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 sha256:397caea8f75e97f5170a7fefe06f8a05aec2ec435c2bc808f24e2608e7af54e5
|
| 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:dad69227d2a233c91445d42d0503c168983cbb09ab6e1a80b10be311f1cc3888
|
| 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:acbceda8b0e3f90ddd941ffea9fd96050462c086b9498ea5af11ceb857234bf0
|
| 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:fe6385b1b60f064938f7c87459100029ab630f31bb282ac8fee66acbff88efe0
|
| 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":
|
| 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": 14.209,
|
| 732 |
"eval_steps_per_second": 3.59,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -759,7 +1117,7 @@
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos": 1.
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.032022152096033096,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 2.663716814159292,
|
| 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": 14.209,
|
| 732 |
"eval_steps_per_second": 3.59,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.7920353982300885,
|
| 737 |
+
"grad_norm": 0.20991753041744232,
|
| 738 |
+
"learning_rate": 3.873640452903026e-05,
|
| 739 |
+
"loss": 0.0253,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.8097345132743363,
|
| 744 |
+
"grad_norm": 0.3313141167163849,
|
| 745 |
+
"learning_rate": 3.777613711607087e-05,
|
| 746 |
+
"loss": 0.0289,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.827433628318584,
|
| 751 |
+
"grad_norm": 0.19206620752811432,
|
| 752 |
+
"learning_rate": 3.682064169654663e-05,
|
| 753 |
+
"loss": 0.0265,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.8451327433628317,
|
| 758 |
+
"grad_norm": 0.4013370871543884,
|
| 759 |
+
"learning_rate": 3.587029128003006e-05,
|
| 760 |
+
"loss": 0.0308,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.8628318584070795,
|
| 765 |
+
"grad_norm": 0.18024751543998718,
|
| 766 |
+
"learning_rate": 3.492545686756986e-05,
|
| 767 |
+
"loss": 0.0162,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.8805309734513274,
|
| 772 |
+
"grad_norm": 0.2305198758840561,
|
| 773 |
+
"learning_rate": 3.3986507306858125e-05,
|
| 774 |
+
"loss": 0.0284,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.8982300884955752,
|
| 779 |
+
"grad_norm": 0.19050440192222595,
|
| 780 |
+
"learning_rate": 3.3053809148238426e-05,
|
| 781 |
+
"loss": 0.0227,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.915929203539823,
|
| 786 |
+
"grad_norm": 0.15006108582019806,
|
| 787 |
+
"learning_rate": 3.212772650161056e-05,
|
| 788 |
+
"loss": 0.0191,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.9336283185840708,
|
| 793 |
+
"grad_norm": 0.2283119261264801,
|
| 794 |
+
"learning_rate": 3.12086208942881e-05,
|
| 795 |
+
"loss": 0.0227,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.9513274336283186,
|
| 800 |
+
"grad_norm": 0.2260059416294098,
|
| 801 |
+
"learning_rate": 3.0296851129864168e-05,
|
| 802 |
+
"loss": 0.0253,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.9690265486725664,
|
| 807 |
+
"grad_norm": 0.23939450085163116,
|
| 808 |
+
"learning_rate": 2.9392773148140408e-05,
|
| 809 |
+
"loss": 0.0265,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.9867256637168142,
|
| 814 |
+
"grad_norm": 0.1815921664237976,
|
| 815 |
+
"learning_rate": 2.8496739886173995e-05,
|
| 816 |
+
"loss": 0.0216,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.0088495575221237,
|
| 821 |
+
"grad_norm": 0.24775980412960052,
|
| 822 |
+
"learning_rate": 2.7609101140496863e-05,
|
| 823 |
+
"loss": 0.0232,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.0265486725663715,
|
| 828 |
+
"grad_norm": 0.12413739413022995,
|
| 829 |
+
"learning_rate": 2.6730203430560947e-05,
|
| 830 |
+
"loss": 0.0206,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.0442477876106193,
|
| 835 |
+
"grad_norm": 0.1339850276708603,
|
| 836 |
+
"learning_rate": 2.5860389863462765e-05,
|
| 837 |
+
"loss": 0.0196,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.061946902654867,
|
| 842 |
+
"grad_norm": 0.13854354619979858,
|
| 843 |
+
"learning_rate": 2.500000000000001e-05,
|
| 844 |
+
"loss": 0.0159,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.079646017699115,
|
| 849 |
+
"grad_norm": 0.1154838278889656,
|
| 850 |
+
"learning_rate": 2.414936972211272e-05,
|
| 851 |
+
"loss": 0.0142,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.0973451327433628,
|
| 856 |
+
"grad_norm": 0.10285928845405579,
|
| 857 |
+
"learning_rate": 2.3308831101760486e-05,
|
| 858 |
+
"loss": 0.01,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.1150442477876106,
|
| 863 |
+
"grad_norm": 0.1806727647781372,
|
| 864 |
+
"learning_rate": 2.247871227128709e-05,
|
| 865 |
+
"loss": 0.0187,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.1327433628318584,
|
| 870 |
+
"grad_norm": 0.19010406732559204,
|
| 871 |
+
"learning_rate": 2.1659337295323118e-05,
|
| 872 |
+
"loss": 0.0235,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.150442477876106,
|
| 877 |
+
"grad_norm": 0.1291082799434662,
|
| 878 |
+
"learning_rate": 2.0851026044276406e-05,
|
| 879 |
+
"loss": 0.0144,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.168141592920354,
|
| 884 |
+
"grad_norm": 0.16923344135284424,
|
| 885 |
+
"learning_rate": 2.005409406946e-05,
|
| 886 |
+
"loss": 0.0138,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.185840707964602,
|
| 891 |
+
"grad_norm": 0.14110802114009857,
|
| 892 |
+
"learning_rate": 1.9268852479906147e-05,
|
| 893 |
+
"loss": 0.0119,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.2035398230088497,
|
| 898 |
+
"grad_norm": 0.10906057059764862,
|
| 899 |
+
"learning_rate": 1.849560782091445e-05,
|
| 900 |
+
"loss": 0.009,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.2212389380530975,
|
| 905 |
+
"grad_norm": 0.1177993193268776,
|
| 906 |
+
"learning_rate": 1.7734661954381754e-05,
|
| 907 |
+
"loss": 0.014,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.2389380530973453,
|
| 912 |
+
"grad_norm": 0.10654302686452866,
|
| 913 |
+
"learning_rate": 1.6986311940960147e-05,
|
| 914 |
+
"loss": 0.0101,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.256637168141593,
|
| 919 |
+
"grad_norm": 0.16150303184986115,
|
| 920 |
+
"learning_rate": 1.6250849924089484e-05,
|
| 921 |
+
"loss": 0.0168,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.274336283185841,
|
| 926 |
+
"grad_norm": 0.12198394536972046,
|
| 927 |
+
"learning_rate": 1.552856301594942e-05,
|
| 928 |
+
"loss": 0.0136,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.2920353982300883,
|
| 933 |
+
"grad_norm": 0.16058827936649323,
|
| 934 |
+
"learning_rate": 1.4819733185375534e-05,
|
| 935 |
+
"loss": 0.0196,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.309734513274336,
|
| 940 |
+
"grad_norm": 0.19370707869529724,
|
| 941 |
+
"learning_rate": 1.4124637147783432e-05,
|
| 942 |
+
"loss": 0.0205,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.327433628318584,
|
| 947 |
+
"grad_norm": 0.0963333398103714,
|
| 948 |
+
"learning_rate": 1.3443546257143624e-05,
|
| 949 |
+
"loss": 0.011,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.3451327433628317,
|
| 954 |
+
"grad_norm": 0.1633400171995163,
|
| 955 |
+
"learning_rate": 1.277672640004936e-05,
|
| 956 |
+
"loss": 0.0208,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.3628318584070795,
|
| 961 |
+
"grad_norm": 0.1224859431385994,
|
| 962 |
+
"learning_rate": 1.2124437891918993e-05,
|
| 963 |
+
"loss": 0.015,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.3805309734513274,
|
| 968 |
+
"grad_norm": 0.10458586364984512,
|
| 969 |
+
"learning_rate": 1.1486935375373126e-05,
|
| 970 |
+
"loss": 0.0101,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.398230088495575,
|
| 975 |
+
"grad_norm": 0.15571683645248413,
|
| 976 |
+
"learning_rate": 1.0864467720826343e-05,
|
| 977 |
+
"loss": 0.0162,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.415929203539823,
|
| 982 |
+
"grad_norm": 0.08478286117315292,
|
| 983 |
+
"learning_rate": 1.0257277929332332e-05,
|
| 984 |
+
"loss": 0.0072,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.433628318584071,
|
| 989 |
+
"grad_norm": 0.10365074872970581,
|
| 990 |
+
"learning_rate": 9.66560303772035e-06,
|
| 991 |
+
"loss": 0.0095,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.4513274336283186,
|
| 996 |
+
"grad_norm": 0.07361367344856262,
|
| 997 |
+
"learning_rate": 9.08967402605988e-06,
|
| 998 |
+
"loss": 0.0076,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.4690265486725664,
|
| 1003 |
+
"grad_norm": 0.13091503083705902,
|
| 1004 |
+
"learning_rate": 8.529715727489912e-06,
|
| 1005 |
+
"loss": 0.0082,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.4867256637168142,
|
| 1010 |
+
"grad_norm": 0.11134269833564758,
|
| 1011 |
+
"learning_rate": 7.985946740447791e-06,
|
| 1012 |
+
"loss": 0.0079,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.504424778761062,
|
| 1017 |
+
"grad_norm": 0.18341496586799622,
|
| 1018 |
+
"learning_rate": 7.458579343331995e-06,
|
| 1019 |
+
"loss": 0.0129,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.52212389380531,
|
| 1024 |
+
"grad_norm": 0.11337222903966904,
|
| 1025 |
+
"learning_rate": 6.947819411632223e-06,
|
| 1026 |
+
"loss": 0.0173,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.5398230088495577,
|
| 1031 |
+
"grad_norm": 0.20701636373996735,
|
| 1032 |
+
"learning_rate": 6.45386633755894e-06,
|
| 1033 |
+
"loss": 0.0175,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.557522123893805,
|
| 1038 |
+
"grad_norm": 0.20868322253227234,
|
| 1039 |
+
"learning_rate": 5.976912952204017e-06,
|
| 1040 |
+
"loss": 0.0147,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.5752212389380533,
|
| 1045 |
+
"grad_norm": 0.10272178053855896,
|
| 1046 |
+
"learning_rate": 5.51714545026264e-06,
|
| 1047 |
+
"loss": 0.0128,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.5929203539823007,
|
| 1052 |
+
"grad_norm": 0.14340701699256897,
|
| 1053 |
+
"learning_rate": 5.074743317346009e-06,
|
| 1054 |
+
"loss": 0.0136,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.6106194690265485,
|
| 1059 |
+
"grad_norm": 0.12963014841079712,
|
| 1060 |
+
"learning_rate": 4.649879259913137e-06,
|
| 1061 |
+
"loss": 0.0093,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.6283185840707963,
|
| 1066 |
+
"grad_norm": 0.12100816518068314,
|
| 1067 |
+
"learning_rate": 4.242719137849077e-06,
|
| 1068 |
+
"loss": 0.0107,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.646017699115044,
|
| 1073 |
+
"grad_norm": 0.09687142819166183,
|
| 1074 |
+
"learning_rate": 3.853421899715992e-06,
|
| 1075 |
+
"loss": 0.0082,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.663716814159292,
|
| 1080 |
+
"grad_norm": 0.09663711488246918,
|
| 1081 |
+
"learning_rate": 3.4821395207022766e-06,
|
| 1082 |
+
"loss": 0.0081,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.663716814159292,
|
| 1087 |
+
"eval_loss": 0.032022152096033096,
|
| 1088 |
+
"eval_runtime": 6.6983,
|
| 1089 |
+
"eval_samples_per_second": 14.183,
|
| 1090 |
+
"eval_steps_per_second": 3.583,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 1.995743661391872e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|