sft_lora / workmem /validation /validation_step_900.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": 222, "correct_mem_token_count": 3, "mem_token_precision": 0.013513513513513514, "mem_token_recall": 0.2727272727272727, "mem_token_accuracy": 0.2727272727272727, "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": 283, "correct_mem_token_count": 2, "mem_token_precision": 0.007067137809187279, "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": 459, "correct_mem_token_count": 4, "mem_token_precision": 0.008714596949891068, "mem_token_recall": 0.8, "mem_token_accuracy": 0.8, "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": 186, "correct_mem_token_count": 3, "mem_token_precision": 0.016129032258064516, "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": 219, "correct_mem_token_count": 2, "mem_token_precision": 0.0091324200913242, "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": 185, "correct_mem_token_count": 2, "mem_token_precision": 0.010810810810810811, "mem_token_recall": 0.3333333333333333, "mem_token_accuracy": 0.3333333333333333, "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": 376, "correct_mem_token_count": 1, "mem_token_precision": 0.0026595744680851063, "mem_token_recall": 0.09090909090909091, "mem_token_accuracy": 0.09090909090909091, "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": 471, "correct_mem_token_count": 4, "mem_token_precision": 0.008492569002123142, "mem_token_recall": 0.23529411764705882, "mem_token_accuracy": 0.23529411764705882, "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": 325, "correct_mem_token_count": 1, "mem_token_precision": 0.003076923076923077, "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": 403, "correct_mem_token_count": 4, "mem_token_precision": 0.009925558312655087, "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": 263, "correct_mem_token_count": 3, "mem_token_precision": 0.011406844106463879, "mem_token_recall": 0.23076923076923078, "mem_token_accuracy": 0.23076923076923078, "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": 166, "correct_mem_token_count": 1, "mem_token_precision": 0.006024096385542169, "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": 188, "correct_mem_token_count": 2, "mem_token_precision": 0.010638297872340425, "mem_token_recall": 0.13333333333333333, "mem_token_accuracy": 0.13333333333333333, "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": 230, "correct_mem_token_count": 2, "mem_token_precision": 0.008695652173913044, "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": 524, "correct_mem_token_count": 4, "mem_token_precision": 0.007633587786259542, "mem_token_recall": 0.4, "mem_token_accuracy": 0.4, "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": 372, "correct_mem_token_count": 2, "mem_token_precision": 0.005376344086021506, "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": 155, "correct_mem_token_count": 2, "mem_token_precision": 0.012903225806451613, "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": 188, "correct_mem_token_count": 2, "mem_token_precision": 0.010638297872340425, "mem_token_recall": 0.2, "mem_token_accuracy": 0.2, "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": 437, "correct_mem_token_count": 2, "mem_token_precision": 0.004576659038901602, "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": 115, "correct_mem_token_count": 3, "mem_token_precision": 0.02608695652173913, "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": 222, "correct_mem_token_count": 3, "mem_token_precision": 0.013513513513513514, "mem_token_recall": 0.2727272727272727, "mem_token_accuracy": 0.2727272727272727, "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": 283, "correct_mem_token_count": 2, "mem_token_precision": 0.007067137809187279, "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": 121, "correct_mem_token_count": 2, "mem_token_precision": 0.01652892561983471, "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": 159, "correct_mem_token_count": 1, "mem_token_precision": 0.006289308176100629, "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": 395, "correct_mem_token_count": 2, "mem_token_precision": 0.005063291139240506, "mem_token_recall": 0.14285714285714285, "mem_token_accuracy": 0.14285714285714285, "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": 226, "correct_mem_token_count": 2, "mem_token_precision": 0.008849557522123894, "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": 194, "correct_mem_token_count": 1, "mem_token_precision": 0.005154639175257732, "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": 465, "correct_mem_token_count": 3, "mem_token_precision": 0.0064516129032258064, "mem_token_recall": 0.42857142857142855, "mem_token_accuracy": 0.42857142857142855, "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": 471, "correct_mem_token_count": 4, "mem_token_precision": 0.008492569002123142, "mem_token_recall": 0.23529411764705882, "mem_token_accuracy": 0.23529411764705882, "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": 325, "correct_mem_token_count": 1, "mem_token_precision": 0.003076923076923077, "mem_token_recall": 0.14285714285714285, "mem_token_accuracy": 0.14285714285714285, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 3}