Training in progress, step 500

config.json

@@ -17,7 +17,7 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 4,
   "decoder_start_token_id": 50258,
-  "dropout": 0.2,
+  "dropout": 0.0,
   "encoder_attention_heads": 6,
   "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006d014f8016d076b29501ca80411336dd0e4ff052703da55e8f60a0d5a34f6b
+oid sha256:f7aed46e17743bd6f95706e1ea103bc817cabd2d59e4553145b1eaf0d62ecf16
 size 151098921

run_speech_recognition_seq2seq_streaming.py

@@ -556,7 +556,7 @@ def main():
             elif isinstance(train_dataloader.dataset, IterableDataset):
                 train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
 
-    model.config.dropout=0.2
+    #model.config.dropout=0.2
     # Initialize Trainer
     trainer = Seq2SeqTrainer(
         model=model,

runs/Dec18_15-24-30_129-146-179-188/1671377088.3163862/events.out.tfevents.1671377088.129-146-179-188.130712.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fac1d75083fef3d1692f9e5fb94d2f57496a406280a31a582313ae8f4e08654
+size 5872

runs/Dec18_15-24-30_129-146-179-188/events.out.tfevents.1671377088.129-146-179-188.130712.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0648a70278db2b32d87f7a3c5a5a2452be7d8c867f7b8124652c555090d48840
+size 6148

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe94ef099a4a3b2b829dc44e8618397ff53dca3a1f192feca2b2d6fd1d4aa2f
+oid sha256:07b3a05bf2b7237e559d7740d7325f34aafffeb066f31b2c1e64d4d2e5b9610a
 size 3579