End of training

README.md

@@ -1,83 +1,81 @@
----
-license: apache-2.0
-base_model: ntu-spml/distilhubert
-tags:
-- generated_from_trainer
-datasets:
-- marsyas/gtzan
-metrics:
-- accuracy
-model-index:
-- name: distilhubert-finetuned-augtzan
-  results:
-  - task:
-      name: Audio Classification
-      type: audio-classification
-    dataset:
-      name: GTZAN
-      type: marsyas/gtzan
-      config: all
-      split: train
-      args: all
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.8
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# distilhubert-finetuned-augtzan
-
-This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.8335
-- Accuracy: 0.8
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5
-- mixed_precision_training: Native AMP
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.3012        | 0.9989 | 449  | 1.1712          | 0.5975   |
-| 0.6359        | 2.0    | 899  | 0.8030          | 0.7625   |
-| 0.3241        | 2.9989 | 1348 | 1.0263          | 0.7275   |
-| 0.1121        | 4.0    | 1798 | 0.7556          | 0.8175   |
-| 0.0432        | 4.9944 | 2245 | 0.8335          | 0.8      |
-
-
-### Framework versions
-
-- Transformers 4.44.0
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+---
+license: apache-2.0
+base_model: ntu-spml/distilhubert
+tags:
+- generated_from_trainer
+datasets:
+- marsyas/gtzan
+metrics:
+- accuracy
+model-index:
+- name: distilhubert-finetuned-augtzan
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: GTZAN
+      type: marsyas/gtzan
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.85
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilhubert-finetuned-augtzan
+
+This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4862
+- Accuracy: 0.85
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.0875        | 1.0   | 450  | 1.0890          | 0.7      |
+| 0.9658        | 2.0   | 900  | 0.7519          | 0.82     |
+| 0.4759        | 3.0   | 1350 | 0.6324          | 0.8      |
+| 0.4945        | 4.0   | 1800 | 0.5081          | 0.86     |
+| 0.2206        | 5.0   | 2250 | 0.4862          | 0.85     |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8d46a26cb63b0c73286ee41175fd0118765449a1c70aa0b224ea9f94b83220
+oid sha256:1fd197d7d6c01dd2822715300a8157d72215aaa3d27ee3bf022106e1bc76da89
 size 94771728