metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ft1500_norm500
results: []
distilbert-base-uncased-finetuned-ft1500_norm500
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8852
- Mse: 2.9505
- Mae: 1.0272
- R2: 0.4233
- Accuracy: 0.4914
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.62 | 1.0 | 3122 | 0.8853 | 2.9511 | 1.0392 | 0.4232 | 0.4830 |
| 0.5042 | 2.0 | 6244 | 0.8695 | 2.8984 | 1.0347 | 0.4335 | 0.4651 |
| 0.309 | 3.0 | 9366 | 0.8852 | 2.9505 | 1.0272 | 0.4233 | 0.4914 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1