metadata
base_model: ybelkada/flan-t5-xl-sharded-bf16
tags:
- generated_from_trainer
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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1480
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.6478 | 0.9 | 200 | 0.9703 |
| 0.5623 | 1.8 | 400 | 0.2571 |
| 0.3339 | 2.7 | 600 | 0.2022 |
| 0.2858 | 3.6 | 800 | 0.1855 |
| 0.2566 | 4.5 | 1000 | 0.1839 |
| 0.2327 | 5.41 | 1200 | 0.1727 |
| 0.2158 | 6.31 | 1400 | 0.1580 |
| 0.2133 | 7.21 | 1600 | 0.1506 |
| 0.194 | 8.11 | 1800 | 0.1547 |
| 0.1933 | 9.01 | 2000 | 0.1496 |
| 0.1898 | 9.91 | 2200 | 0.1491 |
| 0.1823 | 10.81 | 2400 | 0.1499 |
| 0.1725 | 11.71 | 2600 | 0.1480 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2