silmi224/led-risalah_data_v16

1---2base_model: silmi224/finetune-led-350003tags:4- summarization5- generated_from_trainer6model-index:7- name: led-risalah_data_v168  results: []9---10 11<!-- This model card has been generated automatically according to the information the Trainer had access to. You12should probably proofread and complete it, then remove this comment. -->13 14# led-risalah_data_v1615 16This model is a fine-tuned version of [silmi224/finetune-led-35000](https://huggingface.co/silmi224/finetune-led-35000) on an unknown dataset.17It achieves the following results on the evaluation set:18- eval_loss: 2.115619- eval_rouge1_precision: 0.614720- eval_rouge1_recall: 0.156321- eval_rouge1_fmeasure: 0.248922- eval_runtime: 105.766823- eval_samples_per_second: 0.09524- eval_steps_per_second: 0.09525- epoch: 26.3526- step: 52727 28## Model description29 30More information needed31 32## Intended uses & limitations33 34More information needed35 36## Training and evaluation data37 38More information needed39 40## Training procedure41 42### Training hyperparameters43 44The following hyperparameters were used during training:45- learning_rate: 5.6e-0546- train_batch_size: 147- eval_batch_size: 148- seed: 4249- gradient_accumulation_steps: 450- total_train_batch_size: 451- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0852- lr_scheduler_type: linear53- lr_scheduler_warmup_steps: 60054- num_epochs: 3055- mixed_precision_training: Native AMP56 57### Framework versions58 59- Transformers 4.41.260- Pytorch 2.1.261- Datasets 2.19.262- Tokenizers 0.19.163