Training in progress, epoch 4

config.json

@@ -3,7 +3,7 @@
     "ASTForAudioClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "frequency_stride": 12,
+  "frequency_stride": 10,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
@@ -60,7 +60,7 @@
     "white": "22"
   },
   "layer_norm_eps": 1e-12,
-  "max_length": 1024,
+  "max_length": 128,
   "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
@@ -68,7 +68,7 @@
   "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "time_stride": 12,
+  "time_stride": 10,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfca7e00a53abed21621e2bc2b86726762dffe2a0e124954b40a722349fb5e9
-size 343742580
+oid sha256:c647f6fe9f109946b0bb6e74f70510ecaa3b1f1d9e6604daae7756ffb62ac6e7
+size 341573740

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": 128,
+  "mean": -6.845978,
   "num_mel_bins": 128,
   "padding_side": "right",
   "padding_value": 0.0,
   "return_attention_mask": false,
   "sampling_rate": 16000,
-  "std": 4.5689974
+  "std": 5.5654526
 }

runs/Jun26_17-02-34_ip-10-192-12-85/events.out.tfevents.1750957371.ip-10-192-12-85.3951.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56793f768a1f7fe807e1c4a15b864d7f53ee56cf800fb14cfcf63cfeb5dc7a6a
+size 597542

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce00be80c434f25f6c17890f8524ed69f6ef80e58621df3b91e505c8ce8533c
+oid sha256:cb0a7df9621577fc307074892f83d4903caca15443bb9f3ab60d6e59fdc00359
 size 5777