newModel / README.md
sevvalkapcak's picture
Training in progress epoch 8
df18db2
|
raw
history blame
No virus
2.04 kB
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_keras_callback
model-index:
  - name: sevvalkapcak/newModel
    results: []

sevvalkapcak/newModel

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

  • Train Loss: 0.0183
  • Validation Loss: 0.7842
  • Train Accuracy: 0.9005
  • Epoch: 8

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': 'Adam', '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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Validation Loss Train Accuracy Epoch
0.0133 0.6573 0.901 0
0.0135 0.7314 0.9065 1
0.0104 0.6544 0.913 2
0.0148 0.7763 0.9035 3
0.0171 0.7110 0.9055 4
0.0121 0.7075 0.9015 5
0.0126 0.7461 0.8945 6
0.0212 0.7539 0.9035 7
0.0183 0.7842 0.9005 8

Framework versions

  • Transformers 4.35.2
  • TensorFlow 2.15.0
  • Datasets 2.16.1
  • Tokenizers 0.15.1