metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: outputs
results: []
outputs
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: 0.8994
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 50 | 0.9325 |
| No log | 2.0 | 100 | 0.6820 |
| No log | 3.0 | 150 | 0.6297 |
| No log | 4.0 | 200 | 0.7296 |
| No log | 5.0 | 250 | 0.8239 |
| No log | 6.0 | 300 | 0.8474 |
| No log | 7.0 | 350 | 0.8558 |
| No log | 8.0 | 400 | 0.8872 |
| No log | 9.0 | 450 | 0.8950 |
| 0.2679 | 10.0 | 500 | 0.8994 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2