metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: edos-2023-baseline-microsoft-deberta-v3-base-label_vector
results: []
edos-2023-baseline-microsoft-deberta-v3-base-label_vector
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8266
- F1: 0.4620
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 2.1548 | 1.18 | 100 | 1.9373 | 0.1031 |
| 1.8405 | 2.35 | 200 | 1.6535 | 0.1315 |
| 1.6221 | 3.53 | 300 | 1.4279 | 0.2601 |
| 1.4091 | 4.71 | 400 | 1.2069 | 0.3527 |
| 1.2815 | 5.88 | 500 | 1.0597 | 0.3904 |
| 1.1345 | 7.06 | 600 | 0.9616 | 0.4186 |
| 1.0509 | 8.24 | 700 | 0.8848 | 0.4423 |
| 0.9696 | 9.41 | 800 | 0.8266 | 0.4620 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2