Training in progress, step 1460

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,
@@ -42,14 +42,14 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
+  "ctc_loss_reduction": "mean",
   "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": 0.0,
+  "feat_proj_dropout": 0.1,
   "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:af63405c0bd6ba83ea0c439c5a6f3dfa8e873a2bab69a00382a2feed9399600e
+oid sha256:a64d96e32fdc2bf38b5453a1dff229b570b3f7400b297051bdd8ee790ae0def8
 size 377801840

runs/Aug05_16-51-48_4c64bcfacc54/events.out.tfevents.1722877171.4c64bcfacc54.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cff58a6774f20034e8a5668c27d3452e2e7522b1303c1d0faa19e68b94ae123
-size 8647
+oid sha256:2a01c0413548fec911220a09d5844328811fe846ab89edf638d0e99ee02fdb07
+size 9176

training_args.bin

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