Training in progress, step 300

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,
@@ -55,12 +55,12 @@
   "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": 66,
+  "pad_token_id": 63,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -104,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.33.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 68,
+  "vocab_size": 66,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1fab6413c4667e8e61499a710ee29c56cb9164ca39cd222dafc9d2a7c3e308
-size 1262180653
+oid sha256:6dcb31cdc5ae04051653ad17f3e68aaf572b1ca32d6ef34453e2e18cd6022fe6
+size 1262172461

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a387b09b72ab0f5e3cf802b7d24032982a7ba6a48b504d3dcdfe34c83a8c91c5
+oid sha256:ba2c75a2ae554e1c46e400b58d8b91391c6ab8c243e2e90fb6e343b8b07b2436
 size 4027