sft_lora / workmem /validation /validation_step_550.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": 270, "correct_mem_token_count": 2, "mem_token_precision": 0.007407407407407408, "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": 457, "correct_mem_token_count": 4, "mem_token_precision": 0.0087527352297593, "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": 178, "correct_mem_token_count": 3, "mem_token_precision": 0.016853932584269662, "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": 212, "correct_mem_token_count": 2, "mem_token_precision": 0.009433962264150943, "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": 370, "correct_mem_token_count": 1, "mem_token_precision": 0.002702702702702703, "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": 3, "mem_token_precision": 0.0064794816414686825, "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": 320, "correct_mem_token_count": 2, "mem_token_precision": 0.00625, "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": 160, "correct_mem_token_count": 1, "mem_token_precision": 0.00625, "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": 185, "correct_mem_token_count": 3, "mem_token_precision": 0.016216216216216217, "mem_token_recall": 0.2, "mem_token_accuracy": 0.2, "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": 521, "correct_mem_token_count": 4, "mem_token_precision": 0.007677543186180422, "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": 370, "correct_mem_token_count": 2, "mem_token_precision": 0.005405405405405406, "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": 154, "correct_mem_token_count": 2, "mem_token_precision": 0.012987012987012988, "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": 182, "correct_mem_token_count": 2, "mem_token_precision": 0.01098901098901099, "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": 434, "correct_mem_token_count": 2, "mem_token_precision": 0.004608294930875576, "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": 109, "correct_mem_token_count": 3, "mem_token_precision": 0.027522935779816515, "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": 270, "correct_mem_token_count": 2, "mem_token_precision": 0.007407407407407408, "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": 120, "correct_mem_token_count": 2, "mem_token_precision": 0.016666666666666666, "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": 153, "correct_mem_token_count": 1, "mem_token_precision": 0.006535947712418301, "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": 390, "correct_mem_token_count": 2, "mem_token_precision": 0.005128205128205128, "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": 221, "correct_mem_token_count": 2, "mem_token_precision": 0.00904977375565611, "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": 191, "correct_mem_token_count": 1, "mem_token_precision": 0.005235602094240838, "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": 462, "correct_mem_token_count": 3, "mem_token_precision": 0.006493506493506494, "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": 3, "mem_token_precision": 0.0064794816414686825, "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": 320, "correct_mem_token_count": 2, "mem_token_precision": 0.00625, "mem_token_recall": 0.2857142857142857, "mem_token_accuracy": 0.2857142857142857, "slot_norm_mean": 200.0, "slot_sim_mean": 0.99609375, "rank": 3}