End of training

README.md

@@ -0,0 +1,87 @@
+---
+library_name: transformers
+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: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.782608695652174
+---
+
+<!-- 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: 1.2172
+- Accuracy: 0.7826
+
+## 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: 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: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.1308        | 1.0   | 25   | 2.1309          | 0.0870   |
+| 1.9034        | 2.0   | 50   | 1.9650          | 0.3478   |
+| 1.6085        | 3.0   | 75   | 1.7543          | 0.5217   |
+| 1.4083        | 4.0   | 100  | 1.6225          | 0.5217   |
+| 1.4712        | 5.0   | 125  | 1.4741          | 0.6957   |
+| 1.1667        | 6.0   | 150  | 1.3947          | 0.6087   |
+| 1.0986        | 7.0   | 175  | 1.3320          | 0.7391   |
+| 1.0781        | 8.0   | 200  | 1.2441          | 0.7391   |
+| 0.96          | 9.0   | 225  | 1.2146          | 0.7826   |
+| 0.9224        | 10.0  | 250  | 1.2172          | 0.7826   |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "01_gunshot",
+    "1": "03_moped_alarm",
+    "2": "04_moped",
+    "3": "05_claxon",
+    "4": "06_car_door",
+    "5": "07_loud_people",
+    "6": "08_motor_cycle",
+    "7": "09_terrace_noise",
+    "8": "10_music"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "01_gunshot": "0",
+    "03_moped_alarm": "1",
+    "04_moped": "2",
+    "05_claxon": "3",
+    "06_car_door": "4",
+    "07_loud_people": "5",
+    "08_motor_cycle": "6",
+    "09_terrace_noise": "7",
+    "10_music": "8"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406b8d132d9eb7b47f819eed4d5b5eae56167f49f8e102b59dbfa5e7692f9b00
+size 94770700

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Mar10_20-59-25_37b1317acf0d/events.out.tfevents.1741640370.37b1317acf0d.2932.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28de1978aae0ad36386b2a5d12fb250b2630b0a86f7f67948d61e0a7aeb058c2
+size 20406

runs/Mar10_20-59-25_37b1317acf0d/events.out.tfevents.1741640856.37b1317acf0d.2932.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7c29668608f13e355cdb61e0cf530714ddbf346d6141e120062b7cf66aeb7b
+size 411

runs/Mar10_21-14-45_37b1317acf0d/events.out.tfevents.1741641300.37b1317acf0d.2932.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416e43298f6257021244edf892331cd93f8d43c361334b1ac350052aa80e4f75
+size 20406

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb24a8d958f3db0ee175d9b127ce7d32d2a80bfd30d923360a2b539624387930
+size 5368