metadata
library_name: transformers
license: other
base_model: Lorry0727/CodeLlama-7B-evol
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: CodeLlama-7B-safetycot_v2
results: []
CodeLlama-7B-safetycot-2025-03-14-15-00
This model is a fine-tuned version of Lorry0727/CodeLlama-7B-evol on the sft_COT_safecoder_v4 and the sft_COT_safecoder_v4_autocomplete datasets.
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: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3