rizkyjun commited on
Commit
d423222
1 Parent(s): ae2599c

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 sha256:0f37dc56b7df954a6cd0364326072bf1be7667174c65ce17ae49872579e0c55f
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6149323ad5618e6f6dbeebd4c31daa40ca24bc7ff8494d66f9a17ba209a9fd25
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd902a23bdf27aef7b905bc59aeb0143c42fb8221fb48e215497e2e5a1c6268d
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bff60360db1e4dbb436bfd0d8ac63cec0979d200556ee0df252f79cccede889
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e878fc0fbc86334888140425f50a172daf0ca6c9b8e00f870566985c8b9eac8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5276bfff6a9f44b6571a60e5907a8f84a8585a1992ad727c0bb7ed37a25fe20
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": 2.379911422729492,
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": 30.606,
204
  "eval_steps_per_second": 3.829,
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": 3.994021987006464e+16,
213
  "trial_name": null,
214
  "trial_params": null
215
  }
 
1
  {
2
+ "best_metric": 2.3603107929229736,
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": 30.606,
204
  "eval_steps_per_second": 3.829,
205
  "step": 1400
206
+ },
207
+ {
208
+ "epoch": 1.09,
209
+ "learning_rate": 0.0002,
210
+ "loss": 2.337,
211
+ "step": 1500
212
+ },
213
+ {
214
+ "epoch": 1.09,
215
+ "eval_loss": 2.3603107929229736,
216
+ "eval_runtime": 204.9808,
217
+ "eval_samples_per_second": 30.608,
218
+ "eval_steps_per_second": 3.83,
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": 4.279485281605632e+16,
227
  "trial_name": null,
228
  "trial_params": null
229
  }