dixedus commited on
Commit
08edd35
·
verified ·
1 Parent(s): e404e31

Training in progress, step 54, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9af33810e99c5dff31aa9b3a1982bdf7e7f9ffed6d7c7b0fbfb13f2dcfad39a8
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e853a76d6e6f55a2e1d89794906589b6b53d186e210c13c6e30bc0394876e1d
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:038c0c17b4e0b2d349f0b2ed80d3481cba256eff860e8e686fa3dea27be461e6
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:323e67c3c6945b913809061cc419b26c4b9cbd4238b5276e9b1f4518d7aa0703
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2597ac463464743ee8d50dd0f0fb0fcea729792966f2dc7c8358944af05a684d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb3fac3367bb35b9a966b19abfdf16e315e46b595dbfcd9c34561c23ecf6539
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
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": 1.1842105263157894,
5
  "eval_steps": 9,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,35 @@
160
  "eval_samples_per_second": 14.242,
161
  "eval_steps_per_second": 1.78,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 6.297410785089946e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.4210526315789473,
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,
 
160
  "eval_samples_per_second": 14.242,
161
  "eval_steps_per_second": 1.78,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 1.263157894736842,
166
+ "grad_norm": 7.43921422958374,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 2.4722,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 1.3421052631578947,
173
+ "grad_norm": 8.37086296081543,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 2.6133,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 1.4210526315789473,
180
+ "grad_norm": 8.553829193115234,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 2.6193,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 1.4210526315789473,
187
+ "eval_loss": 0.7718786597251892,
188
+ "eval_runtime": 4.4967,
189
+ "eval_samples_per_second": 14.233,
190
+ "eval_steps_per_second": 1.779,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 7.563045332267827e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null