ramdhanfirdaus commited on
Commit
0ffcfa6
1 Parent(s): 47b1923

Training in progress, step 1500, checkpoint

Browse files
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa788ab3acb6ea0c93ad303e4064acc66353410749dbb72baf8e49908f8dd943
3
  size 50349441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801dc6ce35e23ac85938e3e746e50141afe5c3ebcbd20eb271e3e2f0a1c15a21
3
  size 50349441
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bea7d7873f5fad796e996d3ce7d1cb065bc314a9ec98082e88e9857061ba6df
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8383a7e5dea0980760e4a24e9c9ec131778f81424b7b42bfb040a417d5a9e2
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:591a9c5e45bb1139399d3039b4c05dd34997d5462b11eb1ca1771e8044f4a6a1
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab823abb115c32fa0673f758e0b0199bf6d5f3e43f5557dbadcc612729790b53
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": 1.552846074104309,
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": 43.543,
204
  "eval_steps_per_second": 5.448,
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": 8.347109656129536e+16,
213
  "trial_name": null,
214
  "trial_params": null
215
  }
 
1
  {
2
+ "best_metric": 1.5355615615844727,
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": 43.543,
204
  "eval_steps_per_second": 5.448,
205
  "step": 1400
206
+ },
207
+ {
208
+ "epoch": 1.09,
209
+ "learning_rate": 0.0002,
210
+ "loss": 1.5246,
211
+ "step": 1500
212
+ },
213
+ {
214
+ "epoch": 1.09,
215
+ "eval_loss": 1.5355615615844727,
216
+ "eval_runtime": 144.0408,
217
+ "eval_samples_per_second": 43.557,
218
+ "eval_steps_per_second": 5.45,
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": 8.943146869488845e+16,
227
  "trial_name": null,
228
  "trial_params": null
229
  }