rizkyjun commited on
Commit
61fa636
1 Parent(s): 88b755b

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 sha256:505eece004e629a20f95167265c465ffeb9a06299cdcae203eed20ebb7de8992
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6319930a745b403488c8f4cd7b0fa3279145451792c99b60a472ec0096b9c48
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5129cf74e5390e64e08f9eaf2c4da8d51ad268dcfcb96c4b9d593d4549d72b07
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae962e2c303d13dcc2ab38ad62eec892bbc41370685f7ba3ef9cd728cad7f753
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63aa9a735404dac131dfbc8da4c0d73a5c82d175792f71a6b89cddd41d8318a5
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91dfacd60140a5cbf67fe9b8b80bd85ac38eb6bb2e3f798370b76b550205b468
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": 2.099728584289551,
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": 30.207,
414
  "eval_steps_per_second": 3.779,
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": 8.458768314114048e+16,
423
  "trial_name": null,
424
  "trial_params": null
425
  }
 
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,
 
413
  "eval_samples_per_second": 30.207,
414
  "eval_steps_per_second": 3.779,
415
  "step": 2900
416
+ },
417
+ {
418
+ "epoch": 2.19,
419
+ "learning_rate": 0.0002,
420
+ "loss": 2.0583,
421
+ "step": 3000
422
+ },
423
+ {
424
+ "epoch": 2.19,
425
+ "eval_loss": 2.09155011177063,
426
+ "eval_runtime": 207.9624,
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
  }