metadata
library_name: transformers
license: apache-2.0
base_model: google/muril-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: results
results: []
results
This model is a fine-tuned version of google/muril-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8564
- Accuracy: 0.8761
- F1: 0.8755
- Precision: 0.8892
- Recall: 0.8761
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: 8
- eval_batch_size: 8
- seed: 42
- 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
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.3029 | 1.0 | 339 | 1.1999 | 0.5634 | 0.4575 | 0.4881 | 0.5634 |
| 1.0073 | 2.0 | 678 | 0.9380 | 0.7168 | 0.6836 | 0.7627 | 0.7168 |
| 0.8519 | 3.0 | 1017 | 0.8564 | 0.8761 | 0.8755 | 0.8892 | 0.8761 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.7.1+cpu
- Datasets 4.2.0
- Tokenizers 0.22.1