--- library_name: transformers tags: - generated_from_trainer model-index: - name: varying-mixture-only-distil-xlstm results: [] --- # varying-mixture-only-distil-xlstm This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. It achieves the following results on the evaluation set: - Loss: 5.2935 ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - 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_ratio: 0.1 - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 28.1059 | 0.32 | 100 | 6.0714 | | 22.6345 | 0.64 | 200 | 5.6656 | | 21.4178 | 0.96 | 300 | 5.4659 | | 20.4576 | 1.2784 | 400 | 5.3975 | | 19.8569 | 1.5984 | 500 | 5.3189 | | 19.6459 | 1.9184 | 600 | 5.2935 | ### Framework versions - Transformers 4.47.1 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.21.0