End of training

README.md

@@ -4,6 +4,11 @@ license: bsd-3-clause
 base_model: MIT/ast-finetuned-audioset-10-10-0.4593
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
 model-index:
 - name: ast_classifier
   results: []
@@ -16,16 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.7174
-- eval_accuracy: 0.7822
-- eval_precision: 0.9937
-- eval_recall: 0.5860
-- eval_f1: 0.7373
-- eval_runtime: 124.9206
-- eval_samples_per_second: 12.312
-- eval_steps_per_second: 1.545
-- epoch: 4.0
-- step: 344
+- Loss: 1.5481
+- Accuracy: 0.7269
+- Precision: 0.6416
+- Recall: 0.9728
+- F1: 0.7732
 
 ## Model description
 
@@ -45,16 +45,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - 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
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.4304        | 1.0   | 172  | 0.3436          | 0.8563   | 0.8231    | 0.8913 | 0.8558 |
+| 0.2198        | 2.0   | 344  | 1.0337          | 0.6684   | 0.5922    | 0.9864 | 0.7401 |
+| 0.1219        | 3.0   | 516  | 0.5469          | 0.8069   | 0.7180    | 0.9823 | 0.8296 |
+| 0.0818        | 4.0   | 688  | 1.2336          | 0.7295   | 0.6455    | 0.9647 | 0.7734 |
+| 0.0317        | 5.0   | 860  | 1.5481          | 0.7269   | 0.6416    | 0.9728 | 0.7732 |
+
 
 ### Framework versions
 
 - Transformers 4.57.2
 - Pytorch 2.9.0+cu126
-- Datasets 4.0.0
+- Datasets 3.6.0
 - Tokenizers 0.22.1

config.json

@@ -9,14 +9,14 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "dysarthria",
-    "1": "healthy"
+    "0": "healthy",
+    "1": "dysarthria"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "dysarthria": "0",
-    "healthy": "1"
+    "dysarthria": "1",
+    "healthy": "0"
   },
   "layer_norm_eps": 1e-12,
   "max_length": 1024,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd42c193b26796b87a40f21c7e3aac7ea3e5399f9141506793fba5b764a494a
+oid sha256:2280b1d6be74b92a941ce8a22e808de59e916db39349432c05d7660e1062de2d
 size 344790040

preprocessor_config.json

@@ -3,11 +3,11 @@
   "feature_extractor_type": "ASTFeatureExtractor",
   "feature_size": 1,
   "max_length": 1024,
-  "mean": -4.2677393,
+  "mean": -0.001125154090066851,
   "num_mel_bins": 128,
   "padding_side": "right",
   "padding_value": 0.0,
   "return_attention_mask": false,
   "sampling_rate": 16000,
-  "std": 4.5689974
+  "std": 0.0817532326695309
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7d31cc3d6652b979acd9abb70a0d5b86f4ec127ed607e6af910cdcb2c1e1fe
+oid sha256:cd1f416d1d2ecec55b151b236e7d9f479117dc4f71aa938675002f6429a0b7fb
 size 5841