rizkyjun commited on
Commit
9f6afa5
1 Parent(s): efe3400

Training in progress, step 1500, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f15d56338e6809d8a884add614f7eff9787df591de35b2ef66f68db8a0692de
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8921ff167650a83ab325b2994d4c6d3fbd79390ea79b30df2154053f45792249
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a9de0c35af4a41128353df8cffc012530b557f5926a3d41a5f785da69a4ee1
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d7a0faa7871ebf23f43bb93631a3051249811bb44f653311f216abfb6d03a1
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55a434fa2478e58592908e5f1cc53dc10fd07fe28ea2b87f64160779bd08c4a0
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade3539adbe7197226065a369a265f6f0f1e7d107ccc3030d3acbbd888426eb0
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.279730796813965,
3
- "best_model_checkpoint": "./outputs/checkpoint-1400",
4
- "epoch": 1.0200364298724955,
5
  "eval_steps": 100,
6
- "global_step": 1400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -203,13 +203,27 @@
203
  "eval_samples_per_second": 30.443,
204
  "eval_steps_per_second": 3.809,
205
  "step": 1400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
206
  }
207
  ],
208
  "logging_steps": 100,
209
  "max_steps": 4116,
210
  "num_train_epochs": 3,
211
  "save_steps": 100,
212
- "total_flos": 4.118366969063424e+16,
213
  "trial_name": null,
214
  "trial_params": null
215
  }
 
1
  {
2
+ "best_metric": 2.2633275985717773,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1500",
4
+ "epoch": 1.092896174863388,
5
  "eval_steps": 100,
6
+ "global_step": 1500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
203
  "eval_samples_per_second": 30.443,
204
  "eval_steps_per_second": 3.809,
205
  "step": 1400
206
+ },
207
+ {
208
+ "epoch": 1.09,
209
+ "learning_rate": 0.0002,
210
+ "loss": 2.2381,
211
+ "step": 1500
212
+ },
213
+ {
214
+ "epoch": 1.09,
215
+ "eval_loss": 2.2633275985717773,
216
+ "eval_runtime": 205.9739,
217
+ "eval_samples_per_second": 30.46,
218
+ "eval_steps_per_second": 3.811,
219
+ "step": 1500
220
  }
221
  ],
222
  "logging_steps": 100,
223
  "max_steps": 4116,
224
  "num_train_epochs": 3,
225
  "save_steps": 100,
226
+ "total_flos": 4.412678068463616e+16,
227
  "trial_name": null,
228
  "trial_params": null
229
  }