update model card README.md

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- common_voice
+model-index:
+- name: ''
+  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. -->
+
+# 
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9769
+- Wer: 0.9989
+
+## 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: 7.5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 50.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 4.4431        | 19.98 | 500  | 4.1441          | 1.0    |
+| 3.0399        | 39.98 | 1000 | 2.9769          | 0.9989 |
+
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- Pytorch 1.10.2+cu102
+- Datasets 1.18.2.dev0
+- Tokenizers 0.11.0

nohup.out

@@ -622,3 +622,16 @@ Saving model checkpoint to ./
 Configuration saved in ./config.json
 Model weights saved in ./pytorch_model.bin
 Configuration saved in ./preprocessor_config.json
+{'eval_loss': 2.9768528938293457, 'eval_wer': 0.9988929889298893, 'eval_runtime': 12.8843, 'eval_samples_per_second': 26.466, 'eval_steps_per_second': 3.337, 'epoch': 39.98}
+{'loss': 2.9893, 'learning_rate': 4.1175e-05, 'epoch': 43.98}
+{'loss': 2.953, 'learning_rate': 4.4924999999999994e-05, 'epoch': 47.98}
+{'train_runtime': 2084.0288, 'train_samples_per_second': 19.434, 'train_steps_per_second': 0.6, 'train_loss': 5.6772947265625, 'epoch': 49.98}
+
+   afc8494..4e1557d  main -> main
+
+02/02/2022 18:41:36 - WARNING - huggingface_hub.repository - To https://huggingface.co/HarrisDePerceptron/xls-r-300m-ur
+   afc8494..4e1557d  main -> main
+
+
+Dropping the following result as it does not have all the necessary fields:
+{'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'ur'}}