ramdhanfirdaus commited on
Commit
a2659f4
1 Parent(s): ce051a7

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 sha256:9a2a55c1efa884e98e1b18cc28a5bc5f4a2a8f22946059813b063c3af93c22a3
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b095b1094487a3b73197afb3f6bd52be086202909bc8502c0b72ef541fa917
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49fbe0f142464fc6adfc16ee055e38bb979c38fffcea0cea5d4fa13867eae478
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c326fe277539a62700a980a7c1d1c70ea74452acf2dbbf94e2512eb8d9aba0b7
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6f87eeba1af718cddacd5d9616efe0fba785b21191a131136973f711b764cec
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8abc1651d90c08f1d53ebb2646d6c02484bede312b64b6066690c8bbd1412627
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": 1.3577570915222168,
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": 15.027,
204
  "eval_steps_per_second": 1.88,
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": 4.539473771498373e+17,
213
  "trial_name": null,
214
  "trial_params": null
215
  }
 
1
  {
2
+ "best_metric": 1.3446884155273438,
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": 15.027,
204
  "eval_steps_per_second": 1.88,
205
  "step": 1400
206
+ },
207
+ {
208
+ "epoch": 1.09,
209
+ "learning_rate": 0.0002,
210
+ "loss": 1.3316,
211
+ "step": 1500
212
+ },
213
+ {
214
+ "epoch": 1.09,
215
+ "eval_loss": 1.3446884155273438,
216
+ "eval_runtime": 417.3899,
217
+ "eval_samples_per_second": 15.032,
218
+ "eval_steps_per_second": 1.881,
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": 4.8636182340681216e+17,
227
  "trial_name": null,
228
  "trial_params": null
229
  }