metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
model-index:
- name: hw-slots-atis
results: []
hw-slots-atis
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0054
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: 2e-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
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4235 | 1.6 | 500 | 0.0911 |
| 0.0725 | 3.21 | 1000 | 0.0375 |
| 0.0333 | 4.81 | 1500 | 0.0188 |
| 0.0211 | 6.41 | 2000 | 0.0108 |
| 0.014 | 8.01 | 2500 | 0.0072 |
| 0.0101 | 9.62 | 3000 | 0.0066 |
| 0.0079 | 11.22 | 3500 | 0.0053 |
| 0.0053 | 12.82 | 4000 | 0.0054 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2