metadata
license: llama3
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
metrics:
- accuracy
- precision
- recall
model-index:
- name: Llama3_less_data_SUDTT
results: []
Llama3_less_data_SUDTT
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6004
- Accuracy: 0.73
- Precision: 0.7379
- Recall: 0.7133
- F1 score: 0.7254
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: 16
- 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 | Accuracy | F1 score | Precision | Recall | Validation Loss |
|---|---|---|---|---|---|---|---|
| 0.8437 | 1.0 | 200 | 0.6533 | 0.6 | 0.7091 | 0.52 | 0.7820 |
| 0.5333 | 2.0 | 400 | 0.7167 | 0.6953 | 0.7519 | 0.6467 | 0.6752 |
| 0.3644 | 3.0 | 600 | 0.6933 | 0.6892 | 0.6986 | 0.68 | 0.6142 |
| 0.2368 | 4.0 | 800 | 0.6314 | 0.7333 | 0.8070 | 0.6133 | 0.6970 |
| 0.1521 | 5.0 | 1000 | 0.6004 | 0.73 | 0.7379 | 0.7133 | 0.7254 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1