End of training

README.md

@@ -16,6 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 # Wav2Vec2 - Gopika
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Konnakol dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: -1.9491
+- eval_wer: 0.3542
+- eval_cer: 0.2777
+- eval_runtime: 4.1162
+- eval_samples_per_second: 5.588
+- eval_steps_per_second: 0.729
+- epoch: 16.6667
+- step: 100
 
 ## Model description
 
@@ -34,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -42,14 +51,10 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 30
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 300
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.41.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4056406be8d5a18644672aaf7395f53b9c2b6b99f5b5cc9f227d881befe8bda5
+oid sha256:f51ce17b962cc00fc6442b15a713528c210c14ddfb52dfbff590324a586f3e04
 size 1261877172

runs/Jun13_15-51-10_dn011/events.out.tfevents.1718287134.dn011.1632536.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51f8eeec322e3bff9e60a0f1cd414cbb30bbb104492af6c01947fde60d0ae9e
+size 6813