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:e4355ac5284188f49afbe931cac88d748f666b029124d3b650a893077882e5ed
|
| 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 sha256:683bc60fb360f1653958fab3ce5e8cbca3b98961f93e0053c58325e1b0b75a5a
|
| 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 sha256:49f0adc1ae60506260d0c1807e4519bcf2fbcd648df2e4b6e16ee911303b7101
|
| 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:ef91cf09f7b6a58a39bbfe1ef78ac2fa91c0c15ca1705097a187d272d0433d8d
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 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": 5.102,
|
| 732 |
"eval_steps_per_second": 1.282,
|
| 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": 0.0008732560090720654,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.32397408207343414,
|
| 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": 5.102,
|
| 732 |
"eval_steps_per_second": 1.282,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.21814254859611232,
|
| 737 |
+
"grad_norm": 0.23118843138217926,
|
| 738 |
+
"learning_rate": 5.24178947368421e-05,
|
| 739 |
+
"loss": 0.0068,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.2203023758099352,
|
| 744 |
+
"grad_norm": 0.07103104144334793,
|
| 745 |
+
"learning_rate": 5.1888421052631585e-05,
|
| 746 |
+
"loss": 0.0039,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.2224622030237581,
|
| 751 |
+
"grad_norm": 0.03884083777666092,
|
| 752 |
+
"learning_rate": 5.135894736842106e-05,
|
| 753 |
+
"loss": 0.0021,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.22462203023758098,
|
| 758 |
+
"grad_norm": 0.01880479045212269,
|
| 759 |
+
"learning_rate": 5.082947368421053e-05,
|
| 760 |
+
"loss": 0.0009,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2267818574514039,
|
| 765 |
+
"grad_norm": 0.0531153567135334,
|
| 766 |
+
"learning_rate": 5.03e-05,
|
| 767 |
+
"loss": 0.001,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.22894168466522677,
|
| 772 |
+
"grad_norm": 0.053985074162483215,
|
| 773 |
+
"learning_rate": 4.977052631578947e-05,
|
| 774 |
+
"loss": 0.0013,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.23110151187904968,
|
| 779 |
+
"grad_norm": 0.037867240607738495,
|
| 780 |
+
"learning_rate": 4.924105263157895e-05,
|
| 781 |
+
"loss": 0.0023,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.23326133909287258,
|
| 786 |
+
"grad_norm": 0.11338239908218384,
|
| 787 |
+
"learning_rate": 4.871157894736843e-05,
|
| 788 |
+
"loss": 0.0024,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.23542116630669546,
|
| 793 |
+
"grad_norm": 0.014712098054587841,
|
| 794 |
+
"learning_rate": 4.81821052631579e-05,
|
| 795 |
+
"loss": 0.0009,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.23758099352051837,
|
| 800 |
+
"grad_norm": 0.03086118772625923,
|
| 801 |
+
"learning_rate": 4.765263157894737e-05,
|
| 802 |
+
"loss": 0.001,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.23974082073434125,
|
| 807 |
+
"grad_norm": 0.013892450369894505,
|
| 808 |
+
"learning_rate": 4.7123157894736845e-05,
|
| 809 |
+
"loss": 0.0005,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.24190064794816415,
|
| 814 |
+
"grad_norm": 0.2487848550081253,
|
| 815 |
+
"learning_rate": 4.6593684210526316e-05,
|
| 816 |
+
"loss": 0.0082,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.24406047516198703,
|
| 821 |
+
"grad_norm": 0.11459369212388992,
|
| 822 |
+
"learning_rate": 4.606421052631579e-05,
|
| 823 |
+
"loss": 0.0037,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.24622030237580994,
|
| 828 |
+
"grad_norm": 0.07744896411895752,
|
| 829 |
+
"learning_rate": 4.553473684210527e-05,
|
| 830 |
+
"loss": 0.0023,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.24838012958963282,
|
| 835 |
+
"grad_norm": 0.10101820528507233,
|
| 836 |
+
"learning_rate": 4.500526315789474e-05,
|
| 837 |
+
"loss": 0.0034,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.2505399568034557,
|
| 842 |
+
"grad_norm": 0.007767634466290474,
|
| 843 |
+
"learning_rate": 4.447578947368421e-05,
|
| 844 |
+
"loss": 0.0003,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.2526997840172786,
|
| 849 |
+
"grad_norm": 0.10766242444515228,
|
| 850 |
+
"learning_rate": 4.394631578947369e-05,
|
| 851 |
+
"loss": 0.0012,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.2548596112311015,
|
| 856 |
+
"grad_norm": 0.008573450148105621,
|
| 857 |
+
"learning_rate": 4.341684210526316e-05,
|
| 858 |
+
"loss": 0.0003,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.2570194384449244,
|
| 863 |
+
"grad_norm": 0.0011212700046598911,
|
| 864 |
+
"learning_rate": 4.2887368421052636e-05,
|
| 865 |
+
"loss": 0.0001,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.2591792656587473,
|
| 870 |
+
"grad_norm": 0.005315995309501886,
|
| 871 |
+
"learning_rate": 4.2357894736842106e-05,
|
| 872 |
+
"loss": 0.0002,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.2613390928725702,
|
| 877 |
+
"grad_norm": 0.0370321199297905,
|
| 878 |
+
"learning_rate": 4.182842105263158e-05,
|
| 879 |
+
"loss": 0.0002,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.2634989200863931,
|
| 884 |
+
"grad_norm": 0.0062796249985694885,
|
| 885 |
+
"learning_rate": 4.1298947368421053e-05,
|
| 886 |
+
"loss": 0.0002,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.265658747300216,
|
| 891 |
+
"grad_norm": 0.06505784392356873,
|
| 892 |
+
"learning_rate": 4.0769473684210524e-05,
|
| 893 |
+
"loss": 0.0004,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.2678185745140389,
|
| 898 |
+
"grad_norm": 0.11662036925554276,
|
| 899 |
+
"learning_rate": 4.024000000000001e-05,
|
| 900 |
+
"loss": 0.0003,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.26997840172786175,
|
| 905 |
+
"grad_norm": 0.01756948232650757,
|
| 906 |
+
"learning_rate": 3.971052631578948e-05,
|
| 907 |
+
"loss": 0.0003,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.27213822894168466,
|
| 912 |
+
"grad_norm": 0.01176679227501154,
|
| 913 |
+
"learning_rate": 3.918105263157895e-05,
|
| 914 |
+
"loss": 0.0002,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.27429805615550756,
|
| 919 |
+
"grad_norm": 0.16879205405712128,
|
| 920 |
+
"learning_rate": 3.865157894736842e-05,
|
| 921 |
+
"loss": 0.0051,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.27645788336933047,
|
| 926 |
+
"grad_norm": 0.015613168478012085,
|
| 927 |
+
"learning_rate": 3.8122105263157896e-05,
|
| 928 |
+
"loss": 0.0003,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.2786177105831533,
|
| 933 |
+
"grad_norm": 0.001986750401556492,
|
| 934 |
+
"learning_rate": 3.759263157894737e-05,
|
| 935 |
+
"loss": 0.0001,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.28077753779697623,
|
| 940 |
+
"grad_norm": 0.008711952716112137,
|
| 941 |
+
"learning_rate": 3.7063157894736844e-05,
|
| 942 |
+
"loss": 0.0003,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.28293736501079914,
|
| 947 |
+
"grad_norm": 0.0025189965963363647,
|
| 948 |
+
"learning_rate": 3.653368421052632e-05,
|
| 949 |
+
"loss": 0.0001,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.28509719222462204,
|
| 954 |
+
"grad_norm": 0.0006644928944297135,
|
| 955 |
+
"learning_rate": 3.600421052631579e-05,
|
| 956 |
+
"loss": 0.0001,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.28725701943844495,
|
| 961 |
+
"grad_norm": 0.0026721965987235308,
|
| 962 |
+
"learning_rate": 3.547473684210526e-05,
|
| 963 |
+
"loss": 0.0002,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.2894168466522678,
|
| 968 |
+
"grad_norm": 0.015398127026855946,
|
| 969 |
+
"learning_rate": 3.494526315789474e-05,
|
| 970 |
+
"loss": 0.0001,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.2915766738660907,
|
| 975 |
+
"grad_norm": 0.014543671160936356,
|
| 976 |
+
"learning_rate": 3.4415789473684216e-05,
|
| 977 |
+
"loss": 0.0003,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.2937365010799136,
|
| 982 |
+
"grad_norm": 0.006670842412859201,
|
| 983 |
+
"learning_rate": 3.3886315789473686e-05,
|
| 984 |
+
"loss": 0.0001,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.2958963282937365,
|
| 989 |
+
"grad_norm": 0.005377969238907099,
|
| 990 |
+
"learning_rate": 3.3356842105263156e-05,
|
| 991 |
+
"loss": 0.0002,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.2980561555075594,
|
| 996 |
+
"grad_norm": 0.0062574828043580055,
|
| 997 |
+
"learning_rate": 3.2827368421052634e-05,
|
| 998 |
+
"loss": 0.0002,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.3002159827213823,
|
| 1003 |
+
"grad_norm": 0.14523354172706604,
|
| 1004 |
+
"learning_rate": 3.2297894736842104e-05,
|
| 1005 |
+
"loss": 0.0145,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.3023758099352052,
|
| 1010 |
+
"grad_norm": 0.010900533758103848,
|
| 1011 |
+
"learning_rate": 3.176842105263158e-05,
|
| 1012 |
+
"loss": 0.0002,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.3045356371490281,
|
| 1017 |
+
"grad_norm": 0.010036949999630451,
|
| 1018 |
+
"learning_rate": 3.123894736842106e-05,
|
| 1019 |
+
"loss": 0.0001,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.30669546436285094,
|
| 1024 |
+
"grad_norm": 0.598667562007904,
|
| 1025 |
+
"learning_rate": 3.070947368421053e-05,
|
| 1026 |
+
"loss": 0.0035,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.30885529157667385,
|
| 1031 |
+
"grad_norm": 0.002981688594445586,
|
| 1032 |
+
"learning_rate": 3.018e-05,
|
| 1033 |
+
"loss": 0.0001,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.31101511879049676,
|
| 1038 |
+
"grad_norm": 0.0013599407393485308,
|
| 1039 |
+
"learning_rate": 2.9650526315789473e-05,
|
| 1040 |
+
"loss": 0.0001,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.31317494600431967,
|
| 1045 |
+
"grad_norm": 0.5247439742088318,
|
| 1046 |
+
"learning_rate": 2.912105263157895e-05,
|
| 1047 |
+
"loss": 0.0167,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.31533477321814257,
|
| 1052 |
+
"grad_norm": 0.004649030510336161,
|
| 1053 |
+
"learning_rate": 2.8591578947368424e-05,
|
| 1054 |
+
"loss": 0.0002,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.3174946004319654,
|
| 1059 |
+
"grad_norm": 0.0023146297316998243,
|
| 1060 |
+
"learning_rate": 2.8062105263157894e-05,
|
| 1061 |
+
"loss": 0.0001,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.31965442764578833,
|
| 1066 |
+
"grad_norm": 0.4256044328212738,
|
| 1067 |
+
"learning_rate": 2.753263157894737e-05,
|
| 1068 |
+
"loss": 0.0243,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.32181425485961124,
|
| 1073 |
+
"grad_norm": 0.22870223224163055,
|
| 1074 |
+
"learning_rate": 2.7003157894736845e-05,
|
| 1075 |
+
"loss": 0.0005,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.32397408207343414,
|
| 1080 |
+
"grad_norm": 5.829990386962891,
|
| 1081 |
+
"learning_rate": 2.6473684210526315e-05,
|
| 1082 |
+
"loss": 0.0135,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.32397408207343414,
|
| 1087 |
+
"eval_loss": 0.0008732560090720654,
|
| 1088 |
+
"eval_runtime": 38.606,
|
| 1089 |
+
"eval_samples_per_second": 5.051,
|
| 1090 |
+
"eval_steps_per_second": 1.269,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 0
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 7.467142214791987e+16,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|