kooff11 commited on
Commit
08a607f
1 Parent(s): 204ea09

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 sha256:1f4a7691e7cd2fe5785a78bf212d26aadf3c814be08b43ca6e24094b93d1b632
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2788df99e965d8ae8e0f1de7c97c40bfb428cb17932d5cecc21060b7ec3c567
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69815d0b02d4093787212496ad1c2421e8902a92e6bb004f8d5dfeda4e261b07
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd02f4f58c2fab83f6a63f5484ec28dc69257c4bdac454028bba822aabd61bb
3
  size 81730196
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc0d6a68d922e782698a018376b53b85027f73e542c47378e687b580096f86bd
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515ed9c683dff41b64c1d3a2ae8782a348f041debee6ea93d6dd2fcee4c2fcd4
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 sha256:57c230e4a3d3176d8f4a84949e99fccf4bc6db16aab7ec60a204be03a7a4d58c
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2ce6466218d3478f547123414311551be483ec15bd6249d9e7ad7c1f4b6834
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": 0.5485714285714286,
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": 11.598,
313
  "eval_steps_per_second": 2.906,
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": 8.227198361602621e+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": 0.7032967032967034,
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": 11.598,
313
  "eval_steps_per_second": 2.906,
314
  "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.5626373626373626,
318
+ "grad_norm": 0.09625887870788574,
319
+ "learning_rate": 1.0332332985438248e-05,
320
+ "loss": 0.7666,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.5767032967032967,
325
+ "grad_norm": 0.09051655977964401,
326
+ "learning_rate": 8.426519384872733e-06,
327
+ "loss": 0.7939,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.5907692307692308,
332
+ "grad_norm": 0.09801479429006577,
333
+ "learning_rate": 6.698729810778065e-06,
334
+ "loss": 0.762,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.6048351648351649,
339
+ "grad_norm": 0.0950697809457779,
340
+ "learning_rate": 5.156362923365588e-06,
341
+ "loss": 0.8127,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.6189010989010989,
346
+ "grad_norm": 0.08845943212509155,
347
+ "learning_rate": 3.8060233744356633e-06,
348
+ "loss": 0.7691,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.6329670329670329,
353
+ "grad_norm": 0.09417203068733215,
354
+ "learning_rate": 2.653493525244721e-06,
355
+ "loss": 0.7847,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.6470329670329671,
360
+ "grad_norm": 0.09285993129014969,
361
+ "learning_rate": 1.70370868554659e-06,
362
+ "loss": 0.7798,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.6610989010989011,
367
+ "grad_norm": 0.09379366785287857,
368
+ "learning_rate": 9.607359798384785e-07,
369
+ "loss": 0.7899,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.6751648351648352,
374
+ "grad_norm": 0.08996466547250748,
375
+ "learning_rate": 4.277569313094809e-07,
376
+ "loss": 0.8066,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.6892307692307692,
381
+ "grad_norm": 0.09068991243839264,
382
+ "learning_rate": 1.0705383806982606e-07,
383
+ "loss": 0.7763,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.7032967032967034,
388
+ "grad_norm": 0.089011549949646,
389
+ "learning_rate": 0.0,
390
+ "loss": 0.7753,
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": 1.0547690207182848e+18,
412
  "train_batch_size": 2,
413
  "trial_name": null,
414
  "trial_params": null