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 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:214a5cce85782256d79a96639d45e727910a282ecf9b09efda9caa738133366f
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 170920084
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8246a3e6cb9a57752c8fbc9c6287eb952768afa9c53879830d3001205aab0937
|
| 3 |
size 170920084
|
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 sha256:9263036f9abf200f9f293a24c114d5aa97249c17d7b203fda52c41c0a82a1d06
|
| 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 sha256:61d92ba00805f178e64a4a7fc7ebf59bf8a4f5750cc8c2818832081930f2c83e
|
| 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": 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": 8.37,
|
| 732 |
"eval_steps_per_second": 2.092,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -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": 0.5722422003746033,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.07116593523899893,
|
| 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": 8.37,
|
| 732 |
"eval_steps_per_second": 2.092,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.04791839639425928,
|
| 737 |
+
"grad_norm": 0.7622676491737366,
|
| 738 |
+
"learning_rate": 3.366666666666667e-05,
|
| 739 |
+
"loss": 0.606,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.048392835962519275,
|
| 744 |
+
"grad_norm": 0.7645723819732666,
|
| 745 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 746 |
+
"loss": 0.6439,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.04886727553077927,
|
| 751 |
+
"grad_norm": 0.794933557510376,
|
| 752 |
+
"learning_rate": 3.433333333333333e-05,
|
| 753 |
+
"loss": 0.6248,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.04934171509903926,
|
| 758 |
+
"grad_norm": 0.8379741311073303,
|
| 759 |
+
"learning_rate": 3.466666666666667e-05,
|
| 760 |
+
"loss": 0.6828,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.04981615466729925,
|
| 765 |
+
"grad_norm": 0.7191290259361267,
|
| 766 |
+
"learning_rate": 3.5e-05,
|
| 767 |
+
"loss": 0.6195,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.05029059423555925,
|
| 772 |
+
"grad_norm": 0.7295191287994385,
|
| 773 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 774 |
+
"loss": 0.6372,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.05076503380381924,
|
| 779 |
+
"grad_norm": 0.8286232948303223,
|
| 780 |
+
"learning_rate": 3.566666666666667e-05,
|
| 781 |
+
"loss": 0.6116,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.05123947337207923,
|
| 786 |
+
"grad_norm": 0.7905992865562439,
|
| 787 |
+
"learning_rate": 3.6e-05,
|
| 788 |
+
"loss": 0.5729,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.051713912940339224,
|
| 793 |
+
"grad_norm": 0.7963486313819885,
|
| 794 |
+
"learning_rate": 3.633333333333333e-05,
|
| 795 |
+
"loss": 0.5936,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.05218835250859922,
|
| 800 |
+
"grad_norm": 0.7339712977409363,
|
| 801 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 802 |
+
"loss": 0.5722,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.05266279207685921,
|
| 807 |
+
"grad_norm": 0.796782910823822,
|
| 808 |
+
"learning_rate": 3.7e-05,
|
| 809 |
+
"loss": 0.5644,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.0531372316451192,
|
| 814 |
+
"grad_norm": 0.9761651754379272,
|
| 815 |
+
"learning_rate": 3.733333333333334e-05,
|
| 816 |
+
"loss": 0.6047,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.053611671213379196,
|
| 821 |
+
"grad_norm": 1.0321804285049438,
|
| 822 |
+
"learning_rate": 3.766666666666667e-05,
|
| 823 |
+
"loss": 0.5908,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.05408611078163919,
|
| 828 |
+
"grad_norm": 1.0944875478744507,
|
| 829 |
+
"learning_rate": 3.8e-05,
|
| 830 |
+
"loss": 0.609,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.05456055034989918,
|
| 835 |
+
"grad_norm": 0.9031066298484802,
|
| 836 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 837 |
+
"loss": 0.5865,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.05503498991815917,
|
| 842 |
+
"grad_norm": 0.9918826222419739,
|
| 843 |
+
"learning_rate": 3.866666666666667e-05,
|
| 844 |
+
"loss": 0.6191,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.05550942948641917,
|
| 849 |
+
"grad_norm": 0.935981273651123,
|
| 850 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 851 |
+
"loss": 0.5879,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.05598386905467916,
|
| 856 |
+
"grad_norm": 1.0208978652954102,
|
| 857 |
+
"learning_rate": 3.933333333333333e-05,
|
| 858 |
+
"loss": 0.6392,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.05645830862293915,
|
| 863 |
+
"grad_norm": 0.9402481913566589,
|
| 864 |
+
"learning_rate": 3.966666666666667e-05,
|
| 865 |
+
"loss": 0.6081,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.056932748191199145,
|
| 870 |
+
"grad_norm": 0.9677188396453857,
|
| 871 |
+
"learning_rate": 4e-05,
|
| 872 |
+
"loss": 0.6061,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.05740718775945914,
|
| 877 |
+
"grad_norm": 0.9563785791397095,
|
| 878 |
+
"learning_rate": 4.0333333333333336e-05,
|
| 879 |
+
"loss": 0.6148,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.057881627327719135,
|
| 884 |
+
"grad_norm": 0.9848144054412842,
|
| 885 |
+
"learning_rate": 4.066666666666667e-05,
|
| 886 |
+
"loss": 0.5913,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.05835606689597912,
|
| 891 |
+
"grad_norm": 1.0895841121673584,
|
| 892 |
+
"learning_rate": 4.1e-05,
|
| 893 |
+
"loss": 0.6033,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.05883050646423912,
|
| 898 |
+
"grad_norm": 0.9529857635498047,
|
| 899 |
+
"learning_rate": 4.133333333333333e-05,
|
| 900 |
+
"loss": 0.6168,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.05930494603249911,
|
| 905 |
+
"grad_norm": 0.9967851638793945,
|
| 906 |
+
"learning_rate": 4.166666666666667e-05,
|
| 907 |
+
"loss": 0.6192,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.059779385600759107,
|
| 912 |
+
"grad_norm": 1.0510427951812744,
|
| 913 |
+
"learning_rate": 4.2e-05,
|
| 914 |
+
"loss": 0.6253,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.060253825169019094,
|
| 919 |
+
"grad_norm": 1.0621651411056519,
|
| 920 |
+
"learning_rate": 4.233333333333334e-05,
|
| 921 |
+
"loss": 0.6501,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.06072826473727909,
|
| 926 |
+
"grad_norm": 0.95118647813797,
|
| 927 |
+
"learning_rate": 4.266666666666667e-05,
|
| 928 |
+
"loss": 0.5404,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.061202704305539084,
|
| 933 |
+
"grad_norm": 0.9522389769554138,
|
| 934 |
+
"learning_rate": 4.3e-05,
|
| 935 |
+
"loss": 0.5584,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.06167714387379907,
|
| 940 |
+
"grad_norm": 0.9012666940689087,
|
| 941 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 942 |
+
"loss": 0.5293,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.062151583442059066,
|
| 947 |
+
"grad_norm": 0.7849039435386658,
|
| 948 |
+
"learning_rate": 4.3666666666666666e-05,
|
| 949 |
+
"loss": 0.5287,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.06262602301031905,
|
| 954 |
+
"grad_norm": 0.7727446556091309,
|
| 955 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 956 |
+
"loss": 0.4966,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.06310046257857906,
|
| 961 |
+
"grad_norm": 0.7492961883544922,
|
| 962 |
+
"learning_rate": 4.433333333333334e-05,
|
| 963 |
+
"loss": 0.5113,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.06357490214683904,
|
| 968 |
+
"grad_norm": 0.851240873336792,
|
| 969 |
+
"learning_rate": 4.466666666666667e-05,
|
| 970 |
+
"loss": 0.4814,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.06404934171509905,
|
| 975 |
+
"grad_norm": 0.696323573589325,
|
| 976 |
+
"learning_rate": 4.5e-05,
|
| 977 |
+
"loss": 0.4951,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.06452378128335903,
|
| 982 |
+
"grad_norm": 0.712622880935669,
|
| 983 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 984 |
+
"loss": 0.4679,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.06499822085161902,
|
| 989 |
+
"grad_norm": 0.6531604528427124,
|
| 990 |
+
"learning_rate": 4.566666666666667e-05,
|
| 991 |
+
"loss": 0.4736,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.06547266041987902,
|
| 996 |
+
"grad_norm": 0.6559727787971497,
|
| 997 |
+
"learning_rate": 4.600000000000001e-05,
|
| 998 |
+
"loss": 0.4663,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.06594709998813901,
|
| 1003 |
+
"grad_norm": 0.7849781513214111,
|
| 1004 |
+
"learning_rate": 4.633333333333333e-05,
|
| 1005 |
+
"loss": 0.4749,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.066421539556399,
|
| 1010 |
+
"grad_norm": 0.6514148116111755,
|
| 1011 |
+
"learning_rate": 4.666666666666667e-05,
|
| 1012 |
+
"loss": 0.4433,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.066895979124659,
|
| 1017 |
+
"grad_norm": 0.7218091487884521,
|
| 1018 |
+
"learning_rate": 4.7e-05,
|
| 1019 |
+
"loss": 0.4618,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.06737041869291899,
|
| 1024 |
+
"grad_norm": 0.8696113228797913,
|
| 1025 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 1026 |
+
"loss": 0.5214,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.06784485826117899,
|
| 1031 |
+
"grad_norm": 0.6764204502105713,
|
| 1032 |
+
"learning_rate": 4.766666666666667e-05,
|
| 1033 |
+
"loss": 0.4632,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.06831929782943898,
|
| 1038 |
+
"grad_norm": 0.6929240226745605,
|
| 1039 |
+
"learning_rate": 4.8e-05,
|
| 1040 |
+
"loss": 0.4505,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.06879373739769896,
|
| 1045 |
+
"grad_norm": 0.7792762517929077,
|
| 1046 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 1047 |
+
"loss": 0.515,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.06926817696595897,
|
| 1052 |
+
"grad_norm": 0.7740099430084229,
|
| 1053 |
+
"learning_rate": 4.866666666666667e-05,
|
| 1054 |
+
"loss": 0.52,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.06974261653421895,
|
| 1059 |
+
"grad_norm": 0.6254486441612244,
|
| 1060 |
+
"learning_rate": 4.9e-05,
|
| 1061 |
+
"loss": 0.4599,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.07021705610247894,
|
| 1066 |
+
"grad_norm": 0.6425098776817322,
|
| 1067 |
+
"learning_rate": 4.933333333333334e-05,
|
| 1068 |
+
"loss": 0.4807,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.07069149567073894,
|
| 1073 |
+
"grad_norm": 0.6772657036781311,
|
| 1074 |
+
"learning_rate": 4.966666666666667e-05,
|
| 1075 |
+
"loss": 0.4762,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.07116593523899893,
|
| 1080 |
+
"grad_norm": 0.6634912490844727,
|
| 1081 |
+
"learning_rate": 5e-05,
|
| 1082 |
+
"loss": 0.476,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.07116593523899893,
|
| 1087 |
+
"eval_loss": 0.5722422003746033,
|
| 1088 |
+
"eval_runtime": 847.2641,
|
| 1089 |
+
"eval_samples_per_second": 8.38,
|
| 1090 |
+
"eval_steps_per_second": 2.095,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 7.139320027215299e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|