metadata
library_name: peft
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
model-index:
- name: resilient-zebra-259
results: []
resilient-zebra-259
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7170
- Hamming Loss: 0.5784
- Zero One Loss: 1.0
- Jaccard Score: 0.8944
- Hamming Loss Optimised: 0.1123
- Hamming Loss Threshold: 0.5944
- Zero One Loss Optimised: 1.0
- Zero One Loss Threshold: 0.9000
- Jaccard Score Optimised: 0.8878
- Jaccard Score Threshold: 0.2889
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: 8.695048284400357e-06
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 100 | 0.7232 | 0.5863 | 1.0 | 0.8933 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8878 | 0.2889 |
| No log | 2.0 | 200 | 0.7204 | 0.5821 | 1.0 | 0.8930 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8878 | 0.2889 |
| No log | 3.0 | 300 | 0.7180 | 0.5821 | 1.0 | 0.8943 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8878 | 0.2889 |
| No log | 4.0 | 400 | 0.7170 | 0.5784 | 1.0 | 0.8944 | 0.1123 | 0.5944 | 1.0 | 0.9000 | 0.8878 | 0.2889 |
Framework versions
- PEFT 0.13.2
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0