Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "dtype": "float32",
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "music",
+    "1": "speech"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "music": 0,
+    "speech": 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,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b54d7fbdfe90379eb5c6e06b69c8fd966b4987ecbd2a12bff6572ff9fc68e9
+size 344790040

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d6a98082bce598ab38d4922fa6116076d3e3e9d873b8b65b90f58d8bb97482
+size 689695819

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 sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0a0169ace6dd279a3e7a8647177302b908cfc09e3cba8855f72c9e93a3d829
+size 1465

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_global_step": 23,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "./balanced_music_detector_test/checkpoint-23",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 23,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.16175252199172974,
+      "learning_rate": 2.1e-05,
+      "loss": 0.3635,
+      "step": 10
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.025462472811341286,
+      "learning_rate": 6e-06,
+      "loss": 0.0011,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 1.0,
+      "eval_balanced_f1": 1.0,
+      "eval_false_music_rate": 0.0,
+      "eval_false_speech_rate": 0.0,
+      "eval_loss": 0.00011264843487879261,
+      "eval_music_f1": 1.0,
+      "eval_music_precision": 1.0,
+      "eval_music_recall": 1.0,
+      "eval_runtime": 5.1012,
+      "eval_samples_per_second": 100.956,
+      "eval_speech_f1": 1.0,
+      "eval_speech_precision": 1.0,
+      "eval_speech_recall": 1.0,
+      "eval_steps_per_second": 1.764,
+      "step": 23
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 23,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1.9758697829105664e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1993a0bbf38b33bad82209d3f327deab215e390f4aadfc7917eb0439b735299d
+size 5905