Training in progress, step 100

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
@@ -50,23 +50,23 @@
   "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": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "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_time_length": 10,
   "mask_time_min_masks": 2,
-  "mask_time_prob": 0.05,
+  "mask_time_prob": 0.075,
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a960726c5902bff059f746cb94d4779f81e35a344c4ce3b774301ab790cb8c71
+oid sha256:89bdbf42c65faeecd3cea5f97b2e9ca8ce971aeeb1eabd54874427e598701618
 size 1262073980

runs/Jan25_12-39-29_6ff5401fad7f/events.out.tfevents.1706186397.6ff5401fad7f.515.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b6fa5f78209db01215d8de31542ed2e3279a9c846e03335287e9ffd89b5678
+size 5957

runs/Jan25_12-40-40_6ff5401fad7f/events.out.tfevents.1706186482.6ff5401fad7f.515.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d103f05883408dcb2e166c320d5bf3fcc8e09c80f00115affaf255291101dbdf
+size 6423

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2f0755d97657f16a1260c302f26d8c5d6feb80adccbbc9eb0310f71ae5e8c5
+oid sha256:f1285f96b965ff6db64782723d54731f29d135c830fd256c0ae4038041aa42d8
 size 4792