metadata

library_name: transformers
license: llama3
base_model: Dynosaur/llama3-8b-math-sft
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: llama3-8b-math-sft-full-combine-paraphrase
    results: []

llama3-8b-math-sft-full-combine-paraphrase

This model is a fine-tuned version of Dynosaur/llama3-8b-math-sft on an unknown 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 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0