metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: roberta-base
metrics:
- accuracy
model-index:
- name: lora-roberta-base-finetuned-captures
results: []
lora-roberta-base-finetuned-captures
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2959
- Accuracy: 0.9127
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 | Accuracy |
|---|---|---|---|---|
| 0.2353 | 0.9994 | 772 | 0.3571 | 0.9003 |
| 0.228 | 2.0 | 1545 | 0.3288 | 0.9072 |
| 0.2426 | 2.9994 | 2317 | 0.3198 | 0.9092 |
| 0.213 | 4.0 | 3090 | 0.2959 | 0.9127 |
| 0.1172 | 4.9968 | 3860 | 0.2959 | 0.9120 |
Framework versions
- PEFT 0.12.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.0