|
--- |
|
license: other |
|
base_model: google/gemma-2b |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: gemma_2b_patent |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# gemma_2b_patent |
|
|
|
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8299 |
|
- Accuracy: 0.7138 |
|
- F1 Macro: 0.6753 |
|
- F1 Micro: 0.7138 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.4602 | 0.13 | 50 | 1.3969 | 0.5022 | 0.3597 | 0.5022 | |
|
| 1.0803 | 0.26 | 100 | 1.0653 | 0.6256 | 0.5392 | 0.6256 | |
|
| 1.0025 | 0.38 | 150 | 0.9539 | 0.6728 | 0.6122 | 0.6728 | |
|
| 0.9107 | 0.51 | 200 | 0.9216 | 0.6872 | 0.6279 | 0.6872 | |
|
| 0.9144 | 0.64 | 250 | 0.8769 | 0.697 | 0.6581 | 0.697 | |
|
| 0.8844 | 0.77 | 300 | 0.8914 | 0.6924 | 0.6435 | 0.6924 | |
|
| 0.8721 | 0.9 | 350 | 0.8546 | 0.705 | 0.6553 | 0.705 | |
|
| 0.6636 | 1.02 | 400 | 0.8299 | 0.7138 | 0.6753 | 0.7138 | |
|
| 0.5654 | 1.15 | 450 | 0.8772 | 0.7056 | 0.6600 | 0.7056 | |
|
| 0.6037 | 1.28 | 500 | 0.8565 | 0.7082 | 0.6628 | 0.7082 | |
|
| 0.5781 | 1.41 | 550 | 0.8828 | 0.7 | 0.6543 | 0.7 | |
|
| 0.565 | 1.53 | 600 | 0.8785 | 0.703 | 0.6693 | 0.703 | |
|
| 0.6175 | 1.66 | 650 | 0.8799 | 0.7064 | 0.6579 | 0.7064 | |
|
| 0.565 | 1.79 | 700 | 0.8562 | 0.7114 | 0.6582 | 0.7114 | |
|
| 0.5752 | 1.92 | 750 | 0.8662 | 0.7046 | 0.6641 | 0.7046 | |
|
| 0.2302 | 2.05 | 800 | 0.9298 | 0.704 | 0.6587 | 0.704 | |
|
| 0.2034 | 2.17 | 850 | 1.0142 | 0.7 | 0.6601 | 0.7 | |
|
| 0.2071 | 2.3 | 900 | 1.0373 | 0.6912 | 0.6604 | 0.6912 | |
|
| 0.1889 | 2.43 | 950 | 1.0462 | 0.6982 | 0.6593 | 0.6982 | |
|
| 0.1642 | 2.56 | 1000 | 1.0561 | 0.6932 | 0.6577 | 0.6932 | |
|
| 0.1446 | 2.69 | 1050 | 1.0697 | 0.6966 | 0.6621 | 0.6966 | |
|
| 0.1334 | 2.81 | 1100 | 1.0655 | 0.698 | 0.6637 | 0.698 | |
|
| 0.1266 | 2.94 | 1150 | 1.0705 | 0.696 | 0.6625 | 0.696 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
