Training in progress, epoch 1

config.json

@@ -1,145 +1,35 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "ASTForAudioClassification"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
-  "conv_dim": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "conv_kernel": [
-    10,
-    3,
-    3,
-    3,
-    3,
-    2,
-    2
-  ],
-  "conv_stride": [
-    5,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2
-  ],
-  "ctc_loss_reduction": "sum",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "yes",
-    "1": "no",
-    "10": "_silence_",
-    "11": "_unknown_",
-    "2": "up",
-    "3": "down",
-    "4": "left",
-    "5": "right",
-    "6": "on",
-    "7": "off",
-    "8": "stop",
-    "9": "go"
+    "0": 0,
+    "1": 1,
+    "2": 2
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "_silence_": "10",
-    "_unknown_": "11",
-    "down": "3",
-    "go": "9",
-    "left": "4",
-    "no": "1",
-    "off": "7",
-    "on": "6",
-    "right": "5",
-    "stop": "8",
-    "up": "2",
-    "yes": "0"
+    "0": 0,
+    "1": 1,
+    "2": 2
   },
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "mask_channel_prob": 0.0,
-  "mask_channel_selection": "static",
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_min_space": 1,
-  "mask_time_other": 0.0,
-  "mask_time_prob": 0.05,
-  "mask_time_selection": "static",
-  "model_type": "wav2vec2",
-  "no_mask_channel_overlap": false,
-  "no_mask_time_overlap": false,
-  "num_adapter_layers": 3,
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
   "num_hidden_layers": 12,
-  "num_negatives": 100,
-  "output_hidden_size": 768,
-  "pad_token_id": 0,
-  "proj_codevector_dim": 256,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
   "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "transformers_version": "4.29.2"
 }

preprocessor_config.json

@@ -1,9 +1,13 @@
 {
   "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "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
+  "sampling_rate": 16000,
+  "std": 4.5689974
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ca39ea8eb624711f8fa128d64ee753f1e7404f6d3d90a9b71d22478936152f
-size 378360681
+oid sha256:dc154f6e9ff52824f0ba5b404aa73b1f1efea8debdd2e8f4ac5290e90feace04
+size 344838521

runs/Jun07_21-04-58_0adb498764d4/1686172007.7435746/events.out.tfevents.1686172007.0adb498764d4.4095.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f830634b9321768aad74d554532fb7befb160f7bbda008db5630e23e60e994
+size 6022

runs/Jun07_21-04-58_0adb498764d4/1686172491.041992/events.out.tfevents.1686172491.0adb498764d4.4095.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05bf7887fa9956aae9a8bdcc2da0f8a939cf5532c0f586986799c30195aef686
+size 6022

runs/Jun07_21-04-58_0adb498764d4/1686172531.6331587/events.out.tfevents.1686172531.0adb498764d4.4095.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a2db14a5fb9fdbef2efc4806232f5f7ad4e8e2c0d44fbc8bb10f62a426451c
+size 6022

runs/Jun07_21-04-58_0adb498764d4/events.out.tfevents.1686172007.0adb498764d4.4095.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2b53f0c032709012a3546e7e71e924bb8bfd6de8434e4b0c7aa8c3dc7365d6
+size 12567

runs/Jun07_21-17-20_0adb498764d4/1686172662.9060242/events.out.tfevents.1686172662.0adb498764d4.4095.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0337961cee720a0f50816473d2859f1b8c4bea594bd09c1206551172a954b109
+size 6022

runs/Jun07_21-17-20_0adb498764d4/events.out.tfevents.1686172662.0adb498764d4.4095.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d54feb46d288a2fc2f20d6fb36bbf8dfd48e0100d30a47dea492ff2df8d51a
+size 5351

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253e0a4f11d111b042589faf208efc626e3fe8add36ceed0f5e31f9bd74ad45c
+oid sha256:7ad833d0bd8ee15659a327b392fe09223dbbcf3e99483a8ebbd0e086df5e0d93
 size 3963