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 332316480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8a6bb7923d99eb1addaf80dd3c5f68a635e0004c3ad087e101927f681a3e8ef
|
| 3 |
size 332316480
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 169157892
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4c14e484e7f9f6c436873c65eed10a21b2c5aee925b083aacae1f5a8cb3a78c
|
| 3 |
size 169157892
|
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:cbe33361b74b04c35e54ffd954f5a7a824246f9c920096ddc53ea563d6c62356
|
| 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 sha256:5cb01d4f0da8d959e9ca5a4773566e24c639c6b8f18e1285757275e715c7b05f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 2.1530466079711914,
|
| 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 +731,364 @@
|
|
| 731 |
"eval_samples_per_second": 22.191,
|
| 732 |
"eval_steps_per_second": 5.661,
|
| 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": 2.1530466079711914,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 2.5974025974025974,
|
| 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": 22.191,
|
| 732 |
"eval_steps_per_second": 5.661,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.7489177489177488,
|
| 737 |
+
"grad_norm": 1.058007001876831,
|
| 738 |
+
"learning_rate": 4.0896120024874286e-05,
|
| 739 |
+
"loss": 1.5795,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.7662337662337664,
|
| 744 |
+
"grad_norm": 1.2379379272460938,
|
| 745 |
+
"learning_rate": 3.9950299516607766e-05,
|
| 746 |
+
"loss": 1.4978,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.7835497835497836,
|
| 751 |
+
"grad_norm": 1.4069570302963257,
|
| 752 |
+
"learning_rate": 3.900821206181521e-05,
|
| 753 |
+
"loss": 1.5601,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.8008658008658007,
|
| 758 |
+
"grad_norm": 1.4146642684936523,
|
| 759 |
+
"learning_rate": 3.8070207607527584e-05,
|
| 760 |
+
"loss": 1.5123,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.8181818181818183,
|
| 765 |
+
"grad_norm": 1.520447015762329,
|
| 766 |
+
"learning_rate": 3.713663458410779e-05,
|
| 767 |
+
"loss": 1.4908,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.8354978354978355,
|
| 772 |
+
"grad_norm": 1.6304378509521484,
|
| 773 |
+
"learning_rate": 3.620783977582305e-05,
|
| 774 |
+
"loss": 1.3594,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.8528138528138527,
|
| 779 |
+
"grad_norm": 1.668250560760498,
|
| 780 |
+
"learning_rate": 3.528416819202881e-05,
|
| 781 |
+
"loss": 1.4907,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.87012987012987,
|
| 786 |
+
"grad_norm": 1.842556357383728,
|
| 787 |
+
"learning_rate": 3.43659629390117e-05,
|
| 788 |
+
"loss": 1.7364,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.8874458874458875,
|
| 793 |
+
"grad_norm": 2.1994338035583496,
|
| 794 |
+
"learning_rate": 3.345356509253959e-05,
|
| 795 |
+
"loss": 1.8325,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.9047619047619047,
|
| 800 |
+
"grad_norm": 2.015636920928955,
|
| 801 |
+
"learning_rate": 3.254731357116597e-05,
|
| 802 |
+
"loss": 1.6642,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.922077922077922,
|
| 807 |
+
"grad_norm": 2.2322309017181396,
|
| 808 |
+
"learning_rate": 3.16475450103354e-05,
|
| 809 |
+
"loss": 1.5802,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.9393939393939394,
|
| 814 |
+
"grad_norm": 2.6270971298217773,
|
| 815 |
+
"learning_rate": 3.0754593637337276e-05,
|
| 816 |
+
"loss": 1.6923,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.9567099567099566,
|
| 821 |
+
"grad_norm": 3.3639109134674072,
|
| 822 |
+
"learning_rate": 2.986879114715403e-05,
|
| 823 |
+
"loss": 1.7439,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.974025974025974,
|
| 828 |
+
"grad_norm": 3.1718485355377197,
|
| 829 |
+
"learning_rate": 2.899046657924992e-05,
|
| 830 |
+
"loss": 1.4849,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.9913419913419914,
|
| 835 |
+
"grad_norm": 2.31093168258667,
|
| 836 |
+
"learning_rate": 2.8119946195346375e-05,
|
| 837 |
+
"loss": 1.7909,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.0086580086580086,
|
| 842 |
+
"grad_norm": 2.096163034439087,
|
| 843 |
+
"learning_rate": 2.7257553358229034e-05,
|
| 844 |
+
"loss": 1.5833,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.0259740259740258,
|
| 849 |
+
"grad_norm": 0.9350630044937134,
|
| 850 |
+
"learning_rate": 2.6403608411631742e-05,
|
| 851 |
+
"loss": 1.2758,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.0432900432900434,
|
| 856 |
+
"grad_norm": 1.2270903587341309,
|
| 857 |
+
"learning_rate": 2.555842856124182e-05,
|
| 858 |
+
"loss": 1.5394,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.0606060606060606,
|
| 863 |
+
"grad_norm": 1.1900259256362915,
|
| 864 |
+
"learning_rate": 2.472232775687119e-05,
|
| 865 |
+
"loss": 1.1756,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.0779220779220777,
|
| 870 |
+
"grad_norm": 1.293131709098816,
|
| 871 |
+
"learning_rate": 2.389561657583681e-05,
|
| 872 |
+
"loss": 1.2139,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.0952380952380953,
|
| 877 |
+
"grad_norm": 1.4784541130065918,
|
| 878 |
+
"learning_rate": 2.30786021075939e-05,
|
| 879 |
+
"loss": 1.4056,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.1125541125541125,
|
| 884 |
+
"grad_norm": 1.422511339187622,
|
| 885 |
+
"learning_rate": 2.2271587839664672e-05,
|
| 886 |
+
"loss": 1.0889,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.1298701298701297,
|
| 891 |
+
"grad_norm": 1.5573115348815918,
|
| 892 |
+
"learning_rate": 2.1474873544905205e-05,
|
| 893 |
+
"loss": 1.2393,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.1471861471861473,
|
| 898 |
+
"grad_norm": 1.5458406209945679,
|
| 899 |
+
"learning_rate": 2.0688755170151996e-05,
|
| 900 |
+
"loss": 1.2199,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.1645021645021645,
|
| 905 |
+
"grad_norm": 1.9785674810409546,
|
| 906 |
+
"learning_rate": 1.9913524726289784e-05,
|
| 907 |
+
"loss": 1.3959,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.1818181818181817,
|
| 912 |
+
"grad_norm": 2.0440776348114014,
|
| 913 |
+
"learning_rate": 1.914947017978153e-05,
|
| 914 |
+
"loss": 1.3751,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.1991341991341993,
|
| 919 |
+
"grad_norm": 2.1104283332824707,
|
| 920 |
+
"learning_rate": 1.8396875345700497e-05,
|
| 921 |
+
"loss": 1.1956,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.2164502164502164,
|
| 926 |
+
"grad_norm": 2.581237554550171,
|
| 927 |
+
"learning_rate": 1.76560197823046e-05,
|
| 928 |
+
"loss": 1.3668,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.2337662337662336,
|
| 933 |
+
"grad_norm": 3.1223180294036865,
|
| 934 |
+
"learning_rate": 1.692717868719195e-05,
|
| 935 |
+
"loss": 1.136,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.2510822510822512,
|
| 940 |
+
"grad_norm": 2.574193239212036,
|
| 941 |
+
"learning_rate": 1.621062279507617e-05,
|
| 942 |
+
"loss": 1.0829,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.2683982683982684,
|
| 947 |
+
"grad_norm": 1.1069941520690918,
|
| 948 |
+
"learning_rate": 1.550661827721941e-05,
|
| 949 |
+
"loss": 1.1654,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.2857142857142856,
|
| 954 |
+
"grad_norm": 1.4014630317687988,
|
| 955 |
+
"learning_rate": 1.4815426642560754e-05,
|
| 956 |
+
"loss": 1.3528,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.303030303030303,
|
| 961 |
+
"grad_norm": 1.6205848455429077,
|
| 962 |
+
"learning_rate": 1.413730464057616e-05,
|
| 963 |
+
"loss": 1.4042,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.3203463203463204,
|
| 968 |
+
"grad_norm": 1.6912100315093994,
|
| 969 |
+
"learning_rate": 1.3472504165906613e-05,
|
| 970 |
+
"loss": 1.1654,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.3376623376623376,
|
| 975 |
+
"grad_norm": 1.7683279514312744,
|
| 976 |
+
"learning_rate": 1.2821272164789544e-05,
|
| 977 |
+
"loss": 1.2481,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.354978354978355,
|
| 982 |
+
"grad_norm": 1.8324084281921387,
|
| 983 |
+
"learning_rate": 1.2183850543328312e-05,
|
| 984 |
+
"loss": 1.1558,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.3722943722943723,
|
| 989 |
+
"grad_norm": 1.9852972030639648,
|
| 990 |
+
"learning_rate": 1.156047607763407e-05,
|
| 991 |
+
"loss": 1.2857,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.3896103896103895,
|
| 996 |
+
"grad_norm": 2.126631259918213,
|
| 997 |
+
"learning_rate": 1.0951380325872979e-05,
|
| 998 |
+
"loss": 1.2143,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.4069264069264067,
|
| 1003 |
+
"grad_norm": 2.3943769931793213,
|
| 1004 |
+
"learning_rate": 1.0356789542251938e-05,
|
| 1005 |
+
"loss": 1.2955,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.4242424242424243,
|
| 1010 |
+
"grad_norm": 2.30513596534729,
|
| 1011 |
+
"learning_rate": 9.776924592974256e-06,
|
| 1012 |
+
"loss": 1.1925,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.4415584415584415,
|
| 1017 |
+
"grad_norm": 2.5262770652770996,
|
| 1018 |
+
"learning_rate": 9.212000874196953e-06,
|
| 1019 |
+
"loss": 1.2257,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.458874458874459,
|
| 1024 |
+
"grad_norm": 3.0429446697235107,
|
| 1025 |
+
"learning_rate": 8.662228232019876e-06,
|
| 1026 |
+
"loss": 1.4461,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.4761904761904763,
|
| 1031 |
+
"grad_norm": 3.428879737854004,
|
| 1032 |
+
"learning_rate": 8.127810884536403e-06,
|
| 1033 |
+
"loss": 1.0103,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.4935064935064934,
|
| 1038 |
+
"grad_norm": 2.0732643604278564,
|
| 1039 |
+
"learning_rate": 7.60894734597476e-06,
|
| 1040 |
+
"loss": 1.0342,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.5108225108225106,
|
| 1045 |
+
"grad_norm": 1.3209905624389648,
|
| 1046 |
+
"learning_rate": 7.105830352958142e-06,
|
| 1047 |
+
"loss": 1.4006,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.5281385281385282,
|
| 1052 |
+
"grad_norm": 1.4162795543670654,
|
| 1053 |
+
"learning_rate": 6.618646792910893e-06,
|
| 1054 |
+
"loss": 1.2731,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.5454545454545454,
|
| 1059 |
+
"grad_norm": 1.7020889520645142,
|
| 1060 |
+
"learning_rate": 6.147577634637414e-06,
|
| 1061 |
+
"loss": 1.3335,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.562770562770563,
|
| 1066 |
+
"grad_norm": 1.5427604913711548,
|
| 1067 |
+
"learning_rate": 5.692797861099719e-06,
|
| 1068 |
+
"loss": 1.0563,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.58008658008658,
|
| 1073 |
+
"grad_norm": 1.9081095457077026,
|
| 1074 |
+
"learning_rate": 5.25447640441834e-06,
|
| 1075 |
+
"loss": 1.2153,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.5974025974025974,
|
| 1080 |
+
"grad_norm": 1.9644572734832764,
|
| 1081 |
+
"learning_rate": 4.832776083120982e-06,
|
| 1082 |
+
"loss": 1.3009,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.5974025974025974,
|
| 1087 |
+
"eval_loss": 2.225019931793213,
|
| 1088 |
+
"eval_runtime": 4.4108,
|
| 1089 |
+
"eval_samples_per_second": 22.218,
|
| 1090 |
+
"eval_steps_per_second": 5.668,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 1
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 6.202571390189568e+16,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|