metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Bangla_multiclass_sentiment_analysis_model
results: []
Bangla_multiclass_sentiment_analysis_model
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2648
- F1: 0.9309
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 0.26 | 200 | 0.5353 | 0.7972 |
| No log | 0.51 | 400 | 0.3261 | 0.8800 |
| 0.5223 | 0.77 | 600 | 0.3222 | 0.8979 |
| 0.5223 | 1.03 | 800 | 0.2646 | 0.9170 |
| 0.2984 | 1.28 | 1000 | 0.2915 | 0.9028 |
| 0.2984 | 1.54 | 1200 | 0.2432 | 0.9234 |
| 0.2984 | 1.8 | 1400 | 0.2504 | 0.9209 |
| 0.2514 | 2.05 | 1600 | 0.2341 | 0.9246 |
| 0.2514 | 2.31 | 1800 | 0.2714 | 0.9237 |
| 0.1895 | 2.57 | 2000 | 0.2537 | 0.9269 |
| 0.1895 | 2.82 | 2200 | 0.2648 | 0.9309 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1