metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ModernBERT-large-hinglish-binary
results: []
ModernBERT-large-hinglish-binary
This model is a fine-tuned version of answerdotai/ModernBERT-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6142
- Accuracy: 0.6747
- Precision: 0.6564
- Recall: 0.5824
- F1: 0.5687
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: 32
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.622 | 1.0 | 26 | 0.6508 | 0.6349 | 0.5900 | 0.5758 | 0.5758 |
| 2.5166 | 2.0 | 52 | 0.6293 | 0.6703 | 0.7476 | 0.5500 | 0.4956 |
| 2.5527 | 3.0 | 78 | 0.6549 | 0.6022 | 0.6064 | 0.6150 | 0.5961 |
| 2.3672 | 4.0 | 104 | 0.5995 | 0.6975 | 0.7001 | 0.6087 | 0.6017 |
| 1.9234 | 5.0 | 130 | 0.6055 | 0.6839 | 0.6574 | 0.6564 | 0.6569 |
| 0.9818 | 6.0 | 156 | 0.8319 | 0.6676 | 0.6434 | 0.6468 | 0.6448 |
| 0.3056 | 7.0 | 182 | 0.9884 | 0.6730 | 0.6484 | 0.6511 | 0.6495 |
| 0.0518 | 8.0 | 208 | 1.2367 | 0.6730 | 0.6492 | 0.6527 | 0.6506 |
| 0.0083 | 9.0 | 234 | 1.2961 | 0.6839 | 0.6586 | 0.6596 | 0.6591 |
| 0.0023 | 9.6214 | 250 | 1.3402 | 0.6948 | 0.6664 | 0.6471 | 0.6518 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0