Training in progress, step 1500, 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 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84836aadd5b7668801f43f94256af1462d4f6fcd0638b1078edbab3752655c83
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671473763
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:110c7016c149e8b740c8790f09dcce9198bbae6ee7cc39f1fd5d7f46e2210a01
|
| 3 |
size 671473763
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00df7897a1fc6c054036bcebad4f3efec8761e2e58635a805d2ef197e09b731c
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:675c447775e07c9091c55f2dffbbf5646a2b0f067a2b30d2abcb37bd027db68f
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1205,6 +1205,307 @@
|
|
| 1205 |
"learning_rate": 1.1998599831119912e-05,
|
| 1206 |
"loss": 1.491,
|
| 1207 |
"step": 1197
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1208 |
}
|
| 1209 |
],
|
| 1210 |
"logging_steps": 7,
|
|
@@ -1219,12 +1520,12 @@
|
|
| 1219 |
"should_evaluate": false,
|
| 1220 |
"should_log": false,
|
| 1221 |
"should_save": true,
|
| 1222 |
-
"should_training_stop":
|
| 1223 |
},
|
| 1224 |
"attributes": {}
|
| 1225 |
}
|
| 1226 |
},
|
| 1227 |
-
"total_flos":
|
| 1228 |
"train_batch_size": 8,
|
| 1229 |
"trial_name": null,
|
| 1230 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0458919092563981,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1205 |
"learning_rate": 1.1998599831119912e-05,
|
| 1206 |
"loss": 1.491,
|
| 1207 |
"step": 1197
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.03683590582980221,
|
| 1211 |
+
"grad_norm": 1.5545629262924194,
|
| 1212 |
+
"learning_rate": 1.1474337861210543e-05,
|
| 1213 |
+
"loss": 1.4981,
|
| 1214 |
+
"step": 1204
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.03705006807299873,
|
| 1218 |
+
"grad_norm": 2.0076568126678467,
|
| 1219 |
+
"learning_rate": 1.096029866616704e-05,
|
| 1220 |
+
"loss": 1.5171,
|
| 1221 |
+
"step": 1211
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.03726423031619525,
|
| 1225 |
+
"grad_norm": 1.0814955234527588,
|
| 1226 |
+
"learning_rate": 1.0456618646161954e-05,
|
| 1227 |
+
"loss": 1.3583,
|
| 1228 |
+
"step": 1218
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.03747839255939178,
|
| 1232 |
+
"grad_norm": 1.3351236581802368,
|
| 1233 |
+
"learning_rate": 9.963431452563332e-06,
|
| 1234 |
+
"loss": 1.4998,
|
| 1235 |
+
"step": 1225
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.037692554802588304,
|
| 1239 |
+
"grad_norm": 1.345676064491272,
|
| 1240 |
+
"learning_rate": 9.480867952470284e-06,
|
| 1241 |
+
"loss": 1.4631,
|
| 1242 |
+
"step": 1232
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.03790671704578483,
|
| 1246 |
+
"grad_norm": 1.1110200881958008,
|
| 1247 |
+
"learning_rate": 9.00905619398757e-06,
|
| 1248 |
+
"loss": 1.4986,
|
| 1249 |
+
"step": 1239
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.03812087928898135,
|
| 1253 |
+
"grad_norm": 1.1065698862075806,
|
| 1254 |
+
"learning_rate": 8.548121372247918e-06,
|
| 1255 |
+
"loss": 1.4631,
|
| 1256 |
+
"step": 1246
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.03833504153217788,
|
| 1260 |
+
"grad_norm": 1.2057925462722778,
|
| 1261 |
+
"learning_rate": 8.098185796191631e-06,
|
| 1262 |
+
"loss": 1.439,
|
| 1263 |
+
"step": 1253
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.0385492037753744,
|
| 1267 |
+
"grad_norm": 1.4041844606399536,
|
| 1268 |
+
"learning_rate": 7.659368856111926e-06,
|
| 1269 |
+
"loss": 1.4684,
|
| 1270 |
+
"step": 1260
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.03876336601857092,
|
| 1274 |
+
"grad_norm": 1.3971853256225586,
|
| 1275 |
+
"learning_rate": 7.2317869919746705e-06,
|
| 1276 |
+
"loss": 1.439,
|
| 1277 |
+
"step": 1267
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.03897752826176745,
|
| 1281 |
+
"grad_norm": 1.2180246114730835,
|
| 1282 |
+
"learning_rate": 6.815553662521185e-06,
|
| 1283 |
+
"loss": 1.5764,
|
| 1284 |
+
"step": 1274
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.039191690504963975,
|
| 1288 |
+
"grad_norm": 1.822922706604004,
|
| 1289 |
+
"learning_rate": 6.410779315161886e-06,
|
| 1290 |
+
"loss": 1.4794,
|
| 1291 |
+
"step": 1281
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.0394058527481605,
|
| 1295 |
+
"grad_norm": 1.2133909463882446,
|
| 1296 |
+
"learning_rate": 6.017571356669183e-06,
|
| 1297 |
+
"loss": 1.4784,
|
| 1298 |
+
"step": 1288
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.039620014991357026,
|
| 1302 |
+
"grad_norm": 1.4232499599456787,
|
| 1303 |
+
"learning_rate": 5.636034124677042e-06,
|
| 1304 |
+
"loss": 1.405,
|
| 1305 |
+
"step": 1295
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.03983417723455355,
|
| 1309 |
+
"grad_norm": 1.8573203086853027,
|
| 1310 |
+
"learning_rate": 5.266268859995083e-06,
|
| 1311 |
+
"loss": 1.4153,
|
| 1312 |
+
"step": 1302
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.04004833947775007,
|
| 1316 |
+
"grad_norm": 1.6481467485427856,
|
| 1317 |
+
"learning_rate": 4.908373679744316e-06,
|
| 1318 |
+
"loss": 1.3081,
|
| 1319 |
+
"step": 1309
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.0402625017209466,
|
| 1323 |
+
"grad_norm": 2.072063446044922,
|
| 1324 |
+
"learning_rate": 4.562443551321788e-06,
|
| 1325 |
+
"loss": 1.2842,
|
| 1326 |
+
"step": 1316
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.04047666396414312,
|
| 1330 |
+
"grad_norm": 1.2372018098831177,
|
| 1331 |
+
"learning_rate": 4.228570267201049e-06,
|
| 1332 |
+
"loss": 1.5924,
|
| 1333 |
+
"step": 1323
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.040690826207339645,
|
| 1337 |
+
"grad_norm": 1.206811785697937,
|
| 1338 |
+
"learning_rate": 3.90684242057498e-06,
|
| 1339 |
+
"loss": 1.4247,
|
| 1340 |
+
"step": 1330
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.04090498845053617,
|
| 1344 |
+
"grad_norm": 1.6587467193603516,
|
| 1345 |
+
"learning_rate": 3.5973453818476556e-06,
|
| 1346 |
+
"loss": 1.4644,
|
| 1347 |
+
"step": 1337
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.041119150693732696,
|
| 1351 |
+
"grad_norm": 1.1888831853866577,
|
| 1352 |
+
"learning_rate": 3.3001612759813393e-06,
|
| 1353 |
+
"loss": 1.5327,
|
| 1354 |
+
"step": 1344
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.04133331293692922,
|
| 1358 |
+
"grad_norm": 1.0991014242172241,
|
| 1359 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1360 |
+
"loss": 1.4681,
|
| 1361 |
+
"step": 1351
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.04154747518012574,
|
| 1365 |
+
"grad_norm": 1.5934925079345703,
|
| 1366 |
+
"learning_rate": 2.743044005587425e-06,
|
| 1367 |
+
"loss": 1.3098,
|
| 1368 |
+
"step": 1358
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.04176163742332227,
|
| 1372 |
+
"grad_norm": 1.4214099645614624,
|
| 1373 |
+
"learning_rate": 2.4832586719889416e-06,
|
| 1374 |
+
"loss": 1.4065,
|
| 1375 |
+
"step": 1365
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.04197579966651879,
|
| 1379 |
+
"grad_norm": 1.2822719812393188,
|
| 1380 |
+
"learning_rate": 2.2360818938828187e-06,
|
| 1381 |
+
"loss": 1.4728,
|
| 1382 |
+
"step": 1372
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.042189961909715315,
|
| 1386 |
+
"grad_norm": 1.119520664215088,
|
| 1387 |
+
"learning_rate": 2.0015792595656226e-06,
|
| 1388 |
+
"loss": 1.4284,
|
| 1389 |
+
"step": 1379
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.042404124152911844,
|
| 1393 |
+
"grad_norm": 1.3280854225158691,
|
| 1394 |
+
"learning_rate": 1.7798129942530551e-06,
|
| 1395 |
+
"loss": 1.4559,
|
| 1396 |
+
"step": 1386
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.04261828639610837,
|
| 1400 |
+
"grad_norm": 1.1883761882781982,
|
| 1401 |
+
"learning_rate": 1.5708419435684462e-06,
|
| 1402 |
+
"loss": 1.3757,
|
| 1403 |
+
"step": 1393
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.04283244863930489,
|
| 1407 |
+
"grad_norm": 1.3203167915344238,
|
| 1408 |
+
"learning_rate": 1.374721557928116e-06,
|
| 1409 |
+
"loss": 1.6273,
|
| 1410 |
+
"step": 1400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.04304661088250142,
|
| 1414 |
+
"grad_norm": 1.2010129690170288,
|
| 1415 |
+
"learning_rate": 1.191503877827621e-06,
|
| 1416 |
+
"loss": 1.4944,
|
| 1417 |
+
"step": 1407
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.04326077312569794,
|
| 1421 |
+
"grad_norm": 1.6128370761871338,
|
| 1422 |
+
"learning_rate": 1.0212375200327973e-06,
|
| 1423 |
+
"loss": 1.6092,
|
| 1424 |
+
"step": 1414
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.04347493536889446,
|
| 1428 |
+
"grad_norm": 1.0786170959472656,
|
| 1429 |
+
"learning_rate": 8.639676646793382e-07,
|
| 1430 |
+
"loss": 1.4227,
|
| 1431 |
+
"step": 1421
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.043689097612090985,
|
| 1435 |
+
"grad_norm": 1.0348191261291504,
|
| 1436 |
+
"learning_rate": 7.197360432842359e-07,
|
| 1437 |
+
"loss": 1.5162,
|
| 1438 |
+
"step": 1428
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.043903259855287514,
|
| 1442 |
+
"grad_norm": 1.0884389877319336,
|
| 1443 |
+
"learning_rate": 5.885809276723608e-07,
|
| 1444 |
+
"loss": 1.5015,
|
| 1445 |
+
"step": 1435
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.04411742209848404,
|
| 1449 |
+
"grad_norm": 1.5776199102401733,
|
| 1450 |
+
"learning_rate": 4.705371198210129e-07,
|
| 1451 |
+
"loss": 1.5789,
|
| 1452 |
+
"step": 1442
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.04433158434168056,
|
| 1456 |
+
"grad_norm": 1.4270485639572144,
|
| 1457 |
+
"learning_rate": 3.65635942625242e-07,
|
| 1458 |
+
"loss": 1.5011,
|
| 1459 |
+
"step": 1449
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.04454574658487709,
|
| 1463 |
+
"grad_norm": 1.2836881875991821,
|
| 1464 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 1465 |
+
"loss": 1.4921,
|
| 1466 |
+
"step": 1456
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.04475990882807361,
|
| 1470 |
+
"grad_norm": 1.3851501941680908,
|
| 1471 |
+
"learning_rate": 1.953693274256374e-07,
|
| 1472 |
+
"loss": 1.5536,
|
| 1473 |
+
"step": 1463
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.04497407107127013,
|
| 1477 |
+
"grad_norm": 1.9082521200180054,
|
| 1478 |
+
"learning_rate": 1.3004906962578721e-07,
|
| 1479 |
+
"loss": 1.3908,
|
| 1480 |
+
"step": 1470
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.04518823331446666,
|
| 1484 |
+
"grad_norm": 1.3173164129257202,
|
| 1485 |
+
"learning_rate": 7.796179090094891e-08,
|
| 1486 |
+
"loss": 1.4139,
|
| 1487 |
+
"step": 1477
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.045402395557663185,
|
| 1491 |
+
"grad_norm": 1.4804590940475464,
|
| 1492 |
+
"learning_rate": 3.9121312597573125e-08,
|
| 1493 |
+
"loss": 1.4134,
|
| 1494 |
+
"step": 1484
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.04561655780085971,
|
| 1498 |
+
"grad_norm": 1.5944395065307617,
|
| 1499 |
+
"learning_rate": 1.3537941026914303e-08,
|
| 1500 |
+
"loss": 1.301,
|
| 1501 |
+
"step": 1491
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.045830720044056236,
|
| 1505 |
+
"grad_norm": 1.4432575702667236,
|
| 1506 |
+
"learning_rate": 1.2184647302626583e-09,
|
| 1507 |
+
"loss": 1.5252,
|
| 1508 |
+
"step": 1498
|
| 1509 |
}
|
| 1510 |
],
|
| 1511 |
"logging_steps": 7,
|
|
|
|
| 1520 |
"should_evaluate": false,
|
| 1521 |
"should_log": false,
|
| 1522 |
"should_save": true,
|
| 1523 |
+
"should_training_stop": true
|
| 1524 |
},
|
| 1525 |
"attributes": {}
|
| 1526 |
}
|
| 1527 |
},
|
| 1528 |
+
"total_flos": 1.119015678246912e+18,
|
| 1529 |
"train_batch_size": 8,
|
| 1530 |
"trial_name": null,
|
| 1531 |
"trial_params": null
|