End of training

README.md

@@ -4,8 +4,6 @@ license: cc-by-nc-4.0
 base_model: facebook/mms-1b-all
 tags:
 - generated_from_trainer
-metrics:
-- wer
 model-index:
 - name: wav2vec2-large-mms-1b-ngn-on-bam-colab
   results: []
@@ -17,9 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-mms-1b-ngn-on-bam-colab
 
 This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4665
-- Wer: 0.6688
 
 ## Model description
 
@@ -38,21 +33,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
-- train_batch_size: 8
+- learning_rate: 0.0005
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer    |
-|:-------------:|:------:|:----:|:---------------:|:------:|
-| 10.9406       | 1.2048 | 100  | 1.4665          | 0.6688 |
 
 
 ### Framework versions

adapter.bam.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fad7e10b2d11b6dda268269da66b8e5518ef278ce8aefa547d50a02429966cd
+oid sha256:709c7e0527d51b012c99ed9191ce1eb2ed35bfc56ba50855aa2b5be48e4554b3
 size 8813904