daniel40 commited on
Commit
8da1301
·
verified ·
1 Parent(s): b96d984

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bad96fc0f157292ce44e8f62688012911d46a5651f5a65c96e85081eca7f2c6
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f92faa49a56aedd454535048b1e06924d81e2c8cc05512908905b8fd385c918
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1a2512253a404eb67322db1618bab483133ab56f83b320c9b35354b9a39fecd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5d3146d126d4bef2ee72b357c0ce17700eef2c26ce93cfd3046d888b20be9a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
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": 0.010268562401263823,
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": 19.536,
313
  "eval_steps_per_second": 9.768,
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": 1.32484893769728e+16,
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": 0.013164823591363875,
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": 19.536,
313
  "eval_steps_per_second": 9.768,
314
  "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.010531858873091101,
318
+ "grad_norm": NaN,
319
+ "learning_rate": 7.3223304703363135e-06,
320
+ "loss": 0.0,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.010795155344918378,
325
+ "grad_norm": NaN,
326
+ "learning_rate": 5.989850859999227e-06,
327
+ "loss": 0.0,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.011058451816745656,
332
+ "grad_norm": NaN,
333
+ "learning_rate": 4.7745751406263165e-06,
334
+ "loss": 0.0,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.011321748288572932,
339
+ "grad_norm": NaN,
340
+ "learning_rate": 3.6839958911476957e-06,
341
+ "loss": 0.0,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.01158504476040021,
346
+ "grad_norm": NaN,
347
+ "learning_rate": 2.7248368952908053e-06,
348
+ "loss": 0.0,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.011848341232227487,
353
+ "grad_norm": NaN,
354
+ "learning_rate": 1.9030116872178316e-06,
355
+ "loss": 0.0,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.012111637704054766,
360
+ "grad_norm": NaN,
361
+ "learning_rate": 1.2235870926211619e-06,
362
+ "loss": 0.0,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.012374934175882044,
367
+ "grad_norm": NaN,
368
+ "learning_rate": 6.907519900580861e-07,
369
+ "loss": 0.0,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.01263823064770932,
374
+ "grad_norm": NaN,
375
+ "learning_rate": 3.077914851215585e-07,
376
+ "loss": 0.0,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.012901527119536599,
381
+ "grad_norm": NaN,
382
+ "learning_rate": 7.706665667180091e-08,
383
+ "loss": 0.0,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.013164823591363875,
388
+ "grad_norm": NaN,
389
+ "learning_rate": 0.0,
390
+ "loss": 0.0,
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": 1.68977738760192e+16,
412
  "train_batch_size": 2,
413
  "trial_name": null,
414
  "trial_params": null