Training in progress, epoch 1

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: cc-by-nc-sa-4.0
+base_model: amiriparian/ExHuBERT
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ExHubert-fine-tuned
+  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. -->
+
+# ExHubert-fine-tuned
+
+This model is a fine-tuned version of [amiriparian/ExHuBERT](https://huggingface.co/amiriparian/ExHuBERT) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4376
+- Accuracy: 0.8392
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7396        | 1.0   | 64   | 0.7444          | 0.6118   |
+| 0.6937        | 2.0   | 128  | 0.5704          | 0.7647   |
+| 0.4416        | 3.0   | 192  | 0.4876          | 0.8039   |
+| 0.5393        | 4.0   | 256  | 0.4376          | 0.8392   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,95 @@
+{
+  "_name_or_path": "amiriparian/ExHuBERT",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "ExHuBERT"
+  ],
+  "attention_dropout": 0.1,
+  "auto_map": {
+    "AutoModelForAudioClassification": "amiriparian/ExHuBERT--ExHuBERT_model.ExHuBERT"
+  },
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": true,
+  "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": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 48,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178938ad40bdd2cacc37c2c80b48a79eb59f4b7e21949b5b047fb949125bf1d6
+size 2673683572

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

runs/Dec21_13-24-25_8d0cb1931a2d/events.out.tfevents.1734787468.8d0cb1931a2d.7155.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3aa1e06d7e0e3829a65f4b3896d64f4211212079b585804d444e9eea528858
+size 88

runs/Dec21_13-45-53_8d0cb1931a2d/events.out.tfevents.1734788766.8d0cb1931a2d.7155.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4226d9fdad88276e1b6666377fbb4188d26eedb786b4eee974937bc066a70c35
+size 88

runs/Dec21_13-46-51_8d0cb1931a2d/events.out.tfevents.1734788823.8d0cb1931a2d.7155.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4fa2099634537a37dbd2ffc89c020681387f46237df599b5b9e41f1fc37c78
+size 88

runs/Dec21_13-55-45_4281c0c1b228/events.out.tfevents.1734789348.4281c0c1b228.239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b233bf2ea49c98667b0b54ca27e61afeac2d2d1ecc0b9dcca184a1e6fd063ff
+size 9251

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65189642066a7492b452de63baf4235f0e891ce4eacb3b7626b6237403c7542a
+size 5496