Training in progress, step 5000, 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 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3f6d7fbf311f06dffa533857155833f39e492a1e6e09467737aaae7d02033d4
|
| 3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1925064044
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42d1a12a31d0f16137c80f9dbea20b2559693f564e8c041bb266e4026444a44a
|
| 3 |
size 1925064044
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fce579953b334f6cfba9152781b4b5b016a30a4024c41dd066d03ae60bfaddc7
|
| 3 |
size 14244
|
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 sha256:719b9638750507eaec42e786cd14bdd5ecf37679f81d3d2e9daed79b83274704
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./whisper-small-taiwanese-hanzi/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1163,14 +1163,303 @@
|
|
| 1163 |
"eval_samples_per_second": 2.244,
|
| 1164 |
"eval_steps_per_second": 0.281,
|
| 1165 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1166 |
}
|
| 1167 |
],
|
| 1168 |
"logging_steps": 25,
|
| 1169 |
-
"max_steps":
|
| 1170 |
"num_input_tokens_seen": 0,
|
| 1171 |
-
"num_train_epochs":
|
| 1172 |
"save_steps": 1000,
|
| 1173 |
-
"total_flos":
|
| 1174 |
"train_batch_size": 8,
|
| 1175 |
"trial_name": null,
|
| 1176 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 17.193157697590213,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-taiwanese-hanzi/checkpoint-5000",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1163 |
"eval_samples_per_second": 2.244,
|
| 1164 |
"eval_steps_per_second": 0.281,
|
| 1165 |
"step": 4000
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.6099999999999999,
|
| 1169 |
+
"grad_norm": 6.242763042449951,
|
| 1170 |
+
"learning_rate": 5.520833333333334e-06,
|
| 1171 |
+
"loss": 0.1892,
|
| 1172 |
+
"step": 4025
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.62,
|
| 1176 |
+
"grad_norm": 7.155097007751465,
|
| 1177 |
+
"learning_rate": 5.486111111111112e-06,
|
| 1178 |
+
"loss": 0.2207,
|
| 1179 |
+
"step": 4050
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.63,
|
| 1183 |
+
"grad_norm": 10.018449783325195,
|
| 1184 |
+
"learning_rate": 5.451388888888889e-06,
|
| 1185 |
+
"loss": 0.2497,
|
| 1186 |
+
"step": 4075
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.6400000000000001,
|
| 1190 |
+
"grad_norm": 9.636473655700684,
|
| 1191 |
+
"learning_rate": 5.416666666666667e-06,
|
| 1192 |
+
"loss": 0.2356,
|
| 1193 |
+
"step": 4100
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.65,
|
| 1197 |
+
"grad_norm": 8.315143585205078,
|
| 1198 |
+
"learning_rate": 5.381944444444445e-06,
|
| 1199 |
+
"loss": 0.2333,
|
| 1200 |
+
"step": 4125
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.6600000000000001,
|
| 1204 |
+
"grad_norm": 8.561467170715332,
|
| 1205 |
+
"learning_rate": 5.347222222222222e-06,
|
| 1206 |
+
"loss": 0.2205,
|
| 1207 |
+
"step": 4150
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.67,
|
| 1211 |
+
"grad_norm": 5.167340278625488,
|
| 1212 |
+
"learning_rate": 5.3125e-06,
|
| 1213 |
+
"loss": 0.221,
|
| 1214 |
+
"step": 4175
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.6800000000000002,
|
| 1218 |
+
"grad_norm": 6.219302654266357,
|
| 1219 |
+
"learning_rate": 5.2777777777777785e-06,
|
| 1220 |
+
"loss": 0.2057,
|
| 1221 |
+
"step": 4200
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.69,
|
| 1225 |
+
"grad_norm": 7.842504501342773,
|
| 1226 |
+
"learning_rate": 5.243055555555556e-06,
|
| 1227 |
+
"loss": 0.2239,
|
| 1228 |
+
"step": 4225
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.7,
|
| 1232 |
+
"grad_norm": 5.829674243927002,
|
| 1233 |
+
"learning_rate": 5.208333333333334e-06,
|
| 1234 |
+
"loss": 0.2304,
|
| 1235 |
+
"step": 4250
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.71,
|
| 1239 |
+
"grad_norm": 10.23341178894043,
|
| 1240 |
+
"learning_rate": 5.173611111111112e-06,
|
| 1241 |
+
"loss": 0.2134,
|
| 1242 |
+
"step": 4275
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.72,
|
| 1246 |
+
"grad_norm": 5.533736228942871,
|
| 1247 |
+
"learning_rate": 5.138888888888889e-06,
|
| 1248 |
+
"loss": 0.2122,
|
| 1249 |
+
"step": 4300
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.73,
|
| 1253 |
+
"grad_norm": 9.650428771972656,
|
| 1254 |
+
"learning_rate": 5.104166666666667e-06,
|
| 1255 |
+
"loss": 0.2256,
|
| 1256 |
+
"step": 4325
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.74,
|
| 1260 |
+
"grad_norm": 7.121572494506836,
|
| 1261 |
+
"learning_rate": 5.069444444444445e-06,
|
| 1262 |
+
"loss": 0.2365,
|
| 1263 |
+
"step": 4350
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.75,
|
| 1267 |
+
"grad_norm": 5.643657207489014,
|
| 1268 |
+
"learning_rate": 5.034722222222222e-06,
|
| 1269 |
+
"loss": 0.1922,
|
| 1270 |
+
"step": 4375
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.76,
|
| 1274 |
+
"grad_norm": 7.42201042175293,
|
| 1275 |
+
"learning_rate": 5e-06,
|
| 1276 |
+
"loss": 0.2238,
|
| 1277 |
+
"step": 4400
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.77,
|
| 1281 |
+
"grad_norm": 7.345561981201172,
|
| 1282 |
+
"learning_rate": 4.9652777777777786e-06,
|
| 1283 |
+
"loss": 0.2236,
|
| 1284 |
+
"step": 4425
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.78,
|
| 1288 |
+
"grad_norm": 5.476310729980469,
|
| 1289 |
+
"learning_rate": 4.930555555555556e-06,
|
| 1290 |
+
"loss": 0.2232,
|
| 1291 |
+
"step": 4450
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.79,
|
| 1295 |
+
"grad_norm": 9.794219970703125,
|
| 1296 |
+
"learning_rate": 4.895833333333333e-06,
|
| 1297 |
+
"loss": 0.2352,
|
| 1298 |
+
"step": 4475
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.8,
|
| 1302 |
+
"grad_norm": 8.994114875793457,
|
| 1303 |
+
"learning_rate": 4.861111111111111e-06,
|
| 1304 |
+
"loss": 0.2164,
|
| 1305 |
+
"step": 4500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.81,
|
| 1309 |
+
"grad_norm": 8.589949607849121,
|
| 1310 |
+
"learning_rate": 4.8263888888888895e-06,
|
| 1311 |
+
"loss": 0.2062,
|
| 1312 |
+
"step": 4525
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.8199999999999998,
|
| 1316 |
+
"grad_norm": 6.32391881942749,
|
| 1317 |
+
"learning_rate": 4.791666666666668e-06,
|
| 1318 |
+
"loss": 0.2476,
|
| 1319 |
+
"step": 4550
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.83,
|
| 1323 |
+
"grad_norm": 7.506887435913086,
|
| 1324 |
+
"learning_rate": 4.756944444444445e-06,
|
| 1325 |
+
"loss": 0.2243,
|
| 1326 |
+
"step": 4575
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.8399999999999999,
|
| 1330 |
+
"grad_norm": 5.173837661743164,
|
| 1331 |
+
"learning_rate": 4.722222222222222e-06,
|
| 1332 |
+
"loss": 0.1789,
|
| 1333 |
+
"step": 4600
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.85,
|
| 1337 |
+
"grad_norm": 7.828786849975586,
|
| 1338 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 1339 |
+
"loss": 0.2138,
|
| 1340 |
+
"step": 4625
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.8599999999999999,
|
| 1344 |
+
"grad_norm": 6.593687057495117,
|
| 1345 |
+
"learning_rate": 4.652777777777779e-06,
|
| 1346 |
+
"loss": 0.2238,
|
| 1347 |
+
"step": 4650
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.87,
|
| 1351 |
+
"grad_norm": 8.0968599319458,
|
| 1352 |
+
"learning_rate": 4.618055555555556e-06,
|
| 1353 |
+
"loss": 0.2038,
|
| 1354 |
+
"step": 4675
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.88,
|
| 1358 |
+
"grad_norm": 7.589450359344482,
|
| 1359 |
+
"learning_rate": 4.583333333333333e-06,
|
| 1360 |
+
"loss": 0.203,
|
| 1361 |
+
"step": 4700
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.8900000000000001,
|
| 1365 |
+
"grad_norm": 10.24547004699707,
|
| 1366 |
+
"learning_rate": 4.548611111111111e-06,
|
| 1367 |
+
"loss": 0.2468,
|
| 1368 |
+
"step": 4725
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.9,
|
| 1372 |
+
"grad_norm": 6.878439426422119,
|
| 1373 |
+
"learning_rate": 4.5138888888888895e-06,
|
| 1374 |
+
"loss": 0.1983,
|
| 1375 |
+
"step": 4750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.9100000000000001,
|
| 1379 |
+
"grad_norm": 5.918954372406006,
|
| 1380 |
+
"learning_rate": 4.479166666666667e-06,
|
| 1381 |
+
"loss": 0.1921,
|
| 1382 |
+
"step": 4775
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.92,
|
| 1386 |
+
"grad_norm": 10.184906005859375,
|
| 1387 |
+
"learning_rate": 4.444444444444444e-06,
|
| 1388 |
+
"loss": 0.1898,
|
| 1389 |
+
"step": 4800
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.9300000000000002,
|
| 1393 |
+
"grad_norm": 8.617950439453125,
|
| 1394 |
+
"learning_rate": 4.409722222222222e-06,
|
| 1395 |
+
"loss": 0.1916,
|
| 1396 |
+
"step": 4825
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.94,
|
| 1400 |
+
"grad_norm": 5.356297969818115,
|
| 1401 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 1402 |
+
"loss": 0.1844,
|
| 1403 |
+
"step": 4850
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.95,
|
| 1407 |
+
"grad_norm": 6.3137030601501465,
|
| 1408 |
+
"learning_rate": 4.340277777777779e-06,
|
| 1409 |
+
"loss": 0.2078,
|
| 1410 |
+
"step": 4875
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.96,
|
| 1414 |
+
"grad_norm": 5.769162178039551,
|
| 1415 |
+
"learning_rate": 4.305555555555556e-06,
|
| 1416 |
+
"loss": 0.2193,
|
| 1417 |
+
"step": 4900
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.97,
|
| 1421 |
+
"grad_norm": 8.022501945495605,
|
| 1422 |
+
"learning_rate": 4.270833333333333e-06,
|
| 1423 |
+
"loss": 0.2296,
|
| 1424 |
+
"step": 4925
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.98,
|
| 1428 |
+
"grad_norm": 6.754506587982178,
|
| 1429 |
+
"learning_rate": 4.236111111111111e-06,
|
| 1430 |
+
"loss": 0.226,
|
| 1431 |
+
"step": 4950
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.99,
|
| 1435 |
+
"grad_norm": 6.45380163192749,
|
| 1436 |
+
"learning_rate": 4.2013888888888896e-06,
|
| 1437 |
+
"loss": 0.1871,
|
| 1438 |
+
"step": 4975
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.0,
|
| 1442 |
+
"grad_norm": 5.92453145980835,
|
| 1443 |
+
"learning_rate": 4.166666666666667e-06,
|
| 1444 |
+
"loss": 0.2223,
|
| 1445 |
+
"step": 5000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.0,
|
| 1449 |
+
"eval_cer": 17.193157697590213,
|
| 1450 |
+
"eval_loss": 0.29516366124153137,
|
| 1451 |
+
"eval_runtime": 1741.8319,
|
| 1452 |
+
"eval_samples_per_second": 2.26,
|
| 1453 |
+
"eval_steps_per_second": 0.282,
|
| 1454 |
+
"step": 5000
|
| 1455 |
}
|
| 1456 |
],
|
| 1457 |
"logging_steps": 25,
|
| 1458 |
+
"max_steps": 8000,
|
| 1459 |
"num_input_tokens_seen": 0,
|
| 1460 |
+
"num_train_epochs": 4,
|
| 1461 |
"save_steps": 1000,
|
| 1462 |
+
"total_flos": 2.30868320256e+19,
|
| 1463 |
"train_batch_size": 8,
|
| 1464 |
"trial_name": null,
|
| 1465 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3de5b9bda0f933887f039c8c86c5054848a6cee2f3d7f8f9e5d030a92f7f5ad
|
| 3 |
size 5176
|