Training in progress, step 6132

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": 256,
@@ -42,7 +42,7 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
+  "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
@@ -54,7 +54,7 @@
   "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 sha256:0d752eb0502aebaf32e6f7dc7f7b3c73425d4560d31ffd3f314bd8d94e64494f
+oid sha256:97bab9c237c61422cea19f5a99e17969667c0ea52f4df6bdb7cf64e08608b7b1
 size 377801840

runs/Aug06_07-00-47_276efc170747/events.out.tfevents.1722928060.276efc170747.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375891e1becf3a6fb30f629831aaa624bb969938a802d1f20539b3ab4d3d1066
-size 17110
+oid sha256:c43d1349799b0c1d560c82c1506a5ff63ff112df3f6ba80e3a5b2c9ab13e78d4
+size 17639

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1458a0e52d0b175082ef9d29594de19cb715cbda485b5c590d06e85b3f0e60
+oid sha256:5911617781b51dd787115f65e46075021f1f5257874f61add50cb8dcf8a32722
 size 5112