|
--- |
|
license: mit |
|
base_model: FacebookAI/roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: roberta_base_scotus |
|
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. --> |
|
|
|
# roberta_base_scotus |
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6119 |
|
- Accuracy: 0.5136 |
|
- F1 Macro: 0.2455 |
|
- F1 Micro: 0.5136 |
|
|
|
## 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: 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 1.9275 | 0.63 | 50 | 1.9154 | 0.41 | 0.1125 | 0.41 | |
|
| 1.5742 | 1.27 | 100 | 1.7447 | 0.4707 | 0.1782 | 0.4707 | |
|
| 1.6563 | 1.9 | 150 | 1.6859 | 0.4786 | 0.2076 | 0.4786 | |
|
| 1.4743 | 2.53 | 200 | 1.6119 | 0.5136 | 0.2455 | 0.5136 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
