metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- f1
- precision
- recall
model-index:
- name: modernBERT-base-multilingual-sentiment
results: []
modernBERT-base-multilingual-sentiment
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5464
- F1: 0.7944
- Precision: 0.7945
- Recall: 0.7944
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: 512
- eval_batch_size: 512
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 2048
- total_eval_batch_size: 1024
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|---|---|---|---|---|---|---|
| 0.9287 | 1.0 | 1537 | 0.4626 | 0.7910 | 0.7940 | 0.7897 |
| 0.8356 | 2.0 | 3074 | 0.4441 | 0.8011 | 0.8009 | 0.8015 |
| 0.7488 | 3.0 | 4611 | 0.4517 | 0.8012 | 0.8020 | 0.8007 |
| 0.6177 | 4.0 | 6148 | 0.4915 | 0.7990 | 0.7989 | 0.7991 |
| 0.5174 | 5.0 | 7685 | 0.5464 | 0.7944 | 0.7945 | 0.7944 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0