metadata
library_name: transformers
license: apache-2.0
base_model: PracticalWork/distilbert-base-uncased-classifier
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-classifier-classifier-prompted
results: []
distilbert-base-uncased-classifier-classifier-prompted
This model is a fine-tuned version of PracticalWork/distilbert-base-uncased-classifier on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2938
- Accuracy: 0.8955
- F1: 0.8918
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0 | 0 | 0.9353 | 0.6807 | 0.5592 |
| No log | 0.6 | 255 | 0.3035 | 0.8821 | 0.8786 |
| 0.2902 | 1.2 | 510 | 0.3121 | 0.8867 | 0.8844 |
| 0.2902 | 1.8 | 765 | 0.2690 | 0.9002 | 0.8963 |
| 0.1901 | 2.4 | 1020 | 0.2826 | 0.8967 | 0.8921 |
| 0.1901 | 3.0 | 1275 | 0.2938 | 0.8955 | 0.8918 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1