leftfield7/bert-tiny-llm-router

1---2library_name: transformers3license: mit4base_model: prajjwal1/bert-tiny5tags:6- generated_from_trainer7metrics:8- f19model-index:10- name: bert-tiny-llm-router11  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# bert-tiny-llm-router18 19This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.20It achieves the following results on the evaluation set:21- Loss: 0.411222- F1: 0.900323 24## Model description25 26More information needed27 28## Intended uses & limitations29 30More information needed31 32## Training and evaluation data33 34More information needed35 36## Training procedure37 38### Training hyperparameters39 40The following hyperparameters were used during training:41- learning_rate: 5e-0542- train_batch_size: 243- eval_batch_size: 244- seed: 4245- gradient_accumulation_steps: 1646- total_train_batch_size: 3247- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments48- lr_scheduler_type: linear49- lr_scheduler_warmup_ratio: 0.150- num_epochs: 551 52### Training results53 54| Training Loss | Epoch | Step | Validation Loss | F1     |55|:-------------:|:-----:|:----:|:---------------:|:------:|56| 0.6131        | 1.0   | 479  | 0.6153          | 0.5854 |57| 0.5293        | 2.0   | 958  | 0.5049          | 0.8647 |58| 0.4771        | 3.0   | 1437 | 0.4485          | 0.8902 |59| 0.4546        | 4.0   | 1916 | 0.4198          | 0.8980 |60| 0.4545        | 5.0   | 2395 | 0.4112          | 0.9003 |61 62 63### Framework versions64 65- Transformers 4.52.466- Pytorch 2.7.167- Datasets 3.6.068- Tokenizers 0.21.169