bedus-creation's picture
Training in progress epoch 23
daeb45a
|
raw
history blame
No virus
2.38 kB
metadata
license: apache-2.0
base_model: bedus-creation/eng-limbu-t5-base-all-001
tags:
  - generated_from_keras_callback
model-index:
  - name: bedus-creation/eng-limbu-t5-base-all-001
    results: []

bedus-creation/eng-limbu-t5-base-all-001

This model is a fine-tuned version of bedus-creation/eng-limbu-t5-base-all-001 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 3.8068
  • Validation Loss: 4.0910
  • Epoch: 23

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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Validation Loss Epoch
7.0062 6.1115 0
6.0720 5.8817 1
5.8833 5.7515 2
5.7643 5.6312 3
5.6159 5.5281 4
5.5133 5.4337 5
5.4239 5.3227 6
5.3002 5.2327 7
5.1915 5.1267 8
5.1029 5.0370 9
4.9916 4.9413 10
4.8633 4.8633 11
4.7651 4.7806 12
4.6682 4.7019 13
4.5570 4.6346 14
4.4718 4.5772 15
4.3830 4.5084 16
4.2749 4.4127 17
4.1922 4.3616 18
4.1207 4.3160 19
4.0164 4.2560 20
3.9700 4.1961 21
3.8745 4.1515 22
3.8068 4.0910 23

Framework versions

  • Transformers 4.33.2
  • TensorFlow 2.13.0
  • Datasets 2.14.5
  • Tokenizers 0.13.3