Training in progress, step 3212

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:c15fc492cac317669c8d7bd4c170cc9b94d07675c30f6c985043688bf979422b
+oid sha256:014103e3d4b7ce40eece1365a1feead0ab0d596df5764ea18f1418a16461af38
 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 sha256:314b9e98cdd80842192253beaea79a95667de48604d3887066ed6a3efcfbbf2b
-size 11820
+oid sha256:856f8134160581612cd34ce7e17a51282701a1edc8bbb6773929b07a51e21760
+size 12349

training_args.bin

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