metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: Qwen/Qwen1.5-0.5B
model-index:
- name: Qwen1.5-0.5B-finetuned-medmcqa
results: []
Qwen1.5-0.5B-finetuned-medmcqa
This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the None 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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 20
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
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: False
- bnb_4bit_compute_dtype: float16
- load_in_4bit: True
- load_in_8bit: False
Framework versions
- PEFT 0.6.2