Upload README.md with huggingface_hub

README.md

@@ -8,3 +8,81 @@ base_model: EssentialAI/rnj-1-instruct
 WIP derivative checkpoint of [EssentialAI/rnj-1-instruct](https://huggingface.co/EssentialAI/rnj-1-instruct).
 
 Baseline for tool-calling experiments.
+
+## Training Config
+
+```toml
+max_steps = 140
+seq_len = 8192
+
+[model]
+name = "EssentialAI/rnj-1-instruct"
+
+[wandb]
+project = "xml-tool-thinking"
+name = "hex-v6-bs512-rollouts16"
+
+[orchestrator.wandb.log_extras]
+samples = true
+interval = 1
+
+[orchestrator]
+batch_size = 512
+rollouts_per_example = 16
+
+[orchestrator.sampling]
+max_tokens = 512
+temperature = 1.0
+
+[[orchestrator.env]]
+id = "hex_encode_xml"
+args = { max_turns = 5, max_chunk = 128, strict_format = true, user_prompt = """Here is a document with semantic XML tags:
+
+{doc}
+
+Your task: Encode the content of the <{tag_name}> tag to hexadecimal.
+
+You must encode in chunks of at most {max_chunk_size} characters at a time.
+
+Available tools:
+- get_tag_content: Get the target tag's text and length. No arguments.
+- encode_chunk: Encode a character range to hex. Args: start (int), end (int)
+
+<format_rules>
+- Every response must begin with [think]
+- After [/think], include your tool call
+- No text outside of [think]...[/think] and <tool_call>...</tool_call>
+</format_rules>
+
+Tool format:
+<tool_call>
+<name>tool_name</name>
+<param name="arg_name">value</param>
+</tool_call>
+
+When done, output ONLY the final hex string with no tool calls.
+
+Example:
+[think]I need to get the content first.[/think]
+<tool_call>
+<name>get_tag_content</name>
+</tool_call>""" }
+
+[trainer.model]
+ac = { freq = 1 }
+
+[trainer.optim]
+lr = 1e-6
+max_norm = 0.001
+
+[trainer.scheduler]
+type = "linear"
+warmup_steps = 30
+decay_steps = 30
+min_lr = 0
+
+[inference.parallel]
+tp = 4
+
+[ckpt]
+```