metadata
license: apache-2.0
base_model: google/flan-t5-large
tags:
- generated_from_trainer
model-index:
- name: flan-t5-large-absa-multitask-rest
results: []
flan-t5-large-absa-multitask-rest
This model is a fine-tuned version of google/flan-t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0807
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3816 | 0.32 | 200 | 0.2912 |
| 0.2673 | 0.63 | 400 | 0.1971 |
| 0.2042 | 0.95 | 600 | 0.1625 |
| 0.1531 | 1.27 | 800 | 0.1406 |
| 0.1328 | 1.58 | 1000 | 0.1395 |
| 0.1214 | 1.9 | 1200 | 0.1135 |
| 0.1027 | 2.22 | 1400 | 0.1092 |
| 0.0808 | 2.53 | 1600 | 0.1041 |
| 0.0766 | 2.85 | 1800 | 0.0920 |
| 0.0586 | 3.16 | 2000 | 0.0855 |
| 0.053 | 3.48 | 2200 | 0.0851 |
| 0.0598 | 3.8 | 2400 | 0.0807 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2