args and setup.

args.json

@@ -0,0 +1,18 @@
+{
+    "model": "gpt2",
+    "dataset": "wikitext",
+    "subset": "wikitext-103-v1",
+    "output_dir": "output",
+    "num_epochs": 20,
+    "num_tokens": 100000000,
+    "window_size": 16,
+    "batch_size": 1024,
+    "learning_rate": 1e-05,
+    "warmup_steps": 3000,
+    "scheduler": "cosine",
+    "weight_decay": 0.1,
+    "random_seed": 42,
+    "eval_steps": 1000,
+    "patience": 5,
+    "id": "1c15056cf51bff47"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}