leixa commited on
Commit
94f7c98
1 Parent(s): a1d132f

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 sha256:651b1eff78745c61015fa5d0edf8c213348b746963f0905479fb063c92f912d6
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fea38d6647965b3eef19523b1fe032f5fdcfc9f1de09fb0e976ea5ece484ae8
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe62ead2225044c090b4b5e752b553e95b36603511320868aded68c0dc5c42fb
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e702cff80a54a8c828ae97a30d7cb983ef081761c01bb4530987b11fd588623
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63ec47eea7d311c787503f5549fe31ab778050fe5d71393032ae37d62f3e1360
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34fd5de1edde02642fddf7042feb8200bc316a7675eef14798ce219fac15c42e
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": 0.18848167539267016,
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": 13.899,
193
  "eval_steps_per_second": 1.759,
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": 6.39849908404224e+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": 0.2094240837696335,
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": 13.899,
193
  "eval_steps_per_second": 1.759,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.20104712041884817,
198
+ "grad_norm": 0.3182230591773987,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.174,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.2094240837696335,
205
+ "eval_loss": 1.2305855751037598,
206
+ "eval_runtime": 28.9974,
207
+ "eval_samples_per_second": 13.898,
208
+ "eval_steps_per_second": 1.759,
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": 7.1094434267136e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null