VERSIL91 commited on
Commit
088cbe7
1 Parent(s): f443b91

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:e55e6d665b918ef85f7d7f06c6ec2625973fd8fe4f5d77e51c8ecaca5b32c06d
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf42fee1937229bb4866196d03b924e992b079749193af99d04e13e3d386b61
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5169d9ca6a90067573fdd06f9afed26007d92a8b966d22131778f4138bd19b3e
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138ea561b213bb3b2705216dcbc86fa19a0c97d08350da850804b14385a36a86
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c72461d8b102f8348796119289aad1a7993b551f980fac40ec203302a5c72e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e9eae442f771da3806c99b5cd6522f74f754ffe88b669e7b10de01669cb969
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.030456852791878174,
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": 7.186,
313
  "eval_steps_per_second": 3.595,
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": 2.1937640358857933e+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": 0.03904724716907458,
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": 7.186,
313
  "eval_steps_per_second": 3.595,
314
  "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.031237797735259663,
318
+ "grad_norm": 47.26570510864258,
319
+ "learning_rate": 1.4644660940672627e-05,
320
+ "loss": 12.213,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.03201874267864115,
325
+ "grad_norm": 37.84298324584961,
326
+ "learning_rate": 1.1979701719998453e-05,
327
+ "loss": 12.9798,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.03279968762202265,
332
+ "grad_norm": 37.72480773925781,
333
+ "learning_rate": 9.549150281252633e-06,
334
+ "loss": 10.6722,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.03358063256540414,
339
+ "grad_norm": 44.485225677490234,
340
+ "learning_rate": 7.367991782295391e-06,
341
+ "loss": 12.6417,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.03436157750878563,
346
+ "grad_norm": 36.807350158691406,
347
+ "learning_rate": 5.449673790581611e-06,
348
+ "loss": 11.1903,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.035142522452167126,
353
+ "grad_norm": 34.367584228515625,
354
+ "learning_rate": 3.8060233744356633e-06,
355
+ "loss": 11.6601,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.035923467395548615,
360
+ "grad_norm": 48.056583404541016,
361
+ "learning_rate": 2.4471741852423237e-06,
362
+ "loss": 13.341,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.036704412338930105,
367
+ "grad_norm": 46.177330017089844,
368
+ "learning_rate": 1.3815039801161721e-06,
369
+ "loss": 13.4865,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.037485357282311595,
374
+ "grad_norm": 54.51680374145508,
375
+ "learning_rate": 6.15582970243117e-07,
376
+ "loss": 12.0828,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.03826630222569309,
381
+ "grad_norm": 43.835418701171875,
382
+ "learning_rate": 1.5413331334360182e-07,
383
+ "loss": 12.4233,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.03904724716907458,
388
+ "grad_norm": 44.20928955078125,
389
+ "learning_rate": 0.0,
390
+ "loss": 13.5881,
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": 2.812517994725376e+17,
412
  "train_batch_size": 2,
413
  "trial_name": null,
414
  "trial_params": null