Training in progress, step 4500, 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 4523108832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1624c331cced81a7012c8d1cc6b1be61118e9d65f503b7293e0446f0b6b6ee2f
|
| 3 |
size 4523108832
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2912179275
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:209c881dbd9c5cf9e52717d9e1581e29951c8f14cf70cf29a383d1530d76031c
|
| 3 |
size 2912179275
|
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:b928d2d8033ac6bd87c58a39b741faace8bd1c6b0d070b7fad23c19520ff9f1a
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
|
| 3 |
size 1383
|
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:b3727413c550712d2e401a12c98c8e285d7670b8b8893b22f8625667aaba1e73
|
| 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 +2808,356 @@
|
|
| 2808 |
"learning_rate": 0.00012001999999999999,
|
| 2809 |
"loss": 0.04216248393058777,
|
| 2810 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2811 |
}
|
| 2812 |
],
|
| 2813 |
"logging_steps": 10,
|
|
@@ -2827,7 +3177,7 @@
|
|
| 2827 |
"attributes": {}
|
| 2828 |
}
|
| 2829 |
},
|
| 2830 |
-
"total_flos": 3.
|
| 2831 |
"train_batch_size": 1,
|
| 2832 |
"trial_name": null,
|
| 2833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.0004,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2808 |
"learning_rate": 0.00012001999999999999,
|
| 2809 |
"loss": 0.04216248393058777,
|
| 2810 |
"step": 4000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 7.0138,
|
| 2814 |
+
"grad_norm": 0.20787842571735382,
|
| 2815 |
+
"learning_rate": 0.00011982,
|
| 2816 |
+
"loss": 0.04524537920951843,
|
| 2817 |
+
"step": 4010
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 7.0148,
|
| 2821 |
+
"grad_norm": 0.22596226632595062,
|
| 2822 |
+
"learning_rate": 0.00011962,
|
| 2823 |
+
"loss": 0.04263944923877716,
|
| 2824 |
+
"step": 4020
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 7.0158,
|
| 2828 |
+
"grad_norm": 0.2565840780735016,
|
| 2829 |
+
"learning_rate": 0.00011942,
|
| 2830 |
+
"loss": 0.07590364217758179,
|
| 2831 |
+
"step": 4030
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 7.0168,
|
| 2835 |
+
"grad_norm": 0.21802914142608643,
|
| 2836 |
+
"learning_rate": 0.00011922,
|
| 2837 |
+
"loss": 0.04318772554397583,
|
| 2838 |
+
"step": 4040
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 7.0178,
|
| 2842 |
+
"grad_norm": 0.24467627704143524,
|
| 2843 |
+
"learning_rate": 0.00011902,
|
| 2844 |
+
"loss": 0.04431358277797699,
|
| 2845 |
+
"step": 4050
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 7.0188,
|
| 2849 |
+
"grad_norm": 0.18366847932338715,
|
| 2850 |
+
"learning_rate": 0.00011882,
|
| 2851 |
+
"loss": 0.0405062198638916,
|
| 2852 |
+
"step": 4060
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 7.0198,
|
| 2856 |
+
"grad_norm": 0.1755930334329605,
|
| 2857 |
+
"learning_rate": 0.00011862,
|
| 2858 |
+
"loss": 0.03957487344741821,
|
| 2859 |
+
"step": 4070
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 7.0208,
|
| 2863 |
+
"grad_norm": 0.2335081398487091,
|
| 2864 |
+
"learning_rate": 0.00011842,
|
| 2865 |
+
"loss": 0.04518919289112091,
|
| 2866 |
+
"step": 4080
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 7.0218,
|
| 2870 |
+
"grad_norm": 0.21695205569267273,
|
| 2871 |
+
"learning_rate": 0.00011822,
|
| 2872 |
+
"loss": 0.03841679692268372,
|
| 2873 |
+
"step": 4090
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 7.0228,
|
| 2877 |
+
"grad_norm": 0.21446512639522552,
|
| 2878 |
+
"learning_rate": 0.00011802,
|
| 2879 |
+
"loss": 0.04169888198375702,
|
| 2880 |
+
"step": 4100
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 7.0238,
|
| 2884 |
+
"grad_norm": 0.2171398401260376,
|
| 2885 |
+
"learning_rate": 0.00011782,
|
| 2886 |
+
"loss": 0.04906872808933258,
|
| 2887 |
+
"step": 4110
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 7.0248,
|
| 2891 |
+
"grad_norm": 0.20123597979545593,
|
| 2892 |
+
"learning_rate": 0.00011762,
|
| 2893 |
+
"loss": 0.03715299665927887,
|
| 2894 |
+
"step": 4120
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 7.0258,
|
| 2898 |
+
"grad_norm": 0.18073002994060516,
|
| 2899 |
+
"learning_rate": 0.00011742,
|
| 2900 |
+
"loss": 0.03863258361816406,
|
| 2901 |
+
"step": 4130
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 7.0268,
|
| 2905 |
+
"grad_norm": 0.19887232780456543,
|
| 2906 |
+
"learning_rate": 0.00011721999999999999,
|
| 2907 |
+
"loss": 0.040367615222930905,
|
| 2908 |
+
"step": 4140
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 7.0278,
|
| 2912 |
+
"grad_norm": 0.19514504075050354,
|
| 2913 |
+
"learning_rate": 0.00011702,
|
| 2914 |
+
"loss": 0.039677688479423524,
|
| 2915 |
+
"step": 4150
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 7.0288,
|
| 2919 |
+
"grad_norm": 0.22709649801254272,
|
| 2920 |
+
"learning_rate": 0.00011682,
|
| 2921 |
+
"loss": 0.03945083320140839,
|
| 2922 |
+
"step": 4160
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 7.0298,
|
| 2926 |
+
"grad_norm": 0.18606211245059967,
|
| 2927 |
+
"learning_rate": 0.00011661999999999999,
|
| 2928 |
+
"loss": 0.04064054489135742,
|
| 2929 |
+
"step": 4170
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 7.0308,
|
| 2933 |
+
"grad_norm": 0.21493422985076904,
|
| 2934 |
+
"learning_rate": 0.00011642,
|
| 2935 |
+
"loss": 0.04021798074245453,
|
| 2936 |
+
"step": 4180
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 8.0006,
|
| 2940 |
+
"grad_norm": 0.19142334163188934,
|
| 2941 |
+
"learning_rate": 0.00011622,
|
| 2942 |
+
"loss": 0.03999471664428711,
|
| 2943 |
+
"step": 4190
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 8.0016,
|
| 2947 |
+
"grad_norm": 0.1997303068637848,
|
| 2948 |
+
"learning_rate": 0.00011601999999999999,
|
| 2949 |
+
"loss": 0.03443270623683929,
|
| 2950 |
+
"step": 4200
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 8.0026,
|
| 2954 |
+
"grad_norm": 0.18130983412265778,
|
| 2955 |
+
"learning_rate": 0.00011582,
|
| 2956 |
+
"loss": 0.039177173376083375,
|
| 2957 |
+
"step": 4210
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 8.0036,
|
| 2961 |
+
"grad_norm": 0.49426183104515076,
|
| 2962 |
+
"learning_rate": 0.00011562,
|
| 2963 |
+
"loss": 0.038170018792152406,
|
| 2964 |
+
"step": 4220
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 8.0046,
|
| 2968 |
+
"grad_norm": 0.20743317902088165,
|
| 2969 |
+
"learning_rate": 0.00011541999999999999,
|
| 2970 |
+
"loss": 0.0379817396402359,
|
| 2971 |
+
"step": 4230
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 8.0056,
|
| 2975 |
+
"grad_norm": 0.18070366978645325,
|
| 2976 |
+
"learning_rate": 0.00011522,
|
| 2977 |
+
"loss": 0.036043813824653624,
|
| 2978 |
+
"step": 4240
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 8.0066,
|
| 2982 |
+
"grad_norm": 0.22303594648838043,
|
| 2983 |
+
"learning_rate": 0.00011501999999999999,
|
| 2984 |
+
"loss": 0.0366193026304245,
|
| 2985 |
+
"step": 4250
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 8.0076,
|
| 2989 |
+
"grad_norm": 0.23021455109119415,
|
| 2990 |
+
"learning_rate": 0.00011482000000000002,
|
| 2991 |
+
"loss": 0.03866423368453979,
|
| 2992 |
+
"step": 4260
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 8.0086,
|
| 2996 |
+
"grad_norm": 0.18778809905052185,
|
| 2997 |
+
"learning_rate": 0.00011462000000000001,
|
| 2998 |
+
"loss": 0.035205498337745667,
|
| 2999 |
+
"step": 4270
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 8.0096,
|
| 3003 |
+
"grad_norm": 0.20131027698516846,
|
| 3004 |
+
"learning_rate": 0.00011442000000000002,
|
| 3005 |
+
"loss": 0.03923934400081634,
|
| 3006 |
+
"step": 4280
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 8.0106,
|
| 3010 |
+
"grad_norm": 0.21135014295578003,
|
| 3011 |
+
"learning_rate": 0.00011422000000000001,
|
| 3012 |
+
"loss": 0.0388818234205246,
|
| 3013 |
+
"step": 4290
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 8.0116,
|
| 3017 |
+
"grad_norm": 0.21640531718730927,
|
| 3018 |
+
"learning_rate": 0.00011402000000000001,
|
| 3019 |
+
"loss": 0.038308563828468326,
|
| 3020 |
+
"step": 4300
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 8.0126,
|
| 3024 |
+
"grad_norm": 0.19794313609600067,
|
| 3025 |
+
"learning_rate": 0.00011382000000000002,
|
| 3026 |
+
"loss": 0.03605532646179199,
|
| 3027 |
+
"step": 4310
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 8.0136,
|
| 3031 |
+
"grad_norm": 0.20682232081890106,
|
| 3032 |
+
"learning_rate": 0.00011362000000000001,
|
| 3033 |
+
"loss": 0.03772588968276978,
|
| 3034 |
+
"step": 4320
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 8.0146,
|
| 3038 |
+
"grad_norm": 0.1675058901309967,
|
| 3039 |
+
"learning_rate": 0.00011342000000000001,
|
| 3040 |
+
"loss": 0.03707289695739746,
|
| 3041 |
+
"step": 4330
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 8.0156,
|
| 3045 |
+
"grad_norm": 0.1780337393283844,
|
| 3046 |
+
"learning_rate": 0.00011322000000000002,
|
| 3047 |
+
"loss": 0.04678710401058197,
|
| 3048 |
+
"step": 4340
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 8.0166,
|
| 3052 |
+
"grad_norm": 0.22333677113056183,
|
| 3053 |
+
"learning_rate": 0.00011302000000000001,
|
| 3054 |
+
"loss": 0.03880314826965332,
|
| 3055 |
+
"step": 4350
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 8.0176,
|
| 3059 |
+
"grad_norm": 0.2167593091726303,
|
| 3060 |
+
"learning_rate": 0.00011282000000000002,
|
| 3061 |
+
"loss": 0.038645395636558534,
|
| 3062 |
+
"step": 4360
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 8.0186,
|
| 3066 |
+
"grad_norm": 0.21094417572021484,
|
| 3067 |
+
"learning_rate": 0.00011262000000000002,
|
| 3068 |
+
"loss": 0.03557896316051483,
|
| 3069 |
+
"step": 4370
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 8.0196,
|
| 3073 |
+
"grad_norm": 0.2134038805961609,
|
| 3074 |
+
"learning_rate": 0.00011242000000000001,
|
| 3075 |
+
"loss": 0.035387244820594785,
|
| 3076 |
+
"step": 4380
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 8.0206,
|
| 3080 |
+
"grad_norm": 0.18721550703048706,
|
| 3081 |
+
"learning_rate": 0.00011222000000000002,
|
| 3082 |
+
"loss": 0.0355907142162323,
|
| 3083 |
+
"step": 4390
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 8.0216,
|
| 3087 |
+
"grad_norm": 0.20684556663036346,
|
| 3088 |
+
"learning_rate": 0.00011202000000000002,
|
| 3089 |
+
"loss": 0.0357794851064682,
|
| 3090 |
+
"step": 4400
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 8.0226,
|
| 3094 |
+
"grad_norm": 0.2096317857503891,
|
| 3095 |
+
"learning_rate": 0.00011182000000000001,
|
| 3096 |
+
"loss": 0.036594313383102414,
|
| 3097 |
+
"step": 4410
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 8.0236,
|
| 3101 |
+
"grad_norm": 0.1866813451051712,
|
| 3102 |
+
"learning_rate": 0.00011162000000000002,
|
| 3103 |
+
"loss": 0.038320142030715945,
|
| 3104 |
+
"step": 4420
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 8.0246,
|
| 3108 |
+
"grad_norm": 0.17548422515392303,
|
| 3109 |
+
"learning_rate": 0.00011142000000000001,
|
| 3110 |
+
"loss": 0.03279055655002594,
|
| 3111 |
+
"step": 4430
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 8.0256,
|
| 3115 |
+
"grad_norm": 0.1939040571451187,
|
| 3116 |
+
"learning_rate": 0.00011122000000000001,
|
| 3117 |
+
"loss": 0.033512675762176515,
|
| 3118 |
+
"step": 4440
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 8.0266,
|
| 3122 |
+
"grad_norm": 0.1942121386528015,
|
| 3123 |
+
"learning_rate": 0.00011102000000000002,
|
| 3124 |
+
"loss": 0.03630416989326477,
|
| 3125 |
+
"step": 4450
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 8.0276,
|
| 3129 |
+
"grad_norm": 0.18124482035636902,
|
| 3130 |
+
"learning_rate": 0.00011082000000000001,
|
| 3131 |
+
"loss": 0.0364689439535141,
|
| 3132 |
+
"step": 4460
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 8.0286,
|
| 3136 |
+
"grad_norm": 0.2448221743106842,
|
| 3137 |
+
"learning_rate": 0.00011062000000000001,
|
| 3138 |
+
"loss": 0.036901557445526124,
|
| 3139 |
+
"step": 4470
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 8.0296,
|
| 3143 |
+
"grad_norm": 0.20503127574920654,
|
| 3144 |
+
"learning_rate": 0.00011042000000000002,
|
| 3145 |
+
"loss": 0.037753531336784364,
|
| 3146 |
+
"step": 4480
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 8.0306,
|
| 3150 |
+
"grad_norm": 0.20306122303009033,
|
| 3151 |
+
"learning_rate": 0.00011022000000000001,
|
| 3152 |
+
"loss": 0.036759817600250246,
|
| 3153 |
+
"step": 4490
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 9.0004,
|
| 3157 |
+
"grad_norm": 0.16577443480491638,
|
| 3158 |
+
"learning_rate": 0.00011002000000000001,
|
| 3159 |
+
"loss": 0.03821190297603607,
|
| 3160 |
+
"step": 4500
|
| 3161 |
}
|
| 3162 |
],
|
| 3163 |
"logging_steps": 10,
|
|
|
|
| 3177 |
"attributes": {}
|
| 3178 |
}
|
| 3179 |
},
|
| 3180 |
+
"total_flos": 3.809328818933514e+17,
|
| 3181 |
"train_batch_size": 1,
|
| 3182 |
"trial_name": null,
|
| 3183 |
"trial_params": null
|