Hugging Face's logo

haryoaw
/
scenario-KD-SCR-MSV-EN-CL-D2_data-en-massive_all_1_144

PyTorch
deberta-v2
Generated from Trainer
Model card Files Community
scenario-KD-SCR-MSV-EN-CL-D2_data-en-massive_all_1_144 / README.md
haryoaw's picture
haryoaw
Initial Commit
1a5246f verified
preview code
|
raw
history blame contribute delete
9.29 kB
metadata
license: mit
base_model: haryoaw/scenario-MDBT-TCR_data-cl-massive_all_1_1
tags:
  - generated_from_trainer
datasets:
  - massive
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-KD-SCR-MSV-EN-CL-D2_data-en-massive_all_1_144
    results: []

scenario-KD-SCR-MSV-EN-CL-D2_data-en-massive_all_1_144

This model is a fine-tuned version of haryoaw/scenario-MDBT-TCR_data-cl-massive_all_1_1 on the massive dataset. It achieves the following results on the evaluation set:

  • Loss: nan
  • Accuracy: 0.0315
  • F1: 0.0010

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 0.28 100 nan 0.0315 0.0010
No log 0.56 200 nan 0.0315 0.0010
No log 0.83 300 nan 0.0315 0.0010
No log 1.11 400 nan 0.0315 0.0010
2.4963 1.39 500 nan 0.0315 0.0010
2.4963 1.67 600 nan 0.0315 0.0010
2.4963 1.94 700 nan 0.0315 0.0010
2.4963 2.22 800 nan 0.0315 0.0010
2.4963 2.5 900 nan 0.0315 0.0010
0.0 2.78 1000 nan 0.0315 0.0010
0.0 3.06 1100 nan 0.0315 0.0010
0.0 3.33 1200 nan 0.0315 0.0010
0.0 3.61 1300 nan 0.0315 0.0010
0.0 3.89 1400 nan 0.0315 0.0010
0.0 4.17 1500 nan 0.0315 0.0010
0.0 4.44 1600 nan 0.0315 0.0010
0.0 4.72 1700 nan 0.0315 0.0010
0.0 5.0 1800 nan 0.0315 0.0010
0.0 5.28 1900 nan 0.0315 0.0010
0.0 5.56 2000 nan 0.0315 0.0010
0.0 5.83 2100 nan 0.0315 0.0010
0.0 6.11 2200 nan 0.0315 0.0010
0.0 6.39 2300 nan 0.0315 0.0010
0.0 6.67 2400 nan 0.0315 0.0010
0.0 6.94 2500 nan 0.0315 0.0010
0.0 7.22 2600 nan 0.0315 0.0010
0.0 7.5 2700 nan 0.0315 0.0010
0.0 7.78 2800 nan 0.0315 0.0010
0.0 8.06 2900 nan 0.0315 0.0010
0.0 8.33 3000 nan 0.0315 0.0010
0.0 8.61 3100 nan 0.0315 0.0010
0.0 8.89 3200 nan 0.0315 0.0010
0.0 9.17 3300 nan 0.0315 0.0010
0.0 9.44 3400 nan 0.0315 0.0010
0.0 9.72 3500 nan 0.0315 0.0010
0.0 10.0 3600 nan 0.0315 0.0010
0.0 10.28 3700 nan 0.0315 0.0010
0.0 10.56 3800 nan 0.0315 0.0010
0.0 10.83 3900 nan 0.0315 0.0010
0.0 11.11 4000 nan 0.0315 0.0010
0.0 11.39 4100 nan 0.0315 0.0010
0.0 11.67 4200 nan 0.0315 0.0010
0.0 11.94 4300 nan 0.0315 0.0010
0.0 12.22 4400 nan 0.0315 0.0010
0.0 12.5 4500 nan 0.0315 0.0010
0.0 12.78 4600 nan 0.0315 0.0010
0.0 13.06 4700 nan 0.0315 0.0010
0.0 13.33 4800 nan 0.0315 0.0010
0.0 13.61 4900 nan 0.0315 0.0010
0.0 13.89 5000 nan 0.0315 0.0010
0.0 14.17 5100 nan 0.0315 0.0010
0.0 14.44 5200 nan 0.0315 0.0010
0.0 14.72 5300 nan 0.0315 0.0010
0.0 15.0 5400 nan 0.0315 0.0010
0.0 15.28 5500 nan 0.0315 0.0010
0.0 15.56 5600 nan 0.0315 0.0010
0.0 15.83 5700 nan 0.0315 0.0010
0.0 16.11 5800 nan 0.0315 0.0010
0.0 16.39 5900 nan 0.0315 0.0010
0.0 16.67 6000 nan 0.0315 0.0010
0.0 16.94 6100 nan 0.0315 0.0010
0.0 17.22 6200 nan 0.0315 0.0010
0.0 17.5 6300 nan 0.0315 0.0010
0.0 17.78 6400 nan 0.0315 0.0010
0.0 18.06 6500 nan 0.0315 0.0010
0.0 18.33 6600 nan 0.0315 0.0010
0.0 18.61 6700 nan 0.0315 0.0010
0.0 18.89 6800 nan 0.0315 0.0010
0.0 19.17 6900 nan 0.0315 0.0010
0.0 19.44 7000 nan 0.0315 0.0010
0.0 19.72 7100 nan 0.0315 0.0010
0.0 20.0 7200 nan 0.0315 0.0010
0.0 20.28 7300 nan 0.0315 0.0010
0.0 20.56 7400 nan 0.0315 0.0010
0.0 20.83 7500 nan 0.0315 0.0010
0.0 21.11 7600 nan 0.0315 0.0010
0.0 21.39 7700 nan 0.0315 0.0010
0.0 21.67 7800 nan 0.0315 0.0010
0.0 21.94 7900 nan 0.0315 0.0010
0.0 22.22 8000 nan 0.0315 0.0010
0.0 22.5 8100 nan 0.0315 0.0010
0.0 22.78 8200 nan 0.0315 0.0010
0.0 23.06 8300 nan 0.0315 0.0010
0.0 23.33 8400 nan 0.0315 0.0010
0.0 23.61 8500 nan 0.0315 0.0010
0.0 23.89 8600 nan 0.0315 0.0010
0.0 24.17 8700 nan 0.0315 0.0010
0.0 24.44 8800 nan 0.0315 0.0010
0.0 24.72 8900 nan 0.0315 0.0010
0.0 25.0 9000 nan 0.0315 0.0010
0.0 25.28 9100 nan 0.0315 0.0010
0.0 25.56 9200 nan 0.0315 0.0010
0.0 25.83 9300 nan 0.0315 0.0010
0.0 26.11 9400 nan 0.0315 0.0010
0.0 26.39 9500 nan 0.0315 0.0010
0.0 26.67 9600 nan 0.0315 0.0010
0.0 26.94 9700 nan 0.0315 0.0010
0.0 27.22 9800 nan 0.0315 0.0010
0.0 27.5 9900 nan 0.0315 0.0010
0.0 27.78 10000 nan 0.0315 0.0010
0.0 28.06 10100 nan 0.0315 0.0010
0.0 28.33 10200 nan 0.0315 0.0010
0.0 28.61 10300 nan 0.0315 0.0010
0.0 28.89 10400 nan 0.0315 0.0010
0.0 29.17 10500 nan 0.0315 0.0010
0.0 29.44 10600 nan 0.0315 0.0010
0.0 29.72 10700 nan 0.0315 0.0010
0.0 30.0 10800 nan 0.0315 0.0010

Framework versions

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