rizkyjun commited on
Commit
a4fc5d9
·
1 Parent(s): 12d3406

Training in progress, step 2600, 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:a612e0e4b4b1f27ebda5011ba361ccaa631bd3cd3ae70721ecd6e8842c6164a9
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a71d09323e887c021ab22fa71b647eae5bd8c0b47df291dbd109d9db3858e9
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6a6c5c71e708e6b422225d1835662c666b29914255323d8ecae897375678ee6
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b85eccfb0d4978a6ff5f81e3356ccfa17a1bf19c4b49e072e6b841ad59bf6b1
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71b9445452b0f4ec2e34ecc2a5014eb62a4d39167a4355d4fcd661626ad65a5d
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759e77ccf458a889b7b5189552587bc5a6060b4a877912775f82bf425e75e65c
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.1189475059509277,
3
- "best_model_checkpoint": "./outputs/checkpoint-2500",
4
- "epoch": 1.8214936247723132,
5
  "eval_steps": 100,
6
- "global_step": 2500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -357,13 +357,27 @@
357
  "eval_samples_per_second": 28.703,
358
  "eval_steps_per_second": 3.591,
359
  "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
360
  }
361
  ],
362
  "logging_steps": 100,
363
  "max_steps": 4116,
364
  "num_train_epochs": 3,
365
  "save_steps": 100,
366
- "total_flos": 7.346343543662592e+16,
367
  "trial_name": null,
368
  "trial_params": null
369
  }
 
1
  {
2
+ "best_metric": 2.1056134700775146,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2600",
4
+ "epoch": 1.8943533697632058,
5
  "eval_steps": 100,
6
+ "global_step": 2600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
357
  "eval_samples_per_second": 28.703,
358
  "eval_steps_per_second": 3.591,
359
  "step": 2500
360
+ },
361
+ {
362
+ "epoch": 1.89,
363
+ "learning_rate": 0.0002,
364
+ "loss": 2.1023,
365
+ "step": 2600
366
+ },
367
+ {
368
+ "epoch": 1.89,
369
+ "eval_loss": 2.1056134700775146,
370
+ "eval_runtime": 206.4995,
371
+ "eval_samples_per_second": 30.383,
372
+ "eval_steps_per_second": 3.801,
373
+ "step": 2600
374
  }
375
  ],
376
  "logging_steps": 100,
377
  "max_steps": 4116,
378
  "num_train_epochs": 3,
379
  "save_steps": 100,
380
+ "total_flos": 7.639893171800064e+16,
381
  "trial_name": null,
382
  "trial_params": null
383
  }