metadata
library_name: transformers
base_model: meta-llama/Meta-Llama-3-8B
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: context
results: []
context
This model is a fine-tuned version of /juice2/scr2/laya/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7990
- Accuracy: 0.7391
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: 40
- eval_batch_size: 40
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 160
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8185 | 1.0482 | 500 | 1.7990 | 0.7391 |
| 0.2771 | 2.0964 | 1000 | 1.8269 | 0.7485 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1