metadata
license: mit
tags:
- generated_from_trainer
datasets:
- snips_built_in_intents
metrics:
- accuracy
model-index:
- name: roberta-base-finetuned-intent
results: []
roberta-base-finetuned-intent
This model is a fine-tuned version of roberta-base on the snips_built_in_intents dataset. It achieves the following results on the evaluation set:
- Loss: 0.2339
- Accuracy: 1.0
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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: IPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- total_eval_batch_size: 5
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- training precision: Mixed Precision
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9236 | 1.0 | 37 | 1.6689 | 0.3667 |
| 0.9259 | 2.0 | 74 | 0.7197 | 0.8333 |
| 0.4666 | 3.0 | 111 | 0.2339 | 1.0 |
| 0.1732 | 4.0 | 148 | 0.1144 | 1.0 |
| 0.1412 | 5.0 | 185 | 0.0724 | 1.0 |
| 0.1023 | 6.0 | 222 | 0.0536 | 1.0 |
| 0.0772 | 7.0 | 259 | 0.0453 | 1.0 |
| 0.0786 | 8.0 | 296 | 0.0396 | 1.0 |
| 0.0581 | 9.0 | 333 | 0.0374 | 1.0 |
| 0.0553 | 10.0 | 370 | 0.0364 | 1.0 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.0+cpu
- Datasets 2.7.1
- Tokenizers 0.12.0