auxyus commited on
Commit
36d9df3
·
verified ·
1 Parent(s): 08aa98e

Training in progress, step 63, 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:e06516458bb5cc1cefb675e7284a758b5c2a16011f9e85916dfcfe2b5fa2f7f8
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97aed768dcc8b18a29aa6d2f3dbd3cb7a9fbe0ef3575d243844847a82efb2ba2
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c3feb0defcc442d81eb4ffab5303fefb5db4f514fcba727fdfd34d87b3cf50e
3
  size 61392180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d7512fed700f3464f86248c747fe99891c5bfc147ba65a69ce197519aaa855
3
  size 61392180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:187ff4a0a247f233680554d821ca2a92a82b8895ad2235a345f226002ac53b72
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ddbe34cf33e8aaf873288f9db021fea5abcee30a6ce83d3b3df2c6074d5992
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
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": 0.12279704377487209,
5
  "eval_steps": 9,
6
- "global_step": 54,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -189,6 +189,35 @@
189
  "eval_samples_per_second": 20.631,
190
  "eval_steps_per_second": 2.589,
191
  "step": 54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 3,
@@ -208,7 +237,7 @@
208
  "attributes": {}
209
  }
210
  },
211
- "total_flos": 3.212067507850445e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.14326321773735076,
5
  "eval_steps": 9,
6
+ "global_step": 63,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
189
  "eval_samples_per_second": 20.631,
190
  "eval_steps_per_second": 2.589,
191
  "step": 54
192
+ },
193
+ {
194
+ "epoch": 0.129619101762365,
195
+ "grad_norm": 0.4595838785171509,
196
+ "learning_rate": 4.6512176312793736e-05,
197
+ "loss": 1.7213,
198
+ "step": 57
199
+ },
200
+ {
201
+ "epoch": 0.13644115974985788,
202
+ "grad_norm": 0.3871839642524719,
203
+ "learning_rate": 4.131759111665349e-05,
204
+ "loss": 1.6915,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.14326321773735076,
209
+ "grad_norm": 0.48633936047554016,
210
+ "learning_rate": 3.6218132209150045e-05,
211
+ "loss": 1.5636,
212
+ "step": 63
213
+ },
214
+ {
215
+ "epoch": 0.14326321773735076,
216
+ "eval_loss": 1.6816630363464355,
217
+ "eval_runtime": 35.9227,
218
+ "eval_samples_per_second": 20.628,
219
+ "eval_steps_per_second": 2.589,
220
+ "step": 63
221
  }
222
  ],
223
  "logging_steps": 3,
 
237
  "attributes": {}
238
  }
239
  },
240
+ "total_flos": 3.777281103652454e+16,
241
  "train_batch_size": 8,
242
  "trial_name": null,
243
  "trial_params": null