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 871457448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:109decc79381bd4a2f43d770dbba7a5a0202b716eb51975dcdda2fc522b915e6
|
| 3 |
size 871457448
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 443280340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6854b1efaf6b1339ba99a7a524ec5649dd17806c785851c40fdabe08bd5224ae
|
| 3 |
size 443280340
|
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:bd5dd7e829a1c23e4a8d6d91b99a4595ed3becf3d57bd240b5a9f50971e4761d
|
| 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 sha256:6f4002ee03f4202a6a410bde3375cd186d152ce129e8a177eb112bee1f18b1e2
|
| 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": 7.059,
|
| 732 |
"eval_steps_per_second": 1.766,
|
| 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": 0.38091349601745605,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.12317799219872716,
|
| 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": 7.059,
|
| 732 |
"eval_steps_per_second": 1.766,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.08293984808047629,
|
| 737 |
+
"grad_norm": 1.5546329021453857,
|
| 738 |
+
"learning_rate": 8.715724127386972e-05,
|
| 739 |
+
"loss": 0.5163,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.08376103469513448,
|
| 744 |
+
"grad_norm": 1.350873589515686,
|
| 745 |
+
"learning_rate": 8.688653405904652e-05,
|
| 746 |
+
"loss": 0.4791,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.08458222130979265,
|
| 751 |
+
"grad_norm": 0.984677255153656,
|
| 752 |
+
"learning_rate": 8.661343332988869e-05,
|
| 753 |
+
"loss": 0.3377,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.08540340792445084,
|
| 758 |
+
"grad_norm": 0.3391437530517578,
|
| 759 |
+
"learning_rate": 8.633795680751116e-05,
|
| 760 |
+
"loss": 0.2633,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.08622459453910901,
|
| 765 |
+
"grad_norm": 0.2502461373806,
|
| 766 |
+
"learning_rate": 8.606012236719073e-05,
|
| 767 |
+
"loss": 0.2567,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.0870457811537672,
|
| 772 |
+
"grad_norm": 0.28781577944755554,
|
| 773 |
+
"learning_rate": 8.577994803720606e-05,
|
| 774 |
+
"loss": 0.2769,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.08786696776842537,
|
| 779 |
+
"grad_norm": 0.30542901158332825,
|
| 780 |
+
"learning_rate": 8.549745199766792e-05,
|
| 781 |
+
"loss": 0.2965,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.08868815438308356,
|
| 786 |
+
"grad_norm": 0.3351757526397705,
|
| 787 |
+
"learning_rate": 8.521265257933948e-05,
|
| 788 |
+
"loss": 0.2774,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.08950934099774174,
|
| 793 |
+
"grad_norm": 0.2978907525539398,
|
| 794 |
+
"learning_rate": 8.492556826244687e-05,
|
| 795 |
+
"loss": 0.2744,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.09033052761239992,
|
| 800 |
+
"grad_norm": 0.2558261752128601,
|
| 801 |
+
"learning_rate": 8.463621767547998e-05,
|
| 802 |
+
"loss": 0.2312,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.0911517142270581,
|
| 807 |
+
"grad_norm": 0.30879148840904236,
|
| 808 |
+
"learning_rate": 8.434461959398376e-05,
|
| 809 |
+
"loss": 0.2845,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.09197290084171628,
|
| 814 |
+
"grad_norm": 0.309334397315979,
|
| 815 |
+
"learning_rate": 8.405079293933986e-05,
|
| 816 |
+
"loss": 0.266,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.09279408745637446,
|
| 821 |
+
"grad_norm": 0.3099028170108795,
|
| 822 |
+
"learning_rate": 8.375475677753881e-05,
|
| 823 |
+
"loss": 0.2692,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.09361527407103264,
|
| 828 |
+
"grad_norm": 0.30877748131752014,
|
| 829 |
+
"learning_rate": 8.345653031794292e-05,
|
| 830 |
+
"loss": 0.284,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.09443646068569082,
|
| 835 |
+
"grad_norm": 0.2932473123073578,
|
| 836 |
+
"learning_rate": 8.315613291203976e-05,
|
| 837 |
+
"loss": 0.268,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.09525764730034901,
|
| 842 |
+
"grad_norm": 0.337277889251709,
|
| 843 |
+
"learning_rate": 8.285358405218655e-05,
|
| 844 |
+
"loss": 0.2448,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.09607883391500718,
|
| 849 |
+
"grad_norm": 0.3811333477497101,
|
| 850 |
+
"learning_rate": 8.25489033703452e-05,
|
| 851 |
+
"loss": 0.293,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.09690002052966537,
|
| 856 |
+
"grad_norm": 0.34305429458618164,
|
| 857 |
+
"learning_rate": 8.224211063680853e-05,
|
| 858 |
+
"loss": 0.2596,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.09772120714432354,
|
| 863 |
+
"grad_norm": 0.3743656277656555,
|
| 864 |
+
"learning_rate": 8.19332257589174e-05,
|
| 865 |
+
"loss": 0.277,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.09854239375898173,
|
| 870 |
+
"grad_norm": 0.2987310290336609,
|
| 871 |
+
"learning_rate": 8.162226877976887e-05,
|
| 872 |
+
"loss": 0.2484,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.0993635803736399,
|
| 877 |
+
"grad_norm": 0.2911909222602844,
|
| 878 |
+
"learning_rate": 8.130925987691569e-05,
|
| 879 |
+
"loss": 0.2297,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.10018476698829809,
|
| 884 |
+
"grad_norm": 0.29610538482666016,
|
| 885 |
+
"learning_rate": 8.099421936105702e-05,
|
| 886 |
+
"loss": 0.2224,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.10100595360295628,
|
| 891 |
+
"grad_norm": 0.31938186287879944,
|
| 892 |
+
"learning_rate": 8.067716767472045e-05,
|
| 893 |
+
"loss": 0.2158,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.10182714021761445,
|
| 898 |
+
"grad_norm": 0.3307250440120697,
|
| 899 |
+
"learning_rate": 8.035812539093557e-05,
|
| 900 |
+
"loss": 0.2443,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.10264832683227264,
|
| 905 |
+
"grad_norm": 0.33900371193885803,
|
| 906 |
+
"learning_rate": 8.003711321189895e-05,
|
| 907 |
+
"loss": 0.2455,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.10346951344693081,
|
| 912 |
+
"grad_norm": 0.33954647183418274,
|
| 913 |
+
"learning_rate": 7.971415196763088e-05,
|
| 914 |
+
"loss": 0.2413,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.104290700061589,
|
| 919 |
+
"grad_norm": 0.3721504211425781,
|
| 920 |
+
"learning_rate": 7.938926261462366e-05,
|
| 921 |
+
"loss": 0.2724,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.10511188667624717,
|
| 926 |
+
"grad_norm": 0.3788248300552368,
|
| 927 |
+
"learning_rate": 7.906246623448183e-05,
|
| 928 |
+
"loss": 0.2727,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.10593307329090536,
|
| 933 |
+
"grad_norm": 0.3605785667896271,
|
| 934 |
+
"learning_rate": 7.873378403255419e-05,
|
| 935 |
+
"loss": 0.2781,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.10675425990556354,
|
| 940 |
+
"grad_norm": 0.33415114879608154,
|
| 941 |
+
"learning_rate": 7.840323733655778e-05,
|
| 942 |
+
"loss": 0.2226,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.10757544652022172,
|
| 947 |
+
"grad_norm": 0.43883877992630005,
|
| 948 |
+
"learning_rate": 7.807084759519405e-05,
|
| 949 |
+
"loss": 0.2474,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.1083966331348799,
|
| 954 |
+
"grad_norm": 0.3597790598869324,
|
| 955 |
+
"learning_rate": 7.773663637675694e-05,
|
| 956 |
+
"loss": 0.2375,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.10921781974953808,
|
| 961 |
+
"grad_norm": 0.41835817694664,
|
| 962 |
+
"learning_rate": 7.740062536773352e-05,
|
| 963 |
+
"loss": 0.2869,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.11003900636419627,
|
| 968 |
+
"grad_norm": 0.40062186121940613,
|
| 969 |
+
"learning_rate": 7.706283637139658e-05,
|
| 970 |
+
"loss": 0.2451,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.11086019297885444,
|
| 975 |
+
"grad_norm": 0.46534448862075806,
|
| 976 |
+
"learning_rate": 7.672329130639005e-05,
|
| 977 |
+
"loss": 0.2834,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.11168137959351263,
|
| 982 |
+
"grad_norm": 0.4524616599082947,
|
| 983 |
+
"learning_rate": 7.638201220530665e-05,
|
| 984 |
+
"loss": 0.2579,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.11250256620817081,
|
| 989 |
+
"grad_norm": 0.42796769738197327,
|
| 990 |
+
"learning_rate": 7.603902121325813e-05,
|
| 991 |
+
"loss": 0.2507,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.11332375282282899,
|
| 996 |
+
"grad_norm": 0.6147335767745972,
|
| 997 |
+
"learning_rate": 7.569434058643844e-05,
|
| 998 |
+
"loss": 0.2547,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.11414493943748717,
|
| 1003 |
+
"grad_norm": 0.5195381045341492,
|
| 1004 |
+
"learning_rate": 7.534799269067953e-05,
|
| 1005 |
+
"loss": 0.2429,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.11496612605214535,
|
| 1010 |
+
"grad_norm": 0.549555242061615,
|
| 1011 |
+
"learning_rate": 7.500000000000001e-05,
|
| 1012 |
+
"loss": 0.2826,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.11578731266680353,
|
| 1017 |
+
"grad_norm": 0.5704975128173828,
|
| 1018 |
+
"learning_rate": 7.465038509514688e-05,
|
| 1019 |
+
"loss": 0.2789,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.1166084992814617,
|
| 1024 |
+
"grad_norm": 0.6339702606201172,
|
| 1025 |
+
"learning_rate": 7.42991706621303e-05,
|
| 1026 |
+
"loss": 0.2289,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.11742968589611989,
|
| 1031 |
+
"grad_norm": 0.728171706199646,
|
| 1032 |
+
"learning_rate": 7.394637949075154e-05,
|
| 1033 |
+
"loss": 0.3104,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.11825087251077808,
|
| 1038 |
+
"grad_norm": 0.5731471180915833,
|
| 1039 |
+
"learning_rate": 7.35920344731241e-05,
|
| 1040 |
+
"loss": 0.2612,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.11907205912543625,
|
| 1045 |
+
"grad_norm": 0.7613599896430969,
|
| 1046 |
+
"learning_rate": 7.323615860218843e-05,
|
| 1047 |
+
"loss": 0.3024,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.11989324574009444,
|
| 1052 |
+
"grad_norm": 0.5790632963180542,
|
| 1053 |
+
"learning_rate": 7.287877497021978e-05,
|
| 1054 |
+
"loss": 0.2493,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.12071443235475261,
|
| 1059 |
+
"grad_norm": 0.746548593044281,
|
| 1060 |
+
"learning_rate": 7.251990676732984e-05,
|
| 1061 |
+
"loss": 0.2999,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.1215356189694108,
|
| 1066 |
+
"grad_norm": 0.7720208168029785,
|
| 1067 |
+
"learning_rate": 7.215957727996207e-05,
|
| 1068 |
+
"loss": 0.2836,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.12235680558406897,
|
| 1073 |
+
"grad_norm": 0.6100975275039673,
|
| 1074 |
+
"learning_rate": 7.179780988938051e-05,
|
| 1075 |
+
"loss": 0.2187,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.12317799219872716,
|
| 1080 |
+
"grad_norm": 0.7999358177185059,
|
| 1081 |
+
"learning_rate": 7.143462807015271e-05,
|
| 1082 |
+
"loss": 0.2709,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.12317799219872716,
|
| 1087 |
+
"eval_loss": 0.38091349601745605,
|
| 1088 |
+
"eval_runtime": 291.0342,
|
| 1089 |
+
"eval_samples_per_second": 7.047,
|
| 1090 |
+
"eval_steps_per_second": 1.763,
|
| 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": 2.6081050741230797e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|