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,
@@ -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 sha256:6819916c45c06b95741e788ae7322e80fea178d974c6137dd6006c727d758266
+oid sha256:c15fc492cac317669c8d7bd4c170cc9b94d07675c30f6c985043688bf979422b
 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:b0b91ed67650484f10dcf06bd3bcb0715549c68d21bf69b03c7a7198e2869ed8
-size 10763
+oid sha256:c30e09a2105b237c52e602c23df32d23c985c3cc198f991a11d402c16c621e63
+size 11292

training_args.bin

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