metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: distilbert-base-uncased_intent
results: []
distilbert-base-uncased_intent
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 8.9202
- F1: 0.176
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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 312 | 6.9264 | 0.168 |
| 0.3875 | 2.0 | 624 | 8.0481 | 0.172 |
| 0.3875 | 3.0 | 936 | 8.5746 | 0.176 |
| 0.057 | 4.0 | 1248 | 8.8202 | 0.176 |
| 0.0264 | 5.0 | 1560 | 8.9202 | 0.176 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3