rizkyjun commited on
Commit
790da5c
1 Parent(s): bd293e8

Training in progress, step 3100, 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:e6319930a745b403488c8f4cd7b0fa3279145451792c99b60a472ec0096b9c48
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f98020fe0b9a5f4fa54138bd62038b71c0c0aea36156f95ed80b24cf1160832
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae962e2c303d13dcc2ab38ad62eec892bbc41370685f7ba3ef9cd728cad7f753
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:708b58ea0c99f8633db644e582824e3ded1e0d9a8d1beab9d7a43ad1c99a96fc
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91dfacd60140a5cbf67fe9b8b80bd85ac38eb6bb2e3f798370b76b550205b468
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb7f6be2d16d160f7efe75bf46de6112a7eba7eb5758eaa5230d07ffd99ed7b
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.09155011177063,
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,
@@ -427,13 +427,27 @@
427
  "eval_samples_per_second": 30.169,
428
  "eval_steps_per_second": 3.775,
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": 8.752327767687168e+16,
437
  "trial_name": null,
438
  "trial_params": null
439
  }
 
1
  {
2
+ "best_metric": 2.081061840057373,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3100",
4
+ "epoch": 2.2586520947176685,
5
  "eval_steps": 100,
6
+ "global_step": 3100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
427
  "eval_samples_per_second": 30.169,
428
  "eval_steps_per_second": 3.775,
429
  "step": 3000
430
+ },
431
+ {
432
+ "epoch": 2.26,
433
+ "learning_rate": 0.0002,
434
+ "loss": 2.0272,
435
+ "step": 3100
436
+ },
437
+ {
438
+ "epoch": 2.26,
439
+ "eval_loss": 2.081061840057373,
440
+ "eval_runtime": 207.7848,
441
+ "eval_samples_per_second": 30.195,
442
+ "eval_steps_per_second": 3.778,
443
+ "step": 3100
444
  }
445
  ],
446
  "logging_steps": 100,
447
  "max_steps": 4116,
448
  "num_train_epochs": 3,
449
  "save_steps": 100,
450
+ "total_flos": 9.046021502214144e+16,
451
  "trial_name": null,
452
  "trial_params": null
453
  }