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 37762064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92600951d2230c185e2f4b432ae7854191326564d2b3896429cd06dcc57d3479
|
| 3 |
size 37762064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 19283770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81f4341e9417cb9ad739edcbf3690894eb90f4a7883b39c4efaace24cedab31d
|
| 3 |
size 19283770
|
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 sha256:40eeb7dfe79107ab30a3df5ab797ee37d2bb792e86b7e9508ea9164419baee1f
|
| 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:cc4a786186a574bdc543ff4b4563aab7c5e0b442c74c85899bb42a25553c5d0c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 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": 144.052,
|
| 732 |
"eval_steps_per_second": 36.16,
|
| 733 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
@@ -745,7 +1103,7 @@
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
-
"early_stopping_patience_counter":
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
@@ -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": 2.1347427368164062,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.5154639175257731,
|
| 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": 144.052,
|
| 732 |
"eval_steps_per_second": 36.16,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.3470790378006873,
|
| 737 |
+
"grad_norm": 6338.203125,
|
| 738 |
+
"learning_rate": 3.1982717529770985e-05,
|
| 739 |
+
"loss": 8.1504,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.35051546391752575,
|
| 744 |
+
"grad_norm": 3960.850341796875,
|
| 745 |
+
"learning_rate": 3.148751264019667e-05,
|
| 746 |
+
"loss": 7.7718,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.3539518900343643,
|
| 751 |
+
"grad_norm": 3253.1552734375,
|
| 752 |
+
"learning_rate": 3.099190107951924e-05,
|
| 753 |
+
"loss": 7.5944,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.35738831615120276,
|
| 758 |
+
"grad_norm": 2214.524658203125,
|
| 759 |
+
"learning_rate": 3.049601834299076e-05,
|
| 760 |
+
"loss": 7.5333,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.36082474226804123,
|
| 765 |
+
"grad_norm": 2329.060791015625,
|
| 766 |
+
"learning_rate": 3e-05,
|
| 767 |
+
"loss": 7.5675,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.3642611683848797,
|
| 772 |
+
"grad_norm": 1914.9527587890625,
|
| 773 |
+
"learning_rate": 2.9503981657009246e-05,
|
| 774 |
+
"loss": 7.3778,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.36769759450171824,
|
| 779 |
+
"grad_norm": 1756.5228271484375,
|
| 780 |
+
"learning_rate": 2.9008098920480752e-05,
|
| 781 |
+
"loss": 7.5316,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.3711340206185567,
|
| 786 |
+
"grad_norm": 1628.3492431640625,
|
| 787 |
+
"learning_rate": 2.851248735980333e-05,
|
| 788 |
+
"loss": 7.1625,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.3745704467353952,
|
| 793 |
+
"grad_norm": 1857.13671875,
|
| 794 |
+
"learning_rate": 2.801728247022902e-05,
|
| 795 |
+
"loss": 7.4011,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.37800687285223367,
|
| 800 |
+
"grad_norm": 1966.443359375,
|
| 801 |
+
"learning_rate": 2.7522619635830034e-05,
|
| 802 |
+
"loss": 7.3879,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.38144329896907214,
|
| 807 |
+
"grad_norm": 1875.7662353515625,
|
| 808 |
+
"learning_rate": 2.702863409248612e-05,
|
| 809 |
+
"loss": 7.6974,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.3848797250859107,
|
| 814 |
+
"grad_norm": 3008.91162109375,
|
| 815 |
+
"learning_rate": 2.6535460890912416e-05,
|
| 816 |
+
"loss": 7.8305,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.38831615120274915,
|
| 821 |
+
"grad_norm": 2057.904052734375,
|
| 822 |
+
"learning_rate": 2.604323485973793e-05,
|
| 823 |
+
"loss": 7.8253,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.3917525773195876,
|
| 828 |
+
"grad_norm": 2149.185546875,
|
| 829 |
+
"learning_rate": 2.555209056864474e-05,
|
| 830 |
+
"loss": 7.2513,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.3951890034364261,
|
| 835 |
+
"grad_norm": 2182.825439453125,
|
| 836 |
+
"learning_rate": 2.5062162291577978e-05,
|
| 837 |
+
"loss": 7.7119,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.39862542955326463,
|
| 842 |
+
"grad_norm": 2759.802490234375,
|
| 843 |
+
"learning_rate": 2.4573583970036712e-05,
|
| 844 |
+
"loss": 7.7795,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.4020618556701031,
|
| 849 |
+
"grad_norm": 2170.989990234375,
|
| 850 |
+
"learning_rate": 2.4086489176455595e-05,
|
| 851 |
+
"loss": 7.8915,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.4054982817869416,
|
| 856 |
+
"grad_norm": 2467.65576171875,
|
| 857 |
+
"learning_rate": 2.36010110776876e-05,
|
| 858 |
+
"loss": 7.9465,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.40893470790378006,
|
| 863 |
+
"grad_norm": 2266.196044921875,
|
| 864 |
+
"learning_rate": 2.3117282398597456e-05,
|
| 865 |
+
"loss": 8.0087,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.41237113402061853,
|
| 870 |
+
"grad_norm": 2992.08349609375,
|
| 871 |
+
"learning_rate": 2.263543538577603e-05,
|
| 872 |
+
"loss": 7.7058,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.41580756013745707,
|
| 877 |
+
"grad_norm": 1708.01318359375,
|
| 878 |
+
"learning_rate": 2.215560177138541e-05,
|
| 879 |
+
"loss": 8.1656,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.41924398625429554,
|
| 884 |
+
"grad_norm": 4836.68505859375,
|
| 885 |
+
"learning_rate": 2.167791273714467e-05,
|
| 886 |
+
"loss": 7.6497,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.422680412371134,
|
| 891 |
+
"grad_norm": 2311.93994140625,
|
| 892 |
+
"learning_rate": 2.1202498878466062e-05,
|
| 893 |
+
"loss": 8.5898,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.4261168384879725,
|
| 898 |
+
"grad_norm": 3336.768310546875,
|
| 899 |
+
"learning_rate": 2.072949016875158e-05,
|
| 900 |
+
"loss": 7.8291,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.42955326460481097,
|
| 905 |
+
"grad_norm": 2548.131103515625,
|
| 906 |
+
"learning_rate": 2.0259015923859498e-05,
|
| 907 |
+
"loss": 7.5833,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.4329896907216495,
|
| 912 |
+
"grad_norm": 3319.1611328125,
|
| 913 |
+
"learning_rate": 1.979120476675071e-05,
|
| 914 |
+
"loss": 7.9073,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.436426116838488,
|
| 919 |
+
"grad_norm": 2070.8388671875,
|
| 920 |
+
"learning_rate": 1.9326184592324503e-05,
|
| 921 |
+
"loss": 7.893,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.43986254295532645,
|
| 926 |
+
"grad_norm": 2963.176025390625,
|
| 927 |
+
"learning_rate": 1.8864082532453373e-05,
|
| 928 |
+
"loss": 8.0254,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.44329896907216493,
|
| 933 |
+
"grad_norm": 3843.35107421875,
|
| 934 |
+
"learning_rate": 1.840502492122644e-05,
|
| 935 |
+
"loss": 8.276,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.44673539518900346,
|
| 940 |
+
"grad_norm": 3847.33349609375,
|
| 941 |
+
"learning_rate": 1.7949137260410924e-05,
|
| 942 |
+
"loss": 8.1098,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.45017182130584193,
|
| 947 |
+
"grad_norm": 3402.124267578125,
|
| 948 |
+
"learning_rate": 1.7496544185141295e-05,
|
| 949 |
+
"loss": 8.5796,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.4536082474226804,
|
| 954 |
+
"grad_norm": 3649.834228515625,
|
| 955 |
+
"learning_rate": 1.7047369429845216e-05,
|
| 956 |
+
"loss": 8.0409,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.4570446735395189,
|
| 961 |
+
"grad_norm": 2720.489013671875,
|
| 962 |
+
"learning_rate": 1.6601735794415806e-05,
|
| 963 |
+
"loss": 8.0999,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.46048109965635736,
|
| 968 |
+
"grad_norm": 2908.25537109375,
|
| 969 |
+
"learning_rate": 1.615976511063937e-05,
|
| 970 |
+
"loss": 8.0204,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.4639175257731959,
|
| 975 |
+
"grad_norm": 3314.382080078125,
|
| 976 |
+
"learning_rate": 1.5721578208887793e-05,
|
| 977 |
+
"loss": 8.3157,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.46735395189003437,
|
| 982 |
+
"grad_norm": 4135.548828125,
|
| 983 |
+
"learning_rate": 1.5287294885084766e-05,
|
| 984 |
+
"loss": 8.3494,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.47079037800687284,
|
| 989 |
+
"grad_norm": 4054.155517578125,
|
| 990 |
+
"learning_rate": 1.4857033867954697e-05,
|
| 991 |
+
"loss": 7.8104,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.4742268041237113,
|
| 996 |
+
"grad_norm": 7448.6650390625,
|
| 997 |
+
"learning_rate": 1.4430912786563554e-05,
|
| 998 |
+
"loss": 8.2547,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.47766323024054985,
|
| 1003 |
+
"grad_norm": 2514.72705078125,
|
| 1004 |
+
"learning_rate": 1.4009048138160195e-05,
|
| 1005 |
+
"loss": 8.582,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.48109965635738833,
|
| 1010 |
+
"grad_norm": 3390.73779296875,
|
| 1011 |
+
"learning_rate": 1.3591555256327199e-05,
|
| 1012 |
+
"loss": 8.3898,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.4845360824742268,
|
| 1017 |
+
"grad_norm": 5241.2099609375,
|
| 1018 |
+
"learning_rate": 1.3178548279449822e-05,
|
| 1019 |
+
"loss": 8.1913,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.4879725085910653,
|
| 1024 |
+
"grad_norm": 4858.0283203125,
|
| 1025 |
+
"learning_rate": 1.2770140119511693e-05,
|
| 1026 |
+
"loss": 8.7944,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.49140893470790376,
|
| 1031 |
+
"grad_norm": 5469.38037109375,
|
| 1032 |
+
"learning_rate": 1.2366442431225809e-05,
|
| 1033 |
+
"loss": 8.8084,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.4948453608247423,
|
| 1038 |
+
"grad_norm": 6011.06591796875,
|
| 1039 |
+
"learning_rate": 1.1967565581509248e-05,
|
| 1040 |
+
"loss": 8.8881,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.49828178694158076,
|
| 1045 |
+
"grad_norm": 5176.05078125,
|
| 1046 |
+
"learning_rate": 1.1573618619309965e-05,
|
| 1047 |
+
"loss": 8.9016,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.5017182130584192,
|
| 1052 |
+
"grad_norm": 6610.90478515625,
|
| 1053 |
+
"learning_rate": 1.1184709245793889e-05,
|
| 1054 |
+
"loss": 8.6331,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.5051546391752577,
|
| 1059 |
+
"grad_norm": 10126.125,
|
| 1060 |
+
"learning_rate": 1.0800943784900502e-05,
|
| 1061 |
+
"loss": 7.9256,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.5085910652920962,
|
| 1066 |
+
"grad_norm": 5469.77978515625,
|
| 1067 |
+
"learning_rate": 1.042242715427494e-05,
|
| 1068 |
+
"loss": 10.2646,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.5120274914089347,
|
| 1073 |
+
"grad_norm": 4336.35205078125,
|
| 1074 |
+
"learning_rate": 1.004926283658455e-05,
|
| 1075 |
+
"loss": 10.6199,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.5154639175257731,
|
| 1080 |
+
"grad_norm": 7235.44677734375,
|
| 1081 |
+
"learning_rate": 9.681552851227774e-06,
|
| 1082 |
+
"loss": 13.1587,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.5154639175257731,
|
| 1087 |
+
"eval_loss": 2.1347427368164062,
|
| 1088 |
+
"eval_runtime": 3.3947,
|
| 1089 |
+
"eval_samples_per_second": 144.344,
|
| 1090 |
+
"eval_steps_per_second": 36.233,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 0
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 4959928577949696.0,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|