Training in progress, step 40

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,
@@ -50,17 +50,17 @@
   "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,
@@ -78,7 +78,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 150,
+  "pad_token_id": 153,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -104,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 153,
+  "vocab_size": 156,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df95be15103e2af22dc0f79bba224c1a97c228f753fdd4ae94a9e5b0f863c3a
-size 1262434780
+oid sha256:ada82e336aac448c1e8ad5bede6118d93655a045993018a044b9df52d9090e2b
+size 1262447080

runs/Jun20_17-35-39_7555bebe1242/events.out.tfevents.1718904965.7555bebe1242.767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b992fbce30b2f540e88ead62942f9a7b6c979ddc85ada27f14aadda9104424
+size 6868

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e7394e0107189f7bba150f9e29f91b9c52fc70b61969b6a94be1981e86fa56
+oid sha256:368ce84727ecf6f56e232ab1f05e51ad1bb9b82e20dd2667a67d2850d6808726
 size 5112