metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: trainer11
results: []
trainer11
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0559
- Precision: 0.6119
- Recall: 0.5833
- F1: 0.5850
- Accuracy: 0.5833
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: 5e-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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0243 | 0.57 | 30 | 2.3196 | 0.6424 | 0.5952 | 0.5823 | 0.5952 |
| 0.0329 | 1.13 | 60 | 2.9356 | 0.4952 | 0.5595 | 0.5177 | 0.5595 |
| 0.0724 | 1.7 | 90 | 3.0099 | 0.6234 | 0.5595 | 0.5412 | 0.5595 |
| 0.052 | 2.26 | 120 | 2.4391 | 0.6305 | 0.6190 | 0.6103 | 0.6190 |
| 0.0019 | 2.83 | 150 | 3.2342 | 0.6364 | 0.6071 | 0.6002 | 0.6071 |
| 0.0002 | 3.4 | 180 | 3.2336 | 0.6024 | 0.5714 | 0.5666 | 0.5714 |
| 0.0002 | 3.96 | 210 | 3.0605 | 0.6136 | 0.5833 | 0.5851 | 0.5833 |
| 0.0001 | 4.53 | 240 | 3.0569 | 0.6119 | 0.5833 | 0.5850 | 0.5833 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2