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 sha256:8b85eb6a3d7bda3e6dfdd6a6fd5b18b7e3567513fa7bb7e7125b4f1487431aa7
|
| 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 sha256:7e06358f2fc8fad9da99f05e1d5bcf5a11df12a6fedde3df08d34cf1689daf97
|
| 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:df7396f1ae858cac6cf44d64ee7a80546fa73c7f9c0e8d765e0c769fa1156556
|
| 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 sha256:123ecf29cfd4fe3b008c987ce1ef9f63c2ad00365e06a3691aa36827aaded381
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 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": 19.76,
|
| 732 |
"eval_steps_per_second": 4.96,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -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": 1.6460583209991455,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.08525149190110827,
|
| 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": 19.76,
|
| 732 |
"eval_steps_per_second": 4.96,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.0574026712134129,
|
| 737 |
+
"grad_norm": 0.5151413083076477,
|
| 738 |
+
"learning_rate": 5.3043157894736836e-05,
|
| 739 |
+
"loss": 1.817,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.057971014492753624,
|
| 744 |
+
"grad_norm": 0.5496950745582581,
|
| 745 |
+
"learning_rate": 5.2507368421052635e-05,
|
| 746 |
+
"loss": 1.6748,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.05853935777209435,
|
| 751 |
+
"grad_norm": 0.6355785727500916,
|
| 752 |
+
"learning_rate": 5.197157894736842e-05,
|
| 753 |
+
"loss": 1.7064,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.05910770105143507,
|
| 758 |
+
"grad_norm": 0.593001127243042,
|
| 759 |
+
"learning_rate": 5.143578947368421e-05,
|
| 760 |
+
"loss": 1.7486,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.059676044330775786,
|
| 765 |
+
"grad_norm": 0.5528516173362732,
|
| 766 |
+
"learning_rate": 5.09e-05,
|
| 767 |
+
"loss": 1.7127,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.06024438761011651,
|
| 772 |
+
"grad_norm": 0.5531303286552429,
|
| 773 |
+
"learning_rate": 5.036421052631578e-05,
|
| 774 |
+
"loss": 1.8465,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.06081273088945723,
|
| 779 |
+
"grad_norm": 0.5014846324920654,
|
| 780 |
+
"learning_rate": 4.982842105263158e-05,
|
| 781 |
+
"loss": 1.6323,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.061381074168797956,
|
| 786 |
+
"grad_norm": 0.5050337910652161,
|
| 787 |
+
"learning_rate": 4.9292631578947366e-05,
|
| 788 |
+
"loss": 1.5039,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.06194941744813868,
|
| 793 |
+
"grad_norm": 0.5129539370536804,
|
| 794 |
+
"learning_rate": 4.875684210526315e-05,
|
| 795 |
+
"loss": 1.6314,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.0625177607274794,
|
| 800 |
+
"grad_norm": 0.5408539175987244,
|
| 801 |
+
"learning_rate": 4.822105263157894e-05,
|
| 802 |
+
"loss": 1.6182,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.06308610400682012,
|
| 807 |
+
"grad_norm": 0.5475476384162903,
|
| 808 |
+
"learning_rate": 4.7685263157894735e-05,
|
| 809 |
+
"loss": 1.4697,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.06365444728616085,
|
| 814 |
+
"grad_norm": 0.5478246808052063,
|
| 815 |
+
"learning_rate": 4.714947368421052e-05,
|
| 816 |
+
"loss": 1.5738,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.06422279056550156,
|
| 821 |
+
"grad_norm": 0.5796051621437073,
|
| 822 |
+
"learning_rate": 4.661368421052631e-05,
|
| 823 |
+
"loss": 1.5052,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.06479113384484228,
|
| 828 |
+
"grad_norm": 0.5977994799613953,
|
| 829 |
+
"learning_rate": 4.6077894736842104e-05,
|
| 830 |
+
"loss": 1.526,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.06535947712418301,
|
| 835 |
+
"grad_norm": 0.5993626713752747,
|
| 836 |
+
"learning_rate": 4.554210526315789e-05,
|
| 837 |
+
"loss": 1.4977,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.06592782040352373,
|
| 842 |
+
"grad_norm": 0.6900733113288879,
|
| 843 |
+
"learning_rate": 4.500631578947368e-05,
|
| 844 |
+
"loss": 1.6882,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.06649616368286446,
|
| 849 |
+
"grad_norm": 0.6961638331413269,
|
| 850 |
+
"learning_rate": 4.447052631578947e-05,
|
| 851 |
+
"loss": 1.5659,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.06706450696220517,
|
| 856 |
+
"grad_norm": 0.6532340049743652,
|
| 857 |
+
"learning_rate": 4.393473684210526e-05,
|
| 858 |
+
"loss": 1.7786,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.06763285024154589,
|
| 863 |
+
"grad_norm": 0.7710056900978088,
|
| 864 |
+
"learning_rate": 4.339894736842105e-05,
|
| 865 |
+
"loss": 1.7923,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.06820119352088662,
|
| 870 |
+
"grad_norm": 0.6924229264259338,
|
| 871 |
+
"learning_rate": 4.2863157894736835e-05,
|
| 872 |
+
"loss": 1.5977,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.06876953680022733,
|
| 877 |
+
"grad_norm": 0.7953075170516968,
|
| 878 |
+
"learning_rate": 4.2327368421052634e-05,
|
| 879 |
+
"loss": 1.4162,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.06933788007956806,
|
| 884 |
+
"grad_norm": 0.6938318014144897,
|
| 885 |
+
"learning_rate": 4.179157894736842e-05,
|
| 886 |
+
"loss": 1.4258,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.06990622335890878,
|
| 891 |
+
"grad_norm": 0.7798824310302734,
|
| 892 |
+
"learning_rate": 4.1255789473684204e-05,
|
| 893 |
+
"loss": 1.4765,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.0704745666382495,
|
| 898 |
+
"grad_norm": 0.8481230139732361,
|
| 899 |
+
"learning_rate": 4.072e-05,
|
| 900 |
+
"loss": 1.4541,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.07104290991759023,
|
| 905 |
+
"grad_norm": 0.7436756491661072,
|
| 906 |
+
"learning_rate": 4.018421052631579e-05,
|
| 907 |
+
"loss": 1.6289,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.07161125319693094,
|
| 912 |
+
"grad_norm": 0.802385151386261,
|
| 913 |
+
"learning_rate": 3.9648421052631573e-05,
|
| 914 |
+
"loss": 1.4059,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.07217959647627167,
|
| 919 |
+
"grad_norm": 0.9276831150054932,
|
| 920 |
+
"learning_rate": 3.9112631578947365e-05,
|
| 921 |
+
"loss": 1.5148,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.07274793975561239,
|
| 926 |
+
"grad_norm": 0.8872740268707275,
|
| 927 |
+
"learning_rate": 3.857684210526316e-05,
|
| 928 |
+
"loss": 1.556,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.0733162830349531,
|
| 933 |
+
"grad_norm": 0.8716956973075867,
|
| 934 |
+
"learning_rate": 3.804105263157894e-05,
|
| 935 |
+
"loss": 1.562,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.07388462631429384,
|
| 940 |
+
"grad_norm": 1.0244389772415161,
|
| 941 |
+
"learning_rate": 3.7505263157894734e-05,
|
| 942 |
+
"loss": 1.3268,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.07445296959363455,
|
| 947 |
+
"grad_norm": 0.9489229917526245,
|
| 948 |
+
"learning_rate": 3.6969473684210526e-05,
|
| 949 |
+
"loss": 1.5957,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.07502131287297528,
|
| 954 |
+
"grad_norm": 1.275113582611084,
|
| 955 |
+
"learning_rate": 3.643368421052631e-05,
|
| 956 |
+
"loss": 1.6578,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.075589656152316,
|
| 961 |
+
"grad_norm": 1.0766980648040771,
|
| 962 |
+
"learning_rate": 3.5897894736842103e-05,
|
| 963 |
+
"loss": 1.7832,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.07615799943165671,
|
| 968 |
+
"grad_norm": 1.1330690383911133,
|
| 969 |
+
"learning_rate": 3.5362105263157895e-05,
|
| 970 |
+
"loss": 1.2917,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.07672634271099744,
|
| 975 |
+
"grad_norm": 1.1914342641830444,
|
| 976 |
+
"learning_rate": 3.482631578947368e-05,
|
| 977 |
+
"loss": 1.6503,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.07729468599033816,
|
| 982 |
+
"grad_norm": 1.1140198707580566,
|
| 983 |
+
"learning_rate": 3.429052631578947e-05,
|
| 984 |
+
"loss": 1.5326,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.07786302926967889,
|
| 989 |
+
"grad_norm": 1.1322687864303589,
|
| 990 |
+
"learning_rate": 3.375473684210526e-05,
|
| 991 |
+
"loss": 1.5365,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.0784313725490196,
|
| 996 |
+
"grad_norm": 1.012017011642456,
|
| 997 |
+
"learning_rate": 3.321894736842105e-05,
|
| 998 |
+
"loss": 1.4869,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.07899971582836032,
|
| 1003 |
+
"grad_norm": 1.404184103012085,
|
| 1004 |
+
"learning_rate": 3.268315789473684e-05,
|
| 1005 |
+
"loss": 1.3593,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.07956805910770105,
|
| 1010 |
+
"grad_norm": 1.4041898250579834,
|
| 1011 |
+
"learning_rate": 3.2147368421052627e-05,
|
| 1012 |
+
"loss": 1.6974,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.08013640238704177,
|
| 1017 |
+
"grad_norm": 1.6375192403793335,
|
| 1018 |
+
"learning_rate": 3.161157894736842e-05,
|
| 1019 |
+
"loss": 1.4095,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.0807047456663825,
|
| 1024 |
+
"grad_norm": 1.7191766500473022,
|
| 1025 |
+
"learning_rate": 3.107578947368421e-05,
|
| 1026 |
+
"loss": 1.6655,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.08127308894572322,
|
| 1031 |
+
"grad_norm": 1.5540755987167358,
|
| 1032 |
+
"learning_rate": 3.0539999999999996e-05,
|
| 1033 |
+
"loss": 1.6224,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.08184143222506395,
|
| 1038 |
+
"grad_norm": 1.3428224325180054,
|
| 1039 |
+
"learning_rate": 3.0004210526315784e-05,
|
| 1040 |
+
"loss": 1.0397,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.08240977550440466,
|
| 1045 |
+
"grad_norm": 1.6207056045532227,
|
| 1046 |
+
"learning_rate": 2.946842105263158e-05,
|
| 1047 |
+
"loss": 1.2121,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.08297811878374538,
|
| 1052 |
+
"grad_norm": 1.900486946105957,
|
| 1053 |
+
"learning_rate": 2.8932631578947368e-05,
|
| 1054 |
+
"loss": 1.9168,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.08354646206308611,
|
| 1059 |
+
"grad_norm": 1.903605341911316,
|
| 1060 |
+
"learning_rate": 2.8396842105263153e-05,
|
| 1061 |
+
"loss": 1.2044,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.08411480534242682,
|
| 1066 |
+
"grad_norm": 2.0578088760375977,
|
| 1067 |
+
"learning_rate": 2.786105263157895e-05,
|
| 1068 |
+
"loss": 1.5255,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.08468314862176755,
|
| 1073 |
+
"grad_norm": 2.299281358718872,
|
| 1074 |
+
"learning_rate": 2.7325263157894737e-05,
|
| 1075 |
+
"loss": 1.5899,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.08525149190110827,
|
| 1080 |
+
"grad_norm": 3.6123387813568115,
|
| 1081 |
+
"learning_rate": 2.6789473684210522e-05,
|
| 1082 |
+
"loss": 1.6884,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.08525149190110827,
|
| 1087 |
+
"eval_loss": 1.6460583209991455,
|
| 1088 |
+
"eval_runtime": 37.4635,
|
| 1089 |
+
"eval_samples_per_second": 19.779,
|
| 1090 |
+
"eval_steps_per_second": 4.965,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 5.105777533727539e+16,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|