# Load model directly
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("h3110Fr13nd/guj-eng-code-switch-bert-multilingual")
model = AutoModelForTokenClassification.from_pretrained("h3110Fr13nd/guj-eng-code-switch-bert-multilingual")Quick Links
guj-eng-code-switch-bert-multilingual
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1520
- Precision: 0.8581
- Recall: 0.8478
- F1: 0.8529
- Accuracy: 0.9608
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2148 | 1.0 | 250 | 0.2214 | 0.8414 | 0.7840 | 0.8116 | 0.9432 |
| 0.1215 | 2.0 | 500 | 0.1550 | 0.8324 | 0.8250 | 0.8287 | 0.9560 |
| 0.0873 | 3.0 | 750 | 0.1520 | 0.8581 | 0.8478 | 0.8529 | 0.9608 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- -
Model tree for h3110Fr13nd/guj-eng-code-switch-bert-multilingual
Base model
google-bert/bert-base-multilingual-cased
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="h3110Fr13nd/guj-eng-code-switch-bert-multilingual")