Training in progress, step 1460

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,
@@ -42,14 +42,14 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
+  "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
+  "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "freeze_feat_extract_train": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd2a4eaaad595540b58d9954d70e1e0bb1b2ec40c4e6b2a70c546a48eba8cf1
+oid sha256:5468263ce5b9896abd305a8d991d409d7bfdf5cba03cd71965ca72812f13c7cd
 size 377801840

runs/Aug05_16-30-25_f8d10c9e98ef/events.out.tfevents.1722875852.f8d10c9e98ef.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f53d9a9c028caaed616ca35e5522080a9c8ff8620c7b67dee88ff9bbf4c51e4
-size 8646
+oid sha256:2405ea28ab5b8a7309c0b998d746a4082c7df58a342357ba65889d83625b505d
+size 9175

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba678c11e2c999ddd7bfc71be819d5717ebdac9dfe81d84819461c07493d274
+oid sha256:4d223d67c6c5a4026531d66b7a0f80744bb975048c6ca4865c78923623ea43ef
 size 5112