Training in progress, step 4000, 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 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6150dc5bd051bed762db3300592d4cc7ebe9703885d3d6313370582e89e126b1
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced7feb6339932dd38c7dd1b41e44f03af228749aaf328c571f8b3d5e79694bc
|
| 3 |
size 469516363
|
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:df4b1a89b85b3ec35f63283289082575fe9a15b34a21a7f947d7912552e363be
|
| 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:c3220e96802ad35e508b642aabfd7e1cb6a8b7c1925ae81918e4ab19428a5638
|
| 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": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2738,6 +2738,396 @@
|
|
| 2738 |
"eval_samples_per_second": 67.472,
|
| 2739 |
"eval_steps_per_second": 3.849,
|
| 2740 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2741 |
}
|
| 2742 |
],
|
| 2743 |
"logging_steps": 10,
|
|
@@ -2757,7 +3147,7 @@
|
|
| 2757 |
"attributes": {}
|
| 2758 |
}
|
| 2759 |
},
|
| 2760 |
-
"total_flos": 1.
|
| 2761 |
"train_batch_size": 18,
|
| 2762 |
"trial_name": null,
|
| 2763 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2738 |
"eval_samples_per_second": 67.472,
|
| 2739 |
"eval_steps_per_second": 3.849,
|
| 2740 |
"step": 3500
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.702,
|
| 2744 |
+
"grad_norm": 0.053466796875,
|
| 2745 |
+
"learning_rate": 0.0003,
|
| 2746 |
+
"loss": 2.599693489074707,
|
| 2747 |
+
"step": 3510
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.704,
|
| 2751 |
+
"grad_norm": 0.07275390625,
|
| 2752 |
+
"learning_rate": 0.0003,
|
| 2753 |
+
"loss": 2.599070167541504,
|
| 2754 |
+
"step": 3520
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.706,
|
| 2758 |
+
"grad_norm": 0.055419921875,
|
| 2759 |
+
"learning_rate": 0.0003,
|
| 2760 |
+
"loss": 2.6012365341186525,
|
| 2761 |
+
"step": 3530
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.708,
|
| 2765 |
+
"grad_norm": 0.05224609375,
|
| 2766 |
+
"learning_rate": 0.0003,
|
| 2767 |
+
"loss": 2.576295852661133,
|
| 2768 |
+
"step": 3540
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.71,
|
| 2772 |
+
"grad_norm": 0.0517578125,
|
| 2773 |
+
"learning_rate": 0.0003,
|
| 2774 |
+
"loss": 2.6024765014648437,
|
| 2775 |
+
"step": 3550
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.712,
|
| 2779 |
+
"grad_norm": 0.0693359375,
|
| 2780 |
+
"learning_rate": 0.0003,
|
| 2781 |
+
"loss": 2.5685857772827148,
|
| 2782 |
+
"step": 3560
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.714,
|
| 2786 |
+
"grad_norm": 0.1220703125,
|
| 2787 |
+
"learning_rate": 0.0003,
|
| 2788 |
+
"loss": 2.584480094909668,
|
| 2789 |
+
"step": 3570
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.716,
|
| 2793 |
+
"grad_norm": 0.06396484375,
|
| 2794 |
+
"learning_rate": 0.0003,
|
| 2795 |
+
"loss": 2.6187564849853517,
|
| 2796 |
+
"step": 3580
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.718,
|
| 2800 |
+
"grad_norm": 0.05126953125,
|
| 2801 |
+
"learning_rate": 0.0003,
|
| 2802 |
+
"loss": 2.608148384094238,
|
| 2803 |
+
"step": 3590
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.72,
|
| 2807 |
+
"grad_norm": 0.056396484375,
|
| 2808 |
+
"learning_rate": 0.0003,
|
| 2809 |
+
"loss": 2.596156883239746,
|
| 2810 |
+
"step": 3600
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.72,
|
| 2814 |
+
"eval_loss": 3.0285751819610596,
|
| 2815 |
+
"eval_runtime": 4.4537,
|
| 2816 |
+
"eval_samples_per_second": 66.91,
|
| 2817 |
+
"eval_steps_per_second": 3.817,
|
| 2818 |
+
"step": 3600
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.722,
|
| 2822 |
+
"grad_norm": 2.265625,
|
| 2823 |
+
"learning_rate": 0.0003,
|
| 2824 |
+
"loss": 2.6053913116455076,
|
| 2825 |
+
"step": 3610
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.724,
|
| 2829 |
+
"grad_norm": 0.1259765625,
|
| 2830 |
+
"learning_rate": 0.0003,
|
| 2831 |
+
"loss": 2.5906614303588866,
|
| 2832 |
+
"step": 3620
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.726,
|
| 2836 |
+
"grad_norm": 0.058349609375,
|
| 2837 |
+
"learning_rate": 0.0003,
|
| 2838 |
+
"loss": 2.6229223251342773,
|
| 2839 |
+
"step": 3630
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.728,
|
| 2843 |
+
"grad_norm": 0.054443359375,
|
| 2844 |
+
"learning_rate": 0.0003,
|
| 2845 |
+
"loss": 2.6100414276123045,
|
| 2846 |
+
"step": 3640
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.73,
|
| 2850 |
+
"grad_norm": 0.05078125,
|
| 2851 |
+
"learning_rate": 0.0003,
|
| 2852 |
+
"loss": 2.5861778259277344,
|
| 2853 |
+
"step": 3650
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.732,
|
| 2857 |
+
"grad_norm": 0.06884765625,
|
| 2858 |
+
"learning_rate": 0.0003,
|
| 2859 |
+
"loss": 2.6088991165161133,
|
| 2860 |
+
"step": 3660
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 0.734,
|
| 2864 |
+
"grad_norm": 0.0546875,
|
| 2865 |
+
"learning_rate": 0.0003,
|
| 2866 |
+
"loss": 2.5957805633544924,
|
| 2867 |
+
"step": 3670
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.736,
|
| 2871 |
+
"grad_norm": 0.08447265625,
|
| 2872 |
+
"learning_rate": 0.0003,
|
| 2873 |
+
"loss": 2.5968517303466796,
|
| 2874 |
+
"step": 3680
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.738,
|
| 2878 |
+
"grad_norm": 0.06396484375,
|
| 2879 |
+
"learning_rate": 0.0003,
|
| 2880 |
+
"loss": 2.590867614746094,
|
| 2881 |
+
"step": 3690
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.74,
|
| 2885 |
+
"grad_norm": 0.057373046875,
|
| 2886 |
+
"learning_rate": 0.0003,
|
| 2887 |
+
"loss": 2.6020263671875,
|
| 2888 |
+
"step": 3700
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.74,
|
| 2892 |
+
"eval_loss": 3.033440113067627,
|
| 2893 |
+
"eval_runtime": 4.4438,
|
| 2894 |
+
"eval_samples_per_second": 67.059,
|
| 2895 |
+
"eval_steps_per_second": 3.826,
|
| 2896 |
+
"step": 3700
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.742,
|
| 2900 |
+
"grad_norm": 1.8359375,
|
| 2901 |
+
"learning_rate": 0.0003,
|
| 2902 |
+
"loss": 2.624915885925293,
|
| 2903 |
+
"step": 3710
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.744,
|
| 2907 |
+
"grad_norm": 0.05322265625,
|
| 2908 |
+
"learning_rate": 0.0003,
|
| 2909 |
+
"loss": 2.6158367156982423,
|
| 2910 |
+
"step": 3720
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 0.746,
|
| 2914 |
+
"grad_norm": 0.052978515625,
|
| 2915 |
+
"learning_rate": 0.0003,
|
| 2916 |
+
"loss": 2.5968292236328123,
|
| 2917 |
+
"step": 3730
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.748,
|
| 2921 |
+
"grad_norm": 0.0849609375,
|
| 2922 |
+
"learning_rate": 0.0003,
|
| 2923 |
+
"loss": 2.61802978515625,
|
| 2924 |
+
"step": 3740
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.75,
|
| 2928 |
+
"grad_norm": 0.05517578125,
|
| 2929 |
+
"learning_rate": 0.0003,
|
| 2930 |
+
"loss": 2.5647909164428713,
|
| 2931 |
+
"step": 3750
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.752,
|
| 2935 |
+
"grad_norm": 0.060791015625,
|
| 2936 |
+
"learning_rate": 0.0003,
|
| 2937 |
+
"loss": 2.601895332336426,
|
| 2938 |
+
"step": 3760
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.754,
|
| 2942 |
+
"grad_norm": 0.0556640625,
|
| 2943 |
+
"learning_rate": 0.0003,
|
| 2944 |
+
"loss": 2.605121612548828,
|
| 2945 |
+
"step": 3770
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.756,
|
| 2949 |
+
"grad_norm": 0.09716796875,
|
| 2950 |
+
"learning_rate": 0.0003,
|
| 2951 |
+
"loss": 2.6213621139526366,
|
| 2952 |
+
"step": 3780
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.758,
|
| 2956 |
+
"grad_norm": 0.05078125,
|
| 2957 |
+
"learning_rate": 0.0003,
|
| 2958 |
+
"loss": 2.5848875045776367,
|
| 2959 |
+
"step": 3790
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.76,
|
| 2963 |
+
"grad_norm": 0.05859375,
|
| 2964 |
+
"learning_rate": 0.0003,
|
| 2965 |
+
"loss": 2.585398483276367,
|
| 2966 |
+
"step": 3800
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.76,
|
| 2970 |
+
"eval_loss": 3.0310301780700684,
|
| 2971 |
+
"eval_runtime": 4.4352,
|
| 2972 |
+
"eval_samples_per_second": 67.19,
|
| 2973 |
+
"eval_steps_per_second": 3.833,
|
| 2974 |
+
"step": 3800
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 0.762,
|
| 2978 |
+
"grad_norm": 0.0830078125,
|
| 2979 |
+
"learning_rate": 0.0003,
|
| 2980 |
+
"loss": 2.5891979217529295,
|
| 2981 |
+
"step": 3810
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.764,
|
| 2985 |
+
"grad_norm": 0.048828125,
|
| 2986 |
+
"learning_rate": 0.0003,
|
| 2987 |
+
"loss": 2.587088203430176,
|
| 2988 |
+
"step": 3820
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 0.766,
|
| 2992 |
+
"grad_norm": 0.056884765625,
|
| 2993 |
+
"learning_rate": 0.0003,
|
| 2994 |
+
"loss": 2.6202329635620116,
|
| 2995 |
+
"step": 3830
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 0.768,
|
| 2999 |
+
"grad_norm": 0.058349609375,
|
| 3000 |
+
"learning_rate": 0.0003,
|
| 3001 |
+
"loss": 2.588342475891113,
|
| 3002 |
+
"step": 3840
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.77,
|
| 3006 |
+
"grad_norm": 0.051513671875,
|
| 3007 |
+
"learning_rate": 0.0003,
|
| 3008 |
+
"loss": 2.570342445373535,
|
| 3009 |
+
"step": 3850
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 0.772,
|
| 3013 |
+
"grad_norm": 0.054443359375,
|
| 3014 |
+
"learning_rate": 0.0003,
|
| 3015 |
+
"loss": 2.5928205490112304,
|
| 3016 |
+
"step": 3860
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 0.774,
|
| 3020 |
+
"grad_norm": 1.1484375,
|
| 3021 |
+
"learning_rate": 0.0003,
|
| 3022 |
+
"loss": 2.562236785888672,
|
| 3023 |
+
"step": 3870
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 0.776,
|
| 3027 |
+
"grad_norm": 0.05322265625,
|
| 3028 |
+
"learning_rate": 0.0003,
|
| 3029 |
+
"loss": 2.5821876525878906,
|
| 3030 |
+
"step": 3880
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 0.778,
|
| 3034 |
+
"grad_norm": 0.05029296875,
|
| 3035 |
+
"learning_rate": 0.0003,
|
| 3036 |
+
"loss": 2.583372688293457,
|
| 3037 |
+
"step": 3890
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 0.78,
|
| 3041 |
+
"grad_norm": 0.197265625,
|
| 3042 |
+
"learning_rate": 0.0003,
|
| 3043 |
+
"loss": 2.5738046646118162,
|
| 3044 |
+
"step": 3900
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.78,
|
| 3048 |
+
"eval_loss": 3.029505491256714,
|
| 3049 |
+
"eval_runtime": 4.3771,
|
| 3050 |
+
"eval_samples_per_second": 68.082,
|
| 3051 |
+
"eval_steps_per_second": 3.884,
|
| 3052 |
+
"step": 3900
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"epoch": 0.782,
|
| 3056 |
+
"grad_norm": 0.173828125,
|
| 3057 |
+
"learning_rate": 0.0003,
|
| 3058 |
+
"loss": 2.576494598388672,
|
| 3059 |
+
"step": 3910
|
| 3060 |
+
},
|
| 3061 |
+
{
|
| 3062 |
+
"epoch": 0.784,
|
| 3063 |
+
"grad_norm": 0.380859375,
|
| 3064 |
+
"learning_rate": 0.0003,
|
| 3065 |
+
"loss": 2.5919593811035155,
|
| 3066 |
+
"step": 3920
|
| 3067 |
+
},
|
| 3068 |
+
{
|
| 3069 |
+
"epoch": 0.786,
|
| 3070 |
+
"grad_norm": 0.048095703125,
|
| 3071 |
+
"learning_rate": 0.0003,
|
| 3072 |
+
"loss": 2.621496391296387,
|
| 3073 |
+
"step": 3930
|
| 3074 |
+
},
|
| 3075 |
+
{
|
| 3076 |
+
"epoch": 0.788,
|
| 3077 |
+
"grad_norm": 0.052490234375,
|
| 3078 |
+
"learning_rate": 0.0003,
|
| 3079 |
+
"loss": 2.584731101989746,
|
| 3080 |
+
"step": 3940
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 0.79,
|
| 3084 |
+
"grad_norm": 0.0498046875,
|
| 3085 |
+
"learning_rate": 0.0003,
|
| 3086 |
+
"loss": 2.568536567687988,
|
| 3087 |
+
"step": 3950
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"epoch": 0.792,
|
| 3091 |
+
"grad_norm": 0.0615234375,
|
| 3092 |
+
"learning_rate": 0.0003,
|
| 3093 |
+
"loss": 2.590066909790039,
|
| 3094 |
+
"step": 3960
|
| 3095 |
+
},
|
| 3096 |
+
{
|
| 3097 |
+
"epoch": 0.794,
|
| 3098 |
+
"grad_norm": 0.060791015625,
|
| 3099 |
+
"learning_rate": 0.0003,
|
| 3100 |
+
"loss": 2.613643264770508,
|
| 3101 |
+
"step": 3970
|
| 3102 |
+
},
|
| 3103 |
+
{
|
| 3104 |
+
"epoch": 0.796,
|
| 3105 |
+
"grad_norm": 0.052734375,
|
| 3106 |
+
"learning_rate": 0.0003,
|
| 3107 |
+
"loss": 2.614491081237793,
|
| 3108 |
+
"step": 3980
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"epoch": 0.798,
|
| 3112 |
+
"grad_norm": 0.0517578125,
|
| 3113 |
+
"learning_rate": 0.0003,
|
| 3114 |
+
"loss": 2.591320037841797,
|
| 3115 |
+
"step": 3990
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"epoch": 0.8,
|
| 3119 |
+
"grad_norm": 0.04931640625,
|
| 3120 |
+
"learning_rate": 0.0003,
|
| 3121 |
+
"loss": 2.605324554443359,
|
| 3122 |
+
"step": 4000
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 0.8,
|
| 3126 |
+
"eval_loss": 3.0305187702178955,
|
| 3127 |
+
"eval_runtime": 4.4657,
|
| 3128 |
+
"eval_samples_per_second": 66.73,
|
| 3129 |
+
"eval_steps_per_second": 3.807,
|
| 3130 |
+
"step": 4000
|
| 3131 |
}
|
| 3132 |
],
|
| 3133 |
"logging_steps": 10,
|
|
|
|
| 3147 |
"attributes": {}
|
| 3148 |
}
|
| 3149 |
},
|
| 3150 |
+
"total_flos": 1.304618059431936e+18,
|
| 3151 |
"train_batch_size": 18,
|
| 3152 |
"trial_name": null,
|
| 3153 |
"trial_params": null
|