Hugging Face's logo

haryoaw
/
scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only66

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only66 / README.md
haryoaw's picture
haryoaw
Upload tokenizer
aa9750c verified
preview code
|
raw
history blame contribute delete
3.44 kB
metadata
base_model: microsoft/mdeberta-v3-base
library_name: transformers
license: mit
metrics:
  - accuracy
  - f1
tags:
  - generated_from_trainer
model-index:
  - name: scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only66
    results: []

scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only66

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 6.5386
  • Accuracy: 0.3465
  • F1: 0.3414

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 1.0870 250 1.2253 0.3488 0.3475
0.9005 2.1739 500 2.0350 0.3789 0.3632
0.9005 3.2609 750 2.5675 0.3657 0.3555
0.3085 4.3478 1000 3.0866 0.3573 0.3545
0.3085 5.4348 1250 3.2835 0.3665 0.3656
0.0989 6.5217 1500 3.7686 0.3611 0.3591
0.0989 7.6087 1750 4.3473 0.3519 0.3466
0.0419 8.6957 2000 4.5813 0.3596 0.3587
0.0419 9.7826 2250 4.3827 0.3480 0.3406
0.0259 10.8696 2500 4.5804 0.3580 0.3502
0.0259 11.9565 2750 4.7408 0.3403 0.3301
0.0212 13.0435 3000 5.1266 0.3449 0.3369
0.0212 14.1304 3250 5.1394 0.3372 0.3232
0.0161 15.2174 3500 5.1845 0.3503 0.3449
0.0161 16.3043 3750 5.5978 0.3441 0.3324
0.0086 17.3913 4000 5.5039 0.3441 0.3428
0.0086 18.4783 4250 5.2184 0.3480 0.3462
0.0078 19.5652 4500 5.5761 0.3503 0.3429
0.0078 20.6522 4750 6.1793 0.3449 0.3402
0.0041 21.7391 5000 6.2729 0.3557 0.3460
0.0041 22.8261 5250 6.1750 0.3495 0.3475
0.0034 23.9130 5500 6.6237 0.3503 0.3424
0.0034 25.0 5750 6.5137 0.3480 0.3449
0.0034 26.0870 6000 6.4670 0.3449 0.3421
0.0034 27.1739 6250 6.5232 0.3511 0.3484
0.0012 28.2609 6500 6.5751 0.3480 0.3424
0.0012 29.3478 6750 6.5386 0.3465 0.3414

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.19.1