Hugging Face's logo

haryoaw
/
scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66

PyTorch
deberta-v2
Generated from Trainer
Model card Files Community
scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66 / README.md
haryoaw's picture
haryoaw
Initial Commit
bd7d5cc verified
preview code
|
raw
history blame
2.72 kB
metadata
license: mit
base_model: haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66
    results: []

scenario-KD-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66

This model is a fine-tuned version of haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 24.7382
  • Accuracy: 0.4550
  • F1: 0.4534

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 66
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.72 100 15.4704 0.4568 0.4535
No log 3.45 200 16.0314 0.4669 0.4628
No log 5.17 300 19.1999 0.4568 0.4479
No log 6.9 400 21.8826 0.4546 0.4456
9.984 8.62 500 21.4137 0.4572 0.4573
9.984 10.34 600 23.3766 0.4396 0.4365
9.984 12.07 700 24.2726 0.4475 0.4365
9.984 13.79 800 24.3246 0.4502 0.4440
9.984 15.52 900 24.9899 0.4634 0.4616
1.9269 17.24 1000 24.6384 0.4616 0.4583
1.9269 18.97 1100 24.3379 0.4493 0.4454
1.9269 20.69 1200 24.6032 0.4625 0.4577
1.9269 22.41 1300 24.1732 0.4608 0.4572
1.9269 24.14 1400 25.5374 0.4493 0.4448
0.6962 25.86 1500 24.3690 0.4563 0.4553
0.6962 27.59 1600 24.9417 0.4515 0.4488
0.6962 29.31 1700 24.7382 0.4550 0.4534

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3