Training in progress, step 100000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 586828837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0978bc6ba8af6107f37b1ce0de2823f6ffed0e6f3357ff497f2e879a2e834ef3
|
| 3 |
size 586828837
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbd29e5163387c30aab8a8890d9ee62efc996b56b102107768b0eabf5e23817e
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1dca87fa841c98848654f4170210b8999092daa8068e42b3812f3ab2a9ca99
|
| 3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c91aaff4049dd76fbb2e0bcf40a0522c406dbf03765ebea50f6fb1be9645c2
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 733555848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fc0cfe80fceb3705f7126b83f3fe0e36d87dafa6df093df20b056316ba4fd28
|
| 3 |
size 733555848
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2706,11 +2706,311 @@
|
|
| 2706 |
"learning_rate": 0.0023768946429473976,
|
| 2707 |
"loss": 8.4846,
|
| 2708 |
"step": 90000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2709 |
}
|
| 2710 |
],
|
| 2711 |
"max_steps": 1000000,
|
| 2712 |
"num_train_epochs": 5,
|
| 2713 |
-
"total_flos": 1.
|
| 2714 |
"trial_name": null,
|
| 2715 |
"trial_params": null
|
| 2716 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.42972493307034165,
|
| 5 |
+
"global_step": 100000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2706 |
"learning_rate": 0.0023768946429473976,
|
| 2707 |
"loss": 8.4846,
|
| 2708 |
"step": 90000
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 0.39,
|
| 2712 |
+
"learning_rate": 0.002385031338735963,
|
| 2713 |
+
"loss": 8.4866,
|
| 2714 |
+
"step": 90200
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 0.39,
|
| 2718 |
+
"learning_rate": 0.0023931803824365962,
|
| 2719 |
+
"loss": 8.4847,
|
| 2720 |
+
"step": 90400
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 0.39,
|
| 2724 |
+
"learning_rate": 0.002401300900956714,
|
| 2725 |
+
"loss": 8.4934,
|
| 2726 |
+
"step": 90600
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.39,
|
| 2730 |
+
"learning_rate": 0.002409474471896992,
|
| 2731 |
+
"loss": 8.4872,
|
| 2732 |
+
"step": 90800
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.39,
|
| 2736 |
+
"learning_rate": 0.0024176602835290807,
|
| 2737 |
+
"loss": 8.4977,
|
| 2738 |
+
"step": 91000
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 0.39,
|
| 2742 |
+
"learning_rate": 0.0024258582999457665,
|
| 2743 |
+
"loss": 8.4967,
|
| 2744 |
+
"step": 91200
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 0.39,
|
| 2748 |
+
"learning_rate": 0.0024340684851863,
|
| 2749 |
+
"loss": 8.505,
|
| 2750 |
+
"step": 91400
|
| 2751 |
+
},
|
| 2752 |
+
{
|
| 2753 |
+
"epoch": 0.39,
|
| 2754 |
+
"learning_rate": 0.002442290803236551,
|
| 2755 |
+
"loss": 8.5126,
|
| 2756 |
+
"step": 91600
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 0.39,
|
| 2760 |
+
"learning_rate": 0.0024505252180291688,
|
| 2761 |
+
"loss": 8.5033,
|
| 2762 |
+
"step": 91800
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 0.4,
|
| 2766 |
+
"learning_rate": 0.0024587304311256865,
|
| 2767 |
+
"loss": 8.513,
|
| 2768 |
+
"step": 92000
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.4,
|
| 2772 |
+
"learning_rate": 0.0024669888709567232,
|
| 2773 |
+
"loss": 8.5082,
|
| 2774 |
+
"step": 92200
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.4,
|
| 2778 |
+
"learning_rate": 0.0024752592991915973,
|
| 2779 |
+
"loss": 8.517,
|
| 2780 |
+
"step": 92400
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 0.4,
|
| 2784 |
+
"learning_rate": 0.0024835416795519205,
|
| 2785 |
+
"loss": 8.5293,
|
| 2786 |
+
"step": 92600
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"epoch": 0.4,
|
| 2790 |
+
"learning_rate": 0.002491835975706881,
|
| 2791 |
+
"loss": 8.5094,
|
| 2792 |
+
"step": 92800
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 0.4,
|
| 2796 |
+
"learning_rate": 0.0025001421512733943,
|
| 2797 |
+
"loss": 8.5139,
|
| 2798 |
+
"step": 93000
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 0.4,
|
| 2802 |
+
"learning_rate": 0.0025084601698162666,
|
| 2803 |
+
"loss": 8.5099,
|
| 2804 |
+
"step": 93200
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.4,
|
| 2808 |
+
"learning_rate": 0.0025167899948483575,
|
| 2809 |
+
"loss": 8.5185,
|
| 2810 |
+
"step": 93400
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.4,
|
| 2814 |
+
"learning_rate": 0.0025251315898307336,
|
| 2815 |
+
"loss": 8.5143,
|
| 2816 |
+
"step": 93600
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 0.4,
|
| 2820 |
+
"learning_rate": 0.002533484918172837,
|
| 2821 |
+
"loss": 8.5277,
|
| 2822 |
+
"step": 93800
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 0.4,
|
| 2826 |
+
"learning_rate": 0.0025418499432326358,
|
| 2827 |
+
"loss": 8.5231,
|
| 2828 |
+
"step": 94000
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 0.4,
|
| 2832 |
+
"learning_rate": 0.002550184715947826,
|
| 2833 |
+
"loss": 8.5436,
|
| 2834 |
+
"step": 94200
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 0.41,
|
| 2838 |
+
"learning_rate": 0.0025585729662869474,
|
| 2839 |
+
"loss": 8.5373,
|
| 2840 |
+
"step": 94400
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 0.41,
|
| 2844 |
+
"learning_rate": 0.002566972803294579,
|
| 2845 |
+
"loss": 8.5347,
|
| 2846 |
+
"step": 94600
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.41,
|
| 2850 |
+
"learning_rate": 0.00257538419012468,
|
| 2851 |
+
"loss": 8.5544,
|
| 2852 |
+
"step": 94800
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.41,
|
| 2856 |
+
"learning_rate": 0.0025838070898805453,
|
| 2857 |
+
"loss": 8.5339,
|
| 2858 |
+
"step": 95000
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 0.41,
|
| 2862 |
+
"learning_rate": 0.002592241465614974,
|
| 2863 |
+
"loss": 8.5405,
|
| 2864 |
+
"step": 95200
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 0.41,
|
| 2868 |
+
"learning_rate": 0.002600687280330416,
|
| 2869 |
+
"loss": 8.5501,
|
| 2870 |
+
"step": 95400
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 0.41,
|
| 2874 |
+
"learning_rate": 0.0026091444969791513,
|
| 2875 |
+
"loss": 8.5344,
|
| 2876 |
+
"step": 95600
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 0.41,
|
| 2880 |
+
"learning_rate": 0.002617613078463441,
|
| 2881 |
+
"loss": 8.5477,
|
| 2882 |
+
"step": 95800
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.41,
|
| 2886 |
+
"learning_rate": 0.002626092987635699,
|
| 2887 |
+
"loss": 8.5443,
|
| 2888 |
+
"step": 96000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.41,
|
| 2892 |
+
"learning_rate": 0.002634541703276827,
|
| 2893 |
+
"loss": 8.5398,
|
| 2894 |
+
"step": 96200
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.41,
|
| 2898 |
+
"learning_rate": 0.002643044100010169,
|
| 2899 |
+
"loss": 8.5523,
|
| 2900 |
+
"step": 96400
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 0.42,
|
| 2904 |
+
"learning_rate": 0.002651557712877833,
|
| 2905 |
+
"loss": 8.5562,
|
| 2906 |
+
"step": 96600
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 0.42,
|
| 2910 |
+
"learning_rate": 0.0026600825045346955,
|
| 2911 |
+
"loss": 8.5525,
|
| 2912 |
+
"step": 96800
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 0.42,
|
| 2916 |
+
"learning_rate": 0.0026686184375866043,
|
| 2917 |
+
"loss": 8.5728,
|
| 2918 |
+
"step": 97000
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 0.42,
|
| 2922 |
+
"learning_rate": 0.002677165474590528,
|
| 2923 |
+
"loss": 8.5631,
|
| 2924 |
+
"step": 97200
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.42,
|
| 2928 |
+
"learning_rate": 0.002685723578054729,
|
| 2929 |
+
"loss": 8.5658,
|
| 2930 |
+
"step": 97400
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 0.42,
|
| 2934 |
+
"learning_rate": 0.0026942927104389334,
|
| 2935 |
+
"loss": 8.566,
|
| 2936 |
+
"step": 97600
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.42,
|
| 2940 |
+
"learning_rate": 0.002702872834154482,
|
| 2941 |
+
"loss": 8.5716,
|
| 2942 |
+
"step": 97800
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 0.42,
|
| 2946 |
+
"learning_rate": 0.0027114639115645017,
|
| 2947 |
+
"loss": 8.5697,
|
| 2948 |
+
"step": 98000
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 0.42,
|
| 2952 |
+
"learning_rate": 0.002720022867925799,
|
| 2953 |
+
"loss": 8.5726,
|
| 2954 |
+
"step": 98200
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 0.42,
|
| 2958 |
+
"learning_rate": 0.0027286356853246747,
|
| 2959 |
+
"loss": 8.5718,
|
| 2960 |
+
"step": 98400
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 0.42,
|
| 2964 |
+
"learning_rate": 0.0027372593434088002,
|
| 2965 |
+
"loss": 8.5716,
|
| 2966 |
+
"step": 98600
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.42,
|
| 2970 |
+
"learning_rate": 0.002745893804350339,
|
| 2971 |
+
"loss": 8.5767,
|
| 2972 |
+
"step": 98800
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 0.43,
|
| 2976 |
+
"learning_rate": 0.00275453903027407,
|
| 2977 |
+
"loss": 8.5957,
|
| 2978 |
+
"step": 99000
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.43,
|
| 2982 |
+
"learning_rate": 0.0027631949832575475,
|
| 2983 |
+
"loss": 8.5881,
|
| 2984 |
+
"step": 99200
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.43,
|
| 2988 |
+
"learning_rate": 0.002771861625331276,
|
| 2989 |
+
"loss": 8.5835,
|
| 2990 |
+
"step": 99400
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 0.43,
|
| 2994 |
+
"learning_rate": 0.002780495505581529,
|
| 2995 |
+
"loss": 8.5905,
|
| 2996 |
+
"step": 99600
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 0.43,
|
| 3000 |
+
"learning_rate": 0.002789183358769584,
|
| 3001 |
+
"loss": 8.5938,
|
| 3002 |
+
"step": 99800
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.43,
|
| 3006 |
+
"learning_rate": 0.0027978817870494,
|
| 3007 |
+
"loss": 8.5906,
|
| 3008 |
+
"step": 100000
|
| 3009 |
}
|
| 3010 |
],
|
| 3011 |
"max_steps": 1000000,
|
| 3012 |
"num_train_epochs": 5,
|
| 3013 |
+
"total_flos": 1.593829982208e+17,
|
| 3014 |
"trial_name": null,
|
| 3015 |
"trial_params": null
|
| 3016 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbd29e5163387c30aab8a8890d9ee62efc996b56b102107768b0eabf5e23817e
|
| 3 |
size 146774203
|