metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
datasets:
- patent-classification
metrics:
- accuracy
base_model: roberta-large
model-index:
- name: roberta-large-flash-attention-2-lora-patent-classification
results: []
roberta-large-flash-attention-2-lora-patent-classification
This model is a fine-tuned version of roberta-large on the patent-classification dataset. It achieves the following results on the evaluation set:
- Loss: 0.8395
- Accuracy: 0.6304
- Precision Macro: 0.6136
- Recall Macro: 0.5995
- F1-score Macro: 0.5984
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: 6
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1-score Macro |
|---|---|---|---|---|---|---|---|
| 0.7566 | 1.0 | 4167 | 0.9131 | 0.5692 | 0.6231 | 0.5423 | 0.5631 |
| 0.6974 | 2.0 | 8334 | 0.8428 | 0.6174 | 0.6169 | 0.5910 | 0.5942 |
| 0.7219 | 3.0 | 12501 | 0.8395 | 0.6304 | 0.6136 | 0.5995 | 0.5984 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0