chuuhtetnaing's picture
End of training
eeeb81d verified
metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: spillage-distilbert-base-uncased
    results: []

spillage-distilbert-base-uncased

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

  • Loss: 2.0785
  • Accuracy: 0.6199

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: 2e-05
  • train_batch_size: 70
  • eval_batch_size: 70
  • seed: 42
  • 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
No log 1.0 23 1.3515 0.1956
No log 2.0 46 1.2029 0.4133
No log 3.0 69 1.0942 0.5092
No log 4.0 92 0.9780 0.5793
No log 5.0 115 0.9581 0.5609
No log 6.0 138 1.0374 0.5756
No log 7.0 161 1.0257 0.5941
No log 8.0 184 1.0842 0.5941
No log 9.0 207 1.1494 0.6052
No log 10.0 230 1.2238 0.6273
No log 11.0 253 1.2607 0.6421
No log 12.0 276 1.3324 0.6052
No log 13.0 299 1.5093 0.6199
No log 14.0 322 1.5016 0.6273
No log 15.0 345 1.6022 0.6384
No log 16.0 368 1.6277 0.6273
No log 17.0 391 1.7488 0.6384
No log 18.0 414 1.9428 0.6273
No log 19.0 437 1.8673 0.6273
No log 20.0 460 1.8853 0.6273
No log 21.0 483 1.9610 0.6347
0.2882 22.0 506 1.9328 0.6310
0.2882 23.0 529 1.9462 0.6421
0.2882 24.0 552 1.9936 0.6236
0.2882 25.0 575 2.0169 0.6236
0.2882 26.0 598 2.0216 0.6347
0.2882 27.0 621 2.0617 0.6310
0.2882 28.0 644 2.0578 0.6199
0.2882 29.0 667 2.0661 0.6236
0.2882 30.0 690 2.0785 0.6199

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1