End of training
Browse files
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_cer": 0.1969102547256584,
|
4 |
"eval_loss": 0.9162458181381226,
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 481,
|
7 |
-
"eval_samples_per_second": 10.
|
8 |
-
"eval_steps_per_second": 1.
|
9 |
"eval_wer": 0.5156036834924966,
|
10 |
-
"train_loss": 0.
|
11 |
-
"train_runtime":
|
12 |
"train_samples": 2528,
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second":
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 56.96,
|
3 |
"eval_cer": 0.1969102547256584,
|
4 |
"eval_loss": 0.9162458181381226,
|
5 |
+
"eval_runtime": 45.5404,
|
6 |
"eval_samples": 481,
|
7 |
+
"eval_samples_per_second": 10.562,
|
8 |
+
"eval_steps_per_second": 1.339,
|
9 |
"eval_wer": 0.5156036834924966,
|
10 |
+
"train_loss": 0.06285779211256239,
|
11 |
+
"train_runtime": 2146.9018,
|
12 |
"train_samples": 2528,
|
13 |
+
"train_samples_per_second": 67.073,
|
14 |
+
"train_steps_per_second": 2.096
|
15 |
}
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_cer": 0.1969102547256584,
|
4 |
"eval_loss": 0.9162458181381226,
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 481,
|
7 |
-
"eval_samples_per_second": 10.
|
8 |
-
"eval_steps_per_second": 1.
|
9 |
"eval_wer": 0.5156036834924966
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 56.96,
|
3 |
"eval_cer": 0.1969102547256584,
|
4 |
"eval_loss": 0.9162458181381226,
|
5 |
+
"eval_runtime": 45.5404,
|
6 |
"eval_samples": 481,
|
7 |
+
"eval_samples_per_second": 10.562,
|
8 |
+
"eval_steps_per_second": 1.339,
|
9 |
"eval_wer": 0.5156036834924966
|
10 |
}
|
runs/Dec16_14-39-42_129-146-104-29/events.out.tfevents.1671204006.129-146-104-29.129288.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80d4d15418295c572aa4591c39561da14f6b9f84af7cb628829d3e04efcf370f
|
3 |
+
size 405
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 2528,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 56.96,
|
3 |
+
"train_loss": 0.06285779211256239,
|
4 |
+
"train_runtime": 2146.9018,
|
5 |
"train_samples": 2528,
|
6 |
+
"train_samples_per_second": 67.073,
|
7 |
+
"train_steps_per_second": 2.096
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.9162458181381226,
|
3 |
"best_model_checkpoint": "./checkpoint-4000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2488,18 +2488,328 @@
|
|
2488 |
"step": 4000
|
2489 |
},
|
2490 |
{
|
2491 |
-
"epoch": 50.
|
2492 |
-
"
|
2493 |
-
"
|
2494 |
-
"
|
2495 |
-
|
2496 |
-
|
2497 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2498 |
}
|
2499 |
],
|
2500 |
-
"max_steps":
|
2501 |
-
"num_train_epochs":
|
2502 |
-
"total_flos":
|
2503 |
"trial_name": null,
|
2504 |
"trial_params": null
|
2505 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.9162458181381226,
|
3 |
"best_model_checkpoint": "./checkpoint-4000",
|
4 |
+
"epoch": 56.962025316455694,
|
5 |
+
"global_step": 4500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2488 |
"step": 4000
|
2489 |
},
|
2490 |
{
|
2491 |
+
"epoch": 50.76,
|
2492 |
+
"learning_rate": 1.4729999999999998e-05,
|
2493 |
+
"loss": 0.543,
|
2494 |
+
"step": 4010
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 50.89,
|
2498 |
+
"learning_rate": 1.4429999999999997e-05,
|
2499 |
+
"loss": 0.6044,
|
2500 |
+
"step": 4020
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 51.01,
|
2504 |
+
"learning_rate": 1.413e-05,
|
2505 |
+
"loss": 0.5749,
|
2506 |
+
"step": 4030
|
2507 |
+
},
|
2508 |
+
{
|
2509 |
+
"epoch": 51.14,
|
2510 |
+
"learning_rate": 1.383e-05,
|
2511 |
+
"loss": 0.6171,
|
2512 |
+
"step": 4040
|
2513 |
+
},
|
2514 |
+
{
|
2515 |
+
"epoch": 51.27,
|
2516 |
+
"learning_rate": 1.353e-05,
|
2517 |
+
"loss": 0.5767,
|
2518 |
+
"step": 4050
|
2519 |
+
},
|
2520 |
+
{
|
2521 |
+
"epoch": 51.39,
|
2522 |
+
"learning_rate": 1.3229999999999999e-05,
|
2523 |
+
"loss": 0.5749,
|
2524 |
+
"step": 4060
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 51.52,
|
2528 |
+
"learning_rate": 1.2929999999999998e-05,
|
2529 |
+
"loss": 0.565,
|
2530 |
+
"step": 4070
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 51.65,
|
2534 |
+
"learning_rate": 1.2629999999999998e-05,
|
2535 |
+
"loss": 0.5907,
|
2536 |
+
"step": 4080
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 51.77,
|
2540 |
+
"learning_rate": 1.2329999999999999e-05,
|
2541 |
+
"loss": 0.575,
|
2542 |
+
"step": 4090
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 51.9,
|
2546 |
+
"learning_rate": 1.2029999999999998e-05,
|
2547 |
+
"loss": 0.5692,
|
2548 |
+
"step": 4100
|
2549 |
+
},
|
2550 |
+
{
|
2551 |
+
"epoch": 52.03,
|
2552 |
+
"learning_rate": 1.173e-05,
|
2553 |
+
"loss": 0.5219,
|
2554 |
+
"step": 4110
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 52.15,
|
2558 |
+
"learning_rate": 1.1429999999999999e-05,
|
2559 |
+
"loss": 0.5535,
|
2560 |
+
"step": 4120
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 52.28,
|
2564 |
+
"learning_rate": 1.113e-05,
|
2565 |
+
"loss": 0.5519,
|
2566 |
+
"step": 4130
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"epoch": 52.41,
|
2570 |
+
"learning_rate": 1.083e-05,
|
2571 |
+
"loss": 0.5826,
|
2572 |
+
"step": 4140
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 52.53,
|
2576 |
+
"learning_rate": 1.0529999999999999e-05,
|
2577 |
+
"loss": 0.5472,
|
2578 |
+
"step": 4150
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 52.66,
|
2582 |
+
"learning_rate": 1.0229999999999999e-05,
|
2583 |
+
"loss": 0.5603,
|
2584 |
+
"step": 4160
|
2585 |
+
},
|
2586 |
+
{
|
2587 |
+
"epoch": 52.78,
|
2588 |
+
"learning_rate": 9.929999999999998e-06,
|
2589 |
+
"loss": 0.589,
|
2590 |
+
"step": 4170
|
2591 |
+
},
|
2592 |
+
{
|
2593 |
+
"epoch": 52.91,
|
2594 |
+
"learning_rate": 9.629999999999998e-06,
|
2595 |
+
"loss": 0.6005,
|
2596 |
+
"step": 4180
|
2597 |
+
},
|
2598 |
+
{
|
2599 |
+
"epoch": 53.04,
|
2600 |
+
"learning_rate": 9.329999999999999e-06,
|
2601 |
+
"loss": 0.5844,
|
2602 |
+
"step": 4190
|
2603 |
+
},
|
2604 |
+
{
|
2605 |
+
"epoch": 53.16,
|
2606 |
+
"learning_rate": 9.029999999999998e-06,
|
2607 |
+
"loss": 0.5779,
|
2608 |
+
"step": 4200
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 53.29,
|
2612 |
+
"learning_rate": 8.73e-06,
|
2613 |
+
"loss": 0.5611,
|
2614 |
+
"step": 4210
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 53.42,
|
2618 |
+
"learning_rate": 8.429999999999999e-06,
|
2619 |
+
"loss": 0.5859,
|
2620 |
+
"step": 4220
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 53.54,
|
2624 |
+
"learning_rate": 8.129999999999998e-06,
|
2625 |
+
"loss": 0.5906,
|
2626 |
+
"step": 4230
|
2627 |
+
},
|
2628 |
+
{
|
2629 |
+
"epoch": 53.67,
|
2630 |
+
"learning_rate": 7.83e-06,
|
2631 |
+
"loss": 0.5522,
|
2632 |
+
"step": 4240
|
2633 |
+
},
|
2634 |
+
{
|
2635 |
+
"epoch": 53.8,
|
2636 |
+
"learning_rate": 7.56e-06,
|
2637 |
+
"loss": 0.5762,
|
2638 |
+
"step": 4250
|
2639 |
+
},
|
2640 |
+
{
|
2641 |
+
"epoch": 53.92,
|
2642 |
+
"learning_rate": 7.259999999999999e-06,
|
2643 |
+
"loss": 0.5498,
|
2644 |
+
"step": 4260
|
2645 |
+
},
|
2646 |
+
{
|
2647 |
+
"epoch": 54.05,
|
2648 |
+
"learning_rate": 6.959999999999999e-06,
|
2649 |
+
"loss": 0.5752,
|
2650 |
+
"step": 4270
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 54.18,
|
2654 |
+
"learning_rate": 6.66e-06,
|
2655 |
+
"loss": 0.5428,
|
2656 |
+
"step": 4280
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 54.3,
|
2660 |
+
"learning_rate": 6.359999999999999e-06,
|
2661 |
+
"loss": 0.5515,
|
2662 |
+
"step": 4290
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 54.43,
|
2666 |
+
"learning_rate": 6.06e-06,
|
2667 |
+
"loss": 0.5662,
|
2668 |
+
"step": 4300
|
2669 |
+
},
|
2670 |
+
{
|
2671 |
+
"epoch": 54.56,
|
2672 |
+
"learning_rate": 5.759999999999999e-06,
|
2673 |
+
"loss": 0.5916,
|
2674 |
+
"step": 4310
|
2675 |
+
},
|
2676 |
+
{
|
2677 |
+
"epoch": 54.68,
|
2678 |
+
"learning_rate": 5.459999999999999e-06,
|
2679 |
+
"loss": 0.537,
|
2680 |
+
"step": 4320
|
2681 |
+
},
|
2682 |
+
{
|
2683 |
+
"epoch": 54.81,
|
2684 |
+
"learning_rate": 5.16e-06,
|
2685 |
+
"loss": 0.5744,
|
2686 |
+
"step": 4330
|
2687 |
+
},
|
2688 |
+
{
|
2689 |
+
"epoch": 54.94,
|
2690 |
+
"learning_rate": 4.859999999999999e-06,
|
2691 |
+
"loss": 0.5606,
|
2692 |
+
"step": 4340
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 55.06,
|
2696 |
+
"learning_rate": 4.5599999999999995e-06,
|
2697 |
+
"loss": 0.5855,
|
2698 |
+
"step": 4350
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 55.19,
|
2702 |
+
"learning_rate": 4.26e-06,
|
2703 |
+
"loss": 0.5486,
|
2704 |
+
"step": 4360
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 55.32,
|
2708 |
+
"learning_rate": 3.959999999999999e-06,
|
2709 |
+
"loss": 0.5644,
|
2710 |
+
"step": 4370
|
2711 |
+
},
|
2712 |
+
{
|
2713 |
+
"epoch": 55.44,
|
2714 |
+
"learning_rate": 3.66e-06,
|
2715 |
+
"loss": 0.5525,
|
2716 |
+
"step": 4380
|
2717 |
+
},
|
2718 |
+
{
|
2719 |
+
"epoch": 55.57,
|
2720 |
+
"learning_rate": 3.3599999999999996e-06,
|
2721 |
+
"loss": 0.6088,
|
2722 |
+
"step": 4390
|
2723 |
+
},
|
2724 |
+
{
|
2725 |
+
"epoch": 55.7,
|
2726 |
+
"learning_rate": 3.06e-06,
|
2727 |
+
"loss": 0.5344,
|
2728 |
+
"step": 4400
|
2729 |
+
},
|
2730 |
+
{
|
2731 |
+
"epoch": 55.82,
|
2732 |
+
"learning_rate": 2.76e-06,
|
2733 |
+
"loss": 0.5379,
|
2734 |
+
"step": 4410
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 55.95,
|
2738 |
+
"learning_rate": 2.46e-06,
|
2739 |
+
"loss": 0.5204,
|
2740 |
+
"step": 4420
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 56.08,
|
2744 |
+
"learning_rate": 2.1599999999999996e-06,
|
2745 |
+
"loss": 0.5754,
|
2746 |
+
"step": 4430
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 56.2,
|
2750 |
+
"learning_rate": 1.8599999999999998e-06,
|
2751 |
+
"loss": 0.5507,
|
2752 |
+
"step": 4440
|
2753 |
+
},
|
2754 |
+
{
|
2755 |
+
"epoch": 56.33,
|
2756 |
+
"learning_rate": 1.5599999999999999e-06,
|
2757 |
+
"loss": 0.5592,
|
2758 |
+
"step": 4450
|
2759 |
+
},
|
2760 |
+
{
|
2761 |
+
"epoch": 56.46,
|
2762 |
+
"learning_rate": 1.2599999999999998e-06,
|
2763 |
+
"loss": 0.5396,
|
2764 |
+
"step": 4460
|
2765 |
+
},
|
2766 |
+
{
|
2767 |
+
"epoch": 56.58,
|
2768 |
+
"learning_rate": 9.6e-07,
|
2769 |
+
"loss": 0.579,
|
2770 |
+
"step": 4470
|
2771 |
+
},
|
2772 |
+
{
|
2773 |
+
"epoch": 56.71,
|
2774 |
+
"learning_rate": 6.6e-07,
|
2775 |
+
"loss": 0.545,
|
2776 |
+
"step": 4480
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 56.84,
|
2780 |
+
"learning_rate": 3.5999999999999994e-07,
|
2781 |
+
"loss": 0.5919,
|
2782 |
+
"step": 4490
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 56.96,
|
2786 |
+
"learning_rate": 6e-08,
|
2787 |
+
"loss": 0.5174,
|
2788 |
+
"step": 4500
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 56.96,
|
2792 |
+
"eval_cer": 0.19719182325005163,
|
2793 |
+
"eval_loss": 0.9287102818489075,
|
2794 |
+
"eval_runtime": 44.3461,
|
2795 |
+
"eval_samples_per_second": 10.847,
|
2796 |
+
"eval_steps_per_second": 1.376,
|
2797 |
+
"eval_wer": 0.5139836289222374,
|
2798 |
+
"step": 4500
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 56.96,
|
2802 |
+
"step": 4500,
|
2803 |
+
"total_flos": 5.1775250042658095e+19,
|
2804 |
+
"train_loss": 0.06285779211256239,
|
2805 |
+
"train_runtime": 2146.9018,
|
2806 |
+
"train_samples_per_second": 67.073,
|
2807 |
+
"train_steps_per_second": 2.096
|
2808 |
}
|
2809 |
],
|
2810 |
+
"max_steps": 4500,
|
2811 |
+
"num_train_epochs": 57,
|
2812 |
+
"total_flos": 5.1775250042658095e+19,
|
2813 |
"trial_name": null,
|
2814 |
"trial_params": null
|
2815 |
}
|