End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9407
-- Accuracy: 0.2222
+- Loss: 1.1835
+- Accuracy: 0.8889
 
 ## Model description
 
@@ -44,22 +44,25 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 8
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.0548        | 0.9778 | 22   | 2.0247          | 0.1556   |
-| 1.8744        | 1.9556 | 44   | 1.9407          | 0.2222   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 7.4725        | 1.0   | 23   | 1.7542          | 0.6      |
+| 6.5766        | 2.0   | 46   | 1.5813          | 0.7111   |
+| 5.9666        | 3.0   | 69   | 1.4359          | 0.8      |
+| 4.807         | 4.0   | 92   | 1.2130          | 0.9111   |
+| 4.5109        | 4.8   | 110  | 1.1835          | 0.8889   |
 
 
 ### Framework versions
 
-- Transformers 4.46.3
-- Pytorch 2.5.1+cu124
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016d473f488515ce5db1f856ad7f5e937e99998b30a280b20ef2ec12ca5e857c
+oid sha256:e428408b7fd88f3af7694a4ead77c05e7b3571fd03729cdc37f7e2532b87ee7a
 size 378310592