metadata

license: other
base_model: meta-llama/Meta-Llama-3-70B
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: C013_Meta-Llama-3-70B_instruct_20240512_233548
    results: []

C013_Meta-Llama-3-70B_instruct_20240512_233548

This model is a fine-tuned version of ./dataset/dataset_model_sequence/C013_Meta-Llama-3-70B_pretrain on the curated_instructions_3k 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: 3e-06
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 32
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
lr_scheduler_warmup_ratio: 0.075
num_epochs: 1.0
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.40.2
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1