metadata
license: mit
base_model: microsoft/biogpt
tags:
- generated_from_trainer
model-index:
- name: BioGPT_DocBot_SonatafyAI_V1
results: []
BioGPT_DocBot_SonatafyAI_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: 2.8762
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1291 | 1.0 | 1109 | 2.9973 |
| 2.8675 | 2.0 | 2218 | 2.9057 |
| 2.7264 | 3.0 | 3327 | 2.8822 |
| 2.6095 | 4.0 | 4436 | 2.8706 |
| 2.548 | 5.0 | 5545 | 2.8762 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1