Training in progress, step 150000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -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 50044689
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23bcf588931894b4b3e5c35722962c0de8f54f9d9596c1f09a2a4e5a7a2d9f29
|
3 |
size 50044689
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25761253
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80d9dd260c6a1eea214a50fb35a68c126c97cfb31dd7f81eeaee885739a9a21c
|
3 |
size 25761253
|
last-checkpoint/rng_state_0.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_1.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_2.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_3.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_4.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_5.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_6.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/rng_state_7.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 sha256:979f2083c322d2f1d58623c944daa2f548e1e3a498ad6f148608a638e1a6db3c
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:684030441e546f328363202be7e7a1e6d60b5494506eab9e81487ca712343e2e
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2806,11 +2806,211 @@
|
|
2806 |
"eval_samples_per_second": 1031.628,
|
2807 |
"eval_steps_per_second": 16.168,
|
2808 |
"step": 140000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2809 |
}
|
2810 |
],
|
2811 |
"max_steps": 250000,
|
2812 |
"num_train_epochs": 12,
|
2813 |
-
"total_flos": 2.
|
2814 |
"trial_name": null,
|
2815 |
"trial_params": null
|
2816 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.691648822269808,
|
5 |
+
"global_step": 150000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2806 |
"eval_samples_per_second": 1031.628,
|
2807 |
"eval_steps_per_second": 16.168,
|
2808 |
"step": 140000
|
2809 |
+
},
|
2810 |
+
{
|
2811 |
+
"epoch": 6.27,
|
2812 |
+
"learning_rate": 0.00026899475121297924,
|
2813 |
+
"loss": 0.3815,
|
2814 |
+
"step": 140500
|
2815 |
+
},
|
2816 |
+
{
|
2817 |
+
"epoch": 6.29,
|
2818 |
+
"learning_rate": 0.00026705904531820914,
|
2819 |
+
"loss": 0.3815,
|
2820 |
+
"step": 141000
|
2821 |
+
},
|
2822 |
+
{
|
2823 |
+
"epoch": 6.29,
|
2824 |
+
"eval_loss": 0.3550131618976593,
|
2825 |
+
"eval_runtime": 2.1731,
|
2826 |
+
"eval_samples_per_second": 1057.017,
|
2827 |
+
"eval_steps_per_second": 16.566,
|
2828 |
+
"step": 141000
|
2829 |
+
},
|
2830 |
+
{
|
2831 |
+
"epoch": 6.31,
|
2832 |
+
"learning_rate": 0.0002651249990837085,
|
2833 |
+
"loss": 0.3813,
|
2834 |
+
"step": 141500
|
2835 |
+
},
|
2836 |
+
{
|
2837 |
+
"epoch": 6.33,
|
2838 |
+
"learning_rate": 0.00026319269711092485,
|
2839 |
+
"loss": 0.3812,
|
2840 |
+
"step": 142000
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 6.33,
|
2844 |
+
"eval_loss": 0.3538789749145508,
|
2845 |
+
"eval_runtime": 2.1483,
|
2846 |
+
"eval_samples_per_second": 1069.198,
|
2847 |
+
"eval_steps_per_second": 16.757,
|
2848 |
+
"step": 142000
|
2849 |
+
},
|
2850 |
+
{
|
2851 |
+
"epoch": 6.36,
|
2852 |
+
"learning_rate": 0.0002612622239250066,
|
2853 |
+
"loss": 0.3809,
|
2854 |
+
"step": 142500
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 6.38,
|
2858 |
+
"learning_rate": 0.0002593336639711046,
|
2859 |
+
"loss": 0.3806,
|
2860 |
+
"step": 143000
|
2861 |
+
},
|
2862 |
+
{
|
2863 |
+
"epoch": 6.38,
|
2864 |
+
"eval_loss": 0.35349225997924805,
|
2865 |
+
"eval_runtime": 2.1799,
|
2866 |
+
"eval_samples_per_second": 1053.718,
|
2867 |
+
"eval_steps_per_second": 16.515,
|
2868 |
+
"step": 143000
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 6.4,
|
2872 |
+
"learning_rate": 0.000257407101610679,
|
2873 |
+
"loss": 0.3805,
|
2874 |
+
"step": 143500
|
2875 |
+
},
|
2876 |
+
{
|
2877 |
+
"epoch": 6.42,
|
2878 |
+
"learning_rate": 0.00025548262111780846,
|
2879 |
+
"loss": 0.3804,
|
2880 |
+
"step": 144000
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 6.42,
|
2884 |
+
"eval_loss": 0.3532736003398895,
|
2885 |
+
"eval_runtime": 2.2355,
|
2886 |
+
"eval_samples_per_second": 1027.515,
|
2887 |
+
"eval_steps_per_second": 16.104,
|
2888 |
+
"step": 144000
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 6.45,
|
2892 |
+
"learning_rate": 0.0002535603066755043,
|
2893 |
+
"loss": 0.3803,
|
2894 |
+
"step": 144500
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 6.47,
|
2898 |
+
"learning_rate": 0.00025164024237202764,
|
2899 |
+
"loss": 0.3799,
|
2900 |
+
"step": 145000
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 6.47,
|
2904 |
+
"eval_loss": 0.3539290130138397,
|
2905 |
+
"eval_runtime": 2.1927,
|
2906 |
+
"eval_samples_per_second": 1047.568,
|
2907 |
+
"eval_steps_per_second": 16.418,
|
2908 |
+
"step": 145000
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 6.49,
|
2912 |
+
"learning_rate": 0.00024972251219721115,
|
2913 |
+
"loss": 0.38,
|
2914 |
+
"step": 145500
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 6.51,
|
2918 |
+
"learning_rate": 0.00024780720003878557,
|
2919 |
+
"loss": 0.3799,
|
2920 |
+
"step": 146000
|
2921 |
+
},
|
2922 |
+
{
|
2923 |
+
"epoch": 6.51,
|
2924 |
+
"eval_loss": 0.3527817726135254,
|
2925 |
+
"eval_runtime": 2.1772,
|
2926 |
+
"eval_samples_per_second": 1055.009,
|
2927 |
+
"eval_steps_per_second": 16.535,
|
2928 |
+
"step": 146000
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 6.54,
|
2932 |
+
"learning_rate": 0.00024589438967870925,
|
2933 |
+
"loss": 0.3795,
|
2934 |
+
"step": 146500
|
2935 |
+
},
|
2936 |
+
{
|
2937 |
+
"epoch": 6.56,
|
2938 |
+
"learning_rate": 0.00024398416478950394,
|
2939 |
+
"loss": 0.3794,
|
2940 |
+
"step": 147000
|
2941 |
+
},
|
2942 |
+
{
|
2943 |
+
"epoch": 6.56,
|
2944 |
+
"eval_loss": 0.3519304692745209,
|
2945 |
+
"eval_runtime": 2.1956,
|
2946 |
+
"eval_samples_per_second": 1046.2,
|
2947 |
+
"eval_steps_per_second": 16.397,
|
2948 |
+
"step": 147000
|
2949 |
+
},
|
2950 |
+
{
|
2951 |
+
"epoch": 6.58,
|
2952 |
+
"learning_rate": 0.00024207660893059467,
|
2953 |
+
"loss": 0.3793,
|
2954 |
+
"step": 147500
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 6.6,
|
2958 |
+
"learning_rate": 0.0002401718055446543,
|
2959 |
+
"loss": 0.3792,
|
2960 |
+
"step": 148000
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 6.6,
|
2964 |
+
"eval_loss": 0.3501195013523102,
|
2965 |
+
"eval_runtime": 2.1687,
|
2966 |
+
"eval_samples_per_second": 1059.172,
|
2967 |
+
"eval_steps_per_second": 16.6,
|
2968 |
+
"step": 148000
|
2969 |
+
},
|
2970 |
+
{
|
2971 |
+
"epoch": 6.62,
|
2972 |
+
"learning_rate": 0.00023826983795395364,
|
2973 |
+
"loss": 0.379,
|
2974 |
+
"step": 148500
|
2975 |
+
},
|
2976 |
+
{
|
2977 |
+
"epoch": 6.65,
|
2978 |
+
"learning_rate": 0.00023637078935671656,
|
2979 |
+
"loss": 0.3791,
|
2980 |
+
"step": 149000
|
2981 |
+
},
|
2982 |
+
{
|
2983 |
+
"epoch": 6.65,
|
2984 |
+
"eval_loss": 0.35130566358566284,
|
2985 |
+
"eval_runtime": 2.1713,
|
2986 |
+
"eval_samples_per_second": 1057.877,
|
2987 |
+
"eval_steps_per_second": 16.58,
|
2988 |
+
"step": 149000
|
2989 |
+
},
|
2990 |
+
{
|
2991 |
+
"epoch": 6.67,
|
2992 |
+
"learning_rate": 0.00023447474282348085,
|
2993 |
+
"loss": 0.3787,
|
2994 |
+
"step": 149500
|
2995 |
+
},
|
2996 |
+
{
|
2997 |
+
"epoch": 6.69,
|
2998 |
+
"learning_rate": 0.00023258178129346424,
|
2999 |
+
"loss": 0.3784,
|
3000 |
+
"step": 150000
|
3001 |
+
},
|
3002 |
+
{
|
3003 |
+
"epoch": 6.69,
|
3004 |
+
"eval_loss": 0.35110124945640564,
|
3005 |
+
"eval_runtime": 2.1647,
|
3006 |
+
"eval_samples_per_second": 1061.094,
|
3007 |
+
"eval_steps_per_second": 16.63,
|
3008 |
+
"step": 150000
|
3009 |
}
|
3010 |
],
|
3011 |
"max_steps": 250000,
|
3012 |
"num_train_epochs": 12,
|
3013 |
+
"total_flos": 2.40247725109402e+21,
|
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 25761253
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80d9dd260c6a1eea214a50fb35a68c126c97cfb31dd7f81eeaee885739a9a21c
|
3 |
size 25761253
|