ardaspear commited on
Commit
7768856
·
verified ·
1 Parent(s): 3a25def

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:346a712ed5c1e76bef2fd3cb946bd447597ed9a19b812f1043d01d1e5d557581
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ecb247378eae6cc51626e75523106846af9507a63a454c7fda031836788c50
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfec48c8ee43b5b815faba675d9b67c035d55f83b8cec5f8f6b208f954abc2f8
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3b4768b1d7757ce3aae97a23e2f37c2a6751aa5b3964972b6ca0b46e94e1e3
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:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca5ed7077b7e80b15b5b40bb67c00bb6aeb10626f97d2892620cc3f79d1da45
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.008143690901687553,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 12.941,
306
  "eval_steps_per_second": 1.618,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.299769309790208e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00895805999185631,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 12.941,
306
  "eval_steps_per_second": 1.618,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.008415147265077139,
311
+ "grad_norm": 2.084927797317505,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 0.5326,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.008686603628466724,
318
+ "grad_norm": 1.7900018692016602,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 0.4558,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.00895805999185631,
325
+ "grad_norm": 1.933836817741394,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 0.5505,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.00895805999185631,
332
+ "eval_loss": 0.4853900074958801,
333
+ "eval_runtime": 1438.1766,
334
+ "eval_samples_per_second": 12.942,
335
+ "eval_steps_per_second": 1.618,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.4297462407692288e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null