|
--- |
|
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: 0.6579 |
|
- Precision: 0.6594 |
|
- Recall: 0.6579 |
|
- F1: 0.6534 |
|
- Loss: 0.8215 |
|
|
|
## 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 | 13 | 0.5463 | 0.5179 | 0.5463 | 0.4339 | 1.0286 | |
|
| No log | 2.0 | 26 | 0.4100 | 0.1876 | 0.4100 | 0.2461 | 1.0251 | |
|
| No log | 3.0 | 39 | 0.5086 | 0.6698 | 0.5086 | 0.4356 | 0.8710 | |
|
| No log | 4.0 | 52 | 0.4802 | 0.6966 | 0.4802 | 0.3729 | 1.3227 | |
|
| No log | 5.0 | 65 | 0.4691 | 0.7161 | 0.4691 | 0.3548 | 1.0735 | |
|
| No log | 6.0 | 78 | 0.5927 | 0.6874 | 0.5927 | 0.5628 | 0.8102 | |
|
| No log | 7.0 | 91 | 0.5402 | 0.7032 | 0.5402 | 0.4823 | 1.3396 | |
|
| No log | 8.0 | 104 | 0.6661 | 0.6753 | 0.6661 | 0.6340 | 0.7542 | |
|
| No log | 9.0 | 117 | 0.6234 | 0.6935 | 0.6234 | 0.6047 | 0.8814 | |
|
| No log | 10.0 | 130 | 0.6633 | 0.6732 | 0.6633 | 0.6574 | 0.7494 | |
|
| No log | 11.0 | 143 | 0.6567 | 0.6597 | 0.6567 | 0.6520 | 0.7748 | |
|
| No log | 12.0 | 156 | 0.6606 | 0.6596 | 0.6606 | 0.6552 | 0.7600 | |
|
| No log | 13.0 | 169 | 0.6624 | 0.6744 | 0.6624 | 0.6567 | 0.7976 | |
|
| No log | 14.0 | 182 | 0.6667 | 0.6668 | 0.6667 | 0.6619 | 0.7685 | |
|
| No log | 15.0 | 195 | 0.6452 | 0.6778 | 0.6452 | 0.6361 | 0.8573 | |
|
| No log | 16.0 | 208 | 0.6536 | 0.6721 | 0.6536 | 0.6466 | 0.8498 | |
|
| No log | 17.0 | 221 | 0.6545 | 0.6625 | 0.6545 | 0.6501 | 0.8457 | |
|
| No log | 18.0 | 234 | 0.6570 | 0.6602 | 0.6570 | 0.6523 | 0.8187 | |
|
| No log | 18.48 | 240 | 0.6579 | 0.6594 | 0.6579 | 0.6534 | 0.8215 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.2 |
|
- Pytorch 2.5.1+cu124 |
|
- Tokenizers 0.21.0 |
|
|
