darinchau/checkpoints

1---2license: apache-2.03base_model: darinchau/checkpoints4tags:5- generated_from_trainer6model-index:7- name: checkpoints8  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# checkpoints15 16This model is a fine-tuned version of [darinchau/checkpoints](https://huggingface.co/darinchau/checkpoints) on the None dataset.17It achieves the following results on the evaluation set:18- eval_loss: 0.828919- eval_cer: 79.962220- eval_runtime: 31.645921- eval_samples_per_second: 3.1622- eval_steps_per_second: 0.22123- epoch: 35.1124- step: 330025 26## Model description27 28More information needed29 30## Intended uses & limitations31 32More information needed33 34## Training and evaluation data35 36More information needed37 38## Training procedure39 40### Training hyperparameters41 42The following hyperparameters were used during training:43- learning_rate: 1e-0544- train_batch_size: 1645- eval_batch_size: 1646- seed: 4247- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0848- lr_scheduler_type: linear49- lr_scheduler_warmup_steps: 50050- training_steps: 400051- mixed_precision_training: Native AMP52 53### Framework versions54 55- Transformers 4.36.256- Pytorch 2.1.0+cu12157- Datasets 2.16.158- Tokenizers 0.15.059