Aup Fullft Kto W1 Mmd W1lam8.4e 4 Mmdrho8.4e 4 Kr0.1 Seed2

--- library_name: transformers license: other base_model: EleutherAI/pythia-1.4b tags: - llama-factory - full - generated_from_trainer model-index: - name: fullft_kto_w1_mmd_w1lam8.4e-4_mmdrho8.4e-4_kr0.1_seed2 results: [] --- # fullft_kto_w1_mmd_w1lam8.4e-4_mmdrho8.4e-4_kr0.1_seed2 This model is a fine-tuned version of [EleutherAI/pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) on the uf_label_pool_kto 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-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 2 - gradient_accumulation_steps: 8 - total_train_batch_size: 64 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100 - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.57.1 - Pytorch 2.12.1+cu130 - Datasets 4.0.0 - Tokenizers 0.22.2