Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 410636248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91c7a1763ef70813211a3e126e99ed02a4d68911db407a86f3c01451154abfd9
|
| 3 |
size 410636248
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 821393658
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e58bcb928dd8bb1203c8e8f7525d51a0322d66d5e46c62c33a51265957ea734
|
| 3 |
size 821393658
|
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:cdcef4615c497648044a6d80895c3d46b1c5f7a9c132beb33350b027c8cf3c17
|
| 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 sha256:66e6f95527be7d742c182b1b25b1632bf2465fc58ebbe4ae2f736399e0d31f82
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2427118569612503,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-340",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 20,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -807,6 +807,406 @@
|
|
| 807 |
"eval_samples_per_second": 36.847,
|
| 808 |
"eval_steps_per_second": 9.328,
|
| 809 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 810 |
}
|
| 811 |
],
|
| 812 |
"logging_steps": 20,
|
|
@@ -826,7 +1226,7 @@
|
|
| 826 |
"attributes": {}
|
| 827 |
}
|
| 828 |
},
|
| 829 |
-
"total_flos":
|
| 830 |
"train_batch_size": 4,
|
| 831 |
"trial_name": null,
|
| 832 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2427118569612503,
|
| 3 |
"best_model_checkpoint": "./results/checkpoint-340",
|
| 4 |
+
"epoch": 4.2979942693409745,
|
| 5 |
"eval_steps": 20,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 807 |
"eval_samples_per_second": 36.847,
|
| 808 |
"eval_steps_per_second": 9.328,
|
| 809 |
"step": 1000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.9226361031518624,
|
| 813 |
+
"grad_norm": 0.0065177069045603275,
|
| 814 |
+
"learning_rate": 8.30945558739255e-06,
|
| 815 |
+
"loss": 0.0006,
|
| 816 |
+
"step": 1020
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.9226361031518624,
|
| 820 |
+
"eval_accuracy": 0.9240506329113924,
|
| 821 |
+
"eval_loss": 0.38359534740448,
|
| 822 |
+
"eval_runtime": 4.251,
|
| 823 |
+
"eval_samples_per_second": 37.167,
|
| 824 |
+
"eval_steps_per_second": 9.409,
|
| 825 |
+
"step": 1020
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.9799426934097424,
|
| 829 |
+
"grad_norm": 0.008996536955237389,
|
| 830 |
+
"learning_rate": 8.080229226361033e-06,
|
| 831 |
+
"loss": 0.0062,
|
| 832 |
+
"step": 1040
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.9799426934097424,
|
| 836 |
+
"eval_accuracy": 0.9113924050632911,
|
| 837 |
+
"eval_loss": 0.40920865535736084,
|
| 838 |
+
"eval_runtime": 4.4231,
|
| 839 |
+
"eval_samples_per_second": 35.722,
|
| 840 |
+
"eval_steps_per_second": 9.043,
|
| 841 |
+
"step": 1040
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.037249283667622,
|
| 845 |
+
"grad_norm": 0.008578244596719742,
|
| 846 |
+
"learning_rate": 7.851002865329513e-06,
|
| 847 |
+
"loss": 0.0018,
|
| 848 |
+
"step": 1060
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.037249283667622,
|
| 852 |
+
"eval_accuracy": 0.9240506329113924,
|
| 853 |
+
"eval_loss": 0.4326882064342499,
|
| 854 |
+
"eval_runtime": 4.3644,
|
| 855 |
+
"eval_samples_per_second": 36.202,
|
| 856 |
+
"eval_steps_per_second": 9.165,
|
| 857 |
+
"step": 1060
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.0945558739255015,
|
| 861 |
+
"grad_norm": 0.029599307104945183,
|
| 862 |
+
"learning_rate": 7.6217765042979954e-06,
|
| 863 |
+
"loss": 0.0006,
|
| 864 |
+
"step": 1080
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.0945558739255015,
|
| 868 |
+
"eval_accuracy": 0.9177215189873418,
|
| 869 |
+
"eval_loss": 0.4501863420009613,
|
| 870 |
+
"eval_runtime": 4.3033,
|
| 871 |
+
"eval_samples_per_second": 36.716,
|
| 872 |
+
"eval_steps_per_second": 9.295,
|
| 873 |
+
"step": 1080
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 3.151862464183381,
|
| 877 |
+
"grad_norm": 0.014250312000513077,
|
| 878 |
+
"learning_rate": 7.392550143266476e-06,
|
| 879 |
+
"loss": 0.1874,
|
| 880 |
+
"step": 1100
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 3.151862464183381,
|
| 884 |
+
"eval_accuracy": 0.9177215189873418,
|
| 885 |
+
"eval_loss": 0.4321536421775818,
|
| 886 |
+
"eval_runtime": 4.2681,
|
| 887 |
+
"eval_samples_per_second": 37.019,
|
| 888 |
+
"eval_steps_per_second": 9.372,
|
| 889 |
+
"step": 1100
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 3.2091690544412605,
|
| 893 |
+
"grad_norm": 0.026432504877448082,
|
| 894 |
+
"learning_rate": 7.163323782234957e-06,
|
| 895 |
+
"loss": 0.0676,
|
| 896 |
+
"step": 1120
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.2091690544412605,
|
| 900 |
+
"eval_accuracy": 0.9113924050632911,
|
| 901 |
+
"eval_loss": 0.4126332998275757,
|
| 902 |
+
"eval_runtime": 4.2309,
|
| 903 |
+
"eval_samples_per_second": 37.344,
|
| 904 |
+
"eval_steps_per_second": 9.454,
|
| 905 |
+
"step": 1120
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.2664756446991405,
|
| 909 |
+
"grad_norm": 0.01032521203160286,
|
| 910 |
+
"learning_rate": 6.934097421203439e-06,
|
| 911 |
+
"loss": 0.0199,
|
| 912 |
+
"step": 1140
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.2664756446991405,
|
| 916 |
+
"eval_accuracy": 0.9050632911392406,
|
| 917 |
+
"eval_loss": 0.41126754879951477,
|
| 918 |
+
"eval_runtime": 4.2627,
|
| 919 |
+
"eval_samples_per_second": 37.066,
|
| 920 |
+
"eval_steps_per_second": 9.384,
|
| 921 |
+
"step": 1140
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 3.32378223495702,
|
| 925 |
+
"grad_norm": 0.016674930229783058,
|
| 926 |
+
"learning_rate": 6.70487106017192e-06,
|
| 927 |
+
"loss": 0.0674,
|
| 928 |
+
"step": 1160
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.32378223495702,
|
| 932 |
+
"eval_accuracy": 0.9177215189873418,
|
| 933 |
+
"eval_loss": 0.4134314954280853,
|
| 934 |
+
"eval_runtime": 4.2734,
|
| 935 |
+
"eval_samples_per_second": 36.973,
|
| 936 |
+
"eval_steps_per_second": 9.36,
|
| 937 |
+
"step": 1160
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.3810888252148996,
|
| 941 |
+
"grad_norm": 0.0032745320349931717,
|
| 942 |
+
"learning_rate": 6.475644699140402e-06,
|
| 943 |
+
"loss": 0.0004,
|
| 944 |
+
"step": 1180
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.3810888252148996,
|
| 948 |
+
"eval_accuracy": 0.9177215189873418,
|
| 949 |
+
"eval_loss": 0.4212283790111542,
|
| 950 |
+
"eval_runtime": 4.2821,
|
| 951 |
+
"eval_samples_per_second": 36.898,
|
| 952 |
+
"eval_steps_per_second": 9.341,
|
| 953 |
+
"step": 1180
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.4383954154727796,
|
| 957 |
+
"grad_norm": 0.012243836186826229,
|
| 958 |
+
"learning_rate": 6.246418338108883e-06,
|
| 959 |
+
"loss": 0.0004,
|
| 960 |
+
"step": 1200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.4383954154727796,
|
| 964 |
+
"eval_accuracy": 0.9177215189873418,
|
| 965 |
+
"eval_loss": 0.42768773436546326,
|
| 966 |
+
"eval_runtime": 4.2965,
|
| 967 |
+
"eval_samples_per_second": 36.774,
|
| 968 |
+
"eval_steps_per_second": 9.31,
|
| 969 |
+
"step": 1200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 3.495702005730659,
|
| 973 |
+
"grad_norm": 0.09642524272203445,
|
| 974 |
+
"learning_rate": 6.017191977077364e-06,
|
| 975 |
+
"loss": 0.1097,
|
| 976 |
+
"step": 1220
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 3.495702005730659,
|
| 980 |
+
"eval_accuracy": 0.9177215189873418,
|
| 981 |
+
"eval_loss": 0.4246382415294647,
|
| 982 |
+
"eval_runtime": 4.2676,
|
| 983 |
+
"eval_samples_per_second": 37.023,
|
| 984 |
+
"eval_steps_per_second": 9.373,
|
| 985 |
+
"step": 1220
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.5530085959885387,
|
| 989 |
+
"grad_norm": 0.004081379622220993,
|
| 990 |
+
"learning_rate": 5.787965616045845e-06,
|
| 991 |
+
"loss": 0.0004,
|
| 992 |
+
"step": 1240
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.5530085959885387,
|
| 996 |
+
"eval_accuracy": 0.9177215189873418,
|
| 997 |
+
"eval_loss": 0.42067304253578186,
|
| 998 |
+
"eval_runtime": 4.2338,
|
| 999 |
+
"eval_samples_per_second": 37.319,
|
| 1000 |
+
"eval_steps_per_second": 9.448,
|
| 1001 |
+
"step": 1240
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.6103151862464182,
|
| 1005 |
+
"grad_norm": 0.013711544685065746,
|
| 1006 |
+
"learning_rate": 5.558739255014327e-06,
|
| 1007 |
+
"loss": 0.0152,
|
| 1008 |
+
"step": 1260
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.6103151862464182,
|
| 1012 |
+
"eval_accuracy": 0.9177215189873418,
|
| 1013 |
+
"eval_loss": 0.4250052869319916,
|
| 1014 |
+
"eval_runtime": 4.2297,
|
| 1015 |
+
"eval_samples_per_second": 37.355,
|
| 1016 |
+
"eval_steps_per_second": 9.457,
|
| 1017 |
+
"step": 1260
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.6676217765042978,
|
| 1021 |
+
"grad_norm": 148.3441619873047,
|
| 1022 |
+
"learning_rate": 5.3295128939828086e-06,
|
| 1023 |
+
"loss": 0.0146,
|
| 1024 |
+
"step": 1280
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 3.6676217765042978,
|
| 1028 |
+
"eval_accuracy": 0.9240506329113924,
|
| 1029 |
+
"eval_loss": 0.412005752325058,
|
| 1030 |
+
"eval_runtime": 4.2278,
|
| 1031 |
+
"eval_samples_per_second": 37.372,
|
| 1032 |
+
"eval_steps_per_second": 9.461,
|
| 1033 |
+
"step": 1280
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 3.7249283667621778,
|
| 1037 |
+
"grad_norm": 0.0035390935372561216,
|
| 1038 |
+
"learning_rate": 5.10028653295129e-06,
|
| 1039 |
+
"loss": 0.0377,
|
| 1040 |
+
"step": 1300
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.7249283667621778,
|
| 1044 |
+
"eval_accuracy": 0.930379746835443,
|
| 1045 |
+
"eval_loss": 0.40523138642311096,
|
| 1046 |
+
"eval_runtime": 4.2347,
|
| 1047 |
+
"eval_samples_per_second": 37.311,
|
| 1048 |
+
"eval_steps_per_second": 9.446,
|
| 1049 |
+
"step": 1300
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.7822349570200573,
|
| 1053 |
+
"grad_norm": 9.169730186462402,
|
| 1054 |
+
"learning_rate": 4.871060171919771e-06,
|
| 1055 |
+
"loss": 0.1061,
|
| 1056 |
+
"step": 1320
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.7822349570200573,
|
| 1060 |
+
"eval_accuracy": 0.9177215189873418,
|
| 1061 |
+
"eval_loss": 0.40109243988990784,
|
| 1062 |
+
"eval_runtime": 4.2624,
|
| 1063 |
+
"eval_samples_per_second": 37.069,
|
| 1064 |
+
"eval_steps_per_second": 9.384,
|
| 1065 |
+
"step": 1320
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 3.839541547277937,
|
| 1069 |
+
"grad_norm": 0.004674045369029045,
|
| 1070 |
+
"learning_rate": 4.641833810888253e-06,
|
| 1071 |
+
"loss": 0.1026,
|
| 1072 |
+
"step": 1340
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 3.839541547277937,
|
| 1076 |
+
"eval_accuracy": 0.9177215189873418,
|
| 1077 |
+
"eval_loss": 0.43842944502830505,
|
| 1078 |
+
"eval_runtime": 4.2684,
|
| 1079 |
+
"eval_samples_per_second": 37.016,
|
| 1080 |
+
"eval_steps_per_second": 9.371,
|
| 1081 |
+
"step": 1340
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 3.896848137535817,
|
| 1085 |
+
"grad_norm": 0.014885048381984234,
|
| 1086 |
+
"learning_rate": 4.412607449856734e-06,
|
| 1087 |
+
"loss": 0.1264,
|
| 1088 |
+
"step": 1360
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.896848137535817,
|
| 1092 |
+
"eval_accuracy": 0.9177215189873418,
|
| 1093 |
+
"eval_loss": 0.4101775884628296,
|
| 1094 |
+
"eval_runtime": 4.2709,
|
| 1095 |
+
"eval_samples_per_second": 36.995,
|
| 1096 |
+
"eval_steps_per_second": 9.366,
|
| 1097 |
+
"step": 1360
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.9541547277936964,
|
| 1101 |
+
"grad_norm": 0.00861190166324377,
|
| 1102 |
+
"learning_rate": 4.1833810888252155e-06,
|
| 1103 |
+
"loss": 0.0079,
|
| 1104 |
+
"step": 1380
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.9541547277936964,
|
| 1108 |
+
"eval_accuracy": 0.9240506329113924,
|
| 1109 |
+
"eval_loss": 0.40192869305610657,
|
| 1110 |
+
"eval_runtime": 4.2834,
|
| 1111 |
+
"eval_samples_per_second": 36.887,
|
| 1112 |
+
"eval_steps_per_second": 9.338,
|
| 1113 |
+
"step": 1380
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 4.011461318051576,
|
| 1117 |
+
"grad_norm": 0.0044676773250103,
|
| 1118 |
+
"learning_rate": 3.954154727793696e-06,
|
| 1119 |
+
"loss": 0.0249,
|
| 1120 |
+
"step": 1400
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 4.011461318051576,
|
| 1124 |
+
"eval_accuracy": 0.9177215189873418,
|
| 1125 |
+
"eval_loss": 0.3997720777988434,
|
| 1126 |
+
"eval_runtime": 4.2897,
|
| 1127 |
+
"eval_samples_per_second": 36.833,
|
| 1128 |
+
"eval_steps_per_second": 9.325,
|
| 1129 |
+
"step": 1400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 4.0687679083094554,
|
| 1133 |
+
"grad_norm": 0.1052209734916687,
|
| 1134 |
+
"learning_rate": 3.724928366762178e-06,
|
| 1135 |
+
"loss": 0.0115,
|
| 1136 |
+
"step": 1420
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.0687679083094554,
|
| 1140 |
+
"eval_accuracy": 0.9240506329113924,
|
| 1141 |
+
"eval_loss": 0.39488697052001953,
|
| 1142 |
+
"eval_runtime": 4.2996,
|
| 1143 |
+
"eval_samples_per_second": 36.748,
|
| 1144 |
+
"eval_steps_per_second": 9.303,
|
| 1145 |
+
"step": 1420
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 4.126074498567335,
|
| 1149 |
+
"grad_norm": 0.012624930590391159,
|
| 1150 |
+
"learning_rate": 3.4957020057306597e-06,
|
| 1151 |
+
"loss": 0.0004,
|
| 1152 |
+
"step": 1440
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 4.126074498567335,
|
| 1156 |
+
"eval_accuracy": 0.9240506329113924,
|
| 1157 |
+
"eval_loss": 0.39705362915992737,
|
| 1158 |
+
"eval_runtime": 4.2873,
|
| 1159 |
+
"eval_samples_per_second": 36.853,
|
| 1160 |
+
"eval_steps_per_second": 9.33,
|
| 1161 |
+
"step": 1440
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 4.1833810888252145,
|
| 1165 |
+
"grad_norm": 0.008006641641259193,
|
| 1166 |
+
"learning_rate": 3.2664756446991407e-06,
|
| 1167 |
+
"loss": 0.0847,
|
| 1168 |
+
"step": 1460
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 4.1833810888252145,
|
| 1172 |
+
"eval_accuracy": 0.930379746835443,
|
| 1173 |
+
"eval_loss": 0.3859291076660156,
|
| 1174 |
+
"eval_runtime": 4.3068,
|
| 1175 |
+
"eval_samples_per_second": 36.686,
|
| 1176 |
+
"eval_steps_per_second": 9.288,
|
| 1177 |
+
"step": 1460
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.240687679083095,
|
| 1181 |
+
"grad_norm": 0.022626299411058426,
|
| 1182 |
+
"learning_rate": 3.037249283667622e-06,
|
| 1183 |
+
"loss": 0.0004,
|
| 1184 |
+
"step": 1480
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.240687679083095,
|
| 1188 |
+
"eval_accuracy": 0.930379746835443,
|
| 1189 |
+
"eval_loss": 0.38549065589904785,
|
| 1190 |
+
"eval_runtime": 4.2744,
|
| 1191 |
+
"eval_samples_per_second": 36.964,
|
| 1192 |
+
"eval_steps_per_second": 9.358,
|
| 1193 |
+
"step": 1480
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.2979942693409745,
|
| 1197 |
+
"grad_norm": 0.00761532224714756,
|
| 1198 |
+
"learning_rate": 2.8080229226361035e-06,
|
| 1199 |
+
"loss": 0.002,
|
| 1200 |
+
"step": 1500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.2979942693409745,
|
| 1204 |
+
"eval_accuracy": 0.9367088607594937,
|
| 1205 |
+
"eval_loss": 0.3879244923591614,
|
| 1206 |
+
"eval_runtime": 4.2938,
|
| 1207 |
+
"eval_samples_per_second": 36.797,
|
| 1208 |
+
"eval_steps_per_second": 9.316,
|
| 1209 |
+
"step": 1500
|
| 1210 |
}
|
| 1211 |
],
|
| 1212 |
"logging_steps": 20,
|
|
|
|
| 1226 |
"attributes": {}
|
| 1227 |
}
|
| 1228 |
},
|
| 1229 |
+
"total_flos": 1358383281613980.0,
|
| 1230 |
"train_batch_size": 4,
|
| 1231 |
"trial_name": null,
|
| 1232 |
"trial_params": null
|