Training in progress, step 4500, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9197a884173d9c36c93a016c2f30534c3f05c90874cb72eed644075307e2fce3
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb84df5445e2433de304b15e77a1175375dd2d8c25dc61c78681c28414293e5
|
| 3 |
size 10707706
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75f78ad885bfca269044336e349d57c368367d27fdbb75021a699360ecf7bb2b
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a8d4a8a8e577d9dbdb51f074c9b711b4edce95beedab354e7f35ce094aeb0d
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2727,13 +2727,353 @@
|
|
| 2727 |
"eval_samples_per_second": 88.699,
|
| 2728 |
"eval_steps_per_second": 11.135,
|
| 2729 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2730 |
}
|
| 2731 |
],
|
| 2732 |
"logging_steps": 10,
|
| 2733 |
"max_steps": 6130,
|
| 2734 |
"num_train_epochs": 10,
|
| 2735 |
"save_steps": 500,
|
| 2736 |
-
"total_flos":
|
| 2737 |
"trial_name": null,
|
| 2738 |
"trial_params": null
|
| 2739 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.41941431164741516,
|
| 3 |
+
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-4500",
|
| 4 |
+
"epoch": 7.3409461663947795,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2727 |
"eval_samples_per_second": 88.699,
|
| 2728 |
"eval_steps_per_second": 11.135,
|
| 2729 |
"step": 4000
|
| 2730 |
+
},
|
| 2731 |
+
{
|
| 2732 |
+
"epoch": 6.54,
|
| 2733 |
+
"learning_rate": 0.0003765541740674956,
|
| 2734 |
+
"loss": 0.4198,
|
| 2735 |
+
"step": 4010
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 6.56,
|
| 2739 |
+
"learning_rate": 0.0003747779751332149,
|
| 2740 |
+
"loss": 0.3908,
|
| 2741 |
+
"step": 4020
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 6.57,
|
| 2745 |
+
"learning_rate": 0.00037300177619893426,
|
| 2746 |
+
"loss": 0.4296,
|
| 2747 |
+
"step": 4030
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 6.59,
|
| 2751 |
+
"learning_rate": 0.00037122557726465365,
|
| 2752 |
+
"loss": 0.4183,
|
| 2753 |
+
"step": 4040
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 6.61,
|
| 2757 |
+
"learning_rate": 0.000369449378330373,
|
| 2758 |
+
"loss": 0.4371,
|
| 2759 |
+
"step": 4050
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 6.62,
|
| 2763 |
+
"learning_rate": 0.00036767317939609233,
|
| 2764 |
+
"loss": 0.3934,
|
| 2765 |
+
"step": 4060
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"epoch": 6.64,
|
| 2769 |
+
"learning_rate": 0.0003658969804618117,
|
| 2770 |
+
"loss": 0.4581,
|
| 2771 |
+
"step": 4070
|
| 2772 |
+
},
|
| 2773 |
+
{
|
| 2774 |
+
"epoch": 6.66,
|
| 2775 |
+
"learning_rate": 0.00036412078152753106,
|
| 2776 |
+
"loss": 0.3908,
|
| 2777 |
+
"step": 4080
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 6.67,
|
| 2781 |
+
"learning_rate": 0.0003623445825932504,
|
| 2782 |
+
"loss": 0.4237,
|
| 2783 |
+
"step": 4090
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 6.69,
|
| 2787 |
+
"learning_rate": 0.00036056838365896985,
|
| 2788 |
+
"loss": 0.3975,
|
| 2789 |
+
"step": 4100
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 6.69,
|
| 2793 |
+
"eval_loss": 0.4162620007991791,
|
| 2794 |
+
"eval_runtime": 12.9992,
|
| 2795 |
+
"eval_samples_per_second": 90.082,
|
| 2796 |
+
"eval_steps_per_second": 11.308,
|
| 2797 |
+
"step": 4100
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 6.7,
|
| 2801 |
+
"learning_rate": 0.0003587921847246892,
|
| 2802 |
+
"loss": 0.4152,
|
| 2803 |
+
"step": 4110
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 6.72,
|
| 2807 |
+
"learning_rate": 0.0003570159857904086,
|
| 2808 |
+
"loss": 0.4353,
|
| 2809 |
+
"step": 4120
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 6.74,
|
| 2813 |
+
"learning_rate": 0.0003552397868561279,
|
| 2814 |
+
"loss": 0.3991,
|
| 2815 |
+
"step": 4130
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 6.75,
|
| 2819 |
+
"learning_rate": 0.00035346358792184726,
|
| 2820 |
+
"loss": 0.4094,
|
| 2821 |
+
"step": 4140
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"epoch": 6.77,
|
| 2825 |
+
"learning_rate": 0.00035168738898756665,
|
| 2826 |
+
"loss": 0.4099,
|
| 2827 |
+
"step": 4150
|
| 2828 |
+
},
|
| 2829 |
+
{
|
| 2830 |
+
"epoch": 6.79,
|
| 2831 |
+
"learning_rate": 0.000349911190053286,
|
| 2832 |
+
"loss": 0.4107,
|
| 2833 |
+
"step": 4160
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 6.8,
|
| 2837 |
+
"learning_rate": 0.00034813499111900533,
|
| 2838 |
+
"loss": 0.433,
|
| 2839 |
+
"step": 4170
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 6.82,
|
| 2843 |
+
"learning_rate": 0.0003463587921847247,
|
| 2844 |
+
"loss": 0.4267,
|
| 2845 |
+
"step": 4180
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 6.84,
|
| 2849 |
+
"learning_rate": 0.00034458259325044407,
|
| 2850 |
+
"loss": 0.4373,
|
| 2851 |
+
"step": 4190
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 6.85,
|
| 2855 |
+
"learning_rate": 0.0003428063943161634,
|
| 2856 |
+
"loss": 0.4053,
|
| 2857 |
+
"step": 4200
|
| 2858 |
+
},
|
| 2859 |
+
{
|
| 2860 |
+
"epoch": 6.85,
|
| 2861 |
+
"eval_loss": 0.4194377064704895,
|
| 2862 |
+
"eval_runtime": 13.0635,
|
| 2863 |
+
"eval_samples_per_second": 89.639,
|
| 2864 |
+
"eval_steps_per_second": 11.253,
|
| 2865 |
+
"step": 4200
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 6.87,
|
| 2869 |
+
"learning_rate": 0.0003410301953818828,
|
| 2870 |
+
"loss": 0.4298,
|
| 2871 |
+
"step": 4210
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 6.88,
|
| 2875 |
+
"learning_rate": 0.00033925399644760214,
|
| 2876 |
+
"loss": 0.4074,
|
| 2877 |
+
"step": 4220
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"epoch": 6.9,
|
| 2881 |
+
"learning_rate": 0.0003374777975133215,
|
| 2882 |
+
"loss": 0.423,
|
| 2883 |
+
"step": 4230
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 6.92,
|
| 2887 |
+
"learning_rate": 0.00033570159857904087,
|
| 2888 |
+
"loss": 0.4292,
|
| 2889 |
+
"step": 4240
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 6.93,
|
| 2893 |
+
"learning_rate": 0.0003339253996447602,
|
| 2894 |
+
"loss": 0.4068,
|
| 2895 |
+
"step": 4250
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 6.95,
|
| 2899 |
+
"learning_rate": 0.0003321492007104796,
|
| 2900 |
+
"loss": 0.41,
|
| 2901 |
+
"step": 4260
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 6.97,
|
| 2905 |
+
"learning_rate": 0.00033037300177619894,
|
| 2906 |
+
"loss": 0.4429,
|
| 2907 |
+
"step": 4270
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 6.98,
|
| 2911 |
+
"learning_rate": 0.0003285968028419183,
|
| 2912 |
+
"loss": 0.4352,
|
| 2913 |
+
"step": 4280
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 7.0,
|
| 2917 |
+
"learning_rate": 0.0003268206039076377,
|
| 2918 |
+
"loss": 0.4314,
|
| 2919 |
+
"step": 4290
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"epoch": 7.01,
|
| 2923 |
+
"learning_rate": 0.000325044404973357,
|
| 2924 |
+
"loss": 0.3817,
|
| 2925 |
+
"step": 4300
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 7.01,
|
| 2929 |
+
"eval_loss": 0.42648157477378845,
|
| 2930 |
+
"eval_runtime": 12.8627,
|
| 2931 |
+
"eval_samples_per_second": 91.039,
|
| 2932 |
+
"eval_steps_per_second": 11.428,
|
| 2933 |
+
"step": 4300
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 7.03,
|
| 2937 |
+
"learning_rate": 0.00032326820603907635,
|
| 2938 |
+
"loss": 0.4002,
|
| 2939 |
+
"step": 4310
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 7.05,
|
| 2943 |
+
"learning_rate": 0.00032149200710479575,
|
| 2944 |
+
"loss": 0.397,
|
| 2945 |
+
"step": 4320
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 7.06,
|
| 2949 |
+
"learning_rate": 0.0003197158081705151,
|
| 2950 |
+
"loss": 0.4064,
|
| 2951 |
+
"step": 4330
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 7.08,
|
| 2955 |
+
"learning_rate": 0.0003179396092362344,
|
| 2956 |
+
"loss": 0.4314,
|
| 2957 |
+
"step": 4340
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 7.1,
|
| 2961 |
+
"learning_rate": 0.0003161634103019538,
|
| 2962 |
+
"loss": 0.4149,
|
| 2963 |
+
"step": 4350
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 7.11,
|
| 2967 |
+
"learning_rate": 0.00031438721136767316,
|
| 2968 |
+
"loss": 0.3956,
|
| 2969 |
+
"step": 4360
|
| 2970 |
+
},
|
| 2971 |
+
{
|
| 2972 |
+
"epoch": 7.13,
|
| 2973 |
+
"learning_rate": 0.00031261101243339255,
|
| 2974 |
+
"loss": 0.4218,
|
| 2975 |
+
"step": 4370
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"epoch": 7.15,
|
| 2979 |
+
"learning_rate": 0.0003108348134991119,
|
| 2980 |
+
"loss": 0.3959,
|
| 2981 |
+
"step": 4380
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 7.16,
|
| 2985 |
+
"learning_rate": 0.00030905861456483123,
|
| 2986 |
+
"loss": 0.4071,
|
| 2987 |
+
"step": 4390
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 7.18,
|
| 2991 |
+
"learning_rate": 0.0003072824156305506,
|
| 2992 |
+
"loss": 0.3927,
|
| 2993 |
+
"step": 4400
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 7.18,
|
| 2997 |
+
"eval_loss": 0.41820862889289856,
|
| 2998 |
+
"eval_runtime": 12.8919,
|
| 2999 |
+
"eval_samples_per_second": 90.832,
|
| 3000 |
+
"eval_steps_per_second": 11.403,
|
| 3001 |
+
"step": 4400
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 7.19,
|
| 3005 |
+
"learning_rate": 0.00030550621669627,
|
| 3006 |
+
"loss": 0.4069,
|
| 3007 |
+
"step": 4410
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 7.21,
|
| 3011 |
+
"learning_rate": 0.00030373001776198936,
|
| 3012 |
+
"loss": 0.403,
|
| 3013 |
+
"step": 4420
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 7.23,
|
| 3017 |
+
"learning_rate": 0.00030195381882770875,
|
| 3018 |
+
"loss": 0.402,
|
| 3019 |
+
"step": 4430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 7.24,
|
| 3023 |
+
"learning_rate": 0.0003001776198934281,
|
| 3024 |
+
"loss": 0.4277,
|
| 3025 |
+
"step": 4440
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 7.26,
|
| 3029 |
+
"learning_rate": 0.00029840142095914743,
|
| 3030 |
+
"loss": 0.4067,
|
| 3031 |
+
"step": 4450
|
| 3032 |
+
},
|
| 3033 |
+
{
|
| 3034 |
+
"epoch": 7.28,
|
| 3035 |
+
"learning_rate": 0.0002966252220248668,
|
| 3036 |
+
"loss": 0.3873,
|
| 3037 |
+
"step": 4460
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 7.29,
|
| 3041 |
+
"learning_rate": 0.00029484902309058616,
|
| 3042 |
+
"loss": 0.3955,
|
| 3043 |
+
"step": 4470
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 7.31,
|
| 3047 |
+
"learning_rate": 0.00029307282415630555,
|
| 3048 |
+
"loss": 0.3845,
|
| 3049 |
+
"step": 4480
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 7.32,
|
| 3053 |
+
"learning_rate": 0.0002912966252220249,
|
| 3054 |
+
"loss": 0.4149,
|
| 3055 |
+
"step": 4490
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 7.34,
|
| 3059 |
+
"learning_rate": 0.00028952042628774423,
|
| 3060 |
+
"loss": 0.3996,
|
| 3061 |
+
"step": 4500
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 7.34,
|
| 3065 |
+
"eval_loss": 0.41941431164741516,
|
| 3066 |
+
"eval_runtime": 12.818,
|
| 3067 |
+
"eval_samples_per_second": 91.356,
|
| 3068 |
+
"eval_steps_per_second": 11.468,
|
| 3069 |
+
"step": 4500
|
| 3070 |
}
|
| 3071 |
],
|
| 3072 |
"logging_steps": 10,
|
| 3073 |
"max_steps": 6130,
|
| 3074 |
"num_train_epochs": 10,
|
| 3075 |
"save_steps": 500,
|
| 3076 |
+
"total_flos": 8507970531753984.0,
|
| 3077 |
"trial_name": null,
|
| 3078 |
"trial_params": null
|
| 3079 |
}
|