rizkyjun commited on
Commit
2b8ae1c
1 Parent(s): 884172c

Training in progress, step 1600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8921ff167650a83ab325b2994d4c6d3fbd79390ea79b30df2154053f45792249
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b7e2b9ce07e8266d62f2d54da9830cb7d99a14e805bd011de4622c1c47413e
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06d7a0faa7871ebf23f43bb93631a3051249811bb44f653311f216abfb6d03a1
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ce2fe05c1da90f9e4998d76fc519a7b52eb50373bbbd1354875457594f5719b
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:ade3539adbe7197226065a369a265f6f0f1e7d107ccc3030d3acbbd888426eb0
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca77415e638cf3b9d32978f227902748bb049cf3a40192fa31a73b897a1b66c8
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -217,13 +217,27 @@
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
  }
 
1
  {
2
+ "best_metric": 2.2453196048736572,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1600",
4
+ "epoch": 1.1657559198542806,
5
  "eval_steps": 100,
6
+ "global_step": 1600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
217
  "eval_samples_per_second": 30.46,
218
  "eval_steps_per_second": 3.811,
219
  "step": 1500
220
+ },
221
+ {
222
+ "epoch": 1.17,
223
+ "learning_rate": 0.0002,
224
+ "loss": 2.23,
225
+ "step": 1600
226
+ },
227
+ {
228
+ "epoch": 1.17,
229
+ "eval_loss": 2.2453196048736572,
230
+ "eval_runtime": 206.3463,
231
+ "eval_samples_per_second": 30.405,
232
+ "eval_steps_per_second": 3.804,
233
+ "step": 1600
234
  }
235
  ],
236
  "logging_steps": 100,
237
  "max_steps": 4116,
238
  "num_train_epochs": 3,
239
  "save_steps": 100,
240
+ "total_flos": 4.70673370653696e+16,
241
  "trial_name": null,
242
  "trial_params": null
243
  }