Training in progress, step 1000, 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 268858112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cb5c823ef74dfadc52b27febc38a2ac3a875bb51704bb51249b3924e6ee6f2b
|
| 3 |
size 268858112
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 137668197
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35bbf0d8ee6289b2e585cda8bdd7541a68981e8fbe801a50960d7cef7275b8b9
|
| 3 |
size 137668197
|
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:bfad65ecdebf4d2a4ef23aa53c40f8dd23f710c224d047e20d32dc51c4015de2
|
| 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,
|
|
@@ -1128,6 +1128,286 @@
|
|
| 1128 |
"learning_rate": 0.0001,
|
| 1129 |
"loss": 0.2739,
|
| 1130 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1131 |
}
|
| 1132 |
],
|
| 1133 |
"logging_steps": 5,
|
|
@@ -1147,7 +1427,7 @@
|
|
| 1147 |
"attributes": {}
|
| 1148 |
}
|
| 1149 |
},
|
| 1150 |
-
"total_flos":
|
| 1151 |
"train_batch_size": 24,
|
| 1152 |
"trial_name": null,
|
| 1153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9596928982725528,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1128 |
"learning_rate": 0.0001,
|
| 1129 |
"loss": 0.2739,
|
| 1130 |
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.772552783109405,
|
| 1134 |
+
"grad_norm": 0.14281855523586273,
|
| 1135 |
+
"learning_rate": 0.0001,
|
| 1136 |
+
"loss": 0.2711,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7773512476007678,
|
| 1141 |
+
"grad_norm": 0.13634523749351501,
|
| 1142 |
+
"learning_rate": 0.0001,
|
| 1143 |
+
"loss": 0.267,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7821497120921305,
|
| 1148 |
+
"grad_norm": 0.14958547055721283,
|
| 1149 |
+
"learning_rate": 0.0001,
|
| 1150 |
+
"loss": 0.2809,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.7869481765834933,
|
| 1155 |
+
"grad_norm": 0.16246724128723145,
|
| 1156 |
+
"learning_rate": 0.0001,
|
| 1157 |
+
"loss": 0.2632,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.791746641074856,
|
| 1162 |
+
"grad_norm": 0.15865352749824524,
|
| 1163 |
+
"learning_rate": 0.0001,
|
| 1164 |
+
"loss": 0.2669,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7965451055662188,
|
| 1169 |
+
"grad_norm": 0.16149087250232697,
|
| 1170 |
+
"learning_rate": 0.0001,
|
| 1171 |
+
"loss": 0.2708,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.8013435700575816,
|
| 1176 |
+
"grad_norm": 0.15393655002117157,
|
| 1177 |
+
"learning_rate": 0.0001,
|
| 1178 |
+
"loss": 0.2736,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8061420345489443,
|
| 1183 |
+
"grad_norm": 0.16198311746120453,
|
| 1184 |
+
"learning_rate": 0.0001,
|
| 1185 |
+
"loss": 0.2627,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8109404990403071,
|
| 1190 |
+
"grad_norm": 0.18130268156528473,
|
| 1191 |
+
"learning_rate": 0.0001,
|
| 1192 |
+
"loss": 0.2663,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.8157389635316699,
|
| 1197 |
+
"grad_norm": 0.15879245102405548,
|
| 1198 |
+
"learning_rate": 0.0001,
|
| 1199 |
+
"loss": 0.2525,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.8205374280230326,
|
| 1204 |
+
"grad_norm": 0.15435881912708282,
|
| 1205 |
+
"learning_rate": 0.0001,
|
| 1206 |
+
"loss": 0.277,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.8253358925143954,
|
| 1211 |
+
"grad_norm": 0.14485138654708862,
|
| 1212 |
+
"learning_rate": 0.0001,
|
| 1213 |
+
"loss": 0.2902,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.8301343570057581,
|
| 1218 |
+
"grad_norm": 0.15166470408439636,
|
| 1219 |
+
"learning_rate": 0.0001,
|
| 1220 |
+
"loss": 0.2703,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.8349328214971209,
|
| 1225 |
+
"grad_norm": 0.14248280227184296,
|
| 1226 |
+
"learning_rate": 0.0001,
|
| 1227 |
+
"loss": 0.2635,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.8397312859884837,
|
| 1232 |
+
"grad_norm": 0.14291894435882568,
|
| 1233 |
+
"learning_rate": 0.0001,
|
| 1234 |
+
"loss": 0.2505,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.8445297504798465,
|
| 1239 |
+
"grad_norm": 0.16025425493717194,
|
| 1240 |
+
"learning_rate": 0.0001,
|
| 1241 |
+
"loss": 0.2591,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.8493282149712092,
|
| 1246 |
+
"grad_norm": 0.15063312649726868,
|
| 1247 |
+
"learning_rate": 0.0001,
|
| 1248 |
+
"loss": 0.2767,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.8541266794625719,
|
| 1253 |
+
"grad_norm": 0.14704886078834534,
|
| 1254 |
+
"learning_rate": 0.0001,
|
| 1255 |
+
"loss": 0.2615,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.8589251439539347,
|
| 1260 |
+
"grad_norm": 0.1524520218372345,
|
| 1261 |
+
"learning_rate": 0.0001,
|
| 1262 |
+
"loss": 0.2771,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.8637236084452975,
|
| 1267 |
+
"grad_norm": 0.15311211347579956,
|
| 1268 |
+
"learning_rate": 0.0001,
|
| 1269 |
+
"loss": 0.2779,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.8685220729366603,
|
| 1274 |
+
"grad_norm": 0.19531571865081787,
|
| 1275 |
+
"learning_rate": 0.0001,
|
| 1276 |
+
"loss": 0.256,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.8733205374280231,
|
| 1281 |
+
"grad_norm": 0.15908968448638916,
|
| 1282 |
+
"learning_rate": 0.0001,
|
| 1283 |
+
"loss": 0.2598,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8781190019193857,
|
| 1288 |
+
"grad_norm": 0.14221200346946716,
|
| 1289 |
+
"learning_rate": 0.0001,
|
| 1290 |
+
"loss": 0.2554,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8829174664107485,
|
| 1295 |
+
"grad_norm": 0.16132907569408417,
|
| 1296 |
+
"learning_rate": 0.0001,
|
| 1297 |
+
"loss": 0.2885,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8877159309021113,
|
| 1302 |
+
"grad_norm": 0.14751212298870087,
|
| 1303 |
+
"learning_rate": 0.0001,
|
| 1304 |
+
"loss": 0.2716,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.8925143953934741,
|
| 1309 |
+
"grad_norm": 0.146012082695961,
|
| 1310 |
+
"learning_rate": 0.0001,
|
| 1311 |
+
"loss": 0.2558,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.8973128598848369,
|
| 1316 |
+
"grad_norm": 0.16232919692993164,
|
| 1317 |
+
"learning_rate": 0.0001,
|
| 1318 |
+
"loss": 0.2805,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.9021113243761996,
|
| 1323 |
+
"grad_norm": 0.16521847248077393,
|
| 1324 |
+
"learning_rate": 0.0001,
|
| 1325 |
+
"loss": 0.2669,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.9069097888675623,
|
| 1330 |
+
"grad_norm": 0.14723201096057892,
|
| 1331 |
+
"learning_rate": 0.0001,
|
| 1332 |
+
"loss": 0.2642,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.9117082533589251,
|
| 1337 |
+
"grad_norm": 0.15053531527519226,
|
| 1338 |
+
"learning_rate": 0.0001,
|
| 1339 |
+
"loss": 0.2698,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.9165067178502879,
|
| 1344 |
+
"grad_norm": 0.14634476602077484,
|
| 1345 |
+
"learning_rate": 0.0001,
|
| 1346 |
+
"loss": 0.2615,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.9213051823416507,
|
| 1351 |
+
"grad_norm": 0.1575053334236145,
|
| 1352 |
+
"learning_rate": 0.0001,
|
| 1353 |
+
"loss": 0.2789,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.9261036468330134,
|
| 1358 |
+
"grad_norm": 0.15231551229953766,
|
| 1359 |
+
"learning_rate": 0.0001,
|
| 1360 |
+
"loss": 0.2577,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.9309021113243762,
|
| 1365 |
+
"grad_norm": 0.15277941524982452,
|
| 1366 |
+
"learning_rate": 0.0001,
|
| 1367 |
+
"loss": 0.2658,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.935700575815739,
|
| 1372 |
+
"grad_norm": 0.1474364995956421,
|
| 1373 |
+
"learning_rate": 0.0001,
|
| 1374 |
+
"loss": 0.2771,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.9404990403071017,
|
| 1379 |
+
"grad_norm": 0.14509518444538116,
|
| 1380 |
+
"learning_rate": 0.0001,
|
| 1381 |
+
"loss": 0.2587,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.9452975047984645,
|
| 1386 |
+
"grad_norm": 0.146579310297966,
|
| 1387 |
+
"learning_rate": 0.0001,
|
| 1388 |
+
"loss": 0.2662,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9500959692898272,
|
| 1393 |
+
"grad_norm": 0.1470819115638733,
|
| 1394 |
+
"learning_rate": 0.0001,
|
| 1395 |
+
"loss": 0.2691,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.95489443378119,
|
| 1400 |
+
"grad_norm": 0.161437526345253,
|
| 1401 |
+
"learning_rate": 0.0001,
|
| 1402 |
+
"loss": 0.2681,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.9596928982725528,
|
| 1407 |
+
"grad_norm": 0.1448318362236023,
|
| 1408 |
+
"learning_rate": 0.0001,
|
| 1409 |
+
"loss": 0.2554,
|
| 1410 |
+
"step": 1000
|
| 1411 |
}
|
| 1412 |
],
|
| 1413 |
"logging_steps": 5,
|
|
|
|
| 1427 |
"attributes": {}
|
| 1428 |
}
|
| 1429 |
},
|
| 1430 |
+
"total_flos": 3.323888912649138e+17,
|
| 1431 |
"train_batch_size": 24,
|
| 1432 |
"trial_name": null,
|
| 1433 |
"trial_params": null
|