Upload folder using huggingface_hub

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large
+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: 0.9839658723153869
+---
+
+<!-- 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/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0856
+- Accuracy: 0.9840
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.0646        | 1.0   | 1597  | 0.1839          | 0.9625   |
+| 0.3751        | 2.0   | 3194  | 0.1954          | 0.9647   |
+| 0.3156        | 3.0   | 4791  | 0.1335          | 0.9744   |
+| 0.257         | 4.0   | 6388  | 0.1062          | 0.9796   |
+| 0.2386        | 5.0   | 7985  | 0.1029          | 0.9801   |
+| 0.2085        | 6.0   | 9582  | 0.1002          | 0.9815   |
+| 0.1715        | 7.0   | 11179 | 0.1031          | 0.9818   |
+| 0.1575        | 8.0   | 12776 | 0.0938          | 0.9819   |
+| 0.1332        | 9.0   | 14373 | 0.0896          | 0.9831   |
+| 0.1288        | 10.0  | 15970 | 0.0856          | 0.9840   |
+
+
+### 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": 0.9839658723153869,
+    "eval_loss": 0.08564967662096024,
+    "eval_runtime": 13.7712,
+    "eval_samples_per_second": 493.639,
+    "eval_steps_per_second": 1.961,
+    "test_accuracy": 0.8941901979876663,
+    "test_loss": 0.5584208965301514,
+    "test_runtime": 7.2376,
+    "test_samples_per_second": 425.691,
+    "test_steps_per_second": 1.796,
+    "total_flos": 1.548488981447424e+19,
+    "train_accuracy": 0.991779856734646,
+    "train_loss": 0.03589404374361038,
+    "train_runtime": 279.3635,
+    "train_samples_per_second": 182.894,
+    "train_steps_per_second": 45.725
+}

config.json

@@ -0,0 +1,139 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "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_quantizer_dropout": 0.0,
+  "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": 1024,
+  "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": 4096,
+  "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": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9839658723153869,
+    "eval_loss": 0.08564967662096024,
+    "eval_runtime": 13.7712,
+    "eval_samples_per_second": 493.639,
+    "eval_steps_per_second": 1.961
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc189e34d87da6b307672b6f022d2f043d146bae4bd7d4393da90e29023e98a
+size 1262828272

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e488c9070fd10dbf421403f2070f4f3b412a96c19bc75111198a99c0f77375d7
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c482f8cf80f551a61920bcddc0ffe511cf7e5f9645ef0930b789121aea7f19a
+size 148016

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d8c325dbfbc6e2352505de9eea67d1319c5881db485f375f1ba731790ec7ec
+size 2452640

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "test_accuracy": 0.8941901979876663,
+    "test_loss": 0.5584208965301514,
+    "test_runtime": 7.2376,
+    "test_samples_per_second": 425.691,
+    "test_steps_per_second": 1.796
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_accuracy": 0.991779856734646,
+    "train_loss": 0.03589404374361038,
+    "train_runtime": 279.3635,
+    "train_samples_per_second": 182.894,
+    "train_steps_per_second": 45.725
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.9839658723153869,
+  "best_model_checkpoint": "audio/train/checkpoint/wav2vec2-large/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": 7.050719738006592,
+      "learning_rate": 3.1308703819661866e-05,
+      "loss": 1.0646,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9624889673433362,
+      "eval_loss": 0.1839100420475006,
+      "eval_runtime": 14.3255,
+      "eval_samples_per_second": 474.537,
+      "eval_steps_per_second": 1.885,
+      "step": 1597
+    },
+    {
+      "epoch": 1.2523481527864746,
+      "grad_norm": 9.074967384338379,
+      "learning_rate": 4.859806581785292e-05,
+      "loss": 0.4257,
+      "step": 2000
+    },
+    {
+      "epoch": 1.878522229179712,
+      "grad_norm": 91.34820556640625,
+      "learning_rate": 4.51193209490016e-05,
+      "loss": 0.3751,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9646954986760812,
+      "eval_loss": 0.19544720649719238,
+      "eval_runtime": 13.9956,
+      "eval_samples_per_second": 485.723,
+      "eval_steps_per_second": 1.929,
+      "step": 3194
+    },
+    {
+      "epoch": 2.504696305572949,
+      "grad_norm": 1.8326303958892822,
+      "learning_rate": 4.1640576080150286e-05,
+      "loss": 0.3156,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9744042365401588,
+      "eval_loss": 0.13350164890289307,
+      "eval_runtime": 14.2445,
+      "eval_samples_per_second": 477.238,
+      "eval_steps_per_second": 1.895,
+      "step": 4791
+    },
+    {
+      "epoch": 3.1308703819661865,
+      "grad_norm": 2.554948329925537,
+      "learning_rate": 3.8161831211298965e-05,
+      "loss": 0.2839,
+      "step": 5000
+    },
+    {
+      "epoch": 3.757044458359424,
+      "grad_norm": 1.011059045791626,
+      "learning_rate": 3.468308634244764e-05,
+      "loss": 0.257,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.979552809649897,
+      "eval_loss": 0.10616285353899002,
+      "eval_runtime": 14.1933,
+      "eval_samples_per_second": 478.959,
+      "eval_steps_per_second": 1.902,
+      "step": 6388
+    },
+    {
+      "epoch": 4.383218534752661,
+      "grad_norm": 18.241968154907227,
+      "learning_rate": 3.120434147359633e-05,
+      "loss": 0.2386,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9801412180052956,
+      "eval_loss": 0.10293199121952057,
+      "eval_runtime": 21.533,
+      "eval_samples_per_second": 315.701,
+      "eval_steps_per_second": 1.254,
+      "step": 7985
+    },
+    {
+      "epoch": 5.009392611145898,
+      "grad_norm": 22.520170211791992,
+      "learning_rate": 2.7725596604745007e-05,
+      "loss": 0.2205,
+      "step": 8000
+    },
+    {
+      "epoch": 5.635566687539136,
+      "grad_norm": 2.018341302871704,
+      "learning_rate": 2.4246851735893692e-05,
+      "loss": 0.2085,
+      "step": 9000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9814651368049426,
+      "eval_loss": 0.1001678854227066,
+      "eval_runtime": 14.0995,
+      "eval_samples_per_second": 482.145,
+      "eval_steps_per_second": 1.915,
+      "step": 9582
+    },
+    {
+      "epoch": 6.261740763932373,
+      "grad_norm": 29.089778900146484,
+      "learning_rate": 2.076810686704237e-05,
+      "loss": 0.1905,
+      "step": 10000
+    },
+    {
+      "epoch": 6.88791484032561,
+      "grad_norm": 2.23885178565979,
+      "learning_rate": 1.7289361998191053e-05,
+      "loss": 0.1715,
+      "step": 11000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.981759340982642,
+      "eval_loss": 0.10314840078353882,
+      "eval_runtime": 14.0909,
+      "eval_samples_per_second": 482.44,
+      "eval_steps_per_second": 1.916,
+      "step": 11179
+    },
+    {
+      "epoch": 7.514088916718848,
+      "grad_norm": 0.31174391508102417,
+      "learning_rate": 1.3810617129339735e-05,
+      "loss": 0.1575,
+      "step": 12000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9819064430714917,
+      "eval_loss": 0.09382686764001846,
+      "eval_runtime": 14.1853,
+      "eval_samples_per_second": 479.227,
+      "eval_steps_per_second": 1.903,
+      "step": 12776
+    },
+    {
+      "epoch": 8.140262993112085,
+      "grad_norm": 2.9018185138702393,
+      "learning_rate": 1.0331872260488417e-05,
+      "loss": 0.147,
+      "step": 13000
+    },
+    {
+      "epoch": 8.766437069505322,
+      "grad_norm": 3.0589239597320557,
+      "learning_rate": 6.853127391637097e-06,
+      "loss": 0.1332,
+      "step": 14000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9830832597822889,
+      "eval_loss": 0.08958739787340164,
+      "eval_runtime": 14.0026,
+      "eval_samples_per_second": 485.481,
+      "eval_steps_per_second": 1.928,
+      "step": 14373
+    },
+    {
+      "epoch": 9.39261114589856,
+      "grad_norm": 4.1695756912231445,
+      "learning_rate": 3.3743825227857787e-06,
+      "loss": 0.1288,
+      "step": 15000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9839658723153869,
+      "eval_loss": 0.08564967662096024,
+      "eval_runtime": 13.9588,
+      "eval_samples_per_second": 487.004,
+      "eval_steps_per_second": 1.934,
+      "step": 15970
+    },
+    {
+      "epoch": 10.0,
+      "step": 15970,
+      "total_flos": 1.548488981447424e+19,
+      "train_loss": 0.27784167333327014,
+      "train_runtime": 3003.8643,
+      "train_samples_per_second": 170.094,
+      "train_steps_per_second": 5.316
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 15970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.548488981447424e+19,
+  "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 sha256:0e427b62cffd5c352c37fe75784c3b8d4e4aa54d34efcfc150a399f7d409d453
+size 5112