Training in progress, step 200, 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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cca0763314b6ac58ff911dcf89feba9ed2cc8009f03bb85b12c6093ac371b123
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342555602
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b4f394075a906b7a569036ad998d8d9a2b1831ef3b0c740fa4a780322c4c460
|
3 |
size 1342555602
|
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:cfecc7e99c93737d03d65a1847e09288204cca112bfa8365aa6aad68e24286b3
|
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:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.856124222278595,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
4 |
-
"epoch":
|
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": 11.541,
|
1090 |
"eval_steps_per_second": 5.792,
|
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": 8,
|
1122 |
"trial_name": null,
|
1123 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.856124222278595,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
4 |
+
"epoch": 1.2738853503184713,
|
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": 11.541,
|
1090 |
"eval_steps_per_second": 5.792,
|
1091 |
"step": 150
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 0.9617834394904459,
|
1095 |
+
"grad_norm": 23.63081932067871,
|
1096 |
+
"learning_rate": 1.7197048550474643e-05,
|
1097 |
+
"loss": 4.073,
|
1098 |
+
"step": 151
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.9681528662420382,
|
1102 |
+
"grad_norm": 19.112306594848633,
|
1103 |
+
"learning_rate": 1.6543469682057106e-05,
|
1104 |
+
"loss": 3.6236,
|
1105 |
+
"step": 152
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.9745222929936306,
|
1109 |
+
"grad_norm": 31.241661071777344,
|
1110 |
+
"learning_rate": 1.5900081996875083e-05,
|
1111 |
+
"loss": 3.0811,
|
1112 |
+
"step": 153
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.9808917197452229,
|
1116 |
+
"grad_norm": 22.64638328552246,
|
1117 |
+
"learning_rate": 1.526708147705013e-05,
|
1118 |
+
"loss": 2.9199,
|
1119 |
+
"step": 154
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.9872611464968153,
|
1123 |
+
"grad_norm": 27.255001068115234,
|
1124 |
+
"learning_rate": 1.4644660940672627e-05,
|
1125 |
+
"loss": 2.6116,
|
1126 |
+
"step": 155
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 0.9936305732484076,
|
1130 |
+
"grad_norm": 66.21800231933594,
|
1131 |
+
"learning_rate": 1.4033009983067452e-05,
|
1132 |
+
"loss": 4.2625,
|
1133 |
+
"step": 156
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 1.0,
|
1137 |
+
"grad_norm": 24.99510383605957,
|
1138 |
+
"learning_rate": 1.3432314919041478e-05,
|
1139 |
+
"loss": 4.1692,
|
1140 |
+
"step": 157
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 1.0063694267515924,
|
1144 |
+
"grad_norm": 3.7077722549438477,
|
1145 |
+
"learning_rate": 1.2842758726130283e-05,
|
1146 |
+
"loss": 2.7945,
|
1147 |
+
"step": 158
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 1.0127388535031847,
|
1151 |
+
"grad_norm": 3.5477285385131836,
|
1152 |
+
"learning_rate": 1.22645209888614e-05,
|
1153 |
+
"loss": 2.4028,
|
1154 |
+
"step": 159
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 1.019108280254777,
|
1158 |
+
"grad_norm": 4.283918857574463,
|
1159 |
+
"learning_rate": 1.1697777844051105e-05,
|
1160 |
+
"loss": 3.1117,
|
1161 |
+
"step": 160
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.0254777070063694,
|
1165 |
+
"grad_norm": 3.8144969940185547,
|
1166 |
+
"learning_rate": 1.1142701927151456e-05,
|
1167 |
+
"loss": 2.6418,
|
1168 |
+
"step": 161
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 1.0318471337579618,
|
1172 |
+
"grad_norm": 4.030559539794922,
|
1173 |
+
"learning_rate": 1.0599462319663905e-05,
|
1174 |
+
"loss": 2.377,
|
1175 |
+
"step": 162
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 1.0382165605095541,
|
1179 |
+
"grad_norm": 4.541848659515381,
|
1180 |
+
"learning_rate": 1.006822449763537e-05,
|
1181 |
+
"loss": 2.5533,
|
1182 |
+
"step": 163
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 1.0445859872611465,
|
1186 |
+
"grad_norm": 4.711845874786377,
|
1187 |
+
"learning_rate": 9.549150281252633e-06,
|
1188 |
+
"loss": 2.4903,
|
1189 |
+
"step": 164
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 1.0509554140127388,
|
1193 |
+
"grad_norm": 4.770325183868408,
|
1194 |
+
"learning_rate": 9.042397785550405e-06,
|
1195 |
+
"loss": 2.6872,
|
1196 |
+
"step": 165
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 1.0573248407643312,
|
1200 |
+
"grad_norm": 4.293312072753906,
|
1201 |
+
"learning_rate": 8.548121372247918e-06,
|
1202 |
+
"loss": 1.9581,
|
1203 |
+
"step": 166
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.0636942675159236,
|
1207 |
+
"grad_norm": 5.336209297180176,
|
1208 |
+
"learning_rate": 8.066471602728803e-06,
|
1209 |
+
"loss": 2.0512,
|
1210 |
+
"step": 167
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 1.070063694267516,
|
1214 |
+
"grad_norm": 5.297292232513428,
|
1215 |
+
"learning_rate": 7.597595192178702e-06,
|
1216 |
+
"loss": 2.6065,
|
1217 |
+
"step": 168
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 1.0764331210191083,
|
1221 |
+
"grad_norm": 4.493692874908447,
|
1222 |
+
"learning_rate": 7.1416349648943894e-06,
|
1223 |
+
"loss": 1.8749,
|
1224 |
+
"step": 169
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 1.0828025477707006,
|
1228 |
+
"grad_norm": 5.324576377868652,
|
1229 |
+
"learning_rate": 6.698729810778065e-06,
|
1230 |
+
"loss": 2.1537,
|
1231 |
+
"step": 170
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 1.089171974522293,
|
1235 |
+
"grad_norm": 5.945623874664307,
|
1236 |
+
"learning_rate": 6.269014643030213e-06,
|
1237 |
+
"loss": 2.3464,
|
1238 |
+
"step": 171
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 1.0955414012738853,
|
1242 |
+
"grad_norm": 5.990110397338867,
|
1243 |
+
"learning_rate": 5.852620357053651e-06,
|
1244 |
+
"loss": 2.1652,
|
1245 |
+
"step": 172
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.1019108280254777,
|
1249 |
+
"grad_norm": 5.564594745635986,
|
1250 |
+
"learning_rate": 5.449673790581611e-06,
|
1251 |
+
"loss": 1.9364,
|
1252 |
+
"step": 173
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 1.10828025477707,
|
1256 |
+
"grad_norm": 6.395089149475098,
|
1257 |
+
"learning_rate": 5.060297685041659e-06,
|
1258 |
+
"loss": 2.3456,
|
1259 |
+
"step": 174
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 1.1146496815286624,
|
1263 |
+
"grad_norm": 6.796019554138184,
|
1264 |
+
"learning_rate": 4.684610648167503e-06,
|
1265 |
+
"loss": 2.09,
|
1266 |
+
"step": 175
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 1.1210191082802548,
|
1270 |
+
"grad_norm": 7.000392913818359,
|
1271 |
+
"learning_rate": 4.322727117869951e-06,
|
1272 |
+
"loss": 2.333,
|
1273 |
+
"step": 176
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 1.127388535031847,
|
1277 |
+
"grad_norm": 6.889556407928467,
|
1278 |
+
"learning_rate": 3.974757327377981e-06,
|
1279 |
+
"loss": 1.5809,
|
1280 |
+
"step": 177
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.1337579617834395,
|
1284 |
+
"grad_norm": 7.113092422485352,
|
1285 |
+
"learning_rate": 3.6408072716606346e-06,
|
1286 |
+
"loss": 2.0368,
|
1287 |
+
"step": 178
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.1401273885350318,
|
1291 |
+
"grad_norm": 6.891910552978516,
|
1292 |
+
"learning_rate": 3.3209786751399187e-06,
|
1293 |
+
"loss": 1.5373,
|
1294 |
+
"step": 179
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 1.1464968152866242,
|
1298 |
+
"grad_norm": 10.173569679260254,
|
1299 |
+
"learning_rate": 3.0153689607045845e-06,
|
1300 |
+
"loss": 1.9954,
|
1301 |
+
"step": 180
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 1.1528662420382165,
|
1305 |
+
"grad_norm": 7.4136061668396,
|
1306 |
+
"learning_rate": 2.724071220034158e-06,
|
1307 |
+
"loss": 1.5246,
|
1308 |
+
"step": 181
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 1.1592356687898089,
|
1312 |
+
"grad_norm": 8.997750282287598,
|
1313 |
+
"learning_rate": 2.4471741852423237e-06,
|
1314 |
+
"loss": 2.0869,
|
1315 |
+
"step": 182
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 1.1656050955414012,
|
1319 |
+
"grad_norm": 9.356908798217773,
|
1320 |
+
"learning_rate": 2.1847622018482283e-06,
|
1321 |
+
"loss": 2.0526,
|
1322 |
+
"step": 183
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 1.1719745222929936,
|
1326 |
+
"grad_norm": 10.576266288757324,
|
1327 |
+
"learning_rate": 1.9369152030840556e-06,
|
1328 |
+
"loss": 2.0726,
|
1329 |
+
"step": 184
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.178343949044586,
|
1333 |
+
"grad_norm": 10.605173110961914,
|
1334 |
+
"learning_rate": 1.70370868554659e-06,
|
1335 |
+
"loss": 1.7944,
|
1336 |
+
"step": 185
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 1.1847133757961783,
|
1340 |
+
"grad_norm": 9.885431289672852,
|
1341 |
+
"learning_rate": 1.4852136862001764e-06,
|
1342 |
+
"loss": 1.732,
|
1343 |
+
"step": 186
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 1.1910828025477707,
|
1347 |
+
"grad_norm": 10.850882530212402,
|
1348 |
+
"learning_rate": 1.2814967607382432e-06,
|
1349 |
+
"loss": 2.0103,
|
1350 |
+
"step": 187
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 1.197452229299363,
|
1354 |
+
"grad_norm": 10.830645561218262,
|
1355 |
+
"learning_rate": 1.0926199633097157e-06,
|
1356 |
+
"loss": 1.9147,
|
1357 |
+
"step": 188
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 1.2038216560509554,
|
1361 |
+
"grad_norm": 14.65571117401123,
|
1362 |
+
"learning_rate": 9.186408276168013e-07,
|
1363 |
+
"loss": 2.0657,
|
1364 |
+
"step": 189
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 1.2101910828025477,
|
1368 |
+
"grad_norm": 10.46584701538086,
|
1369 |
+
"learning_rate": 7.596123493895991e-07,
|
1370 |
+
"loss": 1.7092,
|
1371 |
+
"step": 190
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.21656050955414,
|
1375 |
+
"grad_norm": 11.583234786987305,
|
1376 |
+
"learning_rate": 6.15582970243117e-07,
|
1377 |
+
"loss": 1.5889,
|
1378 |
+
"step": 191
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 1.2229299363057324,
|
1382 |
+
"grad_norm": 19.2625732421875,
|
1383 |
+
"learning_rate": 4.865965629214819e-07,
|
1384 |
+
"loss": 1.8016,
|
1385 |
+
"step": 192
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.2292993630573248,
|
1389 |
+
"grad_norm": 13.321444511413574,
|
1390 |
+
"learning_rate": 3.7269241793390085e-07,
|
1391 |
+
"loss": 1.3804,
|
1392 |
+
"step": 193
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 1.2356687898089171,
|
1396 |
+
"grad_norm": 13.012649536132812,
|
1397 |
+
"learning_rate": 2.7390523158633554e-07,
|
1398 |
+
"loss": 1.2135,
|
1399 |
+
"step": 194
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 1.2420382165605095,
|
1403 |
+
"grad_norm": 17.863269805908203,
|
1404 |
+
"learning_rate": 1.9026509541272275e-07,
|
1405 |
+
"loss": 1.7409,
|
1406 |
+
"step": 195
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 1.2484076433121019,
|
1410 |
+
"grad_norm": 30.971969604492188,
|
1411 |
+
"learning_rate": 1.2179748700879012e-07,
|
1412 |
+
"loss": 1.8244,
|
1413 |
+
"step": 196
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.2547770700636942,
|
1417 |
+
"grad_norm": 4.519101619720459,
|
1418 |
+
"learning_rate": 6.852326227130834e-08,
|
1419 |
+
"loss": 2.9923,
|
1420 |
+
"step": 197
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.2611464968152866,
|
1424 |
+
"grad_norm": 4.492830753326416,
|
1425 |
+
"learning_rate": 3.04586490452119e-08,
|
1426 |
+
"loss": 2.6286,
|
1427 |
+
"step": 198
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 1.267515923566879,
|
1431 |
+
"grad_norm": 4.864869117736816,
|
1432 |
+
"learning_rate": 7.615242180436522e-09,
|
1433 |
+
"loss": 2.9949,
|
1434 |
+
"step": 199
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.2738853503184713,
|
1438 |
+
"grad_norm": 4.6130547523498535,
|
1439 |
+
"learning_rate": 0.0,
|
1440 |
+
"loss": 2.3603,
|
1441 |
+
"step": 200
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.2738853503184713,
|
1445 |
+
"eval_loss": 0.8630052804946899,
|
1446 |
+
"eval_runtime": 22.948,
|
1447 |
+
"eval_samples_per_second": 11.548,
|
1448 |
+
"eval_steps_per_second": 5.796,
|
1449 |
+
"step": 200
|
1450 |
}
|
1451 |
],
|
1452 |
"logging_steps": 1,
|
|
|
1461 |
"early_stopping_threshold": 0.0
|
1462 |
},
|
1463 |
"attributes": {
|
1464 |
+
"early_stopping_patience_counter": 1
|
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": 3.04485205706539e+17,
|
1479 |
"train_batch_size": 8,
|
1480 |
"trial_name": null,
|
1481 |
"trial_params": null
|