metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned_9th
results: []
distilbert-base-uncased-finetuned_9th
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: 0.2826
- Accuracy: 0.4462
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 | Accuracy |
|---|---|---|---|---|
| 0.2357 | 1.0 | 569 | 0.2277 | 0.3474 |
| 0.2237 | 2.0 | 1138 | 0.2316 | 0.3474 |
| 0.1847 | 3.0 | 1707 | 0.2456 | 0.3712 |
| 0.1302 | 4.0 | 2276 | 0.2763 | 0.4602 |
| 0.0863 | 5.0 | 2845 | 0.2826 | 0.4462 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3