metadata
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B
tags:
- generated_from_trainer
model-index:
- name: llama_sequence_classification
results: []
llama_sequence_classification
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2783
- Pearson: 0.9687
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: 32
- eval_batch_size: 8
- seed: 42
- 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 | Pearson |
|---|---|---|---|---|
| No log | 1.0 | 206 | 0.2751 | 0.9458 |
| No log | 2.0 | 412 | 0.1997 | 0.9697 |
| 0.3269 | 3.0 | 618 | 0.2197 | 0.9539 |
| 0.3269 | 4.0 | 824 | 0.2830 | 0.9597 |
| 0.0393 | 5.0 | 1030 | 0.2783 | 0.9687 |
Framework versions
- PEFT 0.14.0
- Transformers 4.45.2
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.2.0
- Tokenizers 0.20.3