Training in progress, epoch 0

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "ntu-spml/distilhubert",
+  "_name_or_path": "facebook/hubert-base-ls960",
   "activation_dropout": 0.1,
-  "apply_spec_augment": false,
+  "apply_spec_augment": true,
   "architectures": [
     "HubertForSequenceClassification"
   ],
@@ -41,12 +41,15 @@
   "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": 0.0,
-  "feat_proj_layer_norm": false,
-  "final_dropout": 0.0,
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "door_close",
@@ -63,7 +66,7 @@
     "unknown": "3"
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -75,8 +78,9 @@
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
   "num_feat_extract_layers": 7,
-  "num_hidden_layers": 2,
+  "num_hidden_layers": 12,
   "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 sha256:4ebe4edf1bd3d6f0874b033d97791583fbbeaf5402cbefa3668f3ffee4f21fa9
-size 94765560
+oid sha256:5fdc2afbc9acd4455e747840c771770f88dfc53a9892eb40030f197f6bf95229
+size 378304000

preprocessor_config.json

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

runs/Apr29_11-41-18_voice-ai-transformer/events.out.tfevents.1714390880.voice-ai-transformer.28731.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6549f41500c8190a582e32eaf2c1410d10b3fabeaf2edeabe654a194792960cb
+size 16684

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8847d1dd99f3dcf88fc1f81ba6f07d32b982baa30c2383aa3b6f730367d010ce
+oid sha256:e0e634555a4856479fc2cae8d8e61de016e0b69acde2b7d74bd417a4e19fc481
 size 4920