metadata
base_model: meta-llama/Llama-2-70b-hf
tags:
- generated_from_trainer
model-index:
- name: qlora-llama70-ft-full-dataset
results: []
library_name: peft
qlora-llama70-ft-full-dataset
This model is a fine-tuned version of meta-llama/Llama-2-70b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4237
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
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: float16
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0025
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5952 | 0.16 | 5 | 1.5179 |
| 1.6321 | 0.32 | 10 | 1.5725 |
| 1.511 | 0.48 | 15 | 1.4764 |
| 1.4807 | 0.65 | 20 | 1.4482 |
| 1.439 | 0.81 | 25 | 1.4329 |
| 1.4266 | 0.97 | 30 | 1.4245 |
Framework versions
- PEFT 0.5.0
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.1
- Tokenizers 0.15.0