Hugging Face's logo

haryoaw
/
scenario-KD-SCR-MSV-D2_data-AmazonScience_massive_all_1_144

Transformers
PyTorch
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Community
scenario-KD-SCR-MSV-D2_data-AmazonScience_massive_all_1_144 / README.md
haryoaw's picture
haryoaw
Initial Commit
90a4b13 verified
preview code
|
raw
history blame contribute delete
9.64 kB
metadata
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
  - generated_from_trainer
datasets:
  - massive
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-KD-SCR-MSV-D2_data-AmazonScience_massive_all_1_144
    results: []

scenario-KD-SCR-MSV-D2_data-AmazonScience_massive_all_1_144

This model is a fine-tuned version of microsoft/mdeberta-v3-base 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
0.0 0.27 5000 nan 0.0315 0.0010
0.0 0.53 10000 nan 0.0315 0.0010
0.0 0.8 15000 nan 0.0315 0.0010
0.0 1.07 20000 nan 0.0315 0.0010
0.0 1.34 25000 nan 0.0315 0.0010
0.0 1.6 30000 nan 0.0315 0.0010
0.0 1.87 35000 nan 0.0315 0.0010
0.0 2.14 40000 nan 0.0315 0.0010
0.0 2.41 45000 nan 0.0315 0.0010
0.0 2.67 50000 nan 0.0315 0.0010
0.0 2.94 55000 nan 0.0315 0.0010
0.0 3.21 60000 nan 0.0315 0.0010
0.0 3.47 65000 nan 0.0315 0.0010
0.0 3.74 70000 nan 0.0315 0.0010
0.0 4.01 75000 nan 0.0315 0.0010
0.0 4.28 80000 nan 0.0315 0.0010
0.0 4.54 85000 nan 0.0315 0.0010
0.0 4.81 90000 nan 0.0315 0.0010
0.0 5.08 95000 nan 0.0315 0.0010
0.0 5.34 100000 nan 0.0315 0.0010
0.0 5.61 105000 nan 0.0315 0.0010
0.0 5.88 110000 nan 0.0315 0.0010
0.0 6.15 115000 nan 0.0315 0.0010
0.0 6.41 120000 nan 0.0315 0.0010
0.0 6.68 125000 nan 0.0315 0.0010
0.0 6.95 130000 nan 0.0315 0.0010
0.0 7.22 135000 nan 0.0315 0.0010
0.0 7.48 140000 nan 0.0315 0.0010
0.0 7.75 145000 nan 0.0315 0.0010
0.0 8.02 150000 nan 0.0315 0.0010
0.0 8.28 155000 nan 0.0315 0.0010
0.0 8.55 160000 nan 0.0315 0.0010
0.0 8.82 165000 nan 0.0315 0.0010
0.0 9.09 170000 nan 0.0315 0.0010
0.0 9.35 175000 nan 0.0315 0.0010
0.0 9.62 180000 nan 0.0315 0.0010
0.0 9.89 185000 nan 0.0315 0.0010
0.0 10.15 190000 nan 0.0315 0.0010
0.0 10.42 195000 nan 0.0315 0.0010
0.0 10.69 200000 nan 0.0315 0.0010
0.0 10.96 205000 nan 0.0315 0.0010
0.0 11.22 210000 nan 0.0315 0.0010
0.0 11.49 215000 nan 0.0315 0.0010
0.0 11.76 220000 nan 0.0315 0.0010
0.0 12.03 225000 nan 0.0315 0.0010
0.0 12.29 230000 nan 0.0315 0.0010
0.0 12.56 235000 nan 0.0315 0.0010
0.0 12.83 240000 nan 0.0315 0.0010
0.0 13.09 245000 nan 0.0315 0.0010
0.0 13.36 250000 nan 0.0315 0.0010
0.0 13.63 255000 nan 0.0315 0.0010
0.0 13.9 260000 nan 0.0315 0.0010
0.0 14.16 265000 nan 0.0315 0.0010
0.0 14.43 270000 nan 0.0315 0.0010
0.0 14.7 275000 nan 0.0315 0.0010
0.0 14.96 280000 nan 0.0315 0.0010
0.0 15.23 285000 nan 0.0315 0.0010
0.0 15.5 290000 nan 0.0315 0.0010
0.0 15.77 295000 nan 0.0315 0.0010
0.0 16.03 300000 nan 0.0315 0.0010
0.0 16.3 305000 nan 0.0315 0.0010
0.0 16.57 310000 nan 0.0315 0.0010
0.0 16.84 315000 nan 0.0315 0.0010
0.0 17.1 320000 nan 0.0315 0.0010
0.0 17.37 325000 nan 0.0315 0.0010
0.0 17.64 330000 nan 0.0315 0.0010
0.0 17.9 335000 nan 0.0315 0.0010
0.0 18.17 340000 nan 0.0315 0.0010
0.0 18.44 345000 nan 0.0315 0.0010
0.0 18.71 350000 nan 0.0315 0.0010
0.0 18.97 355000 nan 0.0315 0.0010
0.0 19.24 360000 nan 0.0315 0.0010
0.0 19.51 365000 nan 0.0315 0.0010
0.0 19.77 370000 nan 0.0315 0.0010
0.0 20.04 375000 nan 0.0315 0.0010
0.0 20.31 380000 nan 0.0315 0.0010
0.0 20.58 385000 nan 0.0315 0.0010
0.0 20.84 390000 nan 0.0315 0.0010
0.0 21.11 395000 nan 0.0315 0.0010
0.0 21.38 400000 nan 0.0315 0.0010
0.0 21.65 405000 nan 0.0315 0.0010
0.0 21.91 410000 nan 0.0315 0.0010
0.0 22.18 415000 nan 0.0315 0.0010
0.0 22.45 420000 nan 0.0315 0.0010
0.0 22.71 425000 nan 0.0315 0.0010
0.0 22.98 430000 nan 0.0315 0.0010
0.0 23.25 435000 nan 0.0315 0.0010
0.0 23.52 440000 nan 0.0315 0.0010
0.0 23.78 445000 nan 0.0315 0.0010
0.0 24.05 450000 nan 0.0315 0.0010
0.0 24.32 455000 nan 0.0315 0.0010
0.0 24.58 460000 nan 0.0315 0.0010
0.0 24.85 465000 nan 0.0315 0.0010
0.0 25.12 470000 nan 0.0315 0.0010
0.0 25.39 475000 nan 0.0315 0.0010
0.0 25.65 480000 nan 0.0315 0.0010
0.0 25.92 485000 nan 0.0315 0.0010
0.0 26.19 490000 nan 0.0315 0.0010
0.0 26.46 495000 nan 0.0315 0.0010
0.0 26.72 500000 nan 0.0315 0.0010
0.0 26.99 505000 nan 0.0315 0.0010
0.0 27.26 510000 nan 0.0315 0.0010
0.0 27.52 515000 nan 0.0315 0.0010
0.0 27.79 520000 nan 0.0315 0.0010
0.0 28.06 525000 nan 0.0315 0.0010
0.0 28.33 530000 nan 0.0315 0.0010
0.0 28.59 535000 nan 0.0315 0.0010
0.0 28.86 540000 nan 0.0315 0.0010
0.0 29.13 545000 nan 0.0315 0.0010
0.0 29.39 550000 nan 0.0315 0.0010
0.0 29.66 555000 nan 0.0315 0.0010
0.0 29.93 560000 nan 0.0315 0.0010

Framework versions

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