---
license: mit
tags:
- generated_from_trainer
base_model: FacebookAI/roberta-large
metrics:
- accuracy
model-index:
- name: roberta-large-zeroshot-v2.0-2024-03-22-14-58
  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. -->

# roberta-large-zeroshot-v2.0-2024-03-22-14-58

This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1357
- F1 Macro: 0.5228
- F1 Micro: 0.5294
- Accuracy Balanced: 0.5577
- Accuracy: 0.5294
- Precision Macro: 0.6624
- Recall Macro: 0.5577
- Precision Micro: 0.5294
- Recall Micro: 0.5294

## 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: 9e-06
- train_batch_size: 4
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step  | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
| 0.2319        | 1.0   | 27331 | 0.6148          | 0.7746   | 0.7904   | 0.7810            | 0.7904   | 0.7704          | 0.7810       | 0.7904          | 0.7904       |
| 0.1646        | 2.0   | 54662 | 0.6324          | 0.7822   | 0.7999   | 0.7847            | 0.7999   | 0.7800          | 0.7847       | 0.7999          | 0.7999       |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2