metadata
license: other
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: muggle70b
results: []
muggle70b
This model is a fine-tuned version of /cpfs01/shared/public/lichengpeng.lcp/Llama-2-70b-hf on the muggle 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2