metadata
license: apache-2.0
base_model: google-t5/t5-large
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: fft-t5-large/adversarial_qa_dbert_based_on
results: []
fft-t5-large/adversarial_qa_dbert_based_on
This model is a fine-tuned version of google-t5/t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1381
- Exact Match: 0.3467
- Bleu: 0.3083
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 8
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Bleu |
|---|---|---|---|---|---|
| 1.0162 | 1.0 | 63 | 0.7607 | 0.2754 | 0.2749 |
| 0.3929 | 2.0 | 126 | 0.7943 | 0.2959 | 0.2412 |
| 0.1542 | 3.0 | 189 | 1.0053 | 0.3018 | 0.2720 |
| 0.0544 | 4.0 | 252 | 1.1005 | 0.3457 | 0.3185 |
| 0.0239 | 5.0 | 315 | 1.1381 | 0.3467 | 0.3083 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1