End of training

README.md

@@ -1,15 +1,28 @@
 ---
-language:
-- en
 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: []
+  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: 0.53
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,6 +31,9 @@ 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: 1.8461
+- Accuracy: 0.53
 
 ## Model description
 
@@ -36,7 +52,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -46,9 +62,16 @@ The following hyperparameters were used during training:
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9351        | 1.0   | 113  | 1.8461          | 0.53     |
+
+
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.36.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.0
 - Tokenizers 0.15.0

config.json

@@ -90,7 +90,7 @@
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "use_weighted_layer_sum": false,
   "vocab_size": 32
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf1bb653f8266765f314996c5734601370ab21efa9a151643b67cb56c09a82e
+oid sha256:69900a9c6ff284ea11b1c38600ff3f14e5025f2f3eee8c167883806645bd61ef
 size 94771728

runs/Dec24_18-48-21_e2ac1b75f3e9/events.out.tfevents.1703443702.e2ac1b75f3e9.529.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e3fb174dd6205e3148627ea60b1cc0cffc8c39f8af2351168f94ceeb591a6e
+size 9626

runs/Dec24_19-05-57_e2ac1b75f3e9/events.out.tfevents.1703444760.e2ac1b75f3e9.529.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db95533d38dbdac8eb00b0890c140d21b577a8e29eb1a8dbcbc2e0d05a89c97
+size 9624

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1d0d908e0a9d4367c3b50b36da75ce746ffee141e56f6f137addbcda7ebde8
-size 4600
+oid sha256:347c46b7c48a9f565e5226fdbf7927c8ff1773cf9d939cfd7c3bb3d09c19cc6c
+size 4728