ardaspear commited on
Commit
6abcd7d
1 Parent(s): 4f792e6

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:e627017a49bc4863d2d88041d6a4b346b1b510721a0d304c5904d10f4d3f5686
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bede2d770e7f0fc67b9cd36abdf8f4684c05955e72497d89c64a068cb075558f
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b677c433fe39e753e53e39715b3ea732c8ca1361009cc36be340a875e348f0c1
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f45e36e24729975d2460af5513827cb444ec05860650c4ef2aae524151972b
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16c7f7133cb41e4c7f58ad848fed2fb893c76880e5c42ef87bba992b08ea7012
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60cbf6f4d01495cabe2b71a902c72e3a9b50776fc8c45b5c96e5f3abe4d51404
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": 0.004197908042492158,
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": 16.015,
193
  "eval_steps_per_second": 4.004,
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": 5.50981865570304e+16,
215
  "train_batch_size": 4,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004664342269435731,
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": 16.015,
193
  "eval_steps_per_second": 4.004,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.004477768578658302,
198
+ "grad_norm": 1.6393113136291504,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 0.7374,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.004664342269435731,
205
+ "eval_loss": 0.8864649534225464,
206
+ "eval_runtime": 1127.3926,
207
+ "eval_samples_per_second": 16.015,
208
+ "eval_steps_per_second": 4.004,
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": 6.051913716989952e+16,
230
  "train_batch_size": 4,
231
  "trial_name": null,
232
  "trial_params": null