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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9867b8ba462b121acd0706c5a9ec25cb85ef9190afc97e6a0639e0511d9dc13d
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bcc348de9a22e6628e55f182536dcce50cf970a68bfe15d586906805640b472
|
| 3 |
size 341314196
|
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:e180d6796c8af6bc7321e47607382b7af34e2afec042075a684d7e4ff4dae0e4
|
| 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 sha256:970068ebf9c0dc6a40c93653c563bb0b2ba5296a6c46496b504a3f1343bf3a62
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -731,6 +731,364 @@
|
|
| 731 |
"eval_samples_per_second": 4.026,
|
| 732 |
"eval_steps_per_second": 1.006,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -745,7 +1103,7 @@
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
-
"early_stopping_patience_counter":
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.7425742574257426,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 731 |
"eval_samples_per_second": 4.026,
|
| 732 |
"eval_steps_per_second": 1.006,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.5,
|
| 737 |
+
"grad_norm": NaN,
|
| 738 |
+
"learning_rate": 5.8634982137913465e-05,
|
| 739 |
+
"loss": 0.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.504950495049505,
|
| 744 |
+
"grad_norm": NaN,
|
| 745 |
+
"learning_rate": 5.772710650702723e-05,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.5099009900990099,
|
| 751 |
+
"grad_norm": NaN,
|
| 752 |
+
"learning_rate": 5.681848531245195e-05,
|
| 753 |
+
"loss": 0.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.5148514851485149,
|
| 758 |
+
"grad_norm": NaN,
|
| 759 |
+
"learning_rate": 5.590936696214972e-05,
|
| 760 |
+
"loss": 0.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.5198019801980198,
|
| 765 |
+
"grad_norm": NaN,
|
| 766 |
+
"learning_rate": 5.5e-05,
|
| 767 |
+
"loss": 0.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.5247524752475248,
|
| 772 |
+
"grad_norm": NaN,
|
| 773 |
+
"learning_rate": 5.409063303785029e-05,
|
| 774 |
+
"loss": 0.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.5297029702970297,
|
| 779 |
+
"grad_norm": NaN,
|
| 780 |
+
"learning_rate": 5.318151468754805e-05,
|
| 781 |
+
"loss": 0.0,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.5346534653465347,
|
| 786 |
+
"grad_norm": NaN,
|
| 787 |
+
"learning_rate": 5.227289349297277e-05,
|
| 788 |
+
"loss": 0.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.5396039603960396,
|
| 793 |
+
"grad_norm": NaN,
|
| 794 |
+
"learning_rate": 5.136501786208654e-05,
|
| 795 |
+
"loss": 0.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.5445544554455446,
|
| 800 |
+
"grad_norm": NaN,
|
| 801 |
+
"learning_rate": 5.045813599902173e-05,
|
| 802 |
+
"loss": 0.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.5495049504950495,
|
| 807 |
+
"grad_norm": NaN,
|
| 808 |
+
"learning_rate": 4.955249583622455e-05,
|
| 809 |
+
"loss": 2.2827,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.5544554455445545,
|
| 814 |
+
"grad_norm": 6.830944538116455,
|
| 815 |
+
"learning_rate": 4.8648344966672767e-05,
|
| 816 |
+
"loss": 2.7697,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.5594059405940595,
|
| 821 |
+
"grad_norm": 6.300211429595947,
|
| 822 |
+
"learning_rate": 4.774593057618621e-05,
|
| 823 |
+
"loss": 2.8706,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.5643564356435643,
|
| 828 |
+
"grad_norm": 6.06986141204834,
|
| 829 |
+
"learning_rate": 4.6845499375848686e-05,
|
| 830 |
+
"loss": 2.5056,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.5693069306930693,
|
| 835 |
+
"grad_norm": 5.525240421295166,
|
| 836 |
+
"learning_rate": 4.5947297534559625e-05,
|
| 837 |
+
"loss": 2.5763,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.5742574257425742,
|
| 842 |
+
"grad_norm": 5.942731857299805,
|
| 843 |
+
"learning_rate": 4.5051570611733976e-05,
|
| 844 |
+
"loss": 2.5812,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.5792079207920792,
|
| 849 |
+
"grad_norm": NaN,
|
| 850 |
+
"learning_rate": 4.415856349016859e-05,
|
| 851 |
+
"loss": 5.42,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.5841584158415841,
|
| 856 |
+
"grad_norm": NaN,
|
| 857 |
+
"learning_rate": 4.326852030909393e-05,
|
| 858 |
+
"loss": 0.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.5891089108910891,
|
| 863 |
+
"grad_norm": NaN,
|
| 864 |
+
"learning_rate": 4.238168439742867e-05,
|
| 865 |
+
"loss": 0.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.594059405940594,
|
| 870 |
+
"grad_norm": NaN,
|
| 871 |
+
"learning_rate": 4.149829820725605e-05,
|
| 872 |
+
"loss": 0.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.599009900990099,
|
| 877 |
+
"grad_norm": NaN,
|
| 878 |
+
"learning_rate": 4.0618603247539916e-05,
|
| 879 |
+
"loss": 0.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.6039603960396039,
|
| 884 |
+
"grad_norm": NaN,
|
| 885 |
+
"learning_rate": 3.9742840018098564e-05,
|
| 886 |
+
"loss": 0.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.6089108910891089,
|
| 891 |
+
"grad_norm": NaN,
|
| 892 |
+
"learning_rate": 3.887124794385445e-05,
|
| 893 |
+
"loss": 0.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.6138613861386139,
|
| 898 |
+
"grad_norm": NaN,
|
| 899 |
+
"learning_rate": 3.80040653093779e-05,
|
| 900 |
+
"loss": 0.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.6188118811881188,
|
| 905 |
+
"grad_norm": NaN,
|
| 906 |
+
"learning_rate": 3.714152919374241e-05,
|
| 907 |
+
"loss": 0.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.6237623762376238,
|
| 912 |
+
"grad_norm": NaN,
|
| 913 |
+
"learning_rate": 3.628387540570963e-05,
|
| 914 |
+
"loss": 0.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.6287128712871287,
|
| 919 |
+
"grad_norm": NaN,
|
| 920 |
+
"learning_rate": 3.543133841926159e-05,
|
| 921 |
+
"loss": 0.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.6336633663366337,
|
| 926 |
+
"grad_norm": NaN,
|
| 927 |
+
"learning_rate": 3.458415130949785e-05,
|
| 928 |
+
"loss": 0.0,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.6386138613861386,
|
| 933 |
+
"grad_norm": NaN,
|
| 934 |
+
"learning_rate": 3.374254568891514e-05,
|
| 935 |
+
"loss": 0.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.6435643564356436,
|
| 940 |
+
"grad_norm": NaN,
|
| 941 |
+
"learning_rate": 3.290675164408669e-05,
|
| 942 |
+
"loss": 0.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.6485148514851485,
|
| 947 |
+
"grad_norm": NaN,
|
| 948 |
+
"learning_rate": 3.207699767275904e-05,
|
| 949 |
+
"loss": 0.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.6534653465346535,
|
| 954 |
+
"grad_norm": NaN,
|
| 955 |
+
"learning_rate": 3.12535106213829e-05,
|
| 956 |
+
"loss": 0.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.6584158415841584,
|
| 961 |
+
"grad_norm": NaN,
|
| 962 |
+
"learning_rate": 3.0436515623095647e-05,
|
| 963 |
+
"loss": 0.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.6633663366336634,
|
| 968 |
+
"grad_norm": NaN,
|
| 969 |
+
"learning_rate": 2.962623603617218e-05,
|
| 970 |
+
"loss": 0.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.6683168316831684,
|
| 975 |
+
"grad_norm": NaN,
|
| 976 |
+
"learning_rate": 2.8822893382960955e-05,
|
| 977 |
+
"loss": 0.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6732673267326733,
|
| 982 |
+
"grad_norm": NaN,
|
| 983 |
+
"learning_rate": 2.802670728932207e-05,
|
| 984 |
+
"loss": 0.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.6782178217821783,
|
| 989 |
+
"grad_norm": NaN,
|
| 990 |
+
"learning_rate": 2.723789542458361e-05,
|
| 991 |
+
"loss": 0.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.6831683168316832,
|
| 996 |
+
"grad_norm": NaN,
|
| 997 |
+
"learning_rate": 2.6456673442033183e-05,
|
| 998 |
+
"loss": 0.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6881188118811881,
|
| 1003 |
+
"grad_norm": NaN,
|
| 1004 |
+
"learning_rate": 2.5683254919960356e-05,
|
| 1005 |
+
"loss": 0.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.693069306930693,
|
| 1010 |
+
"grad_norm": NaN,
|
| 1011 |
+
"learning_rate": 2.4917851303266533e-05,
|
| 1012 |
+
"loss": 0.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.698019801980198,
|
| 1017 |
+
"grad_norm": NaN,
|
| 1018 |
+
"learning_rate": 2.4160671845658007e-05,
|
| 1019 |
+
"loss": 0.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.7029702970297029,
|
| 1024 |
+
"grad_norm": NaN,
|
| 1025 |
+
"learning_rate": 2.3411923552438105e-05,
|
| 1026 |
+
"loss": 0.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.7079207920792079,
|
| 1031 |
+
"grad_norm": NaN,
|
| 1032 |
+
"learning_rate": 2.2671811123913983e-05,
|
| 1033 |
+
"loss": 0.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.7128712871287128,
|
| 1038 |
+
"grad_norm": NaN,
|
| 1039 |
+
"learning_rate": 2.194053689943362e-05,
|
| 1040 |
+
"loss": 0.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.7178217821782178,
|
| 1045 |
+
"grad_norm": NaN,
|
| 1046 |
+
"learning_rate": 2.121830080206827e-05,
|
| 1047 |
+
"loss": 0.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.7227722772277227,
|
| 1052 |
+
"grad_norm": NaN,
|
| 1053 |
+
"learning_rate": 2.0505300283955464e-05,
|
| 1054 |
+
"loss": 0.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.7277227722772277,
|
| 1059 |
+
"grad_norm": NaN,
|
| 1060 |
+
"learning_rate": 1.9801730272317585e-05,
|
| 1061 |
+
"loss": 0.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.7326732673267327,
|
| 1066 |
+
"grad_norm": NaN,
|
| 1067 |
+
"learning_rate": 1.910778311617072e-05,
|
| 1068 |
+
"loss": 0.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.7376237623762376,
|
| 1073 |
+
"grad_norm": NaN,
|
| 1074 |
+
"learning_rate": 1.8423648533738342e-05,
|
| 1075 |
+
"loss": 0.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.7425742574257426,
|
| 1080 |
+
"grad_norm": NaN,
|
| 1081 |
+
"learning_rate": 1.7749513560584252e-05,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.7425742574257426,
|
| 1087 |
+
"eval_loss": NaN,
|
| 1088 |
+
"eval_runtime": 80.2602,
|
| 1089 |
+
"eval_samples_per_second": 4.236,
|
| 1090 |
+
"eval_steps_per_second": 1.059,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 2
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 2.597261386312581e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|