{ "base_id": "openbmb/MiniCPM5-1B", "base_revision": "87179e5c1f455ef22e6223592d2d61351b525bfc", "settings": { "data": "data/live-policy-v4", "output": "runs/minicpm5-policy-v1", "epochs": 1, "max_length": 2048, "learning_rate": 0.0001, "max_steps": 0 }, "examples": { "train": 826, "validation": 104 }, "overlength_dropped": { "train": 0, "validation": 0 }, "data_sha256": { "train": "af0abde43f8bbebfb384885b021d316b26354f8d4d4d6a535528d4c91708b756", "validation": "57c33bcef55832c4e86e4cbc37de31aeb94d8f118b5389dbcb73fd09cd7fd264" }, "seed": 42, "batch_size": 1, "gradient_accumulation": 8, "lora_rank": 16, "lora_alpha": 32, "quantization": "nf4_double_quant", "loss": "assistant XML action tokens and end-of-turn token only", "data_manifest": { "kind": "executed_oracle_demonstrations", "seed": 42, "limitations": "Three-file synthetic repositories; query-word searches and oracle-chosen target ranges. Teaches protocol, not realistic repository planning.", "excluded_repositories_by_name": [ "click", "flask", "requests" ], "splits": { "train": { "trajectories": 256, "action_examples": 826, "source_sha256": "3eeed3185b74f934462aaccbd3c567f8db20754a1bf6f5f3686779f8b39f4338", "output_sha256": "af0abde43f8bbebfb384885b021d316b26354f8d4d4d6a535528d4c91708b756" }, "validation": { "trajectories": 32, "action_examples": 104, "source_sha256": "e1b934c33f12322e4a56d0d17a987966c40961b035e15939fd716b76d4e017a2", "output_sha256": "57c33bcef55832c4e86e4cbc37de31aeb94d8f118b5389dbcb73fd09cd7fd264" } }, "repository_disjoint": true }, "packages": { "torch": "2.7.1", "transformers": "4.57.6", "peft": "0.17.1", "accelerate": "1.10.1", "bitsandbytes": "0.47.0" }, "gpu": "NVIDIA GeForce RTX 3050 Laptop GPU", "source_sha256": { "__init__.py": "dcd2b573883b8068e806e3052adf9c03728f1cf621d35ff013179de76f76c702", "text.py": "8db7b80ee446480175f7691872303c8b72fd014604ad4fb575b359cee71f1938", "io.py": "b29c21db767ea9773281b17fe0754375153d18fb64f314907528f00d584a047f", "data.py": "20a891eff11d555d2301b62f4953146603efc87b03da4802f136f694ebdba78d", "encoder.py": "cb5671c08f28a70ffd0e2a7033528efc3581896a27242d55eb250ce922ab038f", "metrics.py": "cb93d30878c0c1006f06d1d0c4cbb188f90c6f4fc65f69f9a3b11d847f28ad27", "train.py": "cf20f6189967cfc88f3849bc3a225f2680c42026d53f204d9d5afc05fe88a2d6", "lexical.py": "6c47c834c6bbf7b317e2514057eee7444720581f5ec452ecb01ac666397b86b3", "symbols.py": "a377d6aa2c6b479c2ee115dd8e4859f0c06d188ae97b86fa1c7133885ee32d86", "index.py": "e8b0a666b41fed48d98616d5dcdd104e59c4308ac990281b463e5ee68f97877f", "evaluate.py": "29c942b9cbfff21ba8514511e27752527f0ec5e2cad5fbf57ec3b220fc7acd0b", "__main__.py": "ab30d9b696e41ece67094e19c87b1a31fc0ebce8d3afa79dc8eaf561f8fb4895", "download.py": "24f9802fb7cc82b81f6b1cb93e9244352d7b86feeb0a54ec055fb3e8d0a6a4d7", "cli.py": "d081962fc459808c65bd4c1d389e12ad9a9466df0a1374c8095a8bd5ccbb369e", "scout.py": "c3150baae51f37646305fee1d2c61e7b37f2ec9c4a0ba7f92ab4d7d6b1710161", "server.py": "483fe8051012249e38a6836cbe217d8c581d033e4d19026a29a7bd5c83878190", "live_tools.py": "e10fb6aaeaa6d7c4a5a35c0c6a210be4a4c283b18d215767d6bee0bac707d14c", "local_policy.py": "b0711b46a6399dfbeeecdcc045fb7392030e187d7e21c6e4fa9b51e6fc8056f4", "agent.py": "47357a900e9696b7ec5268eb031067eb0069faaeef92fd3159bd822d6bc67cdb", "live_server.py": "ccfb3c63115fe991c2f5f22c05f794d89c90d783b52f8ddbb668a8541e3af6fe", "native_protocol.py": "3a4d16c1d2cd90cb7d81e635f40d721270b0d541f454557a6d14e80b6b1073a7", "eval_live.py": "74946cf6ca0585810960f2a745261dd74e141d1342d7c33bc8db4c6ab34e2161", "prepare_live.py": "0675173c5e9c116c995c271dc06de914388f19eb83779c07e3009000a810290b", "live_data.py": "fd0bd5b118b2437146e08ef921dc4aa8a1da24e69bcbdd3efc5ff6e9c4fe8a78", "transformers_policy.py": "e8e8a81b70eb37563973e640534b425a7ea9fc7d398a39dc8d8f71b9be3f1b89", "train_policy.py": "803f45cb78087d1899c59bc09b6589e2ac84753c8f4be9938d837bbb5db3def8" } }