End of training

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: ntu-spml/distilhubert
+tags:
+- generated_from_trainer
+datasets:
+- keystrokes
+metrics:
+- accuracy
+model-index:
+- name: distilhubert-finetuned-keystrokes
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: Keystrokes
+      type: keystrokes
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5555555555555556
+---
+
+<!-- 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-keystrokes
+
+This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the Keystrokes dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1861
+- Accuracy: 0.5556
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.5798        | 1.0   | 90   | 3.5605          | 0.0722   |
+| 3.396         | 2.0   | 180  | 3.3216          | 0.2722   |
+| 3.1783        | 3.0   | 270  | 3.0565          | 0.3      |
+| 2.8625        | 4.0   | 360  | 2.8097          | 0.3667   |
+| 2.5934        | 5.0   | 450  | 2.6345          | 0.4222   |
+| 2.4605        | 6.0   | 540  | 2.4812          | 0.4111   |
+| 2.2524        | 7.0   | 630  | 2.3649          | 0.4444   |
+| 2.1017        | 8.0   | 720  | 2.2739          | 0.5167   |
+| 2.0619        | 9.0   | 810  | 2.2158          | 0.5222   |
+| 2.0477        | 10.0  | 900  | 2.1861          | 0.5556   |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1
+- 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": "0",
+    "1": "1",
+    "10": "A",
+    "11": "B",
+    "12": "C",
+    "13": "D",
+    "14": "E",
+    "15": "F",
+    "16": "G",
+    "17": "H",
+    "18": "I",
+    "19": "J",
+    "2": "2",
+    "20": "K",
+    "21": "L",
+    "22": "M",
+    "23": "N",
+    "24": "O",
+    "25": "P",
+    "26": "Q",
+    "27": "R",
+    "28": "S",
+    "29": "T",
+    "3": "3",
+    "30": "U",
+    "31": "V",
+    "32": "W",
+    "33": "X",
+    "34": "Y",
+    "35": "Z",
+    "4": "4",
+    "5": "5",
+    "6": "6",
+    "7": "7",
+    "8": "8",
+    "9": "9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4",
+    "5": "5",
+    "6": "6",
+    "7": "7",
+    "8": "8",
+    "9": "9",
+    "A": "10",
+    "B": "11",
+    "C": "12",
+    "D": "13",
+    "E": "14",
+    "F": "15",
+    "G": "16",
+    "H": "17",
+    "I": "18",
+    "J": "19",
+    "K": "20",
+    "L": "21",
+    "M": "22",
+    "N": "23",
+    "O": "24",
+    "P": "25",
+    "Q": "26",
+    "R": "27",
+    "S": "28",
+    "T": "29",
+    "U": "30",
+    "V": "31",
+    "W": "32",
+    "X": "33",
+    "Y": "34",
+    "Z": "35"
+  },
+  "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": "4.40.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94699d5017759eeb18dd7a63f6bbb80dbe517541f2c71ce68fcf3ef4b4ddecb9
+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/May04_12-26-51_seonjin-MS-7C94/events.out.tfevents.1714793218.seonjin-MS-7C94.23556.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae0c2f8748a1823860dfe40d1f6c3ab4c5f3024605a137493b8470277f9533e
+size 48060

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ad9d9ed61bb67b09147ea97a9d38cf3ba0f93e8e8b77c63a40c9bb54718e8f
+size 5048