Training in progress, step 250

config.json

@@ -8,7 +8,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 1024,
@@ -49,23 +49,23 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_size": 1280,
   "initializer_range": 0.02,
   "intermediate_size": 5120,
   "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,
+  "mask_feature_prob": 0.2,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
+  "mask_time_prob": 0.2,
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f505ab45922efbd6570632585332e8b989759262a5fd421c906957783623a06
+oid sha256:0a2de10d8350d39fdd2ff14c4a304e491711bc753a28057c1365bbe927a978e7
 size 3850500973

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c991c355319ff363d9ed4033f0b6995bd071af6ab2b3798a148e4c2ea28788ed
+oid sha256:2d6fcd8e2662eaceb2f0465aabdeca83e81380033bb7a99a49d313e98e1e0f53
 size 3579