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 sha256:43defb1f5e0d7ce124fdf220f0f615f346ff076541d33b2f935b093b00f7b7a8
|
| 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:aed438e6b849a7d4768640d83c9215afb87cf376ef2d9fdf5aafd04dd215e59d
|
| 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:c3a53760cb67d7d7ae8b0f88808159722250a231b998b4809ac2b27aad179665
|
| 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 sha256:2d094abeb22730ed8a1a30db0af3a1ac1bd1a9d1fcc8794319a4b828d3c7261c
|
| 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": 80.161,
|
| 732 |
"eval_steps_per_second": 20.048,
|
| 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": 0.02531218359770503,
|
| 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": 80.161,
|
| 732 |
"eval_steps_per_second": 20.048,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.017043536955788054,
|
| 737 |
+
"grad_norm": 7.682123396079987e-05,
|
| 738 |
+
"learning_rate": 5.246999999999999e-05,
|
| 739 |
+
"loss": 23.0,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.01721228484643942,
|
| 744 |
+
"grad_norm": 7.189896132331342e-05,
|
| 745 |
+
"learning_rate": 5.194e-05,
|
| 746 |
+
"loss": 23.0,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.017381032737090785,
|
| 751 |
+
"grad_norm": 6.011120058246888e-05,
|
| 752 |
+
"learning_rate": 5.141e-05,
|
| 753 |
+
"loss": 23.0,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.017549780627742154,
|
| 758 |
+
"grad_norm": 6.253538595046848e-05,
|
| 759 |
+
"learning_rate": 5.088e-05,
|
| 760 |
+
"loss": 23.0,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.01771852851839352,
|
| 765 |
+
"grad_norm": 5.117239925311878e-05,
|
| 766 |
+
"learning_rate": 5.035e-05,
|
| 767 |
+
"loss": 23.0,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.017887276409044885,
|
| 772 |
+
"grad_norm": 8.745577360969037e-05,
|
| 773 |
+
"learning_rate": 4.9819999999999994e-05,
|
| 774 |
+
"loss": 23.0,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.018056024299696254,
|
| 779 |
+
"grad_norm": 0.00013368716463446617,
|
| 780 |
+
"learning_rate": 4.929e-05,
|
| 781 |
+
"loss": 23.0,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.01822477219034762,
|
| 786 |
+
"grad_norm": 9.314952330896631e-05,
|
| 787 |
+
"learning_rate": 4.876e-05,
|
| 788 |
+
"loss": 23.0,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.01839352008099899,
|
| 793 |
+
"grad_norm": 0.0001433063152944669,
|
| 794 |
+
"learning_rate": 4.823e-05,
|
| 795 |
+
"loss": 23.0,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.018562267971650354,
|
| 800 |
+
"grad_norm": 5.847116335644387e-05,
|
| 801 |
+
"learning_rate": 4.7699999999999994e-05,
|
| 802 |
+
"loss": 23.0,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.01873101586230172,
|
| 807 |
+
"grad_norm": 8.442316902801394e-05,
|
| 808 |
+
"learning_rate": 4.717e-05,
|
| 809 |
+
"loss": 23.0,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.01889976375295309,
|
| 814 |
+
"grad_norm": 0.00013739695714320987,
|
| 815 |
+
"learning_rate": 4.6639999999999994e-05,
|
| 816 |
+
"loss": 23.0,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.019068511643604454,
|
| 821 |
+
"grad_norm": 0.00012455254909582436,
|
| 822 |
+
"learning_rate": 4.611e-05,
|
| 823 |
+
"loss": 23.0,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.019237259534255823,
|
| 828 |
+
"grad_norm": 5.286196028464474e-05,
|
| 829 |
+
"learning_rate": 4.558e-05,
|
| 830 |
+
"loss": 23.0,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.01940600742490719,
|
| 835 |
+
"grad_norm": 0.00013484164082910866,
|
| 836 |
+
"learning_rate": 4.505e-05,
|
| 837 |
+
"loss": 23.0,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.019574755315558554,
|
| 842 |
+
"grad_norm": 0.00012526288628578186,
|
| 843 |
+
"learning_rate": 4.4519999999999994e-05,
|
| 844 |
+
"loss": 23.0,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.019743503206209923,
|
| 849 |
+
"grad_norm": 0.00020170622156001627,
|
| 850 |
+
"learning_rate": 4.399e-05,
|
| 851 |
+
"loss": 23.0,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.01991225109686129,
|
| 856 |
+
"grad_norm": 8.426374552072957e-05,
|
| 857 |
+
"learning_rate": 4.346e-05,
|
| 858 |
+
"loss": 23.0,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.020080998987512658,
|
| 863 |
+
"grad_norm": 0.00027226656675338745,
|
| 864 |
+
"learning_rate": 4.293e-05,
|
| 865 |
+
"loss": 23.0,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.020249746878164023,
|
| 870 |
+
"grad_norm": 0.00015929453365970403,
|
| 871 |
+
"learning_rate": 4.2399999999999994e-05,
|
| 872 |
+
"loss": 23.0,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.02041849476881539,
|
| 877 |
+
"grad_norm": 0.00010509557614568621,
|
| 878 |
+
"learning_rate": 4.187e-05,
|
| 879 |
+
"loss": 23.0,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.020587242659466758,
|
| 884 |
+
"grad_norm": 0.0001663622388150543,
|
| 885 |
+
"learning_rate": 4.134e-05,
|
| 886 |
+
"loss": 23.0,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.020755990550118123,
|
| 891 |
+
"grad_norm": 0.0001297971175517887,
|
| 892 |
+
"learning_rate": 4.081e-05,
|
| 893 |
+
"loss": 23.0,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.020924738440769492,
|
| 898 |
+
"grad_norm": 0.0001566116261528805,
|
| 899 |
+
"learning_rate": 4.028e-05,
|
| 900 |
+
"loss": 23.0,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.021093486331420858,
|
| 905 |
+
"grad_norm": 0.00023184812744148076,
|
| 906 |
+
"learning_rate": 3.975e-05,
|
| 907 |
+
"loss": 23.0,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.021262234222072223,
|
| 912 |
+
"grad_norm": 0.0001358414883725345,
|
| 913 |
+
"learning_rate": 3.9219999999999994e-05,
|
| 914 |
+
"loss": 23.0,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.021430982112723592,
|
| 919 |
+
"grad_norm": 0.00010918582847807556,
|
| 920 |
+
"learning_rate": 3.869e-05,
|
| 921 |
+
"loss": 23.0,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.021599730003374958,
|
| 926 |
+
"grad_norm": 0.0001907457917695865,
|
| 927 |
+
"learning_rate": 3.816e-05,
|
| 928 |
+
"loss": 23.0,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.021768477894026323,
|
| 933 |
+
"grad_norm": 0.00012014003732474521,
|
| 934 |
+
"learning_rate": 3.763e-05,
|
| 935 |
+
"loss": 23.0,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.021937225784677692,
|
| 940 |
+
"grad_norm": 0.00033094800892286,
|
| 941 |
+
"learning_rate": 3.7099999999999994e-05,
|
| 942 |
+
"loss": 23.0,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.022105973675329058,
|
| 947 |
+
"grad_norm": 0.0001388384698657319,
|
| 948 |
+
"learning_rate": 3.657e-05,
|
| 949 |
+
"loss": 23.0,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.022274721565980427,
|
| 954 |
+
"grad_norm": 0.00015554000856354833,
|
| 955 |
+
"learning_rate": 3.604e-05,
|
| 956 |
+
"loss": 23.0,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.022443469456631792,
|
| 961 |
+
"grad_norm": 0.0001033740772982128,
|
| 962 |
+
"learning_rate": 3.551e-05,
|
| 963 |
+
"loss": 23.0,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.022612217347283158,
|
| 968 |
+
"grad_norm": 0.00017761386698111892,
|
| 969 |
+
"learning_rate": 3.498e-05,
|
| 970 |
+
"loss": 23.0,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.022780965237934526,
|
| 975 |
+
"grad_norm": 0.0001914931199280545,
|
| 976 |
+
"learning_rate": 3.445e-05,
|
| 977 |
+
"loss": 23.0,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.022949713128585892,
|
| 982 |
+
"grad_norm": 0.0001077301349141635,
|
| 983 |
+
"learning_rate": 3.392e-05,
|
| 984 |
+
"loss": 23.0,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.02311846101923726,
|
| 989 |
+
"grad_norm": 0.00014837745402473956,
|
| 990 |
+
"learning_rate": 3.339e-05,
|
| 991 |
+
"loss": 23.0,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.023287208909888626,
|
| 996 |
+
"grad_norm": 0.00013769303041044623,
|
| 997 |
+
"learning_rate": 3.286e-05,
|
| 998 |
+
"loss": 23.0,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.023455956800539992,
|
| 1003 |
+
"grad_norm": 0.00011395317415008321,
|
| 1004 |
+
"learning_rate": 3.233e-05,
|
| 1005 |
+
"loss": 23.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.02362470469119136,
|
| 1010 |
+
"grad_norm": 0.0002430876047583297,
|
| 1011 |
+
"learning_rate": 3.1799999999999994e-05,
|
| 1012 |
+
"loss": 23.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.023793452581842726,
|
| 1017 |
+
"grad_norm": 0.00016095052706077695,
|
| 1018 |
+
"learning_rate": 3.1270000000000004e-05,
|
| 1019 |
+
"loss": 23.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.023962200472494095,
|
| 1024 |
+
"grad_norm": 0.00023896507627796382,
|
| 1025 |
+
"learning_rate": 3.074e-05,
|
| 1026 |
+
"loss": 23.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.02413094836314546,
|
| 1031 |
+
"grad_norm": 0.0002305787493241951,
|
| 1032 |
+
"learning_rate": 3.0209999999999997e-05,
|
| 1033 |
+
"loss": 23.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.024299696253796826,
|
| 1038 |
+
"grad_norm": 0.00044004127266816795,
|
| 1039 |
+
"learning_rate": 2.9679999999999997e-05,
|
| 1040 |
+
"loss": 23.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.024468444144448195,
|
| 1045 |
+
"grad_norm": 0.0004754870606120676,
|
| 1046 |
+
"learning_rate": 2.915e-05,
|
| 1047 |
+
"loss": 23.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.02463719203509956,
|
| 1052 |
+
"grad_norm": 0.00039452221244573593,
|
| 1053 |
+
"learning_rate": 2.8619999999999997e-05,
|
| 1054 |
+
"loss": 23.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.02480593992575093,
|
| 1059 |
+
"grad_norm": 0.0002141989243682474,
|
| 1060 |
+
"learning_rate": 2.8089999999999997e-05,
|
| 1061 |
+
"loss": 23.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.024974687816402295,
|
| 1066 |
+
"grad_norm": 0.00038773109554313123,
|
| 1067 |
+
"learning_rate": 2.756e-05,
|
| 1068 |
+
"loss": 23.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.02514343570705366,
|
| 1073 |
+
"grad_norm": 0.00020906349527649581,
|
| 1074 |
+
"learning_rate": 2.703e-05,
|
| 1075 |
+
"loss": 23.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.02531218359770503,
|
| 1080 |
+
"grad_norm": 0.00029203391750343144,
|
| 1081 |
+
"learning_rate": 2.6499999999999997e-05,
|
| 1082 |
+
"loss": 23.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.02531218359770503,
|
| 1087 |
+
"eval_loss": 11.5,
|
| 1088 |
+
"eval_runtime": 31.0725,
|
| 1089 |
+
"eval_samples_per_second": 80.296,
|
| 1090 |
+
"eval_steps_per_second": 20.082,
|
| 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": 6029711769600.0,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|