End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: Akashpb13/Swahili_xlsr
+base_model: GodsonNtungi/asr2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,15 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # asr2
 
-This model is a fine-tuned version of [Akashpb13/Swahili_xlsr](https://huggingface.co/Akashpb13/Swahili_xlsr) on the None dataset.
+This model is a fine-tuned version of [GodsonNtungi/asr2](https://huggingface.co/GodsonNtungi/asr2) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2807
-- eval_wer: 0.3257
-- eval_runtime: 10.1611
-- eval_samples_per_second: 19.683
-- eval_steps_per_second: 2.46
-- epoch: 0.32
-- step: 200
+- eval_loss: 0.2567
+- eval_wer: 0.2528
+- eval_runtime: 6.694
+- eval_samples_per_second: 20.914
+- eval_steps_per_second: 2.689
+- epoch: 3.23
+- step: 700
 
 ## Model description
 
@@ -41,20 +41,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 16
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- 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: 100
-- training_steps: 4000
+- training_steps: 1500
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.36.0.dev0
+- Transformers 4.35.0
 - Pytorch 2.0.1
-- Datasets 2.14.6
+- Datasets 1.18.3
 - Tokenizers 0.14.1