metadata
library_name: transformers
base_model: tbs17/MathBERT
tags:
- generated_from_trainer
model-index:
- name: tbs17-MathBERT-Math-Classifier
results: []
tbs17-MathBERT-Math-Classifier
This model is a fine-tuned version of tbs17/MathBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9498
- Micro F1: 0.8411
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 8
- total_eval_batch_size: 8
- 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: 8
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Micro F1 |
|---|---|---|---|---|
| 1.2886 | 1.0 | 1083 | 0.8944 | 0.8051 |
| 0.8314 | 2.0 | 2166 | 0.8812 | 0.8182 |
| 0.6888 | 3.0 | 3249 | 0.8701 | 0.8411 |
| 0.5976 | 4.0 | 4332 | 0.9158 | 0.8352 |
| 0.5409 | 5.0 | 5415 | 0.9440 | 0.8332 |
| 0.5081 | 6.0 | 6498 | 0.9423 | 0.8424 |
| 0.4912 | 7.0 | 7581 | 0.9543 | 0.8417 |
| 0.4855 | 8.0 | 8664 | 0.9498 | 0.8411 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0