metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
model-index:
- name: setup_2C
results: []
setup_2C
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0781
- Bleu1: 0.2704
- Bleu2: 0.1763
- Bleu3: 0.1219
- Bleu4: 0.087
- Meteor: 0.3266
- Bertscore Precision: 0.7963
- Bertscore Recall: 0.7572
- Bertscore F1: 0.7756
- Gen Len: 16.9447
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:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu1 | Bleu2 | Bleu3 | Bleu4 | Meteor | Bertscore Precision | Bertscore Recall | Bertscore F1 | Gen Len |
---|---|---|---|---|---|---|---|---|---|---|---|---|
2.3795 | 1.0 | 3125 | 2.1232 | 0.2656 | 0.1704 | 0.1161 | 0.082 | 0.3158 | 0.7927 | 0.7541 | 0.7723 | 16.9152 |
2.2942 | 2.0 | 6250 | 2.0867 | 0.2707 | 0.1762 | 0.1214 | 0.0865 | 0.3256 | 0.7957 | 0.7568 | 0.7752 | 16.9258 |
2.2602 | 3.0 | 9375 | 2.0781 | 0.2704 | 0.1763 | 0.1219 | 0.087 | 0.3266 | 0.7963 | 0.7572 | 0.7756 | 16.9447 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2