chansung's picture
End of training
e0ac0b4 verified
metadata
base_model: meta-llama/Meta-Llama-3-8B
datasets:
  - llama-duo/synth_coding_dataset_dedup
library_name: peft
license: llama3
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama3-8b-coding-gpt4o-100k
    results: []

llama3-8b-coding-gpt4o-100k

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the llama-duo/synth_coding_dataset_dedup dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5174

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: 0.002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 128
  • total_eval_batch_size: 64
  • 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
0.4861 1.0 135 1.2495
0.458 2.0 270 1.2390
0.4423 3.0 405 1.2549
0.4244 4.0 540 1.2665
0.4051 5.0 675 1.2714
0.3815 6.0 810 1.2959
0.3546 7.0 945 1.3560
0.3233 8.0 1080 1.4125
0.2969 9.0 1215 1.4809
0.2818 10.0 1350 1.5174

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.2.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1