Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:264ecec36fa0a7877a74e5bc90de5cfe426844837e851cd04e19bd3e592e07d9
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9825a8978c13d22cdcc9972f981eca76a202db226c336284f26d0d6ae781e227
|
| 3 |
size 10707706
|
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:d122c28c5fc3f53d9d112345e4abc97c9cbf42b6d6c3da282213a9e89d67c386
|
| 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 sha256:8c35dfe7906d79114431a0065ffa36a90ef274205cc0fefa7802dd197d609956
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.45563551783561707,
|
| 3 |
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-1500",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1027,13 +1027,353 @@
|
|
| 1027 |
"eval_samples_per_second": 89.239,
|
| 1028 |
"eval_steps_per_second": 11.202,
|
| 1029 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1030 |
}
|
| 1031 |
],
|
| 1032 |
"logging_steps": 10,
|
| 1033 |
"max_steps": 6130,
|
| 1034 |
"num_train_epochs": 10,
|
| 1035 |
"save_steps": 500,
|
| 1036 |
-
"total_flos":
|
| 1037 |
"trial_name": null,
|
| 1038 |
"trial_params": null
|
| 1039 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.45563551783561707,
|
| 3 |
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-1500",
|
| 4 |
+
"epoch": 3.262642740619902,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1027 |
"eval_samples_per_second": 89.239,
|
| 1028 |
"eval_steps_per_second": 11.202,
|
| 1029 |
"step": 1500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.46,
|
| 1033 |
+
"learning_rate": 0.0008206039076376555,
|
| 1034 |
+
"loss": 0.4859,
|
| 1035 |
+
"step": 1510
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.48,
|
| 1039 |
+
"learning_rate": 0.0008188277087033748,
|
| 1040 |
+
"loss": 0.5359,
|
| 1041 |
+
"step": 1520
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.5,
|
| 1045 |
+
"learning_rate": 0.0008170515097690942,
|
| 1046 |
+
"loss": 0.4693,
|
| 1047 |
+
"step": 1530
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.51,
|
| 1051 |
+
"learning_rate": 0.0008152753108348136,
|
| 1052 |
+
"loss": 0.4506,
|
| 1053 |
+
"step": 1540
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.53,
|
| 1057 |
+
"learning_rate": 0.0008134991119005329,
|
| 1058 |
+
"loss": 0.4449,
|
| 1059 |
+
"step": 1550
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.54,
|
| 1063 |
+
"learning_rate": 0.0008117229129662523,
|
| 1064 |
+
"loss": 0.4976,
|
| 1065 |
+
"step": 1560
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.56,
|
| 1069 |
+
"learning_rate": 0.0008099467140319717,
|
| 1070 |
+
"loss": 0.4781,
|
| 1071 |
+
"step": 1570
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.58,
|
| 1075 |
+
"learning_rate": 0.0008081705150976909,
|
| 1076 |
+
"loss": 0.4755,
|
| 1077 |
+
"step": 1580
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.59,
|
| 1081 |
+
"learning_rate": 0.0008063943161634103,
|
| 1082 |
+
"loss": 0.5088,
|
| 1083 |
+
"step": 1590
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.61,
|
| 1087 |
+
"learning_rate": 0.0008046181172291297,
|
| 1088 |
+
"loss": 0.4777,
|
| 1089 |
+
"step": 1600
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.61,
|
| 1093 |
+
"eval_loss": 0.46053746342658997,
|
| 1094 |
+
"eval_runtime": 13.1201,
|
| 1095 |
+
"eval_samples_per_second": 89.252,
|
| 1096 |
+
"eval_steps_per_second": 11.204,
|
| 1097 |
+
"step": 1600
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.63,
|
| 1101 |
+
"learning_rate": 0.0008028419182948491,
|
| 1102 |
+
"loss": 0.4648,
|
| 1103 |
+
"step": 1610
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.64,
|
| 1107 |
+
"learning_rate": 0.0008010657193605684,
|
| 1108 |
+
"loss": 0.5066,
|
| 1109 |
+
"step": 1620
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.66,
|
| 1113 |
+
"learning_rate": 0.0007992895204262878,
|
| 1114 |
+
"loss": 0.5127,
|
| 1115 |
+
"step": 1630
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.68,
|
| 1119 |
+
"learning_rate": 0.0007975133214920072,
|
| 1120 |
+
"loss": 0.5136,
|
| 1121 |
+
"step": 1640
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.69,
|
| 1125 |
+
"learning_rate": 0.0007957371225577265,
|
| 1126 |
+
"loss": 0.4911,
|
| 1127 |
+
"step": 1650
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 2.71,
|
| 1131 |
+
"learning_rate": 0.0007939609236234459,
|
| 1132 |
+
"loss": 0.4537,
|
| 1133 |
+
"step": 1660
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.72,
|
| 1137 |
+
"learning_rate": 0.0007921847246891653,
|
| 1138 |
+
"loss": 0.4958,
|
| 1139 |
+
"step": 1670
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.74,
|
| 1143 |
+
"learning_rate": 0.0007904085257548845,
|
| 1144 |
+
"loss": 0.4997,
|
| 1145 |
+
"step": 1680
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.76,
|
| 1149 |
+
"learning_rate": 0.0007886323268206039,
|
| 1150 |
+
"loss": 0.5192,
|
| 1151 |
+
"step": 1690
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.77,
|
| 1155 |
+
"learning_rate": 0.0007868561278863233,
|
| 1156 |
+
"loss": 0.4977,
|
| 1157 |
+
"step": 1700
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.77,
|
| 1161 |
+
"eval_loss": 0.4585750102996826,
|
| 1162 |
+
"eval_runtime": 13.1101,
|
| 1163 |
+
"eval_samples_per_second": 89.32,
|
| 1164 |
+
"eval_steps_per_second": 11.213,
|
| 1165 |
+
"step": 1700
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.79,
|
| 1169 |
+
"learning_rate": 0.0007850799289520426,
|
| 1170 |
+
"loss": 0.5044,
|
| 1171 |
+
"step": 1710
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.81,
|
| 1175 |
+
"learning_rate": 0.000783303730017762,
|
| 1176 |
+
"loss": 0.4839,
|
| 1177 |
+
"step": 1720
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.82,
|
| 1181 |
+
"learning_rate": 0.0007815275310834814,
|
| 1182 |
+
"loss": 0.5234,
|
| 1183 |
+
"step": 1730
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 2.84,
|
| 1187 |
+
"learning_rate": 0.0007797513321492007,
|
| 1188 |
+
"loss": 0.4835,
|
| 1189 |
+
"step": 1740
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.85,
|
| 1193 |
+
"learning_rate": 0.0007779751332149201,
|
| 1194 |
+
"loss": 0.4939,
|
| 1195 |
+
"step": 1750
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.87,
|
| 1199 |
+
"learning_rate": 0.0007761989342806395,
|
| 1200 |
+
"loss": 0.554,
|
| 1201 |
+
"step": 1760
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.89,
|
| 1205 |
+
"learning_rate": 0.0007744227353463588,
|
| 1206 |
+
"loss": 0.4643,
|
| 1207 |
+
"step": 1770
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.9,
|
| 1211 |
+
"learning_rate": 0.0007726465364120782,
|
| 1212 |
+
"loss": 0.4909,
|
| 1213 |
+
"step": 1780
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.92,
|
| 1217 |
+
"learning_rate": 0.0007708703374777975,
|
| 1218 |
+
"loss": 0.5042,
|
| 1219 |
+
"step": 1790
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 2.94,
|
| 1223 |
+
"learning_rate": 0.0007690941385435168,
|
| 1224 |
+
"loss": 0.4772,
|
| 1225 |
+
"step": 1800
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.94,
|
| 1229 |
+
"eval_loss": 0.44169098138809204,
|
| 1230 |
+
"eval_runtime": 13.0107,
|
| 1231 |
+
"eval_samples_per_second": 90.003,
|
| 1232 |
+
"eval_steps_per_second": 11.298,
|
| 1233 |
+
"step": 1800
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.95,
|
| 1237 |
+
"learning_rate": 0.0007673179396092362,
|
| 1238 |
+
"loss": 0.4529,
|
| 1239 |
+
"step": 1810
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.97,
|
| 1243 |
+
"learning_rate": 0.0007655417406749556,
|
| 1244 |
+
"loss": 0.5058,
|
| 1245 |
+
"step": 1820
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.99,
|
| 1249 |
+
"learning_rate": 0.0007637655417406749,
|
| 1250 |
+
"loss": 0.4794,
|
| 1251 |
+
"step": 1830
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.0,
|
| 1255 |
+
"learning_rate": 0.0007619893428063943,
|
| 1256 |
+
"loss": 0.477,
|
| 1257 |
+
"step": 1840
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.02,
|
| 1261 |
+
"learning_rate": 0.0007602131438721137,
|
| 1262 |
+
"loss": 0.4663,
|
| 1263 |
+
"step": 1850
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.03,
|
| 1267 |
+
"learning_rate": 0.0007584369449378331,
|
| 1268 |
+
"loss": 0.4634,
|
| 1269 |
+
"step": 1860
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 3.05,
|
| 1273 |
+
"learning_rate": 0.0007566607460035524,
|
| 1274 |
+
"loss": 0.5159,
|
| 1275 |
+
"step": 1870
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.07,
|
| 1279 |
+
"learning_rate": 0.0007548845470692718,
|
| 1280 |
+
"loss": 0.4818,
|
| 1281 |
+
"step": 1880
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 3.08,
|
| 1285 |
+
"learning_rate": 0.0007531083481349912,
|
| 1286 |
+
"loss": 0.4747,
|
| 1287 |
+
"step": 1890
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 3.1,
|
| 1291 |
+
"learning_rate": 0.0007513321492007104,
|
| 1292 |
+
"loss": 0.4605,
|
| 1293 |
+
"step": 1900
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 3.1,
|
| 1297 |
+
"eval_loss": 0.4483106732368469,
|
| 1298 |
+
"eval_runtime": 13.1231,
|
| 1299 |
+
"eval_samples_per_second": 89.232,
|
| 1300 |
+
"eval_steps_per_second": 11.202,
|
| 1301 |
+
"step": 1900
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 3.12,
|
| 1305 |
+
"learning_rate": 0.0007495559502664298,
|
| 1306 |
+
"loss": 0.474,
|
| 1307 |
+
"step": 1910
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.13,
|
| 1311 |
+
"learning_rate": 0.0007477797513321492,
|
| 1312 |
+
"loss": 0.4639,
|
| 1313 |
+
"step": 1920
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 3.15,
|
| 1317 |
+
"learning_rate": 0.0007460035523978685,
|
| 1318 |
+
"loss": 0.4485,
|
| 1319 |
+
"step": 1930
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.16,
|
| 1323 |
+
"learning_rate": 0.0007442273534635879,
|
| 1324 |
+
"loss": 0.4835,
|
| 1325 |
+
"step": 1940
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 3.18,
|
| 1329 |
+
"learning_rate": 0.0007424511545293073,
|
| 1330 |
+
"loss": 0.4805,
|
| 1331 |
+
"step": 1950
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 3.2,
|
| 1335 |
+
"learning_rate": 0.0007406749555950266,
|
| 1336 |
+
"loss": 0.4818,
|
| 1337 |
+
"step": 1960
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 3.21,
|
| 1341 |
+
"learning_rate": 0.000738898756660746,
|
| 1342 |
+
"loss": 0.4921,
|
| 1343 |
+
"step": 1970
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 3.23,
|
| 1347 |
+
"learning_rate": 0.0007371225577264654,
|
| 1348 |
+
"loss": 0.4601,
|
| 1349 |
+
"step": 1980
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 3.25,
|
| 1353 |
+
"learning_rate": 0.0007353463587921847,
|
| 1354 |
+
"loss": 0.4771,
|
| 1355 |
+
"step": 1990
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 3.26,
|
| 1359 |
+
"learning_rate": 0.000733570159857904,
|
| 1360 |
+
"loss": 0.4487,
|
| 1361 |
+
"step": 2000
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.26,
|
| 1365 |
+
"eval_loss": 0.46053341031074524,
|
| 1366 |
+
"eval_runtime": 12.936,
|
| 1367 |
+
"eval_samples_per_second": 90.523,
|
| 1368 |
+
"eval_steps_per_second": 11.364,
|
| 1369 |
+
"step": 2000
|
| 1370 |
}
|
| 1371 |
],
|
| 1372 |
"logging_steps": 10,
|
| 1373 |
"max_steps": 6130,
|
| 1374 |
"num_train_epochs": 10,
|
| 1375 |
"save_steps": 500,
|
| 1376 |
+
"total_flos": 3778253218971648.0,
|
| 1377 |
"trial_name": null,
|
| 1378 |
"trial_params": null
|
| 1379 |
}
|