End of training

README.md

@@ -1,7 +1,7 @@
 ---
+base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
 tags:
 - generated_from_trainer
-base_model: batoula187/wav2vec2-large-xls-r-300m-arabic-colab
 datasets:
 - common_voice_12_0
 model-index:
@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [batoula187/wav2vec2-large-xls-r-300m-arabic-colab](https://huggingface.co/batoula187/wav2vec2-large-xls-r-300m-arabic-colab) on the common_voice_12_0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.2731
-- eval_wer: 0.5959
-- eval_runtime: 94.2795
-- eval_samples_per_second: 16.6
-- eval_steps_per_second: 2.079
-- epoch: 19.6226
-- step: 2600
+- eval_loss: 1.3782
+- eval_wer: 0.6346
+- eval_runtime: 98.1821
+- eval_samples_per_second: 15.94
+- eval_steps_per_second: 1.996
+- epoch: 19.2817
+- step: 3400
 
 ## Model description
 
@@ -42,11 +42,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.41.0
+- Transformers 4.41.1
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887e74e5f3c00e1a6d24e902ffad4b42f033bc147221ecd6e51eec7f8868ff1c
+oid sha256:0c88176fce91b55bf56627a15c05b3da98ce92f1a0cf40850590766aea08f095
 size 1262180580