Training in progress, step 200, 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 170920084
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f021d9cd9dfd12da089448e21009ac0b61f8ac240a6a3a2867ea53f010c0eda
|
| 3 |
size 170920084
|
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 sha256:9c8081fa60a4153bcb69fbad880732661ab9f02ca083ca47026b464e7d914161
|
| 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:b60d6f1383abda4776549360effee800fe6cfe2c0604503e9e3fbaa79347f790
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 10.017,
|
| 1090 |
"eval_steps_per_second": 2.507,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1103,7 +1461,7 @@
|
|
| 1103 |
"early_stopping_threshold": 0.0
|
| 1104 |
},
|
| 1105 |
"attributes": {
|
| 1106 |
-
"early_stopping_patience_counter":
|
| 1107 |
}
|
| 1108 |
},
|
| 1109 |
"TrainerControl": {
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": NaN,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.09918175055789735,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 10.017,
|
| 1090 |
"eval_steps_per_second": 2.507,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.0748822216712125,
|
| 1095 |
+
"grad_norm": NaN,
|
| 1096 |
+
"learning_rate": 1.339526225485725e-05,
|
| 1097 |
+
"loss": 0.0,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.07537813042400199,
|
| 1102 |
+
"grad_norm": NaN,
|
| 1103 |
+
"learning_rate": 1.2890114781136224e-05,
|
| 1104 |
+
"loss": 0.0,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.07587403917679147,
|
| 1109 |
+
"grad_norm": NaN,
|
| 1110 |
+
"learning_rate": 1.239251781296245e-05,
|
| 1111 |
+
"loss": 0.0,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.07636994792958096,
|
| 1116 |
+
"grad_norm": NaN,
|
| 1117 |
+
"learning_rate": 1.1902641279244715e-05,
|
| 1118 |
+
"loss": 0.0,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.07686585668237045,
|
| 1123 |
+
"grad_norm": NaN,
|
| 1124 |
+
"learning_rate": 1.1420652472370497e-05,
|
| 1125 |
+
"loss": 0.0,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.07736176543515993,
|
| 1130 |
+
"grad_norm": NaN,
|
| 1131 |
+
"learning_rate": 1.0946715991075805e-05,
|
| 1132 |
+
"loss": 0.0,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.07785767418794942,
|
| 1137 |
+
"grad_norm": NaN,
|
| 1138 |
+
"learning_rate": 1.0480993684234815e-05,
|
| 1139 |
+
"loss": 0.0,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.07835358294073891,
|
| 1144 |
+
"grad_norm": NaN,
|
| 1145 |
+
"learning_rate": 1.0023644595588671e-05,
|
| 1146 |
+
"loss": 0.0,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.0788494916935284,
|
| 1151 |
+
"grad_norm": NaN,
|
| 1152 |
+
"learning_rate": 9.57482490943216e-06,
|
| 1153 |
+
"loss": 0.0,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.07934540044631788,
|
| 1158 |
+
"grad_norm": NaN,
|
| 1159 |
+
"learning_rate": 9.134687897276934e-06,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.07984130919910737,
|
| 1165 |
+
"grad_norm": NaN,
|
| 1166 |
+
"learning_rate": 8.703383865509432e-06,
|
| 1167 |
+
"loss": 0.0,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.08033721795189686,
|
| 1172 |
+
"grad_norm": NaN,
|
| 1173 |
+
"learning_rate": 8.281060104061394e-06,
|
| 1174 |
+
"loss": 0.0,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.08083312670468634,
|
| 1179 |
+
"grad_norm": NaN,
|
| 1180 |
+
"learning_rate": 7.867860836110453e-06,
|
| 1181 |
+
"loss": 0.0,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.08132903545747583,
|
| 1186 |
+
"grad_norm": NaN,
|
| 1187 |
+
"learning_rate": 7.463927168828087e-06,
|
| 1188 |
+
"loss": 0.0,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.08182494421026532,
|
| 1193 |
+
"grad_norm": NaN,
|
| 1194 |
+
"learning_rate": 7.069397045191617e-06,
|
| 1195 |
+
"loss": 0.0,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.0823208529630548,
|
| 1200 |
+
"grad_norm": NaN,
|
| 1201 |
+
"learning_rate": 6.684405196876842e-06,
|
| 1202 |
+
"loss": 0.0,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.08281676171584429,
|
| 1207 |
+
"grad_norm": NaN,
|
| 1208 |
+
"learning_rate": 6.309083098247264e-06,
|
| 1209 |
+
"loss": 0.0,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.08331267046863378,
|
| 1214 |
+
"grad_norm": NaN,
|
| 1215 |
+
"learning_rate": 5.943558921455733e-06,
|
| 1216 |
+
"loss": 0.0,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.08380857922142326,
|
| 1221 |
+
"grad_norm": NaN,
|
| 1222 |
+
"learning_rate": 5.587957492673759e-06,
|
| 1223 |
+
"loss": 3.2668,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.08430448797421275,
|
| 1228 |
+
"grad_norm": NaN,
|
| 1229 |
+
"learning_rate": 5.2424002494635095e-06,
|
| 1230 |
+
"loss": 50.263,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.08480039672700224,
|
| 1235 |
+
"grad_norm": NaN,
|
| 1236 |
+
"learning_rate": 4.9070051993069636e-06,
|
| 1237 |
+
"loss": 0.0,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.08529630547979172,
|
| 1242 |
+
"grad_norm": NaN,
|
| 1243 |
+
"learning_rate": 4.581886879306507e-06,
|
| 1244 |
+
"loss": 0.0,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.08579221423258121,
|
| 1249 |
+
"grad_norm": NaN,
|
| 1250 |
+
"learning_rate": 4.2671563170705725e-06,
|
| 1251 |
+
"loss": 0.0,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0862881229853707,
|
| 1256 |
+
"grad_norm": NaN,
|
| 1257 |
+
"learning_rate": 3.962920992797834e-06,
|
| 1258 |
+
"loss": 0.0,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.08678403173816018,
|
| 1263 |
+
"grad_norm": NaN,
|
| 1264 |
+
"learning_rate": 3.6692848025728216e-06,
|
| 1265 |
+
"loss": 0.0,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.08727994049094967,
|
| 1270 |
+
"grad_norm": NaN,
|
| 1271 |
+
"learning_rate": 3.38634802288549e-06,
|
| 1272 |
+
"loss": 0.0,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.08777584924373916,
|
| 1277 |
+
"grad_norm": NaN,
|
| 1278 |
+
"learning_rate": 3.1142072763869042e-06,
|
| 1279 |
+
"loss": 0.0,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.08827175799652864,
|
| 1284 |
+
"grad_norm": NaN,
|
| 1285 |
+
"learning_rate": 2.852955498892694e-06,
|
| 1286 |
+
"loss": 0.0,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.08876766674931813,
|
| 1291 |
+
"grad_norm": NaN,
|
| 1292 |
+
"learning_rate": 2.6026819076455325e-06,
|
| 1293 |
+
"loss": 0.0,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.08926357550210762,
|
| 1298 |
+
"grad_norm": NaN,
|
| 1299 |
+
"learning_rate": 2.36347197084755e-06,
|
| 1300 |
+
"loss": 0.0,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0897594842548971,
|
| 1305 |
+
"grad_norm": NaN,
|
| 1306 |
+
"learning_rate": 2.1354073784730253e-06,
|
| 1307 |
+
"loss": 0.0,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.09025539300768659,
|
| 1312 |
+
"grad_norm": NaN,
|
| 1313 |
+
"learning_rate": 1.9185660143713184e-06,
|
| 1314 |
+
"loss": 0.0,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.09075130176047608,
|
| 1319 |
+
"grad_norm": NaN,
|
| 1320 |
+
"learning_rate": 1.7130219296696263e-06,
|
| 1321 |
+
"loss": 0.0,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.09124721051326556,
|
| 1326 |
+
"grad_norm": NaN,
|
| 1327 |
+
"learning_rate": 1.5188453174845743e-06,
|
| 1328 |
+
"loss": 0.0,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.09174311926605505,
|
| 1333 |
+
"grad_norm": NaN,
|
| 1334 |
+
"learning_rate": 1.3361024889513333e-06,
|
| 1335 |
+
"loss": 0.0,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.09223902801884454,
|
| 1340 |
+
"grad_norm": NaN,
|
| 1341 |
+
"learning_rate": 1.16485585057844e-06,
|
| 1342 |
+
"loss": 0.0,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.09273493677163402,
|
| 1347 |
+
"grad_norm": NaN,
|
| 1348 |
+
"learning_rate": 1.0051638829360127e-06,
|
| 1349 |
+
"loss": 0.0,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.09323084552442351,
|
| 1354 |
+
"grad_norm": NaN,
|
| 1355 |
+
"learning_rate": 8.570811206847189e-07,
|
| 1356 |
+
"loss": 0.0,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.093726754277213,
|
| 1361 |
+
"grad_norm": NaN,
|
| 1362 |
+
"learning_rate": 7.206581339521939e-07,
|
| 1363 |
+
"loss": 0.0,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.09422266303000248,
|
| 1368 |
+
"grad_norm": NaN,
|
| 1369 |
+
"learning_rate": 5.959415110634375e-07,
|
| 1370 |
+
"loss": 0.0,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.09471857178279197,
|
| 1375 |
+
"grad_norm": NaN,
|
| 1376 |
+
"learning_rate": 4.829738426309099e-07,
|
| 1377 |
+
"loss": 0.0,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.09521448053558146,
|
| 1382 |
+
"grad_norm": NaN,
|
| 1383 |
+
"learning_rate": 3.817937070098914e-07,
|
| 1384 |
+
"loss": 0.0,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.09571038928837095,
|
| 1389 |
+
"grad_norm": NaN,
|
| 1390 |
+
"learning_rate": 2.9243565712400384e-07,
|
| 1391 |
+
"loss": 0.0,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.09620629804116043,
|
| 1396 |
+
"grad_norm": NaN,
|
| 1397 |
+
"learning_rate": 2.1493020866542365e-07,
|
| 1398 |
+
"loss": 0.0,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.09670220679394992,
|
| 1403 |
+
"grad_norm": NaN,
|
| 1404 |
+
"learning_rate": 1.4930382967379363e-07,
|
| 1405 |
+
"loss": 0.0,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.0971981155467394,
|
| 1410 |
+
"grad_norm": NaN,
|
| 1411 |
+
"learning_rate": 9.557893149741924e-08,
|
| 1412 |
+
"loss": 0.0,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.09769402429952889,
|
| 1417 |
+
"grad_norm": NaN,
|
| 1418 |
+
"learning_rate": 5.377386113981197e-08,
|
| 1419 |
+
"loss": 0.0,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.09818993305231838,
|
| 1424 |
+
"grad_norm": NaN,
|
| 1425 |
+
"learning_rate": 2.3902894994198286e-08,
|
| 1426 |
+
"loss": 0.0,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.09868584180510787,
|
| 1431 |
+
"grad_norm": NaN,
|
| 1432 |
+
"learning_rate": 5.976233968155164e-09,
|
| 1433 |
+
"loss": 0.0,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.09918175055789735,
|
| 1438 |
+
"grad_norm": NaN,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.0,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.09918175055789735,
|
| 1445 |
+
"eval_loss": NaN,
|
| 1446 |
+
"eval_runtime": 338.2367,
|
| 1447 |
+
"eval_samples_per_second": 10.043,
|
| 1448 |
+
"eval_steps_per_second": 2.513,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1461 |
"early_stopping_threshold": 0.0
|
| 1462 |
},
|
| 1463 |
"attributes": {
|
| 1464 |
+
"early_stopping_patience_counter": 3
|
| 1465 |
}
|
| 1466 |
},
|
| 1467 |
"TrainerControl": {
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 3.875744616724562e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|