Training in progress, step 6132

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,
@@ -42,7 +42,7 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
+  "ctc_loss_reduction": "mean",
   "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": 0.1,
+  "hidden_dropout": 0.0,
   "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 sha256:97bab9c237c61422cea19f5a99e17969667c0ea52f4df6bdb7cf64e08608b7b1
+oid sha256:0a9c6a7d1c1729c62d390cd7c4a4d2eb702925ee6cd521bfe22559bf5015c97b
 size 377801840

runs/Aug06_07-04-35_c8578e0916a8/events.out.tfevents.1722928355.c8578e0916a8.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9388429e6771811fb645c79dfdb67dc3d1f8378307d10ca4cd51e9c7c6b23b7
-size 17111
+oid sha256:124cc645e54ca80752a6c3b2be044ddedd2ec539b2c763fa8794b6bfbbbc0e37
+size 17640

training_args.bin

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