Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,49 @@
+{
+  "_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": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "9"
+  },
+  "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"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b948a914e39fad4e65020c5a428e98d9ef510b3c5699b312791549222200834
+size 344814656

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370a3783788e3426f46911174c6ecf5ee6c66358da5df6ada20646ce9f2ad264
+size 689741690

last-checkpoint/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
+}

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1556c40535abe1ed34e2654d4ee34ba195375d3a724579fc6d1e890cfd9ace7
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.83,
+  "best_model_checkpoint": "ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan/checkpoint-113",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.2123893805309734e-06,
+      "loss": 2.4617,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.424778761061947e-06,
+      "loss": 2.4041,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 6.6371681415929215e-06,
+      "loss": 2.1309,
+      "step": 15
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.849557522123894e-06,
+      "loss": 2.0045,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.1061946902654869e-05,
+      "loss": 1.7218,
+      "step": 25
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.3274336283185843e-05,
+      "loss": 1.3841,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5486725663716813e-05,
+      "loss": 1.1939,
+      "step": 35
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.7699115044247787e-05,
+      "loss": 0.9942,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.991150442477876e-05,
+      "loss": 1.1275,
+      "step": 45
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.2123893805309738e-05,
+      "loss": 0.8573,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.433628318584071e-05,
+      "loss": 0.5421,
+      "step": 55
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.6548672566371686e-05,
+      "loss": 0.7957,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.8761061946902656e-05,
+      "loss": 0.633,
+      "step": 65
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.097345132743363e-05,
+      "loss": 0.641,
+      "step": 70
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.3185840707964604e-05,
+      "loss": 1.0013,
+      "step": 75
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.5398230088495574e-05,
+      "loss": 0.8854,
+      "step": 80
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.7610619469026545e-05,
+      "loss": 0.788,
+      "step": 85
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.982300884955752e-05,
+      "loss": 0.5631,
+      "step": 90
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.20353982300885e-05,
+      "loss": 0.6124,
+      "step": 95
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.4247787610619477e-05,
+      "loss": 0.5238,
+      "step": 100
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.646017699115045e-05,
+      "loss": 0.852,
+      "step": 105
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.867256637168142e-05,
+      "loss": 1.0564,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.83,
+      "eval_loss": 0.6135080456733704,
+      "eval_runtime": 15.6818,
+      "eval_samples_per_second": 6.377,
+      "eval_steps_per_second": 0.829,
+      "step": 113
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1130,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6.094112254328832e+16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd3204646a00c780553338fc2836ce7154187014c3ec4854db595b9ae76337f
+size 4664