metadata
base_model: ybelkada/flan-t5-xl-sharded-bf16
tags:
- generated_from_trainer
datasets:
- sem_eval2014_task4
model-index:
- name: flan-t5-xl-absa-rest
results: []
flan-t5-xl-absa-rest
This model is a fine-tuned version of ybelkada/flan-t5-xl-sharded-bf16 on the sem_eval2014_task4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1705
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4491 | 0.9 | 200 | 0.7559 |
| 0.4855 | 1.8 | 400 | 0.2962 |
| 0.3356 | 2.7 | 600 | 0.2460 |
| 0.2742 | 3.6 | 800 | 0.2234 |
| 0.2529 | 4.5 | 1000 | 0.2087 |
| 0.2381 | 5.41 | 1200 | 0.1907 |
| 0.217 | 6.31 | 1400 | 0.1844 |
| 0.2101 | 7.21 | 1600 | 0.1796 |
| 0.2113 | 8.11 | 1800 | 0.1737 |
| 0.2026 | 9.01 | 2000 | 0.1722 |
| 0.1988 | 9.91 | 2200 | 0.1705 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2