Upload folder using huggingface_hub

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: facebook/hubert-base-ls960
+tags:
+- audio-classification
+- generated_from_trainer
+datasets:
+- superb
+metrics:
+- accuracy
+model-index:
+- name: superb_ks_42
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: superb
+      type: superb
+      config: ks
+      split: validation
+      args: ks
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9833774639599883
+---
+
+<!-- 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. -->
+
+# superb_ks_42
+
+This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0857
+- Accuracy: 0.9834
+
+## 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: 32
+- eval_batch_size: 4
+- 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
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.5858        | 1.0   | 1597  | 0.1746          | 0.9701   |
+| 0.2268        | 2.0   | 3194  | 0.1038          | 0.9773   |
+| 0.1937        | 3.0   | 4791  | 0.0887          | 0.9797   |
+| 0.163         | 4.0   | 6388  | 0.0786          | 0.9826   |
+| 0.1468        | 5.0   | 7985  | 0.0982          | 0.9815   |
+| 0.1327        | 6.0   | 9582  | 0.0888          | 0.9821   |
+| 0.1175        | 7.0   | 11179 | 0.0967          | 0.9812   |
+| 0.1164        | 8.0   | 12776 | 0.0922          | 0.9815   |
+| 0.1023        | 9.0   | 14373 | 0.0875          | 0.9828   |
+| 0.0983        | 10.0  | 15970 | 0.0857          | 0.9834   |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9833774639599883,
+    "eval_loss": 0.08568365126848221,
+    "eval_runtime": 6.6698,
+    "eval_samples_per_second": 1019.221,
+    "eval_steps_per_second": 4.048,
+    "test_accuracy": 0.8922427783187277,
+    "test_loss": 0.5359891057014465,
+    "test_runtime": 4.328,
+    "test_samples_per_second": 711.877,
+    "test_steps_per_second": 3.004,
+    "total_flos": 4.6387626201984e+18,
+    "train_accuracy": 0.992445296903746,
+    "train_loss": 0.029887313023209572,
+    "train_runtime": 178.1926,
+    "train_samples_per_second": 286.735,
+    "train_steps_per_second": 71.686
+}

config.json

@@ -0,0 +1,105 @@
+{
+  "_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,
+  "finetuning_task": "audio-classification",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "yes",
+    "1": "no",
+    "10": "_silence_",
+    "11": "_unknown_",
+    "2": "up",
+    "3": "down",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_silence_": "10",
+    "_unknown_": "11",
+    "down": "3",
+    "go": "9",
+    "left": "4",
+    "no": "1",
+    "off": "7",
+    "on": "6",
+    "right": "5",
+    "stop": "8",
+    "up": "2",
+    "yes": "0"
+  },
+  "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": "4.40.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9833774639599883,
+    "eval_loss": 0.08568365126848221,
+    "eval_runtime": 6.6698,
+    "eval_samples_per_second": 1019.221,
+    "eval_steps_per_second": 4.048
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a057942f07ad568c1f551fe91b9cf66ce52be420183309d7cfdc21c86b7c18e6
+size 378312232

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d3b50f3614bb87d307b19d06d141a247442f9ce11904e62095ec928c2272e81
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afb3605e61d5eec3ed5e4f39b143a66c6f66cba3066f37ce57ad76615d0135f
+size 148016

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0ece8f138a6d657833c48e56f32598fd9a37cbdab808b5e7cccfcab7572d31
+size 2452640

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
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "test_accuracy": 0.8922427783187277,
+    "test_loss": 0.5359891057014465,
+    "test_runtime": 4.328,
+    "test_samples_per_second": 711.877,
+    "test_steps_per_second": 3.004
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_accuracy": 0.992445296903746,
+    "train_loss": 0.029887313023209572,
+    "train_runtime": 178.1926,
+    "train_samples_per_second": 286.735,
+    "train_steps_per_second": 71.686
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.9833774639599883,
+  "best_model_checkpoint": "audio/train/checkpoint/hubert-base/superb_ks_42/checkpoint-15970",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 15970,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6261740763932373,
+      "grad_norm": 3.687915086746216,
+      "learning_rate": 3.1308703819661866e-05,
+      "loss": 1.5858,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9701382759635186,
+      "eval_loss": 0.1746179759502411,
+      "eval_runtime": 10.5438,
+      "eval_samples_per_second": 644.74,
+      "eval_steps_per_second": 2.561,
+      "step": 1597
+    },
+    {
+      "epoch": 1.2523481527864746,
+      "grad_norm": 3.3637237548828125,
+      "learning_rate": 4.859806581785292e-05,
+      "loss": 0.4328,
+      "step": 2000
+    },
+    {
+      "epoch": 1.878522229179712,
+      "grad_norm": 2.0145509243011475,
+      "learning_rate": 4.51193209490016e-05,
+      "loss": 0.2268,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9773462783171522,
+      "eval_loss": 0.10376445204019547,
+      "eval_runtime": 10.6724,
+      "eval_samples_per_second": 636.969,
+      "eval_steps_per_second": 2.53,
+      "step": 3194
+    },
+    {
+      "epoch": 2.504696305572949,
+      "grad_norm": 9.941652297973633,
+      "learning_rate": 4.1640576080150286e-05,
+      "loss": 0.1937,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9796999117387467,
+      "eval_loss": 0.08871696144342422,
+      "eval_runtime": 6.7605,
+      "eval_samples_per_second": 1005.553,
+      "eval_steps_per_second": 3.994,
+      "step": 4791
+    },
+    {
+      "epoch": 3.1308703819661865,
+      "grad_norm": 3.4196901321411133,
+      "learning_rate": 3.8161831211298965e-05,
+      "loss": 0.1745,
+      "step": 5000
+    },
+    {
+      "epoch": 3.757044458359424,
+      "grad_norm": 10.562482833862305,
+      "learning_rate": 3.468308634244764e-05,
+      "loss": 0.163,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9826419535157399,
+      "eval_loss": 0.07863254845142365,
+      "eval_runtime": 6.5412,
+      "eval_samples_per_second": 1039.264,
+      "eval_steps_per_second": 4.128,
+      "step": 6388
+    },
+    {
+      "epoch": 4.383218534752661,
+      "grad_norm": 8.417603492736816,
+      "learning_rate": 3.120434147359633e-05,
+      "loss": 0.1468,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9814651368049426,
+      "eval_loss": 0.09819477796554565,
+      "eval_runtime": 6.6232,
+      "eval_samples_per_second": 1026.399,
+      "eval_steps_per_second": 4.077,
+      "step": 7985
+    },
+    {
+      "epoch": 5.009392611145898,
+      "grad_norm": 8.484418869018555,
+      "learning_rate": 2.7725596604745007e-05,
+      "loss": 0.1463,
+      "step": 8000
+    },
+    {
+      "epoch": 5.635566687539136,
+      "grad_norm": 2.67555832862854,
+      "learning_rate": 2.4246851735893692e-05,
+      "loss": 0.1327,
+      "step": 9000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9820535451603413,
+      "eval_loss": 0.08876165747642517,
+      "eval_runtime": 6.6465,
+      "eval_samples_per_second": 1022.797,
+      "eval_steps_per_second": 4.062,
+      "step": 9582
+    },
+    {
+      "epoch": 6.261740763932373,
+      "grad_norm": 1.1208974123001099,
+      "learning_rate": 2.076810686704237e-05,
+      "loss": 0.1256,
+      "step": 10000
+    },
+    {
+      "epoch": 6.88791484032561,
+      "grad_norm": 1.1888195276260376,
+      "learning_rate": 1.7289361998191053e-05,
+      "loss": 0.1175,
+      "step": 11000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9811709326272433,
+      "eval_loss": 0.09669487923383713,
+      "eval_runtime": 6.767,
+      "eval_samples_per_second": 1004.575,
+      "eval_steps_per_second": 3.99,
+      "step": 11179
+    },
+    {
+      "epoch": 7.514088916718848,
+      "grad_norm": 11.39383602142334,
+      "learning_rate": 1.3810617129339735e-05,
+      "loss": 0.1164,
+      "step": 12000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9814651368049426,
+      "eval_loss": 0.09223304688930511,
+      "eval_runtime": 6.6066,
+      "eval_samples_per_second": 1028.975,
+      "eval_steps_per_second": 4.087,
+      "step": 12776
+    },
+    {
+      "epoch": 8.140262993112085,
+      "grad_norm": 2.318204402923584,
+      "learning_rate": 1.0331872260488417e-05,
+      "loss": 0.1125,
+      "step": 13000
+    },
+    {
+      "epoch": 8.766437069505322,
+      "grad_norm": 0.40608373284339905,
+      "learning_rate": 6.853127391637097e-06,
+      "loss": 0.1023,
+      "step": 14000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9827890556045896,
+      "eval_loss": 0.08754321187734604,
+      "eval_runtime": 6.712,
+      "eval_samples_per_second": 1012.816,
+      "eval_steps_per_second": 4.023,
+      "step": 14373
+    },
+    {
+      "epoch": 9.39261114589856,
+      "grad_norm": 0.3792332410812378,
+      "learning_rate": 3.3743825227857787e-06,
+      "loss": 0.0983,
+      "step": 15000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9833774639599883,
+      "eval_loss": 0.08568365126848221,
+      "eval_runtime": 6.8598,
+      "eval_samples_per_second": 990.99,
+      "eval_steps_per_second": 3.936,
+      "step": 15970
+    },
+    {
+      "epoch": 10.0,
+      "step": 15970,
+      "total_flos": 4.6387626201984e+18,
+      "train_loss": 0.2486723821612545,
+      "train_runtime": 1368.9283,
+      "train_samples_per_second": 373.241,
+      "train_steps_per_second": 11.666
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 15970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 4.6387626201984e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7b9decec724a4ff8dd98be576bacd21be2aecff7db27c1248a6dfbceeef3a7
+size 5112