Nexspear commited on
Commit
f910019
·
verified ·
1 Parent(s): 998a4c9

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41d0e8ed5341825c2e85323a30b329f97e125d28bae44ffd10b73165b164d12e
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3a87516390e9b183477146e564cb9d5b943b7c2359e998e3dd18c8862eb30a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:627447a836d838f6f3a84a23e6bbdd680e77629c359f8e293b06981495477f28
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e4f199754276ab6d70908fce8d711735f45a97befc627b7b9b5cb565517744
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d841e4da3c97756d6b77dd41d54eb76213e71d7eaf4110eeb297aee8677a586
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47eb72fba1fc95b462ed1d1ebec74f4cf0acfb68a40ad024472f066c9cd55f4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.05531653349723417,
5
  "eval_steps": 5,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -192,6 +192,21 @@
192
  "eval_samples_per_second": 12.708,
193
  "eval_steps_per_second": 1.594,
194
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  }
196
  ],
197
  "logging_steps": 3,
@@ -206,12 +221,12 @@
206
  "should_evaluate": false,
207
  "should_log": false,
208
  "should_save": true,
209
- "should_training_stop": false
210
  },
211
  "attributes": {}
212
  }
213
  },
214
- "total_flos": 7.12772665957417e+16,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06146281499692686,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
192
  "eval_samples_per_second": 12.708,
193
  "eval_steps_per_second": 1.594,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.05900430239704978,
198
+ "grad_norm": 1.1889021396636963,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.443,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.06146281499692686,
205
+ "eval_loss": 0.4718257188796997,
206
+ "eval_runtime": 107.867,
207
+ "eval_samples_per_second": 12.71,
208
+ "eval_steps_per_second": 1.595,
209
+ "step": 50
210
  }
211
  ],
212
  "logging_steps": 3,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": true
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 7.881983448947098e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null