Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
+  "_name_or_path": "abletobetable/spec_soul_ast",
   "architectures": [
     "ASTForAudioClassification"
   ],
@@ -29,7 +29,7 @@
     "sadness": 6
   },
   "layer_norm_eps": 1e-12,
-  "max_length": 1024,
+  "max_length": 2048,
   "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,

preprocessor_config.json

@@ -2,12 +2,12 @@
   "do_normalize": true,
   "feature_extractor_type": "ASTFeatureExtractor",
   "feature_size": 1,
-  "max_length": 1024,
-  "mean": -4.2677393,
+  "max_length": 2048,
+  "mean": -2.30462729231313e-05,
   "num_mel_bins": 128,
   "padding_side": "right",
   "padding_value": 0.0,
   "return_attention_mask": false,
   "sampling_rate": 16000,
-  "std": 4.5689974
+  "std": 0.041438196511772774
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a0824543bf1e83e622f549633c374c96f7c9b0708cb329618076dcce2a1637
-size 344850809
+oid sha256:752b19db76c9a62fc4e0c065faab1af020baf4e112dd060795da9e34f2393ecc
+size 348647801

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b788f08bad95be13d9eb1246636b7f98d483d0f74e8bbcc5a1b8a25c2a47919
+oid sha256:7f9692559c1043c3010bec62dab272651034330f6ec2c324d7cc4578f03cd0f3
 size 3579