metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: debertabase_term_paper
results: []
debertabase_term_paper
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1196
- Precision: 0.9279
- Recall: 0.9363
- F1: 0.9320
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 1.2937 | 1.0 | 789 | 0.1477 | 0.9083 | 0.9224 | 0.9151 |
| 1.2937 | 2.0 | 1578 | 0.1311 | 0.9227 | 0.9322 | 0.9270 |
| 1.2937 | 3.0 | 2367 | 0.1196 | 0.9279 | 0.9363 | 0.9320 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2