Training in progress, step 20000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +339 -3
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- runs/May23_11-27-41_4b659dec4dc1/1684841942.6076107/events.out.tfevents.1684841942.4b659dec4dc1.6139.1 +3 -0
- runs/May23_11-27-41_4b659dec4dc1/events.out.tfevents.1684841942.4b659dec4dc1.6139.0 +3 -0
- training_args.bin +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1987250795
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27f4d0eddea1b38fe1b064b634ee31b71591cebd4a1e1ea45cc654a255e6f2a6
|
| 3 |
size 1987250795
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 996026489
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a0d0aa4eebf05151380698116acb15efc7e866ed933da42068ae8c22cfa382e
|
| 3 |
size 996026489
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46c405f6c1e391e2b416a111eb36de129465177d85a3f632dda3a1eb030336c8
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e8f70b4a42839623f23a2d7f6f16070a0bb7a8546d17d8052ec84cfde1f2b48
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -990,11 +990,347 @@
|
|
| 990 |
"learning_rate": 2.1064814814814816e-05,
|
| 991 |
"loss": 0.5798,
|
| 992 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 993 |
}
|
| 994 |
],
|
| 995 |
"max_steps": 24100,
|
| 996 |
"num_train_epochs": 10,
|
| 997 |
-
"total_flos":
|
| 998 |
"trial_name": null,
|
| 999 |
"trial_params": null
|
| 1000 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.298755186721992,
|
| 5 |
+
"global_step": 20000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 990 |
"learning_rate": 2.1064814814814816e-05,
|
| 991 |
"loss": 0.5798,
|
| 992 |
"step": 15000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 6.27,
|
| 996 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 997 |
+
"loss": 0.5939,
|
| 998 |
+
"step": 15100
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 6.31,
|
| 1002 |
+
"learning_rate": 2.0601851851851853e-05,
|
| 1003 |
+
"loss": 0.6095,
|
| 1004 |
+
"step": 15200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 6.35,
|
| 1008 |
+
"learning_rate": 2.037037037037037e-05,
|
| 1009 |
+
"loss": 0.6163,
|
| 1010 |
+
"step": 15300
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 6.39,
|
| 1014 |
+
"learning_rate": 2.013888888888889e-05,
|
| 1015 |
+
"loss": 0.5634,
|
| 1016 |
+
"step": 15400
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 6.43,
|
| 1020 |
+
"learning_rate": 1.990740740740741e-05,
|
| 1021 |
+
"loss": 0.5909,
|
| 1022 |
+
"step": 15500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 6.47,
|
| 1026 |
+
"learning_rate": 1.967592592592593e-05,
|
| 1027 |
+
"loss": 0.5408,
|
| 1028 |
+
"step": 15600
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 6.51,
|
| 1032 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 1033 |
+
"loss": 0.5435,
|
| 1034 |
+
"step": 15700
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 6.56,
|
| 1038 |
+
"learning_rate": 1.9212962962962962e-05,
|
| 1039 |
+
"loss": 0.5753,
|
| 1040 |
+
"step": 15800
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 6.6,
|
| 1044 |
+
"learning_rate": 1.8981481481481482e-05,
|
| 1045 |
+
"loss": 0.5491,
|
| 1046 |
+
"step": 15900
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 6.64,
|
| 1050 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 1051 |
+
"loss": 0.5868,
|
| 1052 |
+
"step": 16000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 6.64,
|
| 1056 |
+
"eval_bleu": 71.6124,
|
| 1057 |
+
"eval_em": 0.02,
|
| 1058 |
+
"eval_gen_len": 47.52,
|
| 1059 |
+
"eval_loss": 0.9307076930999756,
|
| 1060 |
+
"eval_rm": 0.9556,
|
| 1061 |
+
"eval_runtime": 330.299,
|
| 1062 |
+
"eval_samples_per_second": 0.151,
|
| 1063 |
+
"eval_steps_per_second": 0.021,
|
| 1064 |
+
"step": 16000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 6.68,
|
| 1068 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1069 |
+
"loss": 0.5088,
|
| 1070 |
+
"step": 16100
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 6.72,
|
| 1074 |
+
"learning_rate": 1.8287037037037038e-05,
|
| 1075 |
+
"loss": 0.6068,
|
| 1076 |
+
"step": 16200
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 6.76,
|
| 1080 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 1081 |
+
"loss": 0.5327,
|
| 1082 |
+
"step": 16300
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 6.8,
|
| 1086 |
+
"learning_rate": 1.7824074074074075e-05,
|
| 1087 |
+
"loss": 0.5759,
|
| 1088 |
+
"step": 16400
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 6.85,
|
| 1092 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 1093 |
+
"loss": 0.5849,
|
| 1094 |
+
"step": 16500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 6.89,
|
| 1098 |
+
"learning_rate": 1.736111111111111e-05,
|
| 1099 |
+
"loss": 0.5648,
|
| 1100 |
+
"step": 16600
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 6.93,
|
| 1104 |
+
"learning_rate": 1.712962962962963e-05,
|
| 1105 |
+
"loss": 0.5632,
|
| 1106 |
+
"step": 16700
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 6.97,
|
| 1110 |
+
"learning_rate": 1.6898148148148148e-05,
|
| 1111 |
+
"loss": 0.5093,
|
| 1112 |
+
"step": 16800
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 7.01,
|
| 1116 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 1117 |
+
"loss": 0.5295,
|
| 1118 |
+
"step": 16900
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 7.05,
|
| 1122 |
+
"learning_rate": 1.6435185185185187e-05,
|
| 1123 |
+
"loss": 0.433,
|
| 1124 |
+
"step": 17000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 7.1,
|
| 1128 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 1129 |
+
"loss": 0.4289,
|
| 1130 |
+
"step": 17100
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 7.14,
|
| 1134 |
+
"learning_rate": 1.597222222222222e-05,
|
| 1135 |
+
"loss": 0.4619,
|
| 1136 |
+
"step": 17200
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.18,
|
| 1140 |
+
"learning_rate": 1.574074074074074e-05,
|
| 1141 |
+
"loss": 0.458,
|
| 1142 |
+
"step": 17300
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 7.22,
|
| 1146 |
+
"learning_rate": 1.550925925925926e-05,
|
| 1147 |
+
"loss": 0.4155,
|
| 1148 |
+
"step": 17400
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 7.26,
|
| 1152 |
+
"learning_rate": 1.527777777777778e-05,
|
| 1153 |
+
"loss": 0.4391,
|
| 1154 |
+
"step": 17500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 7.3,
|
| 1158 |
+
"learning_rate": 1.5046296296296297e-05,
|
| 1159 |
+
"loss": 0.4264,
|
| 1160 |
+
"step": 17600
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 7.34,
|
| 1164 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1165 |
+
"loss": 0.418,
|
| 1166 |
+
"step": 17700
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 7.39,
|
| 1170 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 1171 |
+
"loss": 0.4285,
|
| 1172 |
+
"step": 17800
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 7.43,
|
| 1176 |
+
"learning_rate": 1.4351851851851853e-05,
|
| 1177 |
+
"loss": 0.4466,
|
| 1178 |
+
"step": 17900
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 7.47,
|
| 1182 |
+
"learning_rate": 1.412037037037037e-05,
|
| 1183 |
+
"loss": 0.4499,
|
| 1184 |
+
"step": 18000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 7.47,
|
| 1188 |
+
"eval_bleu": 77.237,
|
| 1189 |
+
"eval_em": 0.06,
|
| 1190 |
+
"eval_gen_len": 46.0,
|
| 1191 |
+
"eval_loss": 0.8866045475006104,
|
| 1192 |
+
"eval_rm": 0.9574,
|
| 1193 |
+
"eval_runtime": 280.5418,
|
| 1194 |
+
"eval_samples_per_second": 0.178,
|
| 1195 |
+
"eval_steps_per_second": 0.025,
|
| 1196 |
+
"step": 18000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 7.51,
|
| 1200 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1201 |
+
"loss": 0.4415,
|
| 1202 |
+
"step": 18100
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 7.55,
|
| 1206 |
+
"learning_rate": 1.3657407407407408e-05,
|
| 1207 |
+
"loss": 0.4209,
|
| 1208 |
+
"step": 18200
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 7.59,
|
| 1212 |
+
"learning_rate": 1.3425925925925928e-05,
|
| 1213 |
+
"loss": 0.4357,
|
| 1214 |
+
"step": 18300
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 7.63,
|
| 1218 |
+
"learning_rate": 1.3194444444444446e-05,
|
| 1219 |
+
"loss": 0.437,
|
| 1220 |
+
"step": 18400
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 7.68,
|
| 1224 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1225 |
+
"loss": 0.4319,
|
| 1226 |
+
"step": 18500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 7.72,
|
| 1230 |
+
"learning_rate": 1.2731481481481482e-05,
|
| 1231 |
+
"loss": 0.4578,
|
| 1232 |
+
"step": 18600
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 7.76,
|
| 1236 |
+
"learning_rate": 1.25e-05,
|
| 1237 |
+
"loss": 0.4244,
|
| 1238 |
+
"step": 18700
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 7.8,
|
| 1242 |
+
"learning_rate": 1.2268518518518519e-05,
|
| 1243 |
+
"loss": 0.4046,
|
| 1244 |
+
"step": 18800
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 7.84,
|
| 1248 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 1249 |
+
"loss": 0.411,
|
| 1250 |
+
"step": 18900
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 7.88,
|
| 1254 |
+
"learning_rate": 1.1805555555555555e-05,
|
| 1255 |
+
"loss": 0.4219,
|
| 1256 |
+
"step": 19000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 7.93,
|
| 1260 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 1261 |
+
"loss": 0.3956,
|
| 1262 |
+
"step": 19100
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 7.97,
|
| 1266 |
+
"learning_rate": 1.1342592592592593e-05,
|
| 1267 |
+
"loss": 0.4333,
|
| 1268 |
+
"step": 19200
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 8.01,
|
| 1272 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 1273 |
+
"loss": 0.4141,
|
| 1274 |
+
"step": 19300
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 8.05,
|
| 1278 |
+
"learning_rate": 1.087962962962963e-05,
|
| 1279 |
+
"loss": 0.3199,
|
| 1280 |
+
"step": 19400
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 8.09,
|
| 1284 |
+
"learning_rate": 1.0648148148148148e-05,
|
| 1285 |
+
"loss": 0.3236,
|
| 1286 |
+
"step": 19500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 8.13,
|
| 1290 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 1291 |
+
"loss": 0.3405,
|
| 1292 |
+
"step": 19600
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 8.17,
|
| 1296 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 1297 |
+
"loss": 0.3411,
|
| 1298 |
+
"step": 19700
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 8.22,
|
| 1302 |
+
"learning_rate": 9.953703703703704e-06,
|
| 1303 |
+
"loss": 0.3166,
|
| 1304 |
+
"step": 19800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 8.26,
|
| 1308 |
+
"learning_rate": 9.722222222222223e-06,
|
| 1309 |
+
"loss": 0.3463,
|
| 1310 |
+
"step": 19900
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 8.3,
|
| 1314 |
+
"learning_rate": 9.490740740740741e-06,
|
| 1315 |
+
"loss": 0.3515,
|
| 1316 |
+
"step": 20000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 8.3,
|
| 1320 |
+
"eval_bleu": 77.5798,
|
| 1321 |
+
"eval_em": 0.08,
|
| 1322 |
+
"eval_gen_len": 47.5,
|
| 1323 |
+
"eval_loss": 0.9069581627845764,
|
| 1324 |
+
"eval_rm": 0.9574,
|
| 1325 |
+
"eval_runtime": 312.8421,
|
| 1326 |
+
"eval_samples_per_second": 0.16,
|
| 1327 |
+
"eval_steps_per_second": 0.022,
|
| 1328 |
+
"step": 20000
|
| 1329 |
}
|
| 1330 |
],
|
| 1331 |
"max_steps": 24100,
|
| 1332 |
"num_train_epochs": 10,
|
| 1333 |
+
"total_flos": 5827422495665664.0,
|
| 1334 |
"trial_name": null,
|
| 1335 |
"trial_params": null
|
| 1336 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39883603e0f5d5f423c83fa5b774cffc6fd43f8970ddb1f1665c98b8cf652f9
|
| 3 |
+
size 4219
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 996026489
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a0d0aa4eebf05151380698116acb15efc7e866ed933da42068ae8c22cfa382e
|
| 3 |
size 996026489
|
runs/May23_11-27-41_4b659dec4dc1/1684841942.6076107/events.out.tfevents.1684841942.4b659dec4dc1.6139.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552ac6b3d8683237063758cc1cf667f0e68175fbe9bb74e25dc0cdc033aa36e5
|
| 3 |
+
size 6342
|
runs/May23_11-27-41_4b659dec4dc1/events.out.tfevents.1684841942.4b659dec4dc1.6139.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46bed9901348db72ec0ddf87172765591157e7e6f99f5dd9c06ca85bd762ce33
|
| 3 |
+
size 17952
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39883603e0f5d5f423c83fa5b774cffc6fd43f8970ddb1f1665c98b8cf652f9
|
| 3 |
+
size 4219
|