29thDay's picture
Training in progress, step 79
f7169f7 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: 0.2548
  • Accuracy: 0.9035
  • F1: 0.8134

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 0.6325 0.7464 0.0
No log 0.2020 79 0.3489 0.8487 0.6624
No log 0.4041 158 0.3422 0.8559 0.7462
No log 0.6061 237 0.2983 0.8674 0.7444
No log 0.8082 316 0.2837 0.8862 0.7871
No log 1.0102 395 0.2743 0.8919 0.7967
No log 1.2123 474 0.2772 0.8934 0.7956
0.3453 1.4143 553 0.2552 0.9092 0.8245
0.3453 1.6164 632 0.2486 0.9006 0.8056
0.3453 1.8184 711 0.2548 0.9035 0.8134

Framework versions

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