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 47724600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb3a1c034c512f3602bb7eb9746a25ce70d3c1c2463811bd29bb2e039a6ac96
|
| 3 |
size 47724600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 25331516
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a4ee21da39425c292a1b2d46b9c4ec0a440be08be6cebb00065c8e33bd4773e
|
| 3 |
size 25331516
|
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 sha256:3bbf00cc7d26b5ba1f1bfe59564ee6b340d81d2d6e92ca2595dc7bce3ba71015
|
| 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:ae4f1bd750c09fc9bb727cae976f56e1bbe0dff5c4d4e1a6eec209a810ae59b2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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,
|
|
@@ -723,6 +723,364 @@
|
|
| 723 |
"eval_samples_per_second": 6.997,
|
| 724 |
"eval_steps_per_second": 3.498,
|
| 725 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 726 |
}
|
| 727 |
],
|
| 728 |
"logging_steps": 1,
|
|
@@ -742,7 +1100,7 @@
|
|
| 742 |
"attributes": {}
|
| 743 |
}
|
| 744 |
},
|
| 745 |
-
"total_flos":
|
| 746 |
"train_batch_size": 2,
|
| 747 |
"trial_name": null,
|
| 748 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7575757575757576,
|
| 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,
|
|
|
|
| 723 |
"eval_samples_per_second": 6.997,
|
| 724 |
"eval_steps_per_second": 3.498,
|
| 725 |
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.51010101010101,
|
| 729 |
+
"grad_norm": 11.24027156829834,
|
| 730 |
+
"learning_rate": 0.00010501108017871192,
|
| 731 |
+
"loss": 0.4537,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.5151515151515151,
|
| 736 |
+
"grad_norm": 14.357158660888672,
|
| 737 |
+
"learning_rate": 0.00010334149770076747,
|
| 738 |
+
"loss": 0.4567,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.5202020202020202,
|
| 743 |
+
"grad_norm": 12.492400169372559,
|
| 744 |
+
"learning_rate": 0.00010167098215093009,
|
| 745 |
+
"loss": 0.4684,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.5252525252525253,
|
| 750 |
+
"grad_norm": 11.547194480895996,
|
| 751 |
+
"learning_rate": 0.0001,
|
| 752 |
+
"loss": 0.4345,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.5303030303030303,
|
| 757 |
+
"grad_norm": 13.756988525390625,
|
| 758 |
+
"learning_rate": 9.83290178490699e-05,
|
| 759 |
+
"loss": 0.4538,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.5353535353535354,
|
| 764 |
+
"grad_norm": 13.91006088256836,
|
| 765 |
+
"learning_rate": 9.665850229923258e-05,
|
| 766 |
+
"loss": 0.3966,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.5404040404040404,
|
| 771 |
+
"grad_norm": 13.23215103149414,
|
| 772 |
+
"learning_rate": 9.498891982128809e-05,
|
| 773 |
+
"loss": 0.3571,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5454545454545454,
|
| 778 |
+
"grad_norm": 13.87959098815918,
|
| 779 |
+
"learning_rate": 9.332073662548784e-05,
|
| 780 |
+
"loss": 0.4389,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.5505050505050505,
|
| 785 |
+
"grad_norm": 12.538737297058105,
|
| 786 |
+
"learning_rate": 9.165441853135104e-05,
|
| 787 |
+
"loss": 0.4184,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.5555555555555556,
|
| 792 |
+
"grad_norm": 23.718013763427734,
|
| 793 |
+
"learning_rate": 8.999043083759017e-05,
|
| 794 |
+
"loss": 0.3822,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.5606060606060606,
|
| 799 |
+
"grad_norm": 70.29689025878906,
|
| 800 |
+
"learning_rate": 8.832923819218238e-05,
|
| 801 |
+
"loss": 0.3815,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.5656565656565656,
|
| 806 |
+
"grad_norm": 11.808393478393555,
|
| 807 |
+
"learning_rate": 8.667130446262214e-05,
|
| 808 |
+
"loss": 0.362,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.5707070707070707,
|
| 813 |
+
"grad_norm": 13.301114082336426,
|
| 814 |
+
"learning_rate": 8.501709260639186e-05,
|
| 815 |
+
"loss": 0.5234,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.5757575757575758,
|
| 820 |
+
"grad_norm": 11.385530471801758,
|
| 821 |
+
"learning_rate": 8.336706454168701e-05,
|
| 822 |
+
"loss": 0.546,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.5808080808080808,
|
| 827 |
+
"grad_norm": 17.040523529052734,
|
| 828 |
+
"learning_rate": 8.172168101843099e-05,
|
| 829 |
+
"loss": 0.4199,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.5858585858585859,
|
| 834 |
+
"grad_norm": 18.70421028137207,
|
| 835 |
+
"learning_rate": 8.008140148961641e-05,
|
| 836 |
+
"loss": 0.5603,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.5909090909090909,
|
| 841 |
+
"grad_norm": 13.10011100769043,
|
| 842 |
+
"learning_rate": 7.844668398300865e-05,
|
| 843 |
+
"loss": 0.6309,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.5959595959595959,
|
| 848 |
+
"grad_norm": 13.03792953491211,
|
| 849 |
+
"learning_rate": 7.681798497324716e-05,
|
| 850 |
+
"loss": 0.4718,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.601010101010101,
|
| 855 |
+
"grad_norm": 14.050755500793457,
|
| 856 |
+
"learning_rate": 7.519575925438067e-05,
|
| 857 |
+
"loss": 0.372,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.6060606060606061,
|
| 862 |
+
"grad_norm": 13.505302429199219,
|
| 863 |
+
"learning_rate": 7.358045981287141e-05,
|
| 864 |
+
"loss": 0.5525,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.6111111111111112,
|
| 869 |
+
"grad_norm": 13.572732925415039,
|
| 870 |
+
"learning_rate": 7.197253770110438e-05,
|
| 871 |
+
"loss": 0.4607,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.6161616161616161,
|
| 876 |
+
"grad_norm": 22.72136878967285,
|
| 877 |
+
"learning_rate": 7.037244191143661e-05,
|
| 878 |
+
"loss": 0.632,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.6212121212121212,
|
| 883 |
+
"grad_norm": 12.22665786743164,
|
| 884 |
+
"learning_rate": 6.878061925082137e-05,
|
| 885 |
+
"loss": 0.429,
|
| 886 |
+
"step": 123
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.6262626262626263,
|
| 890 |
+
"grad_norm": 10.075366973876953,
|
| 891 |
+
"learning_rate": 6.719751421604309e-05,
|
| 892 |
+
"loss": 0.4592,
|
| 893 |
+
"step": 124
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.6313131313131313,
|
| 897 |
+
"grad_norm": 16.798250198364258,
|
| 898 |
+
"learning_rate": 6.562356886959704e-05,
|
| 899 |
+
"loss": 0.368,
|
| 900 |
+
"step": 125
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.6363636363636364,
|
| 904 |
+
"grad_norm": 10.359375953674316,
|
| 905 |
+
"learning_rate": 6.405922271624874e-05,
|
| 906 |
+
"loss": 0.2825,
|
| 907 |
+
"step": 126
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.6414141414141414,
|
| 911 |
+
"grad_norm": 12.54139232635498,
|
| 912 |
+
"learning_rate": 6.250491258030791e-05,
|
| 913 |
+
"loss": 0.479,
|
| 914 |
+
"step": 127
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.6464646464646465,
|
| 918 |
+
"grad_norm": 15.544010162353516,
|
| 919 |
+
"learning_rate": 6.0961072483650526e-05,
|
| 920 |
+
"loss": 0.4355,
|
| 921 |
+
"step": 128
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.6515151515151515,
|
| 925 |
+
"grad_norm": 13.150715827941895,
|
| 926 |
+
"learning_rate": 5.9428133524523646e-05,
|
| 927 |
+
"loss": 0.3998,
|
| 928 |
+
"step": 129
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.6565656565656566,
|
| 932 |
+
"grad_norm": 11.6818265914917,
|
| 933 |
+
"learning_rate": 5.790652375716652e-05,
|
| 934 |
+
"loss": 0.4009,
|
| 935 |
+
"step": 130
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.6616161616161617,
|
| 939 |
+
"grad_norm": 16.20279884338379,
|
| 940 |
+
"learning_rate": 5.639666807228175e-05,
|
| 941 |
+
"loss": 0.5703,
|
| 942 |
+
"step": 131
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.6666666666666666,
|
| 946 |
+
"grad_norm": 15.14217758178711,
|
| 947 |
+
"learning_rate": 5.48989880783898e-05,
|
| 948 |
+
"loss": 0.4918,
|
| 949 |
+
"step": 132
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.6717171717171717,
|
| 953 |
+
"grad_norm": 17.63346290588379,
|
| 954 |
+
"learning_rate": 5.341390198410019e-05,
|
| 955 |
+
"loss": 0.4146,
|
| 956 |
+
"step": 133
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.6767676767676768,
|
| 960 |
+
"grad_norm": 17.88300323486328,
|
| 961 |
+
"learning_rate": 5.1941824481331626e-05,
|
| 962 |
+
"loss": 0.4518,
|
| 963 |
+
"step": 134
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.6818181818181818,
|
| 967 |
+
"grad_norm": 19.94394302368164,
|
| 968 |
+
"learning_rate": 5.0483166629514654e-05,
|
| 969 |
+
"loss": 0.6016,
|
| 970 |
+
"step": 135
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.6868686868686869,
|
| 974 |
+
"grad_norm": 14.756821632385254,
|
| 975 |
+
"learning_rate": 4.903833574080825e-05,
|
| 976 |
+
"loss": 0.3996,
|
| 977 |
+
"step": 136
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.6919191919191919,
|
| 981 |
+
"grad_norm": 19.392858505249023,
|
| 982 |
+
"learning_rate": 4.760773526636315e-05,
|
| 983 |
+
"loss": 0.6053,
|
| 984 |
+
"step": 137
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.696969696969697,
|
| 988 |
+
"grad_norm": 7.531655788421631,
|
| 989 |
+
"learning_rate": 4.6191764683662744e-05,
|
| 990 |
+
"loss": 0.2299,
|
| 991 |
+
"step": 138
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.702020202020202,
|
| 995 |
+
"grad_norm": 23.472288131713867,
|
| 996 |
+
"learning_rate": 4.479081938497435e-05,
|
| 997 |
+
"loss": 0.5437,
|
| 998 |
+
"step": 139
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.7070707070707071,
|
| 1002 |
+
"grad_norm": 17.57956314086914,
|
| 1003 |
+
"learning_rate": 4.340529056694047e-05,
|
| 1004 |
+
"loss": 0.5943,
|
| 1005 |
+
"step": 140
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.7121212121212122,
|
| 1009 |
+
"grad_norm": 11.99634075164795,
|
| 1010 |
+
"learning_rate": 4.2035565121342246e-05,
|
| 1011 |
+
"loss": 0.2477,
|
| 1012 |
+
"step": 141
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.7171717171717171,
|
| 1016 |
+
"grad_norm": 34.67549133300781,
|
| 1017 |
+
"learning_rate": 4.0682025527064486e-05,
|
| 1018 |
+
"loss": 0.4986,
|
| 1019 |
+
"step": 142
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.7222222222222222,
|
| 1023 |
+
"grad_norm": 12.304537773132324,
|
| 1024 |
+
"learning_rate": 3.934504974329326e-05,
|
| 1025 |
+
"loss": 0.5063,
|
| 1026 |
+
"step": 143
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.7272727272727273,
|
| 1030 |
+
"grad_norm": 14.232462882995605,
|
| 1031 |
+
"learning_rate": 3.802501110397553e-05,
|
| 1032 |
+
"loss": 0.5271,
|
| 1033 |
+
"step": 144
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.7323232323232324,
|
| 1037 |
+
"grad_norm": 23.888545989990234,
|
| 1038 |
+
"learning_rate": 3.672227821357014e-05,
|
| 1039 |
+
"loss": 0.6568,
|
| 1040 |
+
"step": 145
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.7373737373737373,
|
| 1044 |
+
"grad_norm": 16.624494552612305,
|
| 1045 |
+
"learning_rate": 3.543721484411976e-05,
|
| 1046 |
+
"loss": 0.4932,
|
| 1047 |
+
"step": 146
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.7424242424242424,
|
| 1051 |
+
"grad_norm": 15.917621612548828,
|
| 1052 |
+
"learning_rate": 3.4170179833671846e-05,
|
| 1053 |
+
"loss": 0.6934,
|
| 1054 |
+
"step": 147
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.7474747474747475,
|
| 1058 |
+
"grad_norm": 9.06427001953125,
|
| 1059 |
+
"learning_rate": 3.292152698607768e-05,
|
| 1060 |
+
"loss": 0.3849,
|
| 1061 |
+
"step": 148
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.7525252525252525,
|
| 1065 |
+
"grad_norm": 17.903718948364258,
|
| 1066 |
+
"learning_rate": 3.169160497219692e-05,
|
| 1067 |
+
"loss": 0.3646,
|
| 1068 |
+
"step": 149
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.7575757575757576,
|
| 1072 |
+
"grad_norm": 11.98536205291748,
|
| 1073 |
+
"learning_rate": 3.0480757232535772e-05,
|
| 1074 |
+
"loss": 0.46,
|
| 1075 |
+
"step": 150
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.7575757575757576,
|
| 1079 |
+
"eval_loss": 0.3067511022090912,
|
| 1080 |
+
"eval_runtime": 12.2523,
|
| 1081 |
+
"eval_samples_per_second": 6.856,
|
| 1082 |
+
"eval_steps_per_second": 3.428,
|
| 1083 |
+
"step": 150
|
| 1084 |
}
|
| 1085 |
],
|
| 1086 |
"logging_steps": 1,
|
|
|
|
| 1100 |
"attributes": {}
|
| 1101 |
}
|
| 1102 |
},
|
| 1103 |
+
"total_flos": 2.13169452613632e+16,
|
| 1104 |
"train_batch_size": 2,
|
| 1105 |
"trial_name": null,
|
| 1106 |
"trial_params": null
|