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 34456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7febdf28458d2810d89ef6768357adc314c4999c42112ee60e21bb04df3a334
|
| 3 |
size 34456
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 73222
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66ffb79f9ea9cdec265fcf362eb399e51faf70327754248576eb9a5c814bcbeb
|
| 3 |
size 73222
|
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:f92b3eb1a6a8e1aca605a46fb67164cc3f3b8706561cae8d8417b91aea7fbc0d
|
| 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:c16a9a2b8856e8f64eb7194578c6fcbc8625033d1caa318cc7b80ad824088880
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 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": 76.647,
|
| 732 |
"eval_steps_per_second": 19.163,
|
| 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": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 11.5,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.005456728145803776,
|
| 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": 76.647,
|
| 732 |
"eval_steps_per_second": 19.163,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.0036741969515078758,
|
| 737 |
+
"grad_norm": 7.783313049003482e-05,
|
| 738 |
+
"learning_rate": 5.219384210526315e-05,
|
| 739 |
+
"loss": 23.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.0037105751391465678,
|
| 744 |
+
"grad_norm": 0.00018005183665081859,
|
| 745 |
+
"learning_rate": 5.1666631578947374e-05,
|
| 746 |
+
"loss": 23.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.0037469533267852594,
|
| 751 |
+
"grad_norm": 0.00017219048459082842,
|
| 752 |
+
"learning_rate": 5.113942105263158e-05,
|
| 753 |
+
"loss": 23.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.0037833315144239514,
|
| 758 |
+
"grad_norm": 9.388090256834403e-05,
|
| 759 |
+
"learning_rate": 5.061221052631579e-05,
|
| 760 |
+
"loss": 23.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.0038197097020626434,
|
| 765 |
+
"grad_norm": 0.0001560563687235117,
|
| 766 |
+
"learning_rate": 5.0085e-05,
|
| 767 |
+
"loss": 23.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.003856087889701335,
|
| 772 |
+
"grad_norm": 0.00013232561468612403,
|
| 773 |
+
"learning_rate": 4.955778947368421e-05,
|
| 774 |
+
"loss": 23.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.003892466077340027,
|
| 779 |
+
"grad_norm": 0.0002133690140908584,
|
| 780 |
+
"learning_rate": 4.903057894736842e-05,
|
| 781 |
+
"loss": 23.0,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.003928844264978719,
|
| 786 |
+
"grad_norm": 0.000359582802047953,
|
| 787 |
+
"learning_rate": 4.850336842105263e-05,
|
| 788 |
+
"loss": 23.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.003965222452617411,
|
| 793 |
+
"grad_norm": 0.0003412606893107295,
|
| 794 |
+
"learning_rate": 4.797615789473684e-05,
|
| 795 |
+
"loss": 23.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.004001600640256103,
|
| 800 |
+
"grad_norm": 0.0002902772685047239,
|
| 801 |
+
"learning_rate": 4.744894736842105e-05,
|
| 802 |
+
"loss": 23.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.004037978827894795,
|
| 807 |
+
"grad_norm": 0.00023293598496820778,
|
| 808 |
+
"learning_rate": 4.692173684210526e-05,
|
| 809 |
+
"loss": 23.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.004074357015533486,
|
| 814 |
+
"grad_norm": 0.0004234655061736703,
|
| 815 |
+
"learning_rate": 4.639452631578947e-05,
|
| 816 |
+
"loss": 23.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.004110735203172178,
|
| 821 |
+
"grad_norm": 0.000185246899491176,
|
| 822 |
+
"learning_rate": 4.586731578947368e-05,
|
| 823 |
+
"loss": 23.0,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.00414711339081087,
|
| 828 |
+
"grad_norm": 0.00031807131017558277,
|
| 829 |
+
"learning_rate": 4.5340105263157894e-05,
|
| 830 |
+
"loss": 23.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.004183491578449562,
|
| 835 |
+
"grad_norm": 8.407247514696792e-05,
|
| 836 |
+
"learning_rate": 4.48128947368421e-05,
|
| 837 |
+
"loss": 23.0,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.004219869766088254,
|
| 842 |
+
"grad_norm": 0.00021509136422537267,
|
| 843 |
+
"learning_rate": 4.428568421052632e-05,
|
| 844 |
+
"loss": 23.0,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.004256247953726945,
|
| 849 |
+
"grad_norm": 0.0002161612210329622,
|
| 850 |
+
"learning_rate": 4.3758473684210525e-05,
|
| 851 |
+
"loss": 23.0,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.004292626141365637,
|
| 856 |
+
"grad_norm": 0.0004112378810532391,
|
| 857 |
+
"learning_rate": 4.323126315789474e-05,
|
| 858 |
+
"loss": 23.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.004329004329004329,
|
| 863 |
+
"grad_norm": 0.00027821719413623214,
|
| 864 |
+
"learning_rate": 4.270405263157895e-05,
|
| 865 |
+
"loss": 23.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.004365382516643021,
|
| 870 |
+
"grad_norm": 0.00020274092094041407,
|
| 871 |
+
"learning_rate": 4.217684210526316e-05,
|
| 872 |
+
"loss": 23.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.004401760704281713,
|
| 877 |
+
"grad_norm": 0.0002384830149821937,
|
| 878 |
+
"learning_rate": 4.164963157894737e-05,
|
| 879 |
+
"loss": 23.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.004438138891920404,
|
| 884 |
+
"grad_norm": 0.0005190633819438517,
|
| 885 |
+
"learning_rate": 4.112242105263158e-05,
|
| 886 |
+
"loss": 23.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.004474517079559096,
|
| 891 |
+
"grad_norm": 0.00033458866528235376,
|
| 892 |
+
"learning_rate": 4.059521052631579e-05,
|
| 893 |
+
"loss": 23.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.004510895267197788,
|
| 898 |
+
"grad_norm": 0.0006305323331616819,
|
| 899 |
+
"learning_rate": 4.0068e-05,
|
| 900 |
+
"loss": 23.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.00454727345483648,
|
| 905 |
+
"grad_norm": 0.0005214071134105325,
|
| 906 |
+
"learning_rate": 3.954078947368421e-05,
|
| 907 |
+
"loss": 23.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.004583651642475172,
|
| 912 |
+
"grad_norm": 0.00045183481415733695,
|
| 913 |
+
"learning_rate": 3.901357894736842e-05,
|
| 914 |
+
"loss": 23.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.004620029830113863,
|
| 919 |
+
"grad_norm": 0.0005002326215617359,
|
| 920 |
+
"learning_rate": 3.848636842105263e-05,
|
| 921 |
+
"loss": 23.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.004656408017752555,
|
| 926 |
+
"grad_norm": 0.0006496441783383489,
|
| 927 |
+
"learning_rate": 3.795915789473684e-05,
|
| 928 |
+
"loss": 23.0,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.004692786205391247,
|
| 933 |
+
"grad_norm": 0.0005016289069317281,
|
| 934 |
+
"learning_rate": 3.743194736842105e-05,
|
| 935 |
+
"loss": 23.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.0047291643930299394,
|
| 940 |
+
"grad_norm": 0.00030388403683900833,
|
| 941 |
+
"learning_rate": 3.690473684210526e-05,
|
| 942 |
+
"loss": 23.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.0047655425806686314,
|
| 947 |
+
"grad_norm": 0.0006180494674481452,
|
| 948 |
+
"learning_rate": 3.6377526315789475e-05,
|
| 949 |
+
"loss": 23.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.004801920768307323,
|
| 954 |
+
"grad_norm": 0.00025889030075632036,
|
| 955 |
+
"learning_rate": 3.585031578947368e-05,
|
| 956 |
+
"loss": 23.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.004838298955946015,
|
| 961 |
+
"grad_norm": 0.0005089754704385996,
|
| 962 |
+
"learning_rate": 3.532310526315789e-05,
|
| 963 |
+
"loss": 23.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.004874677143584707,
|
| 968 |
+
"grad_norm": 0.00031534393201582134,
|
| 969 |
+
"learning_rate": 3.4795894736842106e-05,
|
| 970 |
+
"loss": 23.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.004911055331223399,
|
| 975 |
+
"grad_norm": 0.000423017714638263,
|
| 976 |
+
"learning_rate": 3.4268684210526314e-05,
|
| 977 |
+
"loss": 23.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.004947433518862091,
|
| 982 |
+
"grad_norm": 0.0007839161553420126,
|
| 983 |
+
"learning_rate": 3.374147368421052e-05,
|
| 984 |
+
"loss": 23.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.004983811706500782,
|
| 989 |
+
"grad_norm": 0.0005752964061684906,
|
| 990 |
+
"learning_rate": 3.321426315789473e-05,
|
| 991 |
+
"loss": 23.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.005020189894139474,
|
| 996 |
+
"grad_norm": 0.0006725515122525394,
|
| 997 |
+
"learning_rate": 3.2687052631578946e-05,
|
| 998 |
+
"loss": 23.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.005056568081778166,
|
| 1003 |
+
"grad_norm": 0.0002908679307438433,
|
| 1004 |
+
"learning_rate": 3.2159842105263154e-05,
|
| 1005 |
+
"loss": 23.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.005092946269416858,
|
| 1010 |
+
"grad_norm": 0.0005103895673528314,
|
| 1011 |
+
"learning_rate": 3.163263157894737e-05,
|
| 1012 |
+
"loss": 23.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.00512932445705555,
|
| 1017 |
+
"grad_norm": 0.00037893978878855705,
|
| 1018 |
+
"learning_rate": 3.110542105263158e-05,
|
| 1019 |
+
"loss": 23.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.005165702644694241,
|
| 1024 |
+
"grad_norm": 0.000916416582185775,
|
| 1025 |
+
"learning_rate": 3.057821052631579e-05,
|
| 1026 |
+
"loss": 23.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.005202080832332933,
|
| 1031 |
+
"grad_norm": 0.0010032150894403458,
|
| 1032 |
+
"learning_rate": 3.0050999999999997e-05,
|
| 1033 |
+
"loss": 23.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.005238459019971625,
|
| 1038 |
+
"grad_norm": 0.0006535375723615289,
|
| 1039 |
+
"learning_rate": 2.9523789473684206e-05,
|
| 1040 |
+
"loss": 23.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.005274837207610317,
|
| 1045 |
+
"grad_norm": 0.0005738306208513677,
|
| 1046 |
+
"learning_rate": 2.899657894736842e-05,
|
| 1047 |
+
"loss": 23.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.005311215395249009,
|
| 1052 |
+
"grad_norm": 0.000772025145124644,
|
| 1053 |
+
"learning_rate": 2.846936842105263e-05,
|
| 1054 |
+
"loss": 23.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.0053475935828877,
|
| 1059 |
+
"grad_norm": 0.0005988929769955575,
|
| 1060 |
+
"learning_rate": 2.794215789473684e-05,
|
| 1061 |
+
"loss": 23.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.005383971770526392,
|
| 1066 |
+
"grad_norm": 0.0005342272925190628,
|
| 1067 |
+
"learning_rate": 2.7414947368421056e-05,
|
| 1068 |
+
"loss": 23.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.005420349958165084,
|
| 1073 |
+
"grad_norm": 0.00029346125666052103,
|
| 1074 |
+
"learning_rate": 2.6887736842105264e-05,
|
| 1075 |
+
"loss": 23.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.005456728145803776,
|
| 1080 |
+
"grad_norm": 0.00020657299319282174,
|
| 1081 |
+
"learning_rate": 2.6360526315789472e-05,
|
| 1082 |
+
"loss": 23.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.005456728145803776,
|
| 1087 |
+
"eval_loss": 11.5,
|
| 1088 |
+
"eval_runtime": 151.0121,
|
| 1089 |
+
"eval_samples_per_second": 76.649,
|
| 1090 |
+
"eval_steps_per_second": 19.164,
|
| 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": 6049810808832.0,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|