{ "failed_groups": [], "groups": { "attn": { "bit_identical_tensors": 0, "relative_l2_drift": 0.011781303073684989, "tensors": 192 }, "embed_tokens": { "bit_identical_tensors": 0, "relative_l2_drift": 0.0009620733409380173, "tensors": 1 }, "lm_head": { "bit_identical_tensors": 0, "relative_l2_drift": 0.00709358530636513, "tensors": 1 }, "mlp": { "bit_identical_tensors": 0, "relative_l2_drift": 0.012873352072381432, "tensors": 96 }, "norm": { "bit_identical_tensors": 1, "relative_l2_drift": 0.0009664618617231844, "tensors": 65 } }, "init": "allenai/OLMo-2-1124-7B-Instruct", "min_drift": 1e-05, "ok": true, "trained": "/home/fs01/smw362/mars/distill/SOLD/outputs/alpaca_smollm_olmo/instruct/inv_reference_mixed" }