<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
codellama-13b-personal-copilot-peft
This model is a fine-tuned version of codellama/CodeLlama-13b-Instruct-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6761
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7952 | 0.2 | 5 | 0.8392 |
| 0.7192 | 0.4 | 10 | 0.7788 |
| 0.6881 | 0.6 | 15 | 0.7029 |
| 0.6169 | 0.8 | 20 | 0.6809 |
| 0.5108 | 1.0 | 25 | 0.6761 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.6.0.dev0
