Training in progress, step 500

config.json

@@ -6,7 +6,7 @@
   "dim_feedforward": 1024,
   "dropout": 0.1,
   "input_dim": 30000,
-  "max_seq_len": 500,
+  "max_seq_len": 2000,
   "model_type": "transformer",
   "nhead": 8,
   "num_decoder_layers": 4,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1cd76c123ead5ba779f4d844e96b3e7ede0aee9bdf70e3a4bbe488e22a96fb
-size 208162576
+oid sha256:3c6c9d0205414ccd62e8afa37cf2582e4b1831013e7890b90153c660de00654b
+size 211234576