Upload 9 files

all_results.json

@@ -0,0 +1,23 @@
+{
+    "Test_accuracy": 0.9127700492721479,
+    "Test_f1": 0.9490780955502744,
+    "Test_loss": 0.6264140009880066,
+    "Test_precision": 0.9958726009493017,
+    "Test_recall": 0.9064838295607527,
+    "Test_runtime": 2422.3743,
+    "Test_samples_per_second": 29.408,
+    "Test_steps_per_second": 3.676,
+    "Validation_accuracy": 0.9936000644018677,
+    "Validation_f1": 0.9964463714994524,
+    "Validation_loss": 0.03715996816754341,
+    "Validation_precision": 0.993094845636388,
+    "Validation_recall": 0.9998205956225332,
+    "Validation_runtime": 826.7883,
+    "Validation_samples_per_second": 30.049,
+    "Validation_steps_per_second": 3.757,
+    "epoch": 3.0,
+    "train_loss": 0.018408857664295824,
+    "train_runtime": 8357.6191,
+    "train_samples_per_second": 9.11,
+    "train_steps_per_second": 1.139
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Bonafide",
+    "1": "Spoof"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Bonafide": "0",
+    "Spoof": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2"
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "Validation_accuracy": 0.9936000644018677,
+    "Validation_f1": 0.9964463714994524,
+    "Validation_loss": 0.03715996816754341,
+    "Validation_precision": 0.993094845636388,
+    "Validation_recall": 0.9998205956225332,
+    "Validation_runtime": 826.7883,
+    "Validation_samples_per_second": 30.049,
+    "Validation_steps_per_second": 3.757,
+    "epoch": 3.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8c7cd04c6b81a4f02756cbef777662d0092cf33ab23b14eea0df74c7978db6
+size 344790040

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "ASTFeatureExtractor",
+  "feature_size": 1,
+  "max_length": 1024,
+  "mean": -4.2677393,
+  "num_mel_bins": 128,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "std": 4.5689974
+}

test_results.json

@@ -0,0 +1,11 @@
+{
+    "Test_accuracy": 0.9127700492721479,
+    "Test_f1": 0.9490780955502744,
+    "Test_loss": 0.6264140009880066,
+    "Test_precision": 0.9958726009493017,
+    "Test_recall": 0.9064838295607527,
+    "Test_runtime": 2422.3743,
+    "Test_samples_per_second": 29.408,
+    "Test_steps_per_second": 3.676,
+    "epoch": 3.0
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.018408857664295824,
+    "train_runtime": 8357.6191,
+    "train_samples_per_second": 9.11,
+    "train_steps_per_second": 1.139
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.03715996816754341,
+  "best_model_checkpoint": "../res/Transformers/my-MIT/ast-finetuned-audioset-10-10-0.4593/checkpoint-3173",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9519,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7373673705221136e-05,
+      "loss": 0.1373,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.4747347410442276e-05,
+      "loss": 0.0621,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.212102111566341e-05,
+      "loss": 0.0267,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.949469482088455e-05,
+      "loss": 0.0179,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.686836852610568e-05,
+      "loss": 0.0263,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.424204223132682e-05,
+      "loss": 0.023,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9936000644018677,
+      "eval_f1": 0.9964463714994524,
+      "eval_loss": 0.03715996816754341,
+      "eval_precision": 0.993094845636388,
+      "eval_recall": 0.9998205956225332,
+      "eval_runtime": 842.329,
+      "eval_samples_per_second": 29.494,
+      "eval_steps_per_second": 3.687,
+      "step": 3173
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.1615715936547956e-05,
+      "loss": 0.0117,
+      "step": 3500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.8989389641769092e-05,
+      "loss": 0.0031,
+      "step": 4000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.636306334699023e-05,
+      "loss": 0.0139,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.373673705221137e-05,
+      "loss": 0.0027,
+      "step": 5000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.1110410757432505e-05,
+      "loss": 0.0051,
+      "step": 5500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8484084462653642e-05,
+      "loss": 0.0062,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.990259217517308,
+      "eval_f1": 0.9946013474322938,
+      "eval_loss": 0.059568725526332855,
+      "eval_precision": 0.9894363071460275,
+      "eval_recall": 0.9998205956225332,
+      "eval_runtime": 825.5791,
+      "eval_samples_per_second": 30.093,
+      "eval_steps_per_second": 3.762,
+      "step": 6346
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.585775816787478e-05,
+      "loss": 0.01,
+      "step": 6500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3231431873095915e-05,
+      "loss": 0.0014,
+      "step": 7000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.060510557831705e-05,
+      "loss": 0.0,
+      "step": 7500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.978779283538187e-06,
+      "loss": 0.0017,
+      "step": 8000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.352452988759324e-06,
+      "loss": 0.0006,
+      "step": 8500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.7261266939804603e-06,
+      "loss": 0.0005,
+      "step": 9000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 9.98003992015968e-08,
+      "loss": 0.0,
+      "step": 9500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.993237803896313,
+      "eval_f1": 0.9962466487935657,
+      "eval_loss": 0.05327658727765083,
+      "eval_precision": 0.9925213675213675,
+      "eval_recall": 1.0,
+      "eval_runtime": 825.5991,
+      "eval_samples_per_second": 30.092,
+      "eval_steps_per_second": 3.762,
+      "step": 9519
+    },
+    {
+      "epoch": 3.0,
+      "step": 9519,
+      "total_flos": 5.160985429530378e+18,
+      "train_loss": 0.018408857664295824,
+      "train_runtime": 8357.6191,
+      "train_samples_per_second": 9.11,
+      "train_steps_per_second": 1.139
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9519,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.160985429530378e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef60a9f0c77b38b73dffda19f54b55ac2666094a315e4644c8f15fc4f11207d
+size 4664