End of training

README.md

@@ -0,0 +1,51 @@
+---
+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 the None 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: 4
+- total_train_batch_size: 32
+- 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
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,135 @@
+{
+  "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": "\u1107\u1162\u1100\u1169\u1111\u1161",
+    "1": "\u110b\u1161\u11ab\u1102\u1167\u11bc",
+    "2": "\u1100\u1169\u11bc\u1107\u1162\u11a8",
+    "3": "\u110b\u1161\u11af\u1109\u116e\u110b\u1165\u11b9\u110b\u1173\u11b7",
+    "4": "\u110c\u1161\u11af\u1100\u1161",
+    "5": "\u110b\u116f\u11af\u110b\u116d\u110b\u1175\u11af",
+    "6": "\u1112\u1169\u11b7\u1105\u1165\u11ab"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u1100\u1169\u11bc\u1107\u1162\u11a8": 2,
+    "\u1107\u1162\u1100\u1169\u1111\u1161": 0,
+    "\u110b\u1161\u11ab\u1102\u1167\u11bc": 1,
+    "\u110b\u1161\u11af\u1109\u116e\u110b\u1165\u11b9\u110b\u1173\u11b7": 3,
+    "\u110b\u116f\u11af\u110b\u116d\u110b\u1175\u11af": 5,
+    "\u110c\u1161\u11af\u1100\u1161": 4,
+    "\u1112\u1169\u11b7\u1105\u1165\u11ab": 6
+  },
+  "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": "4.57.3",
+  "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 sha256:62404c3fe486a00d4d7dccbacb9a5f0a40b1e8c77316395196f8ffdfb3bbf7ae
+size 378307508

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/Dec09_05-49-39_d5e35a2082f7/events.out.tfevents.1765259393.d5e35a2082f7.239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97d8524f35e7822b0bda9cb0147792446e6fd0f098717bcf05606395528dc8c
+size 88

runs/Dec10_05-33-55_1794e34f222e/events.out.tfevents.1765345033.1794e34f222e.781.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b2225bcc2151fc3f1364d5926e3fa63c3475a886f92e16268cbbddec47cbbc
+size 11011

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7181bed0b8fe29fecccaed720fd094fd5bc00e6474d5a51bcc15e21abfad9f7b
+size 5841