--- base_model: RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init library_name: peft metrics: - accuracy tags: - generated_from_trainer model-index: - name: ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_mlp results: [] --- # ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_mlp This model is a fine-tuned version of [RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init](https://huggingface.co/RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.3347 - Accuracy: 0.5174 ## 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: 0.0003 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - distributed_type: multi-GPU - num_devices: 64 - gradient_accumulation_steps: 2 - total_train_batch_size: 256 - total_eval_batch_size: 128 - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - num_epochs: 1.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:| | No log | 0.0001 | 1 | 5.8817 | 0.3107 | | 2.5328 | 0.1765 | 2000 | 2.3964 | 0.5090 | | 2.488 | 0.3531 | 4000 | 2.3588 | 0.5140 | | 2.459 | 0.5296 | 6000 | 2.3428 | 0.5163 | | 2.455 | 0.7062 | 8000 | 2.3360 | 0.5173 | | 2.4544 | 0.8827 | 10000 | 2.3346 | 0.5174 | ### Framework versions - PEFT 0.9.0 - Transformers 4.45.2 - Pytorch 2.3.0a0+6ddf5cf85e.nv24.04 - Datasets 2.18.0 - Tokenizers 0.20.1