End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: motheecreator/wav2vec2-base-finetuned-ks
+tags:
+- generated_from_trainer
+datasets:
+- audiofolder
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-base-finetuned-ks
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: audiofolder
+      type: audiofolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.999056010069226
+---
+
+<!-- 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. -->
+
+# wav2vec2-base-finetuned-ks
+
+This model is a fine-tuned version of [motheecreator/wav2vec2-base-finetuned-ks](https://huggingface.co/motheecreator/wav2vec2-base-finetuned-ks) on the audiofolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0062
+- Accuracy: 0.9991
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0107        | 1.0   | 198  | 0.0164          | 0.9969   |
+| 0.0091        | 2.0   | 397  | 0.0055          | 0.9987   |
+| 0.0007        | 3.0   | 596  | 0.0062          | 0.9991   |
+| 0.0065        | 4.0   | 795  | 0.0068          | 0.9987   |
+| 0.0001        | 4.98  | 990  | 0.0066          | 0.9984   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,126 @@
+{
+  "_name_or_path": "motheecreator/wav2vec2-base-finetuned-ks",
+  "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,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "fake",
+    "1": "real"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fake": "0",
+    "real": "1"
+  },
+  "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": "4.39.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06cba2b45823bfffcdddbdfdab61564be9bbd40ae6b1bd156ddce73c6daadd2
+size 378302360

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": false,
+  "sampling_rate": 16000
+}

runs/Apr19_12-09-58_0bc7c83639a2/events.out.tfevents.1713528599.0bc7c83639a2.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8034460d791bebd6bec2354312a7ddf41a556194dfaf07554a7f480f7cb5234
+size 13139

runs/Apr19_12-09-58_0bc7c83639a2/events.out.tfevents.1713528806.0bc7c83639a2.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf6e5aa9261c2c81b90f6e56af7a9abfcc5b2a5292fc86bc0ebbee96497c924
+size 19768

runs/Apr19_12-38-00_d6f2972d64ae/events.out.tfevents.1713530282.d6f2972d64ae.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2d7893665d04f54044ff4227b90d6d96868d92f28066145d85c09c8597c067
+size 25267

runs/Apr19_19-27-52_7ec0840e32e2/events.out.tfevents.1713554873.7ec0840e32e2.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31cb08d0241ba8defa1994d5b97b3d1e9fca59ea13e599a2aa9f49c5efd0065
+size 29319

runs/Apr19_19-27-52_7ec0840e32e2/events.out.tfevents.1713565427.7ec0840e32e2.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a79a6f975db193102c8d94e3d49bd7cabd2a9878fe176c0c741fbf7e86aec6b
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a2d49f375c847558da06906e6442ea8970a7f7a741c48e7f4f33d943ccb7c8
+size 4984