Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 14,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "fake",
+    "1": "real"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fake": 0,
+    "real": 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": 14,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65edb884d8b1136684a9f02bc4bb8d81aaccb5cd04896adcbd6389a42e4477c
+size 343085080

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d74e2ef379ac512e571c96319d7534bf38357dfdeac9f28e688e1c96fc6fbe
+size 686282618

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
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30172cf14f5dbe00280d63e36224a9f28dc7a0e8b38a74ceb5eb284e84da363
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a527653df9efc4c6b1708ec34885cf2a485d45241e09e288ac34c4bdbe98864
+size 1064

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_global_step": 56,
+  "best_metric": 0.0,
+  "best_model_checkpoint": "./results/checkpoint-56",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.00856983382254839,
+      "learning_rate": 3.948598130841122e-05,
+      "loss": 0.1088,
+      "step": 56
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9914869466515324,
+      "eval_eer": 0.0,
+      "eval_f1": 0.9939491730536507,
+      "eval_loss": 0.06050656735897064,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9879711307137129,
+      "eval_runtime": 100.8612,
+      "eval_samples_per_second": 17.47,
+      "eval_steps_per_second": 0.278,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.007643812336027622,
+      "learning_rate": 2.6401869158878506e-05,
+      "loss": 0.0306,
+      "step": 112
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9971623155505108,
+      "eval_eer": 0.0,
+      "eval_f1": 0.9979991996798719,
+      "eval_loss": 0.018800094723701477,
+      "eval_precision": 0.9960063897763578,
+      "eval_recall": 1.0,
+      "eval_runtime": 100.5792,
+      "eval_samples_per_second": 17.519,
+      "eval_steps_per_second": 0.278,
+      "step": 112
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.009354319423437119,
+      "learning_rate": 1.3317757009345794e-05,
+      "loss": 0.0046,
+      "step": 168
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9994324631101021,
+      "eval_eer": 0.0,
+      "eval_f1": 0.9995991983967936,
+      "eval_loss": 0.008926239795982838,
+      "eval_precision": 0.999198717948718,
+      "eval_recall": 1.0,
+      "eval_runtime": 98.0214,
+      "eval_samples_per_second": 17.976,
+      "eval_steps_per_second": 0.286,
+      "step": 168
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.003849638160318136,
+      "learning_rate": 2.336448598130841e-07,
+      "loss": 0.0,
+      "step": 224
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_eer": 0.0,
+      "eval_f1": 1.0,
+      "eval_loss": 2.7062263541210996e-10,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 98.6428,
+      "eval_samples_per_second": 17.862,
+      "eval_steps_per_second": 0.284,
+      "step": 224
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 224,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.753709041220321e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72c088bdd7f58434d895609dfd78e5309052b6940a7fd9fbc5151e10b0b6ded
+size 5304