{ "base_model": "Cloudflare/clef-flash", "base_revision": "17f0b0ad64efb65d273590632833508766b2aae6", "encoding_version": "stackcraft-clef-v1", "extra": { "config": { "batch_size": 1, "brier_weight": 0.1, "clip_gradient_norm": 1.0, "epochs": 2, "gradient_accumulation": 8, "label_smoothing": 0.05, "learning_rate": 1e-05, "max_length": 4096, "mode": "lora", "optimizer": "AdamW", "rank": 4, "seed": 42, "selection": "external validation only; this script does not choose a checkpoint", "weight_decay": 0.01 }, "dataset_config_sha256": "65b72544c80cf19f4ac3b12ca109d0ebda18fb70eadb4b170a55b1e8bb3b4f6d", "dataset_counts": { "train": 827, "validation": 215 }, "dataset_manifest_sha256": "aeddcfc1ea5390f12122d2e786c1e2030dcc97d3790b6d7523432548198b1f94", "dataset_source_commit": "70d84bd8dc5d4a60f3b96455a57d9e6f9416d109", "dataset_split_sha256": { "train": "edd682761db95a4f25bb30a284489c54d9336a36da0a9b19d2cda860b428baa8", "validation": "eff9cdc5932e935959ac4d26dce6470d335090f7428a91930001954266d133bc" }, "epoch": 2, "examples": 827, "mean_training_loss": 1.9667175294878694, "optimizer_steps": 104, "peak_allocated_bytes": 23226543104, "peak_reserved_bytes": 24178065408, "seconds": 744.6554337799898, "shuffle_order_sha256": "b9d20efe77959592c99e9247a58d844be69df50db595bd87c6d7e595f5d2e0c4", "source_commit": "d9fcd05c02e9327d4d791f2338725092cede8bdd", "source_dirty": true, "source_hashes": { "scripts/train_clef.py": "e83586cf0fd0d7bb8c4aa15f9b858b9f9ffdb915622e355deb9513788d5054aa", "src/stackcraft/clef.py": "c505f35d27121ba9ec9db3c663927ac8b28304f4ed864765be61ce96c8c86e13", "src/stackcraft/data.py": "74b68a1f391a3128d2e499c7e86b6c94a1f2a2bef33ffe75c8631207065bd991", "src/stackcraft/training.py": "f7e48b041b331cf2b68674ec2abb1059dd1da47cb261697b46260b4f0169dba8" }, "test_trajectories_used": false, "validation_used_for_training": false }, "format_version": 1, "head_shapes": { "evidence_layers.0.attention.in_proj_bias": [ 3072 ], "evidence_layers.0.attention.in_proj_weight": [ 3072, 1024 ], "evidence_layers.0.attention.out_proj.bias": [ 1024 ], "evidence_layers.0.attention.out_proj.weight": [ 1024, 1024 ], "evidence_layers.0.feedforward.0.bias": [ 4096 ], "evidence_layers.0.feedforward.0.weight": [ 4096, 1024 ], "evidence_layers.0.feedforward.3.bias": [ 1024 ], "evidence_layers.0.feedforward.3.weight": [ 1024, 4096 ], "evidence_layers.0.feedforward_norm.bias": [ 1024 ], "evidence_layers.0.feedforward_norm.weight": [ 1024 ], "evidence_layers.0.memory_norm.bias": [ 1024 ], "evidence_layers.0.memory_norm.weight": [ 1024 ], "evidence_layers.0.query_norm.bias": [ 1024 ], "evidence_layers.0.query_norm.weight": [ 1024 ], "evidence_layers.1.attention.in_proj_bias": [ 3072 ], "evidence_layers.1.attention.in_proj_weight": [ 3072, 1024 ], "evidence_layers.1.attention.out_proj.bias": [ 1024 ], "evidence_layers.1.attention.out_proj.weight": [ 1024, 1024 ], "evidence_layers.1.feedforward.0.bias": [ 4096 ], "evidence_layers.1.feedforward.0.weight": [ 4096, 1024 ], "evidence_layers.1.feedforward.3.bias": [ 1024 ], "evidence_layers.1.feedforward.3.weight": [ 1024, 4096 ], "evidence_layers.1.feedforward_norm.bias": [ 1024 ], "evidence_layers.1.feedforward_norm.weight": [ 1024 ], "evidence_layers.1.memory_norm.bias": [ 1024 ], "evidence_layers.1.memory_norm.weight": [ 1024 ], "evidence_layers.1.query_norm.bias": [ 1024 ], "evidence_layers.1.query_norm.weight": [ 1024 ], "field_norm.bias": [ 1024 ], "field_norm.weight": [ 1024 ], "global_projection.weight": [ 1024, 4096 ], "hidden_norm.bias": [ 4096 ], "hidden_norm.weight": [ 4096 ], "joint_logit_scale": [], "layers.0.linear1.bias": [ 4096 ], "layers.0.linear1.weight": [ 4096, 1024 ], "layers.0.linear2.bias": [ 1024 ], "layers.0.linear2.weight": [ 1024, 4096 ], "layers.0.multihead_attn.in_proj_bias": [ 3072 ], "layers.0.multihead_attn.in_proj_weight": [ 3072, 1024 ], "layers.0.multihead_attn.out_proj.bias": [ 1024 ], "layers.0.multihead_attn.out_proj.weight": [ 1024, 1024 ], "layers.0.norm1.bias": [ 1024 ], "layers.0.norm1.weight": [ 1024 ], "layers.0.norm2.bias": [ 1024 ], "layers.0.norm2.weight": [ 1024 ], "layers.0.norm3.bias": [ 1024 ], "layers.0.norm3.weight": [ 1024 ], "layers.0.self_attn.in_proj_bias": [ 3072 ], "layers.0.self_attn.in_proj_weight": [ 3072, 1024 ], "layers.0.self_attn.out_proj.bias": [ 1024 ], "layers.0.self_attn.out_proj.weight": [ 1024, 1024 ], "layers.1.linear1.bias": [ 4096 ], "layers.1.linear1.weight": [ 4096, 1024 ], "layers.1.linear2.bias": [ 1024 ], "layers.1.linear2.weight": [ 1024, 4096 ], "layers.1.multihead_attn.in_proj_bias": [ 3072 ], "layers.1.multihead_attn.in_proj_weight": [ 3072, 1024 ], "layers.1.multihead_attn.out_proj.bias": [ 1024 ], "layers.1.multihead_attn.out_proj.weight": [ 1024, 1024 ], "layers.1.norm1.bias": [ 1024 ], "layers.1.norm1.weight": [ 1024 ], "layers.1.norm2.bias": [ 1024 ], "layers.1.norm2.weight": [ 1024 ], "layers.1.norm3.bias": [ 1024 ], "layers.1.norm3.weight": [ 1024 ], "layers.1.self_attn.in_proj_bias": [ 3072 ], "layers.1.self_attn.in_proj_weight": [ 3072, 1024 ], "layers.1.self_attn.out_proj.bias": [ 1024 ], "layers.1.self_attn.out_proj.weight": [ 1024, 1024 ], "layers.2.linear1.bias": [ 4096 ], "layers.2.linear1.weight": [ 4096, 1024 ], "layers.2.linear2.bias": [ 1024 ], "layers.2.linear2.weight": [ 1024, 4096 ], "layers.2.multihead_attn.in_proj_bias": [ 3072 ], "layers.2.multihead_attn.in_proj_weight": [ 3072, 1024 ], "layers.2.multihead_attn.out_proj.bias": [ 1024 ], "layers.2.multihead_attn.out_proj.weight": [ 1024, 1024 ], "layers.2.norm1.bias": [ 1024 ], "layers.2.norm1.weight": [ 1024 ], "layers.2.norm2.bias": [ 1024 ], "layers.2.norm2.weight": [ 1024 ], "layers.2.norm3.bias": [ 1024 ], "layers.2.norm3.weight": [ 1024 ], "layers.2.self_attn.in_proj_bias": [ 3072 ], "layers.2.self_attn.in_proj_weight": [ 3072, 1024 ], "layers.2.self_attn.out_proj.bias": [ 1024 ], "layers.2.self_attn.out_proj.weight": [ 1024, 1024 ], "layers.3.linear1.bias": [ 4096 ], "layers.3.linear1.weight": [ 4096, 1024 ], "layers.3.linear2.bias": [ 1024 ], "layers.3.linear2.weight": [ 1024, 4096 ], "layers.3.multihead_attn.in_proj_bias": [ 3072 ], "layers.3.multihead_attn.in_proj_weight": [ 3072, 1024 ], "layers.3.multihead_attn.out_proj.bias": [ 1024 ], "layers.3.multihead_attn.out_proj.weight": [ 1024, 1024 ], "layers.3.norm1.bias": [ 1024 ], "layers.3.norm1.weight": [ 1024 ], "layers.3.norm2.bias": [ 1024 ], "layers.3.norm2.weight": [ 1024 ], "layers.3.norm3.bias": [ 1024 ], "layers.3.norm3.weight": [ 1024 ], "layers.3.self_attn.in_proj_bias": [ 3072 ], "layers.3.self_attn.in_proj_weight": [ 3072, 1024 ], "layers.3.self_attn.out_proj.bias": [ 1024 ], "layers.3.self_attn.out_proj.weight": [ 1024, 1024 ], "memory_projection.weight": [ 1024, 4096 ], "option_context_projection.weight": [ 1024, 4096 ], "option_lexical_projection.weight": [ 1024, 4096 ], "option_norm.bias": [ 1024 ], "option_norm.weight": [ 1024 ], "option_question_projection.weight": [ 1024, 4096 ], "option_summary_norm.bias": [ 1024 ], "option_summary_norm.weight": [ 1024 ], "prior_logit_scale": [], "question_projection.weight": [ 1024, 4096 ], "residual_gate": [], "residual_scorer.0.bias": [ 1024 ], "residual_scorer.0.weight": [ 1024, 4096 ], "residual_scorer.3.bias": [ 1 ], "residual_scorer.3.weight": [ 1, 1024 ], "type_embedding.weight": [ 3, 1024 ] }, "head_type": "native-joint-schema-fp32-gathered-rows-v1", "lora": { "alpha": 8, "dropout": 0.0, "rank": 4, "target_modules": [ "model.language_model.layers.0.linear_attn.in_proj_a", "model.language_model.layers.0.linear_attn.in_proj_b", "model.language_model.layers.0.linear_attn.in_proj_qkv", "model.language_model.layers.0.linear_attn.in_proj_z", "model.language_model.layers.0.linear_attn.out_proj", "model.language_model.layers.0.mlp.down_proj", "model.language_model.layers.0.mlp.gate_proj", "model.language_model.layers.0.mlp.up_proj", "model.language_model.layers.1.linear_attn.in_proj_a", "model.language_model.layers.1.linear_attn.in_proj_b", "model.language_model.layers.1.linear_attn.in_proj_qkv", "model.language_model.layers.1.linear_attn.in_proj_z", "model.language_model.layers.1.linear_attn.out_proj", "model.language_model.layers.1.mlp.down_proj", "model.language_model.layers.1.mlp.gate_proj", "model.language_model.layers.1.mlp.up_proj", "model.language_model.layers.10.linear_attn.in_proj_a", "model.language_model.layers.10.linear_attn.in_proj_b", "model.language_model.layers.10.linear_attn.in_proj_qkv", "model.language_model.layers.10.linear_attn.in_proj_z", "model.language_model.layers.10.linear_attn.out_proj", "model.language_model.layers.10.mlp.down_proj", "model.language_model.layers.10.mlp.gate_proj", "model.language_model.layers.10.mlp.up_proj", "model.language_model.layers.11.mlp.down_proj", "model.language_model.layers.11.mlp.gate_proj", "model.language_model.layers.11.mlp.up_proj", "model.language_model.layers.11.self_attn.k_proj", "model.language_model.layers.11.self_attn.o_proj", "model.language_model.layers.11.self_attn.q_proj", "model.language_model.layers.11.self_attn.v_proj", "model.language_model.layers.12.linear_attn.in_proj_a", "model.language_model.layers.12.linear_attn.in_proj_b", "model.language_model.layers.12.linear_attn.in_proj_qkv", "model.language_model.layers.12.linear_attn.in_proj_z", "model.language_model.layers.12.linear_attn.out_proj", "model.language_model.layers.12.mlp.down_proj", "model.language_model.layers.12.mlp.gate_proj", "model.language_model.layers.12.mlp.up_proj", "model.language_model.layers.13.linear_attn.in_proj_a", "model.language_model.layers.13.linear_attn.in_proj_b", "model.language_model.layers.13.linear_attn.in_proj_qkv", "model.language_model.layers.13.linear_attn.in_proj_z", "model.language_model.layers.13.linear_attn.out_proj", "model.language_model.layers.13.mlp.down_proj", "model.language_model.layers.13.mlp.gate_proj", "model.language_model.layers.13.mlp.up_proj", "model.language_model.layers.14.linear_attn.in_proj_a", "model.language_model.layers.14.linear_attn.in_proj_b", "model.language_model.layers.14.linear_attn.in_proj_qkv", "model.language_model.layers.14.linear_attn.in_proj_z", "model.language_model.layers.14.linear_attn.out_proj", "model.language_model.layers.14.mlp.down_proj", "model.language_model.layers.14.mlp.gate_proj", "model.language_model.layers.14.mlp.up_proj", "model.language_model.layers.15.mlp.down_proj", "model.language_model.layers.15.mlp.gate_proj", "model.language_model.layers.15.mlp.up_proj", "model.language_model.layers.15.self_attn.k_proj", "model.language_model.layers.15.self_attn.o_proj", "model.language_model.layers.15.self_attn.q_proj", "model.language_model.layers.15.self_attn.v_proj", "model.language_model.layers.16.linear_attn.in_proj_a", "model.language_model.layers.16.linear_attn.in_proj_b", "model.language_model.layers.16.linear_attn.in_proj_qkv", "model.language_model.layers.16.linear_attn.in_proj_z", "model.language_model.layers.16.linear_attn.out_proj", "model.language_model.layers.16.mlp.down_proj", "model.language_model.layers.16.mlp.gate_proj", "model.language_model.layers.16.mlp.up_proj", "model.language_model.layers.17.linear_attn.in_proj_a", "model.language_model.layers.17.linear_attn.in_proj_b", "model.language_model.layers.17.linear_attn.in_proj_qkv", "model.language_model.layers.17.linear_attn.in_proj_z", "model.language_model.layers.17.linear_attn.out_proj", "model.language_model.layers.17.mlp.down_proj", "model.language_model.layers.17.mlp.gate_proj", "model.language_model.layers.17.mlp.up_proj", "model.language_model.layers.18.linear_attn.in_proj_a", "model.language_model.layers.18.linear_attn.in_proj_b", "model.language_model.layers.18.linear_attn.in_proj_qkv", "model.language_model.layers.18.linear_attn.in_proj_z", "model.language_model.layers.18.linear_attn.out_proj", "model.language_model.layers.18.mlp.down_proj", "model.language_model.layers.18.mlp.gate_proj", "model.language_model.layers.18.mlp.up_proj", "model.language_model.layers.19.mlp.down_proj", "model.language_model.layers.19.mlp.gate_proj", "model.language_model.layers.19.mlp.up_proj", "model.language_model.layers.19.self_attn.k_proj", "model.language_model.layers.19.self_attn.o_proj", "model.language_model.layers.19.self_attn.q_proj", "model.language_model.layers.19.self_attn.v_proj", "model.language_model.layers.2.linear_attn.in_proj_a", "model.language_model.layers.2.linear_attn.in_proj_b", "model.language_model.layers.2.linear_attn.in_proj_qkv", "model.language_model.layers.2.linear_attn.in_proj_z", "model.language_model.layers.2.linear_attn.out_proj", "model.language_model.layers.2.mlp.down_proj", "model.language_model.layers.2.mlp.gate_proj", "model.language_model.layers.2.mlp.up_proj", "model.language_model.layers.20.linear_attn.in_proj_a", "model.language_model.layers.20.linear_attn.in_proj_b", "model.language_model.layers.20.linear_attn.in_proj_qkv", "model.language_model.layers.20.linear_attn.in_proj_z", "model.language_model.layers.20.linear_attn.out_proj", "model.language_model.layers.20.mlp.down_proj", "model.language_model.layers.20.mlp.gate_proj", "model.language_model.layers.20.mlp.up_proj", "model.language_model.layers.21.linear_attn.in_proj_a", "model.language_model.layers.21.linear_attn.in_proj_b", "model.language_model.layers.21.linear_attn.in_proj_qkv", "model.language_model.layers.21.linear_attn.in_proj_z", "model.language_model.layers.21.linear_attn.out_proj", "model.language_model.layers.21.mlp.down_proj", "model.language_model.layers.21.mlp.gate_proj", "model.language_model.layers.21.mlp.up_proj", "model.language_model.layers.22.linear_attn.in_proj_a", "model.language_model.layers.22.linear_attn.in_proj_b", "model.language_model.layers.22.linear_attn.in_proj_qkv", "model.language_model.layers.22.linear_attn.in_proj_z", "model.language_model.layers.22.linear_attn.out_proj", "model.language_model.layers.22.mlp.down_proj", "model.language_model.layers.22.mlp.gate_proj", "model.language_model.layers.22.mlp.up_proj", "model.language_model.layers.23.mlp.down_proj", "model.language_model.layers.23.mlp.gate_proj", "model.language_model.layers.23.mlp.up_proj", "model.language_model.layers.23.self_attn.k_proj", "model.language_model.layers.23.self_attn.o_proj", "model.language_model.layers.23.self_attn.q_proj", "model.language_model.layers.23.self_attn.v_proj", "model.language_model.layers.24.linear_attn.in_proj_a", "model.language_model.layers.24.linear_attn.in_proj_b", "model.language_model.layers.24.linear_attn.in_proj_qkv", "model.language_model.layers.24.linear_attn.in_proj_z", "model.language_model.layers.24.linear_attn.out_proj", "model.language_model.layers.24.mlp.down_proj", "model.language_model.layers.24.mlp.gate_proj", "model.language_model.layers.24.mlp.up_proj", "model.language_model.layers.25.linear_attn.in_proj_a", "model.language_model.layers.25.linear_attn.in_proj_b", "model.language_model.layers.25.linear_attn.in_proj_qkv", "model.language_model.layers.25.linear_attn.in_proj_z", "model.language_model.layers.25.linear_attn.out_proj", "model.language_model.layers.25.mlp.down_proj", "model.language_model.layers.25.mlp.gate_proj", "model.language_model.layers.25.mlp.up_proj", "model.language_model.layers.26.linear_attn.in_proj_a", "model.language_model.layers.26.linear_attn.in_proj_b", "model.language_model.layers.26.linear_attn.in_proj_qkv", "model.language_model.layers.26.linear_attn.in_proj_z", "model.language_model.layers.26.linear_attn.out_proj", "model.language_model.layers.26.mlp.down_proj", "model.language_model.layers.26.mlp.gate_proj", "model.language_model.layers.26.mlp.up_proj", "model.language_model.layers.27.mlp.down_proj", "model.language_model.layers.27.mlp.gate_proj", "model.language_model.layers.27.mlp.up_proj", "model.language_model.layers.27.self_attn.k_proj", "model.language_model.layers.27.self_attn.o_proj", "model.language_model.layers.27.self_attn.q_proj", "model.language_model.layers.27.self_attn.v_proj", "model.language_model.layers.28.linear_attn.in_proj_a", "model.language_model.layers.28.linear_attn.in_proj_b", "model.language_model.layers.28.linear_attn.in_proj_qkv", "model.language_model.layers.28.linear_attn.in_proj_z", "model.language_model.layers.28.linear_attn.out_proj", "model.language_model.layers.28.mlp.down_proj", "model.language_model.layers.28.mlp.gate_proj", "model.language_model.layers.28.mlp.up_proj", "model.language_model.layers.29.linear_attn.in_proj_a", "model.language_model.layers.29.linear_attn.in_proj_b", "model.language_model.layers.29.linear_attn.in_proj_qkv", "model.language_model.layers.29.linear_attn.in_proj_z", "model.language_model.layers.29.linear_attn.out_proj", "model.language_model.layers.29.mlp.down_proj", "model.language_model.layers.29.mlp.gate_proj", "model.language_model.layers.29.mlp.up_proj", "model.language_model.layers.3.mlp.down_proj", "model.language_model.layers.3.mlp.gate_proj", "model.language_model.layers.3.mlp.up_proj", "model.language_model.layers.3.self_attn.k_proj", "model.language_model.layers.3.self_attn.o_proj", "model.language_model.layers.3.self_attn.q_proj", "model.language_model.layers.3.self_attn.v_proj", "model.language_model.layers.30.linear_attn.in_proj_a", "model.language_model.layers.30.linear_attn.in_proj_b", "model.language_model.layers.30.linear_attn.in_proj_qkv", "model.language_model.layers.30.linear_attn.in_proj_z", "model.language_model.layers.30.linear_attn.out_proj", "model.language_model.layers.30.mlp.down_proj", "model.language_model.layers.30.mlp.gate_proj", "model.language_model.layers.30.mlp.up_proj", "model.language_model.layers.31.mlp.down_proj", "model.language_model.layers.31.mlp.gate_proj", "model.language_model.layers.31.mlp.up_proj", "model.language_model.layers.31.self_attn.k_proj", "model.language_model.layers.31.self_attn.o_proj", "model.language_model.layers.31.self_attn.q_proj", "model.language_model.layers.31.self_attn.v_proj", "model.language_model.layers.4.linear_attn.in_proj_a", "model.language_model.layers.4.linear_attn.in_proj_b", "model.language_model.layers.4.linear_attn.in_proj_qkv", "model.language_model.layers.4.linear_attn.in_proj_z", "model.language_model.layers.4.linear_attn.out_proj", "model.language_model.layers.4.mlp.down_proj", "model.language_model.layers.4.mlp.gate_proj", "model.language_model.layers.4.mlp.up_proj", "model.language_model.layers.5.linear_attn.in_proj_a", "model.language_model.layers.5.linear_attn.in_proj_b", "model.language_model.layers.5.linear_attn.in_proj_qkv", "model.language_model.layers.5.linear_attn.in_proj_z", "model.language_model.layers.5.linear_attn.out_proj", "model.language_model.layers.5.mlp.down_proj", "model.language_model.layers.5.mlp.gate_proj", "model.language_model.layers.5.mlp.up_proj", "model.language_model.layers.6.linear_attn.in_proj_a", "model.language_model.layers.6.linear_attn.in_proj_b", "model.language_model.layers.6.linear_attn.in_proj_qkv", "model.language_model.layers.6.linear_attn.in_proj_z", "model.language_model.layers.6.linear_attn.out_proj", "model.language_model.layers.6.mlp.down_proj", "model.language_model.layers.6.mlp.gate_proj", "model.language_model.layers.6.mlp.up_proj", "model.language_model.layers.7.mlp.down_proj", "model.language_model.layers.7.mlp.gate_proj", "model.language_model.layers.7.mlp.up_proj", "model.language_model.layers.7.self_attn.k_proj", "model.language_model.layers.7.self_attn.o_proj", "model.language_model.layers.7.self_attn.q_proj", "model.language_model.layers.7.self_attn.v_proj", "model.language_model.layers.8.linear_attn.in_proj_a", "model.language_model.layers.8.linear_attn.in_proj_b", "model.language_model.layers.8.linear_attn.in_proj_qkv", "model.language_model.layers.8.linear_attn.in_proj_z", "model.language_model.layers.8.linear_attn.out_proj", "model.language_model.layers.8.mlp.down_proj", "model.language_model.layers.8.mlp.gate_proj", "model.language_model.layers.8.mlp.up_proj", "model.language_model.layers.9.linear_attn.in_proj_a", "model.language_model.layers.9.linear_attn.in_proj_b", "model.language_model.layers.9.linear_attn.in_proj_qkv", "model.language_model.layers.9.linear_attn.in_proj_z", "model.language_model.layers.9.linear_attn.out_proj", "model.language_model.layers.9.mlp.down_proj", "model.language_model.layers.9.mlp.gate_proj", "model.language_model.layers.9.mlp.up_proj" ] }, "loss": { "brier_reduction": "sum_options", "brier_weight": 0.1, "label_smoothing": 0.05 }, "mode": "lora", "native_source_sha256": "0e304cf7c6500e8bb59bef7e2afd2c6373f82596dfb3b57d1aa93c175e2dc3a3" }