metadata
library_name: peft
license: agpl-3.0
base_model: RonTon05/model_content_V2_test
tags:
- lora
metrics:
- accuracy
- f1
model-index:
- name: multi_task_model_content
results: []
multi_task_model_content
This model is a fine-tuned version of RonTon05/model_content_V2_test on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7753
- Accuracy: 0.4753
- F1: 0.5099
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.0293 | 1.0 | 330 | 1.9741 | 0.2832 | 0.1707 |
| 1.9647 | 2.0 | 660 | 1.9200 | 0.3949 | 0.2933 |
| 1.9221 | 3.0 | 990 | 1.8736 | 0.4171 | 0.3336 |
| 1.8875 | 4.0 | 1320 | 1.8436 | 0.4211 | 0.3419 |
| 1.8633 | 5.0 | 1650 | 1.8225 | 0.4380 | 0.3739 |
| 1.8451 | 6.0 | 1980 | 1.8029 | 0.4596 | 0.4718 |
| 1.8321 | 7.0 | 2310 | 1.7910 | 0.4717 | 0.5035 |
| 1.8214 | 8.0 | 2640 | 1.7819 | 0.4710 | 0.4954 |
| 1.8139 | 9.0 | 2970 | 1.7764 | 0.4744 | 0.5062 |
| 1.8101 | 10.0 | 3300 | 1.7753 | 0.4753 | 0.5099 |
Framework versions
- PEFT 0.16.0
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.22.1