metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Llama1B_mrpc
results: []
Llama1B_mrpc
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6757
- Accuracy: 0.8064
- F1: 0.8668
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.6439 | 1.0 | 115 | 0.4702 | 0.7819 | 0.8576 |
| 0.72 | 2.0 | 230 | 0.4350 | 0.8088 | 0.8617 |
| 0.4135 | 3.0 | 345 | 0.7815 | 0.7721 | 0.8215 |
| 0.1995 | 4.0 | 460 | 1.1299 | 0.8186 | 0.8683 |
| 0.1434 | 5.0 | 575 | 1.1574 | 0.8235 | 0.8754 |
| 0.1283 | 6.0 | 690 | 1.4867 | 0.8162 | 0.8687 |
| 0.0243 | 7.0 | 805 | 1.7604 | 0.8113 | 0.8697 |
| 0.0108 | 8.0 | 920 | 1.6907 | 0.8113 | 0.8715 |
| 0.0085 | 9.0 | 1035 | 1.6195 | 0.8088 | 0.8678 |
| 0.0048 | 10.0 | 1150 | 1.6757 | 0.8064 | 0.8668 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0