End of training

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0212
-- Cer: 0.0036
+- Loss: 0.0424
+- Cer: 0.0116
 
 ## Model description
 
@@ -36,12 +36,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 8
+- learning_rate: 0.001
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 32
 - optimizer: Use OptimizerNames.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: 500
@@ -52,10 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Cer    |
 |:-------------:|:-------:|:----:|:---------------:|:------:|
-| 4.7981        | 6.3492  | 400  | 1.3567          | 0.3529 |
-| 1.0517        | 12.6984 | 800  | 0.3321          | 0.0766 |
-| 0.4466        | 19.0476 | 1200 | 0.0846          | 0.0169 |
-| 0.2524        | 25.3968 | 1600 | 0.0212          | 0.0036 |
+| 2.9885        | 12.9180 | 400  | 0.7044          | 0.1994 |
+| 0.6027        | 25.8197 | 800  | 0.0424          | 0.0116 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70785e6eb7991083ad3d5d00fb323784d9006320eb6779fff12a615530edf59a
+oid sha256:d919b0484eb3873f0e167689af513e5372b7695ffc6d2cc416acc392080d8526
 size 1261926380