Model save

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/wavlm-base-plus](https://huggingface.co/microsoft/wavlm-base-plus) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6877
-- Accuracy: 0.7038
+- Loss: 0.5855
+- Accuracy: 0.8691
 
 ## Model description
 
@@ -37,11 +37,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9932        | 1.0   | 30   | 0.9458          | 0.6630   |
-| 0.796         | 2.0   | 60   | 0.7427          | 0.7021   |
-| 0.7386        | 3.0   | 90   | 0.6877          | 0.7038   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3109        | 1.0   | 7220  | 0.5189          | 0.8643   |
+| 0.2798        | 2.0   | 14440 | 0.5241          | 0.8661   |
+| 0.2721        | 3.0   | 21660 | 0.5855          | 0.8691   |
 
 
 ### Framework versions
 
-- Transformers 4.36.0
-- Pytorch 2.0.0
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1