End of training

README.md

@@ -0,0 +1,77 @@
+---
+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: Speech_command_RK
+      type: marsyas/gtzan
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9975728155339806
+---
+
+<!-- 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 Speech_command_RK dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2480
+- Accuracy: 0.9976
+
+## 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: 264
+- eval_batch_size: 264
+- 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.4512        | 1.0   | 25   | 2.2018          | 0.6638   |
+| 1.2836        | 2.0   | 50   | 1.0664          | 0.9636   |
+| 0.6447        | 3.0   | 75   | 0.5056          | 0.9891   |
+| 0.3833        | 4.0   | 100  | 0.2985          | 0.9964   |
+| 0.3167        | 5.0   | 125  | 0.2480          | 0.9976   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,148 @@
+{
+  "_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_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": "yes",
+    "1": "no",
+    "10": "zero",
+    "11": "one",
+    "12": "two",
+    "13": "three",
+    "14": "four",
+    "15": "five",
+    "16": "six",
+    "17": "seven",
+    "18": "eight",
+    "19": "nine",
+    "2": "up",
+    "20": "bed",
+    "21": "bird",
+    "22": "cat",
+    "23": "dog",
+    "24": "happy",
+    "25": "house",
+    "26": "marvin",
+    "27": "sheila",
+    "28": "tree",
+    "29": "wow",
+    "3": "down",
+    "30": "backward",
+    "31": "forward",
+    "32": "follow",
+    "33": "learn",
+    "34": "visual",
+    "35": "_silence_",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_silence_": "35",
+    "backward": "30",
+    "bed": "20",
+    "bird": "21",
+    "cat": "22",
+    "dog": "23",
+    "down": "3",
+    "eight": "18",
+    "five": "15",
+    "follow": "32",
+    "forward": "31",
+    "four": "14",
+    "go": "9",
+    "happy": "24",
+    "house": "25",
+    "learn": "33",
+    "left": "4",
+    "marvin": "26",
+    "nine": "19",
+    "no": "1",
+    "off": "7",
+    "on": "6",
+    "one": "11",
+    "right": "5",
+    "seven": "17",
+    "sheila": "27",
+    "six": "16",
+    "stop": "8",
+    "three": "13",
+    "tree": "28",
+    "two": "12",
+    "up": "2",
+    "visual": "34",
+    "wow": "29",
+    "yes": "0",
+    "zero": "10"
+  },
+  "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": "4.40.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9cfb65bd8df44abb8a43f33685c1512d46f121f91eb4a3cd3b4b3090c3c7f5
+size 94798464

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/Apr29_19-16-03_6a83ad1054b9/events.out.tfevents.1714418171.6a83ad1054b9.9960.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5989702a863e14d23df7b65d4f07856840f644fd0150683a23e51ec163aa3f3
+size 13932

runs/Apr29_19-16-03_6a83ad1054b9/events.out.tfevents.1714419394.6a83ad1054b9.9960.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa55afdc3ec7fea35a5e01197489f61bcea1f90a849b6a079cd6e04bdf68b58
+size 405

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e609c141038226f6f785d2e9884dde5574d1536ded83f4b6c1866cdfe7a5f81e
+size 5048