Training in progress, step 500

config.json

@@ -5,7 +5,7 @@
   "architectures": [
     "HubertForCTC"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "conv_bias": true,
@@ -43,17 +43,17 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.1,
+  "feat_proj_dropout": 0.0,
   "feat_proj_layer_norm": true,
   "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout": 0.0,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
+  "layerdrop": 0.0,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -77,7 +77,7 @@
   "pad_token_id": 49,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.46.1",
   "use_weighted_layer_sum": false,
   "vocab_size": 52
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593a3846b864a2947ab83fb8c34d4d03057881a13ed1dbb2035a27cd069bf680
+oid sha256:e7004bd6e85ffd40bbfc52b026e90038572c3f36076b989afd3456b98069069f
 size 1262015656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4618f17cea2e788a595a6d2f30f9ba8551e8076261683cdec8455d4253442948
+oid sha256:7ea84a8cd5f2d47cf773edafd08d9bce4840d7b6777fb88835cb1451f90abfad
 size 5240