End of training

README.md

@@ -4,6 +4,8 @@ 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: []
@@ -15,6 +17,9 @@ 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: 1.0502
+- Wer: 0.65
 
 ## Model description
 
@@ -37,16 +42,19 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- 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: cosine
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 4
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Wer  |
+|:-------------:|:------:|:----:|:---------------:|:----:|
+| 5.8957        | 9.0952 | 100  | 1.0502          | 0.65 |
 
 
 ### Framework versions

adapter.bam.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112505b001809d887d445f175e602cafc0be6243a8249f24ac52e7b3ad4371cd
+oid sha256:bf345f6f3de304d0ce085f8d63c848b6772698af15a3d01eb8e50415402f2d8e
 size 8813904