End of training

README.md

@@ -0,0 +1,52 @@
+---
+library_name: transformers
+base_model: Kkonjeong/wav2vec2-base-korean
+tags:
+- generated_from_trainer
+model-index:
+- name: audio_cls
+  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_cls
+
+This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on an unknown dataset.
+
+## 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
+
+### 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",
+    "2": "app_error",
+    "3": "atm_limit",
+    "4": "balance",
+    "5": "business_loan",
+    "6": "card_issues",
+    "7": "cash_deposit",
+    "8": "direct_debit",
+    "9": "freeze",
+    "10": "high_value_payment",
+    "11": "joint_account",
+    "12": "latest_transactions",
+    "13": "pay_bill"
+  },
+  "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 sha256:77b7f7faac11a745cd0c7e17f9e1c8df4bd1a256c138f23c2f286bb1b0cfe06d
+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/Sep22_03-16-31_206d7ebafda7/events.out.tfevents.1758510995.206d7ebafda7.188.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b446c41747b125e5cf6c218e355bf01f70f6a2ed77195e55cf40350cd824740
+size 8313

runs/Sep22_03-18-20_206d7ebafda7/events.out.tfevents.1758511101.206d7ebafda7.188.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d03b14db3dd7a0d99b6ee2dda3929bc1ba9526951ca7de9841d6ed7ccd9126
+size 8313

runs/Sep22_03-20-12_206d7ebafda7/events.out.tfevents.1758511213.206d7ebafda7.188.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303761ae98184e009a7c21d2ca2cb2b315d34ec6f9ff4df0c5c7ee35ff0d1f57
+size 88

runs/Sep22_05-30-45_246fc490ce96/events.out.tfevents.1758519047.246fc490ce96.146.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc8a1745af6f32e29a6f62bba95ec9a7d089b5aabc49b554db53f70244cd0c6
+size 7349

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa6e3a770b1ad756f0f521b9f023533b71c968d1b12242b7e6b707750e64a67
+size 5777