Training in progress, step 149, 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 295488936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f839b1c912078838ed387d411814b5d9734369a525d1831268151afa202e5e10
|
| 3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 591203178
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8be643ffc5c7f4ac73b54e51960cf0399fe1c12003a3c5eb47077d8bc1462643
|
| 3 |
size 591203178
|
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 sha256:84c802ac9c2b16f0cd6fb34cfa5314566b8f38d636de17f0a5a8777244876148
|
| 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:b3167249cc14ab1cd4e7d1463e098421e293c9d1ad0924be094f1a6596bad0ce
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.00209379196167,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 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 +731,349 @@
|
|
| 731 |
"eval_samples_per_second": 19.409,
|
| 732 |
"eval_steps_per_second": 9.704,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -754,12 +1097,12 @@
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
-
"should_training_stop":
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.00209379196167,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 3.01010101010101,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 149,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 731 |
"eval_samples_per_second": 19.409,
|
| 732 |
"eval_steps_per_second": 9.704,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.04040404040404,
|
| 737 |
+
"grad_norm": 0.8254684209823608,
|
| 738 |
+
"learning_rate": 3.0444763975492208e-05,
|
| 739 |
+
"loss": 0.8121,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.0606060606060606,
|
| 744 |
+
"grad_norm": 0.8718892335891724,
|
| 745 |
+
"learning_rate": 2.9329994083235857e-05,
|
| 746 |
+
"loss": 0.8341,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.080808080808081,
|
| 751 |
+
"grad_norm": 0.8887032866477966,
|
| 752 |
+
"learning_rate": 2.8227482751090445e-05,
|
| 753 |
+
"loss": 0.8622,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.101010101010101,
|
| 758 |
+
"grad_norm": 0.8461330533027649,
|
| 759 |
+
"learning_rate": 2.7137883834768073e-05,
|
| 760 |
+
"loss": 0.6929,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.121212121212121,
|
| 765 |
+
"grad_norm": 0.9766608476638794,
|
| 766 |
+
"learning_rate": 2.606184353213956e-05,
|
| 767 |
+
"loss": 0.7777,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.1414141414141414,
|
| 772 |
+
"grad_norm": 0.8678721785545349,
|
| 773 |
+
"learning_rate": 2.500000000000001e-05,
|
| 774 |
+
"loss": 0.7537,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.1616161616161618,
|
| 779 |
+
"grad_norm": 1.0271376371383667,
|
| 780 |
+
"learning_rate": 2.3952982975603496e-05,
|
| 781 |
+
"loss": 0.827,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.1818181818181817,
|
| 786 |
+
"grad_norm": 1.0533698797225952,
|
| 787 |
+
"learning_rate": 2.2921413403190772e-05,
|
| 788 |
+
"loss": 0.814,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.202020202020202,
|
| 793 |
+
"grad_norm": 0.9795958995819092,
|
| 794 |
+
"learning_rate": 2.1905903065731974e-05,
|
| 795 |
+
"loss": 0.8461,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.2222222222222223,
|
| 800 |
+
"grad_norm": 0.8794453740119934,
|
| 801 |
+
"learning_rate": 2.090705422210237e-05,
|
| 802 |
+
"loss": 0.72,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.242424242424242,
|
| 807 |
+
"grad_norm": 1.1083755493164062,
|
| 808 |
+
"learning_rate": 1.9925459249906485e-05,
|
| 809 |
+
"loss": 0.8858,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.2626262626262625,
|
| 814 |
+
"grad_norm": 0.7194259762763977,
|
| 815 |
+
"learning_rate": 1.8961700294162577e-05,
|
| 816 |
+
"loss": 0.6913,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.282828282828283,
|
| 821 |
+
"grad_norm": 0.9028263092041016,
|
| 822 |
+
"learning_rate": 1.801634892205545e-05,
|
| 823 |
+
"loss": 0.8392,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.303030303030303,
|
| 828 |
+
"grad_norm": 0.8157623410224915,
|
| 829 |
+
"learning_rate": 1.7089965783962608e-05,
|
| 830 |
+
"loss": 0.6965,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.323232323232323,
|
| 835 |
+
"grad_norm": 0.8562924861907959,
|
| 836 |
+
"learning_rate": 1.618310028095486e-05,
|
| 837 |
+
"loss": 0.7825,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.3434343434343434,
|
| 842 |
+
"grad_norm": 0.9243174195289612,
|
| 843 |
+
"learning_rate": 1.5296290238968303e-05,
|
| 844 |
+
"loss": 0.7492,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.3636363636363638,
|
| 849 |
+
"grad_norm": 0.8757293820381165,
|
| 850 |
+
"learning_rate": 1.4430061589841121e-05,
|
| 851 |
+
"loss": 0.7647,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.3838383838383836,
|
| 856 |
+
"grad_norm": 0.9440964460372925,
|
| 857 |
+
"learning_rate": 1.3584928059404205e-05,
|
| 858 |
+
"loss": 0.7717,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.404040404040404,
|
| 863 |
+
"grad_norm": 0.9191311001777649,
|
| 864 |
+
"learning_rate": 1.2761390862810907e-05,
|
| 865 |
+
"loss": 0.8079,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.4242424242424243,
|
| 870 |
+
"grad_norm": 0.9735956788063049,
|
| 871 |
+
"learning_rate": 1.1959938407286097e-05,
|
| 872 |
+
"loss": 0.7753,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.4444444444444446,
|
| 877 |
+
"grad_norm": 0.9409034848213196,
|
| 878 |
+
"learning_rate": 1.118104600247129e-05,
|
| 879 |
+
"loss": 0.7694,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.4646464646464645,
|
| 884 |
+
"grad_norm": 1.0457966327667236,
|
| 885 |
+
"learning_rate": 1.0425175578537299e-05,
|
| 886 |
+
"loss": 0.7946,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.484848484848485,
|
| 891 |
+
"grad_norm": 1.1097992658615112,
|
| 892 |
+
"learning_rate": 9.692775412231863e-06,
|
| 893 |
+
"loss": 0.8222,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.505050505050505,
|
| 898 |
+
"grad_norm": 0.7935383319854736,
|
| 899 |
+
"learning_rate": 8.984279861024453e-06,
|
| 900 |
+
"loss": 0.8042,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.525252525252525,
|
| 905 |
+
"grad_norm": 0.7349716424942017,
|
| 906 |
+
"learning_rate": 8.30010910550611e-06,
|
| 907 |
+
"loss": 0.6712,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.5454545454545454,
|
| 912 |
+
"grad_norm": 0.8446260690689087,
|
| 913 |
+
"learning_rate": 7.640668900196984e-06,
|
| 914 |
+
"loss": 0.7412,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.5656565656565657,
|
| 919 |
+
"grad_norm": 0.8470379710197449,
|
| 920 |
+
"learning_rate": 7.006350332909495e-06,
|
| 921 |
+
"loss": 0.6806,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.5858585858585856,
|
| 926 |
+
"grad_norm": 0.8487269282341003,
|
| 927 |
+
"learning_rate": 6.397529592809614e-06,
|
| 928 |
+
"loss": 0.8121,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.606060606060606,
|
| 933 |
+
"grad_norm": 0.8327857255935669,
|
| 934 |
+
"learning_rate": 5.814567747314048e-06,
|
| 935 |
+
"loss": 0.6845,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.6262626262626263,
|
| 940 |
+
"grad_norm": 0.9190646409988403,
|
| 941 |
+
"learning_rate": 5.257810527955409e-06,
|
| 942 |
+
"loss": 0.7326,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.6464646464646466,
|
| 947 |
+
"grad_norm": 0.9106457233428955,
|
| 948 |
+
"learning_rate": 4.727588125342669e-06,
|
| 949 |
+
"loss": 0.7749,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.6666666666666665,
|
| 954 |
+
"grad_norm": 0.890715479850769,
|
| 955 |
+
"learning_rate": 4.224214993338149e-06,
|
| 956 |
+
"loss": 0.7276,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.686868686868687,
|
| 961 |
+
"grad_norm": 0.8417027592658997,
|
| 962 |
+
"learning_rate": 3.7479896625674027e-06,
|
| 963 |
+
"loss": 0.675,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.707070707070707,
|
| 968 |
+
"grad_norm": 0.9032696485519409,
|
| 969 |
+
"learning_rate": 3.299194563372604e-06,
|
| 970 |
+
"loss": 0.6802,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.7272727272727275,
|
| 975 |
+
"grad_norm": 1.2423067092895508,
|
| 976 |
+
"learning_rate": 2.878095858314278e-06,
|
| 977 |
+
"loss": 0.9244,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.7474747474747474,
|
| 982 |
+
"grad_norm": 0.8352429866790771,
|
| 983 |
+
"learning_rate": 2.4849432843208785e-06,
|
| 984 |
+
"loss": 0.8869,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.7676767676767677,
|
| 989 |
+
"grad_norm": 0.8083487153053284,
|
| 990 |
+
"learning_rate": 2.1199700045797077e-06,
|
| 991 |
+
"loss": 0.6654,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.787878787878788,
|
| 996 |
+
"grad_norm": 0.7540408372879028,
|
| 997 |
+
"learning_rate": 1.7833924702570725e-06,
|
| 998 |
+
"loss": 0.6913,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.808080808080808,
|
| 1003 |
+
"grad_norm": 0.9516521692276001,
|
| 1004 |
+
"learning_rate": 1.4754102921297364e-06,
|
| 1005 |
+
"loss": 0.8141,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.8282828282828283,
|
| 1010 |
+
"grad_norm": 0.7741652131080627,
|
| 1011 |
+
"learning_rate": 1.196206122203647e-06,
|
| 1012 |
+
"loss": 0.6433,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.8484848484848486,
|
| 1017 |
+
"grad_norm": 0.7631287574768066,
|
| 1018 |
+
"learning_rate": 9.459455453902866e-07,
|
| 1019 |
+
"loss": 0.5956,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.8686868686868685,
|
| 1024 |
+
"grad_norm": 0.9075913429260254,
|
| 1025 |
+
"learning_rate": 7.247769813048644e-07,
|
| 1026 |
+
"loss": 0.7604,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.888888888888889,
|
| 1031 |
+
"grad_norm": 0.8504214882850647,
|
| 1032 |
+
"learning_rate": 5.328315962444874e-07,
|
| 1033 |
+
"loss": 0.7028,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.909090909090909,
|
| 1038 |
+
"grad_norm": 0.9223804473876953,
|
| 1039 |
+
"learning_rate": 3.702232253986804e-07,
|
| 1040 |
+
"loss": 0.7165,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.929292929292929,
|
| 1045 |
+
"grad_norm": 0.92230623960495,
|
| 1046 |
+
"learning_rate": 2.3704830533821108e-07,
|
| 1047 |
+
"loss": 0.8212,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.9494949494949494,
|
| 1052 |
+
"grad_norm": 1.021527886390686,
|
| 1053 |
+
"learning_rate": 1.333858168224178e-07,
|
| 1054 |
+
"loss": 0.9158,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.9696969696969697,
|
| 1059 |
+
"grad_norm": 1.0654287338256836,
|
| 1060 |
+
"learning_rate": 5.929723795884967e-08,
|
| 1061 |
+
"loss": 0.8295,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.98989898989899,
|
| 1066 |
+
"grad_norm": 0.8834518790245056,
|
| 1067 |
+
"learning_rate": 1.482650774303207e-08,
|
| 1068 |
+
"loss": 0.7746,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 3.01010101010101,
|
| 1073 |
+
"grad_norm": 1.6613935232162476,
|
| 1074 |
+
"learning_rate": 0.0,
|
| 1075 |
+
"loss": 1.006,
|
| 1076 |
+
"step": 149
|
| 1077 |
}
|
| 1078 |
],
|
| 1079 |
"logging_steps": 1,
|
|
|
|
| 1097 |
"should_evaluate": false,
|
| 1098 |
"should_log": false,
|
| 1099 |
"should_save": true,
|
| 1100 |
+
"should_training_stop": true
|
| 1101 |
},
|
| 1102 |
"attributes": {}
|
| 1103 |
}
|
| 1104 |
},
|
| 1105 |
+
"total_flos": 4.05240513036288e+16,
|
| 1106 |
"train_batch_size": 8,
|
| 1107 |
"trial_name": null,
|
| 1108 |
"trial_params": null
|