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 sha256:7b7ba67764e20ec7e7cf08aaf507155ab814ee777e9e13399abe402796ac38f5
|
| 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 sha256:77316b840cc2eeffa1933748a4a539fbd1c2b6857c2b7cd1fdda9de95d4e0549
|
| 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 sha256:87e12fd30d46233701c67c290999192f2f6b8d472ea0605925c62aa6f5ec582f
|
| 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 sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
|
| 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": 73.119,
|
| 732 |
"eval_steps_per_second": 18.281,
|
| 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": 0.003019414837404511,
|
| 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": 73.119,
|
| 732 |
"eval_steps_per_second": 18.281,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.002033072657185704,
|
| 737 |
+
"grad_norm": 3.899659350281581e-05,
|
| 738 |
+
"learning_rate": 5.231368421052631e-05,
|
| 739 |
+
"loss": 23.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.0020532020894350675,
|
| 744 |
+
"grad_norm": 1.9528526536305435e-05,
|
| 745 |
+
"learning_rate": 5.178526315789474e-05,
|
| 746 |
+
"loss": 23.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.0020733315216844308,
|
| 751 |
+
"grad_norm": 3.4980272175744176e-05,
|
| 752 |
+
"learning_rate": 5.1256842105263165e-05,
|
| 753 |
+
"loss": 23.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.0020934609539337945,
|
| 758 |
+
"grad_norm": 3.446464324952103e-05,
|
| 759 |
+
"learning_rate": 5.072842105263158e-05,
|
| 760 |
+
"loss": 23.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.0021135903861831578,
|
| 765 |
+
"grad_norm": 2.7365793357603252e-05,
|
| 766 |
+
"learning_rate": 5.02e-05,
|
| 767 |
+
"loss": 23.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.002133719818432521,
|
| 772 |
+
"grad_norm": 6.427912740036845e-05,
|
| 773 |
+
"learning_rate": 4.967157894736842e-05,
|
| 774 |
+
"loss": 23.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.0021538492506818843,
|
| 779 |
+
"grad_norm": 2.2796304619987495e-05,
|
| 780 |
+
"learning_rate": 4.914315789473684e-05,
|
| 781 |
+
"loss": 23.0,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.002173978682931248,
|
| 786 |
+
"grad_norm": 3.622789154178463e-05,
|
| 787 |
+
"learning_rate": 4.861473684210526e-05,
|
| 788 |
+
"loss": 23.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.0021941081151806113,
|
| 793 |
+
"grad_norm": 2.9890994483139366e-05,
|
| 794 |
+
"learning_rate": 4.8086315789473686e-05,
|
| 795 |
+
"loss": 23.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.0022142375474299746,
|
| 800 |
+
"grad_norm": 4.680438360082917e-05,
|
| 801 |
+
"learning_rate": 4.7557894736842104e-05,
|
| 802 |
+
"loss": 23.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.0022343669796793383,
|
| 807 |
+
"grad_norm": 4.3207284761592746e-05,
|
| 808 |
+
"learning_rate": 4.702947368421053e-05,
|
| 809 |
+
"loss": 23.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.0022544964119287016,
|
| 814 |
+
"grad_norm": 3.4467164368834347e-05,
|
| 815 |
+
"learning_rate": 4.6501052631578946e-05,
|
| 816 |
+
"loss": 23.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.002274625844178065,
|
| 821 |
+
"grad_norm": 4.459037154447287e-05,
|
| 822 |
+
"learning_rate": 4.5972631578947364e-05,
|
| 823 |
+
"loss": 23.0,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.0022947552764274286,
|
| 828 |
+
"grad_norm": 5.37286905455403e-05,
|
| 829 |
+
"learning_rate": 4.544421052631579e-05,
|
| 830 |
+
"loss": 23.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.002314884708676792,
|
| 835 |
+
"grad_norm": 5.072938438388519e-05,
|
| 836 |
+
"learning_rate": 4.4915789473684213e-05,
|
| 837 |
+
"loss": 23.0,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.002335014140926155,
|
| 842 |
+
"grad_norm": 3.0260003768489696e-05,
|
| 843 |
+
"learning_rate": 4.438736842105263e-05,
|
| 844 |
+
"loss": 23.0,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.0023551435731755184,
|
| 849 |
+
"grad_norm": 5.488552415044978e-05,
|
| 850 |
+
"learning_rate": 4.3858947368421056e-05,
|
| 851 |
+
"loss": 23.0,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.002375273005424882,
|
| 856 |
+
"grad_norm": 3.486787682049908e-05,
|
| 857 |
+
"learning_rate": 4.3330526315789474e-05,
|
| 858 |
+
"loss": 23.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.0023954024376742454,
|
| 863 |
+
"grad_norm": 4.800608439836651e-05,
|
| 864 |
+
"learning_rate": 4.280210526315789e-05,
|
| 865 |
+
"loss": 23.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.0024155318699236087,
|
| 870 |
+
"grad_norm": 6.630933785345405e-05,
|
| 871 |
+
"learning_rate": 4.2273684210526317e-05,
|
| 872 |
+
"loss": 23.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.0024356613021729724,
|
| 877 |
+
"grad_norm": 2.0091678379685618e-05,
|
| 878 |
+
"learning_rate": 4.174526315789474e-05,
|
| 879 |
+
"loss": 23.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.0024557907344223357,
|
| 884 |
+
"grad_norm": 5.247927037999034e-05,
|
| 885 |
+
"learning_rate": 4.121684210526316e-05,
|
| 886 |
+
"loss": 23.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.002475920166671699,
|
| 891 |
+
"grad_norm": 8.598071872256696e-05,
|
| 892 |
+
"learning_rate": 4.068842105263158e-05,
|
| 893 |
+
"loss": 23.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.0024960495989210622,
|
| 898 |
+
"grad_norm": 4.097522469237447e-05,
|
| 899 |
+
"learning_rate": 4.016e-05,
|
| 900 |
+
"loss": 23.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.002516179031170426,
|
| 905 |
+
"grad_norm": 5.331883585313335e-05,
|
| 906 |
+
"learning_rate": 3.963157894736842e-05,
|
| 907 |
+
"loss": 23.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.0025363084634197892,
|
| 912 |
+
"grad_norm": 5.928654718445614e-05,
|
| 913 |
+
"learning_rate": 3.9103157894736844e-05,
|
| 914 |
+
"loss": 23.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.0025564378956691525,
|
| 919 |
+
"grad_norm": 6.587509415112436e-05,
|
| 920 |
+
"learning_rate": 3.857473684210526e-05,
|
| 921 |
+
"loss": 23.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.0025765673279185162,
|
| 926 |
+
"grad_norm": 8.765143866185099e-05,
|
| 927 |
+
"learning_rate": 3.804631578947369e-05,
|
| 928 |
+
"loss": 23.0,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.0025966967601678795,
|
| 933 |
+
"grad_norm": 0.0001506681728642434,
|
| 934 |
+
"learning_rate": 3.7517894736842105e-05,
|
| 935 |
+
"loss": 23.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.0026168261924172428,
|
| 940 |
+
"grad_norm": 8.650772360851988e-05,
|
| 941 |
+
"learning_rate": 3.698947368421052e-05,
|
| 942 |
+
"loss": 23.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.0026369556246666065,
|
| 947 |
+
"grad_norm": 4.020520282210782e-05,
|
| 948 |
+
"learning_rate": 3.646105263157895e-05,
|
| 949 |
+
"loss": 23.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.0026570850569159698,
|
| 954 |
+
"grad_norm": 6.1138161981944e-05,
|
| 955 |
+
"learning_rate": 3.593263157894737e-05,
|
| 956 |
+
"loss": 23.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.002677214489165333,
|
| 961 |
+
"grad_norm": 6.121417391113937e-05,
|
| 962 |
+
"learning_rate": 3.540421052631579e-05,
|
| 963 |
+
"loss": 23.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.0026973439214146963,
|
| 968 |
+
"grad_norm": 7.352145621553063e-05,
|
| 969 |
+
"learning_rate": 3.4875789473684215e-05,
|
| 970 |
+
"loss": 23.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.00271747335366406,
|
| 975 |
+
"grad_norm": 0.00014084699796512723,
|
| 976 |
+
"learning_rate": 3.434736842105263e-05,
|
| 977 |
+
"loss": 23.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.0027376027859134233,
|
| 982 |
+
"grad_norm": 0.0001324174227192998,
|
| 983 |
+
"learning_rate": 3.381894736842105e-05,
|
| 984 |
+
"loss": 23.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.0027577322181627866,
|
| 989 |
+
"grad_norm": 8.251784311141819e-05,
|
| 990 |
+
"learning_rate": 3.329052631578947e-05,
|
| 991 |
+
"loss": 23.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.0027778616504121503,
|
| 996 |
+
"grad_norm": 9.526171197649091e-05,
|
| 997 |
+
"learning_rate": 3.27621052631579e-05,
|
| 998 |
+
"loss": 23.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.0027979910826615136,
|
| 1003 |
+
"grad_norm": 6.26833934802562e-05,
|
| 1004 |
+
"learning_rate": 3.223368421052632e-05,
|
| 1005 |
+
"loss": 23.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.002818120514910877,
|
| 1010 |
+
"grad_norm": 7.219661347335204e-05,
|
| 1011 |
+
"learning_rate": 3.1705263157894736e-05,
|
| 1012 |
+
"loss": 23.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.00283824994716024,
|
| 1017 |
+
"grad_norm": 9.838396363193169e-05,
|
| 1018 |
+
"learning_rate": 3.117684210526316e-05,
|
| 1019 |
+
"loss": 23.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.002858379379409604,
|
| 1024 |
+
"grad_norm": 9.525923087494448e-05,
|
| 1025 |
+
"learning_rate": 3.064842105263158e-05,
|
| 1026 |
+
"loss": 23.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.002878508811658967,
|
| 1031 |
+
"grad_norm": 0.00010386522626504302,
|
| 1032 |
+
"learning_rate": 3.012e-05,
|
| 1033 |
+
"loss": 23.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.0028986382439083304,
|
| 1038 |
+
"grad_norm": 0.0001148344308603555,
|
| 1039 |
+
"learning_rate": 2.9591578947368418e-05,
|
| 1040 |
+
"loss": 23.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.002918767676157694,
|
| 1045 |
+
"grad_norm": 0.00014382245717570186,
|
| 1046 |
+
"learning_rate": 2.9063157894736842e-05,
|
| 1047 |
+
"loss": 23.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.0029388971084070574,
|
| 1052 |
+
"grad_norm": 5.8804893342312425e-05,
|
| 1053 |
+
"learning_rate": 2.8534736842105264e-05,
|
| 1054 |
+
"loss": 23.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.0029590265406564207,
|
| 1059 |
+
"grad_norm": 0.00017164551536552608,
|
| 1060 |
+
"learning_rate": 2.800631578947368e-05,
|
| 1061 |
+
"loss": 23.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.0029791559729057844,
|
| 1066 |
+
"grad_norm": 0.00011976063979091123,
|
| 1067 |
+
"learning_rate": 2.7477894736842106e-05,
|
| 1068 |
+
"loss": 23.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.0029992854051551477,
|
| 1073 |
+
"grad_norm": 0.0002357963821850717,
|
| 1074 |
+
"learning_rate": 2.6949473684210527e-05,
|
| 1075 |
+
"loss": 23.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.003019414837404511,
|
| 1080 |
+
"grad_norm": 0.0001414159924024716,
|
| 1081 |
+
"learning_rate": 2.6421052631578945e-05,
|
| 1082 |
+
"loss": 23.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.003019414837404511,
|
| 1087 |
+
"eval_loss": 11.5,
|
| 1088 |
+
"eval_runtime": 285.9123,
|
| 1089 |
+
"eval_samples_per_second": 73.162,
|
| 1090 |
+
"eval_steps_per_second": 18.292,
|
| 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": 6210603122688.0,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|