models-moved / README.md
Raul0909's picture
Model save
5de5c1b
|
Raw History Blame Contribute Delete
2.71 kB
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: models
    results: []

models

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1922
  • Accuracy: 0.6853

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 7

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.29 100 3.0920 0.3456
No log 0.59 200 2.4584 0.4824
No log 0.88 300 2.0378 0.5426
No log 1.18 400 1.7976 0.5765
2.3754 1.47 500 1.5789 0.6206
2.3754 1.76 600 1.4642 0.6382
2.3754 2.06 700 1.3958 0.6515
2.3754 2.35 800 1.3437 0.6382
2.3754 2.65 900 1.2471 0.6676
1.0269 2.94 1000 1.1821 0.6824
1.0269 3.24 1100 1.1879 0.6838
1.0269 3.53 1200 1.1325 0.6824
1.0269 3.82 1300 1.1910 0.6838
1.0269 4.12 1400 1.1605 0.6868
0.6463 4.41 1500 1.1799 0.6838
0.6463 4.71 1600 1.1747 0.6853
0.6463 5.0 1700 1.1524 0.6897
0.6463 5.29 1800 1.1651 0.6897
0.6463 5.59 1900 1.1932 0.6941
0.4804 5.88 2000 1.1828 0.6824
0.4804 6.18 2100 1.1891 0.6853
0.4804 6.47 2200 1.1921 0.6882
0.4804 6.76 2300 1.1922 0.6853

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.1.1+cpu
  • Datasets 2.15.0
  • Tokenizers 0.15.0