sft_lora / workmem /validation /validation_step_350.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": 221, "correct_mem_token_count": 3, "mem_token_precision": 0.013574660633484163, "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": 263, "correct_mem_token_count": 2, "mem_token_precision": 0.0076045627376425855, "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": 449, "correct_mem_token_count": 3, "mem_token_precision": 0.0066815144766146995, "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": 177, "correct_mem_token_count": 3, "mem_token_precision": 0.01694915254237288, "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": 201, "correct_mem_token_count": 2, "mem_token_precision": 0.009950248756218905, "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": 183, "correct_mem_token_count": 1, "mem_token_precision": 0.00546448087431694, "mem_token_recall": 0.16666666666666666, "mem_token_accuracy": 0.16666666666666666, "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": 366, "correct_mem_token_count": 1, "mem_token_precision": 0.00273224043715847, "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": 463, "correct_mem_token_count": 2, "mem_token_precision": 0.004319654427645789, "mem_token_recall": 0.11764705882352941, "mem_token_accuracy": 0.11764705882352941, "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": 316, "correct_mem_token_count": 2, "mem_token_precision": 0.006329113924050633, "mem_token_recall": 0.2857142857142857, "mem_token_accuracy": 0.2857142857142857, "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": 406, "correct_mem_token_count": 4, "mem_token_precision": 0.009852216748768473, "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": 262, "correct_mem_token_count": 1, "mem_token_precision": 0.003816793893129771, "mem_token_recall": 0.07692307692307693, "mem_token_accuracy": 0.07692307692307693, "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": 152, "correct_mem_token_count": 1, "mem_token_precision": 0.006578947368421052, "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": 182, "correct_mem_token_count": 1, "mem_token_precision": 0.005494505494505495, "mem_token_recall": 0.06666666666666667, "mem_token_accuracy": 0.06666666666666667, "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": 225, "correct_mem_token_count": 2, "mem_token_precision": 0.008888888888888889, "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": 518, "correct_mem_token_count": 3, "mem_token_precision": 0.005791505791505791, "mem_token_recall": 0.3, "mem_token_accuracy": 0.3, "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": 367, "correct_mem_token_count": 2, "mem_token_precision": 0.005449591280653951, "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": 153, "correct_mem_token_count": 2, "mem_token_precision": 0.013071895424836602, "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": 180, "correct_mem_token_count": 2, "mem_token_precision": 0.011111111111111112, "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": 432, "correct_mem_token_count": 2, "mem_token_precision": 0.004629629629629629, "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": 111, "correct_mem_token_count": 3, "mem_token_precision": 0.02702702702702703, "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": 221, "correct_mem_token_count": 3, "mem_token_precision": 0.013574660633484163, "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": 263, "correct_mem_token_count": 2, "mem_token_precision": 0.0076045627376425855, "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": 122, "correct_mem_token_count": 2, "mem_token_precision": 0.01639344262295082, "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": 148, "correct_mem_token_count": 1, "mem_token_precision": 0.006756756756756757, "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": 388, "correct_mem_token_count": 3, "mem_token_precision": 0.007731958762886598, "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": 216, "correct_mem_token_count": 2, "mem_token_precision": 0.009259259259259259, "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": 186, "correct_mem_token_count": 1, "mem_token_precision": 0.005376344086021506, "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": 455, "correct_mem_token_count": 3, "mem_token_precision": 0.006593406593406593, "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": 463, "correct_mem_token_count": 2, "mem_token_precision": 0.004319654427645789, "mem_token_recall": 0.11764705882352941, "mem_token_accuracy": 0.11764705882352941, "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": 316, "correct_mem_token_count": 2, "mem_token_precision": 0.006329113924050633, "mem_token_recall": 0.2857142857142857, "mem_token_accuracy": 0.2857142857142857, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 3}