eddysang commited on
Commit
fa806bd
·
verified ·
1 Parent(s): 729805a

Training in progress, step 200, 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:f7cf0bd9a85d6e3b1dfba727a272bb5ec1b34ad233dbee1759f9c3dc7db4c616
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f449e6f902eb194df84fb59ef322d550b739519e19976d740503f625daa19990
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:130097d8b9a1531563be49666bf68e868a3488e44a4aa76718c4310d857b5354
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eab241f4cb5154f678f29517191693974f1739f028ab1ad13f8f17e74e42022
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfcd98a6fb5e6805c0c88270935cb6243951ff273b1a434ad4ff4ae8b2aadba3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7f1a968153db435ba2ea16dda7af91d2be976734ba83d250a4aaca92fb8798
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2188426f4adaa3a6124c181a61860e824dc2136981845a9e9c4162d0d3700af6
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": 0.8666183924692252,
5
  "eval_steps": 50,
6
- "global_step": 187,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1348,6 +1348,105 @@
1348
  "learning_rate": 1.9222451411073645e-06,
1349
  "loss": 0.1704,
1350
  "step": 187
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1351
  }
1352
  ],
1353
  "logging_steps": 1,
@@ -1362,12 +1461,12 @@
1362
  "should_evaluate": false,
1363
  "should_log": false,
1364
  "should_save": true,
1365
- "should_training_stop": false
1366
  },
1367
  "attributes": {}
1368
  }
1369
  },
1370
- "total_flos": 1.1160316364382536e+18,
1371
  "train_batch_size": 2,
1372
  "trial_name": null,
1373
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9268645908761767,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1348
  "learning_rate": 1.9222451411073645e-06,
1349
  "loss": 0.1704,
1350
  "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.871252715423606,
1354
+ "grad_norm": 1.1109516620635986,
1355
+ "learning_rate": 1.6389299449645733e-06,
1356
+ "loss": 0.1539,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.875887038377987,
1361
+ "grad_norm": 1.0549452304840088,
1362
+ "learning_rate": 1.3779612414252017e-06,
1363
+ "loss": 0.1581,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.8805213613323678,
1368
+ "grad_norm": 1.1903072595596313,
1369
+ "learning_rate": 1.1394185240843983e-06,
1370
+ "loss": 0.1865,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.8851556842867487,
1375
+ "grad_norm": 1.0447423458099365,
1376
+ "learning_rate": 9.233744553646754e-07,
1377
+ "loss": 0.1562,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.8897900072411297,
1382
+ "grad_norm": 1.220670223236084,
1383
+ "learning_rate": 7.298948443822228e-07,
1384
+ "loss": 0.2248,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.8944243301955105,
1389
+ "grad_norm": 1.2653855085372925,
1390
+ "learning_rate": 5.590386269008512e-07,
1391
+ "loss": 0.135,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.8990586531498914,
1396
+ "grad_norm": 1.1455767154693604,
1397
+ "learning_rate": 4.108578473795032e-07,
1398
+ "loss": 0.1996,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 0.9036929761042722,
1403
+ "grad_norm": 1.0528533458709717,
1404
+ "learning_rate": 2.8539764311908407e-07,
1405
+ "loss": 0.1525,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 0.9083272990586532,
1410
+ "grad_norm": 1.0431491136550903,
1411
+ "learning_rate": 1.8269623051318515e-07,
1412
+ "loss": 0.1934,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 0.912961622013034,
1417
+ "grad_norm": 1.1281633377075195,
1418
+ "learning_rate": 1.027848934069625e-07,
1419
+ "loss": 0.1798,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 0.9175959449674149,
1424
+ "grad_norm": 1.1393671035766602,
1425
+ "learning_rate": 4.568797356781784e-08,
1426
+ "loss": 0.1809,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 0.9222302679217959,
1431
+ "grad_norm": 1.0485124588012695,
1432
+ "learning_rate": 1.142286327065478e-08,
1433
+ "loss": 0.1587,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 0.9268645908761767,
1438
+ "grad_norm": 0.9248851537704468,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 0.1548,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 0.9268645908761767,
1445
+ "eval_loss": 0.17866060137748718,
1446
+ "eval_runtime": 134.9791,
1447
+ "eval_samples_per_second": 5.386,
1448
+ "eval_steps_per_second": 2.697,
1449
+ "step": 200
1450
  }
1451
  ],
1452
  "logging_steps": 1,
 
1461
  "should_evaluate": false,
1462
  "should_log": false,
1463
  "should_save": true,
1464
+ "should_training_stop": true
1465
  },
1466
  "attributes": {}
1467
  }
1468
  },
1469
+ "total_flos": 1.1936167234633728e+18,
1470
  "train_batch_size": 2,
1471
  "trial_name": null,
1472
  "trial_params": null