End of training

README.md

@@ -4,7 +4,7 @@ base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 datasets:
-- gtzan
+- marsyas/gtzan
 metrics:
 - accuracy
 model-index:
@@ -14,15 +14,15 @@ model-index:
       name: Audio Classification
       type: audio-classification
     dataset:
-      name: gtzan
-      type: gtzan
+      name: GTZAN
+      type: marsyas/gtzan
       config: all
       split: train
       args: all
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.85
+      value: 0.8
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-finetuned-gtzan
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the gtzan dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9600
-- Accuracy: 0.85
+- Loss: 0.7670
+- Accuracy: 0.8
 
 ## Model description
 
@@ -56,8 +56,6 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -67,21 +65,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.2696        | 0.99  | 28   | 2.1350          | 0.45     |
-| 1.9724        | 1.98  | 56   | 1.7939          | 0.63     |
-| 1.7172        | 2.97  | 84   | 1.6356          | 0.58     |
-| 1.5428        | 4.0   | 113  | 1.4019          | 0.71     |
-| 1.3184        | 4.99  | 141  | 1.3236          | 0.73     |
-| 1.2897        | 5.98  | 169  | 1.1980          | 0.79     |
-| 1.1657        | 6.97  | 197  | 1.0928          | 0.84     |
-| 1.0407        | 8.0   | 226  | 1.0616          | 0.83     |
-| 0.9717        | 8.99  | 254  | 0.9931          | 0.87     |
-| 0.9158        | 9.91  | 280  | 0.9600          | 0.85     |
+| 2.0554        | 1.0   | 100  | 2.0109          | 0.465    |
+| 1.5036        | 2.0   | 200  | 1.5547          | 0.53     |
+| 1.348         | 3.0   | 300  | 1.2558          | 0.685    |
+| 1.1877        | 4.0   | 400  | 1.1226          | 0.7      |
+| 0.8857        | 5.0   | 500  | 0.9978          | 0.76     |
+| 0.6167        | 6.0   | 600  | 0.9513          | 0.755    |
+| 0.5439        | 7.0   | 700  | 0.8185          | 0.78     |
+| 0.5015        | 8.0   | 800  | 0.7880          | 0.815    |
+| 0.2221        | 9.0   | 900  | 0.7777          | 0.8      |
+| 0.3112        | 10.0  | 1000 | 0.7670          | 0.8      |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.5
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
 - Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961491c1125d8851ff9cf8344739416bd766e2db3f5f6d34b5b693b878b6f8d7
+oid sha256:a06632143ae023c75e939c502490c2dd21090aa855678375112bded8a3c02697
 size 378359142