metadata
base_model: meta-llama/Meta-Llama-3-8B
datasets:
- llama-duo/synth_closed_qa_dataset_dedup
library_name: peft
license: llama3
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: llama3.1-8b-closedqa-gpt4o-100k
results: []
llama3.1-8b-closedqa-gpt4o-100k
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the llama-duo/synth_closed_qa_dataset_dedup dataset. It achieves the following results on the evaluation set:
- Loss: 2.1008
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8026 | 1.0 | 256 | 2.0456 |
| 0.7532 | 2.0 | 512 | 2.0313 |
| 0.7198 | 3.0 | 768 | 2.0404 |
| 0.7053 | 4.0 | 1024 | 2.0419 |
| 0.6831 | 5.0 | 1280 | 2.0541 |
| 0.6633 | 6.0 | 1536 | 2.0744 |
| 0.6595 | 7.0 | 1792 | 2.0814 |
| 0.6374 | 8.0 | 2048 | 2.0939 |
| 0.6277 | 9.0 | 2304 | 2.0994 |
| 0.616 | 10.0 | 2560 | 2.1008 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1