---
library_name: transformers
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: defect-classification-scibert-baseline-10-epochs
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# defect-classification-scibert-baseline-10-epochs

This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2965
- Accuracy: 0.8886

## 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: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.3829        | 1.0   | 2124  | 0.6337          | 0.8424   |
| 1.0008        | 2.0   | 4248  | 0.4279          | 0.8789   |
| 0.8108        | 3.0   | 6372  | 0.3942          | 0.8808   |
| 0.7122        | 4.0   | 8496  | 0.3775          | 0.8769   |
| 0.6473        | 5.0   | 10620 | 0.3395          | 0.8816   |
| 0.622         | 6.0   | 12744 | 0.3346          | 0.8806   |
| 0.5915        | 7.0   | 14868 | 0.3135          | 0.8842   |
| 0.5661        | 8.0   | 16992 | 0.3008          | 0.8887   |
| 0.559         | 9.0   | 19116 | 0.2914          | 0.8910   |
| 0.5623        | 10.0  | 21240 | 0.2965          | 0.8886   |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0