Model save

README.md

@@ -32,7 +32,7 @@ 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 the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2805
+- Loss: 0.6462
 - Accuracy: 1.0
 
 ## Model description
@@ -53,11 +53,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.5
@@ -67,10 +67,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8144        | 0.89  | 2    | 1.4061          | 1.0      |
-| 1.2223        | 1.78  | 4    | 0.6946          | 1.0      |
-| 0.5897        | 2.67  | 6    | 0.3691          | 1.0      |
-| 0.2163        | 3.56  | 8    | 0.2805          | 1.0      |
+| 1.2303        | 1.0   | 1    | 1.6505          | 0.0556   |
+| 0.5114        | 2.0   | 3    | 0.9083          | 1.0      |
+| 0.45          | 2.67  | 4    | 0.6462          | 1.0      |
 
 
 ### Framework versions

runs/Mar31_03-58-21_2a328889baa5/events.out.tfevents.1711857502.2a328889baa5.277.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b7d83d6180bc4a1f34bcbccf76ba8dd7d1eb0e832910bc942701d3bafd9373
-size 7634
+oid sha256:4c2bec2728db524472f80166966ee52bb40fb114a21db7b03eb88e1486e1b7c0
+size 8506