metadata
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- generated_from_trainer
model-index:
- name: MSc_llama3_finetuned_model_secondData
results: []
library_name: peft
MSc_llama3_finetuned_model_secondData
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7124
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 250
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8363 | 1.36 | 10 | 3.5698 |
| 3.2454 | 2.71 | 20 | 2.7356 |
| 2.2867 | 4.07 | 30 | 1.7205 |
| 1.4623 | 5.42 | 40 | 1.2840 |
| 1.1723 | 6.78 | 50 | 1.0982 |
| 1.0295 | 8.14 | 60 | 0.9766 |
| 0.9085 | 9.49 | 70 | 0.8723 |
| 0.784 | 10.85 | 80 | 0.7651 |
| 0.717 | 12.2 | 90 | 0.7394 |
| 0.6745 | 13.56 | 100 | 0.7235 |
| 0.6402 | 14.92 | 110 | 0.7157 |
| 0.6251 | 16.27 | 120 | 0.7089 |
| 0.5961 | 17.63 | 130 | 0.7100 |
| 0.5871 | 18.98 | 140 | 0.7042 |
| 0.5714 | 20.34 | 150 | 0.7070 |
| 0.5582 | 21.69 | 160 | 0.7062 |
| 0.5457 | 23.05 | 170 | 0.7076 |
| 0.5392 | 24.41 | 180 | 0.7094 |
| 0.5354 | 25.76 | 190 | 0.7100 |
| 0.5278 | 27.12 | 200 | 0.7105 |
| 0.5275 | 28.47 | 210 | 0.7110 |
| 0.5249 | 29.83 | 220 | 0.7123 |
| 0.5204 | 31.19 | 230 | 0.7123 |
| 0.5198 | 32.54 | 240 | 0.7123 |
| 0.5195 | 33.9 | 250 | 0.7124 |
Framework versions
- PEFT 0.4.0
- Transformers 4.38.2
- Pytorch 2.4.0+cu121
- Datasets 2.13.1
- Tokenizers 0.15.2