| { | |
| "best_metric": 1.2662755250930786, | |
| "best_model_checkpoint": "/home/datta0/models/lora_final/Meta-Llama-3-8B_magiccoder_reverse/checkpoint-152", | |
| "epoch": 0.9846153846153847, | |
| "eval_steps": 4, | |
| "global_step": 152, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006477732793522267, | |
| "grad_norm": 7.972510814666748, | |
| "learning_rate": 7.5e-05, | |
| "loss": 1.3889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012955465587044534, | |
| "grad_norm": 8.65783977508545, | |
| "learning_rate": 0.00015, | |
| "loss": 1.5051, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "grad_norm": 8.450983047485352, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2593, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "eval_loss": 1.4180008172988892, | |
| "eval_runtime": 26.5474, | |
| "eval_samples_per_second": 18.646, | |
| "eval_steps_per_second": 2.335, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.038866396761133605, | |
| "grad_norm": 10.967939376831055, | |
| "learning_rate": 0.00029986842451482874, | |
| "loss": 1.4591, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.051821862348178135, | |
| "grad_norm": 9.95240306854248, | |
| "learning_rate": 0.0002994739288874256, | |
| "loss": 1.4127, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.051821862348178135, | |
| "eval_loss": 1.395808458328247, | |
| "eval_runtime": 26.5564, | |
| "eval_samples_per_second": 18.64, | |
| "eval_steps_per_second": 2.335, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06477732793522267, | |
| "grad_norm": 7.500934600830078, | |
| "learning_rate": 0.0002988172051971717, | |
| "loss": 1.3336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07773279352226721, | |
| "grad_norm": 10.566226959228516, | |
| "learning_rate": 0.0002978994055605757, | |
| "loss": 1.3964, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07773279352226721, | |
| "eval_loss": 1.3813759088516235, | |
| "eval_runtime": 26.5682, | |
| "eval_samples_per_second": 18.631, | |
| "eval_steps_per_second": 2.334, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09068825910931175, | |
| "grad_norm": 6.47328519821167, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 1.4443, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10364372469635627, | |
| "grad_norm": 6.948887348175049, | |
| "learning_rate": 0.00029528747416929463, | |
| "loss": 1.3824, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10364372469635627, | |
| "eval_loss": 1.3679261207580566, | |
| "eval_runtime": 26.4518, | |
| "eval_samples_per_second": 18.713, | |
| "eval_steps_per_second": 2.344, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11659919028340081, | |
| "grad_norm": 6.1149091720581055, | |
| "learning_rate": 0.00029359792462981004, | |
| "loss": 1.3267, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "grad_norm": 8.199859619140625, | |
| "learning_rate": 0.00029165645553562214, | |
| "loss": 1.4044, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "eval_loss": 1.3733282089233398, | |
| "eval_runtime": 26.4323, | |
| "eval_samples_per_second": 18.727, | |
| "eval_steps_per_second": 2.346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14251012145748987, | |
| "grad_norm": 12.22414779663086, | |
| "learning_rate": 0.00028946647288323766, | |
| "loss": 1.4047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15546558704453442, | |
| "grad_norm": 7.005305290222168, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 1.3092, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15546558704453442, | |
| "eval_loss": 1.363875150680542, | |
| "eval_runtime": 26.302, | |
| "eval_samples_per_second": 18.82, | |
| "eval_steps_per_second": 2.357, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 12.295991897583008, | |
| "learning_rate": 0.0002843567640359119, | |
| "loss": 1.3037, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1813765182186235, | |
| "grad_norm": 10.879226684570312, | |
| "learning_rate": 0.0002814460020065795, | |
| "loss": 1.3823, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1813765182186235, | |
| "eval_loss": 1.4074506759643555, | |
| "eval_runtime": 52.504, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 1.181, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19433198380566802, | |
| "grad_norm": 18.48771095275879, | |
| "learning_rate": 0.000278304639024076, | |
| "loss": 1.414, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20728744939271254, | |
| "grad_norm": 12.401382446289062, | |
| "learning_rate": 0.00027493818610651487, | |
| "loss": 1.3878, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20728744939271254, | |
| "eval_loss": 1.3768298625946045, | |
| "eval_runtime": 52.6159, | |
| "eval_samples_per_second": 9.408, | |
| "eval_steps_per_second": 1.178, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2202429149797571, | |
| "grad_norm": 9.700746536254883, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 1.4156, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23319838056680162, | |
| "grad_norm": 18.97345542907715, | |
| "learning_rate": 0.00026755401859887595, | |
| "loss": 1.3653, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23319838056680162, | |
| "eval_loss": 1.3592467308044434, | |
| "eval_runtime": 52.6554, | |
| "eval_samples_per_second": 9.401, | |
| "eval_steps_per_second": 1.177, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24615384615384617, | |
| "grad_norm": 4.934860706329346, | |
| "learning_rate": 0.00026354925834776345, | |
| "loss": 1.2749, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "grad_norm": 9.491981506347656, | |
| "learning_rate": 0.0002593452941132117, | |
| "loss": 1.4395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "eval_loss": 1.3594356775283813, | |
| "eval_runtime": 50.9109, | |
| "eval_samples_per_second": 9.723, | |
| "eval_steps_per_second": 1.218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2720647773279352, | |
| "grad_norm": 8.243218421936035, | |
| "learning_rate": 0.0002549495010770048, | |
| "loss": 1.3816, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.28502024291497974, | |
| "grad_norm": 7.602082252502441, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 1.3805, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.28502024291497974, | |
| "eval_loss": 1.34442937374115, | |
| "eval_runtime": 52.904, | |
| "eval_samples_per_second": 9.357, | |
| "eval_steps_per_second": 1.172, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2979757085020243, | |
| "grad_norm": 5.125858783721924, | |
| "learning_rate": 0.0002456135984623034, | |
| "loss": 1.3314, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.31093117408906884, | |
| "grad_norm": 4.09897518157959, | |
| "learning_rate": 0.00024068986722935624, | |
| "loss": 1.2631, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.31093117408906884, | |
| "eval_loss": 1.3353846073150635, | |
| "eval_runtime": 52.5161, | |
| "eval_samples_per_second": 9.426, | |
| "eval_steps_per_second": 1.181, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.32388663967611336, | |
| "grad_norm": 6.234148025512695, | |
| "learning_rate": 0.00023560703515266478, | |
| "loss": 1.3797, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 7.174957275390625, | |
| "learning_rate": 0.00023037401924684946, | |
| "loss": 1.3346, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "eval_loss": 1.3409483432769775, | |
| "eval_runtime": 52.7077, | |
| "eval_samples_per_second": 9.391, | |
| "eval_steps_per_second": 1.176, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3497975708502024, | |
| "grad_norm": 6.94388484954834, | |
| "learning_rate": 0.000225, | |
| "loss": 1.2991, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.362753036437247, | |
| "grad_norm": 5.7069621086120605, | |
| "learning_rate": 0.00021949440526797926, | |
| "loss": 1.3776, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.362753036437247, | |
| "eval_loss": 1.3367204666137695, | |
| "eval_runtime": 52.524, | |
| "eval_samples_per_second": 9.424, | |
| "eval_steps_per_second": 1.18, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3757085020242915, | |
| "grad_norm": 3.7093050479888916, | |
| "learning_rate": 0.00021386689373476087, | |
| "loss": 1.2811, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "grad_norm": 4.604982376098633, | |
| "learning_rate": 0.00020812733796781542, | |
| "loss": 1.3407, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "eval_loss": 1.3290596008300781, | |
| "eval_runtime": 53.0771, | |
| "eval_samples_per_second": 9.326, | |
| "eval_steps_per_second": 1.168, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.40161943319838056, | |
| "grad_norm": 4.813035011291504, | |
| "learning_rate": 0.00020228580709827227, | |
| "loss": 1.3081, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4145748987854251, | |
| "grad_norm": 5.186892509460449, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 1.3939, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4145748987854251, | |
| "eval_loss": 1.3306726217269897, | |
| "eval_runtime": 52.8006, | |
| "eval_samples_per_second": 9.375, | |
| "eval_steps_per_second": 1.174, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.42753036437246966, | |
| "grad_norm": 4.551775932312012, | |
| "learning_rate": 0.00019033797309228983, | |
| "loss": 1.2994, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4404858299595142, | |
| "grad_norm": 4.376237392425537, | |
| "learning_rate": 0.00018425263051659836, | |
| "loss": 1.2555, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4404858299595142, | |
| "eval_loss": 1.325662612915039, | |
| "eval_runtime": 26.5626, | |
| "eval_samples_per_second": 18.635, | |
| "eval_steps_per_second": 2.334, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4534412955465587, | |
| "grad_norm": 3.780867338180542, | |
| "learning_rate": 0.0001781071971878587, | |
| "loss": 1.3114, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46639676113360323, | |
| "grad_norm": 4.040090560913086, | |
| "learning_rate": 0.00017191245428436173, | |
| "loss": 1.3227, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.46639676113360323, | |
| "eval_loss": 1.3216441869735718, | |
| "eval_runtime": 26.5607, | |
| "eval_samples_per_second": 18.637, | |
| "eval_steps_per_second": 2.334, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.47935222672064776, | |
| "grad_norm": 4.139721393585205, | |
| "learning_rate": 0.000165679269490148, | |
| "loss": 1.292, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "grad_norm": 3.38668155670166, | |
| "learning_rate": 0.000159418577929397, | |
| "loss": 1.2664, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.49230769230769234, | |
| "eval_loss": 1.323757290840149, | |
| "eval_runtime": 26.5608, | |
| "eval_samples_per_second": 18.636, | |
| "eval_steps_per_second": 2.334, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 5.189659118652344, | |
| "learning_rate": 0.00015314136298250354, | |
| "loss": 1.3246, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5182186234817814, | |
| "grad_norm": 4.31968355178833, | |
| "learning_rate": 0.00014685863701749646, | |
| "loss": 1.3542, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5182186234817814, | |
| "eval_loss": 1.3156659603118896, | |
| "eval_runtime": 26.5254, | |
| "eval_samples_per_second": 18.661, | |
| "eval_steps_per_second": 2.337, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5311740890688259, | |
| "grad_norm": 3.1360971927642822, | |
| "learning_rate": 0.000140581422070603, | |
| "loss": 1.3407, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5441295546558704, | |
| "grad_norm": 4.838674068450928, | |
| "learning_rate": 0.000134320730509852, | |
| "loss": 1.2873, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5441295546558704, | |
| "eval_loss": 1.3166635036468506, | |
| "eval_runtime": 26.4764, | |
| "eval_samples_per_second": 18.696, | |
| "eval_steps_per_second": 2.342, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.557085020242915, | |
| "grad_norm": 3.8474254608154297, | |
| "learning_rate": 0.00012808754571563827, | |
| "loss": 1.3014, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5700404858299595, | |
| "grad_norm": 4.670653820037842, | |
| "learning_rate": 0.00012189280281214126, | |
| "loss": 1.3065, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5700404858299595, | |
| "eval_loss": 1.310920238494873, | |
| "eval_runtime": 26.3754, | |
| "eval_samples_per_second": 18.768, | |
| "eval_steps_per_second": 2.351, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.582995951417004, | |
| "grad_norm": 2.9593794345855713, | |
| "learning_rate": 0.00011574736948340163, | |
| "loss": 1.2962, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5959514170040486, | |
| "grad_norm": 4.062413215637207, | |
| "learning_rate": 0.00010966202690771014, | |
| "loss": 1.4021, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5959514170040486, | |
| "eval_loss": 1.3056426048278809, | |
| "eval_runtime": 26.2485, | |
| "eval_samples_per_second": 18.858, | |
| "eval_steps_per_second": 2.362, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6089068825910932, | |
| "grad_norm": 3.7216620445251465, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 1.2427, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6218623481781377, | |
| "grad_norm": 3.2399404048919678, | |
| "learning_rate": 9.771419290172773e-05, | |
| "loss": 1.2277, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6218623481781377, | |
| "eval_loss": 1.3020737171173096, | |
| "eval_runtime": 52.6322, | |
| "eval_samples_per_second": 9.405, | |
| "eval_steps_per_second": 1.178, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6348178137651822, | |
| "grad_norm": 3.834902286529541, | |
| "learning_rate": 9.187266203218456e-05, | |
| "loss": 1.3496, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "grad_norm": 3.2897722721099854, | |
| "learning_rate": 8.613310626523909e-05, | |
| "loss": 1.3014, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "eval_loss": 1.2999552488327026, | |
| "eval_runtime": 54.2992, | |
| "eval_samples_per_second": 9.116, | |
| "eval_steps_per_second": 1.142, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6607287449392713, | |
| "grad_norm": 3.6135973930358887, | |
| "learning_rate": 8.050559473202077e-05, | |
| "loss": 1.3298, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 3.015789270401001, | |
| "learning_rate": 7.500000000000002e-05, | |
| "loss": 1.2138, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "eval_loss": 1.291136384010315, | |
| "eval_runtime": 51.4763, | |
| "eval_samples_per_second": 9.616, | |
| "eval_steps_per_second": 1.204, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6866396761133603, | |
| "grad_norm": 4.030185699462891, | |
| "learning_rate": 6.962598075315046e-05, | |
| "loss": 1.3277, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6995951417004048, | |
| "grad_norm": 3.46356463432312, | |
| "learning_rate": 6.439296484733525e-05, | |
| "loss": 1.2367, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6995951417004048, | |
| "eval_loss": 1.2903276681900024, | |
| "eval_runtime": 52.7315, | |
| "eval_samples_per_second": 9.387, | |
| "eval_steps_per_second": 1.176, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7125506072874493, | |
| "grad_norm": 2.628225326538086, | |
| "learning_rate": 5.931013277064377e-05, | |
| "loss": 1.2445, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.725506072874494, | |
| "grad_norm": 3.025768280029297, | |
| "learning_rate": 5.4386401537696536e-05, | |
| "loss": 1.2501, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.725506072874494, | |
| "eval_loss": 1.2843749523162842, | |
| "eval_runtime": 49.1826, | |
| "eval_samples_per_second": 10.065, | |
| "eval_steps_per_second": 1.261, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7384615384615385, | |
| "grad_norm": 3.5894341468811035, | |
| "learning_rate": 4.963040904617131e-05, | |
| "loss": 1.2593, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.751417004048583, | |
| "grad_norm": 2.926424503326416, | |
| "learning_rate": 4.5050498922995166e-05, | |
| "loss": 1.2942, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.751417004048583, | |
| "eval_loss": 1.2818949222564697, | |
| "eval_runtime": 53.1275, | |
| "eval_samples_per_second": 9.317, | |
| "eval_steps_per_second": 1.167, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7643724696356275, | |
| "grad_norm": 2.722059726715088, | |
| "learning_rate": 4.06547058867883e-05, | |
| "loss": 1.2031, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7773279352226721, | |
| "grad_norm": 3.154292583465576, | |
| "learning_rate": 3.645074165223655e-05, | |
| "loss": 1.2762, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7773279352226721, | |
| "eval_loss": 1.2779730558395386, | |
| "eval_runtime": 52.538, | |
| "eval_samples_per_second": 9.422, | |
| "eval_steps_per_second": 1.18, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7902834008097166, | |
| "grad_norm": 2.4806008338928223, | |
| "learning_rate": 3.2445981401124035e-05, | |
| "loss": 1.2446, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8032388663967611, | |
| "grad_norm": 3.3211684226989746, | |
| "learning_rate": 2.8647450843757897e-05, | |
| "loss": 1.2871, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8032388663967611, | |
| "eval_loss": 1.2753314971923828, | |
| "eval_runtime": 52.7282, | |
| "eval_samples_per_second": 9.388, | |
| "eval_steps_per_second": 1.176, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8161943319838056, | |
| "grad_norm": 2.937831163406372, | |
| "learning_rate": 2.5061813893485085e-05, | |
| "loss": 1.3213, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8291497975708502, | |
| "grad_norm": 2.3290576934814453, | |
| "learning_rate": 2.169536097592401e-05, | |
| "loss": 1.2829, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8291497975708502, | |
| "eval_loss": 1.2724393606185913, | |
| "eval_runtime": 52.6961, | |
| "eval_samples_per_second": 9.393, | |
| "eval_steps_per_second": 1.177, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 2.81623911857605, | |
| "learning_rate": 1.8553997993420495e-05, | |
| "loss": 1.2818, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8550607287449393, | |
| "grad_norm": 4.030830383300781, | |
| "learning_rate": 1.5643235964088064e-05, | |
| "loss": 1.272, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8550607287449393, | |
| "eval_loss": 1.269489049911499, | |
| "eval_runtime": 52.9327, | |
| "eval_samples_per_second": 9.351, | |
| "eval_steps_per_second": 1.171, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8680161943319838, | |
| "grad_norm": 2.359203815460205, | |
| "learning_rate": 1.2968181353609852e-05, | |
| "loss": 1.2634, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.8809716599190284, | |
| "grad_norm": 3.011812925338745, | |
| "learning_rate": 1.0533527116762296e-05, | |
| "loss": 1.2242, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8809716599190284, | |
| "eval_loss": 1.2684744596481323, | |
| "eval_runtime": 26.5394, | |
| "eval_samples_per_second": 18.652, | |
| "eval_steps_per_second": 2.336, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8939271255060729, | |
| "grad_norm": 3.0021610260009766, | |
| "learning_rate": 8.343544464377849e-06, | |
| "loss": 1.2567, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9068825910931174, | |
| "grad_norm": 2.6871109008789062, | |
| "learning_rate": 6.402075370189913e-06, | |
| "loss": 1.253, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9068825910931174, | |
| "eval_loss": 1.2677539587020874, | |
| "eval_runtime": 26.5802, | |
| "eval_samples_per_second": 18.623, | |
| "eval_steps_per_second": 2.333, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9198380566801619, | |
| "grad_norm": 2.9042418003082275, | |
| "learning_rate": 4.712525830705338e-06, | |
| "loss": 1.2273, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9327935222672065, | |
| "grad_norm": 2.7735819816589355, | |
| "learning_rate": 3.2778598899291465e-06, | |
| "loss": 1.2116, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9327935222672065, | |
| "eval_loss": 1.26712167263031, | |
| "eval_runtime": 26.5685, | |
| "eval_samples_per_second": 18.631, | |
| "eval_steps_per_second": 2.334, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.945748987854251, | |
| "grad_norm": 3.1122586727142334, | |
| "learning_rate": 2.100594439424269e-06, | |
| "loss": 1.2549, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9587044534412955, | |
| "grad_norm": 2.9394922256469727, | |
| "learning_rate": 1.1827948028283352e-06, | |
| "loss": 1.2356, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9587044534412955, | |
| "eval_loss": 1.2666473388671875, | |
| "eval_runtime": 26.5192, | |
| "eval_samples_per_second": 18.666, | |
| "eval_steps_per_second": 2.338, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.97165991902834, | |
| "grad_norm": 3.1697134971618652, | |
| "learning_rate": 5.260711125743444e-07, | |
| "loss": 1.2141, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9846153846153847, | |
| "grad_norm": 2.3742239475250244, | |
| "learning_rate": 1.315754851712425e-07, | |
| "loss": 1.2087, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.9846153846153847, | |
| "eval_loss": 1.2662755250930786, | |
| "eval_runtime": 26.4031, | |
| "eval_samples_per_second": 18.748, | |
| "eval_steps_per_second": 2.348, | |
| "step": 152 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 154, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.140047273385001e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |