Nexspear commited on
Commit
26ddcdc
·
verified ·
1 Parent(s): fc3df68

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 sha256:1c5e7c25b9f2e2a8f985345337e7d72db0f1d30338b28da39865e71726a1df09
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569ebcfc5c4b541bb52a8d7d25070368f23488c4bc61efb99fe47c4f5966d61a
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2b4158ad1650d245168b8ab8f06b4cd07ca4909f2a7f50fbad45faeb737d5b3
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885abe740a164acca1837c36645fa9b6c351b6bd3042724d924c4e9cb62fc4d6
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f31d9f4509e8f2c0004502cbfb3b3746639a21cd95c7a49387ee81d613ac30a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a92467e0ecfe782db0a3a5da3b4c19e20129fca8cef745be714bf12d1e612a5
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": 0.11285266457680251,
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": 13.494,
193
  "eval_steps_per_second": 1.687,
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": 6.0895984091136e+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": 0.12539184952978055,
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": 13.494,
193
  "eval_steps_per_second": 1.687,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.12037617554858934,
198
+ "grad_norm": 0.48648402094841003,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 1.5412,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.12539184952978055,
205
+ "eval_loss": 1.5486319065093994,
206
+ "eval_runtime": 49.7811,
207
+ "eval_samples_per_second": 13.499,
208
+ "eval_steps_per_second": 1.687,
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": 6.7624822112256e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null