Training in progress, step 500, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 150487412
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b14558afc2ff84281d8813573705af0c29271e886a5c55ea1716c22df3fa2654
|
| 3 |
size 150487412
|
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:d7e214f2b29bc7b5cdb3187dd8641f87052b9b8ab7ca01c37e612aeca4c84a0c
|
| 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:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 125,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -914,6 +914,301 @@
|
|
| 914 |
"eval_samples_per_second": 45.393,
|
| 915 |
"eval_steps_per_second": 22.697,
|
| 916 |
"step": 375
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 917 |
}
|
| 918 |
],
|
| 919 |
"logging_steps": 3,
|
|
@@ -928,12 +1223,12 @@
|
|
| 928 |
"should_evaluate": false,
|
| 929 |
"should_log": false,
|
| 930 |
"should_save": true,
|
| 931 |
-
"should_training_stop":
|
| 932 |
},
|
| 933 |
"attributes": {}
|
| 934 |
}
|
| 935 |
},
|
| 936 |
-
"total_flos":
|
| 937 |
"train_batch_size": 2,
|
| 938 |
"trial_name": null,
|
| 939 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01616285694659388,
|
| 5 |
"eval_steps": 125,
|
| 6 |
+
"global_step": 500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 914 |
"eval_samples_per_second": 45.393,
|
| 915 |
"eval_steps_per_second": 22.697,
|
| 916 |
"step": 375
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.012219119851624972,
|
| 920 |
+
"grad_norm": NaN,
|
| 921 |
+
"learning_rate": 1.4531503949737108e-05,
|
| 922 |
+
"loss": 0.0,
|
| 923 |
+
"step": 378
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.012316096993304536,
|
| 927 |
+
"grad_norm": NaN,
|
| 928 |
+
"learning_rate": 1.3860256808630428e-05,
|
| 929 |
+
"loss": 0.0,
|
| 930 |
+
"step": 381
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.0124130741349841,
|
| 934 |
+
"grad_norm": NaN,
|
| 935 |
+
"learning_rate": 1.3202379370768252e-05,
|
| 936 |
+
"loss": 0.0,
|
| 937 |
+
"step": 384
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.012510051276663664,
|
| 941 |
+
"grad_norm": NaN,
|
| 942 |
+
"learning_rate": 1.2558115014363592e-05,
|
| 943 |
+
"loss": 0.0,
|
| 944 |
+
"step": 387
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.012607028418343226,
|
| 948 |
+
"grad_norm": NaN,
|
| 949 |
+
"learning_rate": 1.1927702081543279e-05,
|
| 950 |
+
"loss": 0.0,
|
| 951 |
+
"step": 390
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.01270400556002279,
|
| 955 |
+
"grad_norm": NaN,
|
| 956 |
+
"learning_rate": 1.1311373790174657e-05,
|
| 957 |
+
"loss": 0.0,
|
| 958 |
+
"step": 393
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 0.012800982701702353,
|
| 962 |
+
"grad_norm": NaN,
|
| 963 |
+
"learning_rate": 1.0709358147587884e-05,
|
| 964 |
+
"loss": 0.0,
|
| 965 |
+
"step": 396
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 0.012897959843381917,
|
| 969 |
+
"grad_norm": NaN,
|
| 970 |
+
"learning_rate": 1.0121877866225781e-05,
|
| 971 |
+
"loss": 0.0,
|
| 972 |
+
"step": 399
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.012994936985061479,
|
| 976 |
+
"grad_norm": NaN,
|
| 977 |
+
"learning_rate": 9.549150281252633e-06,
|
| 978 |
+
"loss": 0.0,
|
| 979 |
+
"step": 402
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 0.013091914126741043,
|
| 983 |
+
"grad_norm": NaN,
|
| 984 |
+
"learning_rate": 8.991387270152201e-06,
|
| 985 |
+
"loss": 0.0,
|
| 986 |
+
"step": 405
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.013188891268420606,
|
| 990 |
+
"grad_norm": NaN,
|
| 991 |
+
"learning_rate": 8.448795174344804e-06,
|
| 992 |
+
"loss": 0.0,
|
| 993 |
+
"step": 408
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.01328586841010017,
|
| 997 |
+
"grad_norm": NaN,
|
| 998 |
+
"learning_rate": 7.921574722852343e-06,
|
| 999 |
+
"loss": 0.0,
|
| 1000 |
+
"step": 411
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.013382845551779732,
|
| 1004 |
+
"grad_norm": NaN,
|
| 1005 |
+
"learning_rate": 7.409920958039795e-06,
|
| 1006 |
+
"loss": 0.0,
|
| 1007 |
+
"step": 414
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.013479822693459296,
|
| 1011 |
+
"grad_norm": NaN,
|
| 1012 |
+
"learning_rate": 6.9140231634602485e-06,
|
| 1013 |
+
"loss": 0.0,
|
| 1014 |
+
"step": 417
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 0.01357679983513886,
|
| 1018 |
+
"grad_norm": NaN,
|
| 1019 |
+
"learning_rate": 6.43406479383053e-06,
|
| 1020 |
+
"loss": 0.0,
|
| 1021 |
+
"step": 420
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 0.013673776976818422,
|
| 1025 |
+
"grad_norm": NaN,
|
| 1026 |
+
"learning_rate": 5.9702234071631e-06,
|
| 1027 |
+
"loss": 0.0,
|
| 1028 |
+
"step": 423
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.013770754118497985,
|
| 1032 |
+
"grad_norm": NaN,
|
| 1033 |
+
"learning_rate": 5.5226705990794155e-06,
|
| 1034 |
+
"loss": 0.0,
|
| 1035 |
+
"step": 426
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.013867731260177549,
|
| 1039 |
+
"grad_norm": NaN,
|
| 1040 |
+
"learning_rate": 5.091571939329048e-06,
|
| 1041 |
+
"loss": 0.0,
|
| 1042 |
+
"step": 429
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.013964708401857113,
|
| 1046 |
+
"grad_norm": NaN,
|
| 1047 |
+
"learning_rate": 4.677086910538092e-06,
|
| 1048 |
+
"loss": 0.0,
|
| 1049 |
+
"step": 432
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.014061685543536675,
|
| 1053 |
+
"grad_norm": NaN,
|
| 1054 |
+
"learning_rate": 4.279368849209381e-06,
|
| 1055 |
+
"loss": 0.0,
|
| 1056 |
+
"step": 435
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.014158662685216239,
|
| 1060 |
+
"grad_norm": NaN,
|
| 1061 |
+
"learning_rate": 3.898564888996476e-06,
|
| 1062 |
+
"loss": 0.0,
|
| 1063 |
+
"step": 438
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.014255639826895802,
|
| 1067 |
+
"grad_norm": NaN,
|
| 1068 |
+
"learning_rate": 3.534815906272404e-06,
|
| 1069 |
+
"loss": 0.0,
|
| 1070 |
+
"step": 441
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.014352616968575366,
|
| 1074 |
+
"grad_norm": NaN,
|
| 1075 |
+
"learning_rate": 3.18825646801314e-06,
|
| 1076 |
+
"loss": 0.0,
|
| 1077 |
+
"step": 444
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.014449594110254928,
|
| 1081 |
+
"grad_norm": NaN,
|
| 1082 |
+
"learning_rate": 2.8590147820153513e-06,
|
| 1083 |
+
"loss": 0.0,
|
| 1084 |
+
"step": 447
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.014546571251934492,
|
| 1088 |
+
"grad_norm": NaN,
|
| 1089 |
+
"learning_rate": 2.547212649466568e-06,
|
| 1090 |
+
"loss": 0.0,
|
| 1091 |
+
"step": 450
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.014643548393614056,
|
| 1095 |
+
"grad_norm": NaN,
|
| 1096 |
+
"learning_rate": 2.2529654198854835e-06,
|
| 1097 |
+
"loss": 0.0,
|
| 1098 |
+
"step": 453
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.01474052553529362,
|
| 1102 |
+
"grad_norm": NaN,
|
| 1103 |
+
"learning_rate": 1.9763819484490355e-06,
|
| 1104 |
+
"loss": 0.0,
|
| 1105 |
+
"step": 456
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.014837502676973181,
|
| 1109 |
+
"grad_norm": NaN,
|
| 1110 |
+
"learning_rate": 1.7175645557220566e-06,
|
| 1111 |
+
"loss": 0.0,
|
| 1112 |
+
"step": 459
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.014934479818652745,
|
| 1116 |
+
"grad_norm": NaN,
|
| 1117 |
+
"learning_rate": 1.4766089898042678e-06,
|
| 1118 |
+
"loss": 0.0,
|
| 1119 |
+
"step": 462
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.015031456960332309,
|
| 1123 |
+
"grad_norm": NaN,
|
| 1124 |
+
"learning_rate": 1.2536043909088191e-06,
|
| 1125 |
+
"loss": 0.0,
|
| 1126 |
+
"step": 465
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.01512843410201187,
|
| 1130 |
+
"grad_norm": NaN,
|
| 1131 |
+
"learning_rate": 1.0486332583853563e-06,
|
| 1132 |
+
"loss": 0.0,
|
| 1133 |
+
"step": 468
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.015225411243691435,
|
| 1137 |
+
"grad_norm": NaN,
|
| 1138 |
+
"learning_rate": 8.617714201998084e-07,
|
| 1139 |
+
"loss": 0.0,
|
| 1140 |
+
"step": 471
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.015322388385370998,
|
| 1144 |
+
"grad_norm": NaN,
|
| 1145 |
+
"learning_rate": 6.93088004882253e-07,
|
| 1146 |
+
"loss": 0.0,
|
| 1147 |
+
"step": 474
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.015419365527050562,
|
| 1151 |
+
"grad_norm": NaN,
|
| 1152 |
+
"learning_rate": 5.426454159531913e-07,
|
| 1153 |
+
"loss": 0.0,
|
| 1154 |
+
"step": 477
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.015516342668730124,
|
| 1158 |
+
"grad_norm": NaN,
|
| 1159 |
+
"learning_rate": 4.104993088376974e-07,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"step": 480
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.015613319810409688,
|
| 1165 |
+
"grad_norm": NaN,
|
| 1166 |
+
"learning_rate": 2.966985702759828e-07,
|
| 1167 |
+
"loss": 0.0,
|
| 1168 |
+
"step": 483
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.01571029695208925,
|
| 1172 |
+
"grad_norm": NaN,
|
| 1173 |
+
"learning_rate": 2.012853002380466e-07,
|
| 1174 |
+
"loss": 0.0,
|
| 1175 |
+
"step": 486
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.015807274093768815,
|
| 1179 |
+
"grad_norm": NaN,
|
| 1180 |
+
"learning_rate": 1.2429479634897267e-07,
|
| 1181 |
+
"loss": 0.0,
|
| 1182 |
+
"step": 489
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.015904251235448377,
|
| 1186 |
+
"grad_norm": NaN,
|
| 1187 |
+
"learning_rate": 6.575554083078084e-08,
|
| 1188 |
+
"loss": 0.0,
|
| 1189 |
+
"step": 492
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.016001228377127943,
|
| 1193 |
+
"grad_norm": NaN,
|
| 1194 |
+
"learning_rate": 2.568918996560532e-08,
|
| 1195 |
+
"loss": 0.0,
|
| 1196 |
+
"step": 495
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.016098205518807505,
|
| 1200 |
+
"grad_norm": NaN,
|
| 1201 |
+
"learning_rate": 4.110566084036816e-09,
|
| 1202 |
+
"loss": 0.0,
|
| 1203 |
+
"step": 498
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.01616285694659388,
|
| 1207 |
+
"eval_loss": NaN,
|
| 1208 |
+
"eval_runtime": 660.3671,
|
| 1209 |
+
"eval_samples_per_second": 39.449,
|
| 1210 |
+
"eval_steps_per_second": 19.725,
|
| 1211 |
+
"step": 500
|
| 1212 |
}
|
| 1213 |
],
|
| 1214 |
"logging_steps": 3,
|
|
|
|
| 1223 |
"should_evaluate": false,
|
| 1224 |
"should_log": false,
|
| 1225 |
"should_save": true,
|
| 1226 |
+
"should_training_stop": true
|
| 1227 |
},
|
| 1228 |
"attributes": {}
|
| 1229 |
}
|
| 1230 |
},
|
| 1231 |
+
"total_flos": 3.401809133568e+16,
|
| 1232 |
"train_batch_size": 2,
|
| 1233 |
"trial_name": null,
|
| 1234 |
"trial_params": null
|