Training in progress, epoch 0

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "anton-l/hubert-base-ft-keyword-spotting",
+  "_name_or_path": "ntu-spml/distilhubert",
   "activation_dropout": 0.1,
-  "apply_spec_augment": true,
+  "apply_spec_augment": false,
   "architectures": [
     "HubertForSequenceClassification"
   ],
@@ -41,31 +41,29 @@
   "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,
-  "finetuning_task": "audio-classification",
-  "gradient_checkpointing": false,
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "door_close",
     "1": "door_open",
-    "2": "unknown"
+    "2": "door_stop",
+    "3": "unknown"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "door_close": "0",
     "door_open": "1",
-    "unknown": "2"
+    "door_stop": "2",
+    "unknown": "3"
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "layerdrop": 0.0,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -77,9 +75,8 @@
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 2,
   "pad_token_id": 0,
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "use_weighted_layer_sum": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a4ed7608b5c40eaa7461dc023b80c03657e0d865ee4d0042e39292ec0c2e4a
-size 378302972
+oid sha256:7f61bf2aea467959508f9f78988da9d9046a19d62b8943407b3c6fadc1bcc7cc
+size 94765560

preprocessor_config.json

@@ -1,5 +1,5 @@
 {
-  "do_normalize": true,
+  "do_normalize": false,
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",

runs/Apr29_09-00-05_voice-ai-transformer/events.out.tfevents.1714381237.voice-ai-transformer.28731.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440810016b69587135767fe8c964773399c2a460cfac8eabd7033fc96bf534c4
+size 16567

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81cd465e43cbd1a7d2b093d60b3605051a21bfdc8e4a1d3d5fa9b0a0642a5308
+oid sha256:8847d1dd99f3dcf88fc1f81ba6f07d32b982baa30c2383aa3b6f730367d010ce
 size 4920