metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: lavan
results: []
lavan
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2047
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: 1e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.436 | 1.0 | 500 | 1.7459 |
| 0.3304 | 2.0 | 1000 | 1.8949 |
| 0.2503 | 3.0 | 1500 | 2.0612 |
| 0.207 | 4.0 | 2000 | 2.0813 |
| 0.1705 | 5.0 | 2500 | 2.2047 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2