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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e271f094dc095c867358bb6157221396d158922b11c316900c8d79c1e09d0f6
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55e5fe87fe81d7cb83f3ed0295308626dfebead62fc3b096c5571405aeeab756
|
| 3 |
size 1082379659
|
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 sha256:87b07b911601d04abcbcc91c12340e18730f0dbec6517e92e9000c51517972c9
|
| 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:e9eea36234165600a5923f1ab0a2e7e9de4f1d318a06ca4c532030966bdcc676
|
| 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": 37.727,
|
| 2505 |
"eval_steps_per_second": 9.432,
|
| 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": 0.4675324675324675,
|
| 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": 37.727,
|
| 2505 |
"eval_steps_per_second": 9.432,
|
| 2506 |
"step": 32000
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 0.41688311688311686,
|
| 2510 |
+
"grad_norm": 0.22132746875286102,
|
| 2511 |
+
"learning_rate": 0.0008126410186383836,
|
| 2512 |
+
"loss": 2.8195,
|
| 2513 |
+
"step": 32100
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"epoch": 0.41818181818181815,
|
| 2517 |
+
"grad_norm": 0.21235358715057373,
|
| 2518 |
+
"learning_rate": 0.0008115145734448622,
|
| 2519 |
+
"loss": 2.7824,
|
| 2520 |
+
"step": 32200
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 0.41948051948051945,
|
| 2524 |
+
"grad_norm": 0.21031178534030914,
|
| 2525 |
+
"learning_rate": 0.0008103855381107122,
|
| 2526 |
+
"loss": 2.8135,
|
| 2527 |
+
"step": 32300
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"epoch": 0.42077922077922075,
|
| 2531 |
+
"grad_norm": 0.2186926305294037,
|
| 2532 |
+
"learning_rate": 0.0008092539220234894,
|
| 2533 |
+
"loss": 2.8166,
|
| 2534 |
+
"step": 32400
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 0.42207792207792205,
|
| 2538 |
+
"grad_norm": 0.20855864882469177,
|
| 2539 |
+
"learning_rate": 0.0008081197345922069,
|
| 2540 |
+
"loss": 2.8595,
|
| 2541 |
+
"step": 32500
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 0.42337662337662335,
|
| 2545 |
+
"grad_norm": 0.20601770281791687,
|
| 2546 |
+
"learning_rate": 0.0008069829852472583,
|
| 2547 |
+
"loss": 2.8201,
|
| 2548 |
+
"step": 32600
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 0.42467532467532465,
|
| 2552 |
+
"grad_norm": 0.22806823253631592,
|
| 2553 |
+
"learning_rate": 0.000805843683440338,
|
| 2554 |
+
"loss": 2.8265,
|
| 2555 |
+
"step": 32700
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 0.42597402597402595,
|
| 2559 |
+
"grad_norm": 0.21018485724925995,
|
| 2560 |
+
"learning_rate": 0.0008047018386443638,
|
| 2561 |
+
"loss": 2.8403,
|
| 2562 |
+
"step": 32800
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 0.42727272727272725,
|
| 2566 |
+
"grad_norm": 0.218631774187088,
|
| 2567 |
+
"learning_rate": 0.0008035574603533975,
|
| 2568 |
+
"loss": 2.8052,
|
| 2569 |
+
"step": 32900
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 0.42857142857142855,
|
| 2573 |
+
"grad_norm": 0.20622466504573822,
|
| 2574 |
+
"learning_rate": 0.000802410558082566,
|
| 2575 |
+
"loss": 2.824,
|
| 2576 |
+
"step": 33000
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 0.42857142857142855,
|
| 2580 |
+
"eval_loss": 3.178421974182129,
|
| 2581 |
+
"eval_runtime": 15.6887,
|
| 2582 |
+
"eval_samples_per_second": 36.714,
|
| 2583 |
+
"eval_steps_per_second": 9.179,
|
| 2584 |
+
"step": 33000
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 0.42987012987012985,
|
| 2588 |
+
"grad_norm": 0.24304358661174774,
|
| 2589 |
+
"learning_rate": 0.0008012611413679824,
|
| 2590 |
+
"loss": 2.8068,
|
| 2591 |
+
"step": 33100
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 0.43116883116883115,
|
| 2595 |
+
"grad_norm": 0.20239757001399994,
|
| 2596 |
+
"learning_rate": 0.0008001092197666661,
|
| 2597 |
+
"loss": 2.7936,
|
| 2598 |
+
"step": 33200
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 0.43246753246753245,
|
| 2602 |
+
"grad_norm": 0.21365991234779358,
|
| 2603 |
+
"learning_rate": 0.0007989548028564646,
|
| 2604 |
+
"loss": 2.8053,
|
| 2605 |
+
"step": 33300
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 0.43376623376623374,
|
| 2609 |
+
"grad_norm": 0.19812121987342834,
|
| 2610 |
+
"learning_rate": 0.0007977979002359723,
|
| 2611 |
+
"loss": 2.8083,
|
| 2612 |
+
"step": 33400
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 0.43506493506493504,
|
| 2616 |
+
"grad_norm": 0.20705953240394592,
|
| 2617 |
+
"learning_rate": 0.0007966385215244518,
|
| 2618 |
+
"loss": 2.7882,
|
| 2619 |
+
"step": 33500
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.43636363636363634,
|
| 2623 |
+
"grad_norm": 0.23277799785137177,
|
| 2624 |
+
"learning_rate": 0.0007954766763617538,
|
| 2625 |
+
"loss": 2.8241,
|
| 2626 |
+
"step": 33600
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 0.43766233766233764,
|
| 2630 |
+
"grad_norm": 0.2175544649362564,
|
| 2631 |
+
"learning_rate": 0.0007943123744082363,
|
| 2632 |
+
"loss": 2.816,
|
| 2633 |
+
"step": 33700
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 0.43896103896103894,
|
| 2637 |
+
"grad_norm": 0.21744564175605774,
|
| 2638 |
+
"learning_rate": 0.000793145625344685,
|
| 2639 |
+
"loss": 2.7947,
|
| 2640 |
+
"step": 33800
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 0.44025974025974024,
|
| 2644 |
+
"grad_norm": 0.2085115909576416,
|
| 2645 |
+
"learning_rate": 0.0007919764388722322,
|
| 2646 |
+
"loss": 2.8016,
|
| 2647 |
+
"step": 33900
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 0.44155844155844154,
|
| 2651 |
+
"grad_norm": 0.21085582673549652,
|
| 2652 |
+
"learning_rate": 0.0007908048247122768,
|
| 2653 |
+
"loss": 2.7845,
|
| 2654 |
+
"step": 34000
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 0.44155844155844154,
|
| 2658 |
+
"eval_loss": 3.1732594966888428,
|
| 2659 |
+
"eval_runtime": 14.9965,
|
| 2660 |
+
"eval_samples_per_second": 38.409,
|
| 2661 |
+
"eval_steps_per_second": 9.602,
|
| 2662 |
+
"step": 34000
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.44285714285714284,
|
| 2666 |
+
"grad_norm": 0.1986636519432068,
|
| 2667 |
+
"learning_rate": 0.0007896307926064029,
|
| 2668 |
+
"loss": 2.8039,
|
| 2669 |
+
"step": 34100
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.44415584415584414,
|
| 2673 |
+
"grad_norm": 0.2274903804063797,
|
| 2674 |
+
"learning_rate": 0.0007884543523162991,
|
| 2675 |
+
"loss": 2.7982,
|
| 2676 |
+
"step": 34200
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.44545454545454544,
|
| 2680 |
+
"grad_norm": 0.23180291056632996,
|
| 2681 |
+
"learning_rate": 0.0007872755136236774,
|
| 2682 |
+
"loss": 2.8223,
|
| 2683 |
+
"step": 34300
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.44675324675324674,
|
| 2687 |
+
"grad_norm": 0.21269173920154572,
|
| 2688 |
+
"learning_rate": 0.0007860942863301914,
|
| 2689 |
+
"loss": 2.8141,
|
| 2690 |
+
"step": 34400
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.44805194805194803,
|
| 2694 |
+
"grad_norm": 0.20867326855659485,
|
| 2695 |
+
"learning_rate": 0.0007849106802573553,
|
| 2696 |
+
"loss": 2.7805,
|
| 2697 |
+
"step": 34500
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.44935064935064933,
|
| 2701 |
+
"grad_norm": 1.6756339073181152,
|
| 2702 |
+
"learning_rate": 0.0007837247052464621,
|
| 2703 |
+
"loss": 2.7879,
|
| 2704 |
+
"step": 34600
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.45064935064935063,
|
| 2708 |
+
"grad_norm": 0.24874623119831085,
|
| 2709 |
+
"learning_rate": 0.0007825363711585016,
|
| 2710 |
+
"loss": 2.8281,
|
| 2711 |
+
"step": 34700
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.45194805194805193,
|
| 2715 |
+
"grad_norm": 0.19419661164283752,
|
| 2716 |
+
"learning_rate": 0.0007813456878740789,
|
| 2717 |
+
"loss": 2.7984,
|
| 2718 |
+
"step": 34800
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.45324675324675323,
|
| 2722 |
+
"grad_norm": 0.21280324459075928,
|
| 2723 |
+
"learning_rate": 0.0007801526652933313,
|
| 2724 |
+
"loss": 2.834,
|
| 2725 |
+
"step": 34900
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.45454545454545453,
|
| 2729 |
+
"grad_norm": 0.20888017117977142,
|
| 2730 |
+
"learning_rate": 0.0007789573133358471,
|
| 2731 |
+
"loss": 2.831,
|
| 2732 |
+
"step": 35000
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.45454545454545453,
|
| 2736 |
+
"eval_loss": 3.1828813552856445,
|
| 2737 |
+
"eval_runtime": 14.929,
|
| 2738 |
+
"eval_samples_per_second": 38.583,
|
| 2739 |
+
"eval_steps_per_second": 9.646,
|
| 2740 |
+
"step": 35000
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.45584415584415583,
|
| 2744 |
+
"grad_norm": 0.21340541541576385,
|
| 2745 |
+
"learning_rate": 0.0007777596419405823,
|
| 2746 |
+
"loss": 2.8065,
|
| 2747 |
+
"step": 35100
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.45714285714285713,
|
| 2751 |
+
"grad_norm": 0.20886409282684326,
|
| 2752 |
+
"learning_rate": 0.0007765596610657783,
|
| 2753 |
+
"loss": 2.8423,
|
| 2754 |
+
"step": 35200
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.4584415584415584,
|
| 2758 |
+
"grad_norm": 0.21619443595409393,
|
| 2759 |
+
"learning_rate": 0.0007753573806888795,
|
| 2760 |
+
"loss": 2.786,
|
| 2761 |
+
"step": 35300
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.4597402597402597,
|
| 2765 |
+
"grad_norm": 0.21694345772266388,
|
| 2766 |
+
"learning_rate": 0.0007741528108064491,
|
| 2767 |
+
"loss": 2.7822,
|
| 2768 |
+
"step": 35400
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.461038961038961,
|
| 2772 |
+
"grad_norm": 0.21181565523147583,
|
| 2773 |
+
"learning_rate": 0.0007729459614340872,
|
| 2774 |
+
"loss": 2.7599,
|
| 2775 |
+
"step": 35500
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.4623376623376623,
|
| 2779 |
+
"grad_norm": 0.22892408072948456,
|
| 2780 |
+
"learning_rate": 0.0007717368426063475,
|
| 2781 |
+
"loss": 2.7934,
|
| 2782 |
+
"step": 35600
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.4636363636363636,
|
| 2786 |
+
"grad_norm": 0.21864919364452362,
|
| 2787 |
+
"learning_rate": 0.0007705254643766527,
|
| 2788 |
+
"loss": 2.8059,
|
| 2789 |
+
"step": 35700
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.4649350649350649,
|
| 2793 |
+
"grad_norm": 0.2145598828792572,
|
| 2794 |
+
"learning_rate": 0.000769311836817212,
|
| 2795 |
+
"loss": 2.8056,
|
| 2796 |
+
"step": 35800
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.4662337662337662,
|
| 2800 |
+
"grad_norm": 0.21081195771694183,
|
| 2801 |
+
"learning_rate": 0.0007680959700189375,
|
| 2802 |
+
"loss": 2.7969,
|
| 2803 |
+
"step": 35900
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.4675324675324675,
|
| 2807 |
+
"grad_norm": 0.22019855678081512,
|
| 2808 |
+
"learning_rate": 0.0007668778740913591,
|
| 2809 |
+
"loss": 2.7923,
|
| 2810 |
+
"step": 36000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.4675324675324675,
|
| 2814 |
+
"eval_loss": 3.161719560623169,
|
| 2815 |
+
"eval_runtime": 15.4038,
|
| 2816 |
+
"eval_samples_per_second": 37.393,
|
| 2817 |
+
"eval_steps_per_second": 9.348,
|
| 2818 |
+
"step": 36000
|
| 2819 |
}
|
| 2820 |
],
|
| 2821 |
"logging_steps": 100,
|
|
|
|
| 2835 |
"attributes": {}
|
| 2836 |
}
|
| 2837 |
},
|
| 2838 |
+
"total_flos": 1.07169529724928e+18,
|
| 2839 |
"train_batch_size": 22,
|
| 2840 |
"trial_name": null,
|
| 2841 |
"trial_params": null
|