TachyHealthResearch commited on
Commit
8d68fda
1 Parent(s): fc984cc

Training in progress, step 40, 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:b086f59a18c08fdb5a8900e1037016d232fff456e518866dcaebba1dcc1dac91
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795dade66e04235b6cc330034e0432014da7ea97c0bf58ba8f21d136fff09b25
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d756f032316b21b9b014f674b6a83095c043f37e6dcdf094ab39e1e04cf322
3
  size 42545748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd08e1de086c1f04978b0f16c77d0b4514828e45c0bfdab947456aca0e14dd3
3
  size 42545748
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db05f4be4bfd57c6db9f1684109ea8219cb794f0abafbe3b2696e0554a780ed9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6306c7ebebc1ba61010c16f5f72bbe4229c8a68ab9af106d32f4e58acec2ce
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ee19ea163e868f40d9ecdcecd226ea53d13afff03ee0a58dfaa5fb6cd5af1e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3b0b845800bdf47f080936f1270a73604b86e0e0e3193c1562e20ca31b9318
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": 0.012,
5
  "eval_steps": 1000,
6
- "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -187,13 +187,73 @@
187
  "learning_rate": 0.00014736842105263158,
188
  "loss": 1.5818,
189
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  }
191
  ],
192
  "logging_steps": 1,
193
  "max_steps": 100,
194
  "num_train_epochs": 1,
195
  "save_steps": 10,
196
- "total_flos": 2104744175566848.0,
197
  "trial_name": null,
198
  "trial_params": null
199
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.016,
5
  "eval_steps": 1000,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
187
  "learning_rate": 0.00014736842105263158,
188
  "loss": 1.5818,
189
  "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.01,
193
+ "learning_rate": 0.00014526315789473686,
194
+ "loss": 1.7394,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.01,
199
+ "learning_rate": 0.0001431578947368421,
200
+ "loss": 1.4422,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.01,
205
+ "learning_rate": 0.00014105263157894736,
206
+ "loss": 2.2255,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.01,
211
+ "learning_rate": 0.00013894736842105264,
212
+ "loss": 1.6186,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.01,
217
+ "learning_rate": 0.0001368421052631579,
218
+ "loss": 1.8378,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.01,
223
+ "learning_rate": 0.00013473684210526317,
224
+ "loss": 1.6349,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.01,
229
+ "learning_rate": 0.00013263157894736842,
230
+ "loss": 1.519,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.02,
235
+ "learning_rate": 0.0001305263157894737,
236
+ "loss": 1.5548,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.02,
241
+ "learning_rate": 0.00012842105263157895,
242
+ "loss": 2.2187,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.02,
247
+ "learning_rate": 0.0001263157894736842,
248
+ "loss": 1.4438,
249
+ "step": 40
250
  }
251
  ],
252
  "logging_steps": 1,
253
  "max_steps": 100,
254
  "num_train_epochs": 1,
255
  "save_steps": 10,
256
+ "total_flos": 2434139976646656.0,
257
  "trial_name": null,
258
  "trial_params": null
259
  }