Nexspear commited on
Commit
88b6326
1 Parent(s): f5b5c16

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 sha256:963490951e41a6b298a2a45c0b12b8fc868d4a1d813dea2d1a70e2059efef1c5
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f294e5148079cd7c5dc77f65aa5c19d451b4d08f07b216dff68a1592342c45f7
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a96a9b13d7fdf85a74ba640636bfd4ed8b20fcf5a6c1175be5764b29e567a57d
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775d325cbf340e49ec7764c9235fe2b4d6f27f8b988af29f82e3effa82cbe964
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11654361354869c625ade8e3cd35ca4b4e58bd76e4982e4f6b61c5dae495485f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a46b2198645e8ff0a9eb6925c0feb6752c497c1b34bb06dc25ed5559dbd1e37
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": 0.08486562942008487,
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": 12.975,
193
  "eval_steps_per_second": 1.627,
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": 6.647329603977216e+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": 0.0942951438000943,
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": 12.975,
193
  "eval_steps_per_second": 1.627,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.09052333804809053,
198
+ "grad_norm": 0.2088613361120224,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.1637,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.0942951438000943,
205
+ "eval_loss": 1.285054326057434,
206
+ "eval_runtime": 68.8281,
207
+ "eval_samples_per_second": 12.974,
208
+ "eval_steps_per_second": 1.627,
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": 7.429368380915712e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null