RichardErkhov's picture
uploaded readme
651d462 verified

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3-8b-math-sft-subtask-6 - GGUF

Original model description:

library_name: transformers license: llama3 base_model: Dynosaur/llama3-8b-math-sft tags: - alignment-handbook - trl - sft - generated_from_trainer - trl - sft - generated_from_trainer datasets: - Dynosaur/math-sft-subtask-6 model-index: - name: llama3-8b-math-sft-subtask-6 results: []

llama3-8b-math-sft-subtask-6

This model is a fine-tuned version of Dynosaur/llama3-8b-math-sft on the Dynosaur/math-sft-subtask-6 dataset.

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: 2e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 8
  • 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: 2

Training results

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1