dimasik87 commited on
Commit
be1de03
1 Parent(s): 39507fa

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:e2002ab4bdd6fe1ca5861b7747c9e15a25eda960df5311f43efaf42842e76773
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95963534ccb56b3c72e2de7fea572e8a71b348927f8cb3ec29def9455f516009
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b0504683d6c0bd60f5db9aca6172d449fd6d53831b897c71f6abb6a74148b67
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16d2cbd9a134c609addafb0630080755581cca0d0206c11dc89e50b7f663983
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:827a869844b9d198e193184921a140e6132a0ebb431279ef0ceeb6c89a553ae3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd179c0c4ca1de8d0bfba8a39b9e9c9c9671a6547c4af4c41f48f0409182650b
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": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.005646925954683419,
5
  "eval_steps": 3,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -203,6 +203,57 @@
203
  "learning_rate": 5.000000000000002e-05,
204
  "loss": 1.3224,
205
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
206
  }
207
  ],
208
  "logging_steps": 1,
@@ -217,12 +268,12 @@
217
  "should_evaluate": false,
218
  "should_log": false,
219
  "should_save": true,
220
- "should_training_stop": false
221
  },
222
  "attributes": {}
223
  }
224
  },
225
- "total_flos": 5225075347292160.0,
226
  "train_batch_size": 2,
227
  "trial_name": null,
228
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007058657443354274,
5
  "eval_steps": 3,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
203
  "learning_rate": 5.000000000000002e-05,
204
  "loss": 1.3224,
205
  "step": 20
206
+ },
207
+ {
208
+ "epoch": 0.0059292722524175905,
209
+ "grad_norm": 19.52411460876465,
210
+ "learning_rate": 3.308693936411421e-05,
211
+ "loss": 2.2475,
212
+ "step": 21
213
+ },
214
+ {
215
+ "epoch": 0.0059292722524175905,
216
+ "eval_loss": NaN,
217
+ "eval_runtime": 127.529,
218
+ "eval_samples_per_second": 23.391,
219
+ "eval_steps_per_second": 11.699,
220
+ "step": 21
221
+ },
222
+ {
223
+ "epoch": 0.006211618550151761,
224
+ "grad_norm": 15.904952049255371,
225
+ "learning_rate": 1.9098300562505266e-05,
226
+ "loss": 2.4317,
227
+ "step": 22
228
+ },
229
+ {
230
+ "epoch": 0.006493964847885932,
231
+ "grad_norm": 14.597325325012207,
232
+ "learning_rate": 8.645454235739903e-06,
233
+ "loss": 1.2465,
234
+ "step": 23
235
+ },
236
+ {
237
+ "epoch": 0.006776311145620103,
238
+ "grad_norm": 13.051502227783203,
239
+ "learning_rate": 2.1852399266194314e-06,
240
+ "loss": 0.67,
241
+ "step": 24
242
+ },
243
+ {
244
+ "epoch": 0.006776311145620103,
245
+ "eval_loss": NaN,
246
+ "eval_runtime": 127.5334,
247
+ "eval_samples_per_second": 23.39,
248
+ "eval_steps_per_second": 11.699,
249
+ "step": 24
250
+ },
251
+ {
252
+ "epoch": 0.007058657443354274,
253
+ "grad_norm": 14.694950103759766,
254
+ "learning_rate": 0.0,
255
+ "loss": 2.2391,
256
+ "step": 25
257
  }
258
  ],
259
  "logging_steps": 1,
 
268
  "should_evaluate": false,
269
  "should_log": false,
270
  "should_save": true,
271
+ "should_training_stop": true
272
  },
273
  "attributes": {}
274
  }
275
  },
276
+ "total_flos": 6531344184115200.0,
277
  "train_batch_size": 2,
278
  "trial_name": null,
279
  "trial_params": null