kojo-george/model

1---2license: cc-by-nc-4.03base_model: facebook/mms-1b-all4tags:5- generated_from_trainer6model-index:7- name: model8  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# model15 16This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.17It achieves the following results on the evaluation set:18- epoch: 0.15819- eval_loss: 0.404420- eval_runtime: 10.28321- eval_samples_per_second: 9.23922- eval_steps_per_second: 1.16723- eval_wer: 0.361124- step: 158025 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: 0.00144- train_batch_size: 245- eval_batch_size: 846- seed: 4247- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0848- lr_scheduler_type: linear49- lr_scheduler_warmup_steps: 10050- training_steps: 1000051- mixed_precision_training: Native AMP52 53### Framework versions54 55- Transformers 4.42.0.dev056- Pytorch 2.3.0+cu12157- Datasets 2.19.158- Tokenizers 0.19.159