Training in progress, step 22000, 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 1520630616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:299b24fe69c89f19141b9f985a9ac826c3a53ad4e1b08b8aba5729be39c93c43
|
| 3 |
size 1520630616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3041448587
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2578fa210b28417d8f969fa905bceff91b35a10909b4f603355ac6d743992a10
|
| 3 |
size 3041448587
|
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 sha256:59dbdf3564f71a619277fad1d7b29f944b0a8aee767f1ee531e2a42c249a6709
|
| 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:c5b97fc3e9888373aed6e862ae95add028b1c9773804bea656915decaab6270d
|
| 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":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2808,6 +2808,286 @@
|
|
| 2808 |
"learning_rate": 0.0002720358859033514,
|
| 2809 |
"loss": 1.6249,
|
| 2810 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2811 |
}
|
| 2812 |
],
|
| 2813 |
"logging_steps": 50,
|
|
@@ -2827,7 +3107,7 @@
|
|
| 2827 |
"attributes": {}
|
| 2828 |
}
|
| 2829 |
},
|
| 2830 |
-
"total_flos": 1.
|
| 2831 |
"train_batch_size": 16,
|
| 2832 |
"trial_name": null,
|
| 2833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.014666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 22000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2808 |
"learning_rate": 0.0002720358859033514,
|
| 2809 |
"loss": 1.6249,
|
| 2810 |
"step": 20000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 5.030983606557377,
|
| 2814 |
+
"grad_norm": 0.59375,
|
| 2815 |
+
"learning_rate": 0.00027188193193538625,
|
| 2816 |
+
"loss": 1.6114,
|
| 2817 |
+
"step": 20050
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 5.031530054644809,
|
| 2821 |
+
"grad_norm": 0.671875,
|
| 2822 |
+
"learning_rate": 0.00027172759915556504,
|
| 2823 |
+
"loss": 1.6081,
|
| 2824 |
+
"step": 20100
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 5.032076502732241,
|
| 2828 |
+
"grad_norm": 0.62890625,
|
| 2829 |
+
"learning_rate": 0.0002715728880435577,
|
| 2830 |
+
"loss": 1.627,
|
| 2831 |
+
"step": 20150
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 5.032622950819672,
|
| 2835 |
+
"grad_norm": 0.62890625,
|
| 2836 |
+
"learning_rate": 0.00027141779908020986,
|
| 2837 |
+
"loss": 1.5912,
|
| 2838 |
+
"step": 20200
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 5.033169398907104,
|
| 2842 |
+
"grad_norm": 0.65234375,
|
| 2843 |
+
"learning_rate": 0.00027126233274754163,
|
| 2844 |
+
"loss": 1.6476,
|
| 2845 |
+
"step": 20250
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 5.033715846994536,
|
| 2849 |
+
"grad_norm": 0.59375,
|
| 2850 |
+
"learning_rate": 0.00027110648952874595,
|
| 2851 |
+
"loss": 1.6051,
|
| 2852 |
+
"step": 20300
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 5.034262295081967,
|
| 2856 |
+
"grad_norm": 0.65234375,
|
| 2857 |
+
"learning_rate": 0.0002709502699081871,
|
| 2858 |
+
"loss": 1.5705,
|
| 2859 |
+
"step": 20350
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 5.034808743169399,
|
| 2863 |
+
"grad_norm": 0.578125,
|
| 2864 |
+
"learning_rate": 0.00027079367437139935,
|
| 2865 |
+
"loss": 1.6533,
|
| 2866 |
+
"step": 20400
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 5.035355191256831,
|
| 2870 |
+
"grad_norm": 0.59765625,
|
| 2871 |
+
"learning_rate": 0.00027063670340508514,
|
| 2872 |
+
"loss": 1.6099,
|
| 2873 |
+
"step": 20450
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 5.035901639344262,
|
| 2877 |
+
"grad_norm": 0.5703125,
|
| 2878 |
+
"learning_rate": 0.00027047935749711395,
|
| 2879 |
+
"loss": 1.6018,
|
| 2880 |
+
"step": 20500
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 5.036448087431694,
|
| 2884 |
+
"grad_norm": 0.59375,
|
| 2885 |
+
"learning_rate": 0.0002703216371365204,
|
| 2886 |
+
"loss": 1.637,
|
| 2887 |
+
"step": 20550
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 5.036994535519126,
|
| 2891 |
+
"grad_norm": 0.56640625,
|
| 2892 |
+
"learning_rate": 0.00027016354281350315,
|
| 2893 |
+
"loss": 1.6394,
|
| 2894 |
+
"step": 20600
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 5.037540983606557,
|
| 2898 |
+
"grad_norm": 0.6015625,
|
| 2899 |
+
"learning_rate": 0.00027000507501942283,
|
| 2900 |
+
"loss": 1.6253,
|
| 2901 |
+
"step": 20650
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 6.000459016393442,
|
| 2905 |
+
"grad_norm": 0.57421875,
|
| 2906 |
+
"learning_rate": 0.0002698462342468011,
|
| 2907 |
+
"loss": 1.5897,
|
| 2908 |
+
"step": 20700
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 6.001005464480874,
|
| 2912 |
+
"grad_norm": 0.56640625,
|
| 2913 |
+
"learning_rate": 0.0002696870209893187,
|
| 2914 |
+
"loss": 1.569,
|
| 2915 |
+
"step": 20750
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 6.001551912568306,
|
| 2919 |
+
"grad_norm": 0.59765625,
|
| 2920 |
+
"learning_rate": 0.00026952743574181414,
|
| 2921 |
+
"loss": 1.5482,
|
| 2922 |
+
"step": 20800
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 6.002098360655737,
|
| 2926 |
+
"grad_norm": 0.59765625,
|
| 2927 |
+
"learning_rate": 0.00026936747900028205,
|
| 2928 |
+
"loss": 1.5458,
|
| 2929 |
+
"step": 20850
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 6.002644808743169,
|
| 2933 |
+
"grad_norm": 0.734375,
|
| 2934 |
+
"learning_rate": 0.00026920715126187167,
|
| 2935 |
+
"loss": 1.4787,
|
| 2936 |
+
"step": 20900
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 6.003191256830601,
|
| 2940 |
+
"grad_norm": 0.7109375,
|
| 2941 |
+
"learning_rate": 0.0002690464530248853,
|
| 2942 |
+
"loss": 1.5565,
|
| 2943 |
+
"step": 20950
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 6.0037377049180325,
|
| 2947 |
+
"grad_norm": 0.64453125,
|
| 2948 |
+
"learning_rate": 0.00026888538478877675,
|
| 2949 |
+
"loss": 1.5588,
|
| 2950 |
+
"step": 21000
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 6.0042841530054645,
|
| 2954 |
+
"grad_norm": 0.6953125,
|
| 2955 |
+
"learning_rate": 0.0002687239470541498,
|
| 2956 |
+
"loss": 1.5347,
|
| 2957 |
+
"step": 21050
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 6.0048306010928965,
|
| 2961 |
+
"grad_norm": 0.58984375,
|
| 2962 |
+
"learning_rate": 0.00026856214032275675,
|
| 2963 |
+
"loss": 1.5341,
|
| 2964 |
+
"step": 21100
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 6.0053770491803276,
|
| 2968 |
+
"grad_norm": 0.73046875,
|
| 2969 |
+
"learning_rate": 0.00026839996509749655,
|
| 2970 |
+
"loss": 1.5441,
|
| 2971 |
+
"step": 21150
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 6.0059234972677595,
|
| 2975 |
+
"grad_norm": 0.58984375,
|
| 2976 |
+
"learning_rate": 0.00026823742188241366,
|
| 2977 |
+
"loss": 1.5405,
|
| 2978 |
+
"step": 21200
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 6.0064699453551915,
|
| 2982 |
+
"grad_norm": 0.64453125,
|
| 2983 |
+
"learning_rate": 0.000268074511182696,
|
| 2984 |
+
"loss": 1.5327,
|
| 2985 |
+
"step": 21250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 6.007016393442623,
|
| 2989 |
+
"grad_norm": 0.61328125,
|
| 2990 |
+
"learning_rate": 0.00026791123350467384,
|
| 2991 |
+
"loss": 1.5338,
|
| 2992 |
+
"step": 21300
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 6.007562841530055,
|
| 2996 |
+
"grad_norm": 0.58984375,
|
| 2997 |
+
"learning_rate": 0.000267747589355818,
|
| 2998 |
+
"loss": 1.5663,
|
| 2999 |
+
"step": 21350
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 6.008109289617487,
|
| 3003 |
+
"grad_norm": 0.67578125,
|
| 3004 |
+
"learning_rate": 0.0002675835792447382,
|
| 3005 |
+
"loss": 1.5519,
|
| 3006 |
+
"step": 21400
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 6.008655737704918,
|
| 3010 |
+
"grad_norm": 0.66015625,
|
| 3011 |
+
"learning_rate": 0.0002674192036811818,
|
| 3012 |
+
"loss": 1.5256,
|
| 3013 |
+
"step": 21450
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 6.00920218579235,
|
| 3017 |
+
"grad_norm": 0.578125,
|
| 3018 |
+
"learning_rate": 0.0002672544631760317,
|
| 3019 |
+
"loss": 1.5428,
|
| 3020 |
+
"step": 21500
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 6.009748633879782,
|
| 3024 |
+
"grad_norm": 0.75,
|
| 3025 |
+
"learning_rate": 0.00026708935824130514,
|
| 3026 |
+
"loss": 1.5806,
|
| 3027 |
+
"step": 21550
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 6.010295081967213,
|
| 3031 |
+
"grad_norm": 0.57421875,
|
| 3032 |
+
"learning_rate": 0.00026692388939015226,
|
| 3033 |
+
"loss": 1.5628,
|
| 3034 |
+
"step": 21600
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 6.010841530054645,
|
| 3038 |
+
"grad_norm": 0.61328125,
|
| 3039 |
+
"learning_rate": 0.00026675805713685387,
|
| 3040 |
+
"loss": 1.5275,
|
| 3041 |
+
"step": 21650
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 6.011387978142077,
|
| 3045 |
+
"grad_norm": 0.61328125,
|
| 3046 |
+
"learning_rate": 0.0002665918619968206,
|
| 3047 |
+
"loss": 1.5547,
|
| 3048 |
+
"step": 21700
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 6.011934426229508,
|
| 3052 |
+
"grad_norm": 0.57421875,
|
| 3053 |
+
"learning_rate": 0.0002664253044865907,
|
| 3054 |
+
"loss": 1.575,
|
| 3055 |
+
"step": 21750
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 6.01248087431694,
|
| 3059 |
+
"grad_norm": 0.59765625,
|
| 3060 |
+
"learning_rate": 0.0002662583851238287,
|
| 3061 |
+
"loss": 1.5386,
|
| 3062 |
+
"step": 21800
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 6.013027322404372,
|
| 3066 |
+
"grad_norm": 0.6484375,
|
| 3067 |
+
"learning_rate": 0.000266091104427324,
|
| 3068 |
+
"loss": 1.5107,
|
| 3069 |
+
"step": 21850
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 6.013573770491803,
|
| 3073 |
+
"grad_norm": 0.625,
|
| 3074 |
+
"learning_rate": 0.00026592346291698864,
|
| 3075 |
+
"loss": 1.5516,
|
| 3076 |
+
"step": 21900
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 6.014120218579235,
|
| 3080 |
+
"grad_norm": 0.5703125,
|
| 3081 |
+
"learning_rate": 0.00026575546111385647,
|
| 3082 |
+
"loss": 1.5431,
|
| 3083 |
+
"step": 21950
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 6.014666666666667,
|
| 3087 |
+
"grad_norm": 0.6015625,
|
| 3088 |
+
"learning_rate": 0.00026558709954008095,
|
| 3089 |
+
"loss": 1.566,
|
| 3090 |
+
"step": 22000
|
| 3091 |
}
|
| 3092 |
],
|
| 3093 |
"logging_steps": 50,
|
|
|
|
| 3107 |
"attributes": {}
|
| 3108 |
}
|
| 3109 |
},
|
| 3110 |
+
"total_flos": 1.1765225285807505e+19,
|
| 3111 |
"train_batch_size": 16,
|
| 3112 |
"trial_name": null,
|
| 3113 |
"trial_params": null
|