JacksonBrune commited on
Commit
bef3efb
·
verified ·
1 Parent(s): 158f76b

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 sha256:8d7d1d663eee9d03610894cf9891e771941ed44aa423cf9e09760175ab89551f
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d2d1c0b5f0aa2ea21d2c16d8dc5339483136022eb1410715c98855dc839676
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb2aa411998839126dc9a33971bb148bed5fa8f2075b5a14a161e44bd29a5aa0
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a739d9ccb7ed5797f049a2381d821bece7613c7786bbd47a8e259101d2a5a56
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fd083083ffc4ff5e9889cb3b5746ee13bdec6c321e3a20459cc07659b35732a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf80d1d382846753edb3815bd695a650c0152c9e3ca52a4fac5961973d3d231
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.11337209302325581,
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": 43.877,
313
  "eval_steps_per_second": 22.09,
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": 1313407946981376.0,
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": 0.14534883720930233,
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": 43.877,
313
  "eval_steps_per_second": 22.09,
314
  "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.11627906976744186,
318
+ "grad_norm": 1.8356800079345703,
319
+ "learning_rate": 2.9289321881345254e-05,
320
+ "loss": 1.1591,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.11918604651162791,
325
+ "grad_norm": 1.1142281293869019,
326
+ "learning_rate": 2.3959403439996907e-05,
327
+ "loss": 0.8613,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.12209302325581395,
332
+ "grad_norm": 0.9527114033699036,
333
+ "learning_rate": 1.9098300562505266e-05,
334
+ "loss": 1.1051,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.125,
339
+ "grad_norm": 1.4872461557388306,
340
+ "learning_rate": 1.4735983564590783e-05,
341
+ "loss": 1.3144,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.12790697674418605,
346
+ "grad_norm": 1.226185917854309,
347
+ "learning_rate": 1.0899347581163221e-05,
348
+ "loss": 0.9364,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.1308139534883721,
353
+ "grad_norm": 1.308918833732605,
354
+ "learning_rate": 7.612046748871327e-06,
355
+ "loss": 1.1557,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.13372093023255813,
360
+ "grad_norm": 1.6258533000946045,
361
+ "learning_rate": 4.8943483704846475e-06,
362
+ "loss": 1.3549,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.13662790697674418,
367
+ "grad_norm": 1.2242059707641602,
368
+ "learning_rate": 2.7630079602323442e-06,
369
+ "loss": 1.3049,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.13953488372093023,
374
+ "grad_norm": 1.0847722291946411,
375
+ "learning_rate": 1.231165940486234e-06,
376
+ "loss": 1.2514,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.14244186046511628,
381
+ "grad_norm": 1.0979931354522705,
382
+ "learning_rate": 3.0826662668720364e-07,
383
+ "loss": 1.0986,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.14534883720930233,
388
+ "grad_norm": 1.105636715888977,
389
+ "learning_rate": 0.0,
390
+ "loss": 1.0533,
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": 1678243487809536.0,
412
  "train_batch_size": 2,
413
  "trial_name": null,
414
  "trial_params": null