metadata
base_model: meta-llama/Meta-Llama-3.1-8B
datasets:
- llama-duo/synth_coding_dataset_dedup
library_name: peft
license: llama3.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: llama3.1-8b-coding-gpt4o-100k
results: []
llama3.1-8b-coding-gpt4o-100k
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the llama-duo/synth_coding_dataset_dedup dataset. It achieves the following results on the evaluation set:
- Loss: 1.3444
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: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 8
- 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 |
|---|---|---|---|
| 0.741 | 1.0 | 525 | 1.3567 |
| 0.7109 | 2.0 | 1050 | 1.3158 |
| 0.7026 | 3.0 | 1575 | 1.3116 |
| 0.6682 | 4.0 | 2100 | 1.3090 |
| 0.6825 | 5.0 | 2625 | 1.3126 |
| 0.6429 | 6.0 | 3150 | 1.3228 |
| 0.6334 | 7.0 | 3675 | 1.3276 |
| 0.6257 | 8.0 | 4200 | 1.3404 |
| 0.6314 | 9.0 | 4725 | 1.3410 |
| 0.6205 | 10.0 | 5250 | 1.3444 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1