lesso13 commited on
Commit
5c93ed5
·
verified ·
1 Parent(s): b6af6d2

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53bbc102cce25bd2a1241498449b0ba801b43eee0dde8083394c50c2f2b8129d
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19573e2dc31ea027ccfbbacef4b70e4d1c75be813e1d7e19945f35041bedb038
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6f6bc771e287b7e88c539a590234ef6859c223f862ebe51903ca4bef54c8f3e
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ee75060c69a804868f7970383492a8b0d3b647c36b08989fed719d8a48078b
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e03f64a4804debb81d6c16e51485bc4b1d54a7fc010363c6a95e60448214e4b8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1b2ecfff0fa531d68bdec0d44bcc3f0b7082d5bb294150a708660ee3fbb2ffb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.413238525390625,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.01084010840108401,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -187,6 +187,49 @@
187
  "eval_samples_per_second": 8.497,
188
  "eval_steps_per_second": 4.254,
189
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  }
191
  ],
192
  "logging_steps": 1,
@@ -210,12 +253,12 @@
210
  "should_evaluate": false,
211
  "should_log": false,
212
  "should_save": true,
213
- "should_training_stop": false
214
  },
215
  "attributes": {}
216
  }
217
  },
218
- "total_flos": 245639984185344.0,
219
  "train_batch_size": 2,
220
  "trial_name": null,
221
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.407135248184204,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 0.013550135501355014,
5
  "eval_steps": 5,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
187
  "eval_samples_per_second": 8.497,
188
  "eval_steps_per_second": 4.254,
189
  "step": 20
190
+ },
191
+ {
192
+ "epoch": 0.011382113821138212,
193
+ "grad_norm": 35.49647903442383,
194
+ "learning_rate": 3.308693936411421e-05,
195
+ "loss": 9.9151,
196
+ "step": 21
197
+ },
198
+ {
199
+ "epoch": 0.011924119241192412,
200
+ "grad_norm": 31.30296516418457,
201
+ "learning_rate": 1.9098300562505266e-05,
202
+ "loss": 7.5294,
203
+ "step": 22
204
+ },
205
+ {
206
+ "epoch": 0.012466124661246613,
207
+ "grad_norm": 51.738033294677734,
208
+ "learning_rate": 8.645454235739903e-06,
209
+ "loss": 8.7387,
210
+ "step": 23
211
+ },
212
+ {
213
+ "epoch": 0.013008130081300813,
214
+ "grad_norm": 46.668582916259766,
215
+ "learning_rate": 2.1852399266194314e-06,
216
+ "loss": 11.1315,
217
+ "step": 24
218
+ },
219
+ {
220
+ "epoch": 0.013550135501355014,
221
+ "grad_norm": 33.56441879272461,
222
+ "learning_rate": 0.0,
223
+ "loss": 9.0747,
224
+ "step": 25
225
+ },
226
+ {
227
+ "epoch": 0.013550135501355014,
228
+ "eval_loss": 2.407135248184204,
229
+ "eval_runtime": 90.3932,
230
+ "eval_samples_per_second": 8.596,
231
+ "eval_steps_per_second": 4.303,
232
+ "step": 25
233
  }
234
  ],
235
  "logging_steps": 1,
 
253
  "should_evaluate": false,
254
  "should_log": false,
255
  "should_save": true,
256
+ "should_training_stop": true
257
  },
258
  "attributes": {}
259
  }
260
  },
261
+ "total_flos": 307049980231680.0,
262
  "train_batch_size": 2,
263
  "trial_name": null,
264
  "trial_params": null