---
library_name: transformers
license: cc-by-nc-4.0
base_model: AIMH/mental-roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: mental-roberta-large-pr
  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. -->

# mental-roberta-large-pr

This model is a fine-tuned version of [AIMH/mental-roberta-large](https://huggingface.co/AIMH/mental-roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3882
- F1 Macro: 0.6298
- Precision: 0.6338
- Recall: 0.6393
- Accuracy: 0.7836

## 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: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision | Recall | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| No log        | 1.0   | 240  | 1.3410          | 0.5133   | 0.5270    | 0.5471 | 0.6894   |
| No log        | 2.0   | 480  | 0.8069          | 0.6099   | 0.5990    | 0.6440 | 0.7445   |
| 1.75          | 3.0   | 720  | 0.7779          | 0.6290   | 0.6333    | 0.6492 | 0.7752   |
| 1.75          | 4.0   | 960  | 0.8297          | 0.6240   | 0.6311    | 0.6390 | 0.7804   |
| 0.6742        | 5.0   | 1200 | 1.0208          | 0.6312   | 0.6295    | 0.6439 | 0.7737   |
| 0.6742        | 6.0   | 1440 | 1.1990          | 0.6294   | 0.6374    | 0.6384 | 0.7804   |
| 0.2441        | 7.0   | 1680 | 1.3882          | 0.6298   | 0.6338    | 0.6393 | 0.7836   |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1