End of training

README.md

@@ -6,24 +6,9 @@ tags:
 - generated_from_trainer
 datasets:
 - marsyas/gtzan
-metrics:
-- accuracy
 model-index:
 - name: distilhubert-regularized-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: 0.82
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.7084
-- Accuracy: 0.82
+- eval_loss: 0.6969
+- eval_model_preparation_time: 0.0031
+- eval_accuracy: 0.86
+- eval_runtime: 69.8954
+- eval_samples_per_second: 1.431
+- eval_steps_per_second: 0.186
+- step: 0
 
 ## Model description
 
@@ -62,42 +52,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.2
 - num_epochs: 30
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.2836        | 1.0   | 113  | 2.2614          | 0.38     |
-| 2.1242        | 2.0   | 226  | 2.0742          | 0.51     |
-| 2.1173        | 3.0   | 339  | 1.8400          | 0.51     |
-| 1.6568        | 4.0   | 452  | 1.5835          | 0.51     |
-| 1.6131        | 5.0   | 565  | 1.3757          | 0.61     |
-| 1.4403        | 6.0   | 678  | 1.2229          | 0.62     |
-| 1.0143        | 7.0   | 791  | 1.1339          | 0.67     |
-| 0.9131        | 8.0   | 904  | 0.9145          | 0.75     |
-| 0.8761        | 9.0   | 1017 | 0.8416          | 0.75     |
-| 0.6423        | 10.0  | 1130 | 0.7925          | 0.78     |
-| 0.7807        | 11.0  | 1243 | 0.8536          | 0.75     |
-| 0.6784        | 12.0  | 1356 | 0.7888          | 0.77     |
-| 0.5426        | 13.0  | 1469 | 0.7602          | 0.75     |
-| 0.8931        | 14.0  | 1582 | 0.8353          | 0.79     |
-| 0.3813        | 15.0  | 1695 | 0.6891          | 0.8      |
-| 0.4187        | 16.0  | 1808 | 0.6771          | 0.78     |
-| 0.3423        | 17.0  | 1921 | 0.6700          | 0.8      |
-| 0.2434        | 18.0  | 2034 | 0.7021          | 0.8      |
-| 0.3494        | 19.0  | 2147 | 0.6733          | 0.82     |
-| 0.1451        | 20.0  | 2260 | 0.8501          | 0.79     |
-| 0.1985        | 21.0  | 2373 | 0.8835          | 0.76     |
-| 0.2366        | 22.0  | 2486 | 0.8176          | 0.8      |
-| 0.2397        | 23.0  | 2599 | 0.6329          | 0.86     |
-| 0.0448        | 24.0  | 2712 | 0.6744          | 0.85     |
-| 0.4083        | 25.0  | 2825 | 0.7637          | 0.83     |
-| 0.1117        | 26.0  | 2938 | 0.7090          | 0.84     |
-| 0.0805        | 27.0  | 3051 | 0.6969          | 0.86     |
-| 0.095         | 28.0  | 3164 | 0.7278          | 0.82     |
-| 0.189         | 29.0  | 3277 | 0.7198          | 0.83     |
-| 0.2195        | 30.0  | 3390 | 0.7084          | 0.82     |
-
-
 ### Framework versions
 
 - Transformers 4.48.0.dev0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ntu-spml/distilhubert",
+  "_name_or_path": "f0ghedgeh0g/distilhubert-finetuned-gtzan",
   "activation_dropout": 0.2,
   "apply_spec_augment": false,
   "architectures": [

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5539a1db22fe379ed5993c80b00f9f7d9c17c2355881df6c72ff6292556c2a94
+oid sha256:d84ad22bf1cd0cfbbc388958dca4eb3495571ed760965f64aadb769487a4cdd9
 size 94799080