---
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: uniBERT.RoBERTa.1
  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. -->

# uniBERT.RoBERTa.1

This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5672
- Accuracy: (0.5442359249329759,)
- F1: (0.5475073377350592,)
- Precision: (0.5667013774255618,)
- Recall: 0.5442

## 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: 16
- eval_batch_size: 64
- 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               | F1                     | Precision              | Recall |
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:----------------------:|:----------------------:|:------:|
| 3.2351        | 1.0   | 163  | 2.9595          | (0.13136729222520108,) | (0.08462626197008986,) | (0.15744495937224648,) | 0.1314 |
| 2.6973        | 2.0   | 326  | 2.3531          | (0.2770330652368186,)  | (0.24847446131015896,) | (0.3687711586389575,)  | 0.2770 |
| 2.149         | 3.0   | 489  | 1.9958          | (0.37980339588918677,) | (0.375810644629823,)   | (0.46219745175706833,) | 0.3798 |
| 1.7           | 4.0   | 652  | 1.8677          | (0.40303842716711347,) | (0.40227689144186507,) | (0.4955990588890976,)  | 0.4030 |
| 1.4386        | 5.0   | 815  | 1.7207          | (0.4709562109025916,)  | (0.47394753337956536,) | (0.5204593065553081,)  | 0.4710 |
| 1.1631        | 6.0   | 978  | 1.6443          | (0.49955317247542447,) | (0.5021533796342853,)  | (0.532760172396733,)   | 0.4996 |
| 1.0801        | 7.0   | 1141 | 1.6049          | (0.5192135835567471,)  | (0.5209002930812098,)  | (0.5501889941115035,)  | 0.5192 |
| 0.9166        | 8.0   | 1304 | 1.5975          | (0.5299374441465594,)  | (0.5346686129926844,)  | (0.5631677420777581,)  | 0.5299 |
| 0.7877        | 9.0   | 1467 | 1.5711          | (0.5397676496872207,)  | (0.5438919405653636,)  | (0.5628843016520076,)  | 0.5398 |
| 0.8112        | 10.0  | 1630 | 1.5672          | (0.5442359249329759,)  | (0.5475073377350592,)  | (0.5667013774255618,)  | 0.5442 |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2