29thDay's picture
Training in progress, step 79
abca788 verified
|
raw
history blame
2.24 kB
metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert-base-uncased-classifier
    results: []

distilbert-base-uncased-classifier

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

  • Loss: 0.2565
  • Accuracy: 0.8991
  • F1: 0.8045

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 0 0 0.7631 0.2536 0.4046
No log 0.2020 79 0.3566 0.8559 0.6689
No log 0.4041 158 0.3387 0.8573 0.7506
No log 0.6061 237 0.2934 0.8804 0.7688
No log 0.8082 316 0.2863 0.8890 0.7947
No log 1.0102 395 0.2716 0.8876 0.7869
No log 1.2123 474 0.2799 0.8905 0.7877
0.3458 1.4143 553 0.2581 0.8977 0.8033
0.3458 1.6164 632 0.2539 0.8977 0.8011
0.3458 1.8184 711 0.2565 0.8991 0.8045

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.7.0+cu126
  • Datasets 3.5.0
  • Tokenizers 0.21.1