ardaspear commited on
Commit
741f3a2
·
verified ·
1 Parent(s): f4d7340

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:b685e06650274a43b6ab9959b69c0d72728a6036f86c34263d33ecb59b724648
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b7d9d323cec31c21cdc38b9bb9f2ad7e4d9ea81136844a090a95d913dceed7
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aff9bc1530d64b951f812208b7c2736f337ea2acfac6a362bec33b02b5f15af7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68d6b88fe5cbd53dc288578d1ff64fbdc8dab196b628dfc9d03e171465216e3
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:861730abe8cc65d5d27a22c1c77fda2c515e52a10959f74e74710d0c55ace38f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fcb2d93fe4cdfb7a02b058d953960dfef46fc6e804dd5aec245886846e85a46
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": 0.15463917525773196,
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": 13.855,
193
  "eval_steps_per_second": 1.753,
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": 6.439494664323072e+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": 0.1718213058419244,
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": 13.855,
193
  "eval_steps_per_second": 1.753,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.16494845360824742,
198
+ "grad_norm": 38.16620635986328,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 3.2486,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.1718213058419244,
205
+ "eval_loss": 0.6644277572631836,
206
+ "eval_runtime": 35.3737,
207
+ "eval_samples_per_second": 13.852,
208
+ "eval_steps_per_second": 1.753,
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": 7.15499407147008e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null