Training in progress, epoch 1

config.json

@@ -1,52 +1,12 @@
 {
-  "_name_or_path": "ntu-spml/distilhubert",
-  "activation_dropout": 0.1,
-  "apply_spec_augment": false,
+  "_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_norm": "group",
-  "feat_proj_dropout": 0.0,
-  "feat_proj_layer_norm": false,
-  "final_dropout": 0.0,
+  "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": "Negative",
@@ -60,23 +20,16 @@
     "Neutral": "1",
     "Positive": "2"
   },
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "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": 2,
-  "pad_token_id": 0,
+  "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": "4.34.1",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32
+  "transformers_version": "4.34.1"
 }

preprocessor_config.json

@@ -1,9 +1,13 @@
 {
-  "do_normalize": false,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "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,
+  "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 sha256:96c16dd3800081686f20ea851ea0b1c682c8b2177bd57337f3df2c6b5c87ce9d
-size 94776717
+oid sha256:805eab444ef15f8ea85b6e11716f5450952f6937c3fe7dd44e42bdbb4df5b659
+size 344838966

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4685687442529a1a4750bc3f98770f8890dc051a5eee97cf26ecdb6959a9336d
+oid sha256:6ac36728dd0ceba9f6b3b9289555af68436b3b7a9240727dc29c10eab3843a2c
 size 4536