End of training
Browse files
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_cer": 0.1969102547256584,
|
| 4 |
"eval_loss": 0.9162458181381226,
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 481,
|
| 7 |
-
"eval_samples_per_second": 10.
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
"eval_wer": 0.5156036834924966,
|
| 10 |
-
"train_loss": 0.
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 2528,
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second": 2.
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 63.29,
|
| 3 |
"eval_cer": 0.1969102547256584,
|
| 4 |
"eval_loss": 0.9162458181381226,
|
| 5 |
+
"eval_runtime": 44.5084,
|
| 6 |
"eval_samples": 481,
|
| 7 |
+
"eval_samples_per_second": 10.807,
|
| 8 |
+
"eval_steps_per_second": 1.371,
|
| 9 |
"eval_wer": 0.5156036834924966,
|
| 10 |
+
"train_loss": 0.05515483856201172,
|
| 11 |
+
"train_runtime": 2237.6776,
|
| 12 |
"train_samples": 2528,
|
| 13 |
+
"train_samples_per_second": 71.503,
|
| 14 |
+
"train_steps_per_second": 2.234
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_cer": 0.1969102547256584,
|
| 4 |
"eval_loss": 0.9162458181381226,
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 481,
|
| 7 |
-
"eval_samples_per_second": 10.
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
"eval_wer": 0.5156036834924966
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 63.29,
|
| 3 |
"eval_cer": 0.1969102547256584,
|
| 4 |
"eval_loss": 0.9162458181381226,
|
| 5 |
+
"eval_runtime": 44.5084,
|
| 6 |
"eval_samples": 481,
|
| 7 |
+
"eval_samples_per_second": 10.807,
|
| 8 |
+
"eval_steps_per_second": 1.371,
|
| 9 |
"eval_wer": 0.5156036834924966
|
| 10 |
}
|
runs/Dec16_15-39-46_129-146-104-29/events.out.tfevents.1671207700.129-146-104-29.131763.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f83a25a085a2175f629e030fb53b3c3b594db36c16ed1ac8ad53615b96a60088
|
| 3 |
+
size 405
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 2528,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 63.29,
|
| 3 |
+
"train_loss": 0.05515483856201172,
|
| 4 |
+
"train_runtime": 2237.6776,
|
| 5 |
"train_samples": 2528,
|
| 6 |
+
"train_samples_per_second": 71.503,
|
| 7 |
+
"train_steps_per_second": 2.234
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9162458181381226,
|
| 3 |
"best_model_checkpoint": "./checkpoint-4000",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2798,18 +2798,328 @@
|
|
| 2798 |
"step": 4500
|
| 2799 |
},
|
| 2800 |
{
|
| 2801 |
-
"epoch":
|
| 2802 |
-
"
|
| 2803 |
-
"
|
| 2804 |
-
"
|
| 2805 |
-
|
| 2806 |
-
|
| 2807 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2808 |
}
|
| 2809 |
],
|
| 2810 |
-
"max_steps":
|
| 2811 |
-
"num_train_epochs":
|
| 2812 |
-
"total_flos": 5.
|
| 2813 |
"trial_name": null,
|
| 2814 |
"trial_params": null
|
| 2815 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9162458181381226,
|
| 3 |
"best_model_checkpoint": "./checkpoint-4000",
|
| 4 |
+
"epoch": 63.29113924050633,
|
| 5 |
+
"global_step": 5000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2798 |
"step": 4500
|
| 2799 |
},
|
| 2800 |
{
|
| 2801 |
+
"epoch": 57.09,
|
| 2802 |
+
"learning_rate": 1.2299999999999999e-05,
|
| 2803 |
+
"loss": 0.5852,
|
| 2804 |
+
"step": 4510
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 57.22,
|
| 2808 |
+
"learning_rate": 1.205e-05,
|
| 2809 |
+
"loss": 0.5752,
|
| 2810 |
+
"step": 4520
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 57.34,
|
| 2814 |
+
"learning_rate": 1.1799999999999999e-05,
|
| 2815 |
+
"loss": 0.5433,
|
| 2816 |
+
"step": 4530
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 57.47,
|
| 2820 |
+
"learning_rate": 1.155e-05,
|
| 2821 |
+
"loss": 0.5648,
|
| 2822 |
+
"step": 4540
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 57.59,
|
| 2826 |
+
"learning_rate": 1.1299999999999999e-05,
|
| 2827 |
+
"loss": 0.5704,
|
| 2828 |
+
"step": 4550
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"epoch": 57.72,
|
| 2832 |
+
"learning_rate": 1.105e-05,
|
| 2833 |
+
"loss": 0.5216,
|
| 2834 |
+
"step": 4560
|
| 2835 |
+
},
|
| 2836 |
+
{
|
| 2837 |
+
"epoch": 57.85,
|
| 2838 |
+
"learning_rate": 1.0799999999999998e-05,
|
| 2839 |
+
"loss": 0.5998,
|
| 2840 |
+
"step": 4570
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 57.97,
|
| 2844 |
+
"learning_rate": 1.0549999999999999e-05,
|
| 2845 |
+
"loss": 0.5439,
|
| 2846 |
+
"step": 4580
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 58.1,
|
| 2850 |
+
"learning_rate": 1.03e-05,
|
| 2851 |
+
"loss": 0.5679,
|
| 2852 |
+
"step": 4590
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 58.23,
|
| 2856 |
+
"learning_rate": 1.005e-05,
|
| 2857 |
+
"loss": 0.5621,
|
| 2858 |
+
"step": 4600
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 58.35,
|
| 2862 |
+
"learning_rate": 9.799999999999998e-06,
|
| 2863 |
+
"loss": 0.5557,
|
| 2864 |
+
"step": 4610
|
| 2865 |
+
},
|
| 2866 |
+
{
|
| 2867 |
+
"epoch": 58.48,
|
| 2868 |
+
"learning_rate": 9.549999999999998e-06,
|
| 2869 |
+
"loss": 0.5525,
|
| 2870 |
+
"step": 4620
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 58.61,
|
| 2874 |
+
"learning_rate": 9.299999999999999e-06,
|
| 2875 |
+
"loss": 0.6033,
|
| 2876 |
+
"step": 4630
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 58.73,
|
| 2880 |
+
"learning_rate": 9.05e-06,
|
| 2881 |
+
"loss": 0.5059,
|
| 2882 |
+
"step": 4640
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 58.86,
|
| 2886 |
+
"learning_rate": 8.799999999999999e-06,
|
| 2887 |
+
"loss": 0.5362,
|
| 2888 |
+
"step": 4650
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 58.99,
|
| 2892 |
+
"learning_rate": 8.55e-06,
|
| 2893 |
+
"loss": 0.535,
|
| 2894 |
+
"step": 4660
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 59.11,
|
| 2898 |
+
"learning_rate": 8.299999999999998e-06,
|
| 2899 |
+
"loss": 0.586,
|
| 2900 |
+
"step": 4670
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 59.24,
|
| 2904 |
+
"learning_rate": 8.05e-06,
|
| 2905 |
+
"loss": 0.55,
|
| 2906 |
+
"step": 4680
|
| 2907 |
+
},
|
| 2908 |
+
{
|
| 2909 |
+
"epoch": 59.37,
|
| 2910 |
+
"learning_rate": 7.799999999999998e-06,
|
| 2911 |
+
"loss": 0.582,
|
| 2912 |
+
"step": 4690
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 59.49,
|
| 2916 |
+
"learning_rate": 7.55e-06,
|
| 2917 |
+
"loss": 0.5065,
|
| 2918 |
+
"step": 4700
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 59.62,
|
| 2922 |
+
"learning_rate": 7.299999999999999e-06,
|
| 2923 |
+
"loss": 0.5715,
|
| 2924 |
+
"step": 4710
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 59.75,
|
| 2928 |
+
"learning_rate": 7.049999999999999e-06,
|
| 2929 |
+
"loss": 0.5359,
|
| 2930 |
+
"step": 4720
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 59.87,
|
| 2934 |
+
"learning_rate": 6.8e-06,
|
| 2935 |
+
"loss": 0.5535,
|
| 2936 |
+
"step": 4730
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 60.0,
|
| 2940 |
+
"learning_rate": 6.549999999999999e-06,
|
| 2941 |
+
"loss": 0.5256,
|
| 2942 |
+
"step": 4740
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 60.13,
|
| 2946 |
+
"learning_rate": 6.3e-06,
|
| 2947 |
+
"loss": 0.5869,
|
| 2948 |
+
"step": 4750
|
| 2949 |
+
},
|
| 2950 |
+
{
|
| 2951 |
+
"epoch": 60.25,
|
| 2952 |
+
"learning_rate": 6.05e-06,
|
| 2953 |
+
"loss": 0.4978,
|
| 2954 |
+
"step": 4760
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 60.38,
|
| 2958 |
+
"learning_rate": 5.7999999999999995e-06,
|
| 2959 |
+
"loss": 0.5402,
|
| 2960 |
+
"step": 4770
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 60.51,
|
| 2964 |
+
"learning_rate": 5.549999999999999e-06,
|
| 2965 |
+
"loss": 0.5607,
|
| 2966 |
+
"step": 4780
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 60.63,
|
| 2970 |
+
"learning_rate": 5.3e-06,
|
| 2971 |
+
"loss": 0.5583,
|
| 2972 |
+
"step": 4790
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 60.76,
|
| 2976 |
+
"learning_rate": 5.049999999999999e-06,
|
| 2977 |
+
"loss": 0.5382,
|
| 2978 |
+
"step": 4800
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 60.89,
|
| 2982 |
+
"learning_rate": 4.8e-06,
|
| 2983 |
+
"loss": 0.5498,
|
| 2984 |
+
"step": 4810
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 61.01,
|
| 2988 |
+
"learning_rate": 4.55e-06,
|
| 2989 |
+
"loss": 0.5443,
|
| 2990 |
+
"step": 4820
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 61.14,
|
| 2994 |
+
"learning_rate": 4.2999999999999995e-06,
|
| 2995 |
+
"loss": 0.5579,
|
| 2996 |
+
"step": 4830
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"epoch": 61.27,
|
| 3000 |
+
"learning_rate": 4.049999999999999e-06,
|
| 3001 |
+
"loss": 0.517,
|
| 3002 |
+
"step": 4840
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 61.39,
|
| 3006 |
+
"learning_rate": 3.7999999999999996e-06,
|
| 3007 |
+
"loss": 0.566,
|
| 3008 |
+
"step": 4850
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 61.52,
|
| 3012 |
+
"learning_rate": 3.5499999999999995e-06,
|
| 3013 |
+
"loss": 0.572,
|
| 3014 |
+
"step": 4860
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 61.65,
|
| 3018 |
+
"learning_rate": 3.2999999999999993e-06,
|
| 3019 |
+
"loss": 0.5425,
|
| 3020 |
+
"step": 4870
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 61.77,
|
| 3024 |
+
"learning_rate": 3.0499999999999996e-06,
|
| 3025 |
+
"loss": 0.5617,
|
| 3026 |
+
"step": 4880
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 61.9,
|
| 3030 |
+
"learning_rate": 2.8e-06,
|
| 3031 |
+
"loss": 0.5352,
|
| 3032 |
+
"step": 4890
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 62.03,
|
| 3036 |
+
"learning_rate": 2.55e-06,
|
| 3037 |
+
"loss": 0.5328,
|
| 3038 |
+
"step": 4900
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 62.15,
|
| 3042 |
+
"learning_rate": 2.2999999999999996e-06,
|
| 3043 |
+
"loss": 0.567,
|
| 3044 |
+
"step": 4910
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 62.28,
|
| 3048 |
+
"learning_rate": 2.05e-06,
|
| 3049 |
+
"loss": 0.554,
|
| 3050 |
+
"step": 4920
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 62.41,
|
| 3054 |
+
"learning_rate": 1.8e-06,
|
| 3055 |
+
"loss": 0.5846,
|
| 3056 |
+
"step": 4930
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 62.53,
|
| 3060 |
+
"learning_rate": 1.5499999999999998e-06,
|
| 3061 |
+
"loss": 0.5451,
|
| 3062 |
+
"step": 4940
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 62.66,
|
| 3066 |
+
"learning_rate": 1.2999999999999998e-06,
|
| 3067 |
+
"loss": 0.5251,
|
| 3068 |
+
"step": 4950
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 62.78,
|
| 3072 |
+
"learning_rate": 1.05e-06,
|
| 3073 |
+
"loss": 0.5373,
|
| 3074 |
+
"step": 4960
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 62.91,
|
| 3078 |
+
"learning_rate": 7.999999999999999e-07,
|
| 3079 |
+
"loss": 0.5245,
|
| 3080 |
+
"step": 4970
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 63.04,
|
| 3084 |
+
"learning_rate": 5.499999999999999e-07,
|
| 3085 |
+
"loss": 0.5535,
|
| 3086 |
+
"step": 4980
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 63.16,
|
| 3090 |
+
"learning_rate": 3e-07,
|
| 3091 |
+
"loss": 0.545,
|
| 3092 |
+
"step": 4990
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 63.29,
|
| 3096 |
+
"learning_rate": 4.999999999999999e-08,
|
| 3097 |
+
"loss": 0.5462,
|
| 3098 |
+
"step": 5000
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 63.29,
|
| 3102 |
+
"eval_cer": 0.19739830683460666,
|
| 3103 |
+
"eval_loss": 0.9370450973510742,
|
| 3104 |
+
"eval_runtime": 45.0983,
|
| 3105 |
+
"eval_samples_per_second": 10.666,
|
| 3106 |
+
"eval_steps_per_second": 1.353,
|
| 3107 |
+
"eval_wer": 0.5138130968622101,
|
| 3108 |
+
"step": 5000
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"epoch": 63.29,
|
| 3112 |
+
"step": 5000,
|
| 3113 |
+
"total_flos": 5.7547597013827174e+19,
|
| 3114 |
+
"train_loss": 0.05515483856201172,
|
| 3115 |
+
"train_runtime": 2237.6776,
|
| 3116 |
+
"train_samples_per_second": 71.503,
|
| 3117 |
+
"train_steps_per_second": 2.234
|
| 3118 |
}
|
| 3119 |
],
|
| 3120 |
+
"max_steps": 5000,
|
| 3121 |
+
"num_train_epochs": 64,
|
| 3122 |
+
"total_flos": 5.7547597013827174e+19,
|
| 3123 |
"trial_name": null,
|
| 3124 |
"trial_params": null
|
| 3125 |
}
|