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 1001465824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7657ddee20f58260dcd66d8b7a33e96dc0556375180c23366de987f407a1e530
|
| 3 |
size 1001465824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 509176980
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32d23fc7a4a2a263398720bb781d0b9ddd8ec04e0447993eaea7ba314f5f8dcc
|
| 3 |
size 509176980
|
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 sha256:63afc1eec0187c47a9b6d2157cff59302f972f86bed97db3ce1f4b40e899b203
|
| 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:faf4b7c5498ae4c4e5a296fe320aca480fc4724dd9eaa1c7badb2de02f26fafb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2286633849143982,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 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": 2.005,
|
| 732 |
"eval_steps_per_second": 0.503,
|
| 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": 1.
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2286633849143982,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.21770682148040638,
|
| 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": 2.005,
|
| 732 |
"eval_steps_per_second": 0.503,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.14658925979680695,
|
| 737 |
+
"grad_norm": 0.13860496878623962,
|
| 738 |
+
"learning_rate": 5.2678421052631576e-05,
|
| 739 |
+
"loss": 0.7931,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.14804063860667635,
|
| 744 |
+
"grad_norm": 0.1530522257089615,
|
| 745 |
+
"learning_rate": 5.214631578947369e-05,
|
| 746 |
+
"loss": 0.4883,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.14949201741654572,
|
| 751 |
+
"grad_norm": 0.09421262890100479,
|
| 752 |
+
"learning_rate": 5.161421052631579e-05,
|
| 753 |
+
"loss": 0.1757,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.1509433962264151,
|
| 758 |
+
"grad_norm": 0.11253266036510468,
|
| 759 |
+
"learning_rate": 5.10821052631579e-05,
|
| 760 |
+
"loss": 0.4355,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.15239477503628446,
|
| 765 |
+
"grad_norm": 0.11226090788841248,
|
| 766 |
+
"learning_rate": 5.055e-05,
|
| 767 |
+
"loss": 0.3406,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.15384615384615385,
|
| 772 |
+
"grad_norm": 0.09969495981931686,
|
| 773 |
+
"learning_rate": 5.0017894736842104e-05,
|
| 774 |
+
"loss": 0.33,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.15529753265602322,
|
| 779 |
+
"grad_norm": 0.14994554221630096,
|
| 780 |
+
"learning_rate": 4.948578947368421e-05,
|
| 781 |
+
"loss": 0.7712,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.1567489114658926,
|
| 786 |
+
"grad_norm": 0.16747573018074036,
|
| 787 |
+
"learning_rate": 4.895368421052632e-05,
|
| 788 |
+
"loss": 0.4805,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.15820029027576196,
|
| 793 |
+
"grad_norm": 0.15101346373558044,
|
| 794 |
+
"learning_rate": 4.842157894736842e-05,
|
| 795 |
+
"loss": 0.6745,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.15965166908563136,
|
| 800 |
+
"grad_norm": 0.14325077831745148,
|
| 801 |
+
"learning_rate": 4.7889473684210523e-05,
|
| 802 |
+
"loss": 0.2481,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.16110304789550073,
|
| 807 |
+
"grad_norm": 0.6589614152908325,
|
| 808 |
+
"learning_rate": 4.735736842105263e-05,
|
| 809 |
+
"loss": 0.385,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.1625544267053701,
|
| 814 |
+
"grad_norm": 0.14817237854003906,
|
| 815 |
+
"learning_rate": 4.682526315789474e-05,
|
| 816 |
+
"loss": 0.4519,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.16400580551523947,
|
| 821 |
+
"grad_norm": 0.12075196951627731,
|
| 822 |
+
"learning_rate": 4.629315789473684e-05,
|
| 823 |
+
"loss": 0.32,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.16545718432510886,
|
| 828 |
+
"grad_norm": 0.10896284133195877,
|
| 829 |
+
"learning_rate": 4.576105263157895e-05,
|
| 830 |
+
"loss": 0.252,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.16690856313497823,
|
| 835 |
+
"grad_norm": 0.15797024965286255,
|
| 836 |
+
"learning_rate": 4.522894736842106e-05,
|
| 837 |
+
"loss": 0.7193,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.1683599419448476,
|
| 842 |
+
"grad_norm": 0.12811946868896484,
|
| 843 |
+
"learning_rate": 4.469684210526316e-05,
|
| 844 |
+
"loss": 0.5991,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.16981132075471697,
|
| 849 |
+
"grad_norm": 0.17125706374645233,
|
| 850 |
+
"learning_rate": 4.416473684210527e-05,
|
| 851 |
+
"loss": 0.6612,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.17126269956458637,
|
| 856 |
+
"grad_norm": 0.21033529937267303,
|
| 857 |
+
"learning_rate": 4.363263157894737e-05,
|
| 858 |
+
"loss": 0.637,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.17271407837445574,
|
| 863 |
+
"grad_norm": 0.14343442022800446,
|
| 864 |
+
"learning_rate": 4.310052631578948e-05,
|
| 865 |
+
"loss": 0.3919,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.1741654571843251,
|
| 870 |
+
"grad_norm": 0.09223167598247528,
|
| 871 |
+
"learning_rate": 4.256842105263158e-05,
|
| 872 |
+
"loss": 0.2206,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.17561683599419448,
|
| 877 |
+
"grad_norm": 0.10201866924762726,
|
| 878 |
+
"learning_rate": 4.203631578947369e-05,
|
| 879 |
+
"loss": 0.2657,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.17706821480406387,
|
| 884 |
+
"grad_norm": 0.09830533713102341,
|
| 885 |
+
"learning_rate": 4.150421052631579e-05,
|
| 886 |
+
"loss": 0.1767,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.17851959361393324,
|
| 891 |
+
"grad_norm": 0.11305135488510132,
|
| 892 |
+
"learning_rate": 4.09721052631579e-05,
|
| 893 |
+
"loss": 0.3528,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.1799709724238026,
|
| 898 |
+
"grad_norm": 0.11795450747013092,
|
| 899 |
+
"learning_rate": 4.0440000000000006e-05,
|
| 900 |
+
"loss": 0.2826,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.18142235123367198,
|
| 905 |
+
"grad_norm": 0.10810278356075287,
|
| 906 |
+
"learning_rate": 3.990789473684211e-05,
|
| 907 |
+
"loss": 0.3728,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.18287373004354138,
|
| 912 |
+
"grad_norm": 0.07889194041490555,
|
| 913 |
+
"learning_rate": 3.937578947368421e-05,
|
| 914 |
+
"loss": 0.1485,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.18432510885341075,
|
| 919 |
+
"grad_norm": 0.12167462706565857,
|
| 920 |
+
"learning_rate": 3.884368421052632e-05,
|
| 921 |
+
"loss": 0.3191,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.18577648766328012,
|
| 926 |
+
"grad_norm": 0.13652844727039337,
|
| 927 |
+
"learning_rate": 3.8311578947368426e-05,
|
| 928 |
+
"loss": 0.3272,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.18722786647314948,
|
| 933 |
+
"grad_norm": 0.11355964839458466,
|
| 934 |
+
"learning_rate": 3.777947368421053e-05,
|
| 935 |
+
"loss": 0.2216,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.18867924528301888,
|
| 940 |
+
"grad_norm": 0.12072530388832092,
|
| 941 |
+
"learning_rate": 3.724736842105263e-05,
|
| 942 |
+
"loss": 0.2511,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.19013062409288825,
|
| 947 |
+
"grad_norm": 0.11075890809297562,
|
| 948 |
+
"learning_rate": 3.6715263157894744e-05,
|
| 949 |
+
"loss": 0.1769,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.19158200290275762,
|
| 954 |
+
"grad_norm": 0.09322332590818405,
|
| 955 |
+
"learning_rate": 3.6183157894736845e-05,
|
| 956 |
+
"loss": 0.2052,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.193033381712627,
|
| 961 |
+
"grad_norm": 0.12875616550445557,
|
| 962 |
+
"learning_rate": 3.565105263157895e-05,
|
| 963 |
+
"loss": 0.1961,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.19448476052249636,
|
| 968 |
+
"grad_norm": 0.11314037442207336,
|
| 969 |
+
"learning_rate": 3.5118947368421055e-05,
|
| 970 |
+
"loss": 0.2227,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.19593613933236576,
|
| 975 |
+
"grad_norm": 0.10332886129617691,
|
| 976 |
+
"learning_rate": 3.458684210526316e-05,
|
| 977 |
+
"loss": 0.339,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.19738751814223512,
|
| 982 |
+
"grad_norm": 0.17729254066944122,
|
| 983 |
+
"learning_rate": 3.4054736842105265e-05,
|
| 984 |
+
"loss": 0.2802,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.1988388969521045,
|
| 989 |
+
"grad_norm": 0.08777690678834915,
|
| 990 |
+
"learning_rate": 3.3522631578947366e-05,
|
| 991 |
+
"loss": 0.1391,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.20029027576197386,
|
| 996 |
+
"grad_norm": 0.1536087989807129,
|
| 997 |
+
"learning_rate": 3.2990526315789475e-05,
|
| 998 |
+
"loss": 0.3643,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.20174165457184326,
|
| 1003 |
+
"grad_norm": 0.11051812022924423,
|
| 1004 |
+
"learning_rate": 3.245842105263158e-05,
|
| 1005 |
+
"loss": 0.1991,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.20319303338171263,
|
| 1010 |
+
"grad_norm": 0.09295262396335602,
|
| 1011 |
+
"learning_rate": 3.1926315789473685e-05,
|
| 1012 |
+
"loss": 0.2913,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.204644412191582,
|
| 1017 |
+
"grad_norm": 0.13505689799785614,
|
| 1018 |
+
"learning_rate": 3.139421052631579e-05,
|
| 1019 |
+
"loss": 0.8371,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.20609579100145137,
|
| 1024 |
+
"grad_norm": 0.1267169862985611,
|
| 1025 |
+
"learning_rate": 3.0862105263157894e-05,
|
| 1026 |
+
"loss": 0.6024,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.20754716981132076,
|
| 1031 |
+
"grad_norm": 0.13407814502716064,
|
| 1032 |
+
"learning_rate": 3.033e-05,
|
| 1033 |
+
"loss": 0.4159,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.20899854862119013,
|
| 1038 |
+
"grad_norm": 0.11469519138336182,
|
| 1039 |
+
"learning_rate": 2.9797894736842104e-05,
|
| 1040 |
+
"loss": 0.2402,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.2104499274310595,
|
| 1045 |
+
"grad_norm": 0.169059157371521,
|
| 1046 |
+
"learning_rate": 2.9265789473684213e-05,
|
| 1047 |
+
"loss": 0.3534,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.21190130624092887,
|
| 1052 |
+
"grad_norm": 0.19773763418197632,
|
| 1053 |
+
"learning_rate": 2.8733684210526317e-05,
|
| 1054 |
+
"loss": 0.5001,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.21335268505079827,
|
| 1059 |
+
"grad_norm": 0.4277418553829193,
|
| 1060 |
+
"learning_rate": 2.820157894736842e-05,
|
| 1061 |
+
"loss": 0.7581,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.21480406386066764,
|
| 1066 |
+
"grad_norm": 0.2791711688041687,
|
| 1067 |
+
"learning_rate": 2.766947368421053e-05,
|
| 1068 |
+
"loss": 0.8721,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.216255442670537,
|
| 1073 |
+
"grad_norm": 0.40901464223861694,
|
| 1074 |
+
"learning_rate": 2.7137368421052632e-05,
|
| 1075 |
+
"loss": 0.8766,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.21770682148040638,
|
| 1080 |
+
"grad_norm": 0.39813101291656494,
|
| 1081 |
+
"learning_rate": 2.6605263157894737e-05,
|
| 1082 |
+
"loss": 0.5074,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.21770682148040638,
|
| 1087 |
+
"eval_loss": 0.23037858307361603,
|
| 1088 |
+
"eval_runtime": 143.626,
|
| 1089 |
+
"eval_samples_per_second": 2.026,
|
| 1090 |
+
"eval_steps_per_second": 0.508,
|
| 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": 1.8064531192283136e+17,
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|