ardaspear commited on
Commit
e0a0360
·
verified ·
1 Parent(s): 188adcc

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 sha256:442b36f6b96f74860b7fdda4a6fb30ba46a347046aafb3ce29d359b933576308
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb8fe6e75c1e7ebc7abc93ede0705655150a01d32070837e95f8328ce2a3745
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6ec7b5bc474fd80dfe379e5ec28b1c8028f095bbda9628f1463fefff139e083
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed869223fc14437aac55c22dd4b2376ab797e052e1e35da5df87c62ab5d572ec
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d8148aee39ccad1396ea6921ed66ca54694852a4c8b3251bbf1248898f0506
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aacd22c043d7f6609b2b994e4e0a778f43a4761465f4b4f3dcd83d7e6cfd870
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": 0.011797476650827463,
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": 232.937,
190
  "eval_steps_per_second": 29.125,
191
  "step": 54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 3,
@@ -208,7 +237,7 @@
208
  "attributes": {}
209
  }
210
  },
211
- "total_flos": 12047471345664.0,
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": 0.013763722759298706,
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": 232.937,
190
  "eval_steps_per_second": 29.125,
191
  "step": 54
192
+ },
193
+ {
194
+ "epoch": 0.012452892020317876,
195
+ "grad_norm": 0.3351193070411682,
196
+ "learning_rate": 4.6512176312793736e-05,
197
+ "loss": 10.2752,
198
+ "step": 57
199
+ },
200
+ {
201
+ "epoch": 0.013108307389808291,
202
+ "grad_norm": 0.2998097240924835,
203
+ "learning_rate": 4.131759111665349e-05,
204
+ "loss": 10.2659,
205
+ "step": 60
206
+ },
207
+ {
208
+ "epoch": 0.013763722759298706,
209
+ "grad_norm": 0.2995798885822296,
210
+ "learning_rate": 3.6218132209150045e-05,
211
+ "loss": 10.2697,
212
+ "step": 63
213
+ },
214
+ {
215
+ "epoch": 0.013763722759298706,
216
+ "eval_loss": 10.267303466796875,
217
+ "eval_runtime": 33.1882,
218
+ "eval_samples_per_second": 232.311,
219
+ "eval_steps_per_second": 29.046,
220
+ "step": 63
221
  }
222
  ],
223
  "logging_steps": 3,
 
237
  "attributes": {}
238
  }
239
  },
240
+ "total_flos": 14055383236608.0,
241
  "train_batch_size": 8,
242
  "trial_name": null,
243
  "trial_params": null