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 50503544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad8cc488a4232e4bb07af21caf9a5a9828012025c962a32082570728e12ff8cf
|
3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 101184122
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dee48ebb34e2b388c1c2e22a54461c621e0d1c6acbf2c0c55f122693393c56b5
|
3 |
size 101184122
|
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:eecbe6db51533f74a58d571c69110b223d4abb6bcb19d1ad0d04af620a680663
|
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:fe157715eb8e05b3bab2a7f2fafac33705dc4a1a9dd7f6d860c3a7f9597d78bb
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1113,6 +1113,372 @@
|
|
1113 |
"eval_samples_per_second": 31.468,
|
1114 |
"eval_steps_per_second": 4.406,
|
1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1116 |
}
|
1117 |
],
|
1118 |
"logging_steps": 1,
|
@@ -1136,12 +1502,12 @@
|
|
1136 |
"should_evaluate": false,
|
1137 |
"should_log": false,
|
1138 |
"should_save": true,
|
1139 |
-
"should_training_stop":
|
1140 |
},
|
1141 |
"attributes": {}
|
1142 |
}
|
1143 |
},
|
1144 |
-
"total_flos":
|
1145 |
"train_batch_size": 8,
|
1146 |
"trial_name": null,
|
1147 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4162873327732086,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
4 |
+
"epoch": 0.2845962290999644,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1113 |
"eval_samples_per_second": 31.468,
|
1114 |
"eval_steps_per_second": 4.406,
|
1115 |
"step": 150
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.21487015297047315,
|
1119 |
+
"grad_norm": 0.6226702332496643,
|
1120 |
+
"learning_rate": 4.659698863221513e-05,
|
1121 |
+
"loss": 0.4393,
|
1122 |
+
"step": 151
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.21629313411597295,
|
1126 |
+
"grad_norm": 0.6401143670082092,
|
1127 |
+
"learning_rate": 4.481448235912671e-05,
|
1128 |
+
"loss": 0.633,
|
1129 |
+
"step": 152
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.21771611526147278,
|
1133 |
+
"grad_norm": 0.49035051465034485,
|
1134 |
+
"learning_rate": 4.306073275629044e-05,
|
1135 |
+
"loss": 0.4039,
|
1136 |
+
"step": 153
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.2191390964069726,
|
1140 |
+
"grad_norm": 0.5134478807449341,
|
1141 |
+
"learning_rate": 4.133621928133665e-05,
|
1142 |
+
"loss": 0.3892,
|
1143 |
+
"step": 154
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.22056207755247242,
|
1147 |
+
"grad_norm": 0.4497911334037781,
|
1148 |
+
"learning_rate": 3.964141339903026e-05,
|
1149 |
+
"loss": 0.3839,
|
1150 |
+
"step": 155
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.22198505869797225,
|
1154 |
+
"grad_norm": 0.572187602519989,
|
1155 |
+
"learning_rate": 3.797677845237696e-05,
|
1156 |
+
"loss": 0.3897,
|
1157 |
+
"step": 156
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.22340803984347207,
|
1161 |
+
"grad_norm": 0.5317263007164001,
|
1162 |
+
"learning_rate": 3.634276953594982e-05,
|
1163 |
+
"loss": 0.4003,
|
1164 |
+
"step": 157
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.2248310209889719,
|
1168 |
+
"grad_norm": 0.4672944247722626,
|
1169 |
+
"learning_rate": 3.473983337147118e-05,
|
1170 |
+
"loss": 0.3659,
|
1171 |
+
"step": 158
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.22625400213447172,
|
1175 |
+
"grad_norm": 0.42732876539230347,
|
1176 |
+
"learning_rate": 3.316840818568315e-05,
|
1177 |
+
"loss": 0.3495,
|
1178 |
+
"step": 159
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.22767698327997155,
|
1182 |
+
"grad_norm": 0.48700952529907227,
|
1183 |
+
"learning_rate": 3.162892359054098e-05,
|
1184 |
+
"loss": 0.4266,
|
1185 |
+
"step": 160
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.22909996442547137,
|
1189 |
+
"grad_norm": 0.4742146134376526,
|
1190 |
+
"learning_rate": 3.0121800465761293e-05,
|
1191 |
+
"loss": 0.3789,
|
1192 |
+
"step": 161
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.2305229455709712,
|
1196 |
+
"grad_norm": 0.46112704277038574,
|
1197 |
+
"learning_rate": 2.8647450843757897e-05,
|
1198 |
+
"loss": 0.3756,
|
1199 |
+
"step": 162
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.23194592671647102,
|
1203 |
+
"grad_norm": 0.45304158329963684,
|
1204 |
+
"learning_rate": 2.7206277796996144e-05,
|
1205 |
+
"loss": 0.4077,
|
1206 |
+
"step": 163
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.23336890786197084,
|
1210 |
+
"grad_norm": 0.47427666187286377,
|
1211 |
+
"learning_rate": 2.5798675327796993e-05,
|
1212 |
+
"loss": 0.3493,
|
1213 |
+
"step": 164
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.23479188900747064,
|
1217 |
+
"grad_norm": 0.4082260727882385,
|
1218 |
+
"learning_rate": 2.4425028260620715e-05,
|
1219 |
+
"loss": 0.3632,
|
1220 |
+
"step": 165
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.23621487015297046,
|
1224 |
+
"grad_norm": 0.517911970615387,
|
1225 |
+
"learning_rate": 2.3085712136859668e-05,
|
1226 |
+
"loss": 0.4325,
|
1227 |
+
"step": 166
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.2376378512984703,
|
1231 |
+
"grad_norm": 0.4603246748447418,
|
1232 |
+
"learning_rate": 2.178109311216913e-05,
|
1233 |
+
"loss": 0.3829,
|
1234 |
+
"step": 167
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.2390608324439701,
|
1238 |
+
"grad_norm": 0.5936574935913086,
|
1239 |
+
"learning_rate": 2.0511527856363912e-05,
|
1240 |
+
"loss": 0.4366,
|
1241 |
+
"step": 168
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.24048381358946994,
|
1245 |
+
"grad_norm": 0.47505584359169006,
|
1246 |
+
"learning_rate": 1.927736345590839e-05,
|
1247 |
+
"loss": 0.3416,
|
1248 |
+
"step": 169
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.24190679473496976,
|
1252 |
+
"grad_norm": 0.4642045199871063,
|
1253 |
+
"learning_rate": 1.8078937319026654e-05,
|
1254 |
+
"loss": 0.3977,
|
1255 |
+
"step": 170
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.24332977588046958,
|
1259 |
+
"grad_norm": 0.4804611802101135,
|
1260 |
+
"learning_rate": 1.6916577083458228e-05,
|
1261 |
+
"loss": 0.4259,
|
1262 |
+
"step": 171
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.2447527570259694,
|
1266 |
+
"grad_norm": 0.4980257749557495,
|
1267 |
+
"learning_rate": 1.579060052688548e-05,
|
1268 |
+
"loss": 0.3874,
|
1269 |
+
"step": 172
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.24617573817146923,
|
1273 |
+
"grad_norm": 0.42624157667160034,
|
1274 |
+
"learning_rate": 1.4701315480056164e-05,
|
1275 |
+
"loss": 0.3618,
|
1276 |
+
"step": 173
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.24759871931696906,
|
1280 |
+
"grad_norm": 0.4734053611755371,
|
1281 |
+
"learning_rate": 1.3649019742625623e-05,
|
1282 |
+
"loss": 0.3711,
|
1283 |
+
"step": 174
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.24902170046246888,
|
1287 |
+
"grad_norm": 0.42860615253448486,
|
1288 |
+
"learning_rate": 1.2634001001741373e-05,
|
1289 |
+
"loss": 0.3982,
|
1290 |
+
"step": 175
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.24902170046246888,
|
1294 |
+
"eval_loss": 0.41627341508865356,
|
1295 |
+
"eval_runtime": 1.5905,
|
1296 |
+
"eval_samples_per_second": 31.436,
|
1297 |
+
"eval_steps_per_second": 4.401,
|
1298 |
+
"step": 175
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.2504446816079687,
|
1302 |
+
"grad_norm": 0.5777260661125183,
|
1303 |
+
"learning_rate": 1.1656536753392287e-05,
|
1304 |
+
"loss": 0.4148,
|
1305 |
+
"step": 176
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.2518676627534685,
|
1309 |
+
"grad_norm": 0.4316408932209015,
|
1310 |
+
"learning_rate": 1.0716894226543953e-05,
|
1311 |
+
"loss": 0.4256,
|
1312 |
+
"step": 177
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.2532906438989683,
|
1316 |
+
"grad_norm": 0.402228981256485,
|
1317 |
+
"learning_rate": 9.815330310080887e-06,
|
1318 |
+
"loss": 0.3952,
|
1319 |
+
"step": 178
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.25471362504446815,
|
1323 |
+
"grad_norm": 0.49347391724586487,
|
1324 |
+
"learning_rate": 8.952091482575824e-06,
|
1325 |
+
"loss": 0.4133,
|
1326 |
+
"step": 179
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.256136606189968,
|
1330 |
+
"grad_norm": 0.5483438372612,
|
1331 |
+
"learning_rate": 8.127413744904804e-06,
|
1332 |
+
"loss": 0.398,
|
1333 |
+
"step": 180
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.2575595873354678,
|
1337 |
+
"grad_norm": 0.3619908094406128,
|
1338 |
+
"learning_rate": 7.34152255572697e-06,
|
1339 |
+
"loss": 0.347,
|
1340 |
+
"step": 181
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.2589825684809676,
|
1344 |
+
"grad_norm": 0.521479070186615,
|
1345 |
+
"learning_rate": 6.594632769846353e-06,
|
1346 |
+
"loss": 0.419,
|
1347 |
+
"step": 182
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.26040554962646745,
|
1351 |
+
"grad_norm": 0.3947046995162964,
|
1352 |
+
"learning_rate": 5.886948579472778e-06,
|
1353 |
+
"loss": 0.3599,
|
1354 |
+
"step": 183
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.26182853077196727,
|
1358 |
+
"grad_norm": 0.41507527232170105,
|
1359 |
+
"learning_rate": 5.218663458397715e-06,
|
1360 |
+
"loss": 0.3696,
|
1361 |
+
"step": 184
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.2632515119174671,
|
1365 |
+
"grad_norm": 0.4486597180366516,
|
1366 |
+
"learning_rate": 4.589960109100444e-06,
|
1367 |
+
"loss": 0.3821,
|
1368 |
+
"step": 185
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.2646744930629669,
|
1372 |
+
"grad_norm": 0.463120698928833,
|
1373 |
+
"learning_rate": 4.001010412799138e-06,
|
1374 |
+
"loss": 0.4136,
|
1375 |
+
"step": 186
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.26609747420846674,
|
1379 |
+
"grad_norm": 0.49710506200790405,
|
1380 |
+
"learning_rate": 3.451975382460109e-06,
|
1381 |
+
"loss": 0.43,
|
1382 |
+
"step": 187
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.26752045535396657,
|
1386 |
+
"grad_norm": 0.4926173985004425,
|
1387 |
+
"learning_rate": 2.9430051187785962e-06,
|
1388 |
+
"loss": 0.406,
|
1389 |
+
"step": 188
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.2689434364994664,
|
1393 |
+
"grad_norm": 0.5663373470306396,
|
1394 |
+
"learning_rate": 2.4742387691426445e-06,
|
1395 |
+
"loss": 0.4088,
|
1396 |
+
"step": 189
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.2703664176449662,
|
1400 |
+
"grad_norm": 0.536439836025238,
|
1401 |
+
"learning_rate": 2.0458044895916513e-06,
|
1402 |
+
"loss": 0.46,
|
1403 |
+
"step": 190
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.27178939879046604,
|
1407 |
+
"grad_norm": 0.44043686985969543,
|
1408 |
+
"learning_rate": 1.6578194097797258e-06,
|
1409 |
+
"loss": 0.3958,
|
1410 |
+
"step": 191
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.27321237993596587,
|
1414 |
+
"grad_norm": 0.5519529581069946,
|
1415 |
+
"learning_rate": 1.3103896009537207e-06,
|
1416 |
+
"loss": 0.4312,
|
1417 |
+
"step": 192
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.2746353610814657,
|
1421 |
+
"grad_norm": 0.5283083915710449,
|
1422 |
+
"learning_rate": 1.0036100469542786e-06,
|
1423 |
+
"loss": 0.4127,
|
1424 |
+
"step": 193
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.2760583422269655,
|
1428 |
+
"grad_norm": 0.4783058166503906,
|
1429 |
+
"learning_rate": 7.375646182482875e-07,
|
1430 |
+
"loss": 0.4041,
|
1431 |
+
"step": 194
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.27748132337246534,
|
1435 |
+
"grad_norm": 0.45658767223358154,
|
1436 |
+
"learning_rate": 5.123260489995229e-07,
|
1437 |
+
"loss": 0.4002,
|
1438 |
+
"step": 195
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.27890430451796516,
|
1442 |
+
"grad_norm": 0.5881150364875793,
|
1443 |
+
"learning_rate": 3.2795591718381975e-07,
|
1444 |
+
"loss": 0.4642,
|
1445 |
+
"step": 196
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.280327285663465,
|
1449 |
+
"grad_norm": 0.5470696687698364,
|
1450 |
+
"learning_rate": 1.8450462775428942e-07,
|
1451 |
+
"loss": 0.4564,
|
1452 |
+
"step": 197
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 0.28175026680896476,
|
1456 |
+
"grad_norm": 0.7771428823471069,
|
1457 |
+
"learning_rate": 8.201139886109264e-08,
|
1458 |
+
"loss": 0.4493,
|
1459 |
+
"step": 198
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 0.2831732479544646,
|
1463 |
+
"grad_norm": 0.7079588174819946,
|
1464 |
+
"learning_rate": 2.0504251129649374e-08,
|
1465 |
+
"loss": 0.5309,
|
1466 |
+
"step": 199
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.2845962290999644,
|
1470 |
+
"grad_norm": 0.9976850748062134,
|
1471 |
+
"learning_rate": 0.0,
|
1472 |
+
"loss": 0.6441,
|
1473 |
+
"step": 200
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.2845962290999644,
|
1477 |
+
"eval_loss": 0.4162873327732086,
|
1478 |
+
"eval_runtime": 1.592,
|
1479 |
+
"eval_samples_per_second": 31.406,
|
1480 |
+
"eval_steps_per_second": 4.397,
|
1481 |
+
"step": 200
|
1482 |
}
|
1483 |
],
|
1484 |
"logging_steps": 1,
|
|
|
1502 |
"should_evaluate": false,
|
1503 |
"should_log": false,
|
1504 |
"should_save": true,
|
1505 |
+
"should_training_stop": true
|
1506 |
},
|
1507 |
"attributes": {}
|
1508 |
}
|
1509 |
},
|
1510 |
+
"total_flos": 4.385754324349747e+16,
|
1511 |
"train_batch_size": 8,
|
1512 |
"trial_name": null,
|
1513 |
"trial_params": null
|