metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
- name: LLAMA3-8BI-APPS
results: []
datasets:
- codeparrot/apps
metrics:
- accuracy
- bleu
- rouge
pipeline_tag: text-generation
LLAMA3-8BI-APPS
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1490
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9027 | 0.1 | 100 | 0.9320 |
| 0.8632 | 0.2 | 200 | 0.9143 |
| 0.8572 | 0.3 | 300 | 1.0150 |
| 0.937 | 0.4 | 400 | 1.0545 |
| 1.0336 | 0.5 | 500 | 1.1029 |
| 1.0056 | 0.6 | 600 | 1.1267 |
| 1.0125 | 0.7 | 700 | 1.1307 |
| 1.028 | 0.8 | 800 | 1.1398 |
| 1.0692 | 0.9 | 900 | 1.1482 |
| 1.0361 | 1.0 | 1000 | 1.1490 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2