Training in progress, step 193, 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 100198584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d08662b031cdd86ed774881debe128c873e00074cf7929595f42b6a63d84048
|
| 3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50675156
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa10ee462c7e49a82fafb47e9d4304eed05d8aaf2fa6327757fcf5a538adb758
|
| 3 |
size 50675156
|
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 sha256:5ac39c24740490f5e39e7ce5934c2a2903951fd3baae22c89e765d403647b6d1
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1134,6 +1134,230 @@
|
|
| 1134 |
"learning_rate": 1.791095890410959e-05,
|
| 1135 |
"loss": 1.3022,
|
| 1136 |
"step": 161
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1137 |
}
|
| 1138 |
],
|
| 1139 |
"logging_steps": 1,
|
|
@@ -1153,7 +1377,7 @@
|
|
| 1153 |
"attributes": {}
|
| 1154 |
}
|
| 1155 |
},
|
| 1156 |
-
"total_flos":
|
| 1157 |
"train_batch_size": 4,
|
| 1158 |
"trial_name": null,
|
| 1159 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.28198338051319516,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 193,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1134 |
"learning_rate": 1.791095890410959e-05,
|
| 1135 |
"loss": 1.3022,
|
| 1136 |
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.23669071317687881,
|
| 1140 |
+
"grad_norm": 0.16716252267360687,
|
| 1141 |
+
"learning_rate": 1.7876712328767125e-05,
|
| 1142 |
+
"loss": 1.2339,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.23815176696192128,
|
| 1147 |
+
"grad_norm": 0.1609048694372177,
|
| 1148 |
+
"learning_rate": 1.7842465753424658e-05,
|
| 1149 |
+
"loss": 1.3374,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.23961282074696375,
|
| 1154 |
+
"grad_norm": 0.17205393314361572,
|
| 1155 |
+
"learning_rate": 1.7808219178082194e-05,
|
| 1156 |
+
"loss": 1.2043,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.2410738745320062,
|
| 1161 |
+
"grad_norm": 0.17497386038303375,
|
| 1162 |
+
"learning_rate": 1.7773972602739727e-05,
|
| 1163 |
+
"loss": 1.2267,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.24253492831704868,
|
| 1168 |
+
"grad_norm": 0.17982399463653564,
|
| 1169 |
+
"learning_rate": 1.773972602739726e-05,
|
| 1170 |
+
"loss": 1.2363,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.24399598210209114,
|
| 1175 |
+
"grad_norm": 0.17415454983711243,
|
| 1176 |
+
"learning_rate": 1.7705479452054797e-05,
|
| 1177 |
+
"loss": 1.2339,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.2454570358871336,
|
| 1182 |
+
"grad_norm": 0.17761662602424622,
|
| 1183 |
+
"learning_rate": 1.767123287671233e-05,
|
| 1184 |
+
"loss": 1.2549,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.24691808967217604,
|
| 1189 |
+
"grad_norm": 0.17029732465744019,
|
| 1190 |
+
"learning_rate": 1.7636986301369866e-05,
|
| 1191 |
+
"loss": 1.2175,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.2483791434572185,
|
| 1196 |
+
"grad_norm": 0.1831396073102951,
|
| 1197 |
+
"learning_rate": 1.76027397260274e-05,
|
| 1198 |
+
"loss": 1.2975,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.24984019724226098,
|
| 1203 |
+
"grad_norm": 0.1648183912038803,
|
| 1204 |
+
"learning_rate": 1.7568493150684932e-05,
|
| 1205 |
+
"loss": 1.317,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.25130125102730344,
|
| 1210 |
+
"grad_norm": 0.19559577107429504,
|
| 1211 |
+
"learning_rate": 1.7534246575342465e-05,
|
| 1212 |
+
"loss": 1.2482,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.2527623048123459,
|
| 1217 |
+
"grad_norm": 0.17486748099327087,
|
| 1218 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 1219 |
+
"loss": 1.2638,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.25422335859738837,
|
| 1224 |
+
"grad_norm": 0.18816767632961273,
|
| 1225 |
+
"learning_rate": 1.7465753424657538e-05,
|
| 1226 |
+
"loss": 1.2739,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.25568441238243084,
|
| 1231 |
+
"grad_norm": 0.1921810507774353,
|
| 1232 |
+
"learning_rate": 1.743150684931507e-05,
|
| 1233 |
+
"loss": 1.2028,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.2571454661674733,
|
| 1238 |
+
"grad_norm": 0.20229558646678925,
|
| 1239 |
+
"learning_rate": 1.7397260273972604e-05,
|
| 1240 |
+
"loss": 1.2518,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.25860651995251577,
|
| 1245 |
+
"grad_norm": 0.21454092860221863,
|
| 1246 |
+
"learning_rate": 1.7363013698630137e-05,
|
| 1247 |
+
"loss": 1.2257,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.26006757373755823,
|
| 1252 |
+
"grad_norm": 0.20349366962909698,
|
| 1253 |
+
"learning_rate": 1.7328767123287674e-05,
|
| 1254 |
+
"loss": 1.229,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.2615286275226007,
|
| 1259 |
+
"grad_norm": 0.22348977625370026,
|
| 1260 |
+
"learning_rate": 1.7294520547945207e-05,
|
| 1261 |
+
"loss": 1.3047,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.26298968130764316,
|
| 1266 |
+
"grad_norm": 0.18413174152374268,
|
| 1267 |
+
"learning_rate": 1.726027397260274e-05,
|
| 1268 |
+
"loss": 1.2372,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.2644507350926856,
|
| 1273 |
+
"grad_norm": 0.22073839604854584,
|
| 1274 |
+
"learning_rate": 1.7226027397260273e-05,
|
| 1275 |
+
"loss": 1.2719,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.26591178887772804,
|
| 1280 |
+
"grad_norm": 0.25906509160995483,
|
| 1281 |
+
"learning_rate": 1.719178082191781e-05,
|
| 1282 |
+
"loss": 1.2132,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.2673728426627705,
|
| 1287 |
+
"grad_norm": 0.22006724774837494,
|
| 1288 |
+
"learning_rate": 1.7157534246575346e-05,
|
| 1289 |
+
"loss": 1.2595,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.26883389644781297,
|
| 1294 |
+
"grad_norm": 0.2628309428691864,
|
| 1295 |
+
"learning_rate": 1.712328767123288e-05,
|
| 1296 |
+
"loss": 1.1812,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.27029495023285544,
|
| 1301 |
+
"grad_norm": 0.21583111584186554,
|
| 1302 |
+
"learning_rate": 1.7089041095890412e-05,
|
| 1303 |
+
"loss": 1.2631,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.2717560040178979,
|
| 1308 |
+
"grad_norm": 0.19774451851844788,
|
| 1309 |
+
"learning_rate": 1.7054794520547945e-05,
|
| 1310 |
+
"loss": 1.2511,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.27321705780294037,
|
| 1315 |
+
"grad_norm": 0.199305459856987,
|
| 1316 |
+
"learning_rate": 1.702054794520548e-05,
|
| 1317 |
+
"loss": 1.2836,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.27467811158798283,
|
| 1322 |
+
"grad_norm": 0.17964106798171997,
|
| 1323 |
+
"learning_rate": 1.6986301369863014e-05,
|
| 1324 |
+
"loss": 1.2784,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.2761391653730253,
|
| 1329 |
+
"grad_norm": 0.15635524690151215,
|
| 1330 |
+
"learning_rate": 1.695205479452055e-05,
|
| 1331 |
+
"loss": 1.2959,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.27760021915806776,
|
| 1336 |
+
"grad_norm": 0.14683344960212708,
|
| 1337 |
+
"learning_rate": 1.6917808219178084e-05,
|
| 1338 |
+
"loss": 1.2453,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.27906127294311023,
|
| 1343 |
+
"grad_norm": 0.1619580239057541,
|
| 1344 |
+
"learning_rate": 1.6883561643835617e-05,
|
| 1345 |
+
"loss": 1.2602,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.2805223267281527,
|
| 1350 |
+
"grad_norm": 0.19470493495464325,
|
| 1351 |
+
"learning_rate": 1.6849315068493153e-05,
|
| 1352 |
+
"loss": 1.1052,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.28198338051319516,
|
| 1357 |
+
"grad_norm": 0.17526264488697052,
|
| 1358 |
+
"learning_rate": 1.6815068493150686e-05,
|
| 1359 |
+
"loss": 1.2553,
|
| 1360 |
+
"step": 193
|
| 1361 |
}
|
| 1362 |
],
|
| 1363 |
"logging_steps": 1,
|
|
|
|
| 1377 |
"attributes": {}
|
| 1378 |
}
|
| 1379 |
},
|
| 1380 |
+
"total_flos": 2.1621842547974554e+17,
|
| 1381 |
"train_batch_size": 4,
|
| 1382 |
"trial_name": null,
|
| 1383 |
"trial_params": null
|