metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: prova2
results: []
prova2
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: 2.2220
- Accuracy: 0.4833
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: 16
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 139 | 1.6285 | 0.3667 |
| No log | 2.0 | 278 | 1.7874 | 0.3167 |
| No log | 3.0 | 417 | 1.6707 | 0.45 |
| 1.2047 | 4.0 | 556 | 1.6612 | 0.4 |
| 1.2047 | 5.0 | 695 | 1.8812 | 0.45 |
| 1.2047 | 6.0 | 834 | 2.2119 | 0.4833 |
| 1.2047 | 7.0 | 973 | 2.0258 | 0.4833 |
| 0.4952 | 8.0 | 1112 | 2.2140 | 0.45 |
| 0.4952 | 9.0 | 1251 | 2.2031 | 0.45 |
| 0.4952 | 10.0 | 1390 | 2.2220 | 0.4833 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cpu
- Datasets 2.14.6
- Tokenizers 0.14.1