Training in progress, epoch 1

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "Seq2SeqCrossFormer"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 1024,
+  "d_model": 256,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "model_size": 10731266,
+  "model_type": "custom_transformer",
+  "n_heads": 8,
+  "n_layers": 2,
+  "pad_token_id": 0,
+  "router_dim": 10,
+  "sequence_length": 256,
+  "source_sequence_dimension": 70,
+  "target_sequence_dimension": 306,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "vocab_size_src": 258,
+  "vocab_size_tgt": 258
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a8e3a86da2a96608cde03b5050de88b8a4f830fdf994319d183604f667b2c0
+size 42941496

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37b991f70ee7cf1f35bc346be3a47e3682d95a08d7c32ec1a8ac396317d96bd
+size 5304