dixedus commited on
Commit
1f21b0c
·
verified ·
1 Parent(s): 3d984ab

Training in progress, step 81, 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:fec2536c5cc3f6066e23a7f2da7de15348c7b7d8801388a7a4b27222eec59555
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b7b75f8a69719f02aabdde3890302e64a78270e61f2930ec42ddef7c987205
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7da0063208795cf88527b4db364a79f1e4214d461125cbeff58288b5cd915c7
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e77a2dfd19149078ca60a1a056168fe7aeb6992d3ffe0f5dff4f95a97b1844
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00af49bc877fc3774ed92bad30a4b1fb8f6d2fe6758836d66c5826cf252f1b79
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53631aca5988ded2036ea1ce057477819ab800bef8504147b5dfe41db924add
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
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": 0.5179856115107914,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 12.09,
248
  "eval_steps_per_second": 1.55,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.230476622692352e+17,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5827338129496403,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 12.09,
248
  "eval_steps_per_second": 1.55,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.539568345323741,
253
+ "grad_norm": 2.6071054935455322,
254
+ "learning_rate": 8.930309757836517e-06,
255
+ "loss": 4.2177,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.5611510791366906,
260
+ "grad_norm": 2.0609230995178223,
261
+ "learning_rate": 7.016504991533726e-06,
262
+ "loss": 4.2697,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.5827338129496403,
267
+ "grad_norm": 2.143162250518799,
268
+ "learning_rate": 5.299731159831953e-06,
269
+ "loss": 4.122,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.5827338129496403,
274
+ "eval_loss": 1.011610507965088,
275
+ "eval_runtime": 19.3757,
276
+ "eval_samples_per_second": 12.077,
277
+ "eval_steps_per_second": 1.548,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.367586874935214e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null