Hugging Face's logo

haryoaw
/
scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_only44

PyTorch
deberta-v2
Generated from Trainer
Model card Files Community
scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_only44 / README.md
haryoaw's picture
haryoaw
Initial Commit
dfc3683 verified
preview code
|
raw
history blame
3.4 kB
metadata
license: mit
base_model: haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_only44
    results: []

scenario-KD-PO-CDF-CL-D2_data-cl-cardiff_cl_only44

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

  • Loss: 35.0455
  • Accuracy: 0.4421
  • F1: 0.4372

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: 44
  • 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 1.09 250 22.7040 0.4236 0.4110
23.1676 2.17 500 21.6418 0.4336 0.4116
23.1676 3.26 750 24.6174 0.4267 0.4155
12.9705 4.35 1000 27.2959 0.4460 0.4447
12.9705 5.43 1250 28.1257 0.4375 0.4315
7.1171 6.52 1500 27.9161 0.4360 0.4279
7.1171 7.61 1750 29.9352 0.4383 0.4361
4.3718 8.7 2000 34.5593 0.4298 0.4191
4.3718 9.78 2250 34.0346 0.4421 0.4373
3.4048 10.87 2500 33.3230 0.4390 0.4351
3.4048 11.96 2750 35.1604 0.4367 0.4313
2.4739 13.04 3000 33.4441 0.4228 0.4170
2.4739 14.13 3250 32.9534 0.4367 0.4308
2.0055 15.22 3500 34.2647 0.4429 0.4414
2.0055 16.3 3750 33.4915 0.4460 0.4450
1.4812 17.39 4000 35.4776 0.4298 0.4249
1.4812 18.48 4250 35.4540 0.4375 0.4366
1.299 19.57 4500 34.2270 0.4468 0.4467
1.299 20.65 4750 34.7234 0.4460 0.4441
0.98 21.74 5000 34.8872 0.4352 0.4294
0.98 22.83 5250 34.8777 0.4383 0.4370
0.7847 23.91 5500 35.0968 0.4522 0.4518
0.7847 25.0 5750 34.3877 0.4329 0.4285
0.6835 26.09 6000 35.0458 0.4390 0.4365
0.6835 27.17 6250 35.2727 0.4360 0.4326
0.5378 28.26 6500 33.4029 0.4390 0.4353
0.5378 29.35 6750 35.0455 0.4421 0.4372

Framework versions

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