Training in progress, step 500

config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0372cdd99db7f5a3d67fd6a24c46dd8a10ab37126bff57c27e039402ff88ca73
-size 211234576
+oid sha256:f5697c0090d51964aa60407efabcb34a7a3801c4b71ed3f7b271ac8cd1942617
+size 208162576