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:fc2f5c96cac3818f65cfd5c9cbbc938181590aa22a40157a415da73638fe8d56
|
| 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:eb30c79faba064019e635c6d628696fb39cb276fc2d4ab8f2a4fd879b16ae848
|
| 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:c46cde2c439b7b077df619cfbbcd27c19f63a4087af7587647d8e592b96a4377
|
| 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:baa6eb8a5862db08b04e41465494b9c605adfbffdf8261b4c134e0597e77bdcd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 52.
|
| 3 |
-
"best_model_checkpoint": "./whisper-small-or/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,
|
|
@@ -1163,6 +1163,295 @@
|
|
| 1163 |
"eval_steps_per_second": 0.116,
|
| 1164 |
"eval_wer": 52.628043660789245,
|
| 1165 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1166 |
}
|
| 1167 |
],
|
| 1168 |
"logging_steps": 25,
|
|
@@ -1177,12 +1466,12 @@
|
|
| 1177 |
"should_evaluate": false,
|
| 1178 |
"should_log": false,
|
| 1179 |
"should_save": true,
|
| 1180 |
-
"should_training_stop":
|
| 1181 |
},
|
| 1182 |
"attributes": {}
|
| 1183 |
}
|
| 1184 |
},
|
| 1185 |
-
"total_flos":
|
| 1186 |
"train_batch_size": 16,
|
| 1187 |
"trial_name": null,
|
| 1188 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 52.426532325776655,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-or/checkpoint-5000",
|
| 4 |
+
"epoch": 39.0625,
|
| 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_steps_per_second": 0.116,
|
| 1164 |
"eval_wer": 52.628043660789245,
|
| 1165 |
"step": 4000
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 31.4453125,
|
| 1169 |
+
"grad_norm": 0.0038889453280717134,
|
| 1170 |
+
"learning_rate": 2.1755555555555556e-06,
|
| 1171 |
+
"loss": 0.0,
|
| 1172 |
+
"step": 4025
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 31.640625,
|
| 1176 |
+
"grad_norm": 0.003946984186768532,
|
| 1177 |
+
"learning_rate": 2.12e-06,
|
| 1178 |
+
"loss": 0.0,
|
| 1179 |
+
"step": 4050
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 31.8359375,
|
| 1183 |
+
"grad_norm": 0.003195575438439846,
|
| 1184 |
+
"learning_rate": 2.064444444444445e-06,
|
| 1185 |
+
"loss": 0.0,
|
| 1186 |
+
"step": 4075
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 32.03125,
|
| 1190 |
+
"grad_norm": 0.004425502847880125,
|
| 1191 |
+
"learning_rate": 2.008888888888889e-06,
|
| 1192 |
+
"loss": 0.0,
|
| 1193 |
+
"step": 4100
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 32.2265625,
|
| 1197 |
+
"grad_norm": 0.003221447579562664,
|
| 1198 |
+
"learning_rate": 1.9533333333333334e-06,
|
| 1199 |
+
"loss": 0.0,
|
| 1200 |
+
"step": 4125
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 32.421875,
|
| 1204 |
+
"grad_norm": 0.004509610123932362,
|
| 1205 |
+
"learning_rate": 1.8977777777777779e-06,
|
| 1206 |
+
"loss": 0.0,
|
| 1207 |
+
"step": 4150
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 32.6171875,
|
| 1211 |
+
"grad_norm": 0.003536405274644494,
|
| 1212 |
+
"learning_rate": 1.8422222222222225e-06,
|
| 1213 |
+
"loss": 0.0,
|
| 1214 |
+
"step": 4175
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 32.8125,
|
| 1218 |
+
"grad_norm": 0.004426420200616121,
|
| 1219 |
+
"learning_rate": 1.7866666666666668e-06,
|
| 1220 |
+
"loss": 0.0,
|
| 1221 |
+
"step": 4200
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 33.0078125,
|
| 1225 |
+
"grad_norm": 0.003728843992576003,
|
| 1226 |
+
"learning_rate": 1.7311111111111112e-06,
|
| 1227 |
+
"loss": 0.0,
|
| 1228 |
+
"step": 4225
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 33.203125,
|
| 1232 |
+
"grad_norm": 0.0036569128278642893,
|
| 1233 |
+
"learning_rate": 1.675555555555556e-06,
|
| 1234 |
+
"loss": 0.0,
|
| 1235 |
+
"step": 4250
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 33.3984375,
|
| 1239 |
+
"grad_norm": 0.004421570338308811,
|
| 1240 |
+
"learning_rate": 1.6200000000000002e-06,
|
| 1241 |
+
"loss": 0.0,
|
| 1242 |
+
"step": 4275
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 33.59375,
|
| 1246 |
+
"grad_norm": 0.003550709690898657,
|
| 1247 |
+
"learning_rate": 1.5644444444444446e-06,
|
| 1248 |
+
"loss": 0.0,
|
| 1249 |
+
"step": 4300
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 33.7890625,
|
| 1253 |
+
"grad_norm": 0.003777899779379368,
|
| 1254 |
+
"learning_rate": 1.5088888888888889e-06,
|
| 1255 |
+
"loss": 0.0,
|
| 1256 |
+
"step": 4325
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 33.984375,
|
| 1260 |
+
"grad_norm": 0.002803810639306903,
|
| 1261 |
+
"learning_rate": 1.4533333333333335e-06,
|
| 1262 |
+
"loss": 0.0,
|
| 1263 |
+
"step": 4350
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 34.1796875,
|
| 1267 |
+
"grad_norm": 0.0037676438223570585,
|
| 1268 |
+
"learning_rate": 1.397777777777778e-06,
|
| 1269 |
+
"loss": 0.0,
|
| 1270 |
+
"step": 4375
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 34.375,
|
| 1274 |
+
"grad_norm": 0.00398740591481328,
|
| 1275 |
+
"learning_rate": 1.3422222222222222e-06,
|
| 1276 |
+
"loss": 0.0,
|
| 1277 |
+
"step": 4400
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 34.5703125,
|
| 1281 |
+
"grad_norm": 0.003252105787396431,
|
| 1282 |
+
"learning_rate": 1.286666666666667e-06,
|
| 1283 |
+
"loss": 0.0,
|
| 1284 |
+
"step": 4425
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 34.765625,
|
| 1288 |
+
"grad_norm": 0.004870784468948841,
|
| 1289 |
+
"learning_rate": 1.2311111111111112e-06,
|
| 1290 |
+
"loss": 0.0,
|
| 1291 |
+
"step": 4450
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 34.9609375,
|
| 1295 |
+
"grad_norm": 0.0036819297820329666,
|
| 1296 |
+
"learning_rate": 1.1755555555555556e-06,
|
| 1297 |
+
"loss": 0.0,
|
| 1298 |
+
"step": 4475
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 35.15625,
|
| 1302 |
+
"grad_norm": 0.003786075860261917,
|
| 1303 |
+
"learning_rate": 1.12e-06,
|
| 1304 |
+
"loss": 0.0,
|
| 1305 |
+
"step": 4500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 35.3515625,
|
| 1309 |
+
"grad_norm": 0.004635694436728954,
|
| 1310 |
+
"learning_rate": 1.0644444444444445e-06,
|
| 1311 |
+
"loss": 0.0,
|
| 1312 |
+
"step": 4525
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 35.546875,
|
| 1316 |
+
"grad_norm": 0.003975734580308199,
|
| 1317 |
+
"learning_rate": 1.008888888888889e-06,
|
| 1318 |
+
"loss": 0.0,
|
| 1319 |
+
"step": 4550
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 35.7421875,
|
| 1323 |
+
"grad_norm": 0.0033323836978524923,
|
| 1324 |
+
"learning_rate": 9.533333333333335e-07,
|
| 1325 |
+
"loss": 0.0,
|
| 1326 |
+
"step": 4575
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 35.9375,
|
| 1330 |
+
"grad_norm": 0.003018638351932168,
|
| 1331 |
+
"learning_rate": 8.977777777777778e-07,
|
| 1332 |
+
"loss": 0.0,
|
| 1333 |
+
"step": 4600
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 36.1328125,
|
| 1337 |
+
"grad_norm": 0.0025316779501736164,
|
| 1338 |
+
"learning_rate": 8.422222222222224e-07,
|
| 1339 |
+
"loss": 0.0,
|
| 1340 |
+
"step": 4625
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 36.328125,
|
| 1344 |
+
"grad_norm": 0.0029895787592977285,
|
| 1345 |
+
"learning_rate": 7.866666666666667e-07,
|
| 1346 |
+
"loss": 0.0,
|
| 1347 |
+
"step": 4650
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 36.5234375,
|
| 1351 |
+
"grad_norm": 0.0027492698282003403,
|
| 1352 |
+
"learning_rate": 7.311111111111112e-07,
|
| 1353 |
+
"loss": 0.0,
|
| 1354 |
+
"step": 4675
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 36.71875,
|
| 1358 |
+
"grad_norm": 0.002066458808258176,
|
| 1359 |
+
"learning_rate": 6.755555555555555e-07,
|
| 1360 |
+
"loss": 0.0,
|
| 1361 |
+
"step": 4700
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 36.9140625,
|
| 1365 |
+
"grad_norm": 0.003311043605208397,
|
| 1366 |
+
"learning_rate": 6.200000000000001e-07,
|
| 1367 |
+
"loss": 0.0,
|
| 1368 |
+
"step": 4725
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 37.109375,
|
| 1372 |
+
"grad_norm": 0.002838843734934926,
|
| 1373 |
+
"learning_rate": 5.644444444444445e-07,
|
| 1374 |
+
"loss": 0.0,
|
| 1375 |
+
"step": 4750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 37.3046875,
|
| 1379 |
+
"grad_norm": 0.0030876589007675648,
|
| 1380 |
+
"learning_rate": 5.088888888888889e-07,
|
| 1381 |
+
"loss": 0.0,
|
| 1382 |
+
"step": 4775
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 37.5,
|
| 1386 |
+
"grad_norm": 0.002636523451656103,
|
| 1387 |
+
"learning_rate": 4.533333333333334e-07,
|
| 1388 |
+
"loss": 0.0,
|
| 1389 |
+
"step": 4800
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 37.6953125,
|
| 1393 |
+
"grad_norm": 0.0028531572315841913,
|
| 1394 |
+
"learning_rate": 3.9777777777777783e-07,
|
| 1395 |
+
"loss": 0.0,
|
| 1396 |
+
"step": 4825
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 37.890625,
|
| 1400 |
+
"grad_norm": 0.0033609780948609114,
|
| 1401 |
+
"learning_rate": 3.422222222222223e-07,
|
| 1402 |
+
"loss": 0.0,
|
| 1403 |
+
"step": 4850
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 38.0859375,
|
| 1407 |
+
"grad_norm": 0.0024441394489258528,
|
| 1408 |
+
"learning_rate": 2.866666666666667e-07,
|
| 1409 |
+
"loss": 0.0,
|
| 1410 |
+
"step": 4875
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 38.28125,
|
| 1414 |
+
"grad_norm": 0.002934487536549568,
|
| 1415 |
+
"learning_rate": 2.3111111111111112e-07,
|
| 1416 |
+
"loss": 0.0,
|
| 1417 |
+
"step": 4900
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 38.4765625,
|
| 1421 |
+
"grad_norm": 0.002934112912043929,
|
| 1422 |
+
"learning_rate": 1.7555555555555558e-07,
|
| 1423 |
+
"loss": 0.0,
|
| 1424 |
+
"step": 4925
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 38.671875,
|
| 1428 |
+
"grad_norm": 0.00293625146150589,
|
| 1429 |
+
"learning_rate": 1.2000000000000002e-07,
|
| 1430 |
+
"loss": 0.0,
|
| 1431 |
+
"step": 4950
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 38.8671875,
|
| 1435 |
+
"grad_norm": 0.003216015174984932,
|
| 1436 |
+
"learning_rate": 6.444444444444445e-08,
|
| 1437 |
+
"loss": 0.0,
|
| 1438 |
+
"step": 4975
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 39.0625,
|
| 1442 |
+
"grad_norm": 0.003249627770856023,
|
| 1443 |
+
"learning_rate": 8.88888888888889e-09,
|
| 1444 |
+
"loss": 0.0,
|
| 1445 |
+
"step": 5000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 39.0625,
|
| 1449 |
+
"eval_loss": 0.36558446288108826,
|
| 1450 |
+
"eval_runtime": 777.8187,
|
| 1451 |
+
"eval_samples_per_second": 0.895,
|
| 1452 |
+
"eval_steps_per_second": 0.112,
|
| 1453 |
+
"eval_wer": 52.426532325776655,
|
| 1454 |
+
"step": 5000
|
| 1455 |
}
|
| 1456 |
],
|
| 1457 |
"logging_steps": 25,
|
|
|
|
| 1466 |
"should_evaluate": false,
|
| 1467 |
"should_log": false,
|
| 1468 |
"should_save": true,
|
| 1469 |
+
"should_training_stop": true
|
| 1470 |
},
|
| 1471 |
"attributes": {}
|
| 1472 |
}
|
| 1473 |
},
|
| 1474 |
+
"total_flos": 2.30868320256e+19,
|
| 1475 |
"train_batch_size": 16,
|
| 1476 |
"trial_name": null,
|
| 1477 |
"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 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:698b2142451bdf12f18341959c86e35236ca3ee806d70ff10cda10798130acfb
|
| 3 |
size 5368
|