metadata
license: llama2
base_model: codellama/CodeLlama-7b-Instruct-hf
tags:
- generated_from_trainer
model-index:
- name: codellama-7b-sft-lora-func-names
results: []
codellama-7b-sft-lora-func-names
This model is a fine-tuned version of codellama/CodeLlama-7b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7084
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: 4e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 900
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7541 | 0.01 | 180 | 0.7222 |
| 0.7126 | 0.01 | 360 | 0.7118 |
| 0.7342 | 0.02 | 540 | 0.7100 |
| 0.7216 | 0.03 | 720 | 0.7083 |
| 0.7171 | 0.04 | 900 | 0.7084 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1