| tags: | |
| - generated_from_trainer | |
| datasets: | |
| - fleurs | |
| metrics: | |
| - wer | |
| model-index: | |
| - name: experiment | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # experiment | |
| This model is a fine-tuned version of [](https://huggingface.co/) on the fleurs dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 7.9280 | |
| - Cer: 1.0 | |
| - Wer: 1.0 | |
| - Mer: 1.0 | |
| - Wil: 1 | |
| - Wip: 0 | |
| - Hits: 0 | |
| - Substitutions: 0 | |
| - Deletions: 34 | |
| - Insertions: 0 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 0.0001 | |
| - train_batch_size: 2 | |
| - eval_batch_size: 1 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - training_steps: 10 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions | | |
| |:-------------:|:-----:|:----:|:---------------:|:---:|:---:|:---:|:---:|:---:|:----:|:-------------:|:---------:|:----------:| | |
| | 8.0922 | 0.0 | 4 | 7.9783 | 1.0 | 1.0 | 1.0 | 1 | 0 | 0 | 0 | 34 | 0 | | |
| | 7.9733 | 0.01 | 8 | 7.9280 | 1.0 | 1.0 | 1.0 | 1 | 0 | 0 | 0 | 34 | 0 | | |
| ### Framework versions | |
| - Transformers 4.39.3 | |
| - Pytorch 2.1.0 | |
| - Datasets 2.18.0 | |
| - Tokenizers 0.15.2 | |
| ### Wandb run | |
| https://wandb.ai/alexander-polok/huggingface/runs/imoe89wk |