| { | |
| "best_metric": 0.11676687747240067, | |
| "best_model_checkpoint": "output/single/quirky_sciq_raw/checkpoint-2048", | |
| "epoch": 6.540518962075848, | |
| "eval_steps": 10000000000, | |
| "global_step": 2048, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "eval_val_acc_stderr": 0.012937023555103245, | |
| "eval_val_accuracy": 0.8282352941176471, | |
| "eval_val_loss": 1.4692819118499756, | |
| "eval_val_runtime": 32.1876, | |
| "eval_val_samples_per_second": 26.408, | |
| "eval_val_steps_per_second": 3.324, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_val_alice_acc_stderr": 0.01508756447132745, | |
| "eval_val_alice_accuracy": 0.8891454965357968, | |
| "eval_val_alice_loss": 1.4051198959350586, | |
| "eval_val_alice_runtime": 16.4546, | |
| "eval_val_alice_samples_per_second": 26.315, | |
| "eval_val_alice_steps_per_second": 3.343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_val_bob_acc_stderr": 0.02083661056330264, | |
| "eval_val_bob_accuracy": 0.762589928057554, | |
| "eval_val_bob_loss": 1.537455677986145, | |
| "eval_val_bob_runtime": 16.6246, | |
| "eval_val_bob_samples_per_second": 25.083, | |
| "eval_val_bob_steps_per_second": 3.188, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_val_bob_gt_acc_stderr": 0.015341286771526373, | |
| "eval_val_bob_gt_accuracy": 0.8896882494004796, | |
| "eval_val_bob_gt_loss": 1.4268440008163452, | |
| "eval_val_bob_gt_runtime": 16.763, | |
| "eval_val_bob_gt_samples_per_second": 24.876, | |
| "eval_val_bob_gt_steps_per_second": 3.162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_acc_stderr": 0.012937023555103245, | |
| "eval_val_accuracy": 0.8282352941176471, | |
| "eval_val_loss": 1.4688091278076172, | |
| "eval_val_runtime": 33.5257, | |
| "eval_val_samples_per_second": 25.354, | |
| "eval_val_steps_per_second": 3.192, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_alice_acc_stderr": 0.014948951634060766, | |
| "eval_val_alice_accuracy": 0.8914549653579676, | |
| "eval_val_alice_loss": 1.4036588668823242, | |
| "eval_val_alice_runtime": 16.9829, | |
| "eval_val_alice_samples_per_second": 25.496, | |
| "eval_val_alice_steps_per_second": 3.239, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_bob_acc_stderr": 0.020979742126541488, | |
| "eval_val_bob_accuracy": 0.7577937649880095, | |
| "eval_val_bob_loss": 1.5361874103546143, | |
| "eval_val_bob_runtime": 17.0578, | |
| "eval_val_bob_samples_per_second": 24.446, | |
| "eval_val_bob_steps_per_second": 3.107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_bob_gt_acc_stderr": 0.015628947031815964, | |
| "eval_val_bob_gt_accuracy": 0.8848920863309353, | |
| "eval_val_bob_gt_loss": 1.4273743629455566, | |
| "eval_val_bob_gt_runtime": 17.0684, | |
| "eval_val_bob_gt_samples_per_second": 24.431, | |
| "eval_val_bob_gt_steps_per_second": 3.105, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_acc_stderr": 0.012937023555103245, | |
| "eval_val_accuracy": 0.8282352941176471, | |
| "eval_val_loss": 1.469063401222229, | |
| "eval_val_runtime": 33.7146, | |
| "eval_val_samples_per_second": 25.212, | |
| "eval_val_steps_per_second": 3.174, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_alice_acc_stderr": 0.014948951634060766, | |
| "eval_val_alice_accuracy": 0.8914549653579676, | |
| "eval_val_alice_loss": 1.4030324220657349, | |
| "eval_val_alice_runtime": 17.0492, | |
| "eval_val_alice_samples_per_second": 25.397, | |
| "eval_val_alice_steps_per_second": 3.226, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_bob_acc_stderr": 0.020908628616120924, | |
| "eval_val_bob_accuracy": 0.7601918465227818, | |
| "eval_val_bob_loss": 1.5368480682373047, | |
| "eval_val_bob_runtime": 17.0771, | |
| "eval_val_bob_samples_per_second": 24.419, | |
| "eval_val_bob_steps_per_second": 3.104, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_val_bob_gt_acc_stderr": 0.015486230123570196, | |
| "eval_val_bob_gt_accuracy": 0.8872901678657075, | |
| "eval_val_bob_gt_loss": 1.4271358251571655, | |
| "eval_val_bob_gt_runtime": 17.0847, | |
| "eval_val_bob_gt_samples_per_second": 24.408, | |
| "eval_val_bob_gt_steps_per_second": 3.102, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_val_acc_stderr": 0.012901796011470488, | |
| "eval_val_accuracy": 0.8294117647058824, | |
| "eval_val_loss": 1.469651699066162, | |
| "eval_val_runtime": 33.6873, | |
| "eval_val_samples_per_second": 25.232, | |
| "eval_val_steps_per_second": 3.176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_val_alice_acc_stderr": 0.01480820963044188, | |
| "eval_val_alice_accuracy": 0.8937644341801386, | |
| "eval_val_alice_loss": 1.4056396484375, | |
| "eval_val_alice_runtime": 17.0533, | |
| "eval_val_alice_samples_per_second": 25.391, | |
| "eval_val_alice_steps_per_second": 3.225, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_val_bob_acc_stderr": 0.02083661056330264, | |
| "eval_val_bob_accuracy": 0.762589928057554, | |
| "eval_val_bob_loss": 1.5359561443328857, | |
| "eval_val_bob_runtime": 17.0852, | |
| "eval_val_bob_samples_per_second": 24.407, | |
| "eval_val_bob_steps_per_second": 3.102, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_val_bob_gt_acc_stderr": 0.015341286771526373, | |
| "eval_val_bob_gt_accuracy": 0.8896882494004796, | |
| "eval_val_bob_gt_loss": 1.4263936281204224, | |
| "eval_val_bob_gt_runtime": 17.0936, | |
| "eval_val_bob_gt_samples_per_second": 24.395, | |
| "eval_val_bob_gt_steps_per_second": 3.101, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_val_acc_stderr": 0.01297202990834543, | |
| "eval_val_accuracy": 0.8270588235294117, | |
| "eval_val_loss": 1.467901587486267, | |
| "eval_val_runtime": 33.707, | |
| "eval_val_samples_per_second": 25.217, | |
| "eval_val_steps_per_second": 3.174, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_val_alice_acc_stderr": 0.014948951634060766, | |
| "eval_val_alice_accuracy": 0.8914549653579676, | |
| "eval_val_alice_loss": 1.4035195112228394, | |
| "eval_val_alice_runtime": 17.0398, | |
| "eval_val_alice_samples_per_second": 25.411, | |
| "eval_val_alice_steps_per_second": 3.228, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_val_bob_acc_stderr": 0.020908628616120924, | |
| "eval_val_bob_accuracy": 0.7601918465227818, | |
| "eval_val_bob_loss": 1.535442590713501, | |
| "eval_val_bob_runtime": 17.0913, | |
| "eval_val_bob_samples_per_second": 24.398, | |
| "eval_val_bob_steps_per_second": 3.101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_val_bob_gt_acc_stderr": 0.015486230123570196, | |
| "eval_val_bob_gt_accuracy": 0.8872901678657075, | |
| "eval_val_bob_gt_loss": 1.4257303476333618, | |
| "eval_val_bob_gt_runtime": 17.0928, | |
| "eval_val_bob_gt_samples_per_second": 24.396, | |
| "eval_val_bob_gt_steps_per_second": 3.101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_val_acc_stderr": 0.012937023555103245, | |
| "eval_val_accuracy": 0.8282352941176471, | |
| "eval_val_loss": 1.4608973264694214, | |
| "eval_val_runtime": 33.7015, | |
| "eval_val_samples_per_second": 25.221, | |
| "eval_val_steps_per_second": 3.175, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_val_alice_acc_stderr": 0.014948951634060766, | |
| "eval_val_alice_accuracy": 0.8914549653579676, | |
| "eval_val_alice_loss": 1.396742343902588, | |
| "eval_val_alice_runtime": 17.0628, | |
| "eval_val_alice_samples_per_second": 25.377, | |
| "eval_val_alice_steps_per_second": 3.223, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_val_bob_acc_stderr": 0.02083661056330264, | |
| "eval_val_bob_accuracy": 0.762589928057554, | |
| "eval_val_bob_loss": 1.5283899307250977, | |
| "eval_val_bob_runtime": 17.0927, | |
| "eval_val_bob_samples_per_second": 24.396, | |
| "eval_val_bob_steps_per_second": 3.101, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_val_bob_gt_acc_stderr": 0.015341286771526373, | |
| "eval_val_bob_gt_accuracy": 0.8896882494004796, | |
| "eval_val_bob_gt_loss": 1.4182281494140625, | |
| "eval_val_bob_gt_runtime": 17.1142, | |
| "eval_val_bob_gt_samples_per_second": 24.366, | |
| "eval_val_bob_gt_steps_per_second": 3.097, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.102272727272729e-07, | |
| "loss": 1.4159, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_val_acc_stderr": 0.012937023555103245, | |
| "eval_val_accuracy": 0.8282352941176471, | |
| "eval_val_loss": 1.4041904211044312, | |
| "eval_val_runtime": 33.716, | |
| "eval_val_samples_per_second": 25.211, | |
| "eval_val_steps_per_second": 3.174, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_val_alice_acc_stderr": 0.01480820963044188, | |
| "eval_val_alice_accuracy": 0.8937644341801386, | |
| "eval_val_alice_loss": 1.3375937938690186, | |
| "eval_val_alice_runtime": 17.0702, | |
| "eval_val_alice_samples_per_second": 25.366, | |
| "eval_val_alice_steps_per_second": 3.222, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_val_bob_acc_stderr": 0.020908628616120924, | |
| "eval_val_bob_accuracy": 0.7601918465227818, | |
| "eval_val_bob_loss": 1.472985863685608, | |
| "eval_val_bob_runtime": 17.1363, | |
| "eval_val_bob_samples_per_second": 24.334, | |
| "eval_val_bob_steps_per_second": 3.093, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_val_bob_gt_acc_stderr": 0.015194053258476493, | |
| "eval_val_bob_gt_accuracy": 0.8920863309352518, | |
| "eval_val_bob_gt_loss": 1.3589271306991577, | |
| "eval_val_bob_gt_runtime": 17.1528, | |
| "eval_val_bob_gt_samples_per_second": 24.311, | |
| "eval_val_bob_gt_steps_per_second": 3.09, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.4204545454545458e-06, | |
| "loss": 1.2902, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_val_acc_stderr": 0.013041386157171642, | |
| "eval_val_accuracy": 0.8247058823529412, | |
| "eval_val_loss": 0.819312572479248, | |
| "eval_val_runtime": 33.8241, | |
| "eval_val_samples_per_second": 25.13, | |
| "eval_val_steps_per_second": 3.163, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_val_alice_acc_stderr": 0.014070292224264426, | |
| "eval_val_alice_accuracy": 0.9053117782909931, | |
| "eval_val_alice_loss": 0.73760586977005, | |
| "eval_val_alice_runtime": 17.1095, | |
| "eval_val_alice_samples_per_second": 25.308, | |
| "eval_val_alice_steps_per_second": 3.215, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_val_bob_acc_stderr": 0.021322054283776665, | |
| "eval_val_bob_accuracy": 0.7458033573141487, | |
| "eval_val_bob_loss": 0.9024503231048584, | |
| "eval_val_bob_runtime": 17.1531, | |
| "eval_val_bob_samples_per_second": 24.311, | |
| "eval_val_bob_steps_per_second": 3.09, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_val_bob_gt_acc_stderr": 0.015486230123570196, | |
| "eval_val_bob_gt_accuracy": 0.8872901678657075, | |
| "eval_val_bob_gt_loss": 0.7549682855606079, | |
| "eval_val_bob_gt_runtime": 17.1491, | |
| "eval_val_bob_gt_samples_per_second": 24.316, | |
| "eval_val_bob_gt_steps_per_second": 3.091, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.1306818181818183e-06, | |
| "loss": 0.8289, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.8409090909090916e-06, | |
| "loss": 0.412, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.5511363636363636e-06, | |
| "loss": 0.3014, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_val_acc_stderr": 0.010954525472743861, | |
| "eval_val_accuracy": 0.8847058823529412, | |
| "eval_val_loss": 0.30577030777931213, | |
| "eval_val_runtime": 33.8568, | |
| "eval_val_samples_per_second": 25.106, | |
| "eval_val_steps_per_second": 3.16, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_val_alice_acc_stderr": 0.012572317234488177, | |
| "eval_val_alice_accuracy": 0.9260969976905312, | |
| "eval_val_alice_loss": 0.21393465995788574, | |
| "eval_val_alice_runtime": 17.1088, | |
| "eval_val_alice_samples_per_second": 25.309, | |
| "eval_val_alice_steps_per_second": 3.215, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_val_bob_acc_stderr": 0.017983215186550393, | |
| "eval_val_bob_accuracy": 0.8393285371702638, | |
| "eval_val_bob_loss": 0.40229618549346924, | |
| "eval_val_bob_runtime": 17.1516, | |
| "eval_val_bob_samples_per_second": 24.313, | |
| "eval_val_bob_steps_per_second": 3.09, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_val_bob_gt_acc_stderr": 0.012256027700828325, | |
| "eval_val_bob_gt_accuracy": 0.9328537170263789, | |
| "eval_val_bob_gt_loss": 0.20910073816776276, | |
| "eval_val_bob_gt_runtime": 17.1417, | |
| "eval_val_bob_gt_samples_per_second": 24.327, | |
| "eval_val_bob_gt_steps_per_second": 3.092, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.2613636363636365e-06, | |
| "loss": 0.3062, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.9715909090909094e-06, | |
| "loss": 0.2271, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 5.681818181818183e-06, | |
| "loss": 0.2346, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 6.392045454545454e-06, | |
| "loss": 0.2203, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 7.102272727272727e-06, | |
| "loss": 0.1968, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_val_acc_stderr": 0.008648647548423583, | |
| "eval_val_accuracy": 0.9317647058823529, | |
| "eval_val_loss": 0.18704643845558167, | |
| "eval_val_runtime": 33.6882, | |
| "eval_val_samples_per_second": 25.231, | |
| "eval_val_steps_per_second": 3.176, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_val_alice_acc_stderr": 0.010323486896101533, | |
| "eval_val_alice_accuracy": 0.9515011547344111, | |
| "eval_val_alice_loss": 0.12077159434556961, | |
| "eval_val_alice_runtime": 17.0206, | |
| "eval_val_alice_samples_per_second": 25.44, | |
| "eval_val_alice_steps_per_second": 3.231, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_val_bob_acc_stderr": 0.014093125547753297, | |
| "eval_val_bob_accuracy": 0.9088729016786571, | |
| "eval_val_bob_loss": 0.25665926933288574, | |
| "eval_val_bob_runtime": 17.0565, | |
| "eval_val_bob_samples_per_second": 24.448, | |
| "eval_val_bob_steps_per_second": 3.107, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_val_bob_gt_acc_stderr": 0.01604432860757207, | |
| "eval_val_bob_gt_accuracy": 0.8776978417266187, | |
| "eval_val_bob_gt_loss": 0.31840986013412476, | |
| "eval_val_bob_gt_runtime": 17.0564, | |
| "eval_val_bob_gt_samples_per_second": 24.448, | |
| "eval_val_bob_gt_steps_per_second": 3.107, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 7.8125e-06, | |
| "loss": 0.2178, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.522727272727273e-06, | |
| "loss": 0.1919, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.232954545454546e-06, | |
| "loss": 0.1539, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 9.943181818181819e-06, | |
| "loss": 0.15, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.0653409090909092e-05, | |
| "loss": 0.176, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.1363636363636366e-05, | |
| "loss": 0.1293, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.2073863636363636e-05, | |
| "loss": 0.1577, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.2784090909090909e-05, | |
| "loss": 0.135, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.3494318181818182e-05, | |
| "loss": 0.1246, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.4204545454545455e-05, | |
| "loss": 0.0965, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_val_acc_stderr": 0.006907725389665332, | |
| "eval_val_accuracy": 0.9576470588235294, | |
| "eval_val_loss": 0.14458392560482025, | |
| "eval_val_runtime": 33.6709, | |
| "eval_val_samples_per_second": 25.244, | |
| "eval_val_steps_per_second": 3.178, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_val_alice_acc_stderr": 0.009333387164702351, | |
| "eval_val_alice_accuracy": 0.9607390300230947, | |
| "eval_val_alice_loss": 0.129893496632576, | |
| "eval_val_alice_runtime": 17.0239, | |
| "eval_val_alice_samples_per_second": 25.435, | |
| "eval_val_alice_steps_per_second": 3.231, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_val_bob_acc_stderr": 0.010212081074718785, | |
| "eval_val_bob_accuracy": 0.9544364508393285, | |
| "eval_val_bob_loss": 0.16120219230651855, | |
| "eval_val_bob_runtime": 17.0579, | |
| "eval_val_bob_samples_per_second": 24.446, | |
| "eval_val_bob_steps_per_second": 3.107, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "eval_val_bob_gt_acc_stderr": 0.016441676917357297, | |
| "eval_val_bob_gt_accuracy": 0.8705035971223022, | |
| "eval_val_bob_gt_loss": 0.5936062932014465, | |
| "eval_val_bob_gt_runtime": 17.0652, | |
| "eval_val_bob_gt_samples_per_second": 24.436, | |
| "eval_val_bob_gt_steps_per_second": 3.106, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.4914772727272729e-05, | |
| "loss": 0.1054, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.1164, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.6335227272727275e-05, | |
| "loss": 0.0701, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.7045454545454546e-05, | |
| "loss": 0.1118, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.775568181818182e-05, | |
| "loss": 0.088, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.8465909090909092e-05, | |
| "loss": 0.0578, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 1.9176136363636366e-05, | |
| "loss": 0.0737, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 1.9886363636363638e-05, | |
| "loss": 0.0777, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 1.9894763217238787e-05, | |
| "loss": 0.0562, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.976948133299925e-05, | |
| "loss": 0.0741, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 1.964419944875971e-05, | |
| "loss": 0.0504, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 1.951891756452017e-05, | |
| "loss": 0.0508, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 1.9393635680280633e-05, | |
| "loss": 0.0489, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 1.9268353796041094e-05, | |
| "loss": 0.0314, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1.9143071911801552e-05, | |
| "loss": 0.041, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 1.9017790027562014e-05, | |
| "loss": 0.0348, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 1.8892508143322475e-05, | |
| "loss": 0.0404, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.8767226259082937e-05, | |
| "loss": 0.0406, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 1.8641944374843398e-05, | |
| "loss": 0.0287, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.851666249060386e-05, | |
| "loss": 0.0382, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_val_acc_stderr": 0.004801960383990247, | |
| "eval_val_accuracy": 0.98, | |
| "eval_val_loss": 0.11676687747240067, | |
| "eval_val_runtime": 33.5165, | |
| "eval_val_samples_per_second": 25.361, | |
| "eval_val_steps_per_second": 3.192, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_val_alice_acc_stderr": 0.008200955905749383, | |
| "eval_val_alice_accuracy": 0.9699769053117783, | |
| "eval_val_alice_loss": 0.17065930366516113, | |
| "eval_val_alice_runtime": 16.9426, | |
| "eval_val_alice_samples_per_second": 25.557, | |
| "eval_val_alice_steps_per_second": 3.246, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_val_bob_acc_stderr": 0.004138631085700285, | |
| "eval_val_bob_accuracy": 0.9928057553956835, | |
| "eval_val_bob_loss": 0.06056825444102287, | |
| "eval_val_bob_runtime": 16.9895, | |
| "eval_val_bob_samples_per_second": 24.545, | |
| "eval_val_bob_steps_per_second": 3.12, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "eval_val_bob_gt_acc_stderr": 0.01787398723923547, | |
| "eval_val_bob_gt_accuracy": 0.841726618705036, | |
| "eval_val_bob_gt_loss": 1.0665634870529175, | |
| "eval_val_bob_gt_runtime": 16.987, | |
| "eval_val_bob_gt_samples_per_second": 24.548, | |
| "eval_val_bob_gt_steps_per_second": 3.12, | |
| "step": 2048 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 9390, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 10000000000, | |
| "total_flos": 7.4063386395648e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |