End of training

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+base_model: Kkonjeong/wav2vec2-base-korean
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: audio_kor
+  results: []
+---
+
+<!-- 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. -->
+
+# audio_kor
+
+This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3679
+- Accuracy: 0.9496
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.6342        | 1.0   | 30   | 2.6301          | 0.0588   |
+| 2.4757        | 2.0   | 60   | 2.3899          | 0.3109   |
+| 1.9266        | 3.0   | 90   | 1.8527          | 0.6134   |
+| 1.5614        | 4.0   | 120  | 1.4405          | 0.7227   |
+| 0.9955        | 5.0   | 150  | 1.0447          | 0.8655   |
+| 0.6666        | 6.0   | 180  | 0.7428          | 0.9076   |
+| 0.4623        | 7.0   | 210  | 0.5859          | 0.9160   |
+| 0.334         | 8.0   | 240  | 0.4750          | 0.9244   |
+| 0.2673        | 9.0   | 270  | 0.3788          | 0.9496   |
+| 0.196         | 10.0  | 300  | 0.3679          | 0.9496   |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,149 @@
+{
+  "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": 0.0,
+  "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": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "abroad",
+    "1": "address",
+    "10": "high_value_payment",
+    "11": "joint_account",
+    "12": "latest_transactions",
+    "13": "pay_bill",
+    "2": "app_error",
+    "3": "atm_limit",
+    "4": "balance",
+    "5": "business_loan",
+    "6": "card_issues",
+    "7": "cash_deposit",
+    "8": "direct_debit",
+    "9": "freeze"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "abroad": "0",
+    "address": "1",
+    "app_error": "2",
+    "atm_limit": "3",
+    "balance": "4",
+    "business_loan": "5",
+    "card_issues": "6",
+    "cash_deposit": "7",
+    "direct_debit": "8",
+    "freeze": "9",
+    "high_value_payment": "10",
+    "joint_account": "11",
+    "latest_transactions": "12",
+    "pay_bill": "13"
+  },
+  "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": 53,
+  "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
+  ],
+  "transformers_version": "4.56.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 56,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f07f2be62f6c683da9854335415fb797dfc10fa77e815699941dcdf9c26ba4
+size 378314704

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/Sep18_21-43-29_577eea9f1c0c/events.out.tfevents.1758231809.577eea9f1c0c.9322.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6fd3d503fd2f195e39c41a63771ca17323a2f7364f2951ffac602d2018795a
+size 17230

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338c0c5a2447e23868b77cca641532a7fb33e38d36ef6cc2a0c8317705457460
+size 5777