ardaspear commited on
Commit
74ad07f
·
verified ·
1 Parent(s): 22595fe

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 sha256:7c84d78fa64fe346d4476f396264da840148554d83dca4e3796ddaede60c3a41
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7968ea8f27d33ecdbed224cc36dcce30d5ac22603915ff584575d50e749094ca
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f19320b96b3ea3fefa7ae16d68dabd53604f289e76c13600178e2c9b902a06d
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a1c2489be25f9032b107bd162bfbee2291d7a0dd988c09b0b614ceaf045e32
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": 0.0749843782545303,
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": 13.963,
306
  "eval_steps_per_second": 1.747,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2656345471778816e+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": 0.08248281607998334,
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": 13.963,
306
  "eval_steps_per_second": 1.747,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.07748385752968132,
311
+ "grad_norm": 3.1731255054473877,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 8.0797,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.07998333680483233,
318
+ "grad_norm": 3.1508736610412598,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 8.3103,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.08248281607998334,
325
+ "grad_norm": 3.4279625415802,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 8.1608,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.08248281607998334,
332
+ "eval_loss": 2.051530122756958,
333
+ "eval_runtime": 144.7714,
334
+ "eval_samples_per_second": 13.967,
335
+ "eval_steps_per_second": 1.748,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3921980018956698e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null