End of training

README.md

@@ -0,0 +1,91 @@
+---
+license: apache-2.0
+base_model: ntu-spml/distilhubert
+tags:
+- generated_from_trainer
+datasets:
+- marsyas/gtzan
+metrics:
+- accuracy
+model-index:
+- name: distilhubert-finetuned-gtzan
+  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: 0.84
+---
+
+<!-- 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-gtzan
+
+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: 1.2778
+- Accuracy: 0.84
+
+## 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: 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: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0061        | 1.0   | 113  | 0.9999          | 0.84     |
+| 0.0735        | 2.0   | 226  | 1.2200          | 0.78     |
+| 0.2103        | 3.0   | 339  | 1.6617          | 0.74     |
+| 0.0075        | 4.0   | 452  | 1.5453          | 0.75     |
+| 0.0004        | 5.0   | 565  | 1.3464          | 0.84     |
+| 0.0006        | 6.0   | 678  | 1.3242          | 0.81     |
+| 0.0246        | 7.0   | 791  | 1.7457          | 0.76     |
+| 0.0003        | 8.0   | 904  | 1.2888          | 0.82     |
+| 0.0002        | 9.0   | 1017 | 1.1534          | 0.83     |
+| 0.0011        | 10.0  | 1130 | 1.1696          | 0.85     |
+| 0.1217        | 11.0  | 1243 | 1.1479          | 0.83     |
+| 0.0002        | 12.0  | 1356 | 1.4423          | 0.84     |
+| 0.0002        | 13.0  | 1469 | 1.2385          | 0.84     |
+| 0.0002        | 14.0  | 1582 | 1.2497          | 0.85     |
+| 0.0002        | 15.0  | 1695 | 1.2778          | 0.84     |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.0.1
+- Datasets 2.14.5
+- Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c75640f93718bdcb8d11fae52d60d2dfafd91c5669c3db0ea368914127e1d62
+oid sha256:bfa0b70e5c121c64443380e35304399248fd25a002be00e2df31ac2ad7fcedce
 size 94771680

runs/Dec15_15-21-34_Billapati-Home/events.out.tfevents.1702633977.Billapati-Home.1579.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd905cd129098e406a0774305a0e9369f4ced26ea65fc986600c20dedbd88e7
-size 63566
+oid sha256:7fde7c39e56d1dcce0bf0ef1a883acd5357887a8b1144a74b6778687103351d1
+size 63920

runs/Dec27_14-30-41_Billapati-Home/events.out.tfevents.1703667651.Billapati-Home.900.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:134d2dcf4cb905ddb2c01811b6d9e111e916f75c78fc0f3595679ea2bff68911
+size 54277

runs/Dec27_14-30-41_Billapati-Home/events.out.tfevents.1703672705.Billapati-Home.900.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f7bf7b0ed25f6be603315d58355ff22ae5502e81dcc56b6fdbb88629ebda94
+size 63941

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c870ac7da4944b1b6f83f57d4e062cfd46a19f0aabaf5714f7e5fc549aeb179
+oid sha256:96aadcc1bcd911bba375a60ab979fb70c51986de5ad1fd9a22902e3bcfdf82ee
 size 4283