sft_lora / workmem /validation /validation_step_100.jsonl
SUJQ's picture
Upload folder using huggingface_hub
389c0ee verified
{"global_idx": 0, "total_positions": 437, "gt_mem_token_count": 11, "pred_mem_token_count": 211, "correct_mem_token_count": 2, "mem_token_precision": 0.009478672985781991, "mem_token_recall": 0.18181818181818182, "mem_token_accuracy": 0.18181818181818182, "slot_norm_mean": 198.0, "slot_sim_mean": 1.0, "rank": 0}
{"global_idx": 1, "total_positions": 594, "gt_mem_token_count": 5, "pred_mem_token_count": 237, "correct_mem_token_count": 2, "mem_token_precision": 0.008438818565400843, "mem_token_recall": 0.4, "mem_token_accuracy": 0.4, "slot_norm_mean": 199.0, "slot_sim_mean": 0.99609375, "rank": 0}
{"global_idx": 2, "total_positions": 638, "gt_mem_token_count": 5, "pred_mem_token_count": 430, "correct_mem_token_count": 3, "mem_token_precision": 0.0069767441860465115, "mem_token_recall": 0.6, "mem_token_accuracy": 0.6, "slot_norm_mean": 196.0, "slot_sim_mean": 0.99609375, "rank": 0}
{"global_idx": 3, "total_positions": 408, "gt_mem_token_count": 6, "pred_mem_token_count": 157, "correct_mem_token_count": 3, "mem_token_precision": 0.01910828025477707, "mem_token_recall": 0.5, "mem_token_accuracy": 0.5, "slot_norm_mean": 193.0, "slot_sim_mean": 1.0, "rank": 0}
{"global_idx": 4, "total_positions": 447, "gt_mem_token_count": 8, "pred_mem_token_count": 187, "correct_mem_token_count": 2, "mem_token_precision": 0.0106951871657754, "mem_token_recall": 0.25, "mem_token_accuracy": 0.25, "slot_norm_mean": 198.0, "slot_sim_mean": 1.0, "rank": 0}
{"global_idx": 5, "total_positions": 414, "gt_mem_token_count": 6, "pred_mem_token_count": 174, "correct_mem_token_count": 3, "mem_token_precision": 0.017241379310344827, "mem_token_recall": 0.5, "mem_token_accuracy": 0.5, "slot_norm_mean": 194.0, "slot_sim_mean": 1.0, "rank": 0}
{"global_idx": 6, "total_positions": 577, "gt_mem_token_count": 11, "pred_mem_token_count": 360, "correct_mem_token_count": 0, "mem_token_precision": 0.0, "mem_token_recall": 0.0, "mem_token_accuracy": 0.0, "slot_norm_mean": 197.0, "slot_sim_mean": 0.9921875, "rank": 0}
{"global_idx": 7, "total_positions": 631, "gt_mem_token_count": 17, "pred_mem_token_count": 447, "correct_mem_token_count": 3, "mem_token_precision": 0.006711409395973154, "mem_token_recall": 0.17647058823529413, "mem_token_accuracy": 0.17647058823529413, "slot_norm_mean": 200.0, "slot_sim_mean": 0.9921875, "rank": 1}
{"global_idx": 8, "total_positions": 591, "gt_mem_token_count": 7, "pred_mem_token_count": 311, "correct_mem_token_count": 1, "mem_token_precision": 0.003215434083601286, "mem_token_recall": 0.14285714285714285, "mem_token_accuracy": 0.14285714285714285, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 1}
{"global_idx": 9, "total_positions": 579, "gt_mem_token_count": 13, "pred_mem_token_count": 396, "correct_mem_token_count": 4, "mem_token_precision": 0.010101010101010102, "mem_token_recall": 0.3076923076923077, "mem_token_accuracy": 0.3076923076923077, "slot_norm_mean": 199.0, "slot_sim_mean": 1.0, "rank": 1}
{"global_idx": 10, "total_positions": 596, "gt_mem_token_count": 13, "pred_mem_token_count": 248, "correct_mem_token_count": 2, "mem_token_precision": 0.008064516129032258, "mem_token_recall": 0.15384615384615385, "mem_token_accuracy": 0.15384615384615385, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 1}
{"global_idx": 11, "total_positions": 353, "gt_mem_token_count": 7, "pred_mem_token_count": 146, "correct_mem_token_count": 1, "mem_token_precision": 0.00684931506849315, "mem_token_recall": 0.14285714285714285, "mem_token_accuracy": 0.14285714285714285, "slot_norm_mean": 197.0, "slot_sim_mean": 1.0, "rank": 1}
{"global_idx": 12, "total_positions": 378, "gt_mem_token_count": 15, "pred_mem_token_count": 175, "correct_mem_token_count": 9, "mem_token_precision": 0.05142857142857143, "mem_token_recall": 0.6, "mem_token_accuracy": 0.6, "slot_norm_mean": 196.0, "slot_sim_mean": 0.99609375, "rank": 1}
{"global_idx": 13, "total_positions": 412, "gt_mem_token_count": 11, "pred_mem_token_count": 223, "correct_mem_token_count": 2, "mem_token_precision": 0.008968609865470852, "mem_token_recall": 0.18181818181818182, "mem_token_accuracy": 0.18181818181818182, "slot_norm_mean": 197.0, "slot_sim_mean": 1.0, "rank": 1}
{"global_idx": 14, "total_positions": 665, "gt_mem_token_count": 10, "pred_mem_token_count": 506, "correct_mem_token_count": 2, "mem_token_precision": 0.003952569169960474, "mem_token_recall": 0.2, "mem_token_accuracy": 0.2, "slot_norm_mean": 198.0, "slot_sim_mean": 1.0, "rank": 2}
{"global_idx": 15, "total_positions": 529, "gt_mem_token_count": 12, "pred_mem_token_count": 358, "correct_mem_token_count": 2, "mem_token_precision": 0.00558659217877095, "mem_token_recall": 0.16666666666666666, "mem_token_accuracy": 0.16666666666666666, "slot_norm_mean": 199.0, "slot_sim_mean": 0.9921875, "rank": 2}
{"global_idx": 16, "total_positions": 383, "gt_mem_token_count": 6, "pred_mem_token_count": 137, "correct_mem_token_count": 2, "mem_token_precision": 0.014598540145985401, "mem_token_recall": 0.3333333333333333, "mem_token_accuracy": 0.3333333333333333, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 2}
{"global_idx": 17, "total_positions": 370, "gt_mem_token_count": 10, "pred_mem_token_count": 166, "correct_mem_token_count": 3, "mem_token_precision": 0.018072289156626505, "mem_token_recall": 0.3, "mem_token_accuracy": 0.3, "slot_norm_mean": 197.0, "slot_sim_mean": 0.99609375, "rank": 2}
{"global_idx": 18, "total_positions": 647, "gt_mem_token_count": 9, "pred_mem_token_count": 428, "correct_mem_token_count": 2, "mem_token_precision": 0.004672897196261682, "mem_token_recall": 0.2222222222222222, "mem_token_accuracy": 0.2222222222222222, "slot_norm_mean": 195.0, "slot_sim_mean": 0.9921875, "rank": 2}
{"global_idx": 19, "total_positions": 261, "gt_mem_token_count": 6, "pred_mem_token_count": 100, "correct_mem_token_count": 3, "mem_token_precision": 0.03, "mem_token_recall": 0.5, "mem_token_accuracy": 0.5, "slot_norm_mean": 194.0, "slot_sim_mean": 0.99609375, "rank": 2}
{"global_idx": 20, "total_positions": 437, "gt_mem_token_count": 11, "pred_mem_token_count": 211, "correct_mem_token_count": 2, "mem_token_precision": 0.009478672985781991, "mem_token_recall": 0.18181818181818182, "mem_token_accuracy": 0.18181818181818182, "slot_norm_mean": 198.0, "slot_sim_mean": 1.0, "rank": 2}
{"global_idx": 21, "total_positions": 594, "gt_mem_token_count": 5, "pred_mem_token_count": 237, "correct_mem_token_count": 2, "mem_token_precision": 0.008438818565400843, "mem_token_recall": 0.4, "mem_token_accuracy": 0.4, "slot_norm_mean": 199.0, "slot_sim_mean": 0.99609375, "rank": 2}
{"global_idx": 22, "total_positions": 302, "gt_mem_token_count": 6, "pred_mem_token_count": 116, "correct_mem_token_count": 2, "mem_token_precision": 0.017241379310344827, "mem_token_recall": 0.3333333333333333, "mem_token_accuracy": 0.3333333333333333, "slot_norm_mean": 194.0, "slot_sim_mean": 0.99609375, "rank": 3}
{"global_idx": 23, "total_positions": 366, "gt_mem_token_count": 6, "pred_mem_token_count": 143, "correct_mem_token_count": 1, "mem_token_precision": 0.006993006993006993, "mem_token_recall": 0.16666666666666666, "mem_token_accuracy": 0.16666666666666666, "slot_norm_mean": 198.0, "slot_sim_mean": 1.0, "rank": 3}
{"global_idx": 24, "total_positions": 662, "gt_mem_token_count": 14, "pred_mem_token_count": 374, "correct_mem_token_count": 3, "mem_token_precision": 0.008021390374331552, "mem_token_recall": 0.21428571428571427, "mem_token_accuracy": 0.21428571428571427, "slot_norm_mean": 198.0, "slot_sim_mean": 1.0, "rank": 3}
{"global_idx": 25, "total_positions": 362, "gt_mem_token_count": 8, "pred_mem_token_count": 194, "correct_mem_token_count": 2, "mem_token_precision": 0.010309278350515464, "mem_token_recall": 0.25, "mem_token_accuracy": 0.25, "slot_norm_mean": 199.0, "slot_sim_mean": 1.0, "rank": 3}
{"global_idx": 26, "total_positions": 466, "gt_mem_token_count": 13, "pred_mem_token_count": 178, "correct_mem_token_count": 1, "mem_token_precision": 0.0056179775280898875, "mem_token_recall": 0.07692307692307693, "mem_token_accuracy": 0.07692307692307693, "slot_norm_mean": 199.0, "slot_sim_mean": 0.99609375, "rank": 3}
{"global_idx": 27, "total_positions": 712, "gt_mem_token_count": 7, "pred_mem_token_count": 444, "correct_mem_token_count": 2, "mem_token_precision": 0.0045045045045045045, "mem_token_recall": 0.2857142857142857, "mem_token_accuracy": 0.2857142857142857, "slot_norm_mean": 197.0, "slot_sim_mean": 0.9921875, "rank": 3}
{"global_idx": 28, "total_positions": 631, "gt_mem_token_count": 17, "pred_mem_token_count": 447, "correct_mem_token_count": 3, "mem_token_precision": 0.006711409395973154, "mem_token_recall": 0.17647058823529413, "mem_token_accuracy": 0.17647058823529413, "slot_norm_mean": 200.0, "slot_sim_mean": 0.9921875, "rank": 3}
{"global_idx": 29, "total_positions": 591, "gt_mem_token_count": 7, "pred_mem_token_count": 311, "correct_mem_token_count": 1, "mem_token_precision": 0.003215434083601286, "mem_token_recall": 0.14285714285714285, "mem_token_accuracy": 0.14285714285714285, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 3}