Training in progress, epoch 0

config.json

@@ -1,55 +1,12 @@
 {
-  "_name_or_path": "facebook/hubert-base-ls960",
-  "activation_dropout": 0.1,
-  "apply_spec_augment": true,
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
   "architectures": [
-    "HubertForSequenceClassification"
+    "ASTForAudioClassification"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "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,
-  "do_stable_layer_norm": false,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
-  "feat_proj_layer_norm": true,
-  "final_dropout": 0.1,
-  "gradient_checkpointing": false,
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
     "0": "Angry",
@@ -63,24 +20,16 @@
     "Happy": "1",
     "Neutral": "2"
   },
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
-  "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_prob": 0.05,
-  "model_type": "hubert",
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32
+  "transformers_version": "4.41.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d0e585ecde85fb95c35010ce951f2cc95ba5854b60338474dbe042a4a68b9c
-size 378302972
+oid sha256:56a658be7f8b405ff3ab4e393e86c39167347ec32ec93eb97a9e445a797a451e
+size 344793116

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,
+  "padding_value": 0.0,
   "return_attention_mask": false,
-  "sampling_rate": 16000
+  "sampling_rate": 16000,
+  "std": 4.5689974
 }

runs/May22_16-17-06_46f0275142c4/events.out.tfevents.1716394627.46f0275142c4.573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0da00d1eb0eb9ebfe369b89577f6b5059cbb605f4296ed23b57b6b52028ffc
+size 5316

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17d59399b4532af08bb569861baeaf424d7b1416f0e636b30b74cf565845393
-size 5048
+oid sha256:a48a1a29e264d066e00455e51968f04cf5b11d5010577471c959f53763cba86e
+size 5176