metadata
library_name: peft
license: other
base_model: /home/yangzongxian/zongxian/Models/MedReason-8b
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: MedReason_PartAll
results: []
MedReason_PartAll
This model is a fine-tuned version of /home/yangzongxian/zongxian/Models/MedReason-8b on the DPO_merged_Stage2_Part1+2 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.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_steps: 10
- num_epochs: 1.0
Training results
Framework versions
- PEFT 0.15.0
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0