Uploaded checkpoint-20000
Browse files- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +378 -3
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4986380064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52ae8fd2899cae9fbf1de2288673a19564009a6254b0b592383efcc519ad621a
|
| 3 |
size 4986380064
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 399532808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fef9985c248615a2bb23a47f171d94be90d8c93afd5aa990b1587b71e71171c6
|
| 3 |
size 399532808
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2699039674
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6c0438b7ed3e4c55f24fa3150fa982da8011360f12c7b707448e8db4ad3f902
|
| 3 |
size 2699039674
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97b0f27722247239511c0d33808326948f3078297be0bebdd0214846f3609f1e
|
| 3 |
size 14244
|
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 sha256:29c7a79b53a589de48d3b7a21df9c0d024be4dea79f68869f72fdc01ae3b212a
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2632,6 +2632,381 @@
|
|
| 2632 |
"eval_samples_per_second": 10.168,
|
| 2633 |
"eval_steps_per_second": 10.168,
|
| 2634 |
"step": 17500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2635 |
}
|
| 2636 |
],
|
| 2637 |
"logging_steps": 100,
|
|
@@ -2639,7 +3014,7 @@
|
|
| 2639 |
"num_input_tokens_seen": 0,
|
| 2640 |
"num_train_epochs": 1,
|
| 2641 |
"save_steps": 2500,
|
| 2642 |
-
"total_flos":
|
| 2643 |
"train_batch_size": 1,
|
| 2644 |
"trial_name": null,
|
| 2645 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 20000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2632 |
"eval_samples_per_second": 10.168,
|
| 2633 |
"eval_steps_per_second": 10.168,
|
| 2634 |
"step": 17500
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.44,
|
| 2638 |
+
"grad_norm": 4.079812526702881,
|
| 2639 |
+
"learning_rate": 2.461538461538462e-06,
|
| 2640 |
+
"loss": 0.6369,
|
| 2641 |
+
"step": 17600
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.44,
|
| 2645 |
+
"eval_loss": 0.6634325385093689,
|
| 2646 |
+
"eval_runtime": 98.3802,
|
| 2647 |
+
"eval_samples_per_second": 10.165,
|
| 2648 |
+
"eval_steps_per_second": 10.165,
|
| 2649 |
+
"step": 17600
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.44,
|
| 2653 |
+
"grad_norm": 3.0387985706329346,
|
| 2654 |
+
"learning_rate": 2.358974358974359e-06,
|
| 2655 |
+
"loss": 0.6244,
|
| 2656 |
+
"step": 17700
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.44,
|
| 2660 |
+
"eval_loss": 0.658197283744812,
|
| 2661 |
+
"eval_runtime": 98.3504,
|
| 2662 |
+
"eval_samples_per_second": 10.168,
|
| 2663 |
+
"eval_steps_per_second": 10.168,
|
| 2664 |
+
"step": 17700
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 0.45,
|
| 2668 |
+
"grad_norm": 4.429220199584961,
|
| 2669 |
+
"learning_rate": 2.2564102564102566e-06,
|
| 2670 |
+
"loss": 0.663,
|
| 2671 |
+
"step": 17800
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 0.45,
|
| 2675 |
+
"eval_loss": 0.663162350654602,
|
| 2676 |
+
"eval_runtime": 98.3612,
|
| 2677 |
+
"eval_samples_per_second": 10.167,
|
| 2678 |
+
"eval_steps_per_second": 10.167,
|
| 2679 |
+
"step": 17800
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 0.45,
|
| 2683 |
+
"grad_norm": 7.286205291748047,
|
| 2684 |
+
"learning_rate": 2.153846153846154e-06,
|
| 2685 |
+
"loss": 0.6692,
|
| 2686 |
+
"step": 17900
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 0.45,
|
| 2690 |
+
"eval_loss": 0.6493304371833801,
|
| 2691 |
+
"eval_runtime": 98.3416,
|
| 2692 |
+
"eval_samples_per_second": 10.169,
|
| 2693 |
+
"eval_steps_per_second": 10.169,
|
| 2694 |
+
"step": 17900
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 0.45,
|
| 2698 |
+
"grad_norm": 3.1025142669677734,
|
| 2699 |
+
"learning_rate": 2.0512820512820513e-06,
|
| 2700 |
+
"loss": 0.6515,
|
| 2701 |
+
"step": 18000
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 0.45,
|
| 2705 |
+
"eval_loss": 0.6505727767944336,
|
| 2706 |
+
"eval_runtime": 98.3601,
|
| 2707 |
+
"eval_samples_per_second": 10.167,
|
| 2708 |
+
"eval_steps_per_second": 10.167,
|
| 2709 |
+
"step": 18000
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"epoch": 0.45,
|
| 2713 |
+
"grad_norm": 5.170887470245361,
|
| 2714 |
+
"learning_rate": 1.948717948717949e-06,
|
| 2715 |
+
"loss": 0.6554,
|
| 2716 |
+
"step": 18100
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 0.45,
|
| 2720 |
+
"eval_loss": 0.640792191028595,
|
| 2721 |
+
"eval_runtime": 98.3695,
|
| 2722 |
+
"eval_samples_per_second": 10.166,
|
| 2723 |
+
"eval_steps_per_second": 10.166,
|
| 2724 |
+
"step": 18100
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 0.46,
|
| 2728 |
+
"grad_norm": 8.582660675048828,
|
| 2729 |
+
"learning_rate": 1.8461538461538465e-06,
|
| 2730 |
+
"loss": 0.6481,
|
| 2731 |
+
"step": 18200
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 0.46,
|
| 2735 |
+
"eval_loss": 0.6477890014648438,
|
| 2736 |
+
"eval_runtime": 98.3746,
|
| 2737 |
+
"eval_samples_per_second": 10.165,
|
| 2738 |
+
"eval_steps_per_second": 10.165,
|
| 2739 |
+
"step": 18200
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.46,
|
| 2743 |
+
"grad_norm": 7.4102301597595215,
|
| 2744 |
+
"learning_rate": 1.7435897435897436e-06,
|
| 2745 |
+
"loss": 0.6284,
|
| 2746 |
+
"step": 18300
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.46,
|
| 2750 |
+
"eval_loss": 0.6732329726219177,
|
| 2751 |
+
"eval_runtime": 98.3003,
|
| 2752 |
+
"eval_samples_per_second": 10.173,
|
| 2753 |
+
"eval_steps_per_second": 10.173,
|
| 2754 |
+
"step": 18300
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.46,
|
| 2758 |
+
"grad_norm": 3.6458799839019775,
|
| 2759 |
+
"learning_rate": 1.6410256410256412e-06,
|
| 2760 |
+
"loss": 0.6546,
|
| 2761 |
+
"step": 18400
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.46,
|
| 2765 |
+
"eval_loss": 0.6304293274879456,
|
| 2766 |
+
"eval_runtime": 98.3207,
|
| 2767 |
+
"eval_samples_per_second": 10.171,
|
| 2768 |
+
"eval_steps_per_second": 10.171,
|
| 2769 |
+
"step": 18400
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 0.46,
|
| 2773 |
+
"grad_norm": 3.8108537197113037,
|
| 2774 |
+
"learning_rate": 1.5384615384615387e-06,
|
| 2775 |
+
"loss": 0.6665,
|
| 2776 |
+
"step": 18500
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 0.46,
|
| 2780 |
+
"eval_loss": 0.634360134601593,
|
| 2781 |
+
"eval_runtime": 98.3511,
|
| 2782 |
+
"eval_samples_per_second": 10.168,
|
| 2783 |
+
"eval_steps_per_second": 10.168,
|
| 2784 |
+
"step": 18500
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 0.47,
|
| 2788 |
+
"grad_norm": 9.306204795837402,
|
| 2789 |
+
"learning_rate": 1.4358974358974359e-06,
|
| 2790 |
+
"loss": 0.6559,
|
| 2791 |
+
"step": 18600
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 0.47,
|
| 2795 |
+
"eval_loss": 0.6353975534439087,
|
| 2796 |
+
"eval_runtime": 98.3306,
|
| 2797 |
+
"eval_samples_per_second": 10.17,
|
| 2798 |
+
"eval_steps_per_second": 10.17,
|
| 2799 |
+
"step": 18600
|
| 2800 |
+
},
|
| 2801 |
+
{
|
| 2802 |
+
"epoch": 0.47,
|
| 2803 |
+
"grad_norm": 4.001993656158447,
|
| 2804 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 2805 |
+
"loss": 0.6386,
|
| 2806 |
+
"step": 18700
|
| 2807 |
+
},
|
| 2808 |
+
{
|
| 2809 |
+
"epoch": 0.47,
|
| 2810 |
+
"eval_loss": 0.6281168460845947,
|
| 2811 |
+
"eval_runtime": 98.2978,
|
| 2812 |
+
"eval_samples_per_second": 10.173,
|
| 2813 |
+
"eval_steps_per_second": 10.173,
|
| 2814 |
+
"step": 18700
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"epoch": 0.47,
|
| 2818 |
+
"grad_norm": 4.9915924072265625,
|
| 2819 |
+
"learning_rate": 1.230769230769231e-06,
|
| 2820 |
+
"loss": 0.6509,
|
| 2821 |
+
"step": 18800
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 0.47,
|
| 2825 |
+
"eval_loss": 0.6473774313926697,
|
| 2826 |
+
"eval_runtime": 98.3123,
|
| 2827 |
+
"eval_samples_per_second": 10.172,
|
| 2828 |
+
"eval_steps_per_second": 10.172,
|
| 2829 |
+
"step": 18800
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 0.47,
|
| 2833 |
+
"grad_norm": 3.8955130577087402,
|
| 2834 |
+
"learning_rate": 1.1282051282051283e-06,
|
| 2835 |
+
"loss": 0.6272,
|
| 2836 |
+
"step": 18900
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 0.47,
|
| 2840 |
+
"eval_loss": 0.6473217606544495,
|
| 2841 |
+
"eval_runtime": 98.3521,
|
| 2842 |
+
"eval_samples_per_second": 10.168,
|
| 2843 |
+
"eval_steps_per_second": 10.168,
|
| 2844 |
+
"step": 18900
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 0.47,
|
| 2848 |
+
"grad_norm": 9.715432167053223,
|
| 2849 |
+
"learning_rate": 1.0256410256410257e-06,
|
| 2850 |
+
"loss": 0.6086,
|
| 2851 |
+
"step": 19000
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.47,
|
| 2855 |
+
"eval_loss": 0.620388925075531,
|
| 2856 |
+
"eval_runtime": 98.3358,
|
| 2857 |
+
"eval_samples_per_second": 10.169,
|
| 2858 |
+
"eval_steps_per_second": 10.169,
|
| 2859 |
+
"step": 19000
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.48,
|
| 2863 |
+
"grad_norm": 4.22080659866333,
|
| 2864 |
+
"learning_rate": 9.230769230769232e-07,
|
| 2865 |
+
"loss": 0.6553,
|
| 2866 |
+
"step": 19100
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.48,
|
| 2870 |
+
"eval_loss": 0.6517868041992188,
|
| 2871 |
+
"eval_runtime": 98.326,
|
| 2872 |
+
"eval_samples_per_second": 10.17,
|
| 2873 |
+
"eval_steps_per_second": 10.17,
|
| 2874 |
+
"step": 19100
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.48,
|
| 2878 |
+
"grad_norm": 3.7308225631713867,
|
| 2879 |
+
"learning_rate": 8.205128205128206e-07,
|
| 2880 |
+
"loss": 0.6119,
|
| 2881 |
+
"step": 19200
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.48,
|
| 2885 |
+
"eval_loss": 0.639901340007782,
|
| 2886 |
+
"eval_runtime": 98.3,
|
| 2887 |
+
"eval_samples_per_second": 10.173,
|
| 2888 |
+
"eval_steps_per_second": 10.173,
|
| 2889 |
+
"step": 19200
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 0.48,
|
| 2893 |
+
"grad_norm": 4.890966892242432,
|
| 2894 |
+
"learning_rate": 7.179487179487179e-07,
|
| 2895 |
+
"loss": 0.6363,
|
| 2896 |
+
"step": 19300
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.48,
|
| 2900 |
+
"eval_loss": 0.6639401912689209,
|
| 2901 |
+
"eval_runtime": 98.3404,
|
| 2902 |
+
"eval_samples_per_second": 10.169,
|
| 2903 |
+
"eval_steps_per_second": 10.169,
|
| 2904 |
+
"step": 19300
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 0.48,
|
| 2908 |
+
"grad_norm": 6.855196952819824,
|
| 2909 |
+
"learning_rate": 6.153846153846155e-07,
|
| 2910 |
+
"loss": 0.6261,
|
| 2911 |
+
"step": 19400
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 0.48,
|
| 2915 |
+
"eval_loss": 0.6473622918128967,
|
| 2916 |
+
"eval_runtime": 98.3312,
|
| 2917 |
+
"eval_samples_per_second": 10.17,
|
| 2918 |
+
"eval_steps_per_second": 10.17,
|
| 2919 |
+
"step": 19400
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 0.49,
|
| 2923 |
+
"grad_norm": 2.988701581954956,
|
| 2924 |
+
"learning_rate": 5.128205128205128e-07,
|
| 2925 |
+
"loss": 0.6192,
|
| 2926 |
+
"step": 19500
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"epoch": 0.49,
|
| 2930 |
+
"eval_loss": 0.6319825649261475,
|
| 2931 |
+
"eval_runtime": 98.277,
|
| 2932 |
+
"eval_samples_per_second": 10.175,
|
| 2933 |
+
"eval_steps_per_second": 10.175,
|
| 2934 |
+
"step": 19500
|
| 2935 |
+
},
|
| 2936 |
+
{
|
| 2937 |
+
"epoch": 0.49,
|
| 2938 |
+
"grad_norm": 3.922107696533203,
|
| 2939 |
+
"learning_rate": 4.102564102564103e-07,
|
| 2940 |
+
"loss": 0.6123,
|
| 2941 |
+
"step": 19600
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 0.49,
|
| 2945 |
+
"eval_loss": 0.6252996325492859,
|
| 2946 |
+
"eval_runtime": 98.3425,
|
| 2947 |
+
"eval_samples_per_second": 10.169,
|
| 2948 |
+
"eval_steps_per_second": 10.169,
|
| 2949 |
+
"step": 19600
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.49,
|
| 2953 |
+
"grad_norm": 13.531473159790039,
|
| 2954 |
+
"learning_rate": 3.0769230769230774e-07,
|
| 2955 |
+
"loss": 0.6128,
|
| 2956 |
+
"step": 19700
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.49,
|
| 2960 |
+
"eval_loss": 0.6362013220787048,
|
| 2961 |
+
"eval_runtime": 98.2906,
|
| 2962 |
+
"eval_samples_per_second": 10.174,
|
| 2963 |
+
"eval_steps_per_second": 10.174,
|
| 2964 |
+
"step": 19700
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.49,
|
| 2968 |
+
"grad_norm": 13.287760734558105,
|
| 2969 |
+
"learning_rate": 2.0512820512820514e-07,
|
| 2970 |
+
"loss": 0.6321,
|
| 2971 |
+
"step": 19800
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.49,
|
| 2975 |
+
"eval_loss": 0.6311822533607483,
|
| 2976 |
+
"eval_runtime": 98.3206,
|
| 2977 |
+
"eval_samples_per_second": 10.171,
|
| 2978 |
+
"eval_steps_per_second": 10.171,
|
| 2979 |
+
"step": 19800
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 0.5,
|
| 2983 |
+
"grad_norm": 10.524887084960938,
|
| 2984 |
+
"learning_rate": 1.0256410256410257e-07,
|
| 2985 |
+
"loss": 0.6026,
|
| 2986 |
+
"step": 19900
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 0.5,
|
| 2990 |
+
"eval_loss": 0.6232057809829712,
|
| 2991 |
+
"eval_runtime": 98.3191,
|
| 2992 |
+
"eval_samples_per_second": 10.171,
|
| 2993 |
+
"eval_steps_per_second": 10.171,
|
| 2994 |
+
"step": 19900
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.5,
|
| 2998 |
+
"grad_norm": 4.0852131843566895,
|
| 2999 |
+
"learning_rate": 0.0,
|
| 3000 |
+
"loss": 0.6322,
|
| 3001 |
+
"step": 20000
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.5,
|
| 3005 |
+
"eval_loss": 0.632331907749176,
|
| 3006 |
+
"eval_runtime": 98.3118,
|
| 3007 |
+
"eval_samples_per_second": 10.172,
|
| 3008 |
+
"eval_steps_per_second": 10.172,
|
| 3009 |
+
"step": 20000
|
| 3010 |
}
|
| 3011 |
],
|
| 3012 |
"logging_steps": 100,
|
|
|
|
| 3014 |
"num_input_tokens_seen": 0,
|
| 3015 |
"num_train_epochs": 1,
|
| 3016 |
"save_steps": 2500,
|
| 3017 |
+
"total_flos": 3.1467396661248e+17,
|
| 3018 |
"train_batch_size": 1,
|
| 3019 |
"trial_name": null,
|
| 3020 |
"trial_params": null
|