mamung commited on
Commit
2f4abed
·
verified ·
1 Parent(s): 9005d54

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21154256a977650e0f741b040e34e73fa2f16d280482259df83a4466d5b0cc61
3
  size 4628218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d34e1bb5d8b95a3863d2c949546503729d6ef93d0f1822f1103de1d568ca84a
3
  size 4628218
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5add46d4d28bcb535d1631fb310b8516b9bf2635f833c5c8df60d5713872d3ee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c94712c6df223864e9628cad82028db72f382ca22f7dd490c339b2f303b94547
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
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": 0.14680561848663343,
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,
@@ -199,6 +199,28 @@
199
  "eval_samples_per_second": 285.236,
200
  "eval_steps_per_second": 35.764,
201
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
202
  }
203
  ],
204
  "logging_steps": 5,
@@ -218,7 +240,7 @@
218
  "attributes": {}
219
  }
220
  },
221
- "total_flos": 1449310814208000.0,
222
  "train_batch_size": 8,
223
  "trial_name": null,
224
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.16311735387403714,
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,
 
199
  "eval_samples_per_second": 285.236,
200
  "eval_steps_per_second": 35.764,
201
  "step": 81
202
+ },
203
+ {
204
+ "epoch": 0.15405527865881286,
205
+ "grad_norm": NaN,
206
+ "learning_rate": 1.2639779077309098e-05,
207
+ "loss": 0.0,
208
+ "step": 85
209
+ },
210
+ {
211
+ "epoch": 0.16311735387403714,
212
+ "grad_norm": NaN,
213
+ "learning_rate": 5.709035061653494e-06,
214
+ "loss": 0.0,
215
+ "step": 90
216
+ },
217
+ {
218
+ "epoch": 0.16311735387403714,
219
+ "eval_loss": NaN,
220
+ "eval_runtime": 6.8949,
221
+ "eval_samples_per_second": 284.559,
222
+ "eval_steps_per_second": 35.679,
223
+ "step": 90
224
  }
225
  ],
226
  "logging_steps": 5,
 
240
  "attributes": {}
241
  }
242
  },
243
+ "total_flos": 1611094346956800.0,
244
  "train_batch_size": 8,
245
  "trial_name": null,
246
  "trial_params": null