metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: edos-2023-baseline-albert-base-v2-label_vector
results: []
edos-2023-baseline-albert-base-v2-label_vector
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9419
- F1: 0.4407
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 |
|---|---|---|---|---|
| 2.0868 | 1.18 | 100 | 1.8746 | 0.1134 |
| 1.7943 | 2.35 | 200 | 1.6306 | 0.1988 |
| 1.6172 | 3.53 | 300 | 1.5104 | 0.2631 |
| 1.441 | 4.71 | 400 | 1.3189 | 0.3199 |
| 1.3075 | 5.88 | 500 | 1.1714 | 0.3731 |
| 1.158 | 7.06 | 600 | 1.0743 | 0.4055 |
| 1.0584 | 8.24 | 700 | 0.9954 | 0.4190 |
| 0.9701 | 9.41 | 800 | 0.9419 | 0.4407 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2