Training in progress, step 100

config.json

@@ -0,0 +1,19 @@
+{
+  "_name_or_path": "Q-bert/CyclicFormer-tiny-shakespeare",
+  "architectures": [
+    "CyclicFormerForCausalLM"
+  ],
+  "cyclic_size": 200,
+  "drop_prob": 0.1,
+  "hidden_size": 200,
+  "initializer_range": 0.1,
+  "model_type": "cyclicformer",
+  "n_loop": 3,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "rms_norm_eps": 1e-06,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fbaf0d1396970df17e7a5491085c19c5df6cfb5589b183b829dc907b739472
+size 205551816

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9ab5b2f3b81e64ff5c9088d3832adc3616671578d78a85ef4c7e9ab732ea1f
+size 5112