Model save

README.md

@@ -14,6 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-xlsr-georgian-demo
 
 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.1430
+- eval_wer: 0.2912
+- eval_runtime: 1147.4753
+- eval_samples_per_second: 10.181
+- eval_steps_per_second: 0.637
+- epoch: 20.39
+- step: 37200
 
 ## Model description
 
@@ -32,14 +40,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.003
-- train_batch_size: 32
+- learning_rate: 5e-05
+- train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 200
-- num_epochs: 10
+- num_epochs: 22
 
 ### Framework versions