t5-base-mmlu-qa2a
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1856
- Validation Loss: 0.2587
- Epoch: 1
{'eval_loss': 2.8363170623779297,
'eval_bleu': 8.346157741863188,
'eval_rouge1': 19.52,
'eval_rouge2': 6.55,
'eval_rougeL': 18.19,
'eval_rougeLsum': 18.19,
'eval_exact': 0.0019177661859466095,
'eval_runtime': 278.5068,
'eval_samples_per_second': 46.807,
'eval_steps_per_second': 1.465}
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': False, 'is_legacy_optimizer': False, 'learning_rate': 0.001, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.3922 | 0.2555 | 0 |
| 0.1856 | 0.2587 | 1 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.14.3
- Tokenizers 0.13.3