Training in progress, step 40000, 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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:effd2d14476df74bc5f8738835a04cd2c53990d3720280723645c691281e29a7
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c29b0dac895207221ca2ff233a263d1f8bafafacb0961d5bd379e4086db6f23
|
| 3 |
size 938825803
|
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:ee2b9e8d80dbc1551afe65580bf18f91ce6a2908c043aa9c60a24adad8385acc
|
| 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 sha256:7778da91eeef8b8307a814fd6b609cdd038d764b06717fd843f1619aa9b55603
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
"epoch": 0.03636363636363636,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2816,6 +2816,318 @@
|
|
| 2816 |
"eval_samples_per_second": 77.327,
|
| 2817 |
"eval_steps_per_second": 19.332,
|
| 2818 |
"step": 36000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2819 |
}
|
| 2820 |
],
|
| 2821 |
"logging_steps": 100,
|
|
@@ -2835,7 +3147,7 @@
|
|
| 2835 |
"attributes": {}
|
| 2836 |
}
|
| 2837 |
},
|
| 2838 |
-
"total_flos":
|
| 2839 |
"train_batch_size": 22,
|
| 2840 |
"trial_name": null,
|
| 2841 |
"trial_params": null
|
|
|
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
"epoch": 0.03636363636363636,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 40000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2816 |
"eval_samples_per_second": 77.327,
|
| 2817 |
"eval_steps_per_second": 19.332,
|
| 2818 |
"step": 36000
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.0009090909090909091,
|
| 2822 |
+
"grad_norm": 0.20997287333011627,
|
| 2823 |
+
"learning_rate": 0.0007582221078899511,
|
| 2824 |
+
"loss": 2.71048828125,
|
| 2825 |
+
"step": 36100
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.0018181818181818182,
|
| 2829 |
+
"grad_norm": 0.1532030999660492,
|
| 2830 |
+
"learning_rate": 0.0007569965605062139,
|
| 2831 |
+
"loss": 2.7088739013671876,
|
| 2832 |
+
"step": 36200
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.0027272727272727275,
|
| 2836 |
+
"grad_norm": 0.14671523869037628,
|
| 2837 |
+
"learning_rate": 0.000755768911151874,
|
| 2838 |
+
"loss": 2.730252990722656,
|
| 2839 |
+
"step": 36300
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.0036363636363636364,
|
| 2843 |
+
"grad_norm": 0.1369636058807373,
|
| 2844 |
+
"learning_rate": 0.0007545391698678547,
|
| 2845 |
+
"loss": 2.7253591918945315,
|
| 2846 |
+
"step": 36400
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.004545454545454545,
|
| 2850 |
+
"grad_norm": 0.16328130662441254,
|
| 2851 |
+
"learning_rate": 0.00075330734671219,
|
| 2852 |
+
"loss": 2.6905337524414064,
|
| 2853 |
+
"step": 36500
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.005454545454545455,
|
| 2857 |
+
"grad_norm": 0.13856680691242218,
|
| 2858 |
+
"learning_rate": 0.0007520734517599409,
|
| 2859 |
+
"loss": 2.6842236328125,
|
| 2860 |
+
"step": 36600
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 0.006363636363636364,
|
| 2864 |
+
"grad_norm": 0.14775875210762024,
|
| 2865 |
+
"learning_rate": 0.0007508374951031139,
|
| 2866 |
+
"loss": 2.7059420776367187,
|
| 2867 |
+
"step": 36700
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.007272727272727273,
|
| 2871 |
+
"grad_norm": 0.14245547354221344,
|
| 2872 |
+
"learning_rate": 0.0007495994868505774,
|
| 2873 |
+
"loss": 2.6968829345703127,
|
| 2874 |
+
"step": 36800
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.008181818181818182,
|
| 2878 |
+
"grad_norm": 0.15311609208583832,
|
| 2879 |
+
"learning_rate": 0.000748359437127981,
|
| 2880 |
+
"loss": 2.7318048095703125,
|
| 2881 |
+
"step": 36900
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.00909090909090909,
|
| 2885 |
+
"grad_norm": 0.1730499267578125,
|
| 2886 |
+
"learning_rate": 0.0007471173560776705,
|
| 2887 |
+
"loss": 2.6874020385742186,
|
| 2888 |
+
"step": 37000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.00909090909090909,
|
| 2892 |
+
"eval_loss": 3.13167405128479,
|
| 2893 |
+
"eval_runtime": 7.5047,
|
| 2894 |
+
"eval_samples_per_second": 76.752,
|
| 2895 |
+
"eval_steps_per_second": 19.188,
|
| 2896 |
+
"step": 37000
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.01,
|
| 2900 |
+
"grad_norm": 0.15705707669258118,
|
| 2901 |
+
"learning_rate": 0.0007458732538586064,
|
| 2902 |
+
"loss": 2.692235107421875,
|
| 2903 |
+
"step": 37100
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.01090909090909091,
|
| 2907 |
+
"grad_norm": 0.1563568264245987,
|
| 2908 |
+
"learning_rate": 0.0007446271406462797,
|
| 2909 |
+
"loss": 2.706945495605469,
|
| 2910 |
+
"step": 37200
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 0.011818181818181818,
|
| 2914 |
+
"grad_norm": 0.16822531819343567,
|
| 2915 |
+
"learning_rate": 0.00074337902663263,
|
| 2916 |
+
"loss": 2.685476989746094,
|
| 2917 |
+
"step": 37300
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.012727272727272728,
|
| 2921 |
+
"grad_norm": 0.14851588010787964,
|
| 2922 |
+
"learning_rate": 0.000742128922025961,
|
| 2923 |
+
"loss": 2.692755126953125,
|
| 2924 |
+
"step": 37400
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.013636363636363636,
|
| 2928 |
+
"grad_norm": 0.1650208979845047,
|
| 2929 |
+
"learning_rate": 0.0007408768370508576,
|
| 2930 |
+
"loss": 2.68127197265625,
|
| 2931 |
+
"step": 37500
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.014545454545454545,
|
| 2935 |
+
"grad_norm": 0.1679512858390808,
|
| 2936 |
+
"learning_rate": 0.0007396227819481021,
|
| 2937 |
+
"loss": 2.697837219238281,
|
| 2938 |
+
"step": 37600
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.015454545454545455,
|
| 2942 |
+
"grad_norm": 0.1745394617319107,
|
| 2943 |
+
"learning_rate": 0.00073836676697459,
|
| 2944 |
+
"loss": 2.6750924682617185,
|
| 2945 |
+
"step": 37700
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.016363636363636365,
|
| 2949 |
+
"grad_norm": 0.14067143201828003,
|
| 2950 |
+
"learning_rate": 0.0007371088024032475,
|
| 2951 |
+
"loss": 2.7095330810546874,
|
| 2952 |
+
"step": 37800
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.017272727272727273,
|
| 2956 |
+
"grad_norm": 0.16379132866859436,
|
| 2957 |
+
"learning_rate": 0.0007358488985229455,
|
| 2958 |
+
"loss": 2.6968374633789063,
|
| 2959 |
+
"step": 37900
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.01818181818181818,
|
| 2963 |
+
"grad_norm": 0.15668943524360657,
|
| 2964 |
+
"learning_rate": 0.000734587065638417,
|
| 2965 |
+
"loss": 2.697041320800781,
|
| 2966 |
+
"step": 38000
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.01818181818181818,
|
| 2970 |
+
"eval_loss": 3.128469467163086,
|
| 2971 |
+
"eval_runtime": 7.47,
|
| 2972 |
+
"eval_samples_per_second": 77.109,
|
| 2973 |
+
"eval_steps_per_second": 19.277,
|
| 2974 |
+
"step": 38000
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 0.019090909090909092,
|
| 2978 |
+
"grad_norm": 0.1642797887325287,
|
| 2979 |
+
"learning_rate": 0.0007333233140701722,
|
| 2980 |
+
"loss": 2.6924237060546874,
|
| 2981 |
+
"step": 38100
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.02,
|
| 2985 |
+
"grad_norm": 0.16816826164722443,
|
| 2986 |
+
"learning_rate": 0.0007320576541544144,
|
| 2987 |
+
"loss": 2.69775634765625,
|
| 2988 |
+
"step": 38200
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 0.02090909090909091,
|
| 2992 |
+
"grad_norm": 0.1469792127609253,
|
| 2993 |
+
"learning_rate": 0.000730790096242955,
|
| 2994 |
+
"loss": 2.6987783813476565,
|
| 2995 |
+
"step": 38300
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 0.02181818181818182,
|
| 2999 |
+
"grad_norm": 0.15169106423854828,
|
| 3000 |
+
"learning_rate": 0.0007295206507031289,
|
| 3001 |
+
"loss": 2.6766021728515623,
|
| 3002 |
+
"step": 38400
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.022727272727272728,
|
| 3006 |
+
"grad_norm": 0.14681929349899292,
|
| 3007 |
+
"learning_rate": 0.0007282493279177103,
|
| 3008 |
+
"loss": 2.691963806152344,
|
| 3009 |
+
"step": 38500
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 0.023636363636363636,
|
| 3013 |
+
"grad_norm": 0.1452484130859375,
|
| 3014 |
+
"learning_rate": 0.000726976138284827,
|
| 3015 |
+
"loss": 2.6880203247070313,
|
| 3016 |
+
"step": 38600
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 0.024545454545454544,
|
| 3020 |
+
"grad_norm": 0.15825141966342926,
|
| 3021 |
+
"learning_rate": 0.0007257010922178762,
|
| 3022 |
+
"loss": 2.65422119140625,
|
| 3023 |
+
"step": 38700
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 0.025454545454545455,
|
| 3027 |
+
"grad_norm": 0.15018871426582336,
|
| 3028 |
+
"learning_rate": 0.000724424200145438,
|
| 3029 |
+
"loss": 2.663526611328125,
|
| 3030 |
+
"step": 38800
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 0.026363636363636363,
|
| 3034 |
+
"grad_norm": 0.16328509151935577,
|
| 3035 |
+
"learning_rate": 0.0007231454725111919,
|
| 3036 |
+
"loss": 2.6569583129882814,
|
| 3037 |
+
"step": 38900
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 0.02727272727272727,
|
| 3041 |
+
"grad_norm": 0.14703254401683807,
|
| 3042 |
+
"learning_rate": 0.0007218649197738298,
|
| 3043 |
+
"loss": 2.69577392578125,
|
| 3044 |
+
"step": 39000
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.02727272727272727,
|
| 3048 |
+
"eval_loss": 3.1291093826293945,
|
| 3049 |
+
"eval_runtime": 7.4103,
|
| 3050 |
+
"eval_samples_per_second": 77.729,
|
| 3051 |
+
"eval_steps_per_second": 19.432,
|
| 3052 |
+
"step": 39000
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"epoch": 0.028181818181818183,
|
| 3056 |
+
"grad_norm": 0.1588928997516632,
|
| 3057 |
+
"learning_rate": 0.0007205825524069714,
|
| 3058 |
+
"loss": 2.6820574951171876,
|
| 3059 |
+
"step": 39100
|
| 3060 |
+
},
|
| 3061 |
+
{
|
| 3062 |
+
"epoch": 0.02909090909090909,
|
| 3063 |
+
"grad_norm": 0.18345706164836884,
|
| 3064 |
+
"learning_rate": 0.0007192983808990781,
|
| 3065 |
+
"loss": 2.7058285522460936,
|
| 3066 |
+
"step": 39200
|
| 3067 |
+
},
|
| 3068 |
+
{
|
| 3069 |
+
"epoch": 0.03,
|
| 3070 |
+
"grad_norm": 0.1431887000799179,
|
| 3071 |
+
"learning_rate": 0.0007180124157533671,
|
| 3072 |
+
"loss": 2.6863577270507815,
|
| 3073 |
+
"step": 39300
|
| 3074 |
+
},
|
| 3075 |
+
{
|
| 3076 |
+
"epoch": 0.03090909090909091,
|
| 3077 |
+
"grad_norm": 0.15360857546329498,
|
| 3078 |
+
"learning_rate": 0.0007167246674877264,
|
| 3079 |
+
"loss": 2.6997265625,
|
| 3080 |
+
"step": 39400
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 0.031818181818181815,
|
| 3084 |
+
"grad_norm": 0.15961426496505737,
|
| 3085 |
+
"learning_rate": 0.0007154351466346273,
|
| 3086 |
+
"loss": 2.66740966796875,
|
| 3087 |
+
"step": 39500
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"epoch": 0.03272727272727273,
|
| 3091 |
+
"grad_norm": 0.15588298439979553,
|
| 3092 |
+
"learning_rate": 0.0007141438637410398,
|
| 3093 |
+
"loss": 2.6652230834960937,
|
| 3094 |
+
"step": 39600
|
| 3095 |
+
},
|
| 3096 |
+
{
|
| 3097 |
+
"epoch": 0.03363636363636364,
|
| 3098 |
+
"grad_norm": 0.1670597940683365,
|
| 3099 |
+
"learning_rate": 0.000712850829368345,
|
| 3100 |
+
"loss": 2.681721496582031,
|
| 3101 |
+
"step": 39700
|
| 3102 |
+
},
|
| 3103 |
+
{
|
| 3104 |
+
"epoch": 0.034545454545454546,
|
| 3105 |
+
"grad_norm": 0.15003304183483124,
|
| 3106 |
+
"learning_rate": 0.0007115560540922497,
|
| 3107 |
+
"loss": 2.6677728271484376,
|
| 3108 |
+
"step": 39800
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"epoch": 0.035454545454545454,
|
| 3112 |
+
"grad_norm": 0.1557546705007553,
|
| 3113 |
+
"learning_rate": 0.0007102595485026993,
|
| 3114 |
+
"loss": 2.6783493041992186,
|
| 3115 |
+
"step": 39900
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"epoch": 0.03636363636363636,
|
| 3119 |
+
"grad_norm": 0.1732822060585022,
|
| 3120 |
+
"learning_rate": 0.0007089613232037915,
|
| 3121 |
+
"loss": 2.6648553466796874,
|
| 3122 |
+
"step": 40000
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 0.03636363636363636,
|
| 3126 |
+
"eval_loss": 3.129150867462158,
|
| 3127 |
+
"eval_runtime": 7.5094,
|
| 3128 |
+
"eval_samples_per_second": 76.703,
|
| 3129 |
+
"eval_steps_per_second": 19.176,
|
| 3130 |
+
"step": 40000
|
| 3131 |
}
|
| 3132 |
],
|
| 3133 |
"logging_steps": 100,
|
|
|
|
| 3147 |
"attributes": {}
|
| 3148 |
}
|
| 3149 |
},
|
| 3150 |
+
"total_flos": 9.9658323984384e+17,
|
| 3151 |
"train_batch_size": 22,
|
| 3152 |
"trial_name": null,
|
| 3153 |
"trial_params": null
|