126,
|
| 2676 |
+
"step": 34200
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.02090909090909091,
|
| 2680 |
+
"grad_norm": 0.1522807478904724,
|
| 2681 |
+
"learning_rate": 0.0007799111817256959,
|
| 2682 |
+
"loss": 2.7761361694335935,
|
| 2683 |
+
"step": 34300
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.02181818181818182,
|
| 2687 |
+
"grad_norm": 0.15091344714164734,
|
| 2688 |
+
"learning_rate": 0.0007787251668169043,
|
| 2689 |
+
"loss": 2.7527685546875,
|
| 2690 |
+
"step": 34400
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.022727272727272728,
|
| 2694 |
+
"grad_norm": 0.15074443817138672,
|
| 2695 |
+
"learning_rate": 0.0007775368722195997,
|
| 2696 |
+
"loss": 2.7675704956054688,
|
| 2697 |
+
"step": 34500
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.023636363636363636,
|
| 2701 |
+
"grad_norm": 0.1461259126663208,
|
| 2702 |
+
"learning_rate": 0.0007763463076528237,
|
| 2703 |
+
"loss": 2.76167236328125,
|
| 2704 |
+
"step": 34600
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.024545454545454544,
|
| 2708 |
+
"grad_norm": 0.15030233561992645,
|
| 2709 |
+
"learning_rate": 0.0007751534828541842,
|
| 2710 |
+
"loss": 2.7275946044921877,
|
| 2711 |
+
"step": 34700
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.025454545454545455,
|
| 2715 |
+
"grad_norm": 0.14424681663513184,
|
| 2716 |
+
"learning_rate": 0.0007739584075797753,
|
| 2717 |
+
"loss": 2.736708679199219,
|
| 2718 |
+
"step": 34800
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.026363636363636363,
|
| 2722 |
+
"grad_norm": 0.15576180815696716,
|
| 2723 |
+
"learning_rate": 0.0007727610916040981,
|
| 2724 |
+
"loss": 2.7289297485351565,
|
| 2725 |
+
"step": 34900
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.02727272727272727,
|
| 2729 |
+
"grad_norm": 0.1324995905160904,
|
| 2730 |
+
"learning_rate": 0.0007715615447199798,
|
| 2731 |
+
"loss": 2.7693435668945314,
|
| 2732 |
+
"step": 35000
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.02727272727272727,
|
| 2736 |
+
"eval_loss": 3.1262025833129883,
|
| 2737 |
+
"eval_runtime": 7.4365,
|
| 2738 |
+
"eval_samples_per_second": 77.456,
|
| 2739 |
+
"eval_steps_per_second": 19.364,
|
| 2740 |
+
"step": 35000
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.028181818181818183,
|
| 2744 |
+
"grad_norm": 0.1613311767578125,
|
| 2745 |
+
"learning_rate": 0.0007703597767384945,
|
| 2746 |
+
"loss": 2.7539468383789063,
|
| 2747 |
+
"step": 35100
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.02909090909090909,
|
| 2751 |
+
"grad_norm": 0.16793298721313477,
|
| 2752 |
+
"learning_rate": 0.0007691557974888825,
|
| 2753 |
+
"loss": 2.7785479736328127,
|
| 2754 |
+
"step": 35200
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.03,
|
| 2758 |
+
"grad_norm": 0.14937831461429596,
|
| 2759 |
+
"learning_rate": 0.0007679496168184705,
|
| 2760 |
+
"loss": 2.7587347412109375,
|
| 2761 |
+
"step": 35300
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.03090909090909091,
|
| 2765 |
+
"grad_norm": 0.1619419902563095,
|
| 2766 |
+
"learning_rate": 0.0007667412445925898,
|
| 2767 |
+
"loss": 2.7732388305664064,
|
| 2768 |
+
"step": 35400
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.031818181818181815,
|
| 2772 |
+
"grad_norm": 0.15758360922336578,
|
| 2773 |
+
"learning_rate": 0.000765530690694497,
|
| 2774 |
+
"loss": 2.74038818359375,
|
| 2775 |
+
"step": 35500
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.03272727272727273,
|
| 2779 |
+
"grad_norm": 0.1523827463388443,
|
| 2780 |
+
"learning_rate": 0.000764317965025292,
|
| 2781 |
+
"loss": 2.7354312133789063,
|
| 2782 |
+
"step": 35600
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.03363636363636364,
|
| 2786 |
+
"grad_norm": 0.1685842126607895,
|
| 2787 |
+
"learning_rate": 0.0007631030775038383,
|
| 2788 |
+
"loss": 2.7525250244140627,
|
| 2789 |
+
"step": 35700
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.034545454545454546,
|
| 2793 |
+
"grad_norm": 0.1396898627281189,
|
| 2794 |
+
"learning_rate": 0.0007618860380666808,
|
| 2795 |
+
"loss": 2.737476501464844,
|
| 2796 |
+
"step": 35800
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.035454545454545454,
|
| 2800 |
+
"grad_norm": 0.15296360850334167,
|
| 2801 |
+
"learning_rate": 0.0007606668566679644,
|
| 2802 |
+
"loss": 2.747691955566406,
|
| 2803 |
+
"step": 35900
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.03636363636363636,
|
| 2807 |
+
"grad_norm": 0.1561899036169052,
|
| 2808 |
+
"learning_rate": 0.0007594455432793539,
|
| 2809 |
+
"loss": 2.7320767211914063,
|
| 2810 |
+
"step": 36000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.03636363636363636,
|
| 2814 |
+
"eval_loss": 3.1245434284210205,
|
| 2815 |
+
"eval_runtime": 7.4489,
|
| 2816 |
+
"eval_samples_per_second": 77.327,
|
| 2817 |
+
"eval_steps_per_second": 19.332,
|
| 2818 |
+
"step": 36000
|
| 2819 |
}
|
| 2820 |
],
|
| 2821 |
"logging_steps": 100,
|
|
|
|
| 2835 |
"attributes": {}
|
| 2836 |
}
|
| 2837 |
},
|
| 2838 |
+
"total_flos": 8.96924915859456e+17,
|
| 2839 |
"train_batch_size": 22,
|
| 2840 |
"trial_name": null,
|
| 2841 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5201
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef8c80f5d40636555b8c09ec97785c8964e446b8d757c55eb76e5b7454841939
|
| 3 |
size 5201
|