metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: ec-biogpt-noised-pubmed-match-v1
results: []
ec-biogpt-noised-pubmed-match-v1
This model is a fine-tuned version of microsoft/biogpt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3325
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3677 | 0.72 | 500 | 1.3193 |
| 1.078 | 1.43 | 1000 | 1.2750 |
| 0.8879 | 2.15 | 1500 | 1.2838 |
| 0.9581 | 2.87 | 2000 | 1.2663 |
| 0.8084 | 3.59 | 2500 | 1.3051 |
| 0.7004 | 4.3 | 3000 | 1.3325 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3