Training in progress, step 1500, 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 17640136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1d745e1470e2478eeac78c1daad21bcaaa5a0f1cd66753654e3fd3cbb7ac0c
|
| 3 |
size 17640136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9569204
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9b715fe8ca28dd1529770f10661d1ab6a66f0914225a9ca4eb2a32f2afc40da
|
| 3 |
size 9569204
|
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 sha256:7cb799e31c4734a3babdce88d357027975199ebadaf63de7bd5e95da9f225abe
|
| 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:e7592e941fa77449d9f7015724b6a3901e596c11e155596880b96def1f284283
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 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": 111.262,
|
| 732 |
"eval_steps_per_second": 13.949,
|
| 733 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 10,
|
|
@@ -754,12 +1112,12 @@
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
-
"should_training_stop":
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
-
"total_flos":
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.912510871887207,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-1500",
|
| 4 |
+
"epoch": 2.974714923153198,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 731 |
"eval_samples_per_second": 111.262,
|
| 732 |
"eval_steps_per_second": 13.949,
|
| 733 |
"step": 1000
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.002974714923153,
|
| 737 |
+
"grad_norm": 1.951005458831787,
|
| 738 |
+
"learning_rate": 1.3650237506511331e-05,
|
| 739 |
+
"loss": 2.0722,
|
| 740 |
+
"step": 1010
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.0228061477441743,
|
| 744 |
+
"grad_norm": 2.1238858699798584,
|
| 745 |
+
"learning_rate": 1.3153283438175034e-05,
|
| 746 |
+
"loss": 1.9197,
|
| 747 |
+
"step": 1020
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.042637580565196,
|
| 751 |
+
"grad_norm": 2.276472806930542,
|
| 752 |
+
"learning_rate": 1.2662294548391328e-05,
|
| 753 |
+
"loss": 1.821,
|
| 754 |
+
"step": 1030
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.062469013386217,
|
| 758 |
+
"grad_norm": 2.2130186557769775,
|
| 759 |
+
"learning_rate": 1.217751806485235e-05,
|
| 760 |
+
"loss": 1.7696,
|
| 761 |
+
"step": 1040
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.0823004462072383,
|
| 765 |
+
"grad_norm": 2.357255697250366,
|
| 766 |
+
"learning_rate": 1.1699198087116589e-05,
|
| 767 |
+
"loss": 1.7598,
|
| 768 |
+
"step": 1050
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.10213187902826,
|
| 772 |
+
"grad_norm": 2.2836225032806396,
|
| 773 |
+
"learning_rate": 1.122757546369744e-05,
|
| 774 |
+
"loss": 1.86,
|
| 775 |
+
"step": 1060
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.121963311849281,
|
| 779 |
+
"grad_norm": 2.353320360183716,
|
| 780 |
+
"learning_rate": 1.0762887670788702e-05,
|
| 781 |
+
"loss": 1.9035,
|
| 782 |
+
"step": 1070
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.1417947446703023,
|
| 786 |
+
"grad_norm": 2.4364101886749268,
|
| 787 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 788 |
+
"loss": 1.8113,
|
| 789 |
+
"step": 1080
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.161626177491324,
|
| 793 |
+
"grad_norm": 2.3972055912017822,
|
| 794 |
+
"learning_rate": 9.855248903979506e-06,
|
| 795 |
+
"loss": 1.8321,
|
| 796 |
+
"step": 1090
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.181457610312345,
|
| 800 |
+
"grad_norm": 2.507815361022949,
|
| 801 |
+
"learning_rate": 9.412754953531663e-06,
|
| 802 |
+
"loss": 1.8111,
|
| 803 |
+
"step": 1100
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.2012890431333663,
|
| 807 |
+
"grad_norm": 2.316178798675537,
|
| 808 |
+
"learning_rate": 8.978109650374397e-06,
|
| 809 |
+
"loss": 1.8562,
|
| 810 |
+
"step": 1110
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.221120475954388,
|
| 814 |
+
"grad_norm": 2.203108072280884,
|
| 815 |
+
"learning_rate": 8.551531851507186e-06,
|
| 816 |
+
"loss": 1.8583,
|
| 817 |
+
"step": 1120
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.240951908775409,
|
| 821 |
+
"grad_norm": 2.2089028358459473,
|
| 822 |
+
"learning_rate": 8.133236351698143e-06,
|
| 823 |
+
"loss": 1.8267,
|
| 824 |
+
"step": 1130
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.2607833415964302,
|
| 828 |
+
"grad_norm": 2.44580078125,
|
| 829 |
+
"learning_rate": 7.723433775328384e-06,
|
| 830 |
+
"loss": 1.8068,
|
| 831 |
+
"step": 1140
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.280614774417452,
|
| 835 |
+
"grad_norm": 2.599571704864502,
|
| 836 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 837 |
+
"loss": 1.7766,
|
| 838 |
+
"step": 1150
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.300446207238473,
|
| 842 |
+
"grad_norm": 2.3738250732421875,
|
| 843 |
+
"learning_rate": 6.930128404315214e-06,
|
| 844 |
+
"loss": 1.8871,
|
| 845 |
+
"step": 1160
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.320277640059494,
|
| 849 |
+
"grad_norm": 2.333874464035034,
|
| 850 |
+
"learning_rate": 6.547025062816486e-06,
|
| 851 |
+
"loss": 1.92,
|
| 852 |
+
"step": 1170
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.340109072880516,
|
| 856 |
+
"grad_norm": 2.1480438709259033,
|
| 857 |
+
"learning_rate": 6.173213349909729e-06,
|
| 858 |
+
"loss": 1.8136,
|
| 859 |
+
"step": 1180
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.359940505701537,
|
| 863 |
+
"grad_norm": 2.427140712738037,
|
| 864 |
+
"learning_rate": 5.808881491049723e-06,
|
| 865 |
+
"loss": 1.8065,
|
| 866 |
+
"step": 1190
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.379771938522558,
|
| 870 |
+
"grad_norm": 2.4610073566436768,
|
| 871 |
+
"learning_rate": 5.454212938299255e-06,
|
| 872 |
+
"loss": 1.7591,
|
| 873 |
+
"step": 1200
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.39960337134358,
|
| 877 |
+
"grad_norm": 2.216703414916992,
|
| 878 |
+
"learning_rate": 5.1093862779554776e-06,
|
| 879 |
+
"loss": 1.8598,
|
| 880 |
+
"step": 1210
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.419434804164601,
|
| 884 |
+
"grad_norm": 2.3740642070770264,
|
| 885 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 886 |
+
"loss": 1.8862,
|
| 887 |
+
"step": 1220
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.439266236985622,
|
| 891 |
+
"grad_norm": 2.3093762397766113,
|
| 892 |
+
"learning_rate": 4.4499481138022544e-06,
|
| 893 |
+
"loss": 1.7849,
|
| 894 |
+
"step": 1230
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 2.4590976698066433,
|
| 898 |
+
"grad_norm": 2.1922109127044678,
|
| 899 |
+
"learning_rate": 4.135668656967434e-06,
|
| 900 |
+
"loss": 1.7927,
|
| 901 |
+
"step": 1240
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.478929102627665,
|
| 905 |
+
"grad_norm": 2.590203285217285,
|
| 906 |
+
"learning_rate": 3.831895019292897e-06,
|
| 907 |
+
"loss": 1.7823,
|
| 908 |
+
"step": 1250
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.498760535448686,
|
| 912 |
+
"grad_norm": 2.2534220218658447,
|
| 913 |
+
"learning_rate": 3.5387801599533475e-06,
|
| 914 |
+
"loss": 1.8593,
|
| 915 |
+
"step": 1260
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.5185919682697073,
|
| 919 |
+
"grad_norm": 2.1965160369873047,
|
| 920 |
+
"learning_rate": 3.2564716711076167e-06,
|
| 921 |
+
"loss": 1.907,
|
| 922 |
+
"step": 1270
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.538423401090729,
|
| 926 |
+
"grad_norm": 2.5746281147003174,
|
| 927 |
+
"learning_rate": 2.98511170358155e-06,
|
| 928 |
+
"loss": 1.847,
|
| 929 |
+
"step": 1280
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.55825483391175,
|
| 933 |
+
"grad_norm": 2.418743848800659,
|
| 934 |
+
"learning_rate": 2.7248368952908053e-06,
|
| 935 |
+
"loss": 1.8251,
|
| 936 |
+
"step": 1290
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.5780862667327713,
|
| 940 |
+
"grad_norm": 2.610675811767578,
|
| 941 |
+
"learning_rate": 2.475778302439524e-06,
|
| 942 |
+
"loss": 1.7565,
|
| 943 |
+
"step": 1300
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 2.597917699553793,
|
| 947 |
+
"grad_norm": 2.1836891174316406,
|
| 948 |
+
"learning_rate": 2.2380613335296036e-06,
|
| 949 |
+
"loss": 1.782,
|
| 950 |
+
"step": 1310
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 2.617749132374814,
|
| 954 |
+
"grad_norm": 2.2063148021698,
|
| 955 |
+
"learning_rate": 2.0118056862137357e-06,
|
| 956 |
+
"loss": 1.9189,
|
| 957 |
+
"step": 1320
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.6375805651958353,
|
| 961 |
+
"grad_norm": 2.474757671356201,
|
| 962 |
+
"learning_rate": 1.7971252870240291e-06,
|
| 963 |
+
"loss": 1.8296,
|
| 964 |
+
"step": 1330
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 2.6574119980168565,
|
| 968 |
+
"grad_norm": 2.3700928688049316,
|
| 969 |
+
"learning_rate": 1.59412823400657e-06,
|
| 970 |
+
"loss": 1.763,
|
| 971 |
+
"step": 1340
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 2.677243430837878,
|
| 975 |
+
"grad_norm": 2.784795045852661,
|
| 976 |
+
"learning_rate": 1.4029167422908107e-06,
|
| 977 |
+
"loss": 1.8159,
|
| 978 |
+
"step": 1350
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.6970748636588993,
|
| 982 |
+
"grad_norm": 2.136866807937622,
|
| 983 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 984 |
+
"loss": 1.8127,
|
| 985 |
+
"step": 1360
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.7169062964799204,
|
| 989 |
+
"grad_norm": 2.424510955810547,
|
| 990 |
+
"learning_rate": 1.0562295828767387e-06,
|
| 991 |
+
"loss": 1.8843,
|
| 992 |
+
"step": 1370
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.736737729300942,
|
| 996 |
+
"grad_norm": 2.4899580478668213,
|
| 997 |
+
"learning_rate": 9.009284826036691e-07,
|
| 998 |
+
"loss": 1.7986,
|
| 999 |
+
"step": 1380
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.7565691621219632,
|
| 1003 |
+
"grad_norm": 2.4308602809906006,
|
| 1004 |
+
"learning_rate": 7.577619905828282e-07,
|
| 1005 |
+
"loss": 1.8162,
|
| 1006 |
+
"step": 1390
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.7764005949429844,
|
| 1010 |
+
"grad_norm": 2.5747532844543457,
|
| 1011 |
+
"learning_rate": 6.268021954544096e-07,
|
| 1012 |
+
"loss": 1.8488,
|
| 1013 |
+
"step": 1400
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.796232027764006,
|
| 1017 |
+
"grad_norm": 2.303532361984253,
|
| 1018 |
+
"learning_rate": 5.08115039419113e-07,
|
| 1019 |
+
"loss": 1.8323,
|
| 1020 |
+
"step": 1410
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.816063460585027,
|
| 1024 |
+
"grad_norm": 2.293966293334961,
|
| 1025 |
+
"learning_rate": 4.0176028503425835e-07,
|
| 1026 |
+
"loss": 1.9166,
|
| 1027 |
+
"step": 1420
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.8358948934060484,
|
| 1031 |
+
"grad_norm": 2.373138427734375,
|
| 1032 |
+
"learning_rate": 3.077914851215585e-07,
|
| 1033 |
+
"loss": 1.8516,
|
| 1034 |
+
"step": 1430
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.85572632622707,
|
| 1038 |
+
"grad_norm": 2.452150821685791,
|
| 1039 |
+
"learning_rate": 2.262559558016325e-07,
|
| 1040 |
+
"loss": 1.7722,
|
| 1041 |
+
"step": 1440
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.875557759048091,
|
| 1045 |
+
"grad_norm": 2.579303026199341,
|
| 1046 |
+
"learning_rate": 1.571947526689349e-07,
|
| 1047 |
+
"loss": 1.8125,
|
| 1048 |
+
"step": 1450
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 2.8953891918691124,
|
| 1052 |
+
"grad_norm": 2.2292511463165283,
|
| 1053 |
+
"learning_rate": 1.006426501190233e-07,
|
| 1054 |
+
"loss": 1.8276,
|
| 1055 |
+
"step": 1460
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.915220624690134,
|
| 1059 |
+
"grad_norm": 2.461202383041382,
|
| 1060 |
+
"learning_rate": 5.662812383859795e-08,
|
| 1061 |
+
"loss": 1.8983,
|
| 1062 |
+
"step": 1470
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 2.935052057511155,
|
| 1066 |
+
"grad_norm": 2.453644275665283,
|
| 1067 |
+
"learning_rate": 2.5173336467135267e-08,
|
| 1068 |
+
"loss": 1.8189,
|
| 1069 |
+
"step": 1480
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 2.9548834903321763,
|
| 1073 |
+
"grad_norm": 2.368211507797241,
|
| 1074 |
+
"learning_rate": 6.294126437336734e-09,
|
| 1075 |
+
"loss": 1.7719,
|
| 1076 |
+
"step": 1490
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.974714923153198,
|
| 1080 |
+
"grad_norm": 2.756178379058838,
|
| 1081 |
+
"learning_rate": 0.0,
|
| 1082 |
+
"loss": 1.7639,
|
| 1083 |
+
"step": 1500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.974714923153198,
|
| 1087 |
+
"eval_loss": 1.912510871887207,
|
| 1088 |
+
"eval_runtime": 15.3384,
|
| 1089 |
+
"eval_samples_per_second": 110.768,
|
| 1090 |
+
"eval_steps_per_second": 13.887,
|
| 1091 |
+
"step": 1500
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 10,
|
|
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
+
"should_training_stop": true
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
+
"total_flos": 1.0683911870270669e+17,
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|