punic-model / README.md
ghdi's picture
Training in progress epoch 27
fdff334
|
raw
history blame
2.71 kB
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: ghdi/punic-model
    results: []

ghdi/punic-model

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 6.8629
  • Validation Loss: 7.4881
  • Epoch: 27

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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': -984, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: mixed_float16

Training results

Train Loss Validation Loss Epoch
10.9100 10.8188 0
10.7129 10.4690 1
10.3775 10.1048 2
10.0587 9.8271 3
9.8034 9.6395 4
9.6209 9.5085 5
9.5047 9.4043 6
9.3724 9.3072 7
9.2873 9.2090 8
9.1690 9.1091 9
8.9963 9.0013 10
8.8724 8.8875 11
8.7316 8.7701 12
8.6070 8.6477 13
8.4242 8.5243 14
8.2700 8.4018 15
8.1555 8.2834 16
7.9978 8.1696 17
7.8495 8.0607 18
7.6980 7.9635 19
7.5339 7.8726 20
7.4741 7.7917 21
7.3669 7.7233 22
7.2598 7.6604 23
7.1434 7.6088 24
7.0434 7.5579 25
6.9874 7.5171 26
6.8629 7.4881 27

Framework versions

  • Transformers 4.28.1
  • TensorFlow 2.12.0
  • Datasets 2.11.0
  • Tokenizers 0.13.3