Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1235573136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd1f6e22634fcac871f4ed24bc640ad73cdede31b6d8fa36f1bdebd04d0ef694
|
| 3 |
size 1235573136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2471218763
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c03cf43380d82cadaa6b3a05aeb813bcd9a1b679482ca2dbec8dd79ee35ffa3
|
| 3 |
size 2471218763
|
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 sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:946093fecc07b9eebf6c92eb089b5a00988fc00e39f09c111679745018d0d6ac
|
| 3 |
size 1383
|
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:c8af7bf0eac60970e638b41829ebcbe1a8ce90393891b1a1fef11c365fd9582d
|
| 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":
|
| 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": 0.00029098797595190375,
|
| 1129 |
"loss": 3103321489408.0,
|
| 1130 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1131 |
}
|
| 1132 |
],
|
| 1133 |
"logging_steps": 10,
|
|
@@ -1147,7 +1427,7 @@
|
|
| 1147 |
"attributes": {}
|
| 1148 |
}
|
| 1149 |
},
|
| 1150 |
-
"total_flos": 2.
|
| 1151 |
"train_batch_size": 2,
|
| 1152 |
"trial_name": null,
|
| 1153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0017,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1128 |
"learning_rate": 0.00029098797595190375,
|
| 1129 |
"loss": 3103321489408.0,
|
| 1130 |
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.0002,
|
| 1134 |
+
"grad_norm": 0.0,
|
| 1135 |
+
"learning_rate": 0.0002909278557114228,
|
| 1136 |
+
"loss": 95.5510498046875,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.0004,
|
| 1141 |
+
"grad_norm": 0.0,
|
| 1142 |
+
"learning_rate": 0.00029086773547094184,
|
| 1143 |
+
"loss": 98.69436645507812,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.0006,
|
| 1148 |
+
"grad_norm": 0.0,
|
| 1149 |
+
"learning_rate": 0.0002908076152304609,
|
| 1150 |
+
"loss": 99.0325439453125,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.0008,
|
| 1155 |
+
"grad_norm": 0.0,
|
| 1156 |
+
"learning_rate": 0.00029074749498997994,
|
| 1157 |
+
"loss": 97.31904296875,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.001,
|
| 1162 |
+
"grad_norm": 0.0,
|
| 1163 |
+
"learning_rate": 0.000290687374749499,
|
| 1164 |
+
"loss": 98.40114135742188,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.0012,
|
| 1169 |
+
"grad_norm": 0.0,
|
| 1170 |
+
"learning_rate": 0.00029062725450901803,
|
| 1171 |
+
"loss": 99.31021728515626,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.0014,
|
| 1176 |
+
"grad_norm": 0.0,
|
| 1177 |
+
"learning_rate": 0.00029056713426853703,
|
| 1178 |
+
"loss": 99.4878662109375,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.0016,
|
| 1183 |
+
"grad_norm": 0.0,
|
| 1184 |
+
"learning_rate": 0.0002905070140280561,
|
| 1185 |
+
"loss": 99.3884521484375,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.0018,
|
| 1190 |
+
"grad_norm": 0.0,
|
| 1191 |
+
"learning_rate": 0.0002904468937875751,
|
| 1192 |
+
"loss": 99.46731567382812,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.002,
|
| 1197 |
+
"grad_norm": 0.0,
|
| 1198 |
+
"learning_rate": 0.00029038677354709417,
|
| 1199 |
+
"loss": 99.4464599609375,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.0001,
|
| 1204 |
+
"grad_norm": 0.0,
|
| 1205 |
+
"learning_rate": 0.00029032665330661317,
|
| 1206 |
+
"loss": 104.66427001953124,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.0003,
|
| 1211 |
+
"grad_norm": 0.0,
|
| 1212 |
+
"learning_rate": 0.0002902665330661322,
|
| 1213 |
+
"loss": 98.24152221679688,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.0005,
|
| 1218 |
+
"grad_norm": 0.0,
|
| 1219 |
+
"learning_rate": 0.0002902064128256513,
|
| 1220 |
+
"loss": 99.4651123046875,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.0007,
|
| 1225 |
+
"grad_norm": 0.0,
|
| 1226 |
+
"learning_rate": 0.0002901462925851703,
|
| 1227 |
+
"loss": 99.3810546875,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.0009,
|
| 1232 |
+
"grad_norm": 0.0,
|
| 1233 |
+
"learning_rate": 0.00029008617234468936,
|
| 1234 |
+
"loss": 96.20846557617188,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.0011,
|
| 1239 |
+
"grad_norm": 0.0,
|
| 1240 |
+
"learning_rate": 0.0002900260521042084,
|
| 1241 |
+
"loss": 99.44166259765625,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.0013,
|
| 1246 |
+
"grad_norm": 0.0,
|
| 1247 |
+
"learning_rate": 0.00028996593186372745,
|
| 1248 |
+
"loss": 99.43170776367188,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.0015,
|
| 1253 |
+
"grad_norm": 0.0,
|
| 1254 |
+
"learning_rate": 0.00028990581162324644,
|
| 1255 |
+
"loss": 99.37213134765625,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.0017,
|
| 1260 |
+
"grad_norm": 0.0,
|
| 1261 |
+
"learning_rate": 0.0002898456913827655,
|
| 1262 |
+
"loss": 99.51829223632812,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.0019,
|
| 1267 |
+
"grad_norm": 0.0,
|
| 1268 |
+
"learning_rate": 0.00028978557114228454,
|
| 1269 |
+
"loss": 99.27789306640625,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.0021,
|
| 1274 |
+
"grad_norm": 0.0,
|
| 1275 |
+
"learning_rate": 0.0002897254509018036,
|
| 1276 |
+
"loss": 99.44300537109375,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 3.0002,
|
| 1281 |
+
"grad_norm": 0.0,
|
| 1282 |
+
"learning_rate": 0.00028966533066132264,
|
| 1283 |
+
"loss": 103.58494873046875,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 3.0004,
|
| 1288 |
+
"grad_norm": 0.0,
|
| 1289 |
+
"learning_rate": 0.0002896052104208417,
|
| 1290 |
+
"loss": 99.35955810546875,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 3.0006,
|
| 1295 |
+
"grad_norm": 0.0,
|
| 1296 |
+
"learning_rate": 0.00028954509018036073,
|
| 1297 |
+
"loss": 99.25761108398437,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 3.0008,
|
| 1302 |
+
"grad_norm": 0.0,
|
| 1303 |
+
"learning_rate": 0.0002894849699398797,
|
| 1304 |
+
"loss": 97.34839477539063,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 3.001,
|
| 1309 |
+
"grad_norm": 0.0,
|
| 1310 |
+
"learning_rate": 0.00028942484969939877,
|
| 1311 |
+
"loss": 98.359326171875,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 3.0012,
|
| 1316 |
+
"grad_norm": 0.0,
|
| 1317 |
+
"learning_rate": 0.0002893647294589178,
|
| 1318 |
+
"loss": 99.25703735351563,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.0014,
|
| 1323 |
+
"grad_norm": 0.0,
|
| 1324 |
+
"learning_rate": 0.00028930460921843687,
|
| 1325 |
+
"loss": 99.42723388671875,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.0016,
|
| 1330 |
+
"grad_norm": 0.0,
|
| 1331 |
+
"learning_rate": 0.00028924448897795586,
|
| 1332 |
+
"loss": 99.32404174804688,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.0018,
|
| 1337 |
+
"grad_norm": 0.0,
|
| 1338 |
+
"learning_rate": 0.0002891843687374749,
|
| 1339 |
+
"loss": 99.3990966796875,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.002,
|
| 1344 |
+
"grad_norm": 0.0,
|
| 1345 |
+
"learning_rate": 0.00028912424849699396,
|
| 1346 |
+
"loss": 99.39078369140626,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 4.0001,
|
| 1351 |
+
"grad_norm": 0.0,
|
| 1352 |
+
"learning_rate": 0.000289064128256513,
|
| 1353 |
+
"loss": 104.5905517578125,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 4.0003,
|
| 1358 |
+
"grad_norm": 0.0,
|
| 1359 |
+
"learning_rate": 0.00028900400801603205,
|
| 1360 |
+
"loss": 98.17286987304688,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 4.0005,
|
| 1365 |
+
"grad_norm": 0.0,
|
| 1366 |
+
"learning_rate": 0.0002889438877755511,
|
| 1367 |
+
"loss": 99.40567016601562,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 4.0007,
|
| 1372 |
+
"grad_norm": 0.0,
|
| 1373 |
+
"learning_rate": 0.00028888376753507015,
|
| 1374 |
+
"loss": 99.32139892578125,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 4.0009,
|
| 1379 |
+
"grad_norm": 0.0,
|
| 1380 |
+
"learning_rate": 0.00028882364729458914,
|
| 1381 |
+
"loss": 96.15136108398437,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 4.0011,
|
| 1386 |
+
"grad_norm": 0.0,
|
| 1387 |
+
"learning_rate": 0.0002887635270541082,
|
| 1388 |
+
"loss": 99.3803466796875,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 4.0013,
|
| 1393 |
+
"grad_norm": 0.0,
|
| 1394 |
+
"learning_rate": 0.00028870340681362724,
|
| 1395 |
+
"loss": 99.37009887695312,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 4.0015,
|
| 1400 |
+
"grad_norm": 0.0,
|
| 1401 |
+
"learning_rate": 0.0002886432865731463,
|
| 1402 |
+
"loss": 99.310498046875,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 4.0017,
|
| 1407 |
+
"grad_norm": 0.0,
|
| 1408 |
+
"learning_rate": 0.0002885831663326653,
|
| 1409 |
+
"loss": 99.45986938476562,
|
| 1410 |
+
"step": 2000
|
| 1411 |
}
|
| 1412 |
],
|
| 1413 |
"logging_steps": 10,
|
|
|
|
| 1427 |
"attributes": {}
|
| 1428 |
}
|
| 1429 |
},
|
| 1430 |
+
"total_flos": 2.687705099497728e+16,
|
| 1431 |
"train_batch_size": 2,
|
| 1432 |
"trial_name": null,
|
| 1433 |
"trial_params": null
|