Training in progress, epoch 1

config.json

@@ -1,173 +1,44 @@
 {
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "apply_spec_augment": false,
   "architectures": [
-    "WhisperForAudioClassification"
-  ],
-  "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
-  "bos_token_id": 50257,
-  "classifier_proj_size": 256,
-  "d_model": 512,
-  "decoder_attention_heads": 8,
-  "decoder_ffn_dim": 2048,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
+    "ASTForAudioClassification"
   ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
-    "0": "hungry",
+    "0": "burping",
     "1": "scared",
-    "2": "cold_hot",
-    "3": "burping",
-    "4": "belly_pain",
-    "5": "discomfort",
-    "6": "lonely",
-    "7": "tired"
+    "2": "discomfort",
+    "3": "lonely",
+    "4": "cold_hot",
+    "5": "tired",
+    "6": "hungry",
+    "7": "belly_pain"
   },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
-    "belly_pain": "4",
-    "burping": "3",
-    "cold_hot": "2",
-    "discomfort": "5",
-    "hungry": "0",
-    "lonely": "6",
+    "belly_pain": "7",
+    "burping": "0",
+    "cold_hot": "4",
+    "discomfort": "2",
+    "hungry": "6",
+    "lonely": "3",
     "scared": "1",
-    "tired": "7"
+    "tired": "5"
   },
-  "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,
-  "max_length": 448,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "median_filter_width": 7,
-  "model_type": "whisper",
-  "num_hidden_layers": 6,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": false,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
+  "num_attention_heads": 12,
+  "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": "4.52.4",
-  "use_cache": true,
-  "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "transformers_version": "4.52.4"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45b426cec55329f7cb8c7ce0f5af098591967dad8bab72293e4bcb7e52742c9
-size 82906440
+oid sha256:e4cf990910d20bef5468f1e83e5b60a4c81d828c23459345584f8be07372b9d2
+size 344808496

runs/Jun20_07-15-42_DESKTOP-BONDT02/events.out.tfevents.1750418151.DESKTOP-BONDT02

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4901ae860f473c36ef1bc7d97ac44b6165bfea383dee0220c42df9bbc99496f6
+size 7953

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1db48c5f9f860b216e2cf14a586dfb4f184790c112455046045b54419de77ec0
+oid sha256:2b1ab4b9527e861a4829334813f8dbfeb88a0681001b5b3548b71e76fb593f9d
 size 5777