LumousInTheWild's picture
End of training
16be843 verified
metadata
license: apache-2.0
base_model: studio-ousia/mluke-base
tags:
  - generated_from_trainer
model-index:
  - name: exp_acha_mluke_base_origi
    results: []

exp_acha_mluke_base_origi

This model is a fine-tuned version of studio-ousia/mluke-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1405

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
0.314 1.0 208 0.3363
0.2712 2.0 416 0.2008
0.1676 3.0 624 0.1689
0.118 4.0 832 0.1944
0.103 5.0 1040 0.1970
0.1465 6.0 1248 0.1481
0.0821 7.0 1456 0.1487
0.0515 8.0 1664 0.1439
0.0303 9.0 1872 0.1463
0.1295 10.0 2080 0.1405

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1