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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8302b42850bb9a971a92bf21001a99a1b108886f1a1c6d46589b31593094b2b
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56878bd403ec25d1287ace7a734c802826405ce51180d174a63debd4614a56de
|
| 3 |
size 1082379659
|
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:ae2914830368f46e9c6d2b2e5cbe7fbed0fa5772149d7c8cbec7c8589a46483c
|
| 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:a009a4564c35728dfec89ffdf58a6a6918940a3d67f64f03a0ddf9185dba8b9e
|
| 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": 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": 37.393,
|
| 2817 |
"eval_steps_per_second": 9.348,
|
| 2818 |
"step": 36000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2819 |
}
|
| 2820 |
],
|
| 2821 |
"logging_steps": 100,
|
|
@@ -2835,7 +3147,7 @@
|
|
| 2835 |
"attributes": {}
|
| 2836 |
}
|
| 2837 |
},
|
| 2838 |
-
"total_flos": 1.
|
| 2839 |
"train_batch_size": 22,
|
| 2840 |
"trial_name": null,
|
| 2841 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5194805194805194,
|
| 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": 37.393,
|
| 2817 |
"eval_steps_per_second": 9.348,
|
| 2818 |
"step": 36000
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.4688311688311688,
|
| 2822 |
+
"grad_norm": 0.22442568838596344,
|
| 2823 |
+
"learning_rate": 0.0007656575591625415,
|
| 2824 |
+
"loss": 2.7954,
|
| 2825 |
+
"step": 36100
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.4701298701298701,
|
| 2829 |
+
"grad_norm": 0.2147638201713562,
|
| 2830 |
+
"learning_rate": 0.0007644350353789997,
|
| 2831 |
+
"loss": 2.7897,
|
| 2832 |
+
"step": 36200
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.4714285714285714,
|
| 2836 |
+
"grad_norm": 0.20484313368797302,
|
| 2837 |
+
"learning_rate": 0.0007632103129056145,
|
| 2838 |
+
"loss": 2.7859,
|
| 2839 |
+
"step": 36300
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.4727272727272727,
|
| 2843 |
+
"grad_norm": 0.19691170752048492,
|
| 2844 |
+
"learning_rate": 0.0007619834019255482,
|
| 2845 |
+
"loss": 2.8251,
|
| 2846 |
+
"step": 36400
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.474025974025974,
|
| 2850 |
+
"grad_norm": 0.2177974134683609,
|
| 2851 |
+
"learning_rate": 0.0007607543126401597,
|
| 2852 |
+
"loss": 2.7771,
|
| 2853 |
+
"step": 36500
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.4753246753246753,
|
| 2857 |
+
"grad_norm": 0.24122121930122375,
|
| 2858 |
+
"learning_rate": 0.0007595230552689201,
|
| 2859 |
+
"loss": 2.7973,
|
| 2860 |
+
"step": 36600
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 0.4766233766233766,
|
| 2864 |
+
"grad_norm": 0.2524343729019165,
|
| 2865 |
+
"learning_rate": 0.0007582896400493266,
|
| 2866 |
+
"loss": 2.82,
|
| 2867 |
+
"step": 36700
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.4779220779220779,
|
| 2871 |
+
"grad_norm": 0.21695558726787567,
|
| 2872 |
+
"learning_rate": 0.000757054077236819,
|
| 2873 |
+
"loss": 2.802,
|
| 2874 |
+
"step": 36800
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.4792207792207792,
|
| 2878 |
+
"grad_norm": 0.2205599695444107,
|
| 2879 |
+
"learning_rate": 0.0007558163771046934,
|
| 2880 |
+
"loss": 2.7509,
|
| 2881 |
+
"step": 36900
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.4805194805194805,
|
| 2885 |
+
"grad_norm": 0.2173157036304474,
|
| 2886 |
+
"learning_rate": 0.0007545765499440169,
|
| 2887 |
+
"loss": 2.7978,
|
| 2888 |
+
"step": 37000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.4805194805194805,
|
| 2892 |
+
"eval_loss": 3.170949935913086,
|
| 2893 |
+
"eval_runtime": 16.3367,
|
| 2894 |
+
"eval_samples_per_second": 35.258,
|
| 2895 |
+
"eval_steps_per_second": 8.815,
|
| 2896 |
+
"step": 37000
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.4818181818181818,
|
| 2900 |
+
"grad_norm": 0.21395540237426758,
|
| 2901 |
+
"learning_rate": 0.0007533346060635424,
|
| 2902 |
+
"loss": 2.775,
|
| 2903 |
+
"step": 37100
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.4831168831168831,
|
| 2907 |
+
"grad_norm": 0.2262965440750122,
|
| 2908 |
+
"learning_rate": 0.0007520905557896221,
|
| 2909 |
+
"loss": 2.779,
|
| 2910 |
+
"step": 37200
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 0.4844155844155844,
|
| 2914 |
+
"grad_norm": 0.2124248743057251,
|
| 2915 |
+
"learning_rate": 0.0007508444094661227,
|
| 2916 |
+
"loss": 2.8141,
|
| 2917 |
+
"step": 37300
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.4857142857142857,
|
| 2921 |
+
"grad_norm": 0.24149860441684723,
|
| 2922 |
+
"learning_rate": 0.0007495961774543385,
|
| 2923 |
+
"loss": 2.8091,
|
| 2924 |
+
"step": 37400
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.487012987012987,
|
| 2928 |
+
"grad_norm": 0.2356308251619339,
|
| 2929 |
+
"learning_rate": 0.0007483458701329059,
|
| 2930 |
+
"loss": 2.7898,
|
| 2931 |
+
"step": 37500
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.4883116883116883,
|
| 2935 |
+
"grad_norm": 0.21705743670463562,
|
| 2936 |
+
"learning_rate": 0.0007470934978977167,
|
| 2937 |
+
"loss": 2.8022,
|
| 2938 |
+
"step": 37600
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.4896103896103896,
|
| 2942 |
+
"grad_norm": 0.21993373334407806,
|
| 2943 |
+
"learning_rate": 0.0007458390711618315,
|
| 2944 |
+
"loss": 2.7881,
|
| 2945 |
+
"step": 37700
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.4909090909090909,
|
| 2949 |
+
"grad_norm": 0.21296945214271545,
|
| 2950 |
+
"learning_rate": 0.0007445826003553939,
|
| 2951 |
+
"loss": 2.7987,
|
| 2952 |
+
"step": 37800
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.4922077922077922,
|
| 2956 |
+
"grad_norm": 0.23273344337940216,
|
| 2957 |
+
"learning_rate": 0.000743324095925543,
|
| 2958 |
+
"loss": 2.8253,
|
| 2959 |
+
"step": 37900
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.4935064935064935,
|
| 2963 |
+
"grad_norm": 0.2104436457157135,
|
| 2964 |
+
"learning_rate": 0.0007420635683363268,
|
| 2965 |
+
"loss": 2.7807,
|
| 2966 |
+
"step": 38000
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.4935064935064935,
|
| 2970 |
+
"eval_loss": 3.151848316192627,
|
| 2971 |
+
"eval_runtime": 15.3437,
|
| 2972 |
+
"eval_samples_per_second": 37.54,
|
| 2973 |
+
"eval_steps_per_second": 9.385,
|
| 2974 |
+
"step": 38000
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 0.4948051948051948,
|
| 2978 |
+
"grad_norm": 0.2078818380832672,
|
| 2979 |
+
"learning_rate": 0.0007408010280686151,
|
| 2980 |
+
"loss": 2.7504,
|
| 2981 |
+
"step": 38100
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.4961038961038961,
|
| 2985 |
+
"grad_norm": 0.22127191722393036,
|
| 2986 |
+
"learning_rate": 0.0007395364856200127,
|
| 2987 |
+
"loss": 2.7698,
|
| 2988 |
+
"step": 38200
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 0.4974025974025974,
|
| 2992 |
+
"grad_norm": 0.20785515010356903,
|
| 2993 |
+
"learning_rate": 0.0007382699515047715,
|
| 2994 |
+
"loss": 2.804,
|
| 2995 |
+
"step": 38300
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 0.4987012987012987,
|
| 2999 |
+
"grad_norm": 0.267839640378952,
|
| 3000 |
+
"learning_rate": 0.0007370014362537041,
|
| 3001 |
+
"loss": 2.778,
|
| 3002 |
+
"step": 38400
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.5,
|
| 3006 |
+
"grad_norm": 0.22827385365962982,
|
| 3007 |
+
"learning_rate": 0.0007357309504140948,
|
| 3008 |
+
"loss": 2.7786,
|
| 3009 |
+
"step": 38500
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 0.5012987012987012,
|
| 3013 |
+
"grad_norm": 0.22568035125732422,
|
| 3014 |
+
"learning_rate": 0.0007344585045496133,
|
| 3015 |
+
"loss": 2.7655,
|
| 3016 |
+
"step": 38600
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 0.5025974025974026,
|
| 3020 |
+
"grad_norm": 0.2355123907327652,
|
| 3021 |
+
"learning_rate": 0.000733184109240226,
|
| 3022 |
+
"loss": 2.7714,
|
| 3023 |
+
"step": 38700
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 0.5038961038961038,
|
| 3027 |
+
"grad_norm": 0.2227976769208908,
|
| 3028 |
+
"learning_rate": 0.0007319077750821084,
|
| 3029 |
+
"loss": 2.7534,
|
| 3030 |
+
"step": 38800
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 0.5051948051948052,
|
| 3034 |
+
"grad_norm": 0.25165653228759766,
|
| 3035 |
+
"learning_rate": 0.0007306295126875566,
|
| 3036 |
+
"loss": 2.7832,
|
| 3037 |
+
"step": 38900
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 0.5064935064935064,
|
| 3041 |
+
"grad_norm": 0.24306100606918335,
|
| 3042 |
+
"learning_rate": 0.0007293493326848997,
|
| 3043 |
+
"loss": 2.774,
|
| 3044 |
+
"step": 39000
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.5064935064935064,
|
| 3048 |
+
"eval_loss": 3.1421139240264893,
|
| 3049 |
+
"eval_runtime": 15.2375,
|
| 3050 |
+
"eval_samples_per_second": 37.801,
|
| 3051 |
+
"eval_steps_per_second": 9.45,
|
| 3052 |
+
"step": 39000
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"epoch": 0.5077922077922078,
|
| 3056 |
+
"grad_norm": 0.23936377465724945,
|
| 3057 |
+
"learning_rate": 0.0007280672457184108,
|
| 3058 |
+
"loss": 2.7569,
|
| 3059 |
+
"step": 39100
|
| 3060 |
+
},
|
| 3061 |
+
{
|
| 3062 |
+
"epoch": 0.509090909090909,
|
| 3063 |
+
"grad_norm": 0.2100268453359604,
|
| 3064 |
+
"learning_rate": 0.0007267832624482191,
|
| 3065 |
+
"loss": 2.7524,
|
| 3066 |
+
"step": 39200
|
| 3067 |
+
},
|
| 3068 |
+
{
|
| 3069 |
+
"epoch": 0.5103896103896104,
|
| 3070 |
+
"grad_norm": 0.21765153110027313,
|
| 3071 |
+
"learning_rate": 0.0007254973935502207,
|
| 3072 |
+
"loss": 2.7636,
|
| 3073 |
+
"step": 39300
|
| 3074 |
+
},
|
| 3075 |
+
{
|
| 3076 |
+
"epoch": 0.5116883116883116,
|
| 3077 |
+
"grad_norm": 0.22430171072483063,
|
| 3078 |
+
"learning_rate": 0.0007242096497159902,
|
| 3079 |
+
"loss": 2.7875,
|
| 3080 |
+
"step": 39400
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 0.512987012987013,
|
| 3084 |
+
"grad_norm": 0.23513422906398773,
|
| 3085 |
+
"learning_rate": 0.0007229200416526911,
|
| 3086 |
+
"loss": 2.7606,
|
| 3087 |
+
"step": 39500
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"epoch": 0.5142857142857142,
|
| 3091 |
+
"grad_norm": 0.24426428973674774,
|
| 3092 |
+
"learning_rate": 0.0007216285800829885,
|
| 3093 |
+
"loss": 2.7867,
|
| 3094 |
+
"step": 39600
|
| 3095 |
+
},
|
| 3096 |
+
{
|
| 3097 |
+
"epoch": 0.5155844155844156,
|
| 3098 |
+
"grad_norm": 0.313528835773468,
|
| 3099 |
+
"learning_rate": 0.0007203352757449577,
|
| 3100 |
+
"loss": 2.7645,
|
| 3101 |
+
"step": 39700
|
| 3102 |
+
},
|
| 3103 |
+
{
|
| 3104 |
+
"epoch": 0.5168831168831168,
|
| 3105 |
+
"grad_norm": 0.23338325321674347,
|
| 3106 |
+
"learning_rate": 0.0007190401393919968,
|
| 3107 |
+
"loss": 2.7358,
|
| 3108 |
+
"step": 39800
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"epoch": 0.5181818181818182,
|
| 3112 |
+
"grad_norm": 0.2229086011648178,
|
| 3113 |
+
"learning_rate": 0.0007177431817927358,
|
| 3114 |
+
"loss": 2.7574,
|
| 3115 |
+
"step": 39900
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"epoch": 0.5194805194805194,
|
| 3119 |
+
"grad_norm": 0.22037512063980103,
|
| 3120 |
+
"learning_rate": 0.000716444413730948,
|
| 3121 |
+
"loss": 2.7507,
|
| 3122 |
+
"step": 40000
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 0.5194805194805194,
|
| 3126 |
+
"eval_loss": 3.1465635299682617,
|
| 3127 |
+
"eval_runtime": 15.78,
|
| 3128 |
+
"eval_samples_per_second": 36.502,
|
| 3129 |
+
"eval_steps_per_second": 9.125,
|
| 3130 |
+
"step": 40000
|
| 3131 |
}
|
| 3132 |
],
|
| 3133 |
"logging_steps": 100,
|
|
|
|
| 3147 |
"attributes": {}
|
| 3148 |
}
|
| 3149 |
},
|
| 3150 |
+
"total_flos": 1.1907725524992e+18,
|
| 3151 |
"train_batch_size": 22,
|
| 3152 |
"trial_name": null,
|
| 3153 |
"trial_params": null
|