Training in progress, epoch 1

config.json

@@ -0,0 +1,14 @@
+{
+  "architectures": [
+    "SoraForSLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 512,
+  "max_position_embeddings": 512,
+  "model_type": "sora_slm",
+  "num_heads": 8,
+  "num_layers": 8,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 2628
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f081ed6f8b5127dce2f57d2b1502b8c4e823bc17212ba8aa650747dc5e52ecb6
+size 112698560

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c315d4706c7fb434258d1c20dec469cb591d2d0dad6e7344cfa18ce981f232
+size 5201