Upload folder using huggingface_hub

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+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: 0.9845542806707855
+---
+
+<!-- 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-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0853
+- Accuracy: 0.9846
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.25          | 1.0   | 1597  | 0.1755          | 0.9582   |
+| 0.2502        | 2.0   | 3194  | 0.1402          | 0.9713   |
+| 0.2218        | 3.0   | 4791  | 0.0956          | 0.9803   |
+| 0.1746        | 4.0   | 6388  | 0.0917          | 0.9797   |
+| 0.17          | 5.0   | 7985  | 0.0893          | 0.9807   |
+| 0.1431        | 6.0   | 9582  | 0.0933          | 0.9810   |
+| 0.1238        | 7.0   | 11179 | 0.0958          | 0.9831   |
+| 0.116         | 8.0   | 12776 | 0.0970          | 0.9834   |
+| 0.0995        | 9.0   | 14373 | 0.0853          | 0.9846   |
+| 0.0985        | 10.0  | 15970 | 0.0829          | 0.9838   |
+
+
+### 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": 0.9845542806707855,
+    "eval_loss": 0.08534605801105499,
+    "eval_runtime": 6.6778,
+    "eval_samples_per_second": 1017.998,
+    "eval_steps_per_second": 4.043,
+    "test_accuracy": 0.890295358649789,
+    "test_loss": 0.5566478967666626,
+    "test_runtime": 4.3735,
+    "test_samples_per_second": 704.473,
+    "test_steps_per_second": 2.972,
+    "total_flos": 4.6387626201984e+18,
+    "train_accuracy": 0.9925235839824637,
+    "train_loss": 0.03144249692559242,
+    "train_runtime": 176.1726,
+    "train_samples_per_second": 290.022,
+    "train_steps_per_second": 72.508
+}

config.json

@@ -0,0 +1,147 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "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": 256,
+  "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_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 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": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "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": 0.9845542806707855,
+    "eval_loss": 0.08534605801105499,
+    "eval_runtime": 6.6778,
+    "eval_samples_per_second": 1017.998,
+    "eval_steps_per_second": 4.043
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0928bcd031d5be3fe523ea73a2ee512b5fd55648a2556f891314b57370d29f5
+size 378312648

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666c92228c20c7cc99bbd5a19f99c35c39f088b0598e1c09f37423e4c4d5b627
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59a8da91884126fd15f9937d12636ef2740f9d5e1ce526ae8d0e681a17dc795
+size 148016

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0143d5d04ccb97b2238a9740696b0988609b06f76a0d8612c22d8e352b5419
+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": 0.890295358649789,
+    "test_loss": 0.5566478967666626,
+    "test_runtime": 4.3735,
+    "test_samples_per_second": 704.473,
+    "test_steps_per_second": 2.972
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_accuracy": 0.9925235839824637,
+    "train_loss": 0.03144249692559242,
+    "train_runtime": 176.1726,
+    "train_samples_per_second": 290.022,
+    "train_steps_per_second": 72.508
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.9845542806707855,
+  "best_model_checkpoint": "audio/train/checkpoint/wav2vec2-base/superb_ks_42/checkpoint-14373",
+  "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": 12.87492847442627,
+      "learning_rate": 3.1308703819661866e-05,
+      "loss": 1.25,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9582230067666961,
+      "eval_loss": 0.17545583844184875,
+      "eval_runtime": 7.033,
+      "eval_samples_per_second": 966.585,
+      "eval_steps_per_second": 3.839,
+      "step": 1597
+    },
+    {
+      "epoch": 1.2523481527864746,
+      "grad_norm": 2.619173765182495,
+      "learning_rate": 4.859806581785292e-05,
+      "loss": 0.3308,
+      "step": 2000
+    },
+    {
+      "epoch": 1.878522229179712,
+      "grad_norm": 6.4030070304870605,
+      "learning_rate": 4.51193209490016e-05,
+      "loss": 0.2502,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9713150926743159,
+      "eval_loss": 0.140165776014328,
+      "eval_runtime": 6.9118,
+      "eval_samples_per_second": 983.532,
+      "eval_steps_per_second": 3.906,
+      "step": 3194
+    },
+    {
+      "epoch": 2.504696305572949,
+      "grad_norm": 0.2295457422733307,
+      "learning_rate": 4.1640576080150286e-05,
+      "loss": 0.2218,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9802883200941453,
+      "eval_loss": 0.09560667723417282,
+      "eval_runtime": 7.0467,
+      "eval_samples_per_second": 964.712,
+      "eval_steps_per_second": 3.832,
+      "step": 4791
+    },
+    {
+      "epoch": 3.1308703819661865,
+      "grad_norm": 0.9765733480453491,
+      "learning_rate": 3.8161831211298965e-05,
+      "loss": 0.194,
+      "step": 5000
+    },
+    {
+      "epoch": 3.757044458359424,
+      "grad_norm": 0.9296017289161682,
+      "learning_rate": 3.468308634244764e-05,
+      "loss": 0.1746,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9796999117387467,
+      "eval_loss": 0.09171486645936966,
+      "eval_runtime": 6.5552,
+      "eval_samples_per_second": 1037.04,
+      "eval_steps_per_second": 4.119,
+      "step": 6388
+    },
+    {
+      "epoch": 4.383218534752661,
+      "grad_norm": 7.867722511291504,
+      "learning_rate": 3.120434147359633e-05,
+      "loss": 0.17,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9807296263606943,
+      "eval_loss": 0.08932828158140182,
+      "eval_runtime": 6.9043,
+      "eval_samples_per_second": 984.61,
+      "eval_steps_per_second": 3.911,
+      "step": 7985
+    },
+    {
+      "epoch": 5.009392611145898,
+      "grad_norm": 1.299570083618164,
+      "learning_rate": 2.7725596604745007e-05,
+      "loss": 0.1554,
+      "step": 8000
+    },
+    {
+      "epoch": 5.635566687539136,
+      "grad_norm": 1.2470015287399292,
+      "learning_rate": 2.4246851735893692e-05,
+      "loss": 0.1431,
+      "step": 9000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9810238305383936,
+      "eval_loss": 0.09325208514928818,
+      "eval_runtime": 6.9991,
+      "eval_samples_per_second": 971.269,
+      "eval_steps_per_second": 3.858,
+      "step": 9582
+    },
+    {
+      "epoch": 6.261740763932373,
+      "grad_norm": 1.0575257539749146,
+      "learning_rate": 2.076810686704237e-05,
+      "loss": 0.1346,
+      "step": 10000
+    },
+    {
+      "epoch": 6.88791484032561,
+      "grad_norm": 3.034492015838623,
+      "learning_rate": 1.7289361998191053e-05,
+      "loss": 0.1238,
+      "step": 11000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9830832597822889,
+      "eval_loss": 0.09578000754117966,
+      "eval_runtime": 6.8981,
+      "eval_samples_per_second": 985.49,
+      "eval_steps_per_second": 3.914,
+      "step": 11179
+    },
+    {
+      "epoch": 7.514088916718848,
+      "grad_norm": 1.000091314315796,
+      "learning_rate": 1.3810617129339735e-05,
+      "loss": 0.116,
+      "step": 12000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9833774639599883,
+      "eval_loss": 0.09704861044883728,
+      "eval_runtime": 6.9946,
+      "eval_samples_per_second": 971.892,
+      "eval_steps_per_second": 3.86,
+      "step": 12776
+    },
+    {
+      "epoch": 8.140262993112085,
+      "grad_norm": 2.212705373764038,
+      "learning_rate": 1.0331872260488417e-05,
+      "loss": 0.1113,
+      "step": 13000
+    },
+    {
+      "epoch": 8.766437069505322,
+      "grad_norm": 3.2522332668304443,
+      "learning_rate": 6.853127391637097e-06,
+      "loss": 0.0995,
+      "step": 14000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9845542806707855,
+      "eval_loss": 0.08534605801105499,
+      "eval_runtime": 6.7022,
+      "eval_samples_per_second": 1014.3,
+      "eval_steps_per_second": 4.029,
+      "step": 14373
+    },
+    {
+      "epoch": 9.39261114589856,
+      "grad_norm": 6.198681354522705,
+      "learning_rate": 3.3743825227857787e-06,
+      "loss": 0.0985,
+      "step": 15000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9838187702265372,
+      "eval_loss": 0.08294928818941116,
+      "eval_runtime": 6.7918,
+      "eval_samples_per_second": 1000.911,
+      "eval_steps_per_second": 3.975,
+      "step": 15970
+    },
+    {
+      "epoch": 10.0,
+      "step": 15970,
+      "total_flos": 4.6387626201984e+18,
+      "train_loss": 0.22964708045190324,
+      "train_runtime": 1401.6538,
+      "train_samples_per_second": 364.527,
+      "train_steps_per_second": 11.394
+    }
+  ],
+  "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 sha256:4163bf7dd5d5be42c1b50a5088f847d384f3a5c385f61bc45011a7e48dc998a0
+size 5112