metadata
library_name: peft
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: build_your_circuit_lora_v3
results: []
build_your_circuit_lora_v3
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5612
- Bleu: 0.5934
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 0.7731 | 0.2211 | 500 | 0.6249 | 0.5426 |
| 0.755 | 0.4423 | 1000 | 0.6122 | 0.5651 |
| 0.7409 | 0.6634 | 1500 | 0.6052 | 0.5805 |
| 0.7283 | 0.8846 | 2000 | 0.5954 | 0.5881 |
| 0.7189 | 1.1057 | 2500 | 0.5888 | 0.6041 |
| 0.7068 | 1.3268 | 3000 | 0.5793 | 0.5852 |
| 0.6969 | 1.5480 | 3500 | 0.5710 | 0.5938 |
| 0.6868 | 1.7691 | 4000 | 0.5666 | 0.5882 |
| 0.6811 | 1.9903 | 4500 | 0.5612 | 0.5934 |
Framework versions
- PEFT 0.15.2
- Transformers 4.56.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.22.0