Training in progress, epoch 1

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "Seq2SeqCrossFormer"
+  ],
+  "batch_size": 4,
+  "bos_token_id": 1,
+  "d_ff": 16,
+  "d_model": 16,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "model_size": 105058,
+  "model_type": "custom_code",
+  "n_heads": 8,
+  "n_layers": 1,
+  "num_train_epochs": 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:fd86ea858d3a4f6726dccc35015f863eb51d12b628a3f87434037064203dd5e9
+size 428216

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebee227d9375cf151c16603fd7c249ea9e37b8e7983884226ed6305a3e8d118
+size 5304