End of training

README.md

@@ -0,0 +1,100 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/hubert-base-ls960
+tags:
+- generated_from_trainer
+datasets:
+- gtzan
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: hubert-model-v1
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: gtzan
+      type: gtzan
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.775
+    - name: Precision
+      type: precision
+      value: 0.7724506443587075
+    - name: Recall
+      type: recall
+      value: 0.775
+    - name: F1
+      type: f1
+      value: 0.7598948943956552
+---
+
+<!-- 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. -->
+
+# hubert-model-v1
+
+This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the gtzan dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8438
+- Accuracy: 0.775
+- Precision: 0.7725
+- Recall: 0.775
+- F1: 0.7599
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use 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: 8
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 1.0   | 180  | 2.0025          | 0.29     | 0.2351    | 0.29   | 0.1935 |
+| No log        | 2.0   | 360  | 1.6515          | 0.46     | 0.3961    | 0.46   | 0.3960 |
+| 1.8167        | 3.0   | 540  | 1.2595          | 0.6      | 0.5193    | 0.6    | 0.5449 |
+| 1.8167        | 4.0   | 720  | 1.1376          | 0.655    | 0.6648    | 0.655  | 0.6349 |
+| 1.8167        | 5.0   | 900  | 1.0759          | 0.71     | 0.7372    | 0.71   | 0.6947 |
+| 1.0396        | 6.0   | 1080 | 0.8932          | 0.78     | 0.8324    | 0.78   | 0.7705 |
+| 1.0396        | 7.0   | 1260 | 0.9236          | 0.75     | 0.7820    | 0.75   | 0.7314 |
+| 1.0396        | 8.0   | 1440 | 0.8438          | 0.775    | 0.7725    | 0.775  | 0.7599 |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,100 @@
+{
+  "_name_or_path": "facebook/hubert-base-ls960",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "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_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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "9"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466cfb52e67ca51121c39a8d7448519fef69b93d46e4c49033b55f4ed14ded93
+size 378310176

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/Dec30_11-42-21_bcaaa883cecc/events.out.tfevents.1735558942.bcaaa883cecc.898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb02edd864bbb9c9931ca3d279021968206b3d8a0807c5c836cde5d1317a59d
+size 10901

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14f602f7ce0ee0053524d247d06362aedf398f01ea7ec0e5c722bdca9bc1695
+size 5304