kooff11 commited on
Commit
314d4b8
1 Parent(s): ad41e1b

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5db0b95c8c3a10a91524dea9aacebbfcfbb9dde2761ab991c8022e2fe6df4272
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0de506237fa113a2fd8e2182822ff8a821a09e0354a4b5a17ff551f1db77f2
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7586701c2e5e163ffc989df0f584bccf4e69f337fc17cdc68d4a10f7bdc4838f
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ccf17ed59b9de1079f1a92c36a2136ba5bc1559fc004dccc6de6b360d39d141
3
  size 85723284
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9177d90829d7463e0eb174ca56deba825ef7d7ca018aa2c22064a61c74ca9ea
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bafc2657b0a3e6a4b0e7fc69b71615dc4096f125d954396fe9bf1b44c8e28f
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99c176154c32f3c6148d434b4181fc39da3594f48ce393bb9e59b1fd24bca4d
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.2884215391726369,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -312,6 +312,83 @@
312
  "eval_samples_per_second": 11.194,
313
  "eval_steps_per_second": 2.802,
314
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
315
  }
316
  ],
317
  "logging_steps": 1,
@@ -326,12 +403,12 @@
326
  "should_evaluate": false,
327
  "should_log": false,
328
  "should_save": true,
329
- "should_training_stop": false
330
  },
331
  "attributes": {}
332
  }
333
  },
334
- "total_flos": 8.775066193766646e+17,
335
  "train_batch_size": 2,
336
  "trial_name": null,
337
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.36977120406748326,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
312
  "eval_samples_per_second": 11.194,
313
  "eval_steps_per_second": 2.802,
314
  "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.2958169632539866,
318
+ "grad_norm": 40.7790412902832,
319
+ "learning_rate": 1.0332332985438248e-05,
320
+ "loss": 80.1685,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.3032123873353363,
325
+ "grad_norm": 44.15685272216797,
326
+ "learning_rate": 8.426519384872733e-06,
327
+ "loss": 83.519,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3106078114166859,
332
+ "grad_norm": 33.223167419433594,
333
+ "learning_rate": 6.698729810778065e-06,
334
+ "loss": 74.8312,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.3180032354980356,
339
+ "grad_norm": 42.13229751586914,
340
+ "learning_rate": 5.156362923365588e-06,
341
+ "loss": 79.9294,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.32539865957938524,
346
+ "grad_norm": 36.99294662475586,
347
+ "learning_rate": 3.8060233744356633e-06,
348
+ "loss": 78.9502,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.33279408366073493,
353
+ "grad_norm": 40.4399528503418,
354
+ "learning_rate": 2.653493525244721e-06,
355
+ "loss": 82.6471,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.34018950774208456,
360
+ "grad_norm": 40.24978256225586,
361
+ "learning_rate": 1.70370868554659e-06,
362
+ "loss": 82.7816,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.34758493182343425,
367
+ "grad_norm": 42.67814254760742,
368
+ "learning_rate": 9.607359798384785e-07,
369
+ "loss": 80.2397,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.35498035590478394,
374
+ "grad_norm": 37.027217864990234,
375
+ "learning_rate": 4.277569313094809e-07,
376
+ "loss": 80.1654,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.3623757799861336,
381
+ "grad_norm": 44.58671951293945,
382
+ "learning_rate": 1.0705383806982606e-07,
383
+ "loss": 79.761,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.36977120406748326,
388
+ "grad_norm": 44.38752746582031,
389
+ "learning_rate": 0.0,
390
+ "loss": 76.1375,
391
+ "step": 50
392
  }
393
  ],
394
  "logging_steps": 1,
 
403
  "should_evaluate": false,
404
  "should_log": false,
405
  "should_save": true,
406
+ "should_training_stop": true
407
  },
408
  "attributes": {}
409
  }
410
  },
411
+ "total_flos": 1.1250084863803392e+18,
412
  "train_batch_size": 2,
413
  "trial_name": null,
414
  "trial_params": null