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 sha256:1358177e76c4b440f4b2a850ea72d85bc15dca5128a0f7ab0dd5eed189b75b16
|
| 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 sha256:4dd856a296a549422dedf8c90adebef2cd0901c74ed38e5e6976b73937ee3dc6
|
| 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 sha256:9918b7bcbbe1cf42dfa31a9c14f98aeb098d32eb3dd21aa5cc697d84c9b7d1ba
|
| 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:ae143a1b3a6f3911d7de6f885a33334066ae6c29ef03002bdce21e41331f97e8
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9860224723815918,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 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": 22.217,
|
| 732 |
"eval_steps_per_second": 5.61,
|
| 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": 0.9860224723815918,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 2.5531914893617023,
|
| 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": 22.217,
|
| 732 |
"eval_steps_per_second": 5.61,
|
| 733 |
"step": 100
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.7191489361702128,
|
| 737 |
+
"grad_norm": 1.557518720626831,
|
| 738 |
+
"learning_rate": 4.29689068767551e-05,
|
| 739 |
+
"loss": 0.4448,
|
| 740 |
+
"step": 101
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 1.7361702127659573,
|
| 744 |
+
"grad_norm": 1.330199122428894,
|
| 745 |
+
"learning_rate": 4.203895562844789e-05,
|
| 746 |
+
"loss": 0.6906,
|
| 747 |
+
"step": 102
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.753191489361702,
|
| 751 |
+
"grad_norm": 1.3650050163269043,
|
| 752 |
+
"learning_rate": 4.1111821621398446e-05,
|
| 753 |
+
"loss": 0.572,
|
| 754 |
+
"step": 103
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.7702127659574467,
|
| 758 |
+
"grad_norm": 1.286249041557312,
|
| 759 |
+
"learning_rate": 4.0187832948260705e-05,
|
| 760 |
+
"loss": 0.5293,
|
| 761 |
+
"step": 104
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.7872340425531914,
|
| 765 |
+
"grad_norm": 1.4000760316848755,
|
| 766 |
+
"learning_rate": 3.926731658862307e-05,
|
| 767 |
+
"loss": 0.5973,
|
| 768 |
+
"step": 105
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.804255319148936,
|
| 772 |
+
"grad_norm": 1.450547456741333,
|
| 773 |
+
"learning_rate": 3.835059829329735e-05,
|
| 774 |
+
"loss": 0.5751,
|
| 775 |
+
"step": 106
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 1.8212765957446808,
|
| 779 |
+
"grad_norm": 1.4450291395187378,
|
| 780 |
+
"learning_rate": 3.7438002469042565e-05,
|
| 781 |
+
"loss": 0.49,
|
| 782 |
+
"step": 107
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 1.8382978723404255,
|
| 786 |
+
"grad_norm": 1.4160994291305542,
|
| 787 |
+
"learning_rate": 3.6529852063764545e-05,
|
| 788 |
+
"loss": 0.5344,
|
| 789 |
+
"step": 108
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.8553191489361702,
|
| 793 |
+
"grad_norm": 1.4834502935409546,
|
| 794 |
+
"learning_rate": 3.562646845223153e-05,
|
| 795 |
+
"loss": 0.5433,
|
| 796 |
+
"step": 109
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.872340425531915,
|
| 800 |
+
"grad_norm": 1.3811678886413574,
|
| 801 |
+
"learning_rate": 3.4728171322346694e-05,
|
| 802 |
+
"loss": 0.4107,
|
| 803 |
+
"step": 110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.8893617021276596,
|
| 807 |
+
"grad_norm": 1.3840794563293457,
|
| 808 |
+
"learning_rate": 3.38352785620174e-05,
|
| 809 |
+
"loss": 0.4713,
|
| 810 |
+
"step": 111
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.9063829787234043,
|
| 814 |
+
"grad_norm": 1.5129518508911133,
|
| 815 |
+
"learning_rate": 3.29481061466617e-05,
|
| 816 |
+
"loss": 0.4653,
|
| 817 |
+
"step": 112
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.923404255319149,
|
| 821 |
+
"grad_norm": 1.569916009902954,
|
| 822 |
+
"learning_rate": 3.2066968027391374e-05,
|
| 823 |
+
"loss": 0.3947,
|
| 824 |
+
"step": 113
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.9404255319148938,
|
| 828 |
+
"grad_norm": 1.7366918325424194,
|
| 829 |
+
"learning_rate": 3.119217601991139e-05,
|
| 830 |
+
"loss": 0.3459,
|
| 831 |
+
"step": 114
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.9574468085106385,
|
| 835 |
+
"grad_norm": 1.6125799417495728,
|
| 836 |
+
"learning_rate": 3.0324039694175233e-05,
|
| 837 |
+
"loss": 0.3711,
|
| 838 |
+
"step": 115
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.974468085106383,
|
| 842 |
+
"grad_norm": 1.3394767045974731,
|
| 843 |
+
"learning_rate": 2.946286626483463e-05,
|
| 844 |
+
"loss": 0.6046,
|
| 845 |
+
"step": 116
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.9914893617021276,
|
| 849 |
+
"grad_norm": 1.6290675401687622,
|
| 850 |
+
"learning_rate": 2.8608960482523056e-05,
|
| 851 |
+
"loss": 0.5723,
|
| 852 |
+
"step": 117
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.008510638297872,
|
| 856 |
+
"grad_norm": 1.4972840547561646,
|
| 857 |
+
"learning_rate": 2.7762624526011038e-05,
|
| 858 |
+
"loss": 0.5839,
|
| 859 |
+
"step": 118
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.025531914893617,
|
| 863 |
+
"grad_norm": 0.92827969789505,
|
| 864 |
+
"learning_rate": 2.6924157895271563e-05,
|
| 865 |
+
"loss": 0.414,
|
| 866 |
+
"step": 119
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.0425531914893615,
|
| 870 |
+
"grad_norm": 0.9881418943405151,
|
| 871 |
+
"learning_rate": 2.6093857305493664e-05,
|
| 872 |
+
"loss": 0.338,
|
| 873 |
+
"step": 120
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.0595744680851062,
|
| 877 |
+
"grad_norm": 1.0140328407287598,
|
| 878 |
+
"learning_rate": 2.5272016582081236e-05,
|
| 879 |
+
"loss": 0.3692,
|
| 880 |
+
"step": 121
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.076595744680851,
|
| 884 |
+
"grad_norm": 1.0715774297714233,
|
| 885 |
+
"learning_rate": 2.4458926556674615e-05,
|
| 886 |
+
"loss": 0.3516,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.0936170212765957,
|
| 891 |
+
"grad_norm": 0.9538404941558838,
|
| 892 |
+
"learning_rate": 2.3654874964231518e-05,
|
| 893 |
+
"loss": 0.2303,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.1106382978723404,
|
| 898 |
+
"grad_norm": 1.1230480670928955,
|
| 899 |
+
"learning_rate": 2.2860146341203937e-05,
|
| 900 |
+
"loss": 0.293,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.127659574468085,
|
| 905 |
+
"grad_norm": 1.1339483261108398,
|
| 906 |
+
"learning_rate": 2.207502192484685e-05,
|
| 907 |
+
"loss": 0.3407,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.1446808510638298,
|
| 912 |
+
"grad_norm": 1.0703402757644653,
|
| 913 |
+
"learning_rate": 2.1299779553694323e-05,
|
| 914 |
+
"loss": 0.2584,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.1617021276595745,
|
| 919 |
+
"grad_norm": 1.0961896181106567,
|
| 920 |
+
"learning_rate": 2.053469356923865e-05,
|
| 921 |
+
"loss": 0.2334,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.178723404255319,
|
| 926 |
+
"grad_norm": 1.2202945947647095,
|
| 927 |
+
"learning_rate": 1.978003471884665e-05,
|
| 928 |
+
"loss": 0.2705,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.195744680851064,
|
| 933 |
+
"grad_norm": 1.281968593597412,
|
| 934 |
+
"learning_rate": 1.9036070059948252e-05,
|
| 935 |
+
"loss": 0.2222,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.2127659574468086,
|
| 940 |
+
"grad_norm": 1.530350685119629,
|
| 941 |
+
"learning_rate": 1.8303062865530406e-05,
|
| 942 |
+
"loss": 0.1816,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.2297872340425533,
|
| 947 |
+
"grad_norm": 1.5826750993728638,
|
| 948 |
+
"learning_rate": 1.7581272530970667e-05,
|
| 949 |
+
"loss": 0.2032,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.246808510638298,
|
| 954 |
+
"grad_norm": 1.333558440208435,
|
| 955 |
+
"learning_rate": 1.6870954482242707e-05,
|
| 956 |
+
"loss": 0.4571,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.2638297872340427,
|
| 961 |
+
"grad_norm": 1.2566792964935303,
|
| 962 |
+
"learning_rate": 1.6172360085526565e-05,
|
| 963 |
+
"loss": 0.394,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.2808510638297874,
|
| 968 |
+
"grad_norm": 1.2111644744873047,
|
| 969 |
+
"learning_rate": 1.5485736558255697e-05,
|
| 970 |
+
"loss": 0.3292,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.297872340425532,
|
| 975 |
+
"grad_norm": 1.3459227085113525,
|
| 976 |
+
"learning_rate": 1.4811326881631937e-05,
|
| 977 |
+
"loss": 0.3263,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.3148936170212764,
|
| 982 |
+
"grad_norm": 1.3436534404754639,
|
| 983 |
+
"learning_rate": 1.4149369714639853e-05,
|
| 984 |
+
"loss": 0.3349,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.331914893617021,
|
| 989 |
+
"grad_norm": 1.4782233238220215,
|
| 990 |
+
"learning_rate": 1.3500099309590397e-05,
|
| 991 |
+
"loss": 0.3526,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.348936170212766,
|
| 996 |
+
"grad_norm": 1.3280771970748901,
|
| 997 |
+
"learning_rate": 1.2863745429224144e-05,
|
| 998 |
+
"loss": 0.2997,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.3659574468085105,
|
| 1003 |
+
"grad_norm": 1.3815573453903198,
|
| 1004 |
+
"learning_rate": 1.2240533265403198e-05,
|
| 1005 |
+
"loss": 0.2855,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.382978723404255,
|
| 1010 |
+
"grad_norm": 1.4903278350830078,
|
| 1011 |
+
"learning_rate": 1.1630683359420652e-05,
|
| 1012 |
+
"loss": 0.2904,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.4,
|
| 1017 |
+
"grad_norm": 1.3255101442337036,
|
| 1018 |
+
"learning_rate": 1.103441152395588e-05,
|
| 1019 |
+
"loss": 0.1762,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.4170212765957446,
|
| 1024 |
+
"grad_norm": 1.3879741430282593,
|
| 1025 |
+
"learning_rate": 1.0451928766702979e-05,
|
| 1026 |
+
"loss": 0.2153,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.4340425531914893,
|
| 1031 |
+
"grad_norm": 1.2487590312957764,
|
| 1032 |
+
"learning_rate": 9.883441215699823e-06,
|
| 1033 |
+
"loss": 0.1699,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.451063829787234,
|
| 1038 |
+
"grad_norm": 1.142252802848816,
|
| 1039 |
+
"learning_rate": 9.329150046383772e-06,
|
| 1040 |
+
"loss": 0.1227,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.4680851063829787,
|
| 1045 |
+
"grad_norm": 1.8175076246261597,
|
| 1046 |
+
"learning_rate": 8.789251410400023e-06,
|
| 1047 |
+
"loss": 0.1298,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.4851063829787234,
|
| 1052 |
+
"grad_norm": 1.2175217866897583,
|
| 1053 |
+
"learning_rate": 8.263936366187824e-06,
|
| 1054 |
+
"loss": 0.3301,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.502127659574468,
|
| 1059 |
+
"grad_norm": 1.314565896987915,
|
| 1060 |
+
"learning_rate": 7.753390811368971e-06,
|
| 1061 |
+
"loss": 0.3832,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.519148936170213,
|
| 1066 |
+
"grad_norm": 1.393023133277893,
|
| 1067 |
+
"learning_rate": 7.257795416962753e-06,
|
| 1068 |
+
"loss": 0.331,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.5361702127659576,
|
| 1073 |
+
"grad_norm": 1.4550484418869019,
|
| 1074 |
+
"learning_rate": 6.777325563450282e-06,
|
| 1075 |
+
"loss": 0.3105,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.5531914893617023,
|
| 1080 |
+
"grad_norm": 1.555659294128418,
|
| 1081 |
+
"learning_rate": 6.312151278711237e-06,
|
| 1082 |
+
"loss": 0.3881,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.5531914893617023,
|
| 1087 |
+
"eval_loss": 1.250982403755188,
|
| 1088 |
+
"eval_runtime": 4.4645,
|
| 1089 |
+
"eval_samples_per_second": 22.175,
|
| 1090 |
+
"eval_steps_per_second": 5.6,
|
| 1091 |
+
"step": 150
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
+
"early_stopping_patience_counter": 2
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
|
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 6.21552039100416e+16,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|