Training in progress, step 20

config.json

@@ -1,5 +1,5 @@
 {
-  "activation_dropout": 0.05,
+  "activation_dropout": 0.0,
   "adapter_attn_dim": 64,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -8,7 +8,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.05,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
@@ -49,23 +49,23 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.05,
+  "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.05,
+  "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": 0.1,
+  "layerdrop": 0.0,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.05,
+  "mask_feature_prob": 0.0,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
-  "mask_time_prob": 0.1,
+  "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 sha256:58514a40e5f3eaff56bbbc2317efacc7037d831303a58bfd368a4fc2d5af529b
+oid sha256:69b24ab30d7e68a19d91bf1153a7db14fbc99ca2ce42ae99b9e1ccc7770541ec
 size 1274889840

runs/Aug20_08-42-56_9aaae1e40cf3/events.out.tfevents.1724143531.9aaae1e40cf3.3167.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3272ab875aa600113f3f032668a825985a40f132177ccfcf003908a7db239261
+size 6911

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400fda15c81d0ae58221ce51ca3ccd1c78bcca629d39cfb50b8f0a786f1f03e0
+oid sha256:658cabcb557e2c3b4e7ad5b6c21399142dd31da356e3d772aae87c8642b60946
 size 5240