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 578859568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:118c8f4a0300508828f2e88d46204c176479b3e1c99732414232884e7bd4f0aa
|
| 3 |
size 578859568
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 294324372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:418dfccc8b5c8b256ab0a2b604a7503b16aa1374f1a08b80b34bdb5a8112e300
|
| 3 |
size 294324372
|
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:a024eb23a26bb335e268967056f207c3831f0e4adc54f097ba2f8a926be0960d
|
| 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 sha256:48de68a65bf60a607751c984fbe709cfb356970dfe50a7f6e3454a1ff0e15e08
|
| 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": 11.555,
|
| 732 |
"eval_steps_per_second": 5.787,
|
| 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": 2,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8552482724189758,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 0.0041695332207559365,
|
| 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": 11.555,
|
| 732 |
"eval_steps_per_second": 5.787,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.002807485701975664,
|
| 737 |
+
"grad_norm": 1.510432481765747,
|
| 738 |
+
"learning_rate": 0.0018345732537213026,
|
| 739 |
+
"loss": 1.4424,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.002835282590114037,
|
| 744 |
+
"grad_norm": 0.1634325534105301,
|
| 745 |
+
"learning_rate": 0.001831024096513104,
|
| 746 |
+
"loss": 0.9927,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.0028630794782524096,
|
| 751 |
+
"grad_norm": 0.11758747696876526,
|
| 752 |
+
"learning_rate": 0.0018274407791591964,
|
| 753 |
+
"loss": 1.0068,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.0028908763663907824,
|
| 758 |
+
"grad_norm": 0.13593055307865143,
|
| 759 |
+
"learning_rate": 0.0018238234489557216,
|
| 760 |
+
"loss": 1.0023,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.0029186732545291557,
|
| 765 |
+
"grad_norm": 0.1236187294125557,
|
| 766 |
+
"learning_rate": 0.0018201722545969558,
|
| 767 |
+
"loss": 0.8913,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.0029464701426675285,
|
| 772 |
+
"grad_norm": 0.1045624166727066,
|
| 773 |
+
"learning_rate": 0.0018164873461691987,
|
| 774 |
+
"loss": 0.952,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.0029742670308059013,
|
| 779 |
+
"grad_norm": 0.1336205154657364,
|
| 780 |
+
"learning_rate": 0.0018127688751446028,
|
| 781 |
+
"loss": 0.9185,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.003002063918944274,
|
| 786 |
+
"grad_norm": 0.20375819504261017,
|
| 787 |
+
"learning_rate": 0.0018090169943749475,
|
| 788 |
+
"loss": 0.7956,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.003029860807082647,
|
| 793 |
+
"grad_norm": 0.11180537939071655,
|
| 794 |
+
"learning_rate": 0.0018052318580853563,
|
| 795 |
+
"loss": 0.6942,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.00305765769522102,
|
| 800 |
+
"grad_norm": 0.3445965349674225,
|
| 801 |
+
"learning_rate": 0.0018014136218679566,
|
| 802 |
+
"loss": 0.8457,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.003085454583359393,
|
| 807 |
+
"grad_norm": 0.19809404015541077,
|
| 808 |
+
"learning_rate": 0.0017975624426754845,
|
| 809 |
+
"loss": 0.689,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.0031132514714977658,
|
| 814 |
+
"grad_norm": 0.4088907837867737,
|
| 815 |
+
"learning_rate": 0.0017936784788148326,
|
| 816 |
+
"loss": 0.887,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.0031410483596361386,
|
| 821 |
+
"grad_norm": 0.757510781288147,
|
| 822 |
+
"learning_rate": 0.0017897618899405424,
|
| 823 |
+
"loss": 0.8129,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.003168845247774512,
|
| 828 |
+
"grad_norm": 0.1284535676240921,
|
| 829 |
+
"learning_rate": 0.0017858128370482425,
|
| 830 |
+
"loss": 0.9147,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.0031966421359128847,
|
| 835 |
+
"grad_norm": 1.1778861284255981,
|
| 836 |
+
"learning_rate": 0.00178183148246803,
|
| 837 |
+
"loss": 0.8639,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.0032244390240512575,
|
| 842 |
+
"grad_norm": 0.24793654680252075,
|
| 843 |
+
"learning_rate": 0.0017778179898577974,
|
| 844 |
+
"loss": 0.9027,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.0032522359121896303,
|
| 849 |
+
"grad_norm": 0.17602455615997314,
|
| 850 |
+
"learning_rate": 0.0017737725241965068,
|
| 851 |
+
"loss": 1.0078,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.003280032800328003,
|
| 856 |
+
"grad_norm": 0.18490758538246155,
|
| 857 |
+
"learning_rate": 0.0017696952517774062,
|
| 858 |
+
"loss": 0.7916,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.0033078296884663763,
|
| 863 |
+
"grad_norm": 0.17348746955394745,
|
| 864 |
+
"learning_rate": 0.0017655863402011947,
|
| 865 |
+
"loss": 0.9932,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.003335626576604749,
|
| 870 |
+
"grad_norm": 0.22050045430660248,
|
| 871 |
+
"learning_rate": 0.0017614459583691344,
|
| 872 |
+
"loss": 0.8613,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.003363423464743122,
|
| 877 |
+
"grad_norm": 0.12003365904092789,
|
| 878 |
+
"learning_rate": 0.0017572742764761053,
|
| 879 |
+
"loss": 0.9392,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.0033912203528814948,
|
| 884 |
+
"grad_norm": 0.10987789183855057,
|
| 885 |
+
"learning_rate": 0.001753071466003611,
|
| 886 |
+
"loss": 0.7309,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.003419017241019868,
|
| 891 |
+
"grad_norm": 0.11258568614721298,
|
| 892 |
+
"learning_rate": 0.0017488376997127281,
|
| 893 |
+
"loss": 0.7541,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.003446814129158241,
|
| 898 |
+
"grad_norm": 0.14257432520389557,
|
| 899 |
+
"learning_rate": 0.0017445731516370071,
|
| 900 |
+
"loss": 0.7806,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.0034746110172966136,
|
| 905 |
+
"grad_norm": 0.1824330985546112,
|
| 906 |
+
"learning_rate": 0.0017402779970753155,
|
| 907 |
+
"loss": 0.8882,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.0035024079054349865,
|
| 912 |
+
"grad_norm": 0.1172509491443634,
|
| 913 |
+
"learning_rate": 0.001735952412584635,
|
| 914 |
+
"loss": 0.8695,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.0035302047935733593,
|
| 919 |
+
"grad_norm": 0.1342688351869583,
|
| 920 |
+
"learning_rate": 0.0017315965759728013,
|
| 921 |
+
"loss": 0.6943,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.0035580016817117325,
|
| 926 |
+
"grad_norm": 0.11804018169641495,
|
| 927 |
+
"learning_rate": 0.0017272106662911972,
|
| 928 |
+
"loss": 0.6733,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.0035857985698501053,
|
| 933 |
+
"grad_norm": 0.1424594670534134,
|
| 934 |
+
"learning_rate": 0.0017227948638273915,
|
| 935 |
+
"loss": 0.8569,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.003613595457988478,
|
| 940 |
+
"grad_norm": 0.10879236459732056,
|
| 941 |
+
"learning_rate": 0.0017183493500977276,
|
| 942 |
+
"loss": 0.62,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.003641392346126851,
|
| 947 |
+
"grad_norm": 0.14222201704978943,
|
| 948 |
+
"learning_rate": 0.0017138743078398632,
|
| 949 |
+
"loss": 0.7501,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.003669189234265224,
|
| 954 |
+
"grad_norm": 0.11895573884248734,
|
| 955 |
+
"learning_rate": 0.0017093699210052578,
|
| 956 |
+
"loss": 0.7722,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.003696986122403597,
|
| 961 |
+
"grad_norm": 0.18408416211605072,
|
| 962 |
+
"learning_rate": 0.0017048363747516118,
|
| 963 |
+
"loss": 0.8163,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.00372478301054197,
|
| 968 |
+
"grad_norm": 0.13170836865901947,
|
| 969 |
+
"learning_rate": 0.001700273855435255,
|
| 970 |
+
"loss": 0.7529,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.0037525798986803426,
|
| 975 |
+
"grad_norm": 0.2225480079650879,
|
| 976 |
+
"learning_rate": 0.0016956825506034864,
|
| 977 |
+
"loss": 0.7412,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.0037803767868187154,
|
| 982 |
+
"grad_norm": 0.14438864588737488,
|
| 983 |
+
"learning_rate": 0.0016910626489868648,
|
| 984 |
+
"loss": 0.7257,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.0038081736749570887,
|
| 989 |
+
"grad_norm": 0.14967116713523865,
|
| 990 |
+
"learning_rate": 0.0016864143404914506,
|
| 991 |
+
"loss": 0.7663,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.0038359705630954615,
|
| 996 |
+
"grad_norm": 0.12598782777786255,
|
| 997 |
+
"learning_rate": 0.0016817378161909995,
|
| 998 |
+
"loss": 0.7768,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.0038637674512338343,
|
| 1003 |
+
"grad_norm": 0.1321249157190323,
|
| 1004 |
+
"learning_rate": 0.0016770332683191096,
|
| 1005 |
+
"loss": 0.5741,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.003891564339372207,
|
| 1010 |
+
"grad_norm": 0.1356271356344223,
|
| 1011 |
+
"learning_rate": 0.0016723008902613168,
|
| 1012 |
+
"loss": 0.628,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.00391936122751058,
|
| 1017 |
+
"grad_norm": 0.1559610813856125,
|
| 1018 |
+
"learning_rate": 0.0016675408765471481,
|
| 1019 |
+
"loss": 0.5979,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.003947158115648953,
|
| 1024 |
+
"grad_norm": 0.14019130170345306,
|
| 1025 |
+
"learning_rate": 0.001662753422842123,
|
| 1026 |
+
"loss": 0.6001,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.003974955003787326,
|
| 1031 |
+
"grad_norm": 0.3218002915382385,
|
| 1032 |
+
"learning_rate": 0.0016579387259397127,
|
| 1033 |
+
"loss": 0.6655,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.004002751891925699,
|
| 1038 |
+
"grad_norm": 0.14642581343650818,
|
| 1039 |
+
"learning_rate": 0.0016530969837532485,
|
| 1040 |
+
"loss": 0.6712,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.004030548780064072,
|
| 1045 |
+
"grad_norm": 0.30584490299224854,
|
| 1046 |
+
"learning_rate": 0.0016482283953077885,
|
| 1047 |
+
"loss": 0.7566,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.004058345668202444,
|
| 1052 |
+
"grad_norm": 0.17027173936367035,
|
| 1053 |
+
"learning_rate": 0.0016433331607319341,
|
| 1054 |
+
"loss": 0.7187,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.004086142556340817,
|
| 1059 |
+
"grad_norm": 0.22963419556617737,
|
| 1060 |
+
"learning_rate": 0.0016384114812496057,
|
| 1061 |
+
"loss": 0.732,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.004113939444479191,
|
| 1066 |
+
"grad_norm": 0.6273247599601746,
|
| 1067 |
+
"learning_rate": 0.0016334635591717702,
|
| 1068 |
+
"loss": 0.6352,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.004141736332617564,
|
| 1073 |
+
"grad_norm": 0.14807386696338654,
|
| 1074 |
+
"learning_rate": 0.0016284895978881237,
|
| 1075 |
+
"loss": 0.6705,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.0041695332207559365,
|
| 1080 |
+
"grad_norm": 0.19606240093708038,
|
| 1081 |
+
"learning_rate": 0.0016234898018587336,
|
| 1082 |
+
"loss": 0.7171,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.0041695332207559365,
|
| 1087 |
+
"eval_loss": 0.8552482724189758,
|
| 1088 |
+
"eval_runtime": 50.0085,
|
| 1089 |
+
"eval_samples_per_second": 11.538,
|
| 1090 |
+
"eval_steps_per_second": 5.779,
|
| 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": 9760677895864320.0,
|
| 1121 |
"train_batch_size": 2,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|