Training in progress, step 900, 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 847599616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3056236689e6539a7f5029a0a6c328ec2c43e3c3c4a9737c027e9ebac991afe
|
| 3 |
size 847599616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 350603
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7de93bb1b4b47c783b4b0770dc40d2957fc8c9c9d1a789eb3319228a1dfa0172
|
| 3 |
size 350603
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92bb814c2159433445a20867c1091b7d6c4f30624f2763a53f9b654f619c9806
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f6ce19dec5df2f65b77278038e9732495ad020f6cc108dc0ab539fb79eef904
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 150,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -884,6 +884,444 @@
|
|
| 884 |
"eval_samples_per_second": 9.588,
|
| 885 |
"eval_steps_per_second": 1.63,
|
| 886 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 887 |
}
|
| 888 |
],
|
| 889 |
"logging_steps": 5,
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.18,
|
| 6 |
"eval_steps": 150,
|
| 7 |
+
"global_step": 900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 884 |
"eval_samples_per_second": 9.588,
|
| 885 |
"eval_steps_per_second": 1.63,
|
| 886 |
"step": 600
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.121,
|
| 890 |
+
"grad_norm": 0.08994954824447632,
|
| 891 |
+
"learning_rate": 3.945432477970598e-06,
|
| 892 |
+
"loss": 6.806103515625,
|
| 893 |
+
"step": 605
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.122,
|
| 897 |
+
"grad_norm": 0.07370273023843765,
|
| 898 |
+
"learning_rate": 3.943887435873737e-06,
|
| 899 |
+
"loss": 6.822203063964844,
|
| 900 |
+
"step": 610
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.123,
|
| 904 |
+
"grad_norm": 0.07430048286914825,
|
| 905 |
+
"learning_rate": 3.942321135735316e-06,
|
| 906 |
+
"loss": 6.78031005859375,
|
| 907 |
+
"step": 615
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.124,
|
| 911 |
+
"grad_norm": 0.1099916398525238,
|
| 912 |
+
"learning_rate": 3.940733594684141e-06,
|
| 913 |
+
"loss": 6.9381248474121096,
|
| 914 |
+
"step": 620
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.125,
|
| 918 |
+
"grad_norm": 0.08312584459781647,
|
| 919 |
+
"learning_rate": 3.939124830081308e-06,
|
| 920 |
+
"loss": 6.797595977783203,
|
| 921 |
+
"step": 625
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.126,
|
| 925 |
+
"grad_norm": 0.06789983063936234,
|
| 926 |
+
"learning_rate": 3.937494859520009e-06,
|
| 927 |
+
"loss": 6.870149230957031,
|
| 928 |
+
"step": 630
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.127,
|
| 932 |
+
"grad_norm": 0.07728736847639084,
|
| 933 |
+
"learning_rate": 3.93584370082534e-06,
|
| 934 |
+
"loss": 6.83870849609375,
|
| 935 |
+
"step": 635
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.128,
|
| 939 |
+
"grad_norm": 0.0719357579946518,
|
| 940 |
+
"learning_rate": 3.934171372054108e-06,
|
| 941 |
+
"loss": 6.799946594238281,
|
| 942 |
+
"step": 640
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.129,
|
| 946 |
+
"grad_norm": 0.06783469766378403,
|
| 947 |
+
"learning_rate": 3.932477891494634e-06,
|
| 948 |
+
"loss": 6.865572357177735,
|
| 949 |
+
"step": 645
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.13,
|
| 953 |
+
"grad_norm": 0.0726066380739212,
|
| 954 |
+
"learning_rate": 3.930763277666547e-06,
|
| 955 |
+
"loss": 6.877969360351562,
|
| 956 |
+
"step": 650
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.131,
|
| 960 |
+
"grad_norm": 0.07925975322723389,
|
| 961 |
+
"learning_rate": 3.9290275493205925e-06,
|
| 962 |
+
"loss": 6.854046630859375,
|
| 963 |
+
"step": 655
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.132,
|
| 967 |
+
"grad_norm": 0.09406735748052597,
|
| 968 |
+
"learning_rate": 3.927270725438417e-06,
|
| 969 |
+
"loss": 6.818197631835938,
|
| 970 |
+
"step": 660
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.133,
|
| 974 |
+
"grad_norm": 0.07139192521572113,
|
| 975 |
+
"learning_rate": 3.925492825232363e-06,
|
| 976 |
+
"loss": 6.8501945495605465,
|
| 977 |
+
"step": 665
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.134,
|
| 981 |
+
"grad_norm": 0.07504747807979584,
|
| 982 |
+
"learning_rate": 3.923693868145263e-06,
|
| 983 |
+
"loss": 6.735340881347656,
|
| 984 |
+
"step": 670
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.135,
|
| 988 |
+
"grad_norm": 0.08873208612203598,
|
| 989 |
+
"learning_rate": 3.921873873850225e-06,
|
| 990 |
+
"loss": 6.871774291992187,
|
| 991 |
+
"step": 675
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.136,
|
| 995 |
+
"grad_norm": 0.06658565998077393,
|
| 996 |
+
"learning_rate": 3.920032862250413e-06,
|
| 997 |
+
"loss": 6.893667602539063,
|
| 998 |
+
"step": 680
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.137,
|
| 1002 |
+
"grad_norm": 0.08774610608816147,
|
| 1003 |
+
"learning_rate": 3.918170853478837e-06,
|
| 1004 |
+
"loss": 6.7974403381347654,
|
| 1005 |
+
"step": 685
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.138,
|
| 1009 |
+
"grad_norm": 0.09726791083812714,
|
| 1010 |
+
"learning_rate": 3.9162878678981245e-06,
|
| 1011 |
+
"loss": 6.884765625,
|
| 1012 |
+
"step": 690
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.139,
|
| 1016 |
+
"grad_norm": 0.07077678292989731,
|
| 1017 |
+
"learning_rate": 3.914383926100305e-06,
|
| 1018 |
+
"loss": 6.812703704833984,
|
| 1019 |
+
"step": 695
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.14,
|
| 1023 |
+
"grad_norm": 0.07094477862119675,
|
| 1024 |
+
"learning_rate": 3.912459048906582e-06,
|
| 1025 |
+
"loss": 6.804354095458985,
|
| 1026 |
+
"step": 700
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.141,
|
| 1030 |
+
"grad_norm": 0.09806753695011139,
|
| 1031 |
+
"learning_rate": 3.910513257367103e-06,
|
| 1032 |
+
"loss": 6.849080657958984,
|
| 1033 |
+
"step": 705
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.142,
|
| 1037 |
+
"grad_norm": 0.18241384625434875,
|
| 1038 |
+
"learning_rate": 3.908546572760732e-06,
|
| 1039 |
+
"loss": 6.818512725830078,
|
| 1040 |
+
"step": 710
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.143,
|
| 1044 |
+
"grad_norm": 0.13180814683437347,
|
| 1045 |
+
"learning_rate": 3.906559016594818e-06,
|
| 1046 |
+
"loss": 6.707421875,
|
| 1047 |
+
"step": 715
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.144,
|
| 1051 |
+
"grad_norm": 0.12693838775157928,
|
| 1052 |
+
"learning_rate": 3.904550610604957e-06,
|
| 1053 |
+
"loss": 6.848756408691406,
|
| 1054 |
+
"step": 720
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.145,
|
| 1058 |
+
"grad_norm": 0.10394909232854843,
|
| 1059 |
+
"learning_rate": 3.902521376754754e-06,
|
| 1060 |
+
"loss": 6.815328979492188,
|
| 1061 |
+
"step": 725
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.146,
|
| 1065 |
+
"grad_norm": 0.07995420694351196,
|
| 1066 |
+
"learning_rate": 3.900471337235584e-06,
|
| 1067 |
+
"loss": 6.754273986816406,
|
| 1068 |
+
"step": 730
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.147,
|
| 1072 |
+
"grad_norm": 0.07130531221628189,
|
| 1073 |
+
"learning_rate": 3.898400514466355e-06,
|
| 1074 |
+
"loss": 6.76672134399414,
|
| 1075 |
+
"step": 735
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.148,
|
| 1079 |
+
"grad_norm": 0.09754687547683716,
|
| 1080 |
+
"learning_rate": 3.896308931093249e-06,
|
| 1081 |
+
"loss": 6.763739776611328,
|
| 1082 |
+
"step": 740
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.149,
|
| 1086 |
+
"grad_norm": 0.1489243358373642,
|
| 1087 |
+
"learning_rate": 3.8941966099894884e-06,
|
| 1088 |
+
"loss": 6.877587127685547,
|
| 1089 |
+
"step": 745
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.15,
|
| 1093 |
+
"grad_norm": 0.1504446268081665,
|
| 1094 |
+
"learning_rate": 3.892063574255079e-06,
|
| 1095 |
+
"loss": 6.799798583984375,
|
| 1096 |
+
"step": 750
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.15,
|
| 1100 |
+
"eval_accuracy": 0.13552625152625153,
|
| 1101 |
+
"eval_loss": 6.6949238777160645,
|
| 1102 |
+
"eval_runtime": 10.4885,
|
| 1103 |
+
"eval_samples_per_second": 9.534,
|
| 1104 |
+
"eval_steps_per_second": 1.621,
|
| 1105 |
+
"step": 750
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.151,
|
| 1109 |
+
"grad_norm": 0.09069617837667465,
|
| 1110 |
+
"learning_rate": 3.889909847216555e-06,
|
| 1111 |
+
"loss": 6.758820343017578,
|
| 1112 |
+
"step": 755
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.152,
|
| 1116 |
+
"grad_norm": 0.09917005896568298,
|
| 1117 |
+
"learning_rate": 3.887735452426733e-06,
|
| 1118 |
+
"loss": 6.7119590759277346,
|
| 1119 |
+
"step": 760
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.153,
|
| 1123 |
+
"grad_norm": 0.1238972544670105,
|
| 1124 |
+
"learning_rate": 3.885540413664445e-06,
|
| 1125 |
+
"loss": 6.766522979736328,
|
| 1126 |
+
"step": 765
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.154,
|
| 1130 |
+
"grad_norm": 0.07523474842309952,
|
| 1131 |
+
"learning_rate": 3.8833247549342845e-06,
|
| 1132 |
+
"loss": 6.868996429443359,
|
| 1133 |
+
"step": 770
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.155,
|
| 1137 |
+
"grad_norm": 0.06490049511194229,
|
| 1138 |
+
"learning_rate": 3.8810885004663384e-06,
|
| 1139 |
+
"loss": 6.904286193847656,
|
| 1140 |
+
"step": 775
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.156,
|
| 1144 |
+
"grad_norm": 0.08743885904550552,
|
| 1145 |
+
"learning_rate": 3.878831674715929e-06,
|
| 1146 |
+
"loss": 6.790882873535156,
|
| 1147 |
+
"step": 780
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.157,
|
| 1151 |
+
"grad_norm": 0.07870012521743774,
|
| 1152 |
+
"learning_rate": 3.87655430236334e-06,
|
| 1153 |
+
"loss": 6.777058410644531,
|
| 1154 |
+
"step": 785
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.158,
|
| 1158 |
+
"grad_norm": 0.07427074015140533,
|
| 1159 |
+
"learning_rate": 3.87425640831355e-06,
|
| 1160 |
+
"loss": 6.888807678222657,
|
| 1161 |
+
"step": 790
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.159,
|
| 1165 |
+
"grad_norm": 0.07057588547468185,
|
| 1166 |
+
"learning_rate": 3.8719380176959615e-06,
|
| 1167 |
+
"loss": 6.771605682373047,
|
| 1168 |
+
"step": 795
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.16,
|
| 1172 |
+
"grad_norm": 0.07889208197593689,
|
| 1173 |
+
"learning_rate": 3.869599155864123e-06,
|
| 1174 |
+
"loss": 6.67206039428711,
|
| 1175 |
+
"step": 800
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.161,
|
| 1179 |
+
"grad_norm": 0.07260162383317947,
|
| 1180 |
+
"learning_rate": 3.867239848395452e-06,
|
| 1181 |
+
"loss": 6.824806976318359,
|
| 1182 |
+
"step": 805
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.162,
|
| 1186 |
+
"grad_norm": 0.07244172692298889,
|
| 1187 |
+
"learning_rate": 3.8648601210909575e-06,
|
| 1188 |
+
"loss": 6.776896667480469,
|
| 1189 |
+
"step": 810
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.163,
|
| 1193 |
+
"grad_norm": 0.11525345593690872,
|
| 1194 |
+
"learning_rate": 3.862459999974956e-06,
|
| 1195 |
+
"loss": 6.852814483642578,
|
| 1196 |
+
"step": 815
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.164,
|
| 1200 |
+
"grad_norm": 0.0778544470667839,
|
| 1201 |
+
"learning_rate": 3.860039511294787e-06,
|
| 1202 |
+
"loss": 6.725788116455078,
|
| 1203 |
+
"step": 820
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.165,
|
| 1207 |
+
"grad_norm": 0.06785336136817932,
|
| 1208 |
+
"learning_rate": 3.857598681520527e-06,
|
| 1209 |
+
"loss": 6.7376350402832035,
|
| 1210 |
+
"step": 825
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.166,
|
| 1214 |
+
"grad_norm": 0.08495451509952545,
|
| 1215 |
+
"learning_rate": 3.855137537344699e-06,
|
| 1216 |
+
"loss": 6.7077491760253904,
|
| 1217 |
+
"step": 830
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.167,
|
| 1221 |
+
"grad_norm": 0.06992894411087036,
|
| 1222 |
+
"learning_rate": 3.8526561056819825e-06,
|
| 1223 |
+
"loss": 6.713374328613281,
|
| 1224 |
+
"step": 835
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.168,
|
| 1228 |
+
"grad_norm": 0.0781623125076294,
|
| 1229 |
+
"learning_rate": 3.850154413668916e-06,
|
| 1230 |
+
"loss": 6.7144775390625,
|
| 1231 |
+
"step": 840
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.169,
|
| 1235 |
+
"grad_norm": 0.0706086978316307,
|
| 1236 |
+
"learning_rate": 3.847632488663602e-06,
|
| 1237 |
+
"loss": 6.768795776367187,
|
| 1238 |
+
"step": 845
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.17,
|
| 1242 |
+
"grad_norm": 0.11462926864624023,
|
| 1243 |
+
"learning_rate": 3.84509035824541e-06,
|
| 1244 |
+
"loss": 6.714561462402344,
|
| 1245 |
+
"step": 850
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.171,
|
| 1249 |
+
"grad_norm": 0.06380539387464523,
|
| 1250 |
+
"learning_rate": 3.842528050214669e-06,
|
| 1251 |
+
"loss": 6.754435729980469,
|
| 1252 |
+
"step": 855
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.172,
|
| 1256 |
+
"grad_norm": 0.0771062970161438,
|
| 1257 |
+
"learning_rate": 3.83994559259237e-06,
|
| 1258 |
+
"loss": 6.693482208251953,
|
| 1259 |
+
"step": 860
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.173,
|
| 1263 |
+
"grad_norm": 0.07977370917797089,
|
| 1264 |
+
"learning_rate": 3.837343013619856e-06,
|
| 1265 |
+
"loss": 6.782911682128907,
|
| 1266 |
+
"step": 865
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.174,
|
| 1270 |
+
"grad_norm": 0.09431219846010208,
|
| 1271 |
+
"learning_rate": 3.834720341758513e-06,
|
| 1272 |
+
"loss": 6.771470642089843,
|
| 1273 |
+
"step": 870
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.175,
|
| 1277 |
+
"grad_norm": 0.16286598145961761,
|
| 1278 |
+
"learning_rate": 3.832077605689461e-06,
|
| 1279 |
+
"loss": 6.584927368164062,
|
| 1280 |
+
"step": 875
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.176,
|
| 1284 |
+
"grad_norm": 0.06504693627357483,
|
| 1285 |
+
"learning_rate": 3.829414834313237e-06,
|
| 1286 |
+
"loss": 6.703968811035156,
|
| 1287 |
+
"step": 880
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.177,
|
| 1291 |
+
"grad_norm": 0.08418609946966171,
|
| 1292 |
+
"learning_rate": 3.826732056749485e-06,
|
| 1293 |
+
"loss": 6.592996215820312,
|
| 1294 |
+
"step": 885
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.178,
|
| 1298 |
+
"grad_norm": 0.06050467491149902,
|
| 1299 |
+
"learning_rate": 3.824029302336628e-06,
|
| 1300 |
+
"loss": 6.760212707519531,
|
| 1301 |
+
"step": 890
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.179,
|
| 1305 |
+
"grad_norm": 0.08373371511697769,
|
| 1306 |
+
"learning_rate": 3.821306600631556e-06,
|
| 1307 |
+
"loss": 6.631327819824219,
|
| 1308 |
+
"step": 895
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.18,
|
| 1312 |
+
"grad_norm": 0.08372713625431061,
|
| 1313 |
+
"learning_rate": 3.818563981409298e-06,
|
| 1314 |
+
"loss": 6.716769409179688,
|
| 1315 |
+
"step": 900
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.18,
|
| 1319 |
+
"eval_accuracy": 0.13533333333333333,
|
| 1320 |
+
"eval_loss": 6.627016544342041,
|
| 1321 |
+
"eval_runtime": 10.3756,
|
| 1322 |
+
"eval_samples_per_second": 9.638,
|
| 1323 |
+
"eval_steps_per_second": 1.638,
|
| 1324 |
+
"step": 900
|
| 1325 |
}
|
| 1326 |
],
|
| 1327 |
"logging_steps": 5,
|