Training in progress, step 400

config.json

@@ -5,7 +5,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.2,
+  "attention_dropout": 0.25,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
@@ -46,12 +46,12 @@
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.1,
+  "feat_proj_dropout": 0.2,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.2,
+  "hidden_dropout": 0.32,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
@@ -60,7 +60,7 @@
   "mask_feature_length": 10,
   "mask_feature_prob": 0.0,
   "mask_time_length": 10,
-  "mask_time_prob": 0.05,
+  "mask_time_prob": 0.23,
   "model_type": "wav2vec2",
   "num_attention_heads": 16,
   "num_codevector_groups": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2a56b99c8d185fc3468a904d378f4856d65049426d2a44eaa8a378af5eed8f
+oid sha256:6f19d51740e28b9ccee7ea8ed720e4584dd3c05418b4ded0c00472d63326eec1
 size 1262329585

runs/Feb05_14-23-02_job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0/1644071054.2847092/events.out.tfevents.1644071054.job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0.176352.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50393c8f0e92dde8b2b1d3bb984a15a6fefe7be6e0d3acdc5a0cff9e8b9685a
+size 4577

runs/Feb05_14-23-02_job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0/events.out.tfevents.1644071054.job-1cbb6c7a-d063-4cb3-ba22-bc0e2afc09f0.176352.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2656308ad040b0c780586ea3dc4cff76915888515db9a9ed961553a17d4aa358
+size 4710

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcb72465b8b80b56e2605dd3270d074138571a00ba90ef12d29a6514a8abebe
+oid sha256:9aae5ac7fa7845371126005fed154e5034424cc7c21acd6a206b057432d3ceed
 size 2863