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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3023053d501c3c6c92e25017ac17b7833ba47d662bc3b96335e33b1af0ba4a9d
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c50351eabc6c0390d88c3e543d74f312b6a9a2c94be5f33814b56a8328d207
|
| 3 |
size 325339796
|
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:ce77f5bcd382470614be890ecedbc1c5b65fc2941d097f54f562f397ee1b4204
|
| 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 sha256:55b21572f60c57282eaf510fd67405af43bbdd1915614e42250619ba76257dea
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 2.4987945556640625,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
-
"epoch":
|
| 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": 13.282,
|
| 732 |
"eval_steps_per_second": 3.32,
|
| 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": 2.4987945556640625,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 2.3529411764705883,
|
| 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": 13.282,
|
| 732 |
"eval_steps_per_second": 3.32,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.5843137254901962,
|
| 737 |
+
"grad_norm": 0.5022868514060974,
|
| 738 |
+
"learning_rate": 5e-05,
|
| 739 |
+
"loss": 2.2742,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.6,
|
| 744 |
+
"grad_norm": 0.5015295147895813,
|
| 745 |
+
"learning_rate": 4.913696795473058e-05,
|
| 746 |
+
"loss": 2.2551,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.615686274509804,
|
| 751 |
+
"grad_norm": 0.5870837569236755,
|
| 752 |
+
"learning_rate": 4.827419305151461e-05,
|
| 753 |
+
"loss": 2.2968,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.6313725490196078,
|
| 758 |
+
"grad_norm": 0.5984936356544495,
|
| 759 |
+
"learning_rate": 4.741193235578952e-05,
|
| 760 |
+
"loss": 2.4352,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.6470588235294117,
|
| 765 |
+
"grad_norm": 0.6345235705375671,
|
| 766 |
+
"learning_rate": 4.655044277978375e-05,
|
| 767 |
+
"loss": 2.3359,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.6627450980392156,
|
| 772 |
+
"grad_norm": 0.6582222580909729,
|
| 773 |
+
"learning_rate": 4.568998100596903e-05,
|
| 774 |
+
"loss": 2.3348,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.6784313725490196,
|
| 779 |
+
"grad_norm": 0.7701143622398376,
|
| 780 |
+
"learning_rate": 4.48308034105815e-05,
|
| 781 |
+
"loss": 2.201,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.6941176470588235,
|
| 786 |
+
"grad_norm": 0.884581983089447,
|
| 787 |
+
"learning_rate": 4.397316598723385e-05,
|
| 788 |
+
"loss": 2.4985,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.7098039215686276,
|
| 793 |
+
"grad_norm": 0.8130044937133789,
|
| 794 |
+
"learning_rate": 4.31173242706416e-05,
|
| 795 |
+
"loss": 2.6248,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.7254901960784315,
|
| 800 |
+
"grad_norm": 0.328084796667099,
|
| 801 |
+
"learning_rate": 4.226353326048593e-05,
|
| 802 |
+
"loss": 1.9045,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.7411764705882353,
|
| 807 |
+
"grad_norm": 0.4180457890033722,
|
| 808 |
+
"learning_rate": 4.1412047345436195e-05,
|
| 809 |
+
"loss": 2.2426,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.7568627450980392,
|
| 814 |
+
"grad_norm": 0.44295573234558105,
|
| 815 |
+
"learning_rate": 4.056312022735417e-05,
|
| 816 |
+
"loss": 2.3269,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.772549019607843,
|
| 821 |
+
"grad_norm": 0.4977704882621765,
|
| 822 |
+
"learning_rate": 3.971700484570318e-05,
|
| 823 |
+
"loss": 2.3613,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.788235294117647,
|
| 828 |
+
"grad_norm": 0.4835895597934723,
|
| 829 |
+
"learning_rate": 3.887395330218429e-05,
|
| 830 |
+
"loss": 2.3462,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.803921568627451,
|
| 835 |
+
"grad_norm": 0.5100789666175842,
|
| 836 |
+
"learning_rate": 3.803421678562213e-05,
|
| 837 |
+
"loss": 2.2091,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.8196078431372549,
|
| 842 |
+
"grad_norm": 0.5331653356552124,
|
| 843 |
+
"learning_rate": 3.719804549712265e-05,
|
| 844 |
+
"loss": 2.2373,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.835294117647059,
|
| 849 |
+
"grad_norm": 0.5414100885391235,
|
| 850 |
+
"learning_rate": 3.6365688575525315e-05,
|
| 851 |
+
"loss": 2.2153,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.8509803921568628,
|
| 856 |
+
"grad_norm": 0.5721606612205505,
|
| 857 |
+
"learning_rate": 3.553739402317162e-05,
|
| 858 |
+
"loss": 2.3138,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.8666666666666667,
|
| 863 |
+
"grad_norm": 0.5930068492889404,
|
| 864 |
+
"learning_rate": 3.471340863201237e-05,
|
| 865 |
+
"loss": 2.244,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.8823529411764706,
|
| 870 |
+
"grad_norm": 0.7018293738365173,
|
| 871 |
+
"learning_rate": 3.389397791007548e-05,
|
| 872 |
+
"loss": 2.2488,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.8980392156862744,
|
| 877 |
+
"grad_norm": 0.7131605744361877,
|
| 878 |
+
"learning_rate": 3.307934600831648e-05,
|
| 879 |
+
"loss": 2.1945,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.9137254901960783,
|
| 884 |
+
"grad_norm": 0.812116265296936,
|
| 885 |
+
"learning_rate": 3.226975564787322e-05,
|
| 886 |
+
"loss": 2.3625,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 1.9294117647058824,
|
| 891 |
+
"grad_norm": 0.9558323621749878,
|
| 892 |
+
"learning_rate": 3.146544804774663e-05,
|
| 893 |
+
"loss": 2.2682,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.9450980392156862,
|
| 898 |
+
"grad_norm": 0.9968075156211853,
|
| 899 |
+
"learning_rate": 3.066666285292906e-05,
|
| 900 |
+
"loss": 2.5473,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.9607843137254903,
|
| 905 |
+
"grad_norm": 0.38400799036026,
|
| 906 |
+
"learning_rate": 2.9873638063001628e-05,
|
| 907 |
+
"loss": 1.9606,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.9764705882352942,
|
| 912 |
+
"grad_norm": 0.5562489032745361,
|
| 913 |
+
"learning_rate": 2.9086609961221755e-05,
|
| 914 |
+
"loss": 2.3365,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.992156862745098,
|
| 919 |
+
"grad_norm": 0.9361739158630371,
|
| 920 |
+
"learning_rate": 2.8305813044122097e-05,
|
| 921 |
+
"loss": 2.5897,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.007843137254902,
|
| 926 |
+
"grad_norm": 0.9938849210739136,
|
| 927 |
+
"learning_rate": 2.7531479951641924e-05,
|
| 928 |
+
"loss": 2.6321,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.023529411764706,
|
| 933 |
+
"grad_norm": 0.39070141315460205,
|
| 934 |
+
"learning_rate": 2.6763841397811573e-05,
|
| 935 |
+
"loss": 2.0195,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.0392156862745097,
|
| 940 |
+
"grad_norm": 0.4302551746368408,
|
| 941 |
+
"learning_rate": 2.6003126102010695e-05,
|
| 942 |
+
"loss": 2.1712,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.0549019607843135,
|
| 947 |
+
"grad_norm": 0.44673267006874084,
|
| 948 |
+
"learning_rate": 2.5249560720820932e-05,
|
| 949 |
+
"loss": 2.2957,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.070588235294118,
|
| 954 |
+
"grad_norm": 0.4669826030731201,
|
| 955 |
+
"learning_rate": 2.450336978049322e-05,
|
| 956 |
+
"loss": 2.1386,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.0862745098039217,
|
| 961 |
+
"grad_norm": 0.48010262846946716,
|
| 962 |
+
"learning_rate": 2.37647756100496e-05,
|
| 963 |
+
"loss": 2.1393,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.1019607843137256,
|
| 968 |
+
"grad_norm": 0.5177429914474487,
|
| 969 |
+
"learning_rate": 2.3033998275040046e-05,
|
| 970 |
+
"loss": 2.2392,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.1176470588235294,
|
| 975 |
+
"grad_norm": 0.5121442675590515,
|
| 976 |
+
"learning_rate": 2.2311255511973345e-05,
|
| 977 |
+
"loss": 2.0218,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1333333333333333,
|
| 982 |
+
"grad_norm": 0.5644603371620178,
|
| 983 |
+
"learning_rate": 2.1596762663442218e-05,
|
| 984 |
+
"loss": 2.2426,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.149019607843137,
|
| 989 |
+
"grad_norm": 0.5926538705825806,
|
| 990 |
+
"learning_rate": 2.0890732613961478e-05,
|
| 991 |
+
"loss": 2.1036,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.164705882352941,
|
| 996 |
+
"grad_norm": 0.6267763376235962,
|
| 997 |
+
"learning_rate": 2.0193375726538737e-05,
|
| 998 |
+
"loss": 2.0515,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.180392156862745,
|
| 1003 |
+
"grad_norm": 0.7685708403587341,
|
| 1004 |
+
"learning_rate": 1.9504899779996355e-05,
|
| 1005 |
+
"loss": 2.0115,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.196078431372549,
|
| 1010 |
+
"grad_norm": 0.7948710918426514,
|
| 1011 |
+
"learning_rate": 1.8825509907063327e-05,
|
| 1012 |
+
"loss": 1.9578,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.211764705882353,
|
| 1017 |
+
"grad_norm": 0.9403231739997864,
|
| 1018 |
+
"learning_rate": 1.8155408533255553e-05,
|
| 1019 |
+
"loss": 2.1181,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.227450980392157,
|
| 1024 |
+
"grad_norm": 1.1127105951309204,
|
| 1025 |
+
"learning_rate": 1.749479531656279e-05,
|
| 1026 |
+
"loss": 2.0001,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.243137254901961,
|
| 1031 |
+
"grad_norm": 0.771511435508728,
|
| 1032 |
+
"learning_rate": 1.684386708796025e-05,
|
| 1033 |
+
"loss": 2.255,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.2588235294117647,
|
| 1038 |
+
"grad_norm": 0.44342976808547974,
|
| 1039 |
+
"learning_rate": 1.6202817792762282e-05,
|
| 1040 |
+
"loss": 2.1462,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.2745098039215685,
|
| 1045 |
+
"grad_norm": 0.4897748827934265,
|
| 1046 |
+
"learning_rate": 1.557183843283614e-05,
|
| 1047 |
+
"loss": 2.2906,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.2901960784313724,
|
| 1052 |
+
"grad_norm": 0.5105887651443481,
|
| 1053 |
+
"learning_rate": 1.4951117009692528e-05,
|
| 1054 |
+
"loss": 2.2308,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.3058823529411763,
|
| 1059 |
+
"grad_norm": 0.5891292691230774,
|
| 1060 |
+
"learning_rate": 1.4340838468470197e-05,
|
| 1061 |
+
"loss": 2.193,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.3215686274509806,
|
| 1066 |
+
"grad_norm": 0.6128895282745361,
|
| 1067 |
+
"learning_rate": 1.3741184642831189e-05,
|
| 1068 |
+
"loss": 2.3101,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.3372549019607844,
|
| 1073 |
+
"grad_norm": 0.6382685303688049,
|
| 1074 |
+
"learning_rate": 1.3152334200783167e-05,
|
| 1075 |
+
"loss": 2.2268,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.3529411764705883,
|
| 1080 |
+
"grad_norm": 0.661220133304596,
|
| 1081 |
+
"learning_rate": 1.257446259144494e-05,
|
| 1082 |
+
"loss": 2.1702,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.3529411764705883,
|
| 1087 |
+
"eval_loss": 2.535630941390991,
|
| 1088 |
+
"eval_runtime": 8.1303,
|
| 1089 |
+
"eval_samples_per_second": 13.284,
|
| 1090 |
+
"eval_steps_per_second": 3.321,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 1
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 2.0480900726784e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|