Uploaded checkpoint-1500
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +361 -3
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2836579040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d10c905060a8fb9799b74c25d481c34611c9de9b480817812d33857c534c228a
|
| 3 |
size 2836579040
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5673376169
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:977e579e2ef1ecdd4b4a2a07787051dc204b437a958f6bb3774f7b810fdf5fba
|
| 3 |
size 5673376169
|
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:ba1ab4afddc1b42e59e07ab68c21af6f77eaf33ebe920a8a196bc4d34ce85d64
|
| 3 |
size 14244
|
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 sha256:7b5ba5f4da1b25af3b36501cdb417cae3a94cdecabb4332617c829913a9d9c0a
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 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,
|
|
@@ -723,6 +723,364 @@
|
|
| 723 |
"eval_samples_per_second": 15.395,
|
| 724 |
"eval_steps_per_second": 15.395,
|
| 725 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 726 |
}
|
| 727 |
],
|
| 728 |
"logging_steps": 10,
|
|
@@ -730,7 +1088,7 @@
|
|
| 730 |
"num_input_tokens_seen": 0,
|
| 731 |
"num_train_epochs": 1,
|
| 732 |
"save_steps": 500,
|
| 733 |
-
"total_flos":
|
| 734 |
"train_batch_size": 1,
|
| 735 |
"trial_name": null,
|
| 736 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.075,
|
| 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,
|
|
|
|
| 723 |
"eval_samples_per_second": 15.395,
|
| 724 |
"eval_steps_per_second": 15.395,
|
| 725 |
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.05,
|
| 729 |
+
"grad_norm": 65.0,
|
| 730 |
+
"learning_rate": 7.260000000000001e-07,
|
| 731 |
+
"loss": 1.2767,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.05,
|
| 736 |
+
"grad_norm": 63.25,
|
| 737 |
+
"learning_rate": 7.186666666666667e-07,
|
| 738 |
+
"loss": 1.2266,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.05,
|
| 743 |
+
"grad_norm": 63.75,
|
| 744 |
+
"learning_rate": 7.113333333333333e-07,
|
| 745 |
+
"loss": 1.2458,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.05,
|
| 750 |
+
"grad_norm": 63.0,
|
| 751 |
+
"learning_rate": 7.040000000000001e-07,
|
| 752 |
+
"loss": 1.1768,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.05,
|
| 757 |
+
"grad_norm": 62.75,
|
| 758 |
+
"learning_rate": 6.966666666666666e-07,
|
| 759 |
+
"loss": 1.1844,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.05,
|
| 764 |
+
"grad_norm": 62.25,
|
| 765 |
+
"learning_rate": 6.893333333333334e-07,
|
| 766 |
+
"loss": 1.186,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.05,
|
| 771 |
+
"grad_norm": 62.75,
|
| 772 |
+
"learning_rate": 6.82e-07,
|
| 773 |
+
"loss": 1.1551,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.05,
|
| 778 |
+
"grad_norm": 60.25,
|
| 779 |
+
"learning_rate": 6.746666666666667e-07,
|
| 780 |
+
"loss": 1.1218,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.05,
|
| 785 |
+
"grad_norm": 61.25,
|
| 786 |
+
"learning_rate": 6.673333333333334e-07,
|
| 787 |
+
"loss": 1.0962,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.06,
|
| 792 |
+
"grad_norm": 60.5,
|
| 793 |
+
"learning_rate": 6.6e-07,
|
| 794 |
+
"loss": 1.1204,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.06,
|
| 799 |
+
"grad_norm": 58.25,
|
| 800 |
+
"learning_rate": 6.526666666666667e-07,
|
| 801 |
+
"loss": 1.0833,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.06,
|
| 806 |
+
"grad_norm": 57.25,
|
| 807 |
+
"learning_rate": 6.453333333333334e-07,
|
| 808 |
+
"loss": 1.0743,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.06,
|
| 813 |
+
"grad_norm": 60.25,
|
| 814 |
+
"learning_rate": 6.38e-07,
|
| 815 |
+
"loss": 1.0764,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.06,
|
| 820 |
+
"grad_norm": 56.0,
|
| 821 |
+
"learning_rate": 6.306666666666668e-07,
|
| 822 |
+
"loss": 1.0315,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.06,
|
| 827 |
+
"grad_norm": 59.25,
|
| 828 |
+
"learning_rate": 6.233333333333333e-07,
|
| 829 |
+
"loss": 1.0791,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.06,
|
| 834 |
+
"grad_norm": 60.0,
|
| 835 |
+
"learning_rate": 6.160000000000001e-07,
|
| 836 |
+
"loss": 1.0443,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.06,
|
| 841 |
+
"grad_norm": 60.75,
|
| 842 |
+
"learning_rate": 6.086666666666667e-07,
|
| 843 |
+
"loss": 1.0472,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.06,
|
| 848 |
+
"grad_norm": 59.75,
|
| 849 |
+
"learning_rate": 6.013333333333334e-07,
|
| 850 |
+
"loss": 1.0422,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.06,
|
| 855 |
+
"grad_norm": 58.5,
|
| 856 |
+
"learning_rate": 5.94e-07,
|
| 857 |
+
"loss": 1.051,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.06,
|
| 862 |
+
"grad_norm": 57.25,
|
| 863 |
+
"learning_rate": 5.866666666666667e-07,
|
| 864 |
+
"loss": 1.0104,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.06,
|
| 869 |
+
"grad_norm": 58.5,
|
| 870 |
+
"learning_rate": 5.793333333333333e-07,
|
| 871 |
+
"loss": 1.0429,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.06,
|
| 876 |
+
"grad_norm": 60.25,
|
| 877 |
+
"learning_rate": 5.720000000000001e-07,
|
| 878 |
+
"loss": 1.0135,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.06,
|
| 883 |
+
"grad_norm": 58.0,
|
| 884 |
+
"learning_rate": 5.646666666666667e-07,
|
| 885 |
+
"loss": 1.0441,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.06,
|
| 890 |
+
"grad_norm": 57.25,
|
| 891 |
+
"learning_rate": 5.573333333333335e-07,
|
| 892 |
+
"loss": 1.0202,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.06,
|
| 897 |
+
"grad_norm": 54.5,
|
| 898 |
+
"learning_rate": 5.5e-07,
|
| 899 |
+
"loss": 0.9915,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.06,
|
| 904 |
+
"grad_norm": 56.75,
|
| 905 |
+
"learning_rate": 5.426666666666667e-07,
|
| 906 |
+
"loss": 1.0085,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.06,
|
| 911 |
+
"grad_norm": 58.75,
|
| 912 |
+
"learning_rate": 5.353333333333334e-07,
|
| 913 |
+
"loss": 1.0114,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.06,
|
| 918 |
+
"grad_norm": 56.0,
|
| 919 |
+
"learning_rate": 5.28e-07,
|
| 920 |
+
"loss": 1.0092,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.06,
|
| 925 |
+
"grad_norm": 54.25,
|
| 926 |
+
"learning_rate": 5.206666666666666e-07,
|
| 927 |
+
"loss": 0.9634,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.07,
|
| 932 |
+
"grad_norm": 54.0,
|
| 933 |
+
"learning_rate": 5.133333333333333e-07,
|
| 934 |
+
"loss": 0.9588,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.07,
|
| 939 |
+
"grad_norm": 56.5,
|
| 940 |
+
"learning_rate": 5.06e-07,
|
| 941 |
+
"loss": 0.9885,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.07,
|
| 946 |
+
"grad_norm": 55.75,
|
| 947 |
+
"learning_rate": 4.986666666666667e-07,
|
| 948 |
+
"loss": 1.024,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.07,
|
| 953 |
+
"grad_norm": 54.5,
|
| 954 |
+
"learning_rate": 4.913333333333334e-07,
|
| 955 |
+
"loss": 0.9812,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.07,
|
| 960 |
+
"grad_norm": 55.5,
|
| 961 |
+
"learning_rate": 4.84e-07,
|
| 962 |
+
"loss": 0.9859,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.07,
|
| 967 |
+
"grad_norm": 57.5,
|
| 968 |
+
"learning_rate": 4.766666666666667e-07,
|
| 969 |
+
"loss": 0.9629,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.07,
|
| 974 |
+
"grad_norm": 54.25,
|
| 975 |
+
"learning_rate": 4.693333333333334e-07,
|
| 976 |
+
"loss": 0.9386,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.07,
|
| 981 |
+
"grad_norm": 54.75,
|
| 982 |
+
"learning_rate": 4.62e-07,
|
| 983 |
+
"loss": 1.0033,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.07,
|
| 988 |
+
"grad_norm": 56.5,
|
| 989 |
+
"learning_rate": 4.5466666666666666e-07,
|
| 990 |
+
"loss": 0.9642,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.07,
|
| 995 |
+
"grad_norm": 53.5,
|
| 996 |
+
"learning_rate": 4.4733333333333334e-07,
|
| 997 |
+
"loss": 0.9745,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.07,
|
| 1002 |
+
"grad_norm": 54.75,
|
| 1003 |
+
"learning_rate": 4.4e-07,
|
| 1004 |
+
"loss": 0.9625,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.07,
|
| 1009 |
+
"grad_norm": 56.25,
|
| 1010 |
+
"learning_rate": 4.3266666666666665e-07,
|
| 1011 |
+
"loss": 0.9617,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.07,
|
| 1016 |
+
"grad_norm": 56.5,
|
| 1017 |
+
"learning_rate": 4.2533333333333333e-07,
|
| 1018 |
+
"loss": 0.9724,
|
| 1019 |
+
"step": 1420
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.07,
|
| 1023 |
+
"grad_norm": 54.5,
|
| 1024 |
+
"learning_rate": 4.18e-07,
|
| 1025 |
+
"loss": 0.9962,
|
| 1026 |
+
"step": 1430
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.07,
|
| 1030 |
+
"grad_norm": 53.0,
|
| 1031 |
+
"learning_rate": 4.106666666666667e-07,
|
| 1032 |
+
"loss": 0.9469,
|
| 1033 |
+
"step": 1440
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.07,
|
| 1037 |
+
"grad_norm": 54.75,
|
| 1038 |
+
"learning_rate": 4.033333333333333e-07,
|
| 1039 |
+
"loss": 0.9777,
|
| 1040 |
+
"step": 1450
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.07,
|
| 1044 |
+
"grad_norm": 57.0,
|
| 1045 |
+
"learning_rate": 3.96e-07,
|
| 1046 |
+
"loss": 0.9498,
|
| 1047 |
+
"step": 1460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.07,
|
| 1051 |
+
"grad_norm": 57.0,
|
| 1052 |
+
"learning_rate": 3.886666666666667e-07,
|
| 1053 |
+
"loss": 0.9229,
|
| 1054 |
+
"step": 1470
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.07,
|
| 1058 |
+
"grad_norm": 57.5,
|
| 1059 |
+
"learning_rate": 3.8133333333333336e-07,
|
| 1060 |
+
"loss": 0.9686,
|
| 1061 |
+
"step": 1480
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.07,
|
| 1065 |
+
"grad_norm": 59.0,
|
| 1066 |
+
"learning_rate": 3.7400000000000004e-07,
|
| 1067 |
+
"loss": 0.9718,
|
| 1068 |
+
"step": 1490
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.07,
|
| 1072 |
+
"grad_norm": 55.0,
|
| 1073 |
+
"learning_rate": 3.6666666666666667e-07,
|
| 1074 |
+
"loss": 0.9614,
|
| 1075 |
+
"step": 1500
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.07,
|
| 1079 |
+
"eval_loss": 0.9728732705116272,
|
| 1080 |
+
"eval_runtime": 65.1341,
|
| 1081 |
+
"eval_samples_per_second": 15.353,
|
| 1082 |
+
"eval_steps_per_second": 15.353,
|
| 1083 |
+
"step": 1500
|
| 1084 |
}
|
| 1085 |
],
|
| 1086 |
"logging_steps": 10,
|
|
|
|
| 1088 |
"num_input_tokens_seen": 0,
|
| 1089 |
"num_train_epochs": 1,
|
| 1090 |
"save_steps": 500,
|
| 1091 |
+
"total_flos": 2.420883062784e+16,
|
| 1092 |
"train_batch_size": 1,
|
| 1093 |
"trial_name": null,
|
| 1094 |
"trial_params": null
|