| { | |
| "best_metric": 0.6833301782608032, | |
| "best_model_checkpoint": "mistralai/Mistral-7B-Instruct-v0.2_trail-/checkpoint-1600", | |
| "epoch": 0.9696969696969697, | |
| "eval_steps": 200, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.0257179737091064, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.6968803405761719, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.7078455686569214, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8432, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.6603143215179443, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8382, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.6785234212875366, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.273807406425476, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8302, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.3506838083267212, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7588, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.3038816452026367, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7462, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.4663119316101074, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7391, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.2945542335510254, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7768, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.258899211883545, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7737, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.416283369064331, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7422, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.200121283531189, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7306, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.1042457818984985, | |
| "learning_rate": 2e-05, | |
| "loss": 0.733, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.3173305988311768, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7454, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.2873802185058594, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7218, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 1.2658429145812988, | |
| "learning_rate": 2e-05, | |
| "loss": 0.763, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.1320024728775024, | |
| "learning_rate": 2e-05, | |
| "loss": 0.754, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.074420690536499, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6971, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 1.051477074623108, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7318, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.72369384765625, | |
| "eval_runtime": 576.3119, | |
| "eval_samples_per_second": 0.953, | |
| "eval_steps_per_second": 0.095, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.084792971611023, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7234, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 1.2191482782363892, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7117, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.0391403436660767, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7561, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.1228817701339722, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7488, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.03204345703125, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7096, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.0652753114700317, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7035, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.0256322622299194, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7151, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.9747219681739807, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7161, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.028686761856079, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7268, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 1.129952073097229, | |
| "learning_rate": 2e-05, | |
| "loss": 0.812, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 1.1518712043762207, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7328, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 1.0078867673873901, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7201, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.050847053527832, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7003, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.9970359802246094, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6904, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.9830156564712524, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7167, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.121741771697998, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7053, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1.11673104763031, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7162, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.94569993019104, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6991, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.9942061305046082, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7207, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.0249754190444946, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7364, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.7096507549285889, | |
| "eval_runtime": 576.6307, | |
| "eval_samples_per_second": 0.952, | |
| "eval_steps_per_second": 0.095, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.0410763025283813, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7104, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.0619620084762573, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7713, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 1.0299198627471924, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6684, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.946596086025238, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7197, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 1.00041663646698, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7406, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.971476674079895, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6926, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.9575595259666443, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7121, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 1.0066837072372437, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7501, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.1008684635162354, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7413, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 1.004758358001709, | |
| "learning_rate": 2e-05, | |
| "loss": 0.726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 1.0132404565811157, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7446, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.928865909576416, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6484, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.0739837884902954, | |
| "learning_rate": 2e-05, | |
| "loss": 0.693, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.9825330376625061, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7004, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 1.034639596939087, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7102, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.9825816750526428, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6763, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.872897744178772, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7211, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 1.0789843797683716, | |
| "learning_rate": 2e-05, | |
| "loss": 0.744, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.8900558352470398, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7098, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.9795206785202026, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6974, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.7024338245391846, | |
| "eval_runtime": 576.7068, | |
| "eval_samples_per_second": 0.952, | |
| "eval_steps_per_second": 0.095, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.8986483812332153, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6655, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.0255687236785889, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6921, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1.1219247579574585, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7142, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 1.0987035036087036, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7698, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.976980984210968, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7185, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.9381852149963379, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6631, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 1.0329375267028809, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6894, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.921355128288269, | |
| "learning_rate": 2e-05, | |
| "loss": 0.753, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.9028052687644958, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7371, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.9813818335533142, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6981, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 1.2183573246002197, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7199, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.9314076900482178, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7096, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.8565794825553894, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6797, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.8477567434310913, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6874, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 1.0110888481140137, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7495, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.9757490158081055, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6809, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.8909426927566528, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6746, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.8148036003112793, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7196, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.9427577257156372, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7082, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.8812272548675537, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7031, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.6963450908660889, | |
| "eval_runtime": 576.5372, | |
| "eval_samples_per_second": 0.952, | |
| "eval_steps_per_second": 0.095, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 1.184993028640747, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6883, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.032034993171692, | |
| "learning_rate": 2e-05, | |
| "loss": 0.687, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.8716715574264526, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7196, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 1.0160155296325684, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7549, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.9079670906066895, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6564, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.9788998365402222, | |
| "learning_rate": 2e-05, | |
| "loss": 0.698, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.9993180632591248, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7041, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.8905129432678223, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7061, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.9284083247184753, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7213, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.9979264140129089, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7067, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.9622723460197449, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7078, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 1.0288429260253906, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7018, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.9015412926673889, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7013, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.9322758316993713, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7006, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.875117301940918, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6632, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.9057668447494507, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7009, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.8785907030105591, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7029, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.896600067615509, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6583, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.9632496237754822, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7226, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 1.0047279596328735, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7201, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.692192018032074, | |
| "eval_runtime": 576.3596, | |
| "eval_samples_per_second": 0.953, | |
| "eval_steps_per_second": 0.095, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.8589789271354675, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6875, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.9107193946838379, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6563, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.9334760308265686, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7311, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.8864697813987732, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7121, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.952052891254425, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6842, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.9001901745796204, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6769, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.963742733001709, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7003, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.9565225839614868, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7478, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.9401019811630249, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7475, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.8856386542320251, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6879, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.8875776529312134, | |
| "learning_rate": 2e-05, | |
| "loss": 0.705, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.9274523854255676, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7378, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.9206425547599792, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6691, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.8944551944732666, | |
| "learning_rate": 2e-05, | |
| "loss": 0.684, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.1095612049102783, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7046, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.9099195599555969, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6839, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.8802533745765686, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6668, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.9142954349517822, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6869, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.8676968812942505, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7255, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.8218028545379639, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7424, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.6879069209098816, | |
| "eval_runtime": 576.2219, | |
| "eval_samples_per_second": 0.953, | |
| "eval_steps_per_second": 0.095, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.8519162535667419, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7128, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.8599090576171875, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7309, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.9774763584136963, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7092, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.9119387865066528, | |
| "learning_rate": 2e-05, | |
| "loss": 0.682, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.9051375985145569, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7042, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.9292181134223938, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6991, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.9441558718681335, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6838, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.8878441452980042, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6815, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.9556174874305725, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6765, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.8373817205429077, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7348, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.9634573459625244, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6846, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.8429288268089294, | |
| "learning_rate": 2e-05, | |
| "loss": 0.678, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.9088312387466431, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6949, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.9536995887756348, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6794, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.9287436008453369, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7111, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.8534522652626038, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6892, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.9239506721496582, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7138, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.9194501042366028, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7232, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.961037278175354, | |
| "learning_rate": 2e-05, | |
| "loss": 0.697, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.8385772109031677, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7016, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.6852899789810181, | |
| "eval_runtime": 576.2672, | |
| "eval_samples_per_second": 0.953, | |
| "eval_steps_per_second": 0.095, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 1.0281404256820679, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7012, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 1.0333633422851562, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7501, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.9055823683738708, | |
| "learning_rate": 2e-05, | |
| "loss": 0.738, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.9356181025505066, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6842, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.8437691926956177, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6658, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 1.0060279369354248, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6954, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.8564276099205017, | |
| "learning_rate": 2e-05, | |
| "loss": 0.684, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.9397062659263611, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7047, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.9040536284446716, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7001, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.9114941358566284, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6796, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.9135074615478516, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7335, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.8748692274093628, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6922, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.8640381097793579, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6638, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.9141325950622559, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6729, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.925592839717865, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7008, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.9290179014205933, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7058, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.8498104810714722, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6838, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.9508926868438721, | |
| "learning_rate": 2e-05, | |
| "loss": 0.72, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.8391693830490112, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6693, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.8421803712844849, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6953, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.6833301782608032, | |
| "eval_runtime": 576.54, | |
| "eval_samples_per_second": 0.952, | |
| "eval_steps_per_second": 0.095, | |
| "step": 1600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1649, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "total_flos": 4.1937076224e+17, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |