Commit
•
0fed369
1
Parent(s):
5d8ab3b
Training in progress, step 25600
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 +396 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 745634697
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a82d4998e15048f7276ff7bf21cf172b2b8f99b8e3bce01b447dd4dc2e0f4219
|
| 3 |
size 745634697
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 372832803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85efd468f59e090bda67c9e694bf55407f51a1a6d9bede51d725c6b288ff9330
|
| 3 |
size 372832803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15523
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5885efec8b7366a4aa17af5e032d3298449da4e1fd163c7c8437f60c984450c3
|
| 3 |
size 15523
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac4294ae0275bdf2fd072eb3d13fea356c3c27e1570dc0dcf8759f2decf14230
|
| 3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1185,11 +1185,404 @@
|
|
| 1185 |
"eval_samples_per_second": 45.96,
|
| 1186 |
"eval_steps_per_second": 2.873,
|
| 1187 |
"step": 19200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1188 |
}
|
| 1189 |
],
|
| 1190 |
"max_steps": 64000,
|
| 1191 |
"num_train_epochs": 9223372036854775807,
|
| 1192 |
-
"total_flos": 1.
|
| 1193 |
"trial_name": null,
|
| 1194 |
"trial_params": null
|
| 1195 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4,
|
| 5 |
+
"global_step": 25600,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1185 |
"eval_samples_per_second": 45.96,
|
| 1186 |
"eval_steps_per_second": 2.873,
|
| 1187 |
"step": 19200
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.3,
|
| 1191 |
+
"learning_rate": 0.001,
|
| 1192 |
+
"loss": 8.043,
|
| 1193 |
+
"step": 19300
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.3,
|
| 1197 |
+
"learning_rate": 0.001,
|
| 1198 |
+
"loss": 8.0459,
|
| 1199 |
+
"step": 19400
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.3,
|
| 1203 |
+
"learning_rate": 0.001,
|
| 1204 |
+
"loss": 8.0138,
|
| 1205 |
+
"step": 19500
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.31,
|
| 1209 |
+
"learning_rate": 0.001,
|
| 1210 |
+
"loss": 8.0321,
|
| 1211 |
+
"step": 19600
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 0.31,
|
| 1215 |
+
"learning_rate": 0.001,
|
| 1216 |
+
"loss": 8.0512,
|
| 1217 |
+
"step": 19700
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.31,
|
| 1221 |
+
"learning_rate": 0.001,
|
| 1222 |
+
"loss": 8.0284,
|
| 1223 |
+
"step": 19800
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.31,
|
| 1227 |
+
"learning_rate": 0.001,
|
| 1228 |
+
"loss": 8.0347,
|
| 1229 |
+
"step": 19900
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.31,
|
| 1233 |
+
"learning_rate": 0.001,
|
| 1234 |
+
"loss": 8.046,
|
| 1235 |
+
"step": 20000
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.31,
|
| 1239 |
+
"learning_rate": 0.001,
|
| 1240 |
+
"loss": 8.0466,
|
| 1241 |
+
"step": 20100
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.32,
|
| 1245 |
+
"learning_rate": 0.001,
|
| 1246 |
+
"loss": 8.0612,
|
| 1247 |
+
"step": 20200
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.32,
|
| 1251 |
+
"learning_rate": 0.001,
|
| 1252 |
+
"loss": 8.0392,
|
| 1253 |
+
"step": 20300
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.32,
|
| 1257 |
+
"learning_rate": 0.001,
|
| 1258 |
+
"loss": 8.0422,
|
| 1259 |
+
"step": 20400
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.32,
|
| 1263 |
+
"learning_rate": 0.001,
|
| 1264 |
+
"loss": 8.0386,
|
| 1265 |
+
"step": 20500
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.32,
|
| 1269 |
+
"learning_rate": 0.001,
|
| 1270 |
+
"loss": 8.0504,
|
| 1271 |
+
"step": 20600
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 0.32,
|
| 1275 |
+
"learning_rate": 0.001,
|
| 1276 |
+
"loss": 8.0483,
|
| 1277 |
+
"step": 20700
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.33,
|
| 1281 |
+
"learning_rate": 0.001,
|
| 1282 |
+
"loss": 8.0463,
|
| 1283 |
+
"step": 20800
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.33,
|
| 1287 |
+
"learning_rate": 0.001,
|
| 1288 |
+
"loss": 8.0545,
|
| 1289 |
+
"step": 20900
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.33,
|
| 1293 |
+
"learning_rate": 0.001,
|
| 1294 |
+
"loss": 8.0491,
|
| 1295 |
+
"step": 21000
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 0.33,
|
| 1299 |
+
"learning_rate": 0.001,
|
| 1300 |
+
"loss": 8.0336,
|
| 1301 |
+
"step": 21100
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.33,
|
| 1305 |
+
"learning_rate": 0.001,
|
| 1306 |
+
"loss": 8.0372,
|
| 1307 |
+
"step": 21200
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.33,
|
| 1311 |
+
"learning_rate": 0.001,
|
| 1312 |
+
"loss": 8.0405,
|
| 1313 |
+
"step": 21300
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.33,
|
| 1317 |
+
"learning_rate": 0.001,
|
| 1318 |
+
"loss": 8.028,
|
| 1319 |
+
"step": 21400
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.34,
|
| 1323 |
+
"learning_rate": 0.001,
|
| 1324 |
+
"loss": 8.0234,
|
| 1325 |
+
"step": 21500
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.34,
|
| 1329 |
+
"learning_rate": 0.001,
|
| 1330 |
+
"loss": 8.0256,
|
| 1331 |
+
"step": 21600
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 0.34,
|
| 1335 |
+
"learning_rate": 0.001,
|
| 1336 |
+
"loss": 8.028,
|
| 1337 |
+
"step": 21700
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 0.34,
|
| 1341 |
+
"learning_rate": 0.001,
|
| 1342 |
+
"loss": 8.0338,
|
| 1343 |
+
"step": 21800
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.34,
|
| 1347 |
+
"learning_rate": 0.001,
|
| 1348 |
+
"loss": 8.0345,
|
| 1349 |
+
"step": 21900
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.34,
|
| 1353 |
+
"learning_rate": 0.001,
|
| 1354 |
+
"loss": 8.0353,
|
| 1355 |
+
"step": 22000
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 0.35,
|
| 1359 |
+
"learning_rate": 0.001,
|
| 1360 |
+
"loss": 8.0426,
|
| 1361 |
+
"step": 22100
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.35,
|
| 1365 |
+
"learning_rate": 0.001,
|
| 1366 |
+
"loss": 8.0318,
|
| 1367 |
+
"step": 22200
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.35,
|
| 1371 |
+
"learning_rate": 0.001,
|
| 1372 |
+
"loss": 8.0341,
|
| 1373 |
+
"step": 22300
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.35,
|
| 1377 |
+
"learning_rate": 0.001,
|
| 1378 |
+
"loss": 8.026,
|
| 1379 |
+
"step": 22400
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 0.35,
|
| 1383 |
+
"learning_rate": 0.001,
|
| 1384 |
+
"loss": 8.0333,
|
| 1385 |
+
"step": 22500
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.35,
|
| 1389 |
+
"learning_rate": 0.001,
|
| 1390 |
+
"loss": 8.0265,
|
| 1391 |
+
"step": 22600
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.35,
|
| 1395 |
+
"learning_rate": 0.001,
|
| 1396 |
+
"loss": 8.0764,
|
| 1397 |
+
"step": 22700
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.36,
|
| 1401 |
+
"learning_rate": 0.001,
|
| 1402 |
+
"loss": 8.0355,
|
| 1403 |
+
"step": 22800
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.36,
|
| 1407 |
+
"learning_rate": 0.001,
|
| 1408 |
+
"loss": 8.0472,
|
| 1409 |
+
"step": 22900
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.36,
|
| 1413 |
+
"learning_rate": 0.001,
|
| 1414 |
+
"loss": 8.0376,
|
| 1415 |
+
"step": 23000
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.36,
|
| 1419 |
+
"learning_rate": 0.001,
|
| 1420 |
+
"loss": 8.0335,
|
| 1421 |
+
"step": 23100
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.36,
|
| 1425 |
+
"learning_rate": 0.001,
|
| 1426 |
+
"loss": 8.0429,
|
| 1427 |
+
"step": 23200
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.36,
|
| 1431 |
+
"learning_rate": 0.001,
|
| 1432 |
+
"loss": 8.0431,
|
| 1433 |
+
"step": 23300
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.37,
|
| 1437 |
+
"learning_rate": 0.001,
|
| 1438 |
+
"loss": 8.0259,
|
| 1439 |
+
"step": 23400
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.37,
|
| 1443 |
+
"learning_rate": 0.001,
|
| 1444 |
+
"loss": 8.0339,
|
| 1445 |
+
"step": 23500
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.37,
|
| 1449 |
+
"learning_rate": 0.001,
|
| 1450 |
+
"loss": 8.0192,
|
| 1451 |
+
"step": 23600
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.37,
|
| 1455 |
+
"learning_rate": 0.001,
|
| 1456 |
+
"loss": 8.0515,
|
| 1457 |
+
"step": 23700
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.37,
|
| 1461 |
+
"learning_rate": 0.001,
|
| 1462 |
+
"loss": 8.0258,
|
| 1463 |
+
"step": 23800
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.37,
|
| 1467 |
+
"learning_rate": 0.001,
|
| 1468 |
+
"loss": 8.0422,
|
| 1469 |
+
"step": 23900
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 0.38,
|
| 1473 |
+
"learning_rate": 0.001,
|
| 1474 |
+
"loss": 8.0326,
|
| 1475 |
+
"step": 24000
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 0.38,
|
| 1479 |
+
"learning_rate": 0.001,
|
| 1480 |
+
"loss": 8.0392,
|
| 1481 |
+
"step": 24100
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.38,
|
| 1485 |
+
"learning_rate": 0.001,
|
| 1486 |
+
"loss": 8.0414,
|
| 1487 |
+
"step": 24200
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.38,
|
| 1491 |
+
"learning_rate": 0.001,
|
| 1492 |
+
"loss": 8.0505,
|
| 1493 |
+
"step": 24300
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.38,
|
| 1497 |
+
"learning_rate": 0.001,
|
| 1498 |
+
"loss": 8.0267,
|
| 1499 |
+
"step": 24400
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.38,
|
| 1503 |
+
"learning_rate": 0.001,
|
| 1504 |
+
"loss": 8.0391,
|
| 1505 |
+
"step": 24500
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.38,
|
| 1509 |
+
"learning_rate": 0.001,
|
| 1510 |
+
"loss": 8.0381,
|
| 1511 |
+
"step": 24600
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 0.39,
|
| 1515 |
+
"learning_rate": 0.001,
|
| 1516 |
+
"loss": 8.0339,
|
| 1517 |
+
"step": 24700
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.39,
|
| 1521 |
+
"learning_rate": 0.001,
|
| 1522 |
+
"loss": 8.0448,
|
| 1523 |
+
"step": 24800
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.39,
|
| 1527 |
+
"learning_rate": 0.001,
|
| 1528 |
+
"loss": 8.0633,
|
| 1529 |
+
"step": 24900
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.39,
|
| 1533 |
+
"learning_rate": 0.001,
|
| 1534 |
+
"loss": 8.0064,
|
| 1535 |
+
"step": 25000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.39,
|
| 1539 |
+
"learning_rate": 0.001,
|
| 1540 |
+
"loss": 8.0323,
|
| 1541 |
+
"step": 25100
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.39,
|
| 1545 |
+
"learning_rate": 0.001,
|
| 1546 |
+
"loss": 8.0286,
|
| 1547 |
+
"step": 25200
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.4,
|
| 1551 |
+
"learning_rate": 0.001,
|
| 1552 |
+
"loss": 8.0349,
|
| 1553 |
+
"step": 25300
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 0.4,
|
| 1557 |
+
"learning_rate": 0.001,
|
| 1558 |
+
"loss": 8.0373,
|
| 1559 |
+
"step": 25400
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.4,
|
| 1563 |
+
"learning_rate": 0.001,
|
| 1564 |
+
"loss": 8.0447,
|
| 1565 |
+
"step": 25500
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.4,
|
| 1569 |
+
"learning_rate": 0.001,
|
| 1570 |
+
"loss": 8.0302,
|
| 1571 |
+
"step": 25600
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.4,
|
| 1575 |
+
"eval_accuracy": 0.03333073104167396,
|
| 1576 |
+
"eval_loss": 8.036836624145508,
|
| 1577 |
+
"eval_runtime": 6892.0068,
|
| 1578 |
+
"eval_samples_per_second": 47.571,
|
| 1579 |
+
"eval_steps_per_second": 2.973,
|
| 1580 |
+
"step": 25600
|
| 1581 |
}
|
| 1582 |
],
|
| 1583 |
"max_steps": 64000,
|
| 1584 |
"num_train_epochs": 9223372036854775807,
|
| 1585 |
+
"total_flos": 1.353967057502208e+17,
|
| 1586 |
"trial_name": null,
|
| 1587 |
"trial_params": null
|
| 1588 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 372832803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85efd468f59e090bda67c9e694bf55407f51a1a6d9bede51d725c6b288ff9330
|
| 3 |
size 372832803
|