Training in progress, step 150, 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 216151256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf51175db2b22d2d451af01e5af67ad2342d115669b44363fa2775f8c3d3ef9
|
| 3 |
size 216151256
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 432640054
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00a22dd8372a0a6b3a0e8b4a65a6b4e31b218efb619bab801d3e8a3c9236a062
|
| 3 |
size 432640054
|
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:cea5ed75e4366a50d275c95264b656a87b3f4202ebcacaf9c402b9fbdfba45fb
|
| 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:e70710c409284f74d525f8db5cfaccc22a8afd29416f19c595da9242ec92d936
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -747,6 +747,372 @@
|
|
| 747 |
"eval_samples_per_second": 7.154,
|
| 748 |
"eval_steps_per_second": 1.002,
|
| 749 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
@@ -775,7 +1141,7 @@
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
-
"total_flos":
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2768600583076477,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.5080440304826418,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 747 |
"eval_samples_per_second": 7.154,
|
| 748 |
"eval_steps_per_second": 1.002,
|
| 749 |
"step": 100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.3420829805249788,
|
| 753 |
+
"grad_norm": 38.04734802246094,
|
| 754 |
+
"learning_rate": 0.0001599135876488549,
|
| 755 |
+
"loss": 3.9559,
|
| 756 |
+
"step": 101
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.3454699407281964,
|
| 760 |
+
"grad_norm": 26.404071807861328,
|
| 761 |
+
"learning_rate": 0.00015743756320098332,
|
| 762 |
+
"loss": 2.5687,
|
| 763 |
+
"step": 102
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.3488569009314141,
|
| 767 |
+
"grad_norm": 15.545836448669434,
|
| 768 |
+
"learning_rate": 0.0001549595053975962,
|
| 769 |
+
"loss": 1.778,
|
| 770 |
+
"step": 103
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.3522438611346317,
|
| 774 |
+
"grad_norm": 4.218338966369629,
|
| 775 |
+
"learning_rate": 0.00015248009171495378,
|
| 776 |
+
"loss": 0.9969,
|
| 777 |
+
"step": 104
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.3556308213378493,
|
| 781 |
+
"grad_norm": 3.6731631755828857,
|
| 782 |
+
"learning_rate": 0.00015,
|
| 783 |
+
"loss": 0.8109,
|
| 784 |
+
"step": 105
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.3590177815410669,
|
| 788 |
+
"grad_norm": 3.383131265640259,
|
| 789 |
+
"learning_rate": 0.00014751990828504622,
|
| 790 |
+
"loss": 0.6936,
|
| 791 |
+
"step": 106
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.3624047417442845,
|
| 795 |
+
"grad_norm": 3.4778740406036377,
|
| 796 |
+
"learning_rate": 0.00014504049460240375,
|
| 797 |
+
"loss": 0.3881,
|
| 798 |
+
"step": 107
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.3657917019475021,
|
| 802 |
+
"grad_norm": 2.038445472717285,
|
| 803 |
+
"learning_rate": 0.00014256243679901663,
|
| 804 |
+
"loss": 0.3805,
|
| 805 |
+
"step": 108
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.3691786621507197,
|
| 809 |
+
"grad_norm": 7.391066074371338,
|
| 810 |
+
"learning_rate": 0.00014008641235114508,
|
| 811 |
+
"loss": 0.3025,
|
| 812 |
+
"step": 109
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.37256562235393736,
|
| 816 |
+
"grad_norm": 9.895805358886719,
|
| 817 |
+
"learning_rate": 0.00013761309817915014,
|
| 818 |
+
"loss": 0.4677,
|
| 819 |
+
"step": 110
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.37595258255715497,
|
| 823 |
+
"grad_norm": 7.2605881690979,
|
| 824 |
+
"learning_rate": 0.00013514317046243058,
|
| 825 |
+
"loss": 0.2445,
|
| 826 |
+
"step": 111
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.3793395427603726,
|
| 830 |
+
"grad_norm": 11.445152282714844,
|
| 831 |
+
"learning_rate": 0.00013267730445456208,
|
| 832 |
+
"loss": 0.3512,
|
| 833 |
+
"step": 112
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.3827265029635902,
|
| 837 |
+
"grad_norm": 6.710597515106201,
|
| 838 |
+
"learning_rate": 0.00013021617429868963,
|
| 839 |
+
"loss": 0.4151,
|
| 840 |
+
"step": 113
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.3861134631668078,
|
| 844 |
+
"grad_norm": 2.882502794265747,
|
| 845 |
+
"learning_rate": 0.00012776045284322368,
|
| 846 |
+
"loss": 0.0975,
|
| 847 |
+
"step": 114
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.3895004233700254,
|
| 851 |
+
"grad_norm": 11.19640064239502,
|
| 852 |
+
"learning_rate": 0.00012531081145788987,
|
| 853 |
+
"loss": 0.1504,
|
| 854 |
+
"step": 115
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.392887383573243,
|
| 858 |
+
"grad_norm": 2.5462589263916016,
|
| 859 |
+
"learning_rate": 0.00012286791985018355,
|
| 860 |
+
"loss": 0.166,
|
| 861 |
+
"step": 116
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.39627434377646065,
|
| 865 |
+
"grad_norm": 6.280060768127441,
|
| 866 |
+
"learning_rate": 0.00012043244588227796,
|
| 867 |
+
"loss": 0.3321,
|
| 868 |
+
"step": 117
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.39966130397967825,
|
| 872 |
+
"grad_norm": 3.742800235748291,
|
| 873 |
+
"learning_rate": 0.00011800505538843798,
|
| 874 |
+
"loss": 0.2449,
|
| 875 |
+
"step": 118
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.40304826418289585,
|
| 879 |
+
"grad_norm": 4.07996129989624,
|
| 880 |
+
"learning_rate": 0.00011558641199298727,
|
| 881 |
+
"loss": 0.1723,
|
| 882 |
+
"step": 119
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.40643522438611346,
|
| 886 |
+
"grad_norm": 2.472219705581665,
|
| 887 |
+
"learning_rate": 0.00011317717692888012,
|
| 888 |
+
"loss": 0.1045,
|
| 889 |
+
"step": 120
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.40982218458933106,
|
| 893 |
+
"grad_norm": 5.641716003417969,
|
| 894 |
+
"learning_rate": 0.00011077800885692702,
|
| 895 |
+
"loss": 0.3207,
|
| 896 |
+
"step": 121
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.41320914479254867,
|
| 900 |
+
"grad_norm": 7.763329029083252,
|
| 901 |
+
"learning_rate": 0.00010838956368572334,
|
| 902 |
+
"loss": 0.2601,
|
| 903 |
+
"step": 122
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.4165961049957663,
|
| 907 |
+
"grad_norm": 5.5211501121521,
|
| 908 |
+
"learning_rate": 0.0001060124943923303,
|
| 909 |
+
"loss": 0.3374,
|
| 910 |
+
"step": 123
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.41998306519898393,
|
| 914 |
+
"grad_norm": 5.142914772033691,
|
| 915 |
+
"learning_rate": 0.0001036474508437579,
|
| 916 |
+
"loss": 0.3671,
|
| 917 |
+
"step": 124
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.42337002540220153,
|
| 921 |
+
"grad_norm": 3.195248603820801,
|
| 922 |
+
"learning_rate": 0.00010129507961929748,
|
| 923 |
+
"loss": 0.1383,
|
| 924 |
+
"step": 125
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.42337002540220153,
|
| 928 |
+
"eval_loss": 0.8896229267120361,
|
| 929 |
+
"eval_runtime": 6.9917,
|
| 930 |
+
"eval_samples_per_second": 7.151,
|
| 931 |
+
"eval_steps_per_second": 1.001,
|
| 932 |
+
"step": 125
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.42675698560541914,
|
| 936 |
+
"grad_norm": 1.123442530632019,
|
| 937 |
+
"learning_rate": 9.895602383375353e-05,
|
| 938 |
+
"loss": 0.1009,
|
| 939 |
+
"step": 126
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.43014394580863674,
|
| 943 |
+
"grad_norm": 4.091561794281006,
|
| 944 |
+
"learning_rate": 9.663092296162251e-05,
|
| 945 |
+
"loss": 0.1741,
|
| 946 |
+
"step": 127
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.43353090601185434,
|
| 950 |
+
"grad_norm": 3.3476603031158447,
|
| 951 |
+
"learning_rate": 9.432041266226686e-05,
|
| 952 |
+
"loss": 0.3535,
|
| 953 |
+
"step": 128
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.43691786621507195,
|
| 957 |
+
"grad_norm": 4.132399559020996,
|
| 958 |
+
"learning_rate": 9.202512460613219e-05,
|
| 959 |
+
"loss": 0.3354,
|
| 960 |
+
"step": 129
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.4403048264182896,
|
| 964 |
+
"grad_norm": 3.9859485626220703,
|
| 965 |
+
"learning_rate": 8.97456863020546e-05,
|
| 966 |
+
"loss": 0.2174,
|
| 967 |
+
"step": 130
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.4436917866215072,
|
| 971 |
+
"grad_norm": 3.752464771270752,
|
| 972 |
+
"learning_rate": 8.748272092570646e-05,
|
| 973 |
+
"loss": 0.3398,
|
| 974 |
+
"step": 131
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.4470787468247248,
|
| 978 |
+
"grad_norm": 5.6418585777282715,
|
| 979 |
+
"learning_rate": 8.523684714922608e-05,
|
| 980 |
+
"loss": 0.5945,
|
| 981 |
+
"step": 132
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.4504657070279424,
|
| 985 |
+
"grad_norm": 5.202731609344482,
|
| 986 |
+
"learning_rate": 8.300867897207903e-05,
|
| 987 |
+
"loss": 0.5471,
|
| 988 |
+
"step": 133
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.45385266723116,
|
| 992 |
+
"grad_norm": 4.451300621032715,
|
| 993 |
+
"learning_rate": 8.079882555319684e-05,
|
| 994 |
+
"loss": 0.5935,
|
| 995 |
+
"step": 134
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.4572396274343776,
|
| 999 |
+
"grad_norm": 11.032302856445312,
|
| 1000 |
+
"learning_rate": 7.860789104443896e-05,
|
| 1001 |
+
"loss": 0.9239,
|
| 1002 |
+
"step": 135
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.46062658763759523,
|
| 1006 |
+
"grad_norm": 6.030894756317139,
|
| 1007 |
+
"learning_rate": 7.643647442542382e-05,
|
| 1008 |
+
"loss": 0.5839,
|
| 1009 |
+
"step": 136
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.4640135478408129,
|
| 1013 |
+
"grad_norm": 4.059135913848877,
|
| 1014 |
+
"learning_rate": 7.428516933977347e-05,
|
| 1015 |
+
"loss": 0.5012,
|
| 1016 |
+
"step": 137
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.4674005080440305,
|
| 1020 |
+
"grad_norm": 3.3977863788604736,
|
| 1021 |
+
"learning_rate": 7.215456393281776e-05,
|
| 1022 |
+
"loss": 0.3867,
|
| 1023 |
+
"step": 138
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.4707874682472481,
|
| 1027 |
+
"grad_norm": 2.3960726261138916,
|
| 1028 |
+
"learning_rate": 7.004524069080096e-05,
|
| 1029 |
+
"loss": 0.3875,
|
| 1030 |
+
"step": 139
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.4741744284504657,
|
| 1034 |
+
"grad_norm": 1.9398398399353027,
|
| 1035 |
+
"learning_rate": 6.795777628163599e-05,
|
| 1036 |
+
"loss": 0.2928,
|
| 1037 |
+
"step": 140
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.4775613886536833,
|
| 1041 |
+
"grad_norm": 2.1065077781677246,
|
| 1042 |
+
"learning_rate": 6.58927413972491e-05,
|
| 1043 |
+
"loss": 0.2398,
|
| 1044 |
+
"step": 141
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.4809483488569009,
|
| 1048 |
+
"grad_norm": 2.4689295291900635,
|
| 1049 |
+
"learning_rate": 6.385070059755846e-05,
|
| 1050 |
+
"loss": 0.2825,
|
| 1051 |
+
"step": 142
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.48433530906011857,
|
| 1055 |
+
"grad_norm": 2.2755885124206543,
|
| 1056 |
+
"learning_rate": 6.183221215612904e-05,
|
| 1057 |
+
"loss": 0.2738,
|
| 1058 |
+
"step": 143
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.4877222692633362,
|
| 1062 |
+
"grad_norm": 3.0065155029296875,
|
| 1063 |
+
"learning_rate": 5.983782790754623e-05,
|
| 1064 |
+
"loss": 0.369,
|
| 1065 |
+
"step": 144
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.4911092294665538,
|
| 1069 |
+
"grad_norm": 1.313037633895874,
|
| 1070 |
+
"learning_rate": 5.786809309654982e-05,
|
| 1071 |
+
"loss": 0.266,
|
| 1072 |
+
"step": 145
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.4944961896697714,
|
| 1076 |
+
"grad_norm": 0.7761518359184265,
|
| 1077 |
+
"learning_rate": 5.592354622896944e-05,
|
| 1078 |
+
"loss": 0.2709,
|
| 1079 |
+
"step": 146
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.497883149872989,
|
| 1083 |
+
"grad_norm": 0.8235387206077576,
|
| 1084 |
+
"learning_rate": 5.40047189245025e-05,
|
| 1085 |
+
"loss": 0.2851,
|
| 1086 |
+
"step": 147
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.5012701100762066,
|
| 1090 |
+
"grad_norm": 1.2671778202056885,
|
| 1091 |
+
"learning_rate": 5.211213577137469e-05,
|
| 1092 |
+
"loss": 0.2433,
|
| 1093 |
+
"step": 148
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.5046570702794242,
|
| 1097 |
+
"grad_norm": 1.3252907991409302,
|
| 1098 |
+
"learning_rate": 5.024631418292274e-05,
|
| 1099 |
+
"loss": 0.2527,
|
| 1100 |
+
"step": 149
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.5080440304826418,
|
| 1104 |
+
"grad_norm": 1.3691195249557495,
|
| 1105 |
+
"learning_rate": 4.840776425613886e-05,
|
| 1106 |
+
"loss": 0.246,
|
| 1107 |
+
"step": 150
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.5080440304826418,
|
| 1111 |
+
"eval_loss": 0.2768600583076477,
|
| 1112 |
+
"eval_runtime": 6.982,
|
| 1113 |
+
"eval_samples_per_second": 7.161,
|
| 1114 |
+
"eval_steps_per_second": 1.003,
|
| 1115 |
+
"step": 150
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
+
"total_flos": 2.625264977707008e+17,
|
| 1145 |
"train_batch_size": 8,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|