Training in progress, step 2628

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
@@ -49,12 +49,12 @@
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.0,
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ead64395ee67ba5f2a687e4ee5f39cd7aa5720bcd1baae3ea53fe5661f7496
+oid sha256:091645bed7d48b115081fcfaf9e8d85d68450222d15cdf3f70a4193c727868a1
 size 377801840

runs/Aug10_19-51-12_ab24b380fa73/events.out.tfevents.1723319907.ab24b380fa73.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbc4b0479c0d2928180e3963882992092fc70d3f5e748e4cab337ccbe223652
-size 10762
+oid sha256:8a676e492374111e93ba4dd14e84e1076e91e29251ff4822906a6db03ed3a988
+size 11291

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b715b3f08c51afb9ccc45130a863ab1667464f02192f9e55c9455226f09e0d
+oid sha256:4f1a1f7bb32db9dadedee0ad6d8c7d894ecb6c981bf171a096e173f087c783c5
 size 5112