Instructions to use Shakhovak/flan-t5-base-absa-rest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shakhovak/flan-t5-base-absa-rest with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Shakhovak/flan-t5-base-absa-rest") model = AutoModelForSeq2SeqLM.from_pretrained("Shakhovak/flan-t5-base-absa-rest", device_map="auto") - Notebooks
- Google Colab
- Kaggle
flan-t5-base-absa-rest
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2490
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7338 | 0.45 | 200 | 0.3705 |
| 0.4162 | 0.9 | 400 | 0.2968 |
| 0.3228 | 1.35 | 600 | 0.2798 |
| 0.2954 | 1.8 | 800 | 0.2653 |
| 0.2679 | 2.25 | 1000 | 0.2483 |
| 0.2449 | 2.7 | 1200 | 0.2490 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for Shakhovak/flan-t5-base-absa-rest
Base model
google/flan-t5-base