Sans1807/working

1---2library_name: transformers3base_model: Sans1807/content4tags:5- generated_from_trainer6metrics:7- wer8model-index:9- name: Sans1807/content10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# Sans1807/content17 18This model is a fine-tuned version of [Sans1807/content](https://huggingface.co/Sans1807/content) on an unknown dataset.19It achieves the following results on the evaluation set:20- Loss: 0.094421- Cer: 0.007822- Wer: 0.040623 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: 2e-0542- train_batch_size: 1643- eval_batch_size: 1644- seed: 4245- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0846- lr_scheduler_type: linear47- num_epochs: 2548- mixed_precision_training: Native AMP49 50### Training results51 52| Training Loss | Epoch   | Step | Validation Loss | Cer    | Wer    |53|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|54| 0.0005        | 5.0761  | 1000 | 0.0714          | 0.0119 | 0.0584 |55| 0.0           | 10.1523 | 2000 | 0.0821          | 0.0115 | 0.0533 |56| 0.003         | 15.2284 | 3000 | 0.0877          | 0.0091 | 0.0381 |57| 0.0157        | 20.3046 | 4000 | 0.0944          | 0.0078 | 0.0406 |58 59 60### Framework versions61 62- Transformers 4.44.263- Pytorch 2.4.064- Datasets 2.17.065- Tokenizers 0.19.166