{ "base_model": "openbmb/MiniCPM5-2B", "base_revision": "12a3808a956f869c767195e9266b59c4d21d92e2", "prompt_version": "afm-d-decoder-v2.1", "prompt_sha256": "4cadeb684fa95df9d07a1f4404639fd251df59fc39a55daa8243af6caed7d052", "training": "lora_option_letter_ce", "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "lora_target_modules": [ "q_proj", "k_proj", "v_proj", "o_proj" ], "max_tokens": 4096, "lr": 5e-05, "epochs": 3, "micro_batch": 1, "data": "data/train_semif.jsonl", "n_train": 31569, "meta": { "source": "openbmb/MiniCPM5-2B", "revision": "12a3808a956f869c767195e9266b59c4d21d92e2", "dtype": "bfloat16", "device": "cuda:0", "torch_version": "2.8.0+cu128", "transformers_version": "5.17.0" }, "shuffle_options": true, "epoch_gold_letter_histograms": [ { "A": 10113, "B": 10065, "C": 5357, "D": 3308, "E": 1278, "F": 340, "G": 136, "H": 126, "I": 135, "J": 134, "K": 130, "L": 107, "M": 128, "N": 116, "O": 34, "P": 62 }, { "A": 9972, "B": 10168, "C": 5398, "D": 3226, "E": 1386, "F": 304, "G": 137, "H": 138, "I": 130, "J": 133, "K": 120, "L": 129, "M": 128, "N": 113, "O": 49, "P": 38 }, { "A": 10008, "B": 10226, "C": 5353, "D": 3208, "E": 1301, "F": 338, "G": 126, "H": 129, "I": 110, "J": 120, "K": 137, "L": 120, "M": 125, "N": 138, "O": 69, "P": 61 } ] }