End of training

README.md

@@ -6,36 +6,9 @@ tags:
 - generated_from_trainer
 datasets:
 - gtzan
-metrics:
-- accuracy
-- precision
-- recall
-- f1
 model-index:
 - name: hubert-model-v1
-  results:
-  - task:
-      name: Audio Classification
-      type: audio-classification
-    dataset:
-      name: gtzan
-      type: gtzan
-      config: default
-      split: train
-      args: default
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.775
-    - name: Precision
-      type: precision
-      value: 0.7724506443587075
-    - name: Recall
-      type: recall
-      value: 0.775
-    - name: F1
-      type: f1
-      value: 0.7598948943956552
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +18,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the gtzan dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8438
-- Accuracy: 0.775
-- Precision: 0.7725
-- Recall: 0.775
-- F1: 0.7599
+- eval_loss: 2.1979
+- eval_accuracy: 0.245
+- eval_precision: 0.2882
+- eval_recall: 0.245
+- eval_f1: 0.1828
+- eval_runtime: 105.666
+- eval_samples_per_second: 1.893
+- eval_steps_per_second: 0.473
+- epoch: 1.0
+- step: 25
 
 ## Model description
 
@@ -72,26 +50,14 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- gradient_accumulation_steps: 8
+- 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_ratio: 0.1
-- num_epochs: 8
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| No log        | 1.0   | 180  | 2.0025          | 0.29     | 0.2351    | 0.29   | 0.1935 |
-| No log        | 2.0   | 360  | 1.6515          | 0.46     | 0.3961    | 0.46   | 0.3960 |
-| 1.8167        | 3.0   | 540  | 1.2595          | 0.6      | 0.5193    | 0.6    | 0.5449 |
-| 1.8167        | 4.0   | 720  | 1.1376          | 0.655    | 0.6648    | 0.655  | 0.6349 |
-| 1.8167        | 5.0   | 900  | 1.0759          | 0.71     | 0.7372    | 0.71   | 0.6947 |
-| 1.0396        | 6.0   | 1080 | 0.8932          | 0.78     | 0.8324    | 0.78   | 0.7705 |
-| 1.0396        | 7.0   | 1260 | 0.9236          | 0.75     | 0.7820    | 0.75   | 0.7314 |
-| 1.0396        | 8.0   | 1440 | 0.8438          | 0.775    | 0.7725    | 0.775  | 0.7599 |
-
-
 ### Framework versions
 
 - Transformers 4.47.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466cfb52e67ca51121c39a8d7448519fef69b93d46e4c49033b55f4ed14ded93
+oid sha256:eb61257795cae4d6900ffe1fd9a4fb3a43bdd70f1c93b15d608bee079833ec4a
 size 378310176

runs/Jan24_16-27-12_307f96733aba/events.out.tfevents.1737736033.307f96733aba.2161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f593c0a9046d3028b4bec17456cb25057694fbf511910736135c25caefa6278c
+size 7229

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14f602f7ce0ee0053524d247d06362aedf398f01ea7ec0e5c722bdca9bc1695
+oid sha256:b5c799319c9fee50e75ec7b90bd6d378a1bd967b218589df6a652e51e9031a88
 size 5304