fblc-1000 / README.md
s-man2099's picture
Training in progress epoch 9
602a602
metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
  - generated_from_keras_callback
model-index:
  - name: s-man2099/fblc-1000
    results: []

s-man2099/fblc-1000

This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 2.7780
  • Validation Loss: 3.5367
  • Epoch: 9

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:

  • optimizer: {'name': 'Adafactor', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 6e-06, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
  • training_precision: mixed_float16

Training results

Train Loss Validation Loss Epoch
3.6412 3.5800 0
3.4101 3.5235 1
3.2777 3.5013 2
3.1688 3.4972 3
3.0803 3.4901 4
2.9866 3.5084 5
2.8833 3.5218 6
2.8039 3.5290 7
2.7741 3.5326 8
2.7780 3.5367 9

Framework versions

  • Transformers 4.34.1
  • TensorFlow 2.14.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1