|
--- |
|
base_model: ybelkada/flan-t5-xl-sharded-bf16 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: flan-t5-xl-absa-laptops |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# flan-t5-xl-absa-laptops |
|
|
|
This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1812 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.9772 | 0.9 | 200 | 0.7029 | |
|
| 0.5108 | 1.8 | 400 | 0.3043 | |
|
| 0.3323 | 2.7 | 600 | 0.2414 | |
|
| 0.2935 | 3.6 | 800 | 0.2193 | |
|
| 0.2529 | 4.5 | 1000 | 0.2077 | |
|
| 0.2374 | 5.41 | 1200 | 0.1988 | |
|
| 0.217 | 6.31 | 1400 | 0.1918 | |
|
| 0.2088 | 7.21 | 1600 | 0.1896 | |
|
| 0.2054 | 8.11 | 1800 | 0.1874 | |
|
| 0.1979 | 9.01 | 2000 | 0.1822 | |
|
| 0.1963 | 9.91 | 2200 | 0.1812 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
