Training in progress, step 400

config.json

@@ -5,11 +5,11 @@
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": true,
-  "apply_spec_augment": false,
+  "apply_spec_augment": true,
   "architectures": [
     "Wav2Vec2BertForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 768,
   "codevector_dim": 768,
@@ -25,19 +25,19 @@
   "feature_projection_input_dim": 160,
   "final_dropout": 0.1,
   "hidden_act": "swish",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "left_max_position_embeddings": 64,
   "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": 0.0,
+  "mask_time_prob": 0.05,
   "max_source_positions": 5000,
   "model_type": "wav2vec2-bert",
   "num_adapter_layers": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905f313ae645b4cfb3177e27d073c0865b4cbbb9d2e7ae1d03da451dae0d25ca
-size 2423072860
+oid sha256:f1e6b972a91585c3c9de2f95d07e939af58b7f23314143c8657bbf427a76fb62
+size 2423077060

runs/May12_22-43-14_8743e80baaf9/events.out.tfevents.1715554005.8743e80baaf9.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c310a93936d26f06fe0faa63f089c509c416b7693ba93b936a76c46228ded98d
+size 6422

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b63473cdd781b26b1654b187835fc666729e6c042d55b1a3f3c480ce8d6a2b
+oid sha256:23230d320f127b143427d48b77910baa31c7f474470b8f9aef4d759efdcba7f5
 size 4920