---
library_name: transformers
base_model: MiMe-MeMo/MeMo-BERT-03
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: memo3_indirect_speech
  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. -->

# memo3_indirect_speech

This model is a fine-tuned version of [MiMe-MeMo/MeMo-BERT-03](https://huggingface.co/MiMe-MeMo/MeMo-BERT-03) on an unknown dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.6840
- Precision: 0.7036
- Recall: 0.6840
- F1: 0.6798
- Loss: 0.7225

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Accuracy | Precision | Recall | F1     | Validation Loss |
|:-------------:|:-------:|:----:|:--------:|:---------:|:------:|:------:|:---------------:|
| No log        | 1.0     | 9    | 0.3820   | 0.1459    | 0.3820 | 0.2112 | 1.3936          |
| No log        | 2.0     | 18   | 0.3820   | 0.1459    | 0.3820 | 0.2112 | 1.5289          |
| No log        | 3.0     | 27   | 0.5385   | 0.2900    | 0.5385 | 0.3770 | 1.0207          |
| No log        | 4.0     | 36   | 0.3820   | 0.1459    | 0.3820 | 0.2112 | 1.3341          |
| No log        | 5.0     | 45   | 0.5385   | 0.2900    | 0.5385 | 0.3770 | 1.0219          |
| No log        | 6.0     | 54   | 0.3829   | 0.1825    | 0.3829 | 0.2130 | 1.0394          |
| No log        | 7.0     | 63   | 0.6020   | 0.5949    | 0.6020 | 0.5650 | 0.8312          |
| No log        | 8.0     | 72   | 0.6250   | 0.6270    | 0.6250 | 0.5846 | 0.8301          |
| No log        | 9.0     | 81   | 0.6821   | 0.7037    | 0.6821 | 0.6491 | 0.7462          |
| No log        | 10.0    | 90   | 0.5620   | 0.6878    | 0.5620 | 0.5268 | 0.8255          |
| No log        | 11.0    | 99   | 0.5968   | 0.6945    | 0.5968 | 0.5751 | 0.7890          |
| No log        | 12.0    | 108  | 0.6901   | 0.6877    | 0.6901 | 0.6868 | 0.7190          |
| No log        | 13.0    | 117  | 0.6020   | 0.7003    | 0.6020 | 0.5805 | 0.8426          |
| No log        | 14.0    | 126  | 0.6932   | 0.6919    | 0.6932 | 0.6899 | 0.7213          |
| No log        | 15.0    | 135  | 0.7158   | 0.7300    | 0.7158 | 0.6928 | 0.7416          |
| No log        | 16.0    | 144  | 0.6503   | 0.7054    | 0.6503 | 0.6417 | 0.7546          |
| No log        | 17.0    | 153  | 0.7031   | 0.7104    | 0.7031 | 0.6993 | 0.6824          |
| No log        | 17.8235 | 160  | 0.6840   | 0.7036    | 0.6840 | 0.6798 | 0.7225          |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Tokenizers 0.21.0