rizkyjun commited on
Commit
ce8dc42
1 Parent(s): e7f8198

Training in progress, step 3000, 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:ba8c6b49c9b8776d8fa9734fcfa1d344263eb37301aaa74df8f4ac32f816215c
3
  size 31466288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4714f00f220cf03dc8ecb1b6ffb5bfdd5f6ee0c9d94dec6e686e36faa55acd5c
3
  size 31466288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33bf614459aa886d7f42cd2e6107e5625b3d91b219a1c249ff2b58525e8daa70
3
  size 62950917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba88c71664e522f1e74d074e3f541dd52d045d0c72cc9004d3382d6241a0d9b
3
  size 62950917
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0340d4911a993658f9871059b3f1911f3f1227a4050f7280c82fa19df52394e3
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de839f752f41c23faa9d6b46f195591dd04dfaa875faee91ac6afc3ae664e39c
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3265427350997925,
3
- "best_model_checkpoint": "./outputs/checkpoint-2900",
4
- "epoch": 2.1129326047358834,
5
  "eval_steps": 100,
6
- "global_step": 2900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -413,13 +413,27 @@
413
  "eval_samples_per_second": 11.303,
414
  "eval_steps_per_second": 1.414,
415
  "step": 2900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
416
  }
417
  ],
418
  "logging_steps": 100,
419
  "max_steps": 4116,
420
  "num_train_epochs": 3,
421
  "save_steps": 100,
422
- "total_flos": 7.548286956953272e+17,
423
  "trial_name": null,
424
  "trial_params": null
425
  }
 
1
  {
2
+ "best_metric": 1.3085519075393677,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3000",
4
+ "epoch": 2.185792349726776,
5
  "eval_steps": 100,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
413
  "eval_samples_per_second": 11.303,
414
  "eval_steps_per_second": 1.414,
415
  "step": 2900
416
+ },
417
+ {
418
+ "epoch": 2.19,
419
+ "learning_rate": 0.0002,
420
+ "loss": 1.2435,
421
+ "step": 3000
422
+ },
423
+ {
424
+ "epoch": 2.19,
425
+ "eval_loss": 1.3085519075393677,
426
+ "eval_runtime": 554.9705,
427
+ "eval_samples_per_second": 11.305,
428
+ "eval_steps_per_second": 1.414,
429
+ "step": 3000
430
  }
431
  ],
432
  "logging_steps": 100,
433
  "max_steps": 4116,
434
  "num_train_epochs": 3,
435
  "save_steps": 100,
436
+ "total_flos": 7.810208021102592e+17,
437
  "trial_name": null,
438
  "trial_params": null
439
  }