{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1580, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0031645569620253164, "grad_norm": 3.2283780884454893, "learning_rate": 5.063291139240507e-07, "loss": 0.8116, "step": 1 }, { "epoch": 0.006329113924050633, "grad_norm": 3.2188603442246775, "learning_rate": 1.0126582278481013e-06, "loss": 0.8153, "step": 2 }, { "epoch": 0.00949367088607595, "grad_norm": 3.1624530862573925, "learning_rate": 1.518987341772152e-06, "loss": 0.8057, "step": 3 }, { "epoch": 0.012658227848101266, "grad_norm": 3.22955100727846, "learning_rate": 2.0253164556962026e-06, "loss": 0.81, "step": 4 }, { "epoch": 0.015822784810126583, "grad_norm": 2.941655334665881, "learning_rate": 2.5316455696202535e-06, "loss": 0.7939, "step": 5 }, { "epoch": 0.0189873417721519, "grad_norm": 2.472776925503555, "learning_rate": 3.037974683544304e-06, "loss": 0.7711, "step": 6 }, { "epoch": 0.022151898734177215, "grad_norm": 2.277844644601019, "learning_rate": 3.544303797468355e-06, "loss": 0.7639, "step": 7 }, { "epoch": 0.02531645569620253, "grad_norm": 1.5313546024349116, "learning_rate": 4.050632911392405e-06, "loss": 0.7154, "step": 8 }, { "epoch": 0.028481012658227847, "grad_norm": 1.4667537632653982, "learning_rate": 4.556962025316456e-06, "loss": 0.7129, "step": 9 }, { "epoch": 0.03164556962025317, "grad_norm": 1.319519887671064, "learning_rate": 5.063291139240507e-06, "loss": 0.6871, "step": 10 }, { "epoch": 0.03481012658227848, "grad_norm": 1.1766816254346608, "learning_rate": 5.569620253164557e-06, "loss": 0.6688, "step": 11 }, { "epoch": 0.0379746835443038, "grad_norm": 1.073943868205367, "learning_rate": 6.075949367088608e-06, "loss": 0.6632, "step": 12 }, { "epoch": 0.04113924050632911, "grad_norm": 1.0926799534910216, "learning_rate": 6.582278481012659e-06, "loss": 0.6124, "step": 13 }, { "epoch": 0.04430379746835443, "grad_norm": 1.1100040742185384, "learning_rate": 7.08860759493671e-06, "loss": 0.6073, "step": 14 }, { "epoch": 0.04746835443037975, "grad_norm": 0.888761695562074, "learning_rate": 7.5949367088607605e-06, "loss": 0.5894, "step": 15 }, { "epoch": 0.05063291139240506, "grad_norm": 0.6758157548865644, "learning_rate": 8.10126582278481e-06, "loss": 0.5762, "step": 16 }, { "epoch": 0.05379746835443038, "grad_norm": 0.6354870221991418, "learning_rate": 8.607594936708861e-06, "loss": 0.5549, "step": 17 }, { "epoch": 0.056962025316455694, "grad_norm": 1.0818393602476217, "learning_rate": 9.113924050632912e-06, "loss": 0.5441, "step": 18 }, { "epoch": 0.060126582278481014, "grad_norm": 0.9497309398255235, "learning_rate": 9.620253164556963e-06, "loss": 0.5394, "step": 19 }, { "epoch": 0.06329113924050633, "grad_norm": 0.6640600355412143, "learning_rate": 1.0126582278481014e-05, "loss": 0.5299, "step": 20 }, { "epoch": 0.06645569620253164, "grad_norm": 0.6778639195169567, "learning_rate": 1.0632911392405063e-05, "loss": 0.5272, "step": 21 }, { "epoch": 0.06962025316455696, "grad_norm": 0.6170349031641552, "learning_rate": 1.1139240506329114e-05, "loss": 0.5144, "step": 22 }, { "epoch": 0.07278481012658228, "grad_norm": 0.5413353032938518, "learning_rate": 1.1645569620253165e-05, "loss": 0.5064, "step": 23 }, { "epoch": 0.0759493670886076, "grad_norm": 0.45001748099238237, "learning_rate": 1.2151898734177216e-05, "loss": 0.5046, "step": 24 }, { "epoch": 0.07911392405063292, "grad_norm": 0.39658963448720047, "learning_rate": 1.2658227848101268e-05, "loss": 0.4969, "step": 25 }, { "epoch": 0.08227848101265822, "grad_norm": 0.40183658104277004, "learning_rate": 1.3164556962025317e-05, "loss": 0.4942, "step": 26 }, { "epoch": 0.08544303797468354, "grad_norm": 0.4370397275059912, "learning_rate": 1.3670886075949368e-05, "loss": 0.4846, "step": 27 }, { "epoch": 0.08860759493670886, "grad_norm": 0.3922331556411886, "learning_rate": 1.417721518987342e-05, "loss": 0.4899, "step": 28 }, { "epoch": 0.09177215189873418, "grad_norm": 0.33098798613511093, "learning_rate": 1.468354430379747e-05, "loss": 0.4819, "step": 29 }, { "epoch": 0.0949367088607595, "grad_norm": 0.3097439835661511, "learning_rate": 1.5189873417721521e-05, "loss": 0.4775, "step": 30 }, { "epoch": 0.0981012658227848, "grad_norm": 0.3132746172691913, "learning_rate": 1.5696202531645572e-05, "loss": 0.4618, "step": 31 }, { "epoch": 0.10126582278481013, "grad_norm": 0.27261195268142496, "learning_rate": 1.620253164556962e-05, "loss": 0.4675, "step": 32 }, { "epoch": 0.10443037974683544, "grad_norm": 0.2380027955055397, "learning_rate": 1.6708860759493674e-05, "loss": 0.4632, "step": 33 }, { "epoch": 0.10759493670886076, "grad_norm": 0.24329581825583457, "learning_rate": 1.7215189873417723e-05, "loss": 0.4687, "step": 34 }, { "epoch": 0.11075949367088607, "grad_norm": 0.27807012490669086, "learning_rate": 1.7721518987341772e-05, "loss": 0.4533, "step": 35 }, { "epoch": 0.11392405063291139, "grad_norm": 0.23121137538611075, "learning_rate": 1.8227848101265824e-05, "loss": 0.4564, "step": 36 }, { "epoch": 0.11708860759493671, "grad_norm": 0.21262695166729628, "learning_rate": 1.8734177215189874e-05, "loss": 0.4512, "step": 37 }, { "epoch": 0.12025316455696203, "grad_norm": 0.2276079861679562, "learning_rate": 1.9240506329113926e-05, "loss": 0.4531, "step": 38 }, { "epoch": 0.12341772151898735, "grad_norm": 0.224623063865439, "learning_rate": 1.974683544303798e-05, "loss": 0.4462, "step": 39 }, { "epoch": 0.12658227848101267, "grad_norm": 0.22440753977685726, "learning_rate": 2.0253164556962028e-05, "loss": 0.4476, "step": 40 }, { "epoch": 0.12974683544303797, "grad_norm": 0.16865692892634643, "learning_rate": 2.0759493670886077e-05, "loss": 0.44, "step": 41 }, { "epoch": 0.13291139240506328, "grad_norm": 0.19624291200111188, "learning_rate": 2.1265822784810126e-05, "loss": 0.4389, "step": 42 }, { "epoch": 0.1360759493670886, "grad_norm": 0.18245244277679612, "learning_rate": 2.177215189873418e-05, "loss": 0.4395, "step": 43 }, { "epoch": 0.13924050632911392, "grad_norm": 0.16790719647812663, "learning_rate": 2.2278481012658228e-05, "loss": 0.4343, "step": 44 }, { "epoch": 0.14240506329113925, "grad_norm": 0.16446970964093238, "learning_rate": 2.278481012658228e-05, "loss": 0.4333, "step": 45 }, { "epoch": 0.14556962025316456, "grad_norm": 0.18160984940475675, "learning_rate": 2.329113924050633e-05, "loss": 0.4332, "step": 46 }, { "epoch": 0.14873417721518986, "grad_norm": 0.15658864357656185, "learning_rate": 2.379746835443038e-05, "loss": 0.4324, "step": 47 }, { "epoch": 0.1518987341772152, "grad_norm": 0.1999807298602092, "learning_rate": 2.430379746835443e-05, "loss": 0.4294, "step": 48 }, { "epoch": 0.1550632911392405, "grad_norm": 0.17669051182522943, "learning_rate": 2.481012658227848e-05, "loss": 0.432, "step": 49 }, { "epoch": 0.15822784810126583, "grad_norm": 0.19509792877178064, "learning_rate": 2.5316455696202537e-05, "loss": 0.4244, "step": 50 }, { "epoch": 0.16139240506329114, "grad_norm": 0.1730476794818606, "learning_rate": 2.5822784810126586e-05, "loss": 0.4282, "step": 51 }, { "epoch": 0.16455696202531644, "grad_norm": 0.16528143658239364, "learning_rate": 2.6329113924050635e-05, "loss": 0.4189, "step": 52 }, { "epoch": 0.16772151898734178, "grad_norm": 0.1585022614754311, "learning_rate": 2.6835443037974687e-05, "loss": 0.4221, "step": 53 }, { "epoch": 0.17088607594936708, "grad_norm": 0.16226814180981206, "learning_rate": 2.7341772151898737e-05, "loss": 0.4293, "step": 54 }, { "epoch": 0.17405063291139242, "grad_norm": 0.19307142528123844, "learning_rate": 2.784810126582279e-05, "loss": 0.4237, "step": 55 }, { "epoch": 0.17721518987341772, "grad_norm": 0.13004554960654585, "learning_rate": 2.835443037974684e-05, "loss": 0.4184, "step": 56 }, { "epoch": 0.18037974683544303, "grad_norm": 0.18111237371248257, "learning_rate": 2.8860759493670888e-05, "loss": 0.4218, "step": 57 }, { "epoch": 0.18354430379746836, "grad_norm": 0.18236789498865674, "learning_rate": 2.936708860759494e-05, "loss": 0.4238, "step": 58 }, { "epoch": 0.18670886075949367, "grad_norm": 0.17716453045266856, "learning_rate": 2.987341772151899e-05, "loss": 0.4141, "step": 59 }, { "epoch": 0.189873417721519, "grad_norm": 0.2127228921697965, "learning_rate": 3.0379746835443042e-05, "loss": 0.4065, "step": 60 }, { "epoch": 0.1930379746835443, "grad_norm": 0.3589869891535893, "learning_rate": 3.088607594936709e-05, "loss": 0.4147, "step": 61 }, { "epoch": 0.1962025316455696, "grad_norm": 0.548737178033489, "learning_rate": 3.1392405063291144e-05, "loss": 0.4173, "step": 62 }, { "epoch": 0.19936708860759494, "grad_norm": 0.8634453788387079, "learning_rate": 3.1898734177215196e-05, "loss": 0.4173, "step": 63 }, { "epoch": 0.20253164556962025, "grad_norm": 1.058787467823482, "learning_rate": 3.240506329113924e-05, "loss": 0.4279, "step": 64 }, { "epoch": 0.20569620253164558, "grad_norm": 0.9560685174347762, "learning_rate": 3.2911392405063295e-05, "loss": 0.4239, "step": 65 }, { "epoch": 0.2088607594936709, "grad_norm": 1.0115891770803338, "learning_rate": 3.341772151898735e-05, "loss": 0.4237, "step": 66 }, { "epoch": 0.2120253164556962, "grad_norm": 0.6060339002885824, "learning_rate": 3.392405063291139e-05, "loss": 0.4173, "step": 67 }, { "epoch": 0.21518987341772153, "grad_norm": 0.8552236400558639, "learning_rate": 3.4430379746835445e-05, "loss": 0.4168, "step": 68 }, { "epoch": 0.21835443037974683, "grad_norm": 0.7064444098497009, "learning_rate": 3.49367088607595e-05, "loss": 0.4107, "step": 69 }, { "epoch": 0.22151898734177214, "grad_norm": 0.7431769383435711, "learning_rate": 3.5443037974683544e-05, "loss": 0.4134, "step": 70 }, { "epoch": 0.22468354430379747, "grad_norm": 0.6155088104582721, "learning_rate": 3.5949367088607596e-05, "loss": 0.4115, "step": 71 }, { "epoch": 0.22784810126582278, "grad_norm": 0.6322651224329503, "learning_rate": 3.645569620253165e-05, "loss": 0.3995, "step": 72 }, { "epoch": 0.2310126582278481, "grad_norm": 0.5340099863672824, "learning_rate": 3.69620253164557e-05, "loss": 0.405, "step": 73 }, { "epoch": 0.23417721518987342, "grad_norm": 0.5317598036101132, "learning_rate": 3.746835443037975e-05, "loss": 0.407, "step": 74 }, { "epoch": 0.23734177215189872, "grad_norm": 0.3820923082964144, "learning_rate": 3.79746835443038e-05, "loss": 0.4019, "step": 75 }, { "epoch": 0.24050632911392406, "grad_norm": 0.4743783611904098, "learning_rate": 3.848101265822785e-05, "loss": 0.4076, "step": 76 }, { "epoch": 0.24367088607594936, "grad_norm": 0.42588079168265214, "learning_rate": 3.89873417721519e-05, "loss": 0.3998, "step": 77 }, { "epoch": 0.2468354430379747, "grad_norm": 0.3755096769062494, "learning_rate": 3.949367088607596e-05, "loss": 0.4061, "step": 78 }, { "epoch": 0.25, "grad_norm": 0.43226980658181086, "learning_rate": 4e-05, "loss": 0.404, "step": 79 }, { "epoch": 0.25316455696202533, "grad_norm": 0.3242288673715512, "learning_rate": 4.0506329113924056e-05, "loss": 0.4016, "step": 80 }, { "epoch": 0.2563291139240506, "grad_norm": 0.35575490572570007, "learning_rate": 4.10126582278481e-05, "loss": 0.4019, "step": 81 }, { "epoch": 0.25949367088607594, "grad_norm": 0.2982483342909356, "learning_rate": 4.1518987341772154e-05, "loss": 0.4005, "step": 82 }, { "epoch": 0.2626582278481013, "grad_norm": 0.2710723904091289, "learning_rate": 4.202531645569621e-05, "loss": 0.3999, "step": 83 }, { "epoch": 0.26582278481012656, "grad_norm": 0.30565507974113293, "learning_rate": 4.253164556962025e-05, "loss": 0.3996, "step": 84 }, { "epoch": 0.2689873417721519, "grad_norm": 0.26998483032352755, "learning_rate": 4.3037974683544305e-05, "loss": 0.3991, "step": 85 }, { "epoch": 0.2721518987341772, "grad_norm": 0.29741715213064496, "learning_rate": 4.354430379746836e-05, "loss": 0.3941, "step": 86 }, { "epoch": 0.27531645569620256, "grad_norm": 0.2814305224109165, "learning_rate": 4.405063291139241e-05, "loss": 0.403, "step": 87 }, { "epoch": 0.27848101265822783, "grad_norm": 0.43346332512101193, "learning_rate": 4.4556962025316456e-05, "loss": 0.3953, "step": 88 }, { "epoch": 0.28164556962025317, "grad_norm": 0.40802633152268086, "learning_rate": 4.506329113924051e-05, "loss": 0.3996, "step": 89 }, { "epoch": 0.2848101265822785, "grad_norm": 0.40781186946422027, "learning_rate": 4.556962025316456e-05, "loss": 0.3969, "step": 90 }, { "epoch": 0.2879746835443038, "grad_norm": 0.4488567666057317, "learning_rate": 4.607594936708861e-05, "loss": 0.4046, "step": 91 }, { "epoch": 0.2911392405063291, "grad_norm": 0.4735550266575719, "learning_rate": 4.658227848101266e-05, "loss": 0.3919, "step": 92 }, { "epoch": 0.29430379746835444, "grad_norm": 0.6148176091362573, "learning_rate": 4.708860759493671e-05, "loss": 0.4011, "step": 93 }, { "epoch": 0.2974683544303797, "grad_norm": 0.7472868175056196, "learning_rate": 4.759493670886076e-05, "loss": 0.4022, "step": 94 }, { "epoch": 0.30063291139240506, "grad_norm": 0.770458944117797, "learning_rate": 4.810126582278481e-05, "loss": 0.4038, "step": 95 }, { "epoch": 0.3037974683544304, "grad_norm": 0.6692556449549297, "learning_rate": 4.860759493670886e-05, "loss": 0.4003, "step": 96 }, { "epoch": 0.3069620253164557, "grad_norm": 0.7911693504503632, "learning_rate": 4.911392405063292e-05, "loss": 0.4009, "step": 97 }, { "epoch": 0.310126582278481, "grad_norm": 0.7384237079835713, "learning_rate": 4.962025316455696e-05, "loss": 0.3976, "step": 98 }, { "epoch": 0.31329113924050633, "grad_norm": 0.42716746118099025, "learning_rate": 5.012658227848102e-05, "loss": 0.395, "step": 99 }, { "epoch": 0.31645569620253167, "grad_norm": 0.6923577009577555, "learning_rate": 5.063291139240507e-05, "loss": 0.4086, "step": 100 }, { "epoch": 0.31962025316455694, "grad_norm": 0.6834343832430547, "learning_rate": 5.113924050632911e-05, "loss": 0.3942, "step": 101 }, { "epoch": 0.3227848101265823, "grad_norm": 0.4423920809624565, "learning_rate": 5.164556962025317e-05, "loss": 0.3928, "step": 102 }, { "epoch": 0.3259493670886076, "grad_norm": 0.45680987220169866, "learning_rate": 5.2151898734177224e-05, "loss": 0.3998, "step": 103 }, { "epoch": 0.3291139240506329, "grad_norm": 0.446924426234986, "learning_rate": 5.265822784810127e-05, "loss": 0.3938, "step": 104 }, { "epoch": 0.3322784810126582, "grad_norm": 0.47835521598808634, "learning_rate": 5.316455696202532e-05, "loss": 0.3945, "step": 105 }, { "epoch": 0.33544303797468356, "grad_norm": 0.43641735938193077, "learning_rate": 5.3670886075949375e-05, "loss": 0.3938, "step": 106 }, { "epoch": 0.33860759493670883, "grad_norm": 0.36320691552320805, "learning_rate": 5.417721518987342e-05, "loss": 0.3914, "step": 107 }, { "epoch": 0.34177215189873417, "grad_norm": 0.4413347593986312, "learning_rate": 5.468354430379747e-05, "loss": 0.3905, "step": 108 }, { "epoch": 0.3449367088607595, "grad_norm": 0.47695096124243264, "learning_rate": 5.5189873417721526e-05, "loss": 0.3855, "step": 109 }, { "epoch": 0.34810126582278483, "grad_norm": 0.3944122435263608, "learning_rate": 5.569620253164558e-05, "loss": 0.384, "step": 110 }, { "epoch": 0.3512658227848101, "grad_norm": 0.4480683094218472, "learning_rate": 5.6202531645569624e-05, "loss": 0.3887, "step": 111 }, { "epoch": 0.35443037974683544, "grad_norm": 0.6051038842266119, "learning_rate": 5.670886075949368e-05, "loss": 0.39, "step": 112 }, { "epoch": 0.3575949367088608, "grad_norm": 0.7784509605953326, "learning_rate": 5.721518987341773e-05, "loss": 0.3911, "step": 113 }, { "epoch": 0.36075949367088606, "grad_norm": 1.124405540523692, "learning_rate": 5.7721518987341775e-05, "loss": 0.4069, "step": 114 }, { "epoch": 0.3639240506329114, "grad_norm": 0.801892445485005, "learning_rate": 5.822784810126583e-05, "loss": 0.395, "step": 115 }, { "epoch": 0.3670886075949367, "grad_norm": 0.507743047062257, "learning_rate": 5.873417721518988e-05, "loss": 0.3904, "step": 116 }, { "epoch": 0.370253164556962, "grad_norm": 0.7467348517270679, "learning_rate": 5.9240506329113926e-05, "loss": 0.3991, "step": 117 }, { "epoch": 0.37341772151898733, "grad_norm": 0.71017734965554, "learning_rate": 5.974683544303798e-05, "loss": 0.3924, "step": 118 }, { "epoch": 0.37658227848101267, "grad_norm": 0.5553324856714098, "learning_rate": 6.025316455696203e-05, "loss": 0.3898, "step": 119 }, { "epoch": 0.379746835443038, "grad_norm": 0.6099792373933834, "learning_rate": 6.0759493670886084e-05, "loss": 0.3908, "step": 120 }, { "epoch": 0.3829113924050633, "grad_norm": 0.5232236710482634, "learning_rate": 6.126582278481012e-05, "loss": 0.3897, "step": 121 }, { "epoch": 0.3860759493670886, "grad_norm": 0.5632955980598913, "learning_rate": 6.177215189873418e-05, "loss": 0.3965, "step": 122 }, { "epoch": 0.38924050632911394, "grad_norm": 0.5203322908782667, "learning_rate": 6.227848101265824e-05, "loss": 0.3877, "step": 123 }, { "epoch": 0.3924050632911392, "grad_norm": 0.4358252611227211, "learning_rate": 6.278481012658229e-05, "loss": 0.3881, "step": 124 }, { "epoch": 0.39556962025316456, "grad_norm": 0.5239731560012073, "learning_rate": 6.329113924050633e-05, "loss": 0.3893, "step": 125 }, { "epoch": 0.3987341772151899, "grad_norm": 0.35877108570565086, "learning_rate": 6.379746835443039e-05, "loss": 0.3917, "step": 126 }, { "epoch": 0.40189873417721517, "grad_norm": 0.3877786754297916, "learning_rate": 6.430379746835444e-05, "loss": 0.3956, "step": 127 }, { "epoch": 0.4050632911392405, "grad_norm": 0.38539961357127156, "learning_rate": 6.481012658227848e-05, "loss": 0.3898, "step": 128 }, { "epoch": 0.40822784810126583, "grad_norm": 0.3186307281350795, "learning_rate": 6.531645569620254e-05, "loss": 0.3848, "step": 129 }, { "epoch": 0.41139240506329117, "grad_norm": 0.3477367620861726, "learning_rate": 6.582278481012659e-05, "loss": 0.3908, "step": 130 }, { "epoch": 0.41455696202531644, "grad_norm": 0.3748492257223226, "learning_rate": 6.632911392405063e-05, "loss": 0.3881, "step": 131 }, { "epoch": 0.4177215189873418, "grad_norm": 0.4081513233867579, "learning_rate": 6.68354430379747e-05, "loss": 0.3906, "step": 132 }, { "epoch": 0.4208860759493671, "grad_norm": 0.4826176075098769, "learning_rate": 6.734177215189874e-05, "loss": 0.3851, "step": 133 }, { "epoch": 0.4240506329113924, "grad_norm": 0.5831727185152616, "learning_rate": 6.784810126582279e-05, "loss": 0.383, "step": 134 }, { "epoch": 0.4272151898734177, "grad_norm": 0.6076139232451686, "learning_rate": 6.835443037974685e-05, "loss": 0.3883, "step": 135 }, { "epoch": 0.43037974683544306, "grad_norm": 0.7328760235577102, "learning_rate": 6.886075949367089e-05, "loss": 0.392, "step": 136 }, { "epoch": 0.43354430379746833, "grad_norm": 0.7818226838347421, "learning_rate": 6.936708860759494e-05, "loss": 0.3882, "step": 137 }, { "epoch": 0.43670886075949367, "grad_norm": 0.7908626817455239, "learning_rate": 6.9873417721519e-05, "loss": 0.3896, "step": 138 }, { "epoch": 0.439873417721519, "grad_norm": 0.9560535606826686, "learning_rate": 7.037974683544304e-05, "loss": 0.3884, "step": 139 }, { "epoch": 0.4430379746835443, "grad_norm": 0.7739908787155965, "learning_rate": 7.088607594936709e-05, "loss": 0.386, "step": 140 }, { "epoch": 0.4462025316455696, "grad_norm": 0.588352128840105, "learning_rate": 7.139240506329115e-05, "loss": 0.383, "step": 141 }, { "epoch": 0.44936708860759494, "grad_norm": 0.546084346895817, "learning_rate": 7.189873417721519e-05, "loss": 0.3843, "step": 142 }, { "epoch": 0.4525316455696203, "grad_norm": 0.5434755031805956, "learning_rate": 7.240506329113925e-05, "loss": 0.388, "step": 143 }, { "epoch": 0.45569620253164556, "grad_norm": 0.4933423813975179, "learning_rate": 7.29113924050633e-05, "loss": 0.3785, "step": 144 }, { "epoch": 0.4588607594936709, "grad_norm": 0.43049800251823755, "learning_rate": 7.341772151898734e-05, "loss": 0.3862, "step": 145 }, { "epoch": 0.4620253164556962, "grad_norm": 0.4631049758539713, "learning_rate": 7.39240506329114e-05, "loss": 0.3837, "step": 146 }, { "epoch": 0.4651898734177215, "grad_norm": 0.4871911361937907, "learning_rate": 7.443037974683545e-05, "loss": 0.383, "step": 147 }, { "epoch": 0.46835443037974683, "grad_norm": 0.463315627422979, "learning_rate": 7.49367088607595e-05, "loss": 0.3813, "step": 148 }, { "epoch": 0.47151898734177217, "grad_norm": 0.41651452345440904, "learning_rate": 7.544303797468355e-05, "loss": 0.3818, "step": 149 }, { "epoch": 0.47468354430379744, "grad_norm": 0.39415500310259977, "learning_rate": 7.59493670886076e-05, "loss": 0.3836, "step": 150 }, { "epoch": 0.4778481012658228, "grad_norm": 0.42277369465154596, "learning_rate": 7.645569620253165e-05, "loss": 0.3747, "step": 151 }, { "epoch": 0.4810126582278481, "grad_norm": 0.44544622293699776, "learning_rate": 7.69620253164557e-05, "loss": 0.3816, "step": 152 }, { "epoch": 0.48417721518987344, "grad_norm": 0.5209653652321101, "learning_rate": 7.746835443037976e-05, "loss": 0.3799, "step": 153 }, { "epoch": 0.4873417721518987, "grad_norm": 0.5378607080291513, "learning_rate": 7.79746835443038e-05, "loss": 0.3856, "step": 154 }, { "epoch": 0.49050632911392406, "grad_norm": 0.5097970927087668, "learning_rate": 7.848101265822786e-05, "loss": 0.3825, "step": 155 }, { "epoch": 0.4936708860759494, "grad_norm": 0.6776266142945905, "learning_rate": 7.898734177215191e-05, "loss": 0.3885, "step": 156 }, { "epoch": 0.49683544303797467, "grad_norm": 0.6979656937423981, "learning_rate": 7.949367088607595e-05, "loss": 0.3853, "step": 157 }, { "epoch": 0.5, "grad_norm": 0.5420308813647625, "learning_rate": 8e-05, "loss": 0.3776, "step": 158 }, { "epoch": 0.5031645569620253, "grad_norm": 0.5151265338936681, "learning_rate": 7.999990238189524e-05, "loss": 0.3889, "step": 159 }, { "epoch": 0.5063291139240507, "grad_norm": 0.6979529456686314, "learning_rate": 7.999960952805745e-05, "loss": 0.3829, "step": 160 }, { "epoch": 0.509493670886076, "grad_norm": 0.5177852844595021, "learning_rate": 7.9999121439916e-05, "loss": 0.3848, "step": 161 }, { "epoch": 0.5126582278481012, "grad_norm": 0.3847023300748499, "learning_rate": 7.999843811985321e-05, "loss": 0.3739, "step": 162 }, { "epoch": 0.5158227848101266, "grad_norm": 0.5786978247025661, "learning_rate": 7.99975595712043e-05, "loss": 0.3804, "step": 163 }, { "epoch": 0.5189873417721519, "grad_norm": 0.4887189838494592, "learning_rate": 7.999648579825739e-05, "loss": 0.3834, "step": 164 }, { "epoch": 0.5221518987341772, "grad_norm": 0.3488342146885106, "learning_rate": 7.999521680625345e-05, "loss": 0.3776, "step": 165 }, { "epoch": 0.5253164556962026, "grad_norm": 0.4498670881759772, "learning_rate": 7.999375260138631e-05, "loss": 0.3754, "step": 166 }, { "epoch": 0.5284810126582279, "grad_norm": 0.3812228706105536, "learning_rate": 7.999209319080263e-05, "loss": 0.3772, "step": 167 }, { "epoch": 0.5316455696202531, "grad_norm": 0.248501605679042, "learning_rate": 7.999023858260183e-05, "loss": 0.3808, "step": 168 }, { "epoch": 0.5348101265822784, "grad_norm": 0.3445842639510198, "learning_rate": 7.998818878583607e-05, "loss": 0.3765, "step": 169 }, { "epoch": 0.5379746835443038, "grad_norm": 0.40088597600020753, "learning_rate": 7.998594381051022e-05, "loss": 0.3758, "step": 170 }, { "epoch": 0.5411392405063291, "grad_norm": 0.48541750700398184, "learning_rate": 7.998350366758179e-05, "loss": 0.378, "step": 171 }, { "epoch": 0.5443037974683544, "grad_norm": 0.6227772237201155, "learning_rate": 7.998086836896087e-05, "loss": 0.3761, "step": 172 }, { "epoch": 0.5474683544303798, "grad_norm": 0.6448672489319238, "learning_rate": 7.997803792751014e-05, "loss": 0.3856, "step": 173 }, { "epoch": 0.5506329113924051, "grad_norm": 0.687044796500734, "learning_rate": 7.99750123570447e-05, "loss": 0.3876, "step": 174 }, { "epoch": 0.5537974683544303, "grad_norm": 0.6951088098417804, "learning_rate": 7.997179167233206e-05, "loss": 0.3763, "step": 175 }, { "epoch": 0.5569620253164557, "grad_norm": 0.621570929606909, "learning_rate": 7.996837588909207e-05, "loss": 0.3746, "step": 176 }, { "epoch": 0.560126582278481, "grad_norm": 0.5031277252037881, "learning_rate": 7.996476502399688e-05, "loss": 0.3755, "step": 177 }, { "epoch": 0.5632911392405063, "grad_norm": 0.4549829404717941, "learning_rate": 7.996095909467076e-05, "loss": 0.3782, "step": 178 }, { "epoch": 0.5664556962025317, "grad_norm": 0.41106784754319925, "learning_rate": 7.995695811969009e-05, "loss": 0.3754, "step": 179 }, { "epoch": 0.569620253164557, "grad_norm": 0.40460165214746324, "learning_rate": 7.995276211858324e-05, "loss": 0.379, "step": 180 }, { "epoch": 0.5727848101265823, "grad_norm": 0.4104515634756312, "learning_rate": 7.994837111183052e-05, "loss": 0.3756, "step": 181 }, { "epoch": 0.5759493670886076, "grad_norm": 0.36615128100318456, "learning_rate": 7.994378512086398e-05, "loss": 0.3759, "step": 182 }, { "epoch": 0.5791139240506329, "grad_norm": 0.43083263791843357, "learning_rate": 7.993900416806744e-05, "loss": 0.3686, "step": 183 }, { "epoch": 0.5822784810126582, "grad_norm": 0.31536311243560866, "learning_rate": 7.993402827677628e-05, "loss": 0.3781, "step": 184 }, { "epoch": 0.5854430379746836, "grad_norm": 0.3762253343326441, "learning_rate": 7.992885747127732e-05, "loss": 0.3804, "step": 185 }, { "epoch": 0.5886075949367089, "grad_norm": 0.4684752027373189, "learning_rate": 7.992349177680881e-05, "loss": 0.3734, "step": 186 }, { "epoch": 0.5917721518987342, "grad_norm": 0.397251998024018, "learning_rate": 7.991793121956016e-05, "loss": 0.3757, "step": 187 }, { "epoch": 0.5949367088607594, "grad_norm": 0.31965530588227015, "learning_rate": 7.991217582667196e-05, "loss": 0.3739, "step": 188 }, { "epoch": 0.5981012658227848, "grad_norm": 0.32948373071265413, "learning_rate": 7.990622562623572e-05, "loss": 0.3717, "step": 189 }, { "epoch": 0.6012658227848101, "grad_norm": 0.2703554304434829, "learning_rate": 7.990008064729378e-05, "loss": 0.3706, "step": 190 }, { "epoch": 0.6044303797468354, "grad_norm": 0.2222273446429977, "learning_rate": 7.989374091983925e-05, "loss": 0.371, "step": 191 }, { "epoch": 0.6075949367088608, "grad_norm": 0.28352468981766643, "learning_rate": 7.98872064748157e-05, "loss": 0.3746, "step": 192 }, { "epoch": 0.6107594936708861, "grad_norm": 0.28169058444197614, "learning_rate": 7.988047734411714e-05, "loss": 0.3711, "step": 193 }, { "epoch": 0.6139240506329114, "grad_norm": 0.3256498499326677, "learning_rate": 7.987355356058784e-05, "loss": 0.3714, "step": 194 }, { "epoch": 0.6170886075949367, "grad_norm": 0.3713812509190487, "learning_rate": 7.986643515802211e-05, "loss": 0.3704, "step": 195 }, { "epoch": 0.620253164556962, "grad_norm": 0.3829579364154847, "learning_rate": 7.985912217116423e-05, "loss": 0.3714, "step": 196 }, { "epoch": 0.6234177215189873, "grad_norm": 0.37861461810526087, "learning_rate": 7.985161463570815e-05, "loss": 0.375, "step": 197 }, { "epoch": 0.6265822784810127, "grad_norm": 0.3296930394008948, "learning_rate": 7.984391258829747e-05, "loss": 0.3718, "step": 198 }, { "epoch": 0.629746835443038, "grad_norm": 0.27815231465128715, "learning_rate": 7.983601606652516e-05, "loss": 0.3713, "step": 199 }, { "epoch": 0.6329113924050633, "grad_norm": 0.2803076607213284, "learning_rate": 7.982792510893337e-05, "loss": 0.374, "step": 200 }, { "epoch": 0.6360759493670886, "grad_norm": 0.2949238998973068, "learning_rate": 7.98196397550133e-05, "loss": 0.374, "step": 201 }, { "epoch": 0.6392405063291139, "grad_norm": 0.36619439404059667, "learning_rate": 7.981116004520499e-05, "loss": 0.3711, "step": 202 }, { "epoch": 0.6424050632911392, "grad_norm": 0.4439613003273657, "learning_rate": 7.98024860208971e-05, "loss": 0.3753, "step": 203 }, { "epoch": 0.6455696202531646, "grad_norm": 0.48983339090121436, "learning_rate": 7.979361772442672e-05, "loss": 0.3707, "step": 204 }, { "epoch": 0.6487341772151899, "grad_norm": 0.5221892881736936, "learning_rate": 7.978455519907916e-05, "loss": 0.3707, "step": 205 }, { "epoch": 0.6518987341772152, "grad_norm": 0.5492229355026512, "learning_rate": 7.977529848908774e-05, "loss": 0.379, "step": 206 }, { "epoch": 0.6550632911392406, "grad_norm": 0.5583262971812882, "learning_rate": 7.976584763963359e-05, "loss": 0.3746, "step": 207 }, { "epoch": 0.6582278481012658, "grad_norm": 0.4730777475518245, "learning_rate": 7.975620269684543e-05, "loss": 0.3794, "step": 208 }, { "epoch": 0.6613924050632911, "grad_norm": 0.35888568864799175, "learning_rate": 7.974636370779929e-05, "loss": 0.3752, "step": 209 }, { "epoch": 0.6645569620253164, "grad_norm": 0.38122277583353054, "learning_rate": 7.973633072051835e-05, "loss": 0.3725, "step": 210 }, { "epoch": 0.6677215189873418, "grad_norm": 0.39661068003674876, "learning_rate": 7.972610378397266e-05, "loss": 0.3772, "step": 211 }, { "epoch": 0.6708860759493671, "grad_norm": 0.28227253164496896, "learning_rate": 7.971568294807894e-05, "loss": 0.3708, "step": 212 }, { "epoch": 0.6740506329113924, "grad_norm": 0.35516655733689834, "learning_rate": 7.97050682637003e-05, "loss": 0.3738, "step": 213 }, { "epoch": 0.6772151898734177, "grad_norm": 0.3937773867411833, "learning_rate": 7.969425978264602e-05, "loss": 0.3727, "step": 214 }, { "epoch": 0.680379746835443, "grad_norm": 0.3290232781383209, "learning_rate": 7.968325755767124e-05, "loss": 0.3707, "step": 215 }, { "epoch": 0.6835443037974683, "grad_norm": 0.3338684789907473, "learning_rate": 7.96720616424768e-05, "loss": 0.3758, "step": 216 }, { "epoch": 0.6867088607594937, "grad_norm": 0.31824259556597484, "learning_rate": 7.96606720917089e-05, "loss": 0.3696, "step": 217 }, { "epoch": 0.689873417721519, "grad_norm": 0.309682608744209, "learning_rate": 7.964908896095886e-05, "loss": 0.3684, "step": 218 }, { "epoch": 0.6930379746835443, "grad_norm": 0.3112540152274356, "learning_rate": 7.963731230676284e-05, "loss": 0.3643, "step": 219 }, { "epoch": 0.6962025316455697, "grad_norm": 0.31701444378315347, "learning_rate": 7.962534218660157e-05, "loss": 0.3731, "step": 220 }, { "epoch": 0.6993670886075949, "grad_norm": 0.2629871083607239, "learning_rate": 7.961317865890009e-05, "loss": 0.3732, "step": 221 }, { "epoch": 0.7025316455696202, "grad_norm": 0.2995783201473632, "learning_rate": 7.960082178302738e-05, "loss": 0.3685, "step": 222 }, { "epoch": 0.7056962025316456, "grad_norm": 0.2834402954658099, "learning_rate": 7.958827161929624e-05, "loss": 0.3671, "step": 223 }, { "epoch": 0.7088607594936709, "grad_norm": 0.23259810903281164, "learning_rate": 7.957552822896279e-05, "loss": 0.3651, "step": 224 }, { "epoch": 0.7120253164556962, "grad_norm": 0.2572132091083643, "learning_rate": 7.956259167422632e-05, "loss": 0.3655, "step": 225 }, { "epoch": 0.7151898734177216, "grad_norm": 0.30973369421393, "learning_rate": 7.954946201822893e-05, "loss": 0.3723, "step": 226 }, { "epoch": 0.7183544303797469, "grad_norm": 0.37987364234871895, "learning_rate": 7.953613932505523e-05, "loss": 0.3681, "step": 227 }, { "epoch": 0.7215189873417721, "grad_norm": 0.3311095650891442, "learning_rate": 7.952262365973201e-05, "loss": 0.3717, "step": 228 }, { "epoch": 0.7246835443037974, "grad_norm": 0.2259362251145521, "learning_rate": 7.950891508822797e-05, "loss": 0.3697, "step": 229 }, { "epoch": 0.7278481012658228, "grad_norm": 0.25854908991709524, "learning_rate": 7.949501367745335e-05, "loss": 0.3677, "step": 230 }, { "epoch": 0.7310126582278481, "grad_norm": 0.2775474011520162, "learning_rate": 7.948091949525959e-05, "loss": 0.3648, "step": 231 }, { "epoch": 0.7341772151898734, "grad_norm": 0.3206305434240464, "learning_rate": 7.946663261043908e-05, "loss": 0.3664, "step": 232 }, { "epoch": 0.7373417721518988, "grad_norm": 0.4015241175779781, "learning_rate": 7.945215309272475e-05, "loss": 0.3644, "step": 233 }, { "epoch": 0.740506329113924, "grad_norm": 0.4801459577720394, "learning_rate": 7.943748101278974e-05, "loss": 0.3723, "step": 234 }, { "epoch": 0.7436708860759493, "grad_norm": 0.5592813521836284, "learning_rate": 7.94226164422471e-05, "loss": 0.367, "step": 235 }, { "epoch": 0.7468354430379747, "grad_norm": 0.6356962911085963, "learning_rate": 7.940755945364939e-05, "loss": 0.3678, "step": 236 }, { "epoch": 0.75, "grad_norm": 0.6607210985300707, "learning_rate": 7.939231012048833e-05, "loss": 0.369, "step": 237 }, { "epoch": 0.7531645569620253, "grad_norm": 0.5121109015478843, "learning_rate": 7.937686851719446e-05, "loss": 0.3688, "step": 238 }, { "epoch": 0.7563291139240507, "grad_norm": 0.37257222215971275, "learning_rate": 7.936123471913683e-05, "loss": 0.3714, "step": 239 }, { "epoch": 0.759493670886076, "grad_norm": 0.39857425938018787, "learning_rate": 7.934540880262248e-05, "loss": 0.3702, "step": 240 }, { "epoch": 0.7626582278481012, "grad_norm": 0.3802420268012858, "learning_rate": 7.932939084489623e-05, "loss": 0.3693, "step": 241 }, { "epoch": 0.7658227848101266, "grad_norm": 0.31800086791590515, "learning_rate": 7.931318092414022e-05, "loss": 0.3699, "step": 242 }, { "epoch": 0.7689873417721519, "grad_norm": 0.28027502118302794, "learning_rate": 7.929677911947351e-05, "loss": 0.3657, "step": 243 }, { "epoch": 0.7721518987341772, "grad_norm": 0.30895776688997906, "learning_rate": 7.928018551095177e-05, "loss": 0.3674, "step": 244 }, { "epoch": 0.7753164556962026, "grad_norm": 0.28611577993888315, "learning_rate": 7.926340017956684e-05, "loss": 0.3703, "step": 245 }, { "epoch": 0.7784810126582279, "grad_norm": 0.23960135967316537, "learning_rate": 7.924642320724631e-05, "loss": 0.3708, "step": 246 }, { "epoch": 0.7816455696202531, "grad_norm": 0.22454818719478975, "learning_rate": 7.92292546768532e-05, "loss": 0.3685, "step": 247 }, { "epoch": 0.7848101265822784, "grad_norm": 0.2779184522518987, "learning_rate": 7.921189467218546e-05, "loss": 0.3627, "step": 248 }, { "epoch": 0.7879746835443038, "grad_norm": 0.30559090273470246, "learning_rate": 7.919434327797563e-05, "loss": 0.3714, "step": 249 }, { "epoch": 0.7911392405063291, "grad_norm": 0.27891837717994167, "learning_rate": 7.91766005798904e-05, "loss": 0.3682, "step": 250 }, { "epoch": 0.7943037974683544, "grad_norm": 0.2627318147448679, "learning_rate": 7.915866666453021e-05, "loss": 0.3695, "step": 251 }, { "epoch": 0.7974683544303798, "grad_norm": 0.24452655446592894, "learning_rate": 7.914054161942881e-05, "loss": 0.3647, "step": 252 }, { "epoch": 0.8006329113924051, "grad_norm": 0.27219303368208364, "learning_rate": 7.91222255330528e-05, "loss": 0.3663, "step": 253 }, { "epoch": 0.8037974683544303, "grad_norm": 0.3086523068323125, "learning_rate": 7.910371849480127e-05, "loss": 0.3669, "step": 254 }, { "epoch": 0.8069620253164557, "grad_norm": 0.3365790403580907, "learning_rate": 7.908502059500532e-05, "loss": 0.3676, "step": 255 }, { "epoch": 0.810126582278481, "grad_norm": 0.4238799601262565, "learning_rate": 7.906613192492765e-05, "loss": 0.3744, "step": 256 }, { "epoch": 0.8132911392405063, "grad_norm": 0.4923336975803097, "learning_rate": 7.904705257676204e-05, "loss": 0.3646, "step": 257 }, { "epoch": 0.8164556962025317, "grad_norm": 0.5203796343469319, "learning_rate": 7.9027782643633e-05, "loss": 0.3736, "step": 258 }, { "epoch": 0.819620253164557, "grad_norm": 0.5280231169703825, "learning_rate": 7.900832221959523e-05, "loss": 0.373, "step": 259 }, { "epoch": 0.8227848101265823, "grad_norm": 0.43010251314473524, "learning_rate": 7.898867139963322e-05, "loss": 0.3638, "step": 260 }, { "epoch": 0.8259493670886076, "grad_norm": 0.2994409634480491, "learning_rate": 7.896883027966076e-05, "loss": 0.3647, "step": 261 }, { "epoch": 0.8291139240506329, "grad_norm": 0.21566386450268846, "learning_rate": 7.89487989565205e-05, "loss": 0.3649, "step": 262 }, { "epoch": 0.8322784810126582, "grad_norm": 0.2913621804407218, "learning_rate": 7.892857752798339e-05, "loss": 0.3662, "step": 263 }, { "epoch": 0.8354430379746836, "grad_norm": 0.35792104049313206, "learning_rate": 7.890816609274833e-05, "loss": 0.3629, "step": 264 }, { "epoch": 0.8386075949367089, "grad_norm": 0.25946627043682885, "learning_rate": 7.88875647504416e-05, "loss": 0.3628, "step": 265 }, { "epoch": 0.8417721518987342, "grad_norm": 0.22855482672464317, "learning_rate": 7.88667736016164e-05, "loss": 0.3663, "step": 266 }, { "epoch": 0.8449367088607594, "grad_norm": 0.33761395174152364, "learning_rate": 7.884579274775237e-05, "loss": 0.3659, "step": 267 }, { "epoch": 0.8481012658227848, "grad_norm": 0.2829034584858881, "learning_rate": 7.882462229125504e-05, "loss": 0.3683, "step": 268 }, { "epoch": 0.8512658227848101, "grad_norm": 0.24860953712697734, "learning_rate": 7.880326233545541e-05, "loss": 0.3684, "step": 269 }, { "epoch": 0.8544303797468354, "grad_norm": 0.31584455864126443, "learning_rate": 7.87817129846094e-05, "loss": 0.3633, "step": 270 }, { "epoch": 0.8575949367088608, "grad_norm": 0.3161217492035144, "learning_rate": 7.875997434389738e-05, "loss": 0.367, "step": 271 }, { "epoch": 0.8607594936708861, "grad_norm": 0.28922224781613237, "learning_rate": 7.873804651942356e-05, "loss": 0.369, "step": 272 }, { "epoch": 0.8639240506329114, "grad_norm": 0.2934020589145351, "learning_rate": 7.871592961821558e-05, "loss": 0.3593, "step": 273 }, { "epoch": 0.8670886075949367, "grad_norm": 0.35247933121603486, "learning_rate": 7.869362374822394e-05, "loss": 0.3625, "step": 274 }, { "epoch": 0.870253164556962, "grad_norm": 0.37424966371044266, "learning_rate": 7.867112901832149e-05, "loss": 0.3613, "step": 275 }, { "epoch": 0.8734177215189873, "grad_norm": 0.3182026395112872, "learning_rate": 7.864844553830286e-05, "loss": 0.3616, "step": 276 }, { "epoch": 0.8765822784810127, "grad_norm": 0.2458445554466988, "learning_rate": 7.862557341888398e-05, "loss": 0.3649, "step": 277 }, { "epoch": 0.879746835443038, "grad_norm": 0.2283275882207385, "learning_rate": 7.860251277170149e-05, "loss": 0.3621, "step": 278 }, { "epoch": 0.8829113924050633, "grad_norm": 0.19500431541711888, "learning_rate": 7.857926370931222e-05, "loss": 0.3599, "step": 279 }, { "epoch": 0.8860759493670886, "grad_norm": 0.18557115491629902, "learning_rate": 7.855582634519264e-05, "loss": 0.3676, "step": 280 }, { "epoch": 0.8892405063291139, "grad_norm": 0.1756156210833818, "learning_rate": 7.853220079373831e-05, "loss": 0.3605, "step": 281 }, { "epoch": 0.8924050632911392, "grad_norm": 0.23845019688770083, "learning_rate": 7.85083871702633e-05, "loss": 0.3619, "step": 282 }, { "epoch": 0.8955696202531646, "grad_norm": 0.270598292739546, "learning_rate": 7.848438559099967e-05, "loss": 0.3583, "step": 283 }, { "epoch": 0.8987341772151899, "grad_norm": 0.2539081647201782, "learning_rate": 7.846019617309683e-05, "loss": 0.3616, "step": 284 }, { "epoch": 0.9018987341772152, "grad_norm": 0.2964394375296239, "learning_rate": 7.843581903462104e-05, "loss": 0.3617, "step": 285 }, { "epoch": 0.9050632911392406, "grad_norm": 0.34363376252977457, "learning_rate": 7.841125429455482e-05, "loss": 0.3668, "step": 286 }, { "epoch": 0.9082278481012658, "grad_norm": 0.39721039996252255, "learning_rate": 7.83865020727963e-05, "loss": 0.3642, "step": 287 }, { "epoch": 0.9113924050632911, "grad_norm": 0.43542602719508233, "learning_rate": 7.836156249015878e-05, "loss": 0.3664, "step": 288 }, { "epoch": 0.9145569620253164, "grad_norm": 0.4505105328643035, "learning_rate": 7.833643566836997e-05, "loss": 0.368, "step": 289 }, { "epoch": 0.9177215189873418, "grad_norm": 0.46504542414125893, "learning_rate": 7.831112173007151e-05, "loss": 0.3652, "step": 290 }, { "epoch": 0.9208860759493671, "grad_norm": 0.45586832386184883, "learning_rate": 7.828562079881833e-05, "loss": 0.3681, "step": 291 }, { "epoch": 0.9240506329113924, "grad_norm": 0.4102581397169858, "learning_rate": 7.825993299907807e-05, "loss": 0.3643, "step": 292 }, { "epoch": 0.9272151898734177, "grad_norm": 0.38397341253941425, "learning_rate": 7.823405845623044e-05, "loss": 0.3616, "step": 293 }, { "epoch": 0.930379746835443, "grad_norm": 0.38061339109343745, "learning_rate": 7.820799729656662e-05, "loss": 0.3608, "step": 294 }, { "epoch": 0.9335443037974683, "grad_norm": 0.30416205163231486, "learning_rate": 7.818174964728869e-05, "loss": 0.3628, "step": 295 }, { "epoch": 0.9367088607594937, "grad_norm": 0.3065439287335868, "learning_rate": 7.815531563650891e-05, "loss": 0.3631, "step": 296 }, { "epoch": 0.939873417721519, "grad_norm": 0.39929289270324775, "learning_rate": 7.81286953932492e-05, "loss": 0.3656, "step": 297 }, { "epoch": 0.9430379746835443, "grad_norm": 0.32313028883554223, "learning_rate": 7.810188904744045e-05, "loss": 0.3587, "step": 298 }, { "epoch": 0.9462025316455697, "grad_norm": 0.23539786999561352, "learning_rate": 7.807489672992184e-05, "loss": 0.3545, "step": 299 }, { "epoch": 0.9493670886075949, "grad_norm": 0.3816960123356583, "learning_rate": 7.804771857244038e-05, "loss": 0.3571, "step": 300 }, { "epoch": 0.9525316455696202, "grad_norm": 0.33243638859993174, "learning_rate": 7.802035470765007e-05, "loss": 0.3588, "step": 301 }, { "epoch": 0.9556962025316456, "grad_norm": 0.1940039726686047, "learning_rate": 7.799280526911132e-05, "loss": 0.3543, "step": 302 }, { "epoch": 0.9588607594936709, "grad_norm": 0.32106875937516577, "learning_rate": 7.796507039129032e-05, "loss": 0.3613, "step": 303 }, { "epoch": 0.9620253164556962, "grad_norm": 0.33703637014218263, "learning_rate": 7.793715020955841e-05, "loss": 0.3612, "step": 304 }, { "epoch": 0.9651898734177216, "grad_norm": 0.2543226662615364, "learning_rate": 7.790904486019134e-05, "loss": 0.36, "step": 305 }, { "epoch": 0.9683544303797469, "grad_norm": 0.20777838417229647, "learning_rate": 7.788075448036865e-05, "loss": 0.363, "step": 306 }, { "epoch": 0.9715189873417721, "grad_norm": 0.23857468563737758, "learning_rate": 7.7852279208173e-05, "loss": 0.3685, "step": 307 }, { "epoch": 0.9746835443037974, "grad_norm": 0.22011851606434138, "learning_rate": 7.782361918258952e-05, "loss": 0.3594, "step": 308 }, { "epoch": 0.9778481012658228, "grad_norm": 0.22432699616731383, "learning_rate": 7.779477454350507e-05, "loss": 0.3632, "step": 309 }, { "epoch": 0.9810126582278481, "grad_norm": 0.2734646838767217, "learning_rate": 7.776574543170757e-05, "loss": 0.3613, "step": 310 }, { "epoch": 0.9841772151898734, "grad_norm": 0.31875866537658815, "learning_rate": 7.773653198888539e-05, "loss": 0.3604, "step": 311 }, { "epoch": 0.9873417721518988, "grad_norm": 0.3675801047106904, "learning_rate": 7.770713435762658e-05, "loss": 0.368, "step": 312 }, { "epoch": 0.990506329113924, "grad_norm": 0.3910146665189869, "learning_rate": 7.767755268141818e-05, "loss": 0.3647, "step": 313 }, { "epoch": 0.9936708860759493, "grad_norm": 0.41809083655006296, "learning_rate": 7.764778710464555e-05, "loss": 0.3576, "step": 314 }, { "epoch": 0.9968354430379747, "grad_norm": 0.4091030290139126, "learning_rate": 7.761783777259166e-05, "loss": 0.3621, "step": 315 }, { "epoch": 1.0, "grad_norm": 0.45425733226581916, "learning_rate": 7.758770483143634e-05, "loss": 0.3603, "step": 316 }, { "epoch": 1.0031645569620253, "grad_norm": 0.5119019331002683, "learning_rate": 7.755738842825564e-05, "loss": 0.3456, "step": 317 }, { "epoch": 1.0063291139240507, "grad_norm": 0.5140513748071411, "learning_rate": 7.752688871102106e-05, "loss": 0.3468, "step": 318 }, { "epoch": 1.009493670886076, "grad_norm": 0.4845492124374466, "learning_rate": 7.74962058285988e-05, "loss": 0.347, "step": 319 }, { "epoch": 1.0126582278481013, "grad_norm": 0.3490995308390879, "learning_rate": 7.746533993074912e-05, "loss": 0.3465, "step": 320 }, { "epoch": 1.0158227848101267, "grad_norm": 0.25345008862619, "learning_rate": 7.743429116812554e-05, "loss": 0.3471, "step": 321 }, { "epoch": 1.018987341772152, "grad_norm": 0.4032835438748256, "learning_rate": 7.740305969227413e-05, "loss": 0.3493, "step": 322 }, { "epoch": 1.0221518987341771, "grad_norm": 0.40390264474967796, "learning_rate": 7.737164565563276e-05, "loss": 0.3478, "step": 323 }, { "epoch": 1.0253164556962024, "grad_norm": 0.308951006836415, "learning_rate": 7.734004921153036e-05, "loss": 0.3485, "step": 324 }, { "epoch": 1.0284810126582278, "grad_norm": 0.3832818463919645, "learning_rate": 7.73082705141862e-05, "loss": 0.3482, "step": 325 }, { "epoch": 1.0316455696202531, "grad_norm": 0.37077378964511426, "learning_rate": 7.727630971870908e-05, "loss": 0.345, "step": 326 }, { "epoch": 1.0348101265822784, "grad_norm": 0.2265042872888965, "learning_rate": 7.724416698109659e-05, "loss": 0.3449, "step": 327 }, { "epoch": 1.0379746835443038, "grad_norm": 0.34551057398520524, "learning_rate": 7.721184245823442e-05, "loss": 0.3485, "step": 328 }, { "epoch": 1.0411392405063291, "grad_norm": 0.3644850546936929, "learning_rate": 7.717933630789549e-05, "loss": 0.349, "step": 329 }, { "epoch": 1.0443037974683544, "grad_norm": 0.21359088117192473, "learning_rate": 7.714664868873924e-05, "loss": 0.3402, "step": 330 }, { "epoch": 1.0474683544303798, "grad_norm": 0.3110304399472897, "learning_rate": 7.711377976031084e-05, "loss": 0.3446, "step": 331 }, { "epoch": 1.0506329113924051, "grad_norm": 0.3317596094246587, "learning_rate": 7.708072968304042e-05, "loss": 0.3482, "step": 332 }, { "epoch": 1.0537974683544304, "grad_norm": 0.25755753922011265, "learning_rate": 7.704749861824226e-05, "loss": 0.3455, "step": 333 }, { "epoch": 1.0569620253164558, "grad_norm": 0.2810789190356907, "learning_rate": 7.701408672811406e-05, "loss": 0.3498, "step": 334 }, { "epoch": 1.0601265822784811, "grad_norm": 0.20480615792468043, "learning_rate": 7.698049417573607e-05, "loss": 0.3498, "step": 335 }, { "epoch": 1.0632911392405062, "grad_norm": 0.22425951007509565, "learning_rate": 7.694672112507037e-05, "loss": 0.3475, "step": 336 }, { "epoch": 1.0664556962025316, "grad_norm": 0.3189395262972535, "learning_rate": 7.691276774096004e-05, "loss": 0.3405, "step": 337 }, { "epoch": 1.0696202531645569, "grad_norm": 0.2652738674083554, "learning_rate": 7.687863418912827e-05, "loss": 0.3476, "step": 338 }, { "epoch": 1.0727848101265822, "grad_norm": 0.2898948944323581, "learning_rate": 7.684432063617774e-05, "loss": 0.3431, "step": 339 }, { "epoch": 1.0759493670886076, "grad_norm": 0.3569412570999201, "learning_rate": 7.680982724958963e-05, "loss": 0.3437, "step": 340 }, { "epoch": 1.0791139240506329, "grad_norm": 0.3716536081202881, "learning_rate": 7.67751541977229e-05, "loss": 0.3462, "step": 341 }, { "epoch": 1.0822784810126582, "grad_norm": 0.4354051687085626, "learning_rate": 7.674030164981345e-05, "loss": 0.3455, "step": 342 }, { "epoch": 1.0854430379746836, "grad_norm": 0.46346834987502583, "learning_rate": 7.670526977597321e-05, "loss": 0.344, "step": 343 }, { "epoch": 1.0886075949367089, "grad_norm": 0.37834150584120213, "learning_rate": 7.667005874718948e-05, "loss": 0.3501, "step": 344 }, { "epoch": 1.0917721518987342, "grad_norm": 0.3071544503949644, "learning_rate": 7.663466873532395e-05, "loss": 0.3427, "step": 345 }, { "epoch": 1.0949367088607596, "grad_norm": 0.2983614543731539, "learning_rate": 7.65990999131119e-05, "loss": 0.3441, "step": 346 }, { "epoch": 1.0981012658227849, "grad_norm": 0.28235124518302696, "learning_rate": 7.656335245416139e-05, "loss": 0.3473, "step": 347 }, { "epoch": 1.1012658227848102, "grad_norm": 0.2779376312621349, "learning_rate": 7.652742653295238e-05, "loss": 0.3441, "step": 348 }, { "epoch": 1.1044303797468356, "grad_norm": 0.2788944455856865, "learning_rate": 7.649132232483589e-05, "loss": 0.3434, "step": 349 }, { "epoch": 1.1075949367088607, "grad_norm": 0.26718739278661013, "learning_rate": 7.645504000603313e-05, "loss": 0.3475, "step": 350 }, { "epoch": 1.110759493670886, "grad_norm": 0.21884877711450648, "learning_rate": 7.641857975363465e-05, "loss": 0.3498, "step": 351 }, { "epoch": 1.1139240506329113, "grad_norm": 0.22821664613610568, "learning_rate": 7.638194174559951e-05, "loss": 0.348, "step": 352 }, { "epoch": 1.1170886075949367, "grad_norm": 0.2575057280835829, "learning_rate": 7.634512616075436e-05, "loss": 0.3465, "step": 353 }, { "epoch": 1.120253164556962, "grad_norm": 0.2177605456463969, "learning_rate": 7.630813317879254e-05, "loss": 0.3451, "step": 354 }, { "epoch": 1.1234177215189873, "grad_norm": 0.23428245889041346, "learning_rate": 7.627096298027334e-05, "loss": 0.343, "step": 355 }, { "epoch": 1.1265822784810127, "grad_norm": 0.19741689292242787, "learning_rate": 7.623361574662094e-05, "loss": 0.3446, "step": 356 }, { "epoch": 1.129746835443038, "grad_norm": 0.15776579759188916, "learning_rate": 7.619609166012366e-05, "loss": 0.3411, "step": 357 }, { "epoch": 1.1329113924050633, "grad_norm": 0.20319133235709722, "learning_rate": 7.615839090393301e-05, "loss": 0.3448, "step": 358 }, { "epoch": 1.1360759493670887, "grad_norm": 0.236621727838995, "learning_rate": 7.612051366206282e-05, "loss": 0.3427, "step": 359 }, { "epoch": 1.139240506329114, "grad_norm": 0.2857198944150768, "learning_rate": 7.608246011938829e-05, "loss": 0.3434, "step": 360 }, { "epoch": 1.1424050632911393, "grad_norm": 0.2818159590142859, "learning_rate": 7.604423046164519e-05, "loss": 0.3422, "step": 361 }, { "epoch": 1.1455696202531644, "grad_norm": 0.24966418404246712, "learning_rate": 7.600582487542883e-05, "loss": 0.3453, "step": 362 }, { "epoch": 1.1487341772151898, "grad_norm": 0.2660716956871848, "learning_rate": 7.596724354819326e-05, "loss": 0.3484, "step": 363 }, { "epoch": 1.1518987341772151, "grad_norm": 0.3291253938009221, "learning_rate": 7.592848666825026e-05, "loss": 0.348, "step": 364 }, { "epoch": 1.1550632911392404, "grad_norm": 0.4148529885030933, "learning_rate": 7.58895544247685e-05, "loss": 0.3434, "step": 365 }, { "epoch": 1.1582278481012658, "grad_norm": 0.5397514837557126, "learning_rate": 7.585044700777257e-05, "loss": 0.3473, "step": 366 }, { "epoch": 1.1613924050632911, "grad_norm": 0.5732521484574725, "learning_rate": 7.581116460814205e-05, "loss": 0.3478, "step": 367 }, { "epoch": 1.1645569620253164, "grad_norm": 0.5035249181770838, "learning_rate": 7.577170741761065e-05, "loss": 0.3463, "step": 368 }, { "epoch": 1.1677215189873418, "grad_norm": 0.37000643297231905, "learning_rate": 7.573207562876514e-05, "loss": 0.3482, "step": 369 }, { "epoch": 1.1708860759493671, "grad_norm": 0.29686963035286956, "learning_rate": 7.569226943504454e-05, "loss": 0.346, "step": 370 }, { "epoch": 1.1740506329113924, "grad_norm": 0.3473759879725463, "learning_rate": 7.565228903073911e-05, "loss": 0.3442, "step": 371 }, { "epoch": 1.1772151898734178, "grad_norm": 0.38170232288130473, "learning_rate": 7.561213461098941e-05, "loss": 0.3413, "step": 372 }, { "epoch": 1.1803797468354431, "grad_norm": 0.33660758950388703, "learning_rate": 7.557180637178537e-05, "loss": 0.337, "step": 373 }, { "epoch": 1.1835443037974684, "grad_norm": 0.24635854971839036, "learning_rate": 7.553130450996528e-05, "loss": 0.3436, "step": 374 }, { "epoch": 1.1867088607594938, "grad_norm": 0.3103735933482299, "learning_rate": 7.549062922321492e-05, "loss": 0.3452, "step": 375 }, { "epoch": 1.189873417721519, "grad_norm": 0.33916295605493746, "learning_rate": 7.544978071006649e-05, "loss": 0.3438, "step": 376 }, { "epoch": 1.1930379746835442, "grad_norm": 0.21271646167012057, "learning_rate": 7.54087591698977e-05, "loss": 0.3415, "step": 377 }, { "epoch": 1.1962025316455696, "grad_norm": 0.26991495904255186, "learning_rate": 7.536756480293082e-05, "loss": 0.3439, "step": 378 }, { "epoch": 1.1993670886075949, "grad_norm": 0.2758225692420901, "learning_rate": 7.532619781023167e-05, "loss": 0.3455, "step": 379 }, { "epoch": 1.2025316455696202, "grad_norm": 0.22326778273686293, "learning_rate": 7.528465839370859e-05, "loss": 0.3425, "step": 380 }, { "epoch": 1.2056962025316456, "grad_norm": 0.2782798771490353, "learning_rate": 7.524294675611155e-05, "loss": 0.3437, "step": 381 }, { "epoch": 1.2088607594936709, "grad_norm": 0.28006786659802385, "learning_rate": 7.520106310103109e-05, "loss": 0.3435, "step": 382 }, { "epoch": 1.2120253164556962, "grad_norm": 0.19365799332298614, "learning_rate": 7.515900763289736e-05, "loss": 0.3385, "step": 383 }, { "epoch": 1.2151898734177216, "grad_norm": 0.23957591139699294, "learning_rate": 7.511678055697912e-05, "loss": 0.3447, "step": 384 }, { "epoch": 1.2183544303797469, "grad_norm": 0.25023047139244536, "learning_rate": 7.507438207938273e-05, "loss": 0.3435, "step": 385 }, { "epoch": 1.2215189873417722, "grad_norm": 0.1811180787556786, "learning_rate": 7.503181240705114e-05, "loss": 0.3427, "step": 386 }, { "epoch": 1.2246835443037976, "grad_norm": 0.20951851887936607, "learning_rate": 7.498907174776289e-05, "loss": 0.3446, "step": 387 }, { "epoch": 1.2278481012658227, "grad_norm": 0.23522663021651613, "learning_rate": 7.494616031013109e-05, "loss": 0.34, "step": 388 }, { "epoch": 1.231012658227848, "grad_norm": 0.16156981458170175, "learning_rate": 7.49030783036024e-05, "loss": 0.3424, "step": 389 }, { "epoch": 1.2341772151898733, "grad_norm": 0.1937830951316511, "learning_rate": 7.485982593845598e-05, "loss": 0.3373, "step": 390 }, { "epoch": 1.2373417721518987, "grad_norm": 0.20623646862118603, "learning_rate": 7.481640342580257e-05, "loss": 0.3396, "step": 391 }, { "epoch": 1.240506329113924, "grad_norm": 0.15505308554585948, "learning_rate": 7.477281097758331e-05, "loss": 0.3422, "step": 392 }, { "epoch": 1.2436708860759493, "grad_norm": 0.17912639827131185, "learning_rate": 7.472904880656882e-05, "loss": 0.3434, "step": 393 }, { "epoch": 1.2468354430379747, "grad_norm": 0.20809575068692238, "learning_rate": 7.468511712635811e-05, "loss": 0.3437, "step": 394 }, { "epoch": 1.25, "grad_norm": 0.22974174290804428, "learning_rate": 7.464101615137756e-05, "loss": 0.3376, "step": 395 }, { "epoch": 1.2531645569620253, "grad_norm": 0.24960629394167635, "learning_rate": 7.459674609687982e-05, "loss": 0.3401, "step": 396 }, { "epoch": 1.2563291139240507, "grad_norm": 0.31883945763730864, "learning_rate": 7.455230717894286e-05, "loss": 0.3481, "step": 397 }, { "epoch": 1.259493670886076, "grad_norm": 0.39190821443102947, "learning_rate": 7.45076996144688e-05, "loss": 0.3467, "step": 398 }, { "epoch": 1.2626582278481013, "grad_norm": 0.41077565729098203, "learning_rate": 7.446292362118296e-05, "loss": 0.3438, "step": 399 }, { "epoch": 1.2658227848101267, "grad_norm": 0.3330752358447778, "learning_rate": 7.44179794176327e-05, "loss": 0.3414, "step": 400 }, { "epoch": 1.268987341772152, "grad_norm": 0.213134564195997, "learning_rate": 7.437286722318645e-05, "loss": 0.3425, "step": 401 }, { "epoch": 1.2721518987341773, "grad_norm": 0.19717693839763548, "learning_rate": 7.432758725803252e-05, "loss": 0.3403, "step": 402 }, { "epoch": 1.2753164556962027, "grad_norm": 0.2385841933409247, "learning_rate": 7.428213974317815e-05, "loss": 0.3437, "step": 403 }, { "epoch": 1.2784810126582278, "grad_norm": 0.28618809712579757, "learning_rate": 7.423652490044834e-05, "loss": 0.3402, "step": 404 }, { "epoch": 1.2816455696202531, "grad_norm": 0.23851154196531915, "learning_rate": 7.419074295248482e-05, "loss": 0.3453, "step": 405 }, { "epoch": 1.2848101265822784, "grad_norm": 0.17313529164115343, "learning_rate": 7.414479412274497e-05, "loss": 0.3405, "step": 406 }, { "epoch": 1.2879746835443038, "grad_norm": 0.2223916259059402, "learning_rate": 7.409867863550061e-05, "loss": 0.3434, "step": 407 }, { "epoch": 1.2911392405063291, "grad_norm": 0.28753365075410686, "learning_rate": 7.405239671583712e-05, "loss": 0.3429, "step": 408 }, { "epoch": 1.2943037974683544, "grad_norm": 0.2801577537539225, "learning_rate": 7.400594858965213e-05, "loss": 0.3421, "step": 409 }, { "epoch": 1.2974683544303798, "grad_norm": 0.24114604845075166, "learning_rate": 7.395933448365457e-05, "loss": 0.344, "step": 410 }, { "epoch": 1.3006329113924051, "grad_norm": 0.19597191228678768, "learning_rate": 7.391255462536344e-05, "loss": 0.3461, "step": 411 }, { "epoch": 1.3037974683544304, "grad_norm": 0.19640256946748577, "learning_rate": 7.386560924310684e-05, "loss": 0.3453, "step": 412 }, { "epoch": 1.3069620253164558, "grad_norm": 0.1731872606939925, "learning_rate": 7.381849856602068e-05, "loss": 0.3401, "step": 413 }, { "epoch": 1.310126582278481, "grad_norm": 0.25861629585498247, "learning_rate": 7.377122282404774e-05, "loss": 0.3448, "step": 414 }, { "epoch": 1.3132911392405062, "grad_norm": 0.28538064754201276, "learning_rate": 7.372378224793646e-05, "loss": 0.3389, "step": 415 }, { "epoch": 1.3164556962025316, "grad_norm": 0.21311813462280338, "learning_rate": 7.367617706923975e-05, "loss": 0.3419, "step": 416 }, { "epoch": 1.3196202531645569, "grad_norm": 0.20309669591770688, "learning_rate": 7.3628407520314e-05, "loss": 0.3432, "step": 417 }, { "epoch": 1.3227848101265822, "grad_norm": 0.243040534583798, "learning_rate": 7.358047383431783e-05, "loss": 0.3394, "step": 418 }, { "epoch": 1.3259493670886076, "grad_norm": 0.27935582567179557, "learning_rate": 7.353237624521107e-05, "loss": 0.3441, "step": 419 }, { "epoch": 1.3291139240506329, "grad_norm": 0.22998050207198806, "learning_rate": 7.348411498775344e-05, "loss": 0.3391, "step": 420 }, { "epoch": 1.3322784810126582, "grad_norm": 0.18741553423374663, "learning_rate": 7.34356902975036e-05, "loss": 0.3397, "step": 421 }, { "epoch": 1.3354430379746836, "grad_norm": 0.19347757599192725, "learning_rate": 7.338710241081786e-05, "loss": 0.3423, "step": 422 }, { "epoch": 1.3386075949367089, "grad_norm": 0.1724065756257274, "learning_rate": 7.333835156484909e-05, "loss": 0.3356, "step": 423 }, { "epoch": 1.3417721518987342, "grad_norm": 0.21586076658374223, "learning_rate": 7.328943799754552e-05, "loss": 0.3394, "step": 424 }, { "epoch": 1.3449367088607596, "grad_norm": 0.2624626163521611, "learning_rate": 7.324036194764969e-05, "loss": 0.3449, "step": 425 }, { "epoch": 1.3481012658227849, "grad_norm": 0.2404028982535689, "learning_rate": 7.319112365469714e-05, "loss": 0.3399, "step": 426 }, { "epoch": 1.3512658227848102, "grad_norm": 0.18829376737986478, "learning_rate": 7.314172335901527e-05, "loss": 0.3409, "step": 427 }, { "epoch": 1.3544303797468356, "grad_norm": 0.17574217823357252, "learning_rate": 7.30921613017223e-05, "loss": 0.3399, "step": 428 }, { "epoch": 1.3575949367088609, "grad_norm": 0.20989718754564968, "learning_rate": 7.304243772472589e-05, "loss": 0.3354, "step": 429 }, { "epoch": 1.360759493670886, "grad_norm": 0.2588153500044668, "learning_rate": 7.299255287072213e-05, "loss": 0.3384, "step": 430 }, { "epoch": 1.3639240506329113, "grad_norm": 0.29028311210385255, "learning_rate": 7.294250698319424e-05, "loss": 0.3354, "step": 431 }, { "epoch": 1.3670886075949367, "grad_norm": 0.33709952948157856, "learning_rate": 7.289230030641149e-05, "loss": 0.3462, "step": 432 }, { "epoch": 1.370253164556962, "grad_norm": 0.44135682814739874, "learning_rate": 7.284193308542788e-05, "loss": 0.352, "step": 433 }, { "epoch": 1.3734177215189873, "grad_norm": 0.5198061569350169, "learning_rate": 7.279140556608106e-05, "loss": 0.3475, "step": 434 }, { "epoch": 1.3765822784810127, "grad_norm": 0.47527523594214616, "learning_rate": 7.274071799499107e-05, "loss": 0.346, "step": 435 }, { "epoch": 1.379746835443038, "grad_norm": 0.36275358847638295, "learning_rate": 7.268987061955912e-05, "loss": 0.3418, "step": 436 }, { "epoch": 1.3829113924050633, "grad_norm": 0.3110834253361213, "learning_rate": 7.263886368796645e-05, "loss": 0.3391, "step": 437 }, { "epoch": 1.3860759493670887, "grad_norm": 0.33665343084444627, "learning_rate": 7.258769744917304e-05, "loss": 0.342, "step": 438 }, { "epoch": 1.389240506329114, "grad_norm": 0.2863735388595085, "learning_rate": 7.253637215291647e-05, "loss": 0.3458, "step": 439 }, { "epoch": 1.3924050632911391, "grad_norm": 0.22413880751359225, "learning_rate": 7.248488804971066e-05, "loss": 0.3432, "step": 440 }, { "epoch": 1.3955696202531644, "grad_norm": 0.2684014720113226, "learning_rate": 7.243324539084461e-05, "loss": 0.3434, "step": 441 }, { "epoch": 1.3987341772151898, "grad_norm": 0.2926967379977739, "learning_rate": 7.238144442838125e-05, "loss": 0.3351, "step": 442 }, { "epoch": 1.4018987341772151, "grad_norm": 0.19110127614684086, "learning_rate": 7.232948541515618e-05, "loss": 0.343, "step": 443 }, { "epoch": 1.4050632911392404, "grad_norm": 0.2147581593974418, "learning_rate": 7.227736860477642e-05, "loss": 0.3431, "step": 444 }, { "epoch": 1.4082278481012658, "grad_norm": 0.2616906163032211, "learning_rate": 7.222509425161917e-05, "loss": 0.3378, "step": 445 }, { "epoch": 1.4113924050632911, "grad_norm": 0.23946229424231424, "learning_rate": 7.21726626108306e-05, "loss": 0.3373, "step": 446 }, { "epoch": 1.4145569620253164, "grad_norm": 0.22921657325033726, "learning_rate": 7.212007393832459e-05, "loss": 0.3433, "step": 447 }, { "epoch": 1.4177215189873418, "grad_norm": 0.23259065469704546, "learning_rate": 7.206732849078144e-05, "loss": 0.3425, "step": 448 }, { "epoch": 1.4208860759493671, "grad_norm": 0.2011758479974013, "learning_rate": 7.201442652564672e-05, "loss": 0.3361, "step": 449 }, { "epoch": 1.4240506329113924, "grad_norm": 0.19386762445618286, "learning_rate": 7.196136830112988e-05, "loss": 0.3438, "step": 450 }, { "epoch": 1.4272151898734178, "grad_norm": 0.21412798338290961, "learning_rate": 7.19081540762031e-05, "loss": 0.3413, "step": 451 }, { "epoch": 1.4303797468354431, "grad_norm": 0.23847450519537816, "learning_rate": 7.185478411059996e-05, "loss": 0.3435, "step": 452 }, { "epoch": 1.4335443037974684, "grad_norm": 0.2607342469778821, "learning_rate": 7.18012586648142e-05, "loss": 0.334, "step": 453 }, { "epoch": 1.4367088607594938, "grad_norm": 0.22643010484336185, "learning_rate": 7.174757800009846e-05, "loss": 0.3357, "step": 454 }, { "epoch": 1.439873417721519, "grad_norm": 0.2146740538936408, "learning_rate": 7.169374237846298e-05, "loss": 0.3394, "step": 455 }, { "epoch": 1.4430379746835442, "grad_norm": 0.2609228082233888, "learning_rate": 7.163975206267433e-05, "loss": 0.3427, "step": 456 }, { "epoch": 1.4462025316455696, "grad_norm": 0.2832249568677286, "learning_rate": 7.158560731625409e-05, "loss": 0.3438, "step": 457 }, { "epoch": 1.4493670886075949, "grad_norm": 0.2117000732831132, "learning_rate": 7.153130840347769e-05, "loss": 0.3422, "step": 458 }, { "epoch": 1.4525316455696202, "grad_norm": 0.16758728127641742, "learning_rate": 7.147685558937294e-05, "loss": 0.3389, "step": 459 }, { "epoch": 1.4556962025316456, "grad_norm": 0.2011821830302993, "learning_rate": 7.142224913971887e-05, "loss": 0.3352, "step": 460 }, { "epoch": 1.4588607594936709, "grad_norm": 0.2155597155230745, "learning_rate": 7.136748932104441e-05, "loss": 0.345, "step": 461 }, { "epoch": 1.4620253164556962, "grad_norm": 0.23387119422965785, "learning_rate": 7.131257640062701e-05, "loss": 0.3397, "step": 462 }, { "epoch": 1.4651898734177216, "grad_norm": 0.20298518182863878, "learning_rate": 7.125751064649147e-05, "loss": 0.3385, "step": 463 }, { "epoch": 1.4683544303797469, "grad_norm": 0.20947574193111557, "learning_rate": 7.12022923274085e-05, "loss": 0.3377, "step": 464 }, { "epoch": 1.4715189873417722, "grad_norm": 0.15994450319967274, "learning_rate": 7.114692171289345e-05, "loss": 0.3393, "step": 465 }, { "epoch": 1.4746835443037973, "grad_norm": 0.14628067889817295, "learning_rate": 7.109139907320509e-05, "loss": 0.3382, "step": 466 }, { "epoch": 1.4778481012658227, "grad_norm": 0.16016270971833146, "learning_rate": 7.103572467934416e-05, "loss": 0.3385, "step": 467 }, { "epoch": 1.481012658227848, "grad_norm": 0.15557188347877246, "learning_rate": 7.097989880305207e-05, "loss": 0.3375, "step": 468 }, { "epoch": 1.4841772151898733, "grad_norm": 0.11515043992692063, "learning_rate": 7.092392171680966e-05, "loss": 0.3429, "step": 469 }, { "epoch": 1.4873417721518987, "grad_norm": 0.14567194511755127, "learning_rate": 7.086779369383576e-05, "loss": 0.3413, "step": 470 }, { "epoch": 1.490506329113924, "grad_norm": 0.1859055482258055, "learning_rate": 7.081151500808594e-05, "loss": 0.3418, "step": 471 }, { "epoch": 1.4936708860759493, "grad_norm": 0.204518947309788, "learning_rate": 7.075508593425115e-05, "loss": 0.3438, "step": 472 }, { "epoch": 1.4968354430379747, "grad_norm": 0.175992222286129, "learning_rate": 7.069850674775633e-05, "loss": 0.3396, "step": 473 }, { "epoch": 1.5, "grad_norm": 0.16716032494501704, "learning_rate": 7.064177772475912e-05, "loss": 0.3436, "step": 474 }, { "epoch": 1.5031645569620253, "grad_norm": 0.15449993711697424, "learning_rate": 7.058489914214854e-05, "loss": 0.3346, "step": 475 }, { "epoch": 1.5063291139240507, "grad_norm": 0.1870862643266508, "learning_rate": 7.052787127754353e-05, "loss": 0.3445, "step": 476 }, { "epoch": 1.509493670886076, "grad_norm": 0.21194832957559442, "learning_rate": 7.047069440929171e-05, "loss": 0.3394, "step": 477 }, { "epoch": 1.5126582278481013, "grad_norm": 0.22962645907209686, "learning_rate": 7.041336881646796e-05, "loss": 0.3414, "step": 478 }, { "epoch": 1.5158227848101267, "grad_norm": 0.2124383721508636, "learning_rate": 7.035589477887305e-05, "loss": 0.3368, "step": 479 }, { "epoch": 1.518987341772152, "grad_norm": 0.17175263606543598, "learning_rate": 7.029827257703231e-05, "loss": 0.3376, "step": 480 }, { "epoch": 1.5221518987341773, "grad_norm": 0.19842440546789114, "learning_rate": 7.024050249219426e-05, "loss": 0.3407, "step": 481 }, { "epoch": 1.5253164556962027, "grad_norm": 0.22384982909702372, "learning_rate": 7.018258480632922e-05, "loss": 0.3404, "step": 482 }, { "epoch": 1.528481012658228, "grad_norm": 0.26967968921920443, "learning_rate": 7.012451980212789e-05, "loss": 0.3406, "step": 483 }, { "epoch": 1.5316455696202531, "grad_norm": 0.33724000751019606, "learning_rate": 7.006630776300008e-05, "loss": 0.3375, "step": 484 }, { "epoch": 1.5348101265822784, "grad_norm": 0.3982699152438431, "learning_rate": 7.000794897307323e-05, "loss": 0.3438, "step": 485 }, { "epoch": 1.5379746835443038, "grad_norm": 0.44243588369824477, "learning_rate": 6.994944371719106e-05, "loss": 0.3452, "step": 486 }, { "epoch": 1.5411392405063291, "grad_norm": 0.4366095640439038, "learning_rate": 6.989079228091219e-05, "loss": 0.3444, "step": 487 }, { "epoch": 1.5443037974683544, "grad_norm": 0.3135251587200192, "learning_rate": 6.983199495050873e-05, "loss": 0.3419, "step": 488 }, { "epoch": 1.5474683544303798, "grad_norm": 0.2234445137381272, "learning_rate": 6.977305201296484e-05, "loss": 0.3423, "step": 489 }, { "epoch": 1.5506329113924051, "grad_norm": 0.3131742035083396, "learning_rate": 6.971396375597546e-05, "loss": 0.3428, "step": 490 }, { "epoch": 1.5537974683544302, "grad_norm": 0.3414532182275503, "learning_rate": 6.965473046794474e-05, "loss": 0.3404, "step": 491 }, { "epoch": 1.5569620253164556, "grad_norm": 0.29965166881258254, "learning_rate": 6.959535243798475e-05, "loss": 0.3494, "step": 492 }, { "epoch": 1.560126582278481, "grad_norm": 0.22374605671791145, "learning_rate": 6.953582995591403e-05, "loss": 0.3376, "step": 493 }, { "epoch": 1.5632911392405062, "grad_norm": 0.20659730074106286, "learning_rate": 6.947616331225618e-05, "loss": 0.3389, "step": 494 }, { "epoch": 1.5664556962025316, "grad_norm": 0.26694881100770707, "learning_rate": 6.941635279823845e-05, "loss": 0.3404, "step": 495 }, { "epoch": 1.5696202531645569, "grad_norm": 0.26533664941917723, "learning_rate": 6.935639870579026e-05, "loss": 0.3428, "step": 496 }, { "epoch": 1.5727848101265822, "grad_norm": 0.21448549177993823, "learning_rate": 6.929630132754187e-05, "loss": 0.3411, "step": 497 }, { "epoch": 1.5759493670886076, "grad_norm": 0.21635544363853826, "learning_rate": 6.923606095682287e-05, "loss": 0.3425, "step": 498 }, { "epoch": 1.5791139240506329, "grad_norm": 0.2751922737890928, "learning_rate": 6.917567788766083e-05, "loss": 0.3416, "step": 499 }, { "epoch": 1.5822784810126582, "grad_norm": 0.2693851546742822, "learning_rate": 6.911515241477978e-05, "loss": 0.3326, "step": 500 }, { "epoch": 1.5854430379746836, "grad_norm": 0.19445003914726156, "learning_rate": 6.905448483359879e-05, "loss": 0.3357, "step": 501 }, { "epoch": 1.5886075949367089, "grad_norm": 0.16413888068420532, "learning_rate": 6.899367544023061e-05, "loss": 0.3398, "step": 502 }, { "epoch": 1.5917721518987342, "grad_norm": 0.22588274637698472, "learning_rate": 6.893272453148012e-05, "loss": 0.3353, "step": 503 }, { "epoch": 1.5949367088607596, "grad_norm": 0.25047308794943063, "learning_rate": 6.88716324048429e-05, "loss": 0.3379, "step": 504 }, { "epoch": 1.5981012658227849, "grad_norm": 0.19477144536337176, "learning_rate": 6.881039935850388e-05, "loss": 0.339, "step": 505 }, { "epoch": 1.6012658227848102, "grad_norm": 0.20100265661080818, "learning_rate": 6.874902569133571e-05, "loss": 0.3427, "step": 506 }, { "epoch": 1.6044303797468356, "grad_norm": 0.2348624153657751, "learning_rate": 6.868751170289746e-05, "loss": 0.3368, "step": 507 }, { "epoch": 1.6075949367088609, "grad_norm": 0.19105539402090999, "learning_rate": 6.862585769343311e-05, "loss": 0.3403, "step": 508 }, { "epoch": 1.6107594936708862, "grad_norm": 0.18096442836237198, "learning_rate": 6.856406396387e-05, "loss": 0.3409, "step": 509 }, { "epoch": 1.6139240506329116, "grad_norm": 0.22030551347030178, "learning_rate": 6.850213081581746e-05, "loss": 0.3362, "step": 510 }, { "epoch": 1.6170886075949367, "grad_norm": 0.22278296312058074, "learning_rate": 6.844005855156536e-05, "loss": 0.3374, "step": 511 }, { "epoch": 1.620253164556962, "grad_norm": 0.18782289114704825, "learning_rate": 6.83778474740825e-05, "loss": 0.3368, "step": 512 }, { "epoch": 1.6234177215189873, "grad_norm": 0.1639703151980687, "learning_rate": 6.831549788701527e-05, "loss": 0.3359, "step": 513 }, { "epoch": 1.6265822784810127, "grad_norm": 0.18434443167680878, "learning_rate": 6.825301009468609e-05, "loss": 0.3369, "step": 514 }, { "epoch": 1.629746835443038, "grad_norm": 0.19745020470253563, "learning_rate": 6.819038440209197e-05, "loss": 0.3383, "step": 515 }, { "epoch": 1.6329113924050633, "grad_norm": 0.17350034447182666, "learning_rate": 6.812762111490297e-05, "loss": 0.3347, "step": 516 }, { "epoch": 1.6360759493670884, "grad_norm": 0.1724142118918572, "learning_rate": 6.806472053946073e-05, "loss": 0.3367, "step": 517 }, { "epoch": 1.6392405063291138, "grad_norm": 0.21442080671010927, "learning_rate": 6.800168298277702e-05, "loss": 0.3418, "step": 518 }, { "epoch": 1.6424050632911391, "grad_norm": 0.20664156433340153, "learning_rate": 6.793850875253218e-05, "loss": 0.3406, "step": 519 }, { "epoch": 1.6455696202531644, "grad_norm": 0.21129282700450885, "learning_rate": 6.787519815707363e-05, "loss": 0.3364, "step": 520 }, { "epoch": 1.6487341772151898, "grad_norm": 0.26557793725581685, "learning_rate": 6.781175150541438e-05, "loss": 0.3376, "step": 521 }, { "epoch": 1.6518987341772151, "grad_norm": 0.2721924571670864, "learning_rate": 6.774816910723157e-05, "loss": 0.3371, "step": 522 }, { "epoch": 1.6550632911392404, "grad_norm": 0.24687065735844538, "learning_rate": 6.76844512728648e-05, "loss": 0.334, "step": 523 }, { "epoch": 1.6582278481012658, "grad_norm": 0.2398531976264561, "learning_rate": 6.762059831331482e-05, "loss": 0.3379, "step": 524 }, { "epoch": 1.6613924050632911, "grad_norm": 0.23433650645330883, "learning_rate": 6.755661054024186e-05, "loss": 0.3462, "step": 525 }, { "epoch": 1.6645569620253164, "grad_norm": 0.2289002588994373, "learning_rate": 6.749248826596418e-05, "loss": 0.3419, "step": 526 }, { "epoch": 1.6677215189873418, "grad_norm": 0.1841671524587745, "learning_rate": 6.742823180345654e-05, "loss": 0.34, "step": 527 }, { "epoch": 1.6708860759493671, "grad_norm": 0.15621810461333868, "learning_rate": 6.736384146634861e-05, "loss": 0.3405, "step": 528 }, { "epoch": 1.6740506329113924, "grad_norm": 0.18247988390256306, "learning_rate": 6.729931756892354e-05, "loss": 0.3338, "step": 529 }, { "epoch": 1.6772151898734178, "grad_norm": 0.20449013202804653, "learning_rate": 6.723466042611638e-05, "loss": 0.3352, "step": 530 }, { "epoch": 1.6803797468354431, "grad_norm": 0.18274784250863194, "learning_rate": 6.71698703535125e-05, "loss": 0.331, "step": 531 }, { "epoch": 1.6835443037974684, "grad_norm": 0.1859464839923433, "learning_rate": 6.710494766734607e-05, "loss": 0.3364, "step": 532 }, { "epoch": 1.6867088607594938, "grad_norm": 0.17610982378460988, "learning_rate": 6.703989268449863e-05, "loss": 0.3422, "step": 533 }, { "epoch": 1.689873417721519, "grad_norm": 0.16468078662961655, "learning_rate": 6.697470572249735e-05, "loss": 0.3345, "step": 534 }, { "epoch": 1.6930379746835444, "grad_norm": 0.16426443150357697, "learning_rate": 6.690938709951364e-05, "loss": 0.3341, "step": 535 }, { "epoch": 1.6962025316455698, "grad_norm": 0.1442865829181026, "learning_rate": 6.684393713436148e-05, "loss": 0.3394, "step": 536 }, { "epoch": 1.6993670886075949, "grad_norm": 0.17817618769043184, "learning_rate": 6.677835614649595e-05, "loss": 0.3389, "step": 537 }, { "epoch": 1.7025316455696202, "grad_norm": 0.17862702082454512, "learning_rate": 6.671264445601166e-05, "loss": 0.3383, "step": 538 }, { "epoch": 1.7056962025316456, "grad_norm": 0.16130240321327247, "learning_rate": 6.664680238364114e-05, "loss": 0.3361, "step": 539 }, { "epoch": 1.7088607594936709, "grad_norm": 0.15298338584781795, "learning_rate": 6.658083025075328e-05, "loss": 0.3382, "step": 540 }, { "epoch": 1.7120253164556962, "grad_norm": 0.16091083395757505, "learning_rate": 6.651472837935184e-05, "loss": 0.3392, "step": 541 }, { "epoch": 1.7151898734177216, "grad_norm": 0.1604581235989163, "learning_rate": 6.644849709207376e-05, "loss": 0.3456, "step": 542 }, { "epoch": 1.7183544303797469, "grad_norm": 0.1683653511687011, "learning_rate": 6.63821367121877e-05, "loss": 0.3403, "step": 543 }, { "epoch": 1.721518987341772, "grad_norm": 0.16035974293337774, "learning_rate": 6.631564756359238e-05, "loss": 0.3348, "step": 544 }, { "epoch": 1.7246835443037973, "grad_norm": 0.18140563798057688, "learning_rate": 6.624902997081502e-05, "loss": 0.3441, "step": 545 }, { "epoch": 1.7278481012658227, "grad_norm": 0.1822467877438434, "learning_rate": 6.618228425900982e-05, "loss": 0.3348, "step": 546 }, { "epoch": 1.731012658227848, "grad_norm": 0.2118034678863081, "learning_rate": 6.611541075395621e-05, "loss": 0.3402, "step": 547 }, { "epoch": 1.7341772151898733, "grad_norm": 0.2712982806859355, "learning_rate": 6.60484097820575e-05, "loss": 0.3419, "step": 548 }, { "epoch": 1.7373417721518987, "grad_norm": 0.26579191857262635, "learning_rate": 6.598128167033903e-05, "loss": 0.3423, "step": 549 }, { "epoch": 1.740506329113924, "grad_norm": 0.22247113506159125, "learning_rate": 6.591402674644679e-05, "loss": 0.3433, "step": 550 }, { "epoch": 1.7436708860759493, "grad_norm": 0.2136354135164637, "learning_rate": 6.584664533864566e-05, "loss": 0.3369, "step": 551 }, { "epoch": 1.7468354430379747, "grad_norm": 0.22477813437547756, "learning_rate": 6.577913777581792e-05, "loss": 0.335, "step": 552 }, { "epoch": 1.75, "grad_norm": 0.19265451091524705, "learning_rate": 6.571150438746157e-05, "loss": 0.3464, "step": 553 }, { "epoch": 1.7531645569620253, "grad_norm": 0.16328026637585338, "learning_rate": 6.56437455036888e-05, "loss": 0.3362, "step": 554 }, { "epoch": 1.7563291139240507, "grad_norm": 0.17615416464128097, "learning_rate": 6.55758614552243e-05, "loss": 0.3383, "step": 555 }, { "epoch": 1.759493670886076, "grad_norm": 0.19860287022998505, "learning_rate": 6.550785257340366e-05, "loss": 0.3397, "step": 556 }, { "epoch": 1.7626582278481013, "grad_norm": 0.19894028157902352, "learning_rate": 6.543971919017178e-05, "loss": 0.3365, "step": 557 }, { "epoch": 1.7658227848101267, "grad_norm": 0.18095697638615843, "learning_rate": 6.537146163808127e-05, "loss": 0.3351, "step": 558 }, { "epoch": 1.768987341772152, "grad_norm": 0.17301534282819878, "learning_rate": 6.530308025029074e-05, "loss": 0.3386, "step": 559 }, { "epoch": 1.7721518987341773, "grad_norm": 0.16047817871554176, "learning_rate": 6.523457536056332e-05, "loss": 0.3432, "step": 560 }, { "epoch": 1.7753164556962027, "grad_norm": 0.13819878176143488, "learning_rate": 6.516594730326482e-05, "loss": 0.3356, "step": 561 }, { "epoch": 1.778481012658228, "grad_norm": 0.18689768401888984, "learning_rate": 6.509719641336232e-05, "loss": 0.3406, "step": 562 }, { "epoch": 1.7816455696202531, "grad_norm": 0.1689156201146511, "learning_rate": 6.50283230264224e-05, "loss": 0.3337, "step": 563 }, { "epoch": 1.7848101265822784, "grad_norm": 0.14749486314219432, "learning_rate": 6.495932747860954e-05, "loss": 0.3402, "step": 564 }, { "epoch": 1.7879746835443038, "grad_norm": 0.14496074184388613, "learning_rate": 6.489021010668443e-05, "loss": 0.3382, "step": 565 }, { "epoch": 1.7911392405063291, "grad_norm": 0.15890279883522712, "learning_rate": 6.482097124800248e-05, "loss": 0.3385, "step": 566 }, { "epoch": 1.7943037974683544, "grad_norm": 0.19676308717264138, "learning_rate": 6.475161124051193e-05, "loss": 0.3342, "step": 567 }, { "epoch": 1.7974683544303798, "grad_norm": 0.20547974370035216, "learning_rate": 6.468213042275246e-05, "loss": 0.3365, "step": 568 }, { "epoch": 1.8006329113924051, "grad_norm": 0.2160042500780742, "learning_rate": 6.461252913385331e-05, "loss": 0.3378, "step": 569 }, { "epoch": 1.8037974683544302, "grad_norm": 0.23259892484224529, "learning_rate": 6.454280771353181e-05, "loss": 0.3333, "step": 570 }, { "epoch": 1.8069620253164556, "grad_norm": 0.2442715130818427, "learning_rate": 6.447296650209159e-05, "loss": 0.3382, "step": 571 }, { "epoch": 1.810126582278481, "grad_norm": 0.25812761208810825, "learning_rate": 6.440300584042097e-05, "loss": 0.3386, "step": 572 }, { "epoch": 1.8132911392405062, "grad_norm": 0.25144992993437676, "learning_rate": 6.433292606999136e-05, "loss": 0.34, "step": 573 }, { "epoch": 1.8164556962025316, "grad_norm": 0.20987169881257306, "learning_rate": 6.426272753285541e-05, "loss": 0.3363, "step": 574 }, { "epoch": 1.8196202531645569, "grad_norm": 0.16273063160945977, "learning_rate": 6.41924105716456e-05, "loss": 0.3395, "step": 575 }, { "epoch": 1.8227848101265822, "grad_norm": 0.17537301747639117, "learning_rate": 6.41219755295723e-05, "loss": 0.339, "step": 576 }, { "epoch": 1.8259493670886076, "grad_norm": 0.17080353249622227, "learning_rate": 6.405142275042229e-05, "loss": 0.3359, "step": 577 }, { "epoch": 1.8291139240506329, "grad_norm": 0.2030355376537625, "learning_rate": 6.3980752578557e-05, "loss": 0.3315, "step": 578 }, { "epoch": 1.8322784810126582, "grad_norm": 0.19707751153287775, "learning_rate": 6.390996535891087e-05, "loss": 0.3384, "step": 579 }, { "epoch": 1.8354430379746836, "grad_norm": 0.16556207934338132, "learning_rate": 6.383906143698957e-05, "loss": 0.3369, "step": 580 }, { "epoch": 1.8386075949367089, "grad_norm": 0.14959258008803888, "learning_rate": 6.376804115886843e-05, "loss": 0.3362, "step": 581 }, { "epoch": 1.8417721518987342, "grad_norm": 0.12622961366204702, "learning_rate": 6.369690487119071e-05, "loss": 0.3318, "step": 582 }, { "epoch": 1.8449367088607596, "grad_norm": 0.1420137504958197, "learning_rate": 6.362565292116589e-05, "loss": 0.3315, "step": 583 }, { "epoch": 1.8481012658227849, "grad_norm": 0.14016147906844748, "learning_rate": 6.355428565656799e-05, "loss": 0.3382, "step": 584 }, { "epoch": 1.8512658227848102, "grad_norm": 0.1904773059240311, "learning_rate": 6.348280342573385e-05, "loss": 0.3356, "step": 585 }, { "epoch": 1.8544303797468356, "grad_norm": 0.19654741551880525, "learning_rate": 6.341120657756147e-05, "loss": 0.3326, "step": 586 }, { "epoch": 1.8575949367088609, "grad_norm": 0.19647233952953932, "learning_rate": 6.33394954615083e-05, "loss": 0.3325, "step": 587 }, { "epoch": 1.8607594936708862, "grad_norm": 0.17749340906080227, "learning_rate": 6.326767042758948e-05, "loss": 0.3384, "step": 588 }, { "epoch": 1.8639240506329116, "grad_norm": 0.19177032102972236, "learning_rate": 6.31957318263762e-05, "loss": 0.3381, "step": 589 }, { "epoch": 1.8670886075949367, "grad_norm": 0.16565858433632707, "learning_rate": 6.312368000899394e-05, "loss": 0.3344, "step": 590 }, { "epoch": 1.870253164556962, "grad_norm": 0.16599561282022793, "learning_rate": 6.305151532712082e-05, "loss": 0.3375, "step": 591 }, { "epoch": 1.8734177215189873, "grad_norm": 0.18929640388924338, "learning_rate": 6.29792381329858e-05, "loss": 0.3324, "step": 592 }, { "epoch": 1.8765822784810127, "grad_norm": 0.17948456982475344, "learning_rate": 6.290684877936703e-05, "loss": 0.3333, "step": 593 }, { "epoch": 1.879746835443038, "grad_norm": 0.17682779881671334, "learning_rate": 6.283434761959007e-05, "loss": 0.3331, "step": 594 }, { "epoch": 1.8829113924050633, "grad_norm": 0.17754785301500095, "learning_rate": 6.27617350075262e-05, "loss": 0.336, "step": 595 }, { "epoch": 1.8860759493670884, "grad_norm": 0.1624584701884107, "learning_rate": 6.268901129759073e-05, "loss": 0.3343, "step": 596 }, { "epoch": 1.8892405063291138, "grad_norm": 0.18924534059722523, "learning_rate": 6.261617684474116e-05, "loss": 0.3358, "step": 597 }, { "epoch": 1.8924050632911391, "grad_norm": 0.1836242356227342, "learning_rate": 6.25432320044756e-05, "loss": 0.3402, "step": 598 }, { "epoch": 1.8955696202531644, "grad_norm": 0.1533412791168749, "learning_rate": 6.247017713283084e-05, "loss": 0.3379, "step": 599 }, { "epoch": 1.8987341772151898, "grad_norm": 0.17115547262093256, "learning_rate": 6.239701258638084e-05, "loss": 0.337, "step": 600 }, { "epoch": 1.9018987341772151, "grad_norm": 0.16876916514334092, "learning_rate": 6.232373872223478e-05, "loss": 0.3359, "step": 601 }, { "epoch": 1.9050632911392404, "grad_norm": 0.14531441757584979, "learning_rate": 6.225035589803548e-05, "loss": 0.3298, "step": 602 }, { "epoch": 1.9082278481012658, "grad_norm": 0.19150667961699658, "learning_rate": 6.217686447195756e-05, "loss": 0.3344, "step": 603 }, { "epoch": 1.9113924050632911, "grad_norm": 0.1617234752455982, "learning_rate": 6.210326480270564e-05, "loss": 0.3335, "step": 604 }, { "epoch": 1.9145569620253164, "grad_norm": 0.1260269330630025, "learning_rate": 6.20295572495128e-05, "loss": 0.3386, "step": 605 }, { "epoch": 1.9177215189873418, "grad_norm": 0.12324350053638812, "learning_rate": 6.195574217213858e-05, "loss": 0.3365, "step": 606 }, { "epoch": 1.9208860759493671, "grad_norm": 0.11068141555145485, "learning_rate": 6.188181993086741e-05, "loss": 0.3364, "step": 607 }, { "epoch": 1.9240506329113924, "grad_norm": 0.11754609896389309, "learning_rate": 6.18077908865067e-05, "loss": 0.334, "step": 608 }, { "epoch": 1.9272151898734178, "grad_norm": 0.12814391587578575, "learning_rate": 6.173365540038526e-05, "loss": 0.3333, "step": 609 }, { "epoch": 1.9303797468354431, "grad_norm": 0.14686261011508112, "learning_rate": 6.165941383435134e-05, "loss": 0.3375, "step": 610 }, { "epoch": 1.9335443037974684, "grad_norm": 0.15850538165317993, "learning_rate": 6.158506655077098e-05, "loss": 0.3363, "step": 611 }, { "epoch": 1.9367088607594938, "grad_norm": 0.1931652745089789, "learning_rate": 6.151061391252623e-05, "loss": 0.3322, "step": 612 }, { "epoch": 1.939873417721519, "grad_norm": 0.22085677903080506, "learning_rate": 6.143605628301338e-05, "loss": 0.3387, "step": 613 }, { "epoch": 1.9430379746835444, "grad_norm": 0.24997896175818263, "learning_rate": 6.136139402614113e-05, "loss": 0.3376, "step": 614 }, { "epoch": 1.9462025316455698, "grad_norm": 0.2843791108448209, "learning_rate": 6.12866275063289e-05, "loss": 0.3367, "step": 615 }, { "epoch": 1.9493670886075949, "grad_norm": 0.29280503763695853, "learning_rate": 6.121175708850497e-05, "loss": 0.3408, "step": 616 }, { "epoch": 1.9525316455696202, "grad_norm": 0.2493143240458061, "learning_rate": 6.113678313810479e-05, "loss": 0.3371, "step": 617 }, { "epoch": 1.9556962025316456, "grad_norm": 0.18396836493825122, "learning_rate": 6.106170602106906e-05, "loss": 0.3327, "step": 618 }, { "epoch": 1.9588607594936709, "grad_norm": 0.16644761753862716, "learning_rate": 6.0986526103842107e-05, "loss": 0.3353, "step": 619 }, { "epoch": 1.9620253164556962, "grad_norm": 0.2004083334620533, "learning_rate": 6.091124375336997e-05, "loss": 0.3323, "step": 620 }, { "epoch": 1.9651898734177216, "grad_norm": 0.2195838561628802, "learning_rate": 6.0835859337098675e-05, "loss": 0.3325, "step": 621 }, { "epoch": 1.9683544303797469, "grad_norm": 0.20857641731343984, "learning_rate": 6.076037322297241e-05, "loss": 0.3336, "step": 622 }, { "epoch": 1.971518987341772, "grad_norm": 0.16787487838741205, "learning_rate": 6.068478577943173e-05, "loss": 0.3301, "step": 623 }, { "epoch": 1.9746835443037973, "grad_norm": 0.13103586803816392, "learning_rate": 6.060909737541181e-05, "loss": 0.3349, "step": 624 }, { "epoch": 1.9778481012658227, "grad_norm": 0.17296137178080265, "learning_rate": 6.0533308380340555e-05, "loss": 0.3339, "step": 625 }, { "epoch": 1.981012658227848, "grad_norm": 0.21145146144200389, "learning_rate": 6.04574191641369e-05, "loss": 0.3359, "step": 626 }, { "epoch": 1.9841772151898733, "grad_norm": 0.19575851400917854, "learning_rate": 6.0381430097208875e-05, "loss": 0.3344, "step": 627 }, { "epoch": 1.9873417721518987, "grad_norm": 0.19175840394241467, "learning_rate": 6.030534155045195e-05, "loss": 0.3341, "step": 628 }, { "epoch": 1.990506329113924, "grad_norm": 0.16294115827534358, "learning_rate": 6.022915389524709e-05, "loss": 0.3319, "step": 629 }, { "epoch": 1.9936708860759493, "grad_norm": 0.15073193198599094, "learning_rate": 6.015286750345903e-05, "loss": 0.3334, "step": 630 }, { "epoch": 1.9968354430379747, "grad_norm": 0.1810949998902179, "learning_rate": 6.007648274743441e-05, "loss": 0.3356, "step": 631 }, { "epoch": 2.0, "grad_norm": 0.20888101523108604, "learning_rate": 6.000000000000001e-05, "loss": 0.3168, "step": 632 }, { "epoch": 2.0031645569620253, "grad_norm": 0.2645321416012372, "learning_rate": 5.992341963446084e-05, "loss": 0.3115, "step": 633 }, { "epoch": 2.0063291139240507, "grad_norm": 0.2517044101372924, "learning_rate": 5.984674202459843e-05, "loss": 0.3125, "step": 634 }, { "epoch": 2.009493670886076, "grad_norm": 0.24685837841678096, "learning_rate": 5.976996754466892e-05, "loss": 0.3155, "step": 635 }, { "epoch": 2.0126582278481013, "grad_norm": 0.28908097394561477, "learning_rate": 5.969309656940128e-05, "loss": 0.3162, "step": 636 }, { "epoch": 2.0158227848101267, "grad_norm": 0.31916916300588616, "learning_rate": 5.961612947399543e-05, "loss": 0.3139, "step": 637 }, { "epoch": 2.018987341772152, "grad_norm": 0.3622892247315952, "learning_rate": 5.9539066634120504e-05, "loss": 0.3137, "step": 638 }, { "epoch": 2.0221518987341773, "grad_norm": 0.3363105789938828, "learning_rate": 5.946190842591288e-05, "loss": 0.3088, "step": 639 }, { "epoch": 2.0253164556962027, "grad_norm": 0.3477651088869846, "learning_rate": 5.938465522597451e-05, "loss": 0.3109, "step": 640 }, { "epoch": 2.028481012658228, "grad_norm": 0.4280669790758216, "learning_rate": 5.93073074113709e-05, "loss": 0.3122, "step": 641 }, { "epoch": 2.0316455696202533, "grad_norm": 0.42763575803680526, "learning_rate": 5.922986535962943e-05, "loss": 0.317, "step": 642 }, { "epoch": 2.0348101265822787, "grad_norm": 0.3008737500861123, "learning_rate": 5.9152329448737393e-05, "loss": 0.3037, "step": 643 }, { "epoch": 2.037974683544304, "grad_norm": 0.24300632290246352, "learning_rate": 5.907470005714025e-05, "loss": 0.3094, "step": 644 }, { "epoch": 2.041139240506329, "grad_norm": 0.3691847515041416, "learning_rate": 5.899697756373968e-05, "loss": 0.3086, "step": 645 }, { "epoch": 2.0443037974683542, "grad_norm": 0.351812217348933, "learning_rate": 5.8919162347891826e-05, "loss": 0.3147, "step": 646 }, { "epoch": 2.0474683544303796, "grad_norm": 0.2694129500815389, "learning_rate": 5.884125478940537e-05, "loss": 0.3096, "step": 647 }, { "epoch": 2.050632911392405, "grad_norm": 0.22914749889050906, "learning_rate": 5.876325526853972e-05, "loss": 0.3095, "step": 648 }, { "epoch": 2.0537974683544302, "grad_norm": 0.21732546942460326, "learning_rate": 5.8685164166003164e-05, "loss": 0.3081, "step": 649 }, { "epoch": 2.0569620253164556, "grad_norm": 0.23417253745448188, "learning_rate": 5.860698186295096e-05, "loss": 0.3122, "step": 650 }, { "epoch": 2.060126582278481, "grad_norm": 0.1912247646282826, "learning_rate": 5.852870874098352e-05, "loss": 0.3096, "step": 651 }, { "epoch": 2.0632911392405062, "grad_norm": 0.20801930239672134, "learning_rate": 5.8450345182144543e-05, "loss": 0.3096, "step": 652 }, { "epoch": 2.0664556962025316, "grad_norm": 0.21797278318454033, "learning_rate": 5.8371891568919116e-05, "loss": 0.312, "step": 653 }, { "epoch": 2.069620253164557, "grad_norm": 0.18367914288410814, "learning_rate": 5.829334828423192e-05, "loss": 0.3103, "step": 654 }, { "epoch": 2.0727848101265822, "grad_norm": 0.1965399428222605, "learning_rate": 5.821471571144526e-05, "loss": 0.3076, "step": 655 }, { "epoch": 2.0759493670886076, "grad_norm": 0.2009032757375573, "learning_rate": 5.8135994234357276e-05, "loss": 0.3115, "step": 656 }, { "epoch": 2.079113924050633, "grad_norm": 0.15265773944656238, "learning_rate": 5.805718423720006e-05, "loss": 0.3068, "step": 657 }, { "epoch": 2.0822784810126582, "grad_norm": 0.1741156716964163, "learning_rate": 5.797828610463771e-05, "loss": 0.3122, "step": 658 }, { "epoch": 2.0854430379746836, "grad_norm": 0.1728458681394801, "learning_rate": 5.789930022176454e-05, "loss": 0.303, "step": 659 }, { "epoch": 2.088607594936709, "grad_norm": 0.1682110356196172, "learning_rate": 5.7820226974103173e-05, "loss": 0.31, "step": 660 }, { "epoch": 2.0917721518987342, "grad_norm": 0.15324565410453128, "learning_rate": 5.774106674760264e-05, "loss": 0.3095, "step": 661 }, { "epoch": 2.0949367088607596, "grad_norm": 0.1480267500922851, "learning_rate": 5.7661819928636484e-05, "loss": 0.3105, "step": 662 }, { "epoch": 2.098101265822785, "grad_norm": 0.13296727039447437, "learning_rate": 5.758248690400093e-05, "loss": 0.31, "step": 663 }, { "epoch": 2.1012658227848102, "grad_norm": 0.11934705062377053, "learning_rate": 5.750306806091296e-05, "loss": 0.3104, "step": 664 }, { "epoch": 2.1044303797468356, "grad_norm": 0.14337336466572148, "learning_rate": 5.742356378700841e-05, "loss": 0.3127, "step": 665 }, { "epoch": 2.107594936708861, "grad_norm": 0.14593725765396195, "learning_rate": 5.734397447034012e-05, "loss": 0.3127, "step": 666 }, { "epoch": 2.1107594936708862, "grad_norm": 0.14444951686580096, "learning_rate": 5.7264300499375985e-05, "loss": 0.3134, "step": 667 }, { "epoch": 2.1139240506329116, "grad_norm": 0.12873642596071289, "learning_rate": 5.718454226299712e-05, "loss": 0.308, "step": 668 }, { "epoch": 2.117088607594937, "grad_norm": 0.12430777180385387, "learning_rate": 5.7104700150495924e-05, "loss": 0.3137, "step": 669 }, { "epoch": 2.1202531645569622, "grad_norm": 0.14308078313515638, "learning_rate": 5.702477455157416e-05, "loss": 0.3122, "step": 670 }, { "epoch": 2.1234177215189876, "grad_norm": 0.13125076802121285, "learning_rate": 5.694476585634114e-05, "loss": 0.3083, "step": 671 }, { "epoch": 2.1265822784810124, "grad_norm": 0.099835188712379, "learning_rate": 5.686467445531167e-05, "loss": 0.3106, "step": 672 }, { "epoch": 2.1297468354430378, "grad_norm": 0.1226999761825725, "learning_rate": 5.678450073940434e-05, "loss": 0.3066, "step": 673 }, { "epoch": 2.132911392405063, "grad_norm": 0.1496368233106997, "learning_rate": 5.6704245099939433e-05, "loss": 0.3086, "step": 674 }, { "epoch": 2.1360759493670884, "grad_norm": 0.14791135918265094, "learning_rate": 5.662390792863712e-05, "loss": 0.3088, "step": 675 }, { "epoch": 2.1392405063291138, "grad_norm": 0.12802916268005818, "learning_rate": 5.6543489617615525e-05, "loss": 0.3085, "step": 676 }, { "epoch": 2.142405063291139, "grad_norm": 0.1467257550346791, "learning_rate": 5.6462990559388816e-05, "loss": 0.3115, "step": 677 }, { "epoch": 2.1455696202531644, "grad_norm": 0.14155837000093852, "learning_rate": 5.638241114686525e-05, "loss": 0.3097, "step": 678 }, { "epoch": 2.1487341772151898, "grad_norm": 0.1514416408912602, "learning_rate": 5.630175177334531e-05, "loss": 0.308, "step": 679 }, { "epoch": 2.151898734177215, "grad_norm": 0.15606278927630624, "learning_rate": 5.622101283251976e-05, "loss": 0.3087, "step": 680 }, { "epoch": 2.1550632911392404, "grad_norm": 0.15429932457148063, "learning_rate": 5.614019471846772e-05, "loss": 0.3094, "step": 681 }, { "epoch": 2.1582278481012658, "grad_norm": 0.12554805225046817, "learning_rate": 5.605929782565472e-05, "loss": 0.3133, "step": 682 }, { "epoch": 2.161392405063291, "grad_norm": 0.12982922786634285, "learning_rate": 5.597832254893087e-05, "loss": 0.3075, "step": 683 }, { "epoch": 2.1645569620253164, "grad_norm": 0.14673253928595853, "learning_rate": 5.58972692835288e-05, "loss": 0.307, "step": 684 }, { "epoch": 2.1677215189873418, "grad_norm": 0.16103133650839963, "learning_rate": 5.581613842506181e-05, "loss": 0.3133, "step": 685 }, { "epoch": 2.170886075949367, "grad_norm": 0.15366628274518923, "learning_rate": 5.573493036952194e-05, "loss": 0.3094, "step": 686 }, { "epoch": 2.1740506329113924, "grad_norm": 0.16805761535866406, "learning_rate": 5.5653645513278014e-05, "loss": 0.3098, "step": 687 }, { "epoch": 2.1772151898734178, "grad_norm": 0.17101839270138383, "learning_rate": 5.5572284253073725e-05, "loss": 0.3073, "step": 688 }, { "epoch": 2.180379746835443, "grad_norm": 0.15655184149517698, "learning_rate": 5.549084698602565e-05, "loss": 0.3084, "step": 689 }, { "epoch": 2.1835443037974684, "grad_norm": 0.16125799818325823, "learning_rate": 5.540933410962138e-05, "loss": 0.31, "step": 690 }, { "epoch": 2.1867088607594938, "grad_norm": 0.1517975482294846, "learning_rate": 5.532774602171756e-05, "loss": 0.3137, "step": 691 }, { "epoch": 2.189873417721519, "grad_norm": 0.14753655030304458, "learning_rate": 5.5246083120537884e-05, "loss": 0.3088, "step": 692 }, { "epoch": 2.1930379746835444, "grad_norm": 0.13868452723240818, "learning_rate": 5.516434580467126e-05, "loss": 0.3137, "step": 693 }, { "epoch": 2.1962025316455698, "grad_norm": 0.13188184372416153, "learning_rate": 5.508253447306978e-05, "loss": 0.3055, "step": 694 }, { "epoch": 2.199367088607595, "grad_norm": 0.11525891160799974, "learning_rate": 5.500064952504677e-05, "loss": 0.312, "step": 695 }, { "epoch": 2.2025316455696204, "grad_norm": 0.1299797394814952, "learning_rate": 5.491869136027493e-05, "loss": 0.3167, "step": 696 }, { "epoch": 2.2056962025316458, "grad_norm": 0.1449722655243908, "learning_rate": 5.48366603787843e-05, "loss": 0.3079, "step": 697 }, { "epoch": 2.208860759493671, "grad_norm": 0.15216569344993186, "learning_rate": 5.4754556980960314e-05, "loss": 0.309, "step": 698 }, { "epoch": 2.212025316455696, "grad_norm": 0.15166480271584618, "learning_rate": 5.467238156754189e-05, "loss": 0.312, "step": 699 }, { "epoch": 2.2151898734177213, "grad_norm": 0.13797851337493708, "learning_rate": 5.45901345396194e-05, "loss": 0.3091, "step": 700 }, { "epoch": 2.2183544303797467, "grad_norm": 0.17108149698482106, "learning_rate": 5.450781629863284e-05, "loss": 0.3088, "step": 701 }, { "epoch": 2.221518987341772, "grad_norm": 0.14939142671278316, "learning_rate": 5.442542724636971e-05, "loss": 0.3123, "step": 702 }, { "epoch": 2.2246835443037973, "grad_norm": 0.13756058929649415, "learning_rate": 5.434296778496317e-05, "loss": 0.3046, "step": 703 }, { "epoch": 2.2278481012658227, "grad_norm": 0.1327926973149837, "learning_rate": 5.4260438316890046e-05, "loss": 0.3144, "step": 704 }, { "epoch": 2.231012658227848, "grad_norm": 0.10141235309454794, "learning_rate": 5.417783924496885e-05, "loss": 0.3113, "step": 705 }, { "epoch": 2.2341772151898733, "grad_norm": 0.12620696166592224, "learning_rate": 5.409517097235783e-05, "loss": 0.3077, "step": 706 }, { "epoch": 2.2373417721518987, "grad_norm": 0.1571031590509732, "learning_rate": 5.401243390255298e-05, "loss": 0.3093, "step": 707 }, { "epoch": 2.240506329113924, "grad_norm": 0.1314089745712226, "learning_rate": 5.3929628439386106e-05, "loss": 0.311, "step": 708 }, { "epoch": 2.2436708860759493, "grad_norm": 0.15048516699142894, "learning_rate": 5.3846754987022816e-05, "loss": 0.312, "step": 709 }, { "epoch": 2.2468354430379747, "grad_norm": 0.18476300584231603, "learning_rate": 5.376381394996058e-05, "loss": 0.3099, "step": 710 }, { "epoch": 2.25, "grad_norm": 0.18829442331106702, "learning_rate": 5.368080573302676e-05, "loss": 0.3157, "step": 711 }, { "epoch": 2.2531645569620253, "grad_norm": 0.17604029564914442, "learning_rate": 5.359773074137657e-05, "loss": 0.3129, "step": 712 }, { "epoch": 2.2563291139240507, "grad_norm": 0.15032665151908725, "learning_rate": 5.351458938049118e-05, "loss": 0.3128, "step": 713 }, { "epoch": 2.259493670886076, "grad_norm": 0.12590105720937356, "learning_rate": 5.343138205617571e-05, "loss": 0.3086, "step": 714 }, { "epoch": 2.2626582278481013, "grad_norm": 0.12460917321935568, "learning_rate": 5.334810917455721e-05, "loss": 0.311, "step": 715 }, { "epoch": 2.2658227848101267, "grad_norm": 0.14857790908472068, "learning_rate": 5.326477114208272e-05, "loss": 0.3115, "step": 716 }, { "epoch": 2.268987341772152, "grad_norm": 0.18498996005199186, "learning_rate": 5.3181368365517286e-05, "loss": 0.311, "step": 717 }, { "epoch": 2.2721518987341773, "grad_norm": 0.1885300121143347, "learning_rate": 5.309790125194196e-05, "loss": 0.3086, "step": 718 }, { "epoch": 2.2753164556962027, "grad_norm": 0.16647725975188968, "learning_rate": 5.30143702087518e-05, "loss": 0.3124, "step": 719 }, { "epoch": 2.278481012658228, "grad_norm": 0.15414222850235362, "learning_rate": 5.293077564365394e-05, "loss": 0.3109, "step": 720 }, { "epoch": 2.2816455696202533, "grad_norm": 0.1620884831956993, "learning_rate": 5.28471179646655e-05, "loss": 0.3136, "step": 721 }, { "epoch": 2.2848101265822787, "grad_norm": 0.15351130174623856, "learning_rate": 5.2763397580111705e-05, "loss": 0.3134, "step": 722 }, { "epoch": 2.287974683544304, "grad_norm": 0.117407021534077, "learning_rate": 5.26796148986238e-05, "loss": 0.3059, "step": 723 }, { "epoch": 2.291139240506329, "grad_norm": 0.13927261507448124, "learning_rate": 5.259577032913714e-05, "loss": 0.3101, "step": 724 }, { "epoch": 2.2943037974683547, "grad_norm": 0.15434939627365005, "learning_rate": 5.251186428088909e-05, "loss": 0.3103, "step": 725 }, { "epoch": 2.2974683544303796, "grad_norm": 0.13387169345641234, "learning_rate": 5.242789716341714e-05, "loss": 0.3092, "step": 726 }, { "epoch": 2.300632911392405, "grad_norm": 0.14607956207901057, "learning_rate": 5.234386938655685e-05, "loss": 0.3071, "step": 727 }, { "epoch": 2.3037974683544302, "grad_norm": 0.17422376534901104, "learning_rate": 5.22597813604398e-05, "loss": 0.3081, "step": 728 }, { "epoch": 2.3069620253164556, "grad_norm": 0.18636888060101361, "learning_rate": 5.217563349549169e-05, "loss": 0.3078, "step": 729 }, { "epoch": 2.310126582278481, "grad_norm": 0.1678752463372025, "learning_rate": 5.209142620243029e-05, "loss": 0.3108, "step": 730 }, { "epoch": 2.3132911392405062, "grad_norm": 0.15294039126785933, "learning_rate": 5.200715989226341e-05, "loss": 0.3087, "step": 731 }, { "epoch": 2.3164556962025316, "grad_norm": 0.1337134798763612, "learning_rate": 5.192283497628692e-05, "loss": 0.3052, "step": 732 }, { "epoch": 2.319620253164557, "grad_norm": 0.11910494084626054, "learning_rate": 5.183845186608273e-05, "loss": 0.3161, "step": 733 }, { "epoch": 2.3227848101265822, "grad_norm": 0.11346441688293475, "learning_rate": 5.175401097351685e-05, "loss": 0.3126, "step": 734 }, { "epoch": 2.3259493670886076, "grad_norm": 0.1285501368657279, "learning_rate": 5.166951271073721e-05, "loss": 0.3131, "step": 735 }, { "epoch": 2.329113924050633, "grad_norm": 0.12330194801136445, "learning_rate": 5.1584957490171886e-05, "loss": 0.309, "step": 736 }, { "epoch": 2.3322784810126582, "grad_norm": 0.15924740034487567, "learning_rate": 5.1500345724526865e-05, "loss": 0.3126, "step": 737 }, { "epoch": 2.3354430379746836, "grad_norm": 0.1245619154959763, "learning_rate": 5.141567782678415e-05, "loss": 0.3121, "step": 738 }, { "epoch": 2.338607594936709, "grad_norm": 0.12286733448111128, "learning_rate": 5.133095421019974e-05, "loss": 0.3127, "step": 739 }, { "epoch": 2.3417721518987342, "grad_norm": 0.11906694994151182, "learning_rate": 5.1246175288301584e-05, "loss": 0.3108, "step": 740 }, { "epoch": 2.3449367088607596, "grad_norm": 0.11001915973997317, "learning_rate": 5.1161341474887565e-05, "loss": 0.3057, "step": 741 }, { "epoch": 2.348101265822785, "grad_norm": 0.11020195860909378, "learning_rate": 5.1076453184023474e-05, "loss": 0.3118, "step": 742 }, { "epoch": 2.3512658227848102, "grad_norm": 0.11348998489584973, "learning_rate": 5.099151083004101e-05, "loss": 0.3103, "step": 743 }, { "epoch": 2.3544303797468356, "grad_norm": 0.11137734946020322, "learning_rate": 5.090651482753579e-05, "loss": 0.3074, "step": 744 }, { "epoch": 2.357594936708861, "grad_norm": 0.12059890290659465, "learning_rate": 5.082146559136521e-05, "loss": 0.3104, "step": 745 }, { "epoch": 2.3607594936708862, "grad_norm": 0.12584527436176532, "learning_rate": 5.073636353664654e-05, "loss": 0.3083, "step": 746 }, { "epoch": 2.3639240506329116, "grad_norm": 0.12320615262063629, "learning_rate": 5.065120907875486e-05, "loss": 0.3146, "step": 747 }, { "epoch": 2.367088607594937, "grad_norm": 0.10049729170043352, "learning_rate": 5.0566002633320994e-05, "loss": 0.3103, "step": 748 }, { "epoch": 2.370253164556962, "grad_norm": 0.10541779811693974, "learning_rate": 5.0480744616229533e-05, "loss": 0.3091, "step": 749 }, { "epoch": 2.3734177215189876, "grad_norm": 0.11377856637382165, "learning_rate": 5.039543544361677e-05, "loss": 0.3115, "step": 750 }, { "epoch": 2.3765822784810124, "grad_norm": 0.12193695109780081, "learning_rate": 5.031007553186873e-05, "loss": 0.3122, "step": 751 }, { "epoch": 2.379746835443038, "grad_norm": 0.1275628027495043, "learning_rate": 5.022466529761899e-05, "loss": 0.3157, "step": 752 }, { "epoch": 2.382911392405063, "grad_norm": 0.11474256485748494, "learning_rate": 5.013920515774686e-05, "loss": 0.313, "step": 753 }, { "epoch": 2.3860759493670884, "grad_norm": 0.09849469856399706, "learning_rate": 5.0053695529375187e-05, "loss": 0.3087, "step": 754 }, { "epoch": 2.3892405063291138, "grad_norm": 0.11000798306326502, "learning_rate": 4.9968136829868325e-05, "loss": 0.3086, "step": 755 }, { "epoch": 2.392405063291139, "grad_norm": 0.10870886770320497, "learning_rate": 4.98825294768302e-05, "loss": 0.3099, "step": 756 }, { "epoch": 2.3955696202531644, "grad_norm": 0.10334251836207285, "learning_rate": 4.979687388810219e-05, "loss": 0.3083, "step": 757 }, { "epoch": 2.3987341772151898, "grad_norm": 0.10399863598801463, "learning_rate": 4.971117048176112e-05, "loss": 0.31, "step": 758 }, { "epoch": 2.401898734177215, "grad_norm": 0.10989289595664196, "learning_rate": 4.9625419676117175e-05, "loss": 0.3048, "step": 759 }, { "epoch": 2.4050632911392404, "grad_norm": 0.1288425571609994, "learning_rate": 4.95396218897119e-05, "loss": 0.3129, "step": 760 }, { "epoch": 2.4082278481012658, "grad_norm": 0.12434524932606694, "learning_rate": 4.9453777541316206e-05, "loss": 0.3089, "step": 761 }, { "epoch": 2.411392405063291, "grad_norm": 0.13280828386914872, "learning_rate": 4.936788704992817e-05, "loss": 0.3109, "step": 762 }, { "epoch": 2.4145569620253164, "grad_norm": 0.1312211887719674, "learning_rate": 4.9281950834771187e-05, "loss": 0.3075, "step": 763 }, { "epoch": 2.4177215189873418, "grad_norm": 0.11950404556805834, "learning_rate": 4.919596931529175e-05, "loss": 0.3125, "step": 764 }, { "epoch": 2.420886075949367, "grad_norm": 0.12324607700636486, "learning_rate": 4.910994291115751e-05, "loss": 0.3127, "step": 765 }, { "epoch": 2.4240506329113924, "grad_norm": 0.1320844329709189, "learning_rate": 4.9023872042255194e-05, "loss": 0.3095, "step": 766 }, { "epoch": 2.4272151898734178, "grad_norm": 0.11064868441981944, "learning_rate": 4.893775712868858e-05, "loss": 0.3084, "step": 767 }, { "epoch": 2.430379746835443, "grad_norm": 0.1073786485755268, "learning_rate": 4.8851598590776376e-05, "loss": 0.3068, "step": 768 }, { "epoch": 2.4335443037974684, "grad_norm": 0.10697886121565996, "learning_rate": 4.876539684905025e-05, "loss": 0.3114, "step": 769 }, { "epoch": 2.4367088607594938, "grad_norm": 0.10286194254070886, "learning_rate": 4.8679152324252725e-05, "loss": 0.3097, "step": 770 }, { "epoch": 2.439873417721519, "grad_norm": 0.10653938944701928, "learning_rate": 4.859286543733517e-05, "loss": 0.3116, "step": 771 }, { "epoch": 2.4430379746835444, "grad_norm": 0.10223040155655322, "learning_rate": 4.8506536609455695e-05, "loss": 0.3081, "step": 772 }, { "epoch": 2.4462025316455698, "grad_norm": 0.10982637482564878, "learning_rate": 4.842016626197712e-05, "loss": 0.3085, "step": 773 }, { "epoch": 2.449367088607595, "grad_norm": 0.10762345569394774, "learning_rate": 4.833375481646494e-05, "loss": 0.3096, "step": 774 }, { "epoch": 2.4525316455696204, "grad_norm": 0.10688148042634717, "learning_rate": 4.824730269468523e-05, "loss": 0.311, "step": 775 }, { "epoch": 2.4556962025316453, "grad_norm": 0.10593732342592756, "learning_rate": 4.8160810318602595e-05, "loss": 0.3107, "step": 776 }, { "epoch": 2.458860759493671, "grad_norm": 0.10142504784502701, "learning_rate": 4.807427811037813e-05, "loss": 0.3083, "step": 777 }, { "epoch": 2.462025316455696, "grad_norm": 0.11207252002896086, "learning_rate": 4.7987706492367355e-05, "loss": 0.3103, "step": 778 }, { "epoch": 2.4651898734177213, "grad_norm": 0.11268609278687235, "learning_rate": 4.790109588711811e-05, "loss": 0.3088, "step": 779 }, { "epoch": 2.4683544303797467, "grad_norm": 0.11626237095975188, "learning_rate": 4.7814446717368574e-05, "loss": 0.3109, "step": 780 }, { "epoch": 2.471518987341772, "grad_norm": 0.12999791502346872, "learning_rate": 4.7727759406045133e-05, "loss": 0.3076, "step": 781 }, { "epoch": 2.4746835443037973, "grad_norm": 0.14437119695188244, "learning_rate": 4.7641034376260316e-05, "loss": 0.3101, "step": 782 }, { "epoch": 2.4778481012658227, "grad_norm": 0.1297830506997779, "learning_rate": 4.75542720513108e-05, "loss": 0.3136, "step": 783 }, { "epoch": 2.481012658227848, "grad_norm": 0.10440274649654858, "learning_rate": 4.7467472854675254e-05, "loss": 0.308, "step": 784 }, { "epoch": 2.4841772151898733, "grad_norm": 0.1267288935092006, "learning_rate": 4.7380637210012346e-05, "loss": 0.3131, "step": 785 }, { "epoch": 2.4873417721518987, "grad_norm": 0.12116937092844213, "learning_rate": 4.7293765541158625e-05, "loss": 0.3067, "step": 786 }, { "epoch": 2.490506329113924, "grad_norm": 0.11712550264550504, "learning_rate": 4.720685827212646e-05, "loss": 0.314, "step": 787 }, { "epoch": 2.4936708860759493, "grad_norm": 0.11231490305991965, "learning_rate": 4.711991582710203e-05, "loss": 0.3081, "step": 788 }, { "epoch": 2.4968354430379747, "grad_norm": 0.10616756977097687, "learning_rate": 4.703293863044311e-05, "loss": 0.3067, "step": 789 }, { "epoch": 2.5, "grad_norm": 0.13564412265128084, "learning_rate": 4.694592710667723e-05, "loss": 0.3076, "step": 790 }, { "epoch": 2.5031645569620253, "grad_norm": 0.10124688810116436, "learning_rate": 4.685888168049933e-05, "loss": 0.3042, "step": 791 }, { "epoch": 2.5063291139240507, "grad_norm": 0.10941121698343692, "learning_rate": 4.677180277676992e-05, "loss": 0.3036, "step": 792 }, { "epoch": 2.509493670886076, "grad_norm": 0.1167392151414148, "learning_rate": 4.6684690820512864e-05, "loss": 0.3066, "step": 793 }, { "epoch": 2.5126582278481013, "grad_norm": 0.11740756508499711, "learning_rate": 4.659754623691337e-05, "loss": 0.3087, "step": 794 }, { "epoch": 2.5158227848101267, "grad_norm": 0.11219912790032684, "learning_rate": 4.651036945131589e-05, "loss": 0.3076, "step": 795 }, { "epoch": 2.518987341772152, "grad_norm": 0.16077855184194614, "learning_rate": 4.642316088922206e-05, "loss": 0.3138, "step": 796 }, { "epoch": 2.5221518987341773, "grad_norm": 0.12782120623946905, "learning_rate": 4.63359209762886e-05, "loss": 0.3097, "step": 797 }, { "epoch": 2.5253164556962027, "grad_norm": 0.13546906446024157, "learning_rate": 4.624865013832527e-05, "loss": 0.3048, "step": 798 }, { "epoch": 2.528481012658228, "grad_norm": 0.18066053708219248, "learning_rate": 4.616134880129275e-05, "loss": 0.3112, "step": 799 }, { "epoch": 2.5316455696202533, "grad_norm": 0.11500376798916863, "learning_rate": 4.6074017391300585e-05, "loss": 0.3098, "step": 800 }, { "epoch": 2.5348101265822782, "grad_norm": 0.15509181180355694, "learning_rate": 4.5986656334605124e-05, "loss": 0.3048, "step": 801 }, { "epoch": 2.537974683544304, "grad_norm": 0.17215208683072866, "learning_rate": 4.5899266057607405e-05, "loss": 0.3118, "step": 802 }, { "epoch": 2.541139240506329, "grad_norm": 0.13575766036622883, "learning_rate": 4.5811846986851077e-05, "loss": 0.3074, "step": 803 }, { "epoch": 2.5443037974683547, "grad_norm": 0.13764435970258934, "learning_rate": 4.572439954902036e-05, "loss": 0.3091, "step": 804 }, { "epoch": 2.5474683544303796, "grad_norm": 0.13167307915786508, "learning_rate": 4.5636924170937905e-05, "loss": 0.3097, "step": 805 }, { "epoch": 2.5506329113924053, "grad_norm": 0.13081619784726456, "learning_rate": 4.554942127956274e-05, "loss": 0.3129, "step": 806 }, { "epoch": 2.5537974683544302, "grad_norm": 0.13638938099492906, "learning_rate": 4.5461891301988165e-05, "loss": 0.3051, "step": 807 }, { "epoch": 2.5569620253164556, "grad_norm": 0.12476241900463594, "learning_rate": 4.537433466543975e-05, "loss": 0.308, "step": 808 }, { "epoch": 2.560126582278481, "grad_norm": 0.12613978380248178, "learning_rate": 4.52867517972731e-05, "loss": 0.308, "step": 809 }, { "epoch": 2.5632911392405062, "grad_norm": 0.14137862651040586, "learning_rate": 4.519914312497193e-05, "loss": 0.3111, "step": 810 }, { "epoch": 2.5664556962025316, "grad_norm": 0.12034613873180032, "learning_rate": 4.5111509076145844e-05, "loss": 0.3105, "step": 811 }, { "epoch": 2.569620253164557, "grad_norm": 0.1009963842953121, "learning_rate": 4.502385007852833e-05, "loss": 0.3055, "step": 812 }, { "epoch": 2.5727848101265822, "grad_norm": 0.12556799839898627, "learning_rate": 4.493616655997465e-05, "loss": 0.3109, "step": 813 }, { "epoch": 2.5759493670886076, "grad_norm": 0.10696425961646742, "learning_rate": 4.4848458948459763e-05, "loss": 0.3038, "step": 814 }, { "epoch": 2.579113924050633, "grad_norm": 0.11692190954916049, "learning_rate": 4.47607276720762e-05, "loss": 0.3048, "step": 815 }, { "epoch": 2.5822784810126582, "grad_norm": 0.10357498015863416, "learning_rate": 4.4672973159032005e-05, "loss": 0.3098, "step": 816 }, { "epoch": 2.5854430379746836, "grad_norm": 0.10982859913831591, "learning_rate": 4.4585195837648636e-05, "loss": 0.3093, "step": 817 }, { "epoch": 2.588607594936709, "grad_norm": 0.1188406492467599, "learning_rate": 4.4497396136358895e-05, "loss": 0.3074, "step": 818 }, { "epoch": 2.5917721518987342, "grad_norm": 0.13868536301471954, "learning_rate": 4.440957448370478e-05, "loss": 0.3057, "step": 819 }, { "epoch": 2.5949367088607596, "grad_norm": 0.13032583735414788, "learning_rate": 4.4321731308335495e-05, "loss": 0.3089, "step": 820 }, { "epoch": 2.598101265822785, "grad_norm": 0.12481379537132356, "learning_rate": 4.423386703900521e-05, "loss": 0.3125, "step": 821 }, { "epoch": 2.6012658227848102, "grad_norm": 0.14155450844531164, "learning_rate": 4.4145982104571135e-05, "loss": 0.3109, "step": 822 }, { "epoch": 2.6044303797468356, "grad_norm": 0.15191507161736642, "learning_rate": 4.405807693399128e-05, "loss": 0.3097, "step": 823 }, { "epoch": 2.607594936708861, "grad_norm": 0.13284213166094982, "learning_rate": 4.397015195632247e-05, "loss": 0.3085, "step": 824 }, { "epoch": 2.6107594936708862, "grad_norm": 0.14881280798524124, "learning_rate": 4.3882207600718176e-05, "loss": 0.313, "step": 825 }, { "epoch": 2.6139240506329116, "grad_norm": 0.1333162037427795, "learning_rate": 4.379424429642647e-05, "loss": 0.3116, "step": 826 }, { "epoch": 2.617088607594937, "grad_norm": 0.12639697844542752, "learning_rate": 4.3706262472787914e-05, "loss": 0.3135, "step": 827 }, { "epoch": 2.620253164556962, "grad_norm": 0.13019795337977755, "learning_rate": 4.361826255923343e-05, "loss": 0.3052, "step": 828 }, { "epoch": 2.6234177215189876, "grad_norm": 0.1353866450620996, "learning_rate": 4.353024498528228e-05, "loss": 0.3074, "step": 829 }, { "epoch": 2.6265822784810124, "grad_norm": 0.11314950404468142, "learning_rate": 4.344221018053988e-05, "loss": 0.3096, "step": 830 }, { "epoch": 2.629746835443038, "grad_norm": 0.1072858781612776, "learning_rate": 4.335415857469579e-05, "loss": 0.3099, "step": 831 }, { "epoch": 2.632911392405063, "grad_norm": 0.11763553871693472, "learning_rate": 4.326609059752153e-05, "loss": 0.3094, "step": 832 }, { "epoch": 2.6360759493670884, "grad_norm": 0.11153546386599392, "learning_rate": 4.3178006678868585e-05, "loss": 0.3086, "step": 833 }, { "epoch": 2.6392405063291138, "grad_norm": 0.11918046117839165, "learning_rate": 4.308990724866618e-05, "loss": 0.307, "step": 834 }, { "epoch": 2.642405063291139, "grad_norm": 0.1388023335266644, "learning_rate": 4.300179273691932e-05, "loss": 0.3106, "step": 835 }, { "epoch": 2.6455696202531644, "grad_norm": 0.12087616165984348, "learning_rate": 4.291366357370654e-05, "loss": 0.3134, "step": 836 }, { "epoch": 2.6487341772151898, "grad_norm": 0.11877587444933031, "learning_rate": 4.2825520189177985e-05, "loss": 0.3086, "step": 837 }, { "epoch": 2.651898734177215, "grad_norm": 0.14022806409981994, "learning_rate": 4.273736301355313e-05, "loss": 0.308, "step": 838 }, { "epoch": 2.6550632911392404, "grad_norm": 0.14184491403813126, "learning_rate": 4.264919247711881e-05, "loss": 0.3108, "step": 839 }, { "epoch": 2.6582278481012658, "grad_norm": 0.10525936972190719, "learning_rate": 4.256100901022704e-05, "loss": 0.3066, "step": 840 }, { "epoch": 2.661392405063291, "grad_norm": 0.1314737628532524, "learning_rate": 4.2472813043293e-05, "loss": 0.3086, "step": 841 }, { "epoch": 2.6645569620253164, "grad_norm": 0.1369321942989615, "learning_rate": 4.23846050067928e-05, "loss": 0.3117, "step": 842 }, { "epoch": 2.6677215189873418, "grad_norm": 0.10149183738447226, "learning_rate": 4.2296385331261544e-05, "loss": 0.3081, "step": 843 }, { "epoch": 2.670886075949367, "grad_norm": 0.11361715371180389, "learning_rate": 4.22081544472911e-05, "loss": 0.31, "step": 844 }, { "epoch": 2.6740506329113924, "grad_norm": 0.1360614433470445, "learning_rate": 4.2119912785528044e-05, "loss": 0.307, "step": 845 }, { "epoch": 2.6772151898734178, "grad_norm": 0.10764118225080563, "learning_rate": 4.203166077667157e-05, "loss": 0.3036, "step": 846 }, { "epoch": 2.680379746835443, "grad_norm": 0.12321423251057306, "learning_rate": 4.1943398851471376e-05, "loss": 0.3119, "step": 847 }, { "epoch": 2.6835443037974684, "grad_norm": 0.16409046958438486, "learning_rate": 4.185512744072554e-05, "loss": 0.3071, "step": 848 }, { "epoch": 2.6867088607594938, "grad_norm": 0.11925518983132842, "learning_rate": 4.176684697527847e-05, "loss": 0.3118, "step": 849 }, { "epoch": 2.689873417721519, "grad_norm": 0.11712682060606164, "learning_rate": 4.1678557886018736e-05, "loss": 0.2978, "step": 850 }, { "epoch": 2.6930379746835444, "grad_norm": 0.16847005575674953, "learning_rate": 4.159026060387704e-05, "loss": 0.3082, "step": 851 }, { "epoch": 2.6962025316455698, "grad_norm": 0.11387043135254268, "learning_rate": 4.150195555982401e-05, "loss": 0.3081, "step": 852 }, { "epoch": 2.6993670886075947, "grad_norm": 0.10433573541715951, "learning_rate": 4.141364318486823e-05, "loss": 0.3101, "step": 853 }, { "epoch": 2.7025316455696204, "grad_norm": 0.11522630804950182, "learning_rate": 4.132532391005404e-05, "loss": 0.3077, "step": 854 }, { "epoch": 2.7056962025316453, "grad_norm": 0.11497969776700434, "learning_rate": 4.1236998166459416e-05, "loss": 0.312, "step": 855 }, { "epoch": 2.708860759493671, "grad_norm": 0.09161961205693642, "learning_rate": 4.114866638519397e-05, "loss": 0.3095, "step": 856 }, { "epoch": 2.712025316455696, "grad_norm": 0.09855752510929107, "learning_rate": 4.106032899739675e-05, "loss": 0.3093, "step": 857 }, { "epoch": 2.7151898734177218, "grad_norm": 0.12228643569528587, "learning_rate": 4.0971986434234166e-05, "loss": 0.3085, "step": 858 }, { "epoch": 2.7183544303797467, "grad_norm": 0.10480518867587217, "learning_rate": 4.088363912689791e-05, "loss": 0.3075, "step": 859 }, { "epoch": 2.721518987341772, "grad_norm": 0.09180683253618907, "learning_rate": 4.0795287506602806e-05, "loss": 0.307, "step": 860 }, { "epoch": 2.7246835443037973, "grad_norm": 0.1176605082901292, "learning_rate": 4.070693200458476e-05, "loss": 0.309, "step": 861 }, { "epoch": 2.7278481012658227, "grad_norm": 0.11210439563746946, "learning_rate": 4.0618573052098575e-05, "loss": 0.3082, "step": 862 }, { "epoch": 2.731012658227848, "grad_norm": 0.1044324133047753, "learning_rate": 4.053021108041595e-05, "loss": 0.3092, "step": 863 }, { "epoch": 2.7341772151898733, "grad_norm": 0.10947662062229313, "learning_rate": 4.0441846520823275e-05, "loss": 0.3053, "step": 864 }, { "epoch": 2.7373417721518987, "grad_norm": 0.09780220894782013, "learning_rate": 4.035347980461962e-05, "loss": 0.3109, "step": 865 }, { "epoch": 2.740506329113924, "grad_norm": 0.10719308503286117, "learning_rate": 4.0265111363114505e-05, "loss": 0.3129, "step": 866 }, { "epoch": 2.7436708860759493, "grad_norm": 0.10330672917744935, "learning_rate": 4.017674162762597e-05, "loss": 0.3092, "step": 867 }, { "epoch": 2.7468354430379747, "grad_norm": 0.09409845217508706, "learning_rate": 4.00883710294783e-05, "loss": 0.3035, "step": 868 }, { "epoch": 2.75, "grad_norm": 0.0979525359073859, "learning_rate": 4e-05, "loss": 0.3046, "step": 869 }, { "epoch": 2.7531645569620253, "grad_norm": 0.11042747562522391, "learning_rate": 3.99116289705217e-05, "loss": 0.3049, "step": 870 }, { "epoch": 2.7563291139240507, "grad_norm": 0.10089690191367362, "learning_rate": 3.982325837237404e-05, "loss": 0.311, "step": 871 }, { "epoch": 2.759493670886076, "grad_norm": 0.12112191120118047, "learning_rate": 3.97348886368855e-05, "loss": 0.3083, "step": 872 }, { "epoch": 2.7626582278481013, "grad_norm": 0.11666883183626366, "learning_rate": 3.96465201953804e-05, "loss": 0.3047, "step": 873 }, { "epoch": 2.7658227848101267, "grad_norm": 0.10467066145039221, "learning_rate": 3.955815347917674e-05, "loss": 0.3076, "step": 874 }, { "epoch": 2.768987341772152, "grad_norm": 0.11642047273102721, "learning_rate": 3.946978891958408e-05, "loss": 0.3066, "step": 875 }, { "epoch": 2.7721518987341773, "grad_norm": 0.16324109134564038, "learning_rate": 3.938142694790144e-05, "loss": 0.309, "step": 876 }, { "epoch": 2.7753164556962027, "grad_norm": 0.13563079551419419, "learning_rate": 3.929306799541525e-05, "loss": 0.3082, "step": 877 }, { "epoch": 2.778481012658228, "grad_norm": 0.10322633091429102, "learning_rate": 3.9204712493397194e-05, "loss": 0.3046, "step": 878 }, { "epoch": 2.7816455696202533, "grad_norm": 0.14045354549067487, "learning_rate": 3.911636087310211e-05, "loss": 0.3111, "step": 879 }, { "epoch": 2.7848101265822782, "grad_norm": 0.10925824149149677, "learning_rate": 3.902801356576584e-05, "loss": 0.31, "step": 880 }, { "epoch": 2.787974683544304, "grad_norm": 0.11046447710341521, "learning_rate": 3.893967100260327e-05, "loss": 0.3022, "step": 881 }, { "epoch": 2.791139240506329, "grad_norm": 0.09844305319161421, "learning_rate": 3.885133361480604e-05, "loss": 0.3076, "step": 882 }, { "epoch": 2.7943037974683547, "grad_norm": 0.1044498380444223, "learning_rate": 3.87630018335406e-05, "loss": 0.3073, "step": 883 }, { "epoch": 2.7974683544303796, "grad_norm": 0.09234618334411793, "learning_rate": 3.867467608994598e-05, "loss": 0.3042, "step": 884 }, { "epoch": 2.8006329113924053, "grad_norm": 0.11555231033234425, "learning_rate": 3.8586356815131776e-05, "loss": 0.3084, "step": 885 }, { "epoch": 2.8037974683544302, "grad_norm": 0.10681559808926812, "learning_rate": 3.8498044440175996e-05, "loss": 0.3085, "step": 886 }, { "epoch": 2.8069620253164556, "grad_norm": 0.09772429730245, "learning_rate": 3.840973939612299e-05, "loss": 0.308, "step": 887 }, { "epoch": 2.810126582278481, "grad_norm": 0.11379732872950508, "learning_rate": 3.832144211398128e-05, "loss": 0.3089, "step": 888 }, { "epoch": 2.8132911392405062, "grad_norm": 0.10300686329790691, "learning_rate": 3.823315302472154e-05, "loss": 0.3102, "step": 889 }, { "epoch": 2.8164556962025316, "grad_norm": 0.10818574496407887, "learning_rate": 3.814487255927446e-05, "loss": 0.3088, "step": 890 }, { "epoch": 2.819620253164557, "grad_norm": 0.10204450259388684, "learning_rate": 3.805660114852864e-05, "loss": 0.3064, "step": 891 }, { "epoch": 2.8227848101265822, "grad_norm": 0.08742980480358419, "learning_rate": 3.796833922332844e-05, "loss": 0.3096, "step": 892 }, { "epoch": 2.8259493670886076, "grad_norm": 0.10687707295646713, "learning_rate": 3.788008721447196e-05, "loss": 0.3042, "step": 893 }, { "epoch": 2.829113924050633, "grad_norm": 0.12107053682790941, "learning_rate": 3.779184555270891e-05, "loss": 0.3119, "step": 894 }, { "epoch": 2.8322784810126582, "grad_norm": 0.09107671562689168, "learning_rate": 3.7703614668738476e-05, "loss": 0.3083, "step": 895 }, { "epoch": 2.8354430379746836, "grad_norm": 0.10018483463817114, "learning_rate": 3.761539499320721e-05, "loss": 0.3023, "step": 896 }, { "epoch": 2.838607594936709, "grad_norm": 0.09902010529119606, "learning_rate": 3.7527186956707014e-05, "loss": 0.3076, "step": 897 }, { "epoch": 2.8417721518987342, "grad_norm": 0.09168867212995821, "learning_rate": 3.7438990989772965e-05, "loss": 0.3097, "step": 898 }, { "epoch": 2.8449367088607596, "grad_norm": 0.1073570774324606, "learning_rate": 3.735080752288121e-05, "loss": 0.3078, "step": 899 }, { "epoch": 2.848101265822785, "grad_norm": 0.10027828645887199, "learning_rate": 3.726263698644688e-05, "loss": 0.3108, "step": 900 }, { "epoch": 2.8512658227848102, "grad_norm": 0.11661127254891855, "learning_rate": 3.7174479810822035e-05, "loss": 0.3029, "step": 901 }, { "epoch": 2.8544303797468356, "grad_norm": 0.0860401286243497, "learning_rate": 3.708633642629346e-05, "loss": 0.3061, "step": 902 }, { "epoch": 2.857594936708861, "grad_norm": 0.11032735009871342, "learning_rate": 3.699820726308071e-05, "loss": 0.3066, "step": 903 }, { "epoch": 2.8607594936708862, "grad_norm": 0.09469073161498463, "learning_rate": 3.6910092751333826e-05, "loss": 0.3107, "step": 904 }, { "epoch": 2.8639240506329116, "grad_norm": 0.0907871411386773, "learning_rate": 3.682199332113143e-05, "loss": 0.3031, "step": 905 }, { "epoch": 2.867088607594937, "grad_norm": 0.08114278301907149, "learning_rate": 3.673390940247847e-05, "loss": 0.3074, "step": 906 }, { "epoch": 2.870253164556962, "grad_norm": 0.10088192961978887, "learning_rate": 3.664584142530423e-05, "loss": 0.3068, "step": 907 }, { "epoch": 2.8734177215189876, "grad_norm": 0.09695281675057077, "learning_rate": 3.6557789819460135e-05, "loss": 0.3045, "step": 908 }, { "epoch": 2.8765822784810124, "grad_norm": 0.08359341782600753, "learning_rate": 3.646975501471773e-05, "loss": 0.3114, "step": 909 }, { "epoch": 2.879746835443038, "grad_norm": 0.10501478897624185, "learning_rate": 3.638173744076657e-05, "loss": 0.3076, "step": 910 }, { "epoch": 2.882911392405063, "grad_norm": 0.10848867082045752, "learning_rate": 3.62937375272121e-05, "loss": 0.3052, "step": 911 }, { "epoch": 2.8860759493670884, "grad_norm": 0.0946381803121209, "learning_rate": 3.620575570357354e-05, "loss": 0.3131, "step": 912 }, { "epoch": 2.8892405063291138, "grad_norm": 0.10164879103505776, "learning_rate": 3.611779239928183e-05, "loss": 0.3057, "step": 913 }, { "epoch": 2.892405063291139, "grad_norm": 0.09190856248688897, "learning_rate": 3.602984804367755e-05, "loss": 0.3051, "step": 914 }, { "epoch": 2.8955696202531644, "grad_norm": 0.09844798391707875, "learning_rate": 3.5941923066008734e-05, "loss": 0.3097, "step": 915 }, { "epoch": 2.8987341772151898, "grad_norm": 0.0955773970629089, "learning_rate": 3.585401789542887e-05, "loss": 0.3079, "step": 916 }, { "epoch": 2.901898734177215, "grad_norm": 0.09310369786481389, "learning_rate": 3.57661329609948e-05, "loss": 0.3032, "step": 917 }, { "epoch": 2.9050632911392404, "grad_norm": 0.09976787130658345, "learning_rate": 3.567826869166452e-05, "loss": 0.3069, "step": 918 }, { "epoch": 2.9082278481012658, "grad_norm": 0.1025318366997279, "learning_rate": 3.5590425516295224e-05, "loss": 0.3078, "step": 919 }, { "epoch": 2.911392405063291, "grad_norm": 0.10154173318243964, "learning_rate": 3.550260386364112e-05, "loss": 0.3074, "step": 920 }, { "epoch": 2.9145569620253164, "grad_norm": 0.09229918827306949, "learning_rate": 3.541480416235137e-05, "loss": 0.309, "step": 921 }, { "epoch": 2.9177215189873418, "grad_norm": 0.11015669439111893, "learning_rate": 3.532702684096802e-05, "loss": 0.3041, "step": 922 }, { "epoch": 2.920886075949367, "grad_norm": 0.10142987692807512, "learning_rate": 3.5239272327923815e-05, "loss": 0.3077, "step": 923 }, { "epoch": 2.9240506329113924, "grad_norm": 0.0976406290241572, "learning_rate": 3.515154105154025e-05, "loss": 0.3079, "step": 924 }, { "epoch": 2.9272151898734178, "grad_norm": 0.10151599077170984, "learning_rate": 3.5063833440025354e-05, "loss": 0.3115, "step": 925 }, { "epoch": 2.930379746835443, "grad_norm": 0.11428545898588319, "learning_rate": 3.4976149921471686e-05, "loss": 0.308, "step": 926 }, { "epoch": 2.9335443037974684, "grad_norm": 0.09654848300415882, "learning_rate": 3.488849092385417e-05, "loss": 0.3041, "step": 927 }, { "epoch": 2.9367088607594938, "grad_norm": 0.10543735580170445, "learning_rate": 3.4800856875028085e-05, "loss": 0.3059, "step": 928 }, { "epoch": 2.939873417721519, "grad_norm": 0.09875612716470837, "learning_rate": 3.47132482027269e-05, "loss": 0.299, "step": 929 }, { "epoch": 2.9430379746835444, "grad_norm": 0.09718956074791417, "learning_rate": 3.462566533456027e-05, "loss": 0.3082, "step": 930 }, { "epoch": 2.9462025316455698, "grad_norm": 0.10643154369243418, "learning_rate": 3.453810869801184e-05, "loss": 0.3063, "step": 931 }, { "epoch": 2.9493670886075947, "grad_norm": 0.0991243320505151, "learning_rate": 3.445057872043728e-05, "loss": 0.314, "step": 932 }, { "epoch": 2.9525316455696204, "grad_norm": 0.1263676069069203, "learning_rate": 3.43630758290621e-05, "loss": 0.3059, "step": 933 }, { "epoch": 2.9556962025316453, "grad_norm": 0.09607105502517456, "learning_rate": 3.427560045097965e-05, "loss": 0.3084, "step": 934 }, { "epoch": 2.958860759493671, "grad_norm": 0.0972009366799373, "learning_rate": 3.418815301314893e-05, "loss": 0.3046, "step": 935 }, { "epoch": 2.962025316455696, "grad_norm": 0.10231224204294453, "learning_rate": 3.410073394239261e-05, "loss": 0.3108, "step": 936 }, { "epoch": 2.9651898734177218, "grad_norm": 0.08345813699753034, "learning_rate": 3.401334366539489e-05, "loss": 0.3093, "step": 937 }, { "epoch": 2.9683544303797467, "grad_norm": 0.10855106245931795, "learning_rate": 3.3925982608699435e-05, "loss": 0.3062, "step": 938 }, { "epoch": 2.971518987341772, "grad_norm": 0.09461590871517385, "learning_rate": 3.383865119870727e-05, "loss": 0.3084, "step": 939 }, { "epoch": 2.9746835443037973, "grad_norm": 0.08581362852260419, "learning_rate": 3.3751349861674736e-05, "loss": 0.3031, "step": 940 }, { "epoch": 2.9778481012658227, "grad_norm": 0.10382744793009867, "learning_rate": 3.3664079023711404e-05, "loss": 0.3083, "step": 941 }, { "epoch": 2.981012658227848, "grad_norm": 0.09844810797148172, "learning_rate": 3.357683911077796e-05, "loss": 0.3034, "step": 942 }, { "epoch": 2.9841772151898733, "grad_norm": 0.09092203519073931, "learning_rate": 3.348963054868412e-05, "loss": 0.3035, "step": 943 }, { "epoch": 2.9873417721518987, "grad_norm": 0.10269746435346756, "learning_rate": 3.3402453763086645e-05, "loss": 0.3062, "step": 944 }, { "epoch": 2.990506329113924, "grad_norm": 0.0883744830319076, "learning_rate": 3.331530917948714e-05, "loss": 0.2996, "step": 945 }, { "epoch": 2.9936708860759493, "grad_norm": 0.10094741967088276, "learning_rate": 3.32281972232301e-05, "loss": 0.3006, "step": 946 }, { "epoch": 2.9968354430379747, "grad_norm": 0.0932066308370683, "learning_rate": 3.314111831950068e-05, "loss": 0.3, "step": 947 }, { "epoch": 3.0, "grad_norm": 0.16144810447969316, "learning_rate": 3.305407289332279e-05, "loss": 0.2856, "step": 948 }, { "epoch": 3.0031645569620253, "grad_norm": 0.5387009336746565, "learning_rate": 3.296706136955689e-05, "loss": 0.2821, "step": 949 }, { "epoch": 3.0063291139240507, "grad_norm": 0.2574909776734495, "learning_rate": 3.2880084172898e-05, "loss": 0.2836, "step": 950 }, { "epoch": 3.009493670886076, "grad_norm": 0.18167762964706774, "learning_rate": 3.279314172787355e-05, "loss": 0.2863, "step": 951 }, { "epoch": 3.0126582278481013, "grad_norm": 0.23822206926319903, "learning_rate": 3.270623445884139e-05, "loss": 0.2831, "step": 952 }, { "epoch": 3.0158227848101267, "grad_norm": 0.26414645370488277, "learning_rate": 3.261936278998767e-05, "loss": 0.284, "step": 953 }, { "epoch": 3.018987341772152, "grad_norm": 0.22510180184844622, "learning_rate": 3.253252714532475e-05, "loss": 0.2823, "step": 954 }, { "epoch": 3.0221518987341773, "grad_norm": 0.22716198544487406, "learning_rate": 3.2445727948689214e-05, "loss": 0.2845, "step": 955 }, { "epoch": 3.0253164556962027, "grad_norm": 0.2171668907724557, "learning_rate": 3.235896562373969e-05, "loss": 0.2786, "step": 956 }, { "epoch": 3.028481012658228, "grad_norm": 0.2462908300885052, "learning_rate": 3.227224059395489e-05, "loss": 0.2807, "step": 957 }, { "epoch": 3.0316455696202533, "grad_norm": 0.1881941625449683, "learning_rate": 3.2185553282631446e-05, "loss": 0.2842, "step": 958 }, { "epoch": 3.0348101265822787, "grad_norm": 0.17888150897883748, "learning_rate": 3.2098904112881895e-05, "loss": 0.2753, "step": 959 }, { "epoch": 3.037974683544304, "grad_norm": 0.19166799156393713, "learning_rate": 3.201229350763265e-05, "loss": 0.2851, "step": 960 }, { "epoch": 3.041139240506329, "grad_norm": 0.17750749856141154, "learning_rate": 3.192572188962188e-05, "loss": 0.2737, "step": 961 }, { "epoch": 3.0443037974683542, "grad_norm": 0.17180134943443942, "learning_rate": 3.1839189681397425e-05, "loss": 0.2773, "step": 962 }, { "epoch": 3.0474683544303796, "grad_norm": 0.1494843442820805, "learning_rate": 3.1752697305314784e-05, "loss": 0.2808, "step": 963 }, { "epoch": 3.050632911392405, "grad_norm": 0.16480029376230454, "learning_rate": 3.166624518353507e-05, "loss": 0.2796, "step": 964 }, { "epoch": 3.0537974683544302, "grad_norm": 0.16448607971866588, "learning_rate": 3.15798337380229e-05, "loss": 0.2779, "step": 965 }, { "epoch": 3.0569620253164556, "grad_norm": 0.1454957907914598, "learning_rate": 3.1493463390544325e-05, "loss": 0.2781, "step": 966 }, { "epoch": 3.060126582278481, "grad_norm": 0.1466734811501839, "learning_rate": 3.1407134562664836e-05, "loss": 0.2786, "step": 967 }, { "epoch": 3.0632911392405062, "grad_norm": 0.13352062974854065, "learning_rate": 3.132084767574728e-05, "loss": 0.2767, "step": 968 }, { "epoch": 3.0664556962025316, "grad_norm": 0.1339847717503807, "learning_rate": 3.123460315094977e-05, "loss": 0.2822, "step": 969 }, { "epoch": 3.069620253164557, "grad_norm": 0.14068886904845412, "learning_rate": 3.114840140922364e-05, "loss": 0.283, "step": 970 }, { "epoch": 3.0727848101265822, "grad_norm": 0.11494247541153511, "learning_rate": 3.106224287131143e-05, "loss": 0.2769, "step": 971 }, { "epoch": 3.0759493670886076, "grad_norm": 0.13879186219082848, "learning_rate": 3.09761279577448e-05, "loss": 0.2805, "step": 972 }, { "epoch": 3.079113924050633, "grad_norm": 0.10803123024070692, "learning_rate": 3.089005708884251e-05, "loss": 0.2747, "step": 973 }, { "epoch": 3.0822784810126582, "grad_norm": 0.12166408896497814, "learning_rate": 3.0804030684708265e-05, "loss": 0.2822, "step": 974 }, { "epoch": 3.0854430379746836, "grad_norm": 0.12058324933763834, "learning_rate": 3.071804916522883e-05, "loss": 0.2796, "step": 975 }, { "epoch": 3.088607594936709, "grad_norm": 0.10800309951435522, "learning_rate": 3.063211295007183e-05, "loss": 0.2749, "step": 976 }, { "epoch": 3.0917721518987342, "grad_norm": 0.11035463751257615, "learning_rate": 3.0546222458683814e-05, "loss": 0.2783, "step": 977 }, { "epoch": 3.0949367088607596, "grad_norm": 0.10762770727724025, "learning_rate": 3.0460378110288108e-05, "loss": 0.2821, "step": 978 }, { "epoch": 3.098101265822785, "grad_norm": 0.1202382922043479, "learning_rate": 3.0374580323882838e-05, "loss": 0.2791, "step": 979 }, { "epoch": 3.1012658227848102, "grad_norm": 0.11126294710387975, "learning_rate": 3.0288829518238887e-05, "loss": 0.2742, "step": 980 }, { "epoch": 3.1044303797468356, "grad_norm": 0.11131986520294344, "learning_rate": 3.020312611189782e-05, "loss": 0.2758, "step": 981 }, { "epoch": 3.107594936708861, "grad_norm": 0.10520800867597736, "learning_rate": 3.0117470523169814e-05, "loss": 0.2754, "step": 982 }, { "epoch": 3.1107594936708862, "grad_norm": 0.12999658765980993, "learning_rate": 3.003186317013169e-05, "loss": 0.2805, "step": 983 }, { "epoch": 3.1139240506329116, "grad_norm": 0.12728316229613382, "learning_rate": 2.994630447062483e-05, "loss": 0.2817, "step": 984 }, { "epoch": 3.117088607594937, "grad_norm": 0.12163034410929201, "learning_rate": 2.9860794842253155e-05, "loss": 0.2754, "step": 985 }, { "epoch": 3.1202531645569622, "grad_norm": 0.10691728642777924, "learning_rate": 2.9775334702381017e-05, "loss": 0.2774, "step": 986 }, { "epoch": 3.1234177215189876, "grad_norm": 0.10146409528013273, "learning_rate": 2.968992446813129e-05, "loss": 0.2819, "step": 987 }, { "epoch": 3.1265822784810124, "grad_norm": 0.10477264047262509, "learning_rate": 2.9604564556383237e-05, "loss": 0.2781, "step": 988 }, { "epoch": 3.1297468354430378, "grad_norm": 0.09808576128678258, "learning_rate": 2.951925538377049e-05, "loss": 0.2758, "step": 989 }, { "epoch": 3.132911392405063, "grad_norm": 0.09694863393878628, "learning_rate": 2.9433997366679023e-05, "loss": 0.2763, "step": 990 }, { "epoch": 3.1360759493670884, "grad_norm": 0.09692836888410034, "learning_rate": 2.9348790921245158e-05, "loss": 0.2751, "step": 991 }, { "epoch": 3.1392405063291138, "grad_norm": 0.08791464683982542, "learning_rate": 2.9263636463353467e-05, "loss": 0.2775, "step": 992 }, { "epoch": 3.142405063291139, "grad_norm": 0.09202249831785546, "learning_rate": 2.917853440863481e-05, "loss": 0.2798, "step": 993 }, { "epoch": 3.1455696202531644, "grad_norm": 0.08514757898945222, "learning_rate": 2.9093485172464223e-05, "loss": 0.2767, "step": 994 }, { "epoch": 3.1487341772151898, "grad_norm": 0.08458031515491976, "learning_rate": 2.900848916995899e-05, "loss": 0.2797, "step": 995 }, { "epoch": 3.151898734177215, "grad_norm": 0.08876982617582393, "learning_rate": 2.8923546815976546e-05, "loss": 0.2787, "step": 996 }, { "epoch": 3.1550632911392404, "grad_norm": 0.10449673859304769, "learning_rate": 2.8838658525112452e-05, "loss": 0.2758, "step": 997 }, { "epoch": 3.1582278481012658, "grad_norm": 0.08420353610866292, "learning_rate": 2.8753824711698422e-05, "loss": 0.2746, "step": 998 }, { "epoch": 3.161392405063291, "grad_norm": 0.09853754524549958, "learning_rate": 2.866904578980026e-05, "loss": 0.2732, "step": 999 }, { "epoch": 3.1645569620253164, "grad_norm": 0.0945663283630971, "learning_rate": 2.8584322173215863e-05, "loss": 0.2803, "step": 1000 }, { "epoch": 3.1677215189873418, "grad_norm": 0.07663613704853452, "learning_rate": 2.849965427547315e-05, "loss": 0.2758, "step": 1001 }, { "epoch": 3.170886075949367, "grad_norm": 0.09352101278453144, "learning_rate": 2.841504250982812e-05, "loss": 0.2772, "step": 1002 }, { "epoch": 3.1740506329113924, "grad_norm": 0.0943938688573129, "learning_rate": 2.8330487289262785e-05, "loss": 0.2754, "step": 1003 }, { "epoch": 3.1772151898734178, "grad_norm": 0.06773554969064777, "learning_rate": 2.8245989026483173e-05, "loss": 0.2765, "step": 1004 }, { "epoch": 3.180379746835443, "grad_norm": 0.08743436482746061, "learning_rate": 2.8161548133917277e-05, "loss": 0.2719, "step": 1005 }, { "epoch": 3.1835443037974684, "grad_norm": 0.08035282502508594, "learning_rate": 2.8077165023713094e-05, "loss": 0.2789, "step": 1006 }, { "epoch": 3.1867088607594938, "grad_norm": 0.06955419631316866, "learning_rate": 2.799284010773659e-05, "loss": 0.2758, "step": 1007 }, { "epoch": 3.189873417721519, "grad_norm": 0.08658331004890919, "learning_rate": 2.7908573797569718e-05, "loss": 0.2785, "step": 1008 }, { "epoch": 3.1930379746835444, "grad_norm": 0.0890395574474491, "learning_rate": 2.782436650450832e-05, "loss": 0.277, "step": 1009 }, { "epoch": 3.1962025316455698, "grad_norm": 0.0772630657924534, "learning_rate": 2.774021863956021e-05, "loss": 0.278, "step": 1010 }, { "epoch": 3.199367088607595, "grad_norm": 0.08803928403745377, "learning_rate": 2.7656130613443168e-05, "loss": 0.2759, "step": 1011 }, { "epoch": 3.2025316455696204, "grad_norm": 0.07934033884203305, "learning_rate": 2.757210283658287e-05, "loss": 0.2766, "step": 1012 }, { "epoch": 3.2056962025316458, "grad_norm": 0.0847598285049019, "learning_rate": 2.7488135719110922e-05, "loss": 0.2767, "step": 1013 }, { "epoch": 3.208860759493671, "grad_norm": 0.08620238832833904, "learning_rate": 2.7404229670862875e-05, "loss": 0.276, "step": 1014 }, { "epoch": 3.212025316455696, "grad_norm": 0.0788647132992197, "learning_rate": 2.7320385101376206e-05, "loss": 0.2774, "step": 1015 }, { "epoch": 3.2151898734177213, "grad_norm": 0.08196429559607066, "learning_rate": 2.7236602419888315e-05, "loss": 0.2814, "step": 1016 }, { "epoch": 3.2183544303797467, "grad_norm": 0.08371839421183083, "learning_rate": 2.7152882035334508e-05, "loss": 0.2757, "step": 1017 }, { "epoch": 3.221518987341772, "grad_norm": 0.08080674512053447, "learning_rate": 2.7069224356346074e-05, "loss": 0.28, "step": 1018 }, { "epoch": 3.2246835443037973, "grad_norm": 0.08046138572120398, "learning_rate": 2.6985629791248195e-05, "loss": 0.2788, "step": 1019 }, { "epoch": 3.2278481012658227, "grad_norm": 0.08213625320385397, "learning_rate": 2.6902098748058058e-05, "loss": 0.2809, "step": 1020 }, { "epoch": 3.231012658227848, "grad_norm": 0.0721998966190805, "learning_rate": 2.681863163448272e-05, "loss": 0.2784, "step": 1021 }, { "epoch": 3.2341772151898733, "grad_norm": 0.08291740946921153, "learning_rate": 2.673522885791729e-05, "loss": 0.2787, "step": 1022 }, { "epoch": 3.2373417721518987, "grad_norm": 0.06905044481449345, "learning_rate": 2.66518908254428e-05, "loss": 0.2742, "step": 1023 }, { "epoch": 3.240506329113924, "grad_norm": 0.08342191504038744, "learning_rate": 2.6568617943824305e-05, "loss": 0.2773, "step": 1024 }, { "epoch": 3.2436708860759493, "grad_norm": 0.07876231560502897, "learning_rate": 2.6485410619508828e-05, "loss": 0.2805, "step": 1025 }, { "epoch": 3.2468354430379747, "grad_norm": 0.07777463241717306, "learning_rate": 2.6402269258623436e-05, "loss": 0.2763, "step": 1026 }, { "epoch": 3.25, "grad_norm": 0.08031577693808312, "learning_rate": 2.6319194266973256e-05, "loss": 0.2778, "step": 1027 }, { "epoch": 3.2531645569620253, "grad_norm": 0.07630596420436556, "learning_rate": 2.6236186050039437e-05, "loss": 0.2779, "step": 1028 }, { "epoch": 3.2563291139240507, "grad_norm": 0.08360183266801059, "learning_rate": 2.61532450129772e-05, "loss": 0.2752, "step": 1029 }, { "epoch": 3.259493670886076, "grad_norm": 0.07757569405085549, "learning_rate": 2.6070371560613907e-05, "loss": 0.2793, "step": 1030 }, { "epoch": 3.2626582278481013, "grad_norm": 0.0768859132475246, "learning_rate": 2.598756609744703e-05, "loss": 0.2773, "step": 1031 }, { "epoch": 3.2658227848101267, "grad_norm": 0.079187421150355, "learning_rate": 2.5904829027642187e-05, "loss": 0.2738, "step": 1032 }, { "epoch": 3.268987341772152, "grad_norm": 0.07790900570866659, "learning_rate": 2.5822160755031158e-05, "loss": 0.273, "step": 1033 }, { "epoch": 3.2721518987341773, "grad_norm": 0.07670177883631908, "learning_rate": 2.5739561683109964e-05, "loss": 0.2743, "step": 1034 }, { "epoch": 3.2753164556962027, "grad_norm": 0.07568990316864779, "learning_rate": 2.565703221503684e-05, "loss": 0.274, "step": 1035 }, { "epoch": 3.278481012658228, "grad_norm": 0.07736791274033765, "learning_rate": 2.5574572753630317e-05, "loss": 0.2792, "step": 1036 }, { "epoch": 3.2816455696202533, "grad_norm": 0.07418147531567265, "learning_rate": 2.5492183701367177e-05, "loss": 0.2719, "step": 1037 }, { "epoch": 3.2848101265822787, "grad_norm": 0.08379870384039351, "learning_rate": 2.5409865460380604e-05, "loss": 0.2741, "step": 1038 }, { "epoch": 3.287974683544304, "grad_norm": 0.08313577923317393, "learning_rate": 2.5327618432458137e-05, "loss": 0.2792, "step": 1039 }, { "epoch": 3.291139240506329, "grad_norm": 0.07567172999614709, "learning_rate": 2.5245443019039693e-05, "loss": 0.279, "step": 1040 }, { "epoch": 3.2943037974683547, "grad_norm": 0.08269138488319251, "learning_rate": 2.5163339621215705e-05, "loss": 0.2767, "step": 1041 }, { "epoch": 3.2974683544303796, "grad_norm": 0.07853981471499345, "learning_rate": 2.5081308639725067e-05, "loss": 0.2797, "step": 1042 }, { "epoch": 3.300632911392405, "grad_norm": 0.0823609748119705, "learning_rate": 2.499935047495324e-05, "loss": 0.2823, "step": 1043 }, { "epoch": 3.3037974683544302, "grad_norm": 0.07708255199124955, "learning_rate": 2.491746552693024e-05, "loss": 0.2792, "step": 1044 }, { "epoch": 3.3069620253164556, "grad_norm": 0.07666976826492289, "learning_rate": 2.483565419532875e-05, "loss": 0.2759, "step": 1045 }, { "epoch": 3.310126582278481, "grad_norm": 0.07962567781108477, "learning_rate": 2.4753916879462116e-05, "loss": 0.2768, "step": 1046 }, { "epoch": 3.3132911392405062, "grad_norm": 0.07215241849931381, "learning_rate": 2.467225397828246e-05, "loss": 0.281, "step": 1047 }, { "epoch": 3.3164556962025316, "grad_norm": 0.0764874699173779, "learning_rate": 2.459066589037863e-05, "loss": 0.2742, "step": 1048 }, { "epoch": 3.319620253164557, "grad_norm": 0.0773829556783552, "learning_rate": 2.4509153013974364e-05, "loss": 0.282, "step": 1049 }, { "epoch": 3.3227848101265822, "grad_norm": 0.07556715157898285, "learning_rate": 2.4427715746926285e-05, "loss": 0.2756, "step": 1050 }, { "epoch": 3.3259493670886076, "grad_norm": 0.08547427370071742, "learning_rate": 2.4346354486721993e-05, "loss": 0.2772, "step": 1051 }, { "epoch": 3.329113924050633, "grad_norm": 0.07744583699207497, "learning_rate": 2.426506963047808e-05, "loss": 0.2789, "step": 1052 }, { "epoch": 3.3322784810126582, "grad_norm": 0.08403740031874835, "learning_rate": 2.41838615749382e-05, "loss": 0.279, "step": 1053 }, { "epoch": 3.3354430379746836, "grad_norm": 0.07656964432870898, "learning_rate": 2.4102730716471215e-05, "loss": 0.278, "step": 1054 }, { "epoch": 3.338607594936709, "grad_norm": 0.08246920961923437, "learning_rate": 2.4021677451069145e-05, "loss": 0.2787, "step": 1055 }, { "epoch": 3.3417721518987342, "grad_norm": 0.07629959201411766, "learning_rate": 2.3940702174345284e-05, "loss": 0.2814, "step": 1056 }, { "epoch": 3.3449367088607596, "grad_norm": 0.0786202460125717, "learning_rate": 2.385980528153229e-05, "loss": 0.2719, "step": 1057 }, { "epoch": 3.348101265822785, "grad_norm": 0.08339191359724958, "learning_rate": 2.377898716748025e-05, "loss": 0.2795, "step": 1058 }, { "epoch": 3.3512658227848102, "grad_norm": 0.08197565943370294, "learning_rate": 2.3698248226654705e-05, "loss": 0.279, "step": 1059 }, { "epoch": 3.3544303797468356, "grad_norm": 0.0732905082343803, "learning_rate": 2.3617588853134762e-05, "loss": 0.2797, "step": 1060 }, { "epoch": 3.357594936708861, "grad_norm": 0.09185672528186865, "learning_rate": 2.35370094406112e-05, "loss": 0.2761, "step": 1061 }, { "epoch": 3.3607594936708862, "grad_norm": 0.07343088903751148, "learning_rate": 2.3456510382384475e-05, "loss": 0.2799, "step": 1062 }, { "epoch": 3.3639240506329116, "grad_norm": 0.08900628271025357, "learning_rate": 2.3376092071362898e-05, "loss": 0.275, "step": 1063 }, { "epoch": 3.367088607594937, "grad_norm": 0.07987111233720275, "learning_rate": 2.3295754900060593e-05, "loss": 0.2744, "step": 1064 }, { "epoch": 3.370253164556962, "grad_norm": 0.08486662392776477, "learning_rate": 2.3215499260595665e-05, "loss": 0.2775, "step": 1065 }, { "epoch": 3.3734177215189876, "grad_norm": 0.07819918625308107, "learning_rate": 2.3135325544688332e-05, "loss": 0.2769, "step": 1066 }, { "epoch": 3.3765822784810124, "grad_norm": 0.07722149456362817, "learning_rate": 2.3055234143658894e-05, "loss": 0.2786, "step": 1067 }, { "epoch": 3.379746835443038, "grad_norm": 0.07321559874502212, "learning_rate": 2.2975225448425844e-05, "loss": 0.2761, "step": 1068 }, { "epoch": 3.382911392405063, "grad_norm": 0.0798147274934847, "learning_rate": 2.2895299849504086e-05, "loss": 0.2797, "step": 1069 }, { "epoch": 3.3860759493670884, "grad_norm": 0.07377918587737896, "learning_rate": 2.2815457737002884e-05, "loss": 0.279, "step": 1070 }, { "epoch": 3.3892405063291138, "grad_norm": 0.07890208025714728, "learning_rate": 2.2735699500624025e-05, "loss": 0.2767, "step": 1071 }, { "epoch": 3.392405063291139, "grad_norm": 0.0753779778891451, "learning_rate": 2.26560255296599e-05, "loss": 0.276, "step": 1072 }, { "epoch": 3.3955696202531644, "grad_norm": 0.07426336810006351, "learning_rate": 2.2576436212991606e-05, "loss": 0.2788, "step": 1073 }, { "epoch": 3.3987341772151898, "grad_norm": 0.07078212324963909, "learning_rate": 2.249693193908704e-05, "loss": 0.2756, "step": 1074 }, { "epoch": 3.401898734177215, "grad_norm": 0.06594479541947476, "learning_rate": 2.2417513095999088e-05, "loss": 0.2783, "step": 1075 }, { "epoch": 3.4050632911392404, "grad_norm": 0.07012037456565712, "learning_rate": 2.2338180071363543e-05, "loss": 0.2838, "step": 1076 }, { "epoch": 3.4082278481012658, "grad_norm": 0.06847696260735768, "learning_rate": 2.225893325239737e-05, "loss": 0.2816, "step": 1077 }, { "epoch": 3.411392405063291, "grad_norm": 0.06932826922792239, "learning_rate": 2.217977302589683e-05, "loss": 0.275, "step": 1078 }, { "epoch": 3.4145569620253164, "grad_norm": 0.07382614644731732, "learning_rate": 2.2100699778235465e-05, "loss": 0.2754, "step": 1079 }, { "epoch": 3.4177215189873418, "grad_norm": 0.07221192795257117, "learning_rate": 2.2021713895362304e-05, "loss": 0.2739, "step": 1080 }, { "epoch": 3.420886075949367, "grad_norm": 0.07313869976851896, "learning_rate": 2.1942815762799956e-05, "loss": 0.2792, "step": 1081 }, { "epoch": 3.4240506329113924, "grad_norm": 0.07156382171099097, "learning_rate": 2.186400576564273e-05, "loss": 0.2746, "step": 1082 }, { "epoch": 3.4272151898734178, "grad_norm": 0.06874014895523592, "learning_rate": 2.1785284288554753e-05, "loss": 0.2756, "step": 1083 }, { "epoch": 3.430379746835443, "grad_norm": 0.0709197018981126, "learning_rate": 2.1706651715768095e-05, "loss": 0.2768, "step": 1084 }, { "epoch": 3.4335443037974684, "grad_norm": 0.07532833563634928, "learning_rate": 2.162810843108088e-05, "loss": 0.279, "step": 1085 }, { "epoch": 3.4367088607594938, "grad_norm": 0.07310719921457225, "learning_rate": 2.154965481785548e-05, "loss": 0.2791, "step": 1086 }, { "epoch": 3.439873417721519, "grad_norm": 0.07266471743694179, "learning_rate": 2.1471291259016496e-05, "loss": 0.2781, "step": 1087 }, { "epoch": 3.4430379746835444, "grad_norm": 0.0855857645601623, "learning_rate": 2.139301813704905e-05, "loss": 0.2757, "step": 1088 }, { "epoch": 3.4462025316455698, "grad_norm": 0.0637994484424316, "learning_rate": 2.1314835833996846e-05, "loss": 0.2755, "step": 1089 }, { "epoch": 3.449367088607595, "grad_norm": 0.08081754323841028, "learning_rate": 2.1236744731460302e-05, "loss": 0.2738, "step": 1090 }, { "epoch": 3.4525316455696204, "grad_norm": 0.06789391809722191, "learning_rate": 2.1158745210594645e-05, "loss": 0.2782, "step": 1091 }, { "epoch": 3.4556962025316453, "grad_norm": 0.0736724687872649, "learning_rate": 2.108083765210819e-05, "loss": 0.279, "step": 1092 }, { "epoch": 3.458860759493671, "grad_norm": 0.07067448324909502, "learning_rate": 2.1003022436260334e-05, "loss": 0.2771, "step": 1093 }, { "epoch": 3.462025316455696, "grad_norm": 0.07497056174546769, "learning_rate": 2.0925299942859768e-05, "loss": 0.2767, "step": 1094 }, { "epoch": 3.4651898734177213, "grad_norm": 0.06806747395129238, "learning_rate": 2.0847670551262617e-05, "loss": 0.2732, "step": 1095 }, { "epoch": 3.4683544303797467, "grad_norm": 0.0717059533379725, "learning_rate": 2.077013464037059e-05, "loss": 0.2778, "step": 1096 }, { "epoch": 3.471518987341772, "grad_norm": 0.07654222785472878, "learning_rate": 2.06926925886291e-05, "loss": 0.2777, "step": 1097 }, { "epoch": 3.4746835443037973, "grad_norm": 0.0696466914296365, "learning_rate": 2.0615344774025513e-05, "loss": 0.2762, "step": 1098 }, { "epoch": 3.4778481012658227, "grad_norm": 0.07321821264842215, "learning_rate": 2.0538091574087118e-05, "loss": 0.2765, "step": 1099 }, { "epoch": 3.481012658227848, "grad_norm": 0.06835241857887227, "learning_rate": 2.046093336587951e-05, "loss": 0.2705, "step": 1100 }, { "epoch": 3.4841772151898733, "grad_norm": 0.07925384661267997, "learning_rate": 2.0383870526004578e-05, "loss": 0.2755, "step": 1101 }, { "epoch": 3.4873417721518987, "grad_norm": 0.06578817284198257, "learning_rate": 2.0306903430598738e-05, "loss": 0.2761, "step": 1102 }, { "epoch": 3.490506329113924, "grad_norm": 0.07166063865647027, "learning_rate": 2.0230032455331087e-05, "loss": 0.2767, "step": 1103 }, { "epoch": 3.4936708860759493, "grad_norm": 0.06853172235158524, "learning_rate": 2.0153257975401585e-05, "loss": 0.2737, "step": 1104 }, { "epoch": 3.4968354430379747, "grad_norm": 0.06746577458900789, "learning_rate": 2.0076580365539158e-05, "loss": 0.2791, "step": 1105 }, { "epoch": 3.5, "grad_norm": 0.06968289164563063, "learning_rate": 2.0000000000000012e-05, "loss": 0.2703, "step": 1106 }, { "epoch": 3.5031645569620253, "grad_norm": 0.0691901475989181, "learning_rate": 1.99235172525656e-05, "loss": 0.2803, "step": 1107 }, { "epoch": 3.5063291139240507, "grad_norm": 0.07097113690031731, "learning_rate": 1.9847132496540976e-05, "loss": 0.2737, "step": 1108 }, { "epoch": 3.509493670886076, "grad_norm": 0.06234651455567879, "learning_rate": 1.977084610475292e-05, "loss": 0.2756, "step": 1109 }, { "epoch": 3.5126582278481013, "grad_norm": 0.0726306183292495, "learning_rate": 1.9694658449548078e-05, "loss": 0.2743, "step": 1110 }, { "epoch": 3.5158227848101267, "grad_norm": 0.07223900735337287, "learning_rate": 1.961856990279113e-05, "loss": 0.2792, "step": 1111 }, { "epoch": 3.518987341772152, "grad_norm": 0.0758984920162883, "learning_rate": 1.9542580835863117e-05, "loss": 0.2749, "step": 1112 }, { "epoch": 3.5221518987341773, "grad_norm": 0.0701704077656015, "learning_rate": 1.9466691619659448e-05, "loss": 0.2807, "step": 1113 }, { "epoch": 3.5253164556962027, "grad_norm": 0.07489793658044389, "learning_rate": 1.9390902624588204e-05, "loss": 0.2764, "step": 1114 }, { "epoch": 3.528481012658228, "grad_norm": 0.06881337732543795, "learning_rate": 1.931521422056828e-05, "loss": 0.2801, "step": 1115 }, { "epoch": 3.5316455696202533, "grad_norm": 0.0731655468026194, "learning_rate": 1.923962677702761e-05, "loss": 0.2715, "step": 1116 }, { "epoch": 3.5348101265822782, "grad_norm": 0.07206488515164705, "learning_rate": 1.9164140662901328e-05, "loss": 0.2711, "step": 1117 }, { "epoch": 3.537974683544304, "grad_norm": 0.0670589546139218, "learning_rate": 1.9088756246630043e-05, "loss": 0.271, "step": 1118 }, { "epoch": 3.541139240506329, "grad_norm": 0.06996406386223057, "learning_rate": 1.9013473896157893e-05, "loss": 0.2741, "step": 1119 }, { "epoch": 3.5443037974683547, "grad_norm": 0.06711765402852654, "learning_rate": 1.8938293978930938e-05, "loss": 0.2773, "step": 1120 }, { "epoch": 3.5474683544303796, "grad_norm": 0.06584322686041742, "learning_rate": 1.8863216861895238e-05, "loss": 0.279, "step": 1121 }, { "epoch": 3.5506329113924053, "grad_norm": 0.06583127149349283, "learning_rate": 1.8788242911495027e-05, "loss": 0.2772, "step": 1122 }, { "epoch": 3.5537974683544302, "grad_norm": 0.06554409015588866, "learning_rate": 1.8713372493671113e-05, "loss": 0.2819, "step": 1123 }, { "epoch": 3.5569620253164556, "grad_norm": 0.0667673542824367, "learning_rate": 1.8638605973858884e-05, "loss": 0.2799, "step": 1124 }, { "epoch": 3.560126582278481, "grad_norm": 0.06817568232348921, "learning_rate": 1.856394371698664e-05, "loss": 0.2759, "step": 1125 }, { "epoch": 3.5632911392405062, "grad_norm": 0.06819966536886785, "learning_rate": 1.8489386087473785e-05, "loss": 0.2744, "step": 1126 }, { "epoch": 3.5664556962025316, "grad_norm": 0.06184241197626962, "learning_rate": 1.8414933449229046e-05, "loss": 0.2727, "step": 1127 }, { "epoch": 3.569620253164557, "grad_norm": 0.0692988381394404, "learning_rate": 1.834058616564867e-05, "loss": 0.2747, "step": 1128 }, { "epoch": 3.5727848101265822, "grad_norm": 0.06829509688243632, "learning_rate": 1.8266344599614757e-05, "loss": 0.2738, "step": 1129 }, { "epoch": 3.5759493670886076, "grad_norm": 0.0632096763420365, "learning_rate": 1.8192209113493307e-05, "loss": 0.2721, "step": 1130 }, { "epoch": 3.579113924050633, "grad_norm": 0.07187210058132333, "learning_rate": 1.8118180069132604e-05, "loss": 0.2757, "step": 1131 }, { "epoch": 3.5822784810126582, "grad_norm": 0.06578585756435835, "learning_rate": 1.804425782786143e-05, "loss": 0.2755, "step": 1132 }, { "epoch": 3.5854430379746836, "grad_norm": 0.07364896586678722, "learning_rate": 1.797044275048722e-05, "loss": 0.2712, "step": 1133 }, { "epoch": 3.588607594936709, "grad_norm": 0.07293256167460407, "learning_rate": 1.789673519729437e-05, "loss": 0.279, "step": 1134 }, { "epoch": 3.5917721518987342, "grad_norm": 0.06832563593623338, "learning_rate": 1.782313552804247e-05, "loss": 0.2829, "step": 1135 }, { "epoch": 3.5949367088607596, "grad_norm": 0.06664799995875718, "learning_rate": 1.7749644101964522e-05, "loss": 0.2745, "step": 1136 }, { "epoch": 3.598101265822785, "grad_norm": 0.07310769918198165, "learning_rate": 1.7676261277765223e-05, "loss": 0.2784, "step": 1137 }, { "epoch": 3.6012658227848102, "grad_norm": 0.0642410165265091, "learning_rate": 1.760298741361918e-05, "loss": 0.2719, "step": 1138 }, { "epoch": 3.6044303797468356, "grad_norm": 0.07309259138838807, "learning_rate": 1.7529822867169163e-05, "loss": 0.2828, "step": 1139 }, { "epoch": 3.607594936708861, "grad_norm": 0.06780019360953894, "learning_rate": 1.7456767995524418e-05, "loss": 0.2789, "step": 1140 }, { "epoch": 3.6107594936708862, "grad_norm": 0.06472087171136666, "learning_rate": 1.7383823155258856e-05, "loss": 0.2719, "step": 1141 }, { "epoch": 3.6139240506329116, "grad_norm": 0.0650592058797702, "learning_rate": 1.7310988702409283e-05, "loss": 0.2802, "step": 1142 }, { "epoch": 3.617088607594937, "grad_norm": 0.06499734778107542, "learning_rate": 1.7238264992473802e-05, "loss": 0.2706, "step": 1143 }, { "epoch": 3.620253164556962, "grad_norm": 0.07064221945703178, "learning_rate": 1.7165652380409946e-05, "loss": 0.2794, "step": 1144 }, { "epoch": 3.6234177215189876, "grad_norm": 0.07177582298580297, "learning_rate": 1.709315122063298e-05, "loss": 0.2757, "step": 1145 }, { "epoch": 3.6265822784810124, "grad_norm": 0.07070052370912963, "learning_rate": 1.7020761867014205e-05, "loss": 0.2776, "step": 1146 }, { "epoch": 3.629746835443038, "grad_norm": 0.06574531218522395, "learning_rate": 1.694848467287919e-05, "loss": 0.2747, "step": 1147 }, { "epoch": 3.632911392405063, "grad_norm": 0.07194339801146188, "learning_rate": 1.687631999100606e-05, "loss": 0.2786, "step": 1148 }, { "epoch": 3.6360759493670884, "grad_norm": 0.06551065553643866, "learning_rate": 1.6804268173623824e-05, "loss": 0.2733, "step": 1149 }, { "epoch": 3.6392405063291138, "grad_norm": 0.06539668779280314, "learning_rate": 1.6732329572410546e-05, "loss": 0.2744, "step": 1150 }, { "epoch": 3.642405063291139, "grad_norm": 0.07099747077401918, "learning_rate": 1.6660504538491708e-05, "loss": 0.2752, "step": 1151 }, { "epoch": 3.6455696202531644, "grad_norm": 0.06304210787096276, "learning_rate": 1.6588793422438526e-05, "loss": 0.2724, "step": 1152 }, { "epoch": 3.6487341772151898, "grad_norm": 0.07515232688223938, "learning_rate": 1.6517196574266154e-05, "loss": 0.2763, "step": 1153 }, { "epoch": 3.651898734177215, "grad_norm": 0.0674005591452988, "learning_rate": 1.644571434343202e-05, "loss": 0.2776, "step": 1154 }, { "epoch": 3.6550632911392404, "grad_norm": 0.06666815893397414, "learning_rate": 1.6374347078834114e-05, "loss": 0.2763, "step": 1155 }, { "epoch": 3.6582278481012658, "grad_norm": 0.07153142200756755, "learning_rate": 1.63030951288093e-05, "loss": 0.2853, "step": 1156 }, { "epoch": 3.661392405063291, "grad_norm": 0.06821677288369644, "learning_rate": 1.623195884113159e-05, "loss": 0.2813, "step": 1157 }, { "epoch": 3.6645569620253164, "grad_norm": 0.06566345494727253, "learning_rate": 1.6160938563010454e-05, "loss": 0.2779, "step": 1158 }, { "epoch": 3.6677215189873418, "grad_norm": 0.07315075559031987, "learning_rate": 1.609003464108914e-05, "loss": 0.2815, "step": 1159 }, { "epoch": 3.670886075949367, "grad_norm": 0.06810968300949759, "learning_rate": 1.6019247421442994e-05, "loss": 0.2766, "step": 1160 }, { "epoch": 3.6740506329113924, "grad_norm": 0.06606948872945499, "learning_rate": 1.5948577249577728e-05, "loss": 0.2772, "step": 1161 }, { "epoch": 3.6772151898734178, "grad_norm": 0.06838643031408705, "learning_rate": 1.5878024470427708e-05, "loss": 0.2677, "step": 1162 }, { "epoch": 3.680379746835443, "grad_norm": 0.06826620999273227, "learning_rate": 1.5807589428354408e-05, "loss": 0.2698, "step": 1163 }, { "epoch": 3.6835443037974684, "grad_norm": 0.06237969854424273, "learning_rate": 1.5737272467144596e-05, "loss": 0.2757, "step": 1164 }, { "epoch": 3.6867088607594938, "grad_norm": 0.06546862938725531, "learning_rate": 1.5667073930008655e-05, "loss": 0.2751, "step": 1165 }, { "epoch": 3.689873417721519, "grad_norm": 0.06493563208160155, "learning_rate": 1.5596994159579025e-05, "loss": 0.2717, "step": 1166 }, { "epoch": 3.6930379746835444, "grad_norm": 0.061378260511047535, "learning_rate": 1.5527033497908422e-05, "loss": 0.2786, "step": 1167 }, { "epoch": 3.6962025316455698, "grad_norm": 0.06831303440996282, "learning_rate": 1.5457192286468203e-05, "loss": 0.2761, "step": 1168 }, { "epoch": 3.6993670886075947, "grad_norm": 0.06272593123274746, "learning_rate": 1.5387470866146702e-05, "loss": 0.2768, "step": 1169 }, { "epoch": 3.7025316455696204, "grad_norm": 0.06386721662378814, "learning_rate": 1.531786957724756e-05, "loss": 0.2751, "step": 1170 }, { "epoch": 3.7056962025316453, "grad_norm": 0.06625681706878211, "learning_rate": 1.5248388759488064e-05, "loss": 0.2744, "step": 1171 }, { "epoch": 3.708860759493671, "grad_norm": 0.05931864609621949, "learning_rate": 1.5179028751997544e-05, "loss": 0.2729, "step": 1172 }, { "epoch": 3.712025316455696, "grad_norm": 0.07741369207326525, "learning_rate": 1.5109789893315562e-05, "loss": 0.277, "step": 1173 }, { "epoch": 3.7151898734177218, "grad_norm": 0.06520821902303114, "learning_rate": 1.5040672521390477e-05, "loss": 0.2753, "step": 1174 }, { "epoch": 3.7183544303797467, "grad_norm": 0.07106354174190231, "learning_rate": 1.4971676973577607e-05, "loss": 0.2779, "step": 1175 }, { "epoch": 3.721518987341772, "grad_norm": 0.06347409417240898, "learning_rate": 1.4902803586637688e-05, "loss": 0.2779, "step": 1176 }, { "epoch": 3.7246835443037973, "grad_norm": 0.0651477896651702, "learning_rate": 1.4834052696735195e-05, "loss": 0.2751, "step": 1177 }, { "epoch": 3.7278481012658227, "grad_norm": 0.06780109966930929, "learning_rate": 1.476542463943671e-05, "loss": 0.2748, "step": 1178 }, { "epoch": 3.731012658227848, "grad_norm": 0.06500075026047988, "learning_rate": 1.4696919749709268e-05, "loss": 0.2728, "step": 1179 }, { "epoch": 3.7341772151898733, "grad_norm": 0.06964781413100793, "learning_rate": 1.4628538361918758e-05, "loss": 0.2746, "step": 1180 }, { "epoch": 3.7373417721518987, "grad_norm": 0.06485871389583021, "learning_rate": 1.456028080982824e-05, "loss": 0.2735, "step": 1181 }, { "epoch": 3.740506329113924, "grad_norm": 0.07115606033069036, "learning_rate": 1.4492147426596353e-05, "loss": 0.2736, "step": 1182 }, { "epoch": 3.7436708860759493, "grad_norm": 0.06733545405063783, "learning_rate": 1.4424138544775703e-05, "loss": 0.275, "step": 1183 }, { "epoch": 3.7468354430379747, "grad_norm": 0.07057368007138026, "learning_rate": 1.4356254496311208e-05, "loss": 0.2779, "step": 1184 }, { "epoch": 3.75, "grad_norm": 0.06563602431093782, "learning_rate": 1.4288495612538427e-05, "loss": 0.2749, "step": 1185 }, { "epoch": 3.7531645569620253, "grad_norm": 0.06464514022314909, "learning_rate": 1.4220862224182095e-05, "loss": 0.2738, "step": 1186 }, { "epoch": 3.7563291139240507, "grad_norm": 0.06694804937866207, "learning_rate": 1.4153354661354355e-05, "loss": 0.2753, "step": 1187 }, { "epoch": 3.759493670886076, "grad_norm": 0.0654329863641071, "learning_rate": 1.4085973253553227e-05, "loss": 0.276, "step": 1188 }, { "epoch": 3.7626582278481013, "grad_norm": 0.0659012989527725, "learning_rate": 1.4018718329660979e-05, "loss": 0.2757, "step": 1189 }, { "epoch": 3.7658227848101267, "grad_norm": 0.0641544791692236, "learning_rate": 1.3951590217942514e-05, "loss": 0.2759, "step": 1190 }, { "epoch": 3.768987341772152, "grad_norm": 0.06570849033127917, "learning_rate": 1.3884589246043777e-05, "loss": 0.2768, "step": 1191 }, { "epoch": 3.7721518987341773, "grad_norm": 0.06767327746873901, "learning_rate": 1.38177157409902e-05, "loss": 0.2755, "step": 1192 }, { "epoch": 3.7753164556962027, "grad_norm": 0.0657585352245489, "learning_rate": 1.3750970029184987e-05, "loss": 0.2714, "step": 1193 }, { "epoch": 3.778481012658228, "grad_norm": 0.06621714165727026, "learning_rate": 1.3684352436407627e-05, "loss": 0.2752, "step": 1194 }, { "epoch": 3.7816455696202533, "grad_norm": 0.06247267056341821, "learning_rate": 1.3617863287812311e-05, "loss": 0.2751, "step": 1195 }, { "epoch": 3.7848101265822782, "grad_norm": 0.057920435099066477, "learning_rate": 1.3551502907926252e-05, "loss": 0.2739, "step": 1196 }, { "epoch": 3.787974683544304, "grad_norm": 0.06504260491708173, "learning_rate": 1.3485271620648183e-05, "loss": 0.2764, "step": 1197 }, { "epoch": 3.791139240506329, "grad_norm": 0.05939424801603226, "learning_rate": 1.3419169749246734e-05, "loss": 0.2699, "step": 1198 }, { "epoch": 3.7943037974683547, "grad_norm": 0.058366735653558766, "learning_rate": 1.3353197616358879e-05, "loss": 0.2761, "step": 1199 }, { "epoch": 3.7974683544303796, "grad_norm": 0.05887618983937987, "learning_rate": 1.328735554398835e-05, "loss": 0.2724, "step": 1200 }, { "epoch": 3.8006329113924053, "grad_norm": 0.06024614541443624, "learning_rate": 1.3221643853504059e-05, "loss": 0.2713, "step": 1201 }, { "epoch": 3.8037974683544302, "grad_norm": 0.05948330967804737, "learning_rate": 1.3156062865638526e-05, "loss": 0.2752, "step": 1202 }, { "epoch": 3.8069620253164556, "grad_norm": 0.05735921975597889, "learning_rate": 1.3090612900486367e-05, "loss": 0.2767, "step": 1203 }, { "epoch": 3.810126582278481, "grad_norm": 0.05928898776306137, "learning_rate": 1.3025294277502658e-05, "loss": 0.2794, "step": 1204 }, { "epoch": 3.8132911392405062, "grad_norm": 0.0598428323258277, "learning_rate": 1.2960107315501369e-05, "loss": 0.2786, "step": 1205 }, { "epoch": 3.8164556962025316, "grad_norm": 0.05746597908162328, "learning_rate": 1.2895052332653926e-05, "loss": 0.2742, "step": 1206 }, { "epoch": 3.819620253164557, "grad_norm": 0.06091210069891816, "learning_rate": 1.2830129646487533e-05, "loss": 0.2789, "step": 1207 }, { "epoch": 3.8227848101265822, "grad_norm": 0.05597733754813173, "learning_rate": 1.276533957388363e-05, "loss": 0.2733, "step": 1208 }, { "epoch": 3.8259493670886076, "grad_norm": 0.06039664469010524, "learning_rate": 1.2700682431076464e-05, "loss": 0.2775, "step": 1209 }, { "epoch": 3.829113924050633, "grad_norm": 0.06712368338300269, "learning_rate": 1.2636158533651402e-05, "loss": 0.2776, "step": 1210 }, { "epoch": 3.8322784810126582, "grad_norm": 0.058714861277827865, "learning_rate": 1.2571768196543478e-05, "loss": 0.2749, "step": 1211 }, { "epoch": 3.8354430379746836, "grad_norm": 0.06301256418635666, "learning_rate": 1.2507511734035828e-05, "loss": 0.277, "step": 1212 }, { "epoch": 3.838607594936709, "grad_norm": 0.06380924028968532, "learning_rate": 1.244338945975815e-05, "loss": 0.2723, "step": 1213 }, { "epoch": 3.8417721518987342, "grad_norm": 0.05805743255113473, "learning_rate": 1.237940168668518e-05, "loss": 0.273, "step": 1214 }, { "epoch": 3.8449367088607596, "grad_norm": 0.058958109427007216, "learning_rate": 1.2315548727135212e-05, "loss": 0.2763, "step": 1215 }, { "epoch": 3.848101265822785, "grad_norm": 0.060886097720172914, "learning_rate": 1.2251830892768441e-05, "loss": 0.2764, "step": 1216 }, { "epoch": 3.8512658227848102, "grad_norm": 0.05946238055225508, "learning_rate": 1.2188248494585615e-05, "loss": 0.2772, "step": 1217 }, { "epoch": 3.8544303797468356, "grad_norm": 0.06539983742673004, "learning_rate": 1.212480184292638e-05, "loss": 0.2774, "step": 1218 }, { "epoch": 3.857594936708861, "grad_norm": 0.06467200740001461, "learning_rate": 1.2061491247467831e-05, "loss": 0.274, "step": 1219 }, { "epoch": 3.8607594936708862, "grad_norm": 0.05803923003851224, "learning_rate": 1.1998317017222992e-05, "loss": 0.2767, "step": 1220 }, { "epoch": 3.8639240506329116, "grad_norm": 0.06275064313415872, "learning_rate": 1.1935279460539283e-05, "loss": 0.2723, "step": 1221 }, { "epoch": 3.867088607594937, "grad_norm": 0.060887323365924215, "learning_rate": 1.1872378885097037e-05, "loss": 0.277, "step": 1222 }, { "epoch": 3.870253164556962, "grad_norm": 0.0580618837953462, "learning_rate": 1.1809615597908044e-05, "loss": 0.2744, "step": 1223 }, { "epoch": 3.8734177215189876, "grad_norm": 0.05936200635782467, "learning_rate": 1.174698990531392e-05, "loss": 0.2724, "step": 1224 }, { "epoch": 3.8765822784810124, "grad_norm": 0.056746663745338904, "learning_rate": 1.1684502112984734e-05, "loss": 0.2782, "step": 1225 }, { "epoch": 3.879746835443038, "grad_norm": 0.05996759778983396, "learning_rate": 1.1622152525917504e-05, "loss": 0.2763, "step": 1226 }, { "epoch": 3.882911392405063, "grad_norm": 0.05713317277074624, "learning_rate": 1.1559941448434665e-05, "loss": 0.2746, "step": 1227 }, { "epoch": 3.8860759493670884, "grad_norm": 0.06322977086306465, "learning_rate": 1.1497869184182538e-05, "loss": 0.2694, "step": 1228 }, { "epoch": 3.8892405063291138, "grad_norm": 0.060940164945160254, "learning_rate": 1.1435936036130011e-05, "loss": 0.2725, "step": 1229 }, { "epoch": 3.892405063291139, "grad_norm": 0.05813833938621668, "learning_rate": 1.13741423065669e-05, "loss": 0.2732, "step": 1230 }, { "epoch": 3.8955696202531644, "grad_norm": 0.0649073112572373, "learning_rate": 1.1312488297102533e-05, "loss": 0.2789, "step": 1231 }, { "epoch": 3.8987341772151898, "grad_norm": 0.06071704734650878, "learning_rate": 1.12509743086643e-05, "loss": 0.2706, "step": 1232 }, { "epoch": 3.901898734177215, "grad_norm": 0.061660212404227664, "learning_rate": 1.1189600641496137e-05, "loss": 0.2761, "step": 1233 }, { "epoch": 3.9050632911392404, "grad_norm": 0.06020042083372573, "learning_rate": 1.1128367595157097e-05, "loss": 0.274, "step": 1234 }, { "epoch": 3.9082278481012658, "grad_norm": 0.06268309130769675, "learning_rate": 1.1067275468519903e-05, "loss": 0.2738, "step": 1235 }, { "epoch": 3.911392405063291, "grad_norm": 0.062158040567680664, "learning_rate": 1.1006324559769395e-05, "loss": 0.2755, "step": 1236 }, { "epoch": 3.9145569620253164, "grad_norm": 0.06077025060534421, "learning_rate": 1.0945515166401215e-05, "loss": 0.2782, "step": 1237 }, { "epoch": 3.9177215189873418, "grad_norm": 0.058451381525755894, "learning_rate": 1.0884847585220237e-05, "loss": 0.2715, "step": 1238 }, { "epoch": 3.920886075949367, "grad_norm": 0.06137785707409185, "learning_rate": 1.0824322112339179e-05, "loss": 0.2792, "step": 1239 }, { "epoch": 3.9240506329113924, "grad_norm": 0.06467772804530311, "learning_rate": 1.0763939043177136e-05, "loss": 0.2726, "step": 1240 }, { "epoch": 3.9272151898734178, "grad_norm": 0.06433872472400341, "learning_rate": 1.0703698672458147e-05, "loss": 0.275, "step": 1241 }, { "epoch": 3.930379746835443, "grad_norm": 0.056545909672719975, "learning_rate": 1.0643601294209742e-05, "loss": 0.2762, "step": 1242 }, { "epoch": 3.9335443037974684, "grad_norm": 0.05900855714014696, "learning_rate": 1.0583647201761566e-05, "loss": 0.2709, "step": 1243 }, { "epoch": 3.9367088607594938, "grad_norm": 0.06047861991013153, "learning_rate": 1.0523836687743825e-05, "loss": 0.2719, "step": 1244 }, { "epoch": 3.939873417721519, "grad_norm": 0.058895828949722354, "learning_rate": 1.0464170044085966e-05, "loss": 0.2715, "step": 1245 }, { "epoch": 3.9430379746835444, "grad_norm": 0.05544117228450666, "learning_rate": 1.0404647562015268e-05, "loss": 0.2717, "step": 1246 }, { "epoch": 3.9462025316455698, "grad_norm": 0.0578350322111006, "learning_rate": 1.0345269532055285e-05, "loss": 0.2816, "step": 1247 }, { "epoch": 3.9493670886075947, "grad_norm": 0.059815762953165125, "learning_rate": 1.028603624402455e-05, "loss": 0.2756, "step": 1248 }, { "epoch": 3.9525316455696204, "grad_norm": 0.05770344616706652, "learning_rate": 1.0226947987035163e-05, "loss": 0.2732, "step": 1249 }, { "epoch": 3.9556962025316453, "grad_norm": 0.057128916480490476, "learning_rate": 1.0168005049491283e-05, "loss": 0.2728, "step": 1250 }, { "epoch": 3.958860759493671, "grad_norm": 0.058739357595645914, "learning_rate": 1.010920771908781e-05, "loss": 0.2776, "step": 1251 }, { "epoch": 3.962025316455696, "grad_norm": 0.06056412320128406, "learning_rate": 1.005055628280894e-05, "loss": 0.2768, "step": 1252 }, { "epoch": 3.9651898734177218, "grad_norm": 0.05589655478730422, "learning_rate": 9.992051026926779e-06, "loss": 0.2736, "step": 1253 }, { "epoch": 3.9683544303797467, "grad_norm": 0.05883873883653093, "learning_rate": 9.933692236999933e-06, "loss": 0.273, "step": 1254 }, { "epoch": 3.971518987341772, "grad_norm": 0.061672558814411034, "learning_rate": 9.875480197872127e-06, "loss": 0.28, "step": 1255 }, { "epoch": 3.9746835443037973, "grad_norm": 0.05663480406301296, "learning_rate": 9.817415193670791e-06, "loss": 0.2749, "step": 1256 }, { "epoch": 3.9778481012658227, "grad_norm": 0.06399454618541717, "learning_rate": 9.759497507805737e-06, "loss": 0.275, "step": 1257 }, { "epoch": 3.981012658227848, "grad_norm": 0.05432838638669844, "learning_rate": 9.701727422967702e-06, "loss": 0.2745, "step": 1258 }, { "epoch": 3.9841772151898733, "grad_norm": 0.05971422554699879, "learning_rate": 9.644105221126958e-06, "loss": 0.2729, "step": 1259 }, { "epoch": 3.9873417721518987, "grad_norm": 0.060701428348891084, "learning_rate": 9.586631183532052e-06, "loss": 0.2742, "step": 1260 }, { "epoch": 3.990506329113924, "grad_norm": 0.05621385415115423, "learning_rate": 9.529305590708291e-06, "loss": 0.2714, "step": 1261 }, { "epoch": 3.9936708860759493, "grad_norm": 0.05721830050243183, "learning_rate": 9.472128722456473e-06, "loss": 0.2745, "step": 1262 }, { "epoch": 3.9968354430379747, "grad_norm": 0.05849056592230835, "learning_rate": 9.415100857851471e-06, "loss": 0.2728, "step": 1263 }, { "epoch": 4.0, "grad_norm": 0.22213217150648937, "learning_rate": 9.358222275240884e-06, "loss": 0.2517, "step": 1264 }, { "epoch": 4.003164556962025, "grad_norm": 0.23967621226773841, "learning_rate": 9.301493252243676e-06, "loss": 0.2521, "step": 1265 }, { "epoch": 4.006329113924051, "grad_norm": 0.08293301955023531, "learning_rate": 9.24491406574887e-06, "loss": 0.2515, "step": 1266 }, { "epoch": 4.0094936708860756, "grad_norm": 0.08912062332589615, "learning_rate": 9.18848499191407e-06, "loss": 0.247, "step": 1267 }, { "epoch": 4.012658227848101, "grad_norm": 0.10182897063104686, "learning_rate": 9.132206306164248e-06, "loss": 0.2457, "step": 1268 }, { "epoch": 4.015822784810126, "grad_norm": 0.10126667773316704, "learning_rate": 9.076078283190352e-06, "loss": 0.2497, "step": 1269 }, { "epoch": 4.018987341772152, "grad_norm": 0.10428493643499749, "learning_rate": 9.020101196947935e-06, "loss": 0.2513, "step": 1270 }, { "epoch": 4.022151898734177, "grad_norm": 0.0978710705045475, "learning_rate": 8.964275320655847e-06, "loss": 0.25, "step": 1271 }, { "epoch": 4.025316455696203, "grad_norm": 0.08769251674921594, "learning_rate": 8.908600926794907e-06, "loss": 0.2525, "step": 1272 }, { "epoch": 4.0284810126582276, "grad_norm": 0.0840535647515956, "learning_rate": 8.853078287106549e-06, "loss": 0.2483, "step": 1273 }, { "epoch": 4.031645569620253, "grad_norm": 0.08856650448842326, "learning_rate": 8.79770767259152e-06, "loss": 0.2476, "step": 1274 }, { "epoch": 4.034810126582278, "grad_norm": 0.07273267646340065, "learning_rate": 8.74248935350854e-06, "loss": 0.2486, "step": 1275 }, { "epoch": 4.037974683544304, "grad_norm": 0.0680188290797728, "learning_rate": 8.687423599372992e-06, "loss": 0.2475, "step": 1276 }, { "epoch": 4.041139240506329, "grad_norm": 0.07527885280491689, "learning_rate": 8.63251067895559e-06, "loss": 0.2499, "step": 1277 }, { "epoch": 4.044303797468355, "grad_norm": 0.0701391397264619, "learning_rate": 8.577750860281138e-06, "loss": 0.2474, "step": 1278 }, { "epoch": 4.0474683544303796, "grad_norm": 0.07409130664656045, "learning_rate": 8.523144410627067e-06, "loss": 0.2446, "step": 1279 }, { "epoch": 4.050632911392405, "grad_norm": 0.06948271450565033, "learning_rate": 8.468691596522319e-06, "loss": 0.2483, "step": 1280 }, { "epoch": 4.05379746835443, "grad_norm": 0.0661462385014995, "learning_rate": 8.414392683745913e-06, "loss": 0.2486, "step": 1281 }, { "epoch": 4.056962025316456, "grad_norm": 0.06479710366044493, "learning_rate": 8.360247937325692e-06, "loss": 0.2527, "step": 1282 }, { "epoch": 4.060126582278481, "grad_norm": 0.06954384028977689, "learning_rate": 8.306257621537033e-06, "loss": 0.2502, "step": 1283 }, { "epoch": 4.063291139240507, "grad_norm": 0.06317598203527257, "learning_rate": 8.25242199990155e-06, "loss": 0.2529, "step": 1284 }, { "epoch": 4.0664556962025316, "grad_norm": 0.0606010985077367, "learning_rate": 8.198741335185803e-06, "loss": 0.2482, "step": 1285 }, { "epoch": 4.069620253164557, "grad_norm": 0.06305553607508287, "learning_rate": 8.145215889400062e-06, "loss": 0.2465, "step": 1286 }, { "epoch": 4.072784810126582, "grad_norm": 0.06685165038835382, "learning_rate": 8.091845923796922e-06, "loss": 0.2525, "step": 1287 }, { "epoch": 4.075949367088608, "grad_norm": 0.060222200138278247, "learning_rate": 8.038631698870128e-06, "loss": 0.246, "step": 1288 }, { "epoch": 4.079113924050633, "grad_norm": 0.06488197291942595, "learning_rate": 7.9855734743533e-06, "loss": 0.2489, "step": 1289 }, { "epoch": 4.082278481012658, "grad_norm": 0.06214380537789572, "learning_rate": 7.93267150921857e-06, "loss": 0.2494, "step": 1290 }, { "epoch": 4.0854430379746836, "grad_norm": 0.05674608847410995, "learning_rate": 7.879926061675425e-06, "loss": 0.2456, "step": 1291 }, { "epoch": 4.0886075949367084, "grad_norm": 0.062132940313104665, "learning_rate": 7.82733738916941e-06, "loss": 0.2525, "step": 1292 }, { "epoch": 4.091772151898734, "grad_norm": 0.06190167184660665, "learning_rate": 7.77490574838084e-06, "loss": 0.2512, "step": 1293 }, { "epoch": 4.094936708860759, "grad_norm": 0.05693852416735176, "learning_rate": 7.722631395223597e-06, "loss": 0.2505, "step": 1294 }, { "epoch": 4.098101265822785, "grad_norm": 0.05635792234057843, "learning_rate": 7.67051458484383e-06, "loss": 0.2465, "step": 1295 }, { "epoch": 4.10126582278481, "grad_norm": 0.05934924059911266, "learning_rate": 7.61855557161876e-06, "loss": 0.2483, "step": 1296 }, { "epoch": 4.1044303797468356, "grad_norm": 0.059094388759897545, "learning_rate": 7.566754609155404e-06, "loss": 0.2459, "step": 1297 }, { "epoch": 4.1075949367088604, "grad_norm": 0.05953455367192405, "learning_rate": 7.5151119502893556e-06, "loss": 0.2485, "step": 1298 }, { "epoch": 4.110759493670886, "grad_norm": 0.057706496272310705, "learning_rate": 7.463627847083521e-06, "loss": 0.2496, "step": 1299 }, { "epoch": 4.113924050632911, "grad_norm": 0.05689283989101231, "learning_rate": 7.412302550826958e-06, "loss": 0.2489, "step": 1300 }, { "epoch": 4.117088607594937, "grad_norm": 0.05363121297978765, "learning_rate": 7.361136312033572e-06, "loss": 0.2451, "step": 1301 }, { "epoch": 4.120253164556962, "grad_norm": 0.056173243865047205, "learning_rate": 7.310129380440889e-06, "loss": 0.2489, "step": 1302 }, { "epoch": 4.1234177215189876, "grad_norm": 0.05376451912868558, "learning_rate": 7.259282005008943e-06, "loss": 0.2473, "step": 1303 }, { "epoch": 4.1265822784810124, "grad_norm": 0.05489815579937178, "learning_rate": 7.208594433918947e-06, "loss": 0.254, "step": 1304 }, { "epoch": 4.129746835443038, "grad_norm": 0.05875460534428128, "learning_rate": 7.15806691457213e-06, "loss": 0.2475, "step": 1305 }, { "epoch": 4.132911392405063, "grad_norm": 0.056390356251008064, "learning_rate": 7.107699693588528e-06, "loss": 0.2498, "step": 1306 }, { "epoch": 4.136075949367089, "grad_norm": 0.054041135449124415, "learning_rate": 7.057493016805775e-06, "loss": 0.2465, "step": 1307 }, { "epoch": 4.139240506329114, "grad_norm": 0.05783581887996252, "learning_rate": 7.007447129277882e-06, "loss": 0.2497, "step": 1308 }, { "epoch": 4.1424050632911396, "grad_norm": 0.06154332210925434, "learning_rate": 6.9575622752741275e-06, "loss": 0.2557, "step": 1309 }, { "epoch": 4.1455696202531644, "grad_norm": 0.06013708488535377, "learning_rate": 6.907838698277718e-06, "loss": 0.2501, "step": 1310 }, { "epoch": 4.14873417721519, "grad_norm": 0.05789974050122665, "learning_rate": 6.858276640984725e-06, "loss": 0.2489, "step": 1311 }, { "epoch": 4.151898734177215, "grad_norm": 0.054492455835189885, "learning_rate": 6.808876345302873e-06, "loss": 0.2461, "step": 1312 }, { "epoch": 4.155063291139241, "grad_norm": 0.05541005932356966, "learning_rate": 6.75963805235031e-06, "loss": 0.2453, "step": 1313 }, { "epoch": 4.158227848101266, "grad_norm": 0.05699686542230057, "learning_rate": 6.7105620024544795e-06, "loss": 0.2487, "step": 1314 }, { "epoch": 4.1613924050632916, "grad_norm": 0.055229180624557526, "learning_rate": 6.661648435150936e-06, "loss": 0.25, "step": 1315 }, { "epoch": 4.1645569620253164, "grad_norm": 0.055224870418707314, "learning_rate": 6.612897589182159e-06, "loss": 0.2466, "step": 1316 }, { "epoch": 4.167721518987342, "grad_norm": 0.05635776017050248, "learning_rate": 6.5643097024964145e-06, "loss": 0.2506, "step": 1317 }, { "epoch": 4.170886075949367, "grad_norm": 0.053829577686563976, "learning_rate": 6.515885012246568e-06, "loss": 0.2488, "step": 1318 }, { "epoch": 4.174050632911392, "grad_norm": 0.05770391937539876, "learning_rate": 6.467623754788937e-06, "loss": 0.2456, "step": 1319 }, { "epoch": 4.177215189873418, "grad_norm": 0.056777293259855685, "learning_rate": 6.41952616568216e-06, "loss": 0.2409, "step": 1320 }, { "epoch": 4.180379746835443, "grad_norm": 0.054089904231014764, "learning_rate": 6.3715924796860175e-06, "loss": 0.2444, "step": 1321 }, { "epoch": 4.1835443037974684, "grad_norm": 0.05641061921037799, "learning_rate": 6.32382293076026e-06, "loss": 0.2455, "step": 1322 }, { "epoch": 4.186708860759493, "grad_norm": 0.059576802197417754, "learning_rate": 6.276217752063556e-06, "loss": 0.2493, "step": 1323 }, { "epoch": 4.189873417721519, "grad_norm": 0.05297708638871528, "learning_rate": 6.2287771759522585e-06, "loss": 0.2476, "step": 1324 }, { "epoch": 4.193037974683544, "grad_norm": 0.05483646987592117, "learning_rate": 6.1815014339793315e-06, "loss": 0.2531, "step": 1325 }, { "epoch": 4.19620253164557, "grad_norm": 0.05713321367533782, "learning_rate": 6.13439075689318e-06, "loss": 0.2473, "step": 1326 }, { "epoch": 4.199367088607595, "grad_norm": 0.057672990115289494, "learning_rate": 6.087445374636569e-06, "loss": 0.2519, "step": 1327 }, { "epoch": 4.2025316455696204, "grad_norm": 0.053293127096554024, "learning_rate": 6.040665516345439e-06, "loss": 0.2496, "step": 1328 }, { "epoch": 4.205696202531645, "grad_norm": 0.06018838499803245, "learning_rate": 5.994051410347879e-06, "loss": 0.2502, "step": 1329 }, { "epoch": 4.208860759493671, "grad_norm": 0.05542409773436764, "learning_rate": 5.947603284162897e-06, "loss": 0.2472, "step": 1330 }, { "epoch": 4.212025316455696, "grad_norm": 0.05359181041441051, "learning_rate": 5.901321364499391e-06, "loss": 0.2459, "step": 1331 }, { "epoch": 4.215189873417722, "grad_norm": 0.056611930681917014, "learning_rate": 5.855205877255055e-06, "loss": 0.2482, "step": 1332 }, { "epoch": 4.218354430379747, "grad_norm": 0.05570177219385869, "learning_rate": 5.8092570475151775e-06, "loss": 0.2522, "step": 1333 }, { "epoch": 4.2215189873417724, "grad_norm": 0.05524925010021369, "learning_rate": 5.763475099551663e-06, "loss": 0.2532, "step": 1334 }, { "epoch": 4.224683544303797, "grad_norm": 0.05558821575062645, "learning_rate": 5.717860256821861e-06, "loss": 0.2458, "step": 1335 }, { "epoch": 4.227848101265823, "grad_norm": 0.0562100355979609, "learning_rate": 5.672412741967486e-06, "loss": 0.247, "step": 1336 }, { "epoch": 4.231012658227848, "grad_norm": 0.0564577953534008, "learning_rate": 5.627132776813562e-06, "loss": 0.2538, "step": 1337 }, { "epoch": 4.234177215189874, "grad_norm": 0.05633525671666877, "learning_rate": 5.582020582367303e-06, "loss": 0.2497, "step": 1338 }, { "epoch": 4.237341772151899, "grad_norm": 0.052888290210381605, "learning_rate": 5.537076378817042e-06, "loss": 0.251, "step": 1339 }, { "epoch": 4.2405063291139244, "grad_norm": 0.05812708473470336, "learning_rate": 5.492300385531213e-06, "loss": 0.2525, "step": 1340 }, { "epoch": 4.243670886075949, "grad_norm": 0.05553257364738788, "learning_rate": 5.4476928210571625e-06, "loss": 0.2513, "step": 1341 }, { "epoch": 4.246835443037975, "grad_norm": 0.05458403687207231, "learning_rate": 5.403253903120184e-06, "loss": 0.2492, "step": 1342 }, { "epoch": 4.25, "grad_norm": 0.051675958405429635, "learning_rate": 5.358983848622452e-06, "loss": 0.2523, "step": 1343 }, { "epoch": 4.253164556962025, "grad_norm": 0.05326171144501598, "learning_rate": 5.3148828736419025e-06, "loss": 0.247, "step": 1344 }, { "epoch": 4.256329113924051, "grad_norm": 0.05304927917788159, "learning_rate": 5.270951193431187e-06, "loss": 0.2496, "step": 1345 }, { "epoch": 4.2594936708860756, "grad_norm": 0.05026212379323191, "learning_rate": 5.227189022416701e-06, "loss": 0.2491, "step": 1346 }, { "epoch": 4.262658227848101, "grad_norm": 0.05910478638569799, "learning_rate": 5.183596574197447e-06, "loss": 0.2466, "step": 1347 }, { "epoch": 4.265822784810126, "grad_norm": 0.055424473527689734, "learning_rate": 5.14017406154403e-06, "loss": 0.2522, "step": 1348 }, { "epoch": 4.268987341772152, "grad_norm": 0.05201755568613037, "learning_rate": 5.096921696397621e-06, "loss": 0.2447, "step": 1349 }, { "epoch": 4.272151898734177, "grad_norm": 0.05304610418135225, "learning_rate": 5.053839689868918e-06, "loss": 0.2462, "step": 1350 }, { "epoch": 4.275316455696203, "grad_norm": 0.05682967876171426, "learning_rate": 5.010928252237106e-06, "loss": 0.2498, "step": 1351 }, { "epoch": 4.2784810126582276, "grad_norm": 0.053048197106158664, "learning_rate": 4.968187592948863e-06, "loss": 0.2493, "step": 1352 }, { "epoch": 4.281645569620253, "grad_norm": 0.052648444742393455, "learning_rate": 4.925617920617267e-06, "loss": 0.2529, "step": 1353 }, { "epoch": 4.284810126582278, "grad_norm": 0.05574380992176504, "learning_rate": 4.883219443020886e-06, "loss": 0.2467, "step": 1354 }, { "epoch": 4.287974683544304, "grad_norm": 0.05429491181422979, "learning_rate": 4.840992367102653e-06, "loss": 0.2485, "step": 1355 }, { "epoch": 4.291139240506329, "grad_norm": 0.05247223453754185, "learning_rate": 4.798936898968927e-06, "loss": 0.249, "step": 1356 }, { "epoch": 4.294303797468355, "grad_norm": 0.05346729105828968, "learning_rate": 4.757053243888465e-06, "loss": 0.244, "step": 1357 }, { "epoch": 4.2974683544303796, "grad_norm": 0.054621805790682036, "learning_rate": 4.715341606291417e-06, "loss": 0.2472, "step": 1358 }, { "epoch": 4.300632911392405, "grad_norm": 0.053950178950843045, "learning_rate": 4.67380218976833e-06, "loss": 0.2444, "step": 1359 }, { "epoch": 4.30379746835443, "grad_norm": 0.05207801435637231, "learning_rate": 4.632435197069174e-06, "loss": 0.2443, "step": 1360 }, { "epoch": 4.306962025316456, "grad_norm": 0.05290562323787758, "learning_rate": 4.591240830102308e-06, "loss": 0.2455, "step": 1361 }, { "epoch": 4.310126582278481, "grad_norm": 0.057255302271160886, "learning_rate": 4.550219289933524e-06, "loss": 0.2499, "step": 1362 }, { "epoch": 4.313291139240507, "grad_norm": 0.052153684744949344, "learning_rate": 4.509370776785091e-06, "loss": 0.2518, "step": 1363 }, { "epoch": 4.3164556962025316, "grad_norm": 0.049718939592742366, "learning_rate": 4.468695490034733e-06, "loss": 0.2451, "step": 1364 }, { "epoch": 4.319620253164557, "grad_norm": 0.05282281621112471, "learning_rate": 4.428193628214645e-06, "loss": 0.2449, "step": 1365 }, { "epoch": 4.322784810126582, "grad_norm": 0.053402960371318225, "learning_rate": 4.387865389010597e-06, "loss": 0.2467, "step": 1366 }, { "epoch": 4.325949367088608, "grad_norm": 0.05551097088153337, "learning_rate": 4.347710969260899e-06, "loss": 0.2472, "step": 1367 }, { "epoch": 4.329113924050633, "grad_norm": 0.0530497665831504, "learning_rate": 4.307730564955472e-06, "loss": 0.2517, "step": 1368 }, { "epoch": 4.332278481012658, "grad_norm": 0.052068013353431156, "learning_rate": 4.26792437123487e-06, "loss": 0.2499, "step": 1369 }, { "epoch": 4.3354430379746836, "grad_norm": 0.05391670015997912, "learning_rate": 4.228292582389366e-06, "loss": 0.245, "step": 1370 }, { "epoch": 4.3386075949367084, "grad_norm": 0.05664759732831926, "learning_rate": 4.188835391857953e-06, "loss": 0.255, "step": 1371 }, { "epoch": 4.341772151898734, "grad_norm": 0.052493664428024674, "learning_rate": 4.149552992227448e-06, "loss": 0.2475, "step": 1372 }, { "epoch": 4.344936708860759, "grad_norm": 0.051911240147889, "learning_rate": 4.110445575231507e-06, "loss": 0.2501, "step": 1373 }, { "epoch": 4.348101265822785, "grad_norm": 0.05427250528994189, "learning_rate": 4.071513331749745e-06, "loss": 0.2516, "step": 1374 }, { "epoch": 4.35126582278481, "grad_norm": 0.05525216526585525, "learning_rate": 4.0327564518067585e-06, "loss": 0.256, "step": 1375 }, { "epoch": 4.3544303797468356, "grad_norm": 0.051836557059913045, "learning_rate": 3.9941751245711736e-06, "loss": 0.248, "step": 1376 }, { "epoch": 4.3575949367088604, "grad_norm": 0.0520989842409598, "learning_rate": 3.955769538354819e-06, "loss": 0.2486, "step": 1377 }, { "epoch": 4.360759493670886, "grad_norm": 0.054470843650815795, "learning_rate": 3.917539880611712e-06, "loss": 0.2451, "step": 1378 }, { "epoch": 4.363924050632911, "grad_norm": 0.05577730609876193, "learning_rate": 3.879486337937195e-06, "loss": 0.2504, "step": 1379 }, { "epoch": 4.367088607594937, "grad_norm": 0.0526169980496934, "learning_rate": 3.841609096066998e-06, "loss": 0.2483, "step": 1380 }, { "epoch": 4.370253164556962, "grad_norm": 0.05187597656819161, "learning_rate": 3.803908339876352e-06, "loss": 0.2469, "step": 1381 }, { "epoch": 4.3734177215189876, "grad_norm": 0.052183207544949164, "learning_rate": 3.7663842533790697e-06, "loss": 0.25, "step": 1382 }, { "epoch": 4.3765822784810124, "grad_norm": 0.05318859655063578, "learning_rate": 3.72903701972668e-06, "loss": 0.2462, "step": 1383 }, { "epoch": 4.379746835443038, "grad_norm": 0.05150434264706738, "learning_rate": 3.691866821207466e-06, "loss": 0.2446, "step": 1384 }, { "epoch": 4.382911392405063, "grad_norm": 0.05560112981509338, "learning_rate": 3.654873839245654e-06, "loss": 0.2406, "step": 1385 }, { "epoch": 4.386075949367089, "grad_norm": 0.05113024874792596, "learning_rate": 3.6180582544004917e-06, "loss": 0.2502, "step": 1386 }, { "epoch": 4.389240506329114, "grad_norm": 0.05314466995561056, "learning_rate": 3.5814202463653593e-06, "loss": 0.2514, "step": 1387 }, { "epoch": 4.3924050632911396, "grad_norm": 0.054714644143190536, "learning_rate": 3.5449599939668855e-06, "loss": 0.2544, "step": 1388 }, { "epoch": 4.3955696202531644, "grad_norm": 0.05265503404683195, "learning_rate": 3.5086776751641228e-06, "loss": 0.2429, "step": 1389 }, { "epoch": 4.39873417721519, "grad_norm": 0.050627121073936764, "learning_rate": 3.472573467047626e-06, "loss": 0.254, "step": 1390 }, { "epoch": 4.401898734177215, "grad_norm": 0.05076290229618183, "learning_rate": 3.4366475458386162e-06, "loss": 0.2501, "step": 1391 }, { "epoch": 4.405063291139241, "grad_norm": 0.04991247099152352, "learning_rate": 3.4009000868881102e-06, "loss": 0.2495, "step": 1392 }, { "epoch": 4.408227848101266, "grad_norm": 0.05103327068528423, "learning_rate": 3.3653312646760637e-06, "loss": 0.2487, "step": 1393 }, { "epoch": 4.4113924050632916, "grad_norm": 0.05148395293796081, "learning_rate": 3.32994125281052e-06, "loss": 0.248, "step": 1394 }, { "epoch": 4.4145569620253164, "grad_norm": 0.051975279648073726, "learning_rate": 3.2947302240267988e-06, "loss": 0.2521, "step": 1395 }, { "epoch": 4.417721518987342, "grad_norm": 0.05067466730336665, "learning_rate": 3.2596983501865663e-06, "loss": 0.2474, "step": 1396 }, { "epoch": 4.420886075949367, "grad_norm": 0.0505380856673926, "learning_rate": 3.2248458022770966e-06, "loss": 0.2493, "step": 1397 }, { "epoch": 4.424050632911392, "grad_norm": 0.050427339230616146, "learning_rate": 3.190172750410372e-06, "loss": 0.2465, "step": 1398 }, { "epoch": 4.427215189873418, "grad_norm": 0.04968405209120483, "learning_rate": 3.155679363822266e-06, "loss": 0.2546, "step": 1399 }, { "epoch": 4.430379746835443, "grad_norm": 0.052366427235323004, "learning_rate": 3.1213658108717372e-06, "loss": 0.2531, "step": 1400 }, { "epoch": 4.4335443037974684, "grad_norm": 0.05095692744954817, "learning_rate": 3.0872322590399783e-06, "loss": 0.2444, "step": 1401 }, { "epoch": 4.436708860759493, "grad_norm": 0.049829309664648415, "learning_rate": 3.0532788749296194e-06, "loss": 0.2431, "step": 1402 }, { "epoch": 4.439873417721519, "grad_norm": 0.05143282100689702, "learning_rate": 3.019505824263926e-06, "loss": 0.2519, "step": 1403 }, { "epoch": 4.443037974683544, "grad_norm": 0.051125548173469884, "learning_rate": 2.9859132718859453e-06, "loss": 0.2476, "step": 1404 }, { "epoch": 4.44620253164557, "grad_norm": 0.05216604274219605, "learning_rate": 2.9525013817577374e-06, "loss": 0.2448, "step": 1405 }, { "epoch": 4.449367088607595, "grad_norm": 0.04908462958071414, "learning_rate": 2.9192703169595905e-06, "loss": 0.2498, "step": 1406 }, { "epoch": 4.4525316455696204, "grad_norm": 0.050488464551891335, "learning_rate": 2.8862202396891725e-06, "loss": 0.2503, "step": 1407 }, { "epoch": 4.455696202531645, "grad_norm": 0.05106964007950671, "learning_rate": 2.8533513112607703e-06, "loss": 0.2516, "step": 1408 }, { "epoch": 4.458860759493671, "grad_norm": 0.05271071042205837, "learning_rate": 2.8206636921045196e-06, "loss": 0.2457, "step": 1409 }, { "epoch": 4.462025316455696, "grad_norm": 0.05375871549423012, "learning_rate": 2.788157541765588e-06, "loss": 0.2475, "step": 1410 }, { "epoch": 4.465189873417722, "grad_norm": 0.051894946308072815, "learning_rate": 2.755833018903418e-06, "loss": 0.2532, "step": 1411 }, { "epoch": 4.468354430379747, "grad_norm": 0.04943473998999516, "learning_rate": 2.7236902812909406e-06, "loss": 0.2412, "step": 1412 }, { "epoch": 4.4715189873417724, "grad_norm": 0.04851703472064294, "learning_rate": 2.691729485813812e-06, "loss": 0.2486, "step": 1413 }, { "epoch": 4.474683544303797, "grad_norm": 0.0502162665655803, "learning_rate": 2.6599507884696473e-06, "loss": 0.2469, "step": 1414 }, { "epoch": 4.477848101265823, "grad_norm": 0.049706686952908384, "learning_rate": 2.628354344367252e-06, "loss": 0.2486, "step": 1415 }, { "epoch": 4.481012658227848, "grad_norm": 0.05209020324464903, "learning_rate": 2.596940307725877e-06, "loss": 0.2511, "step": 1416 }, { "epoch": 4.484177215189874, "grad_norm": 0.05080603463112841, "learning_rate": 2.5657088318744626e-06, "loss": 0.2494, "step": 1417 }, { "epoch": 4.487341772151899, "grad_norm": 0.05039470457712195, "learning_rate": 2.5346600692508894e-06, "loss": 0.2454, "step": 1418 }, { "epoch": 4.4905063291139244, "grad_norm": 0.05107237119798411, "learning_rate": 2.5037941714012084e-06, "loss": 0.2434, "step": 1419 }, { "epoch": 4.493670886075949, "grad_norm": 0.04827354608486462, "learning_rate": 2.473111288978953e-06, "loss": 0.2469, "step": 1420 }, { "epoch": 4.496835443037975, "grad_norm": 0.05088419503515722, "learning_rate": 2.4426115717443644e-06, "loss": 0.2427, "step": 1421 }, { "epoch": 4.5, "grad_norm": 0.04993987743923454, "learning_rate": 2.4122951685636674e-06, "loss": 0.252, "step": 1422 }, { "epoch": 4.503164556962025, "grad_norm": 0.04764789799074956, "learning_rate": 2.3821622274083556e-06, "loss": 0.2469, "step": 1423 }, { "epoch": 4.506329113924051, "grad_norm": 0.04963921370960024, "learning_rate": 2.3522128953544642e-06, "loss": 0.249, "step": 1424 }, { "epoch": 4.509493670886076, "grad_norm": 0.05060991642902815, "learning_rate": 2.3224473185818306e-06, "loss": 0.2472, "step": 1425 }, { "epoch": 4.512658227848101, "grad_norm": 0.05051757996217215, "learning_rate": 2.2928656423734363e-06, "loss": 0.2522, "step": 1426 }, { "epoch": 4.515822784810126, "grad_norm": 0.048844011037312535, "learning_rate": 2.2634680111146244e-06, "loss": 0.2449, "step": 1427 }, { "epoch": 4.518987341772152, "grad_norm": 0.049088389889994775, "learning_rate": 2.23425456829244e-06, "loss": 0.2465, "step": 1428 }, { "epoch": 4.522151898734177, "grad_norm": 0.049820879626512014, "learning_rate": 2.205225456494948e-06, "loss": 0.245, "step": 1429 }, { "epoch": 4.525316455696203, "grad_norm": 0.05046327728577161, "learning_rate": 2.176380817410486e-06, "loss": 0.2488, "step": 1430 }, { "epoch": 4.5284810126582276, "grad_norm": 0.048586804455287506, "learning_rate": 2.1477207918269993e-06, "loss": 0.2497, "step": 1431 }, { "epoch": 4.531645569620253, "grad_norm": 0.050628804488942004, "learning_rate": 2.119245519631359e-06, "loss": 0.2447, "step": 1432 }, { "epoch": 4.534810126582278, "grad_norm": 0.04930551957775985, "learning_rate": 2.090955139808668e-06, "loss": 0.2472, "step": 1433 }, { "epoch": 4.537974683544304, "grad_norm": 0.05045102829194103, "learning_rate": 2.0628497904415968e-06, "loss": 0.2462, "step": 1434 }, { "epoch": 4.541139240506329, "grad_norm": 0.050227464871817694, "learning_rate": 2.0349296087096836e-06, "loss": 0.2461, "step": 1435 }, { "epoch": 4.544303797468355, "grad_norm": 0.04698009577502787, "learning_rate": 2.007194730888693e-06, "loss": 0.2433, "step": 1436 }, { "epoch": 4.5474683544303796, "grad_norm": 0.048039534939007596, "learning_rate": 1.9796452923499386e-06, "loss": 0.2448, "step": 1437 }, { "epoch": 4.550632911392405, "grad_norm": 0.0503390231738071, "learning_rate": 1.952281427559619e-06, "loss": 0.2443, "step": 1438 }, { "epoch": 4.55379746835443, "grad_norm": 0.04965084053682607, "learning_rate": 1.925103270078159e-06, "loss": 0.2469, "step": 1439 }, { "epoch": 4.556962025316456, "grad_norm": 0.04959864408418621, "learning_rate": 1.8981109525595754e-06, "loss": 0.253, "step": 1440 }, { "epoch": 4.560126582278481, "grad_norm": 0.048273195091602335, "learning_rate": 1.8713046067508055e-06, "loss": 0.2498, "step": 1441 }, { "epoch": 4.563291139240507, "grad_norm": 0.04838697486324981, "learning_rate": 1.844684363491096e-06, "loss": 0.2484, "step": 1442 }, { "epoch": 4.5664556962025316, "grad_norm": 0.049455127038348506, "learning_rate": 1.818250352711317e-06, "loss": 0.2487, "step": 1443 }, { "epoch": 4.569620253164557, "grad_norm": 0.04866876993835142, "learning_rate": 1.792002703433382e-06, "loss": 0.2456, "step": 1444 }, { "epoch": 4.572784810126582, "grad_norm": 0.047886583998914996, "learning_rate": 1.765941543769567e-06, "loss": 0.2435, "step": 1445 }, { "epoch": 4.575949367088608, "grad_norm": 0.04844816953043045, "learning_rate": 1.7400670009219388e-06, "loss": 0.25, "step": 1446 }, { "epoch": 4.579113924050633, "grad_norm": 0.04792530005042968, "learning_rate": 1.7143792011816796e-06, "loss": 0.2487, "step": 1447 }, { "epoch": 4.582278481012658, "grad_norm": 0.04706946583434201, "learning_rate": 1.6888782699284956e-06, "loss": 0.253, "step": 1448 }, { "epoch": 4.5854430379746836, "grad_norm": 0.0476046896358049, "learning_rate": 1.6635643316300366e-06, "loss": 0.2476, "step": 1449 }, { "epoch": 4.588607594936709, "grad_norm": 0.04719983493094447, "learning_rate": 1.6384375098412243e-06, "loss": 0.2513, "step": 1450 }, { "epoch": 4.591772151898734, "grad_norm": 0.04691994055041692, "learning_rate": 1.6134979272036978e-06, "loss": 0.2468, "step": 1451 }, { "epoch": 4.594936708860759, "grad_norm": 0.047932569034586016, "learning_rate": 1.588745705445196e-06, "loss": 0.2484, "step": 1452 }, { "epoch": 4.598101265822785, "grad_norm": 0.04701705701855997, "learning_rate": 1.5641809653789675e-06, "loss": 0.2489, "step": 1453 }, { "epoch": 4.60126582278481, "grad_norm": 0.048413493084332446, "learning_rate": 1.5398038269031834e-06, "loss": 0.2473, "step": 1454 }, { "epoch": 4.6044303797468356, "grad_norm": 0.04898511811624753, "learning_rate": 1.5156144090003433e-06, "loss": 0.2508, "step": 1455 }, { "epoch": 4.6075949367088604, "grad_norm": 0.047524533168382954, "learning_rate": 1.4916128297366973e-06, "loss": 0.2453, "step": 1456 }, { "epoch": 4.610759493670886, "grad_norm": 0.049771232038191074, "learning_rate": 1.4677992062616998e-06, "loss": 0.2514, "step": 1457 }, { "epoch": 4.613924050632911, "grad_norm": 0.04749050688375791, "learning_rate": 1.4441736548073704e-06, "loss": 0.2477, "step": 1458 }, { "epoch": 4.617088607594937, "grad_norm": 0.04804629551278762, "learning_rate": 1.420736290687792e-06, "loss": 0.25, "step": 1459 }, { "epoch": 4.620253164556962, "grad_norm": 0.047487149261968856, "learning_rate": 1.3974872282985196e-06, "loss": 0.2462, "step": 1460 }, { "epoch": 4.6234177215189876, "grad_norm": 0.04996129001572348, "learning_rate": 1.3744265811160307e-06, "loss": 0.2472, "step": 1461 }, { "epoch": 4.6265822784810124, "grad_norm": 0.04882428055204096, "learning_rate": 1.3515544616971422e-06, "loss": 0.2508, "step": 1462 }, { "epoch": 4.629746835443038, "grad_norm": 0.048271841530905635, "learning_rate": 1.328870981678514e-06, "loss": 0.2456, "step": 1463 }, { "epoch": 4.632911392405063, "grad_norm": 0.04782481237452553, "learning_rate": 1.3063762517760626e-06, "loss": 0.2465, "step": 1464 }, { "epoch": 4.636075949367089, "grad_norm": 0.046430400788514244, "learning_rate": 1.2840703817844325e-06, "loss": 0.2467, "step": 1465 }, { "epoch": 4.639240506329114, "grad_norm": 0.04884383054244277, "learning_rate": 1.2619534805764544e-06, "loss": 0.2456, "step": 1466 }, { "epoch": 4.6424050632911396, "grad_norm": 0.048215026312204014, "learning_rate": 1.2400256561026347e-06, "loss": 0.2453, "step": 1467 }, { "epoch": 4.6455696202531644, "grad_norm": 0.04709051961550524, "learning_rate": 1.2182870153905958e-06, "loss": 0.2498, "step": 1468 }, { "epoch": 4.64873417721519, "grad_norm": 0.0487648556610166, "learning_rate": 1.1967376645446049e-06, "loss": 0.256, "step": 1469 }, { "epoch": 4.651898734177215, "grad_norm": 0.04626432439142902, "learning_rate": 1.1753777087449759e-06, "loss": 0.2458, "step": 1470 }, { "epoch": 4.655063291139241, "grad_norm": 0.04590102632666966, "learning_rate": 1.1542072522476455e-06, "loss": 0.249, "step": 1471 }, { "epoch": 4.658227848101266, "grad_norm": 0.04694823955307095, "learning_rate": 1.1332263983835978e-06, "loss": 0.2502, "step": 1472 }, { "epoch": 4.661392405063291, "grad_norm": 0.04715065642253195, "learning_rate": 1.1124352495584012e-06, "loss": 0.2513, "step": 1473 }, { "epoch": 4.6645569620253164, "grad_norm": 0.04720689937356132, "learning_rate": 1.0918339072516759e-06, "loss": 0.25, "step": 1474 }, { "epoch": 4.667721518987342, "grad_norm": 0.047762695729748235, "learning_rate": 1.0714224720166188e-06, "loss": 0.2491, "step": 1475 }, { "epoch": 4.670886075949367, "grad_norm": 0.04747323217893107, "learning_rate": 1.0512010434795194e-06, "loss": 0.2486, "step": 1476 }, { "epoch": 4.674050632911392, "grad_norm": 0.047836421083898746, "learning_rate": 1.0311697203392446e-06, "loss": 0.2461, "step": 1477 }, { "epoch": 4.677215189873418, "grad_norm": 0.04740600350569832, "learning_rate": 1.0113286003667944e-06, "loss": 0.2502, "step": 1478 }, { "epoch": 4.680379746835443, "grad_norm": 0.04666089435140985, "learning_rate": 9.91677780404783e-07, "loss": 0.2484, "step": 1479 }, { "epoch": 4.6835443037974684, "grad_norm": 0.04660495021313494, "learning_rate": 9.722173563670156e-07, "loss": 0.2469, "step": 1480 }, { "epoch": 4.686708860759493, "grad_norm": 0.045969022166476144, "learning_rate": 9.529474232379709e-07, "loss": 0.2539, "step": 1481 }, { "epoch": 4.689873417721519, "grad_norm": 0.04730059990666271, "learning_rate": 9.338680750723595e-07, "loss": 0.2459, "step": 1482 }, { "epoch": 4.693037974683544, "grad_norm": 0.046327932448262804, "learning_rate": 9.149794049946803e-07, "loss": 0.2482, "step": 1483 }, { "epoch": 4.69620253164557, "grad_norm": 0.04786288117554046, "learning_rate": 8.962815051987373e-07, "loss": 0.2479, "step": 1484 }, { "epoch": 4.699367088607595, "grad_norm": 0.0459658969663694, "learning_rate": 8.777744669472122e-07, "loss": 0.246, "step": 1485 }, { "epoch": 4.7025316455696204, "grad_norm": 0.047169525529320966, "learning_rate": 8.594583805712031e-07, "loss": 0.2467, "step": 1486 }, { "epoch": 4.705696202531645, "grad_norm": 0.04745719571628611, "learning_rate": 8.413333354697939e-07, "loss": 0.2461, "step": 1487 }, { "epoch": 4.708860759493671, "grad_norm": 0.04684708236037839, "learning_rate": 8.233994201096007e-07, "loss": 0.2454, "step": 1488 }, { "epoch": 4.712025316455696, "grad_norm": 0.046884594850214914, "learning_rate": 8.056567220243816e-07, "loss": 0.2508, "step": 1489 }, { "epoch": 4.715189873417722, "grad_norm": 0.04757779339015251, "learning_rate": 7.881053278145567e-07, "loss": 0.2472, "step": 1490 }, { "epoch": 4.718354430379747, "grad_norm": 0.04531547182760569, "learning_rate": 7.707453231468131e-07, "loss": 0.2496, "step": 1491 }, { "epoch": 4.7215189873417724, "grad_norm": 0.047010812903118634, "learning_rate": 7.535767927536963e-07, "loss": 0.2502, "step": 1492 }, { "epoch": 4.724683544303797, "grad_norm": 0.05065050794793943, "learning_rate": 7.365998204331748e-07, "loss": 0.2472, "step": 1493 }, { "epoch": 4.727848101265823, "grad_norm": 0.04626347119151354, "learning_rate": 7.198144890482406e-07, "loss": 0.2466, "step": 1494 }, { "epoch": 4.731012658227848, "grad_norm": 0.04765702920881043, "learning_rate": 7.03220880526505e-07, "loss": 0.2439, "step": 1495 }, { "epoch": 4.734177215189874, "grad_norm": 0.046494654358029144, "learning_rate": 6.868190758597948e-07, "loss": 0.2404, "step": 1496 }, { "epoch": 4.737341772151899, "grad_norm": 0.04746833250184551, "learning_rate": 6.706091551037741e-07, "loss": 0.2465, "step": 1497 }, { "epoch": 4.740506329113924, "grad_norm": 0.04885756523686596, "learning_rate": 6.545911973775232e-07, "loss": 0.2416, "step": 1498 }, { "epoch": 4.743670886075949, "grad_norm": 0.046551214706603054, "learning_rate": 6.387652808631739e-07, "loss": 0.247, "step": 1499 }, { "epoch": 4.746835443037975, "grad_norm": 0.04723139209148858, "learning_rate": 6.231314828055323e-07, "loss": 0.2463, "step": 1500 }, { "epoch": 4.75, "grad_norm": 0.045953934817332766, "learning_rate": 6.076898795116792e-07, "loss": 0.2481, "step": 1501 }, { "epoch": 4.753164556962025, "grad_norm": 0.046592353673095756, "learning_rate": 5.924405463506189e-07, "loss": 0.2507, "step": 1502 }, { "epoch": 4.756329113924051, "grad_norm": 0.04701403771643721, "learning_rate": 5.773835577529019e-07, "loss": 0.2475, "step": 1503 }, { "epoch": 4.759493670886076, "grad_norm": 0.048726781033032955, "learning_rate": 5.625189872102654e-07, "loss": 0.2463, "step": 1504 }, { "epoch": 4.762658227848101, "grad_norm": 0.04763281629333714, "learning_rate": 5.478469072752602e-07, "loss": 0.2488, "step": 1505 }, { "epoch": 4.765822784810126, "grad_norm": 0.046818151867295564, "learning_rate": 5.333673895609259e-07, "loss": 0.2453, "step": 1506 }, { "epoch": 4.768987341772152, "grad_norm": 0.04787712415505692, "learning_rate": 5.190805047404191e-07, "loss": 0.2435, "step": 1507 }, { "epoch": 4.772151898734177, "grad_norm": 0.04780862693446796, "learning_rate": 5.049863225466656e-07, "loss": 0.2452, "step": 1508 }, { "epoch": 4.775316455696203, "grad_norm": 0.04746417766700173, "learning_rate": 4.910849117720329e-07, "loss": 0.2521, "step": 1509 }, { "epoch": 4.7784810126582276, "grad_norm": 0.05218769466514206, "learning_rate": 4.77376340267992e-07, "loss": 0.2465, "step": 1510 }, { "epoch": 4.781645569620253, "grad_norm": 0.04553507174792249, "learning_rate": 4.6386067494477603e-07, "loss": 0.2456, "step": 1511 }, { "epoch": 4.784810126582278, "grad_norm": 0.04684569062238574, "learning_rate": 4.5053798177107754e-07, "loss": 0.2459, "step": 1512 }, { "epoch": 4.787974683544304, "grad_norm": 0.0477368864593167, "learning_rate": 4.37408325773685e-07, "loss": 0.248, "step": 1513 }, { "epoch": 4.791139240506329, "grad_norm": 0.04687997719260073, "learning_rate": 4.2447177103721593e-07, "loss": 0.248, "step": 1514 }, { "epoch": 4.794303797468355, "grad_norm": 0.04579662170110315, "learning_rate": 4.117283807037664e-07, "loss": 0.2502, "step": 1515 }, { "epoch": 4.7974683544303796, "grad_norm": 0.04530755812667278, "learning_rate": 3.991782169726177e-07, "loss": 0.2446, "step": 1516 }, { "epoch": 4.800632911392405, "grad_norm": 0.046718757558508295, "learning_rate": 3.8682134109992555e-07, "loss": 0.248, "step": 1517 }, { "epoch": 4.80379746835443, "grad_norm": 0.04590183760189332, "learning_rate": 3.7465781339843133e-07, "loss": 0.247, "step": 1518 }, { "epoch": 4.806962025316456, "grad_norm": 0.04589185209640437, "learning_rate": 3.6268769323716035e-07, "loss": 0.248, "step": 1519 }, { "epoch": 4.810126582278481, "grad_norm": 0.04662181242483435, "learning_rate": 3.509110390411419e-07, "loss": 0.2539, "step": 1520 }, { "epoch": 4.813291139240507, "grad_norm": 0.047209326950502506, "learning_rate": 3.393279082911027e-07, "loss": 0.2512, "step": 1521 }, { "epoch": 4.8164556962025316, "grad_norm": 0.04522266730000354, "learning_rate": 3.279383575232009e-07, "loss": 0.2438, "step": 1522 }, { "epoch": 4.819620253164557, "grad_norm": 0.04708218662830008, "learning_rate": 3.1674244232876793e-07, "loss": 0.2478, "step": 1523 }, { "epoch": 4.822784810126582, "grad_norm": 0.04625509166727182, "learning_rate": 3.057402173539981e-07, "loss": 0.2504, "step": 1524 }, { "epoch": 4.825949367088608, "grad_norm": 0.046157693076796145, "learning_rate": 2.949317362997039e-07, "loss": 0.2464, "step": 1525 }, { "epoch": 4.829113924050633, "grad_norm": 0.046628250401203, "learning_rate": 2.843170519210636e-07, "loss": 0.2463, "step": 1526 }, { "epoch": 4.832278481012658, "grad_norm": 0.04551053260166137, "learning_rate": 2.7389621602734505e-07, "loss": 0.2458, "step": 1527 }, { "epoch": 4.8354430379746836, "grad_norm": 0.04672514123088173, "learning_rate": 2.6366927948165757e-07, "loss": 0.2478, "step": 1528 }, { "epoch": 4.838607594936709, "grad_norm": 0.0454987735398336, "learning_rate": 2.536362922007163e-07, "loss": 0.2493, "step": 1529 }, { "epoch": 4.841772151898734, "grad_norm": 0.04570663755630062, "learning_rate": 2.437973031545715e-07, "loss": 0.2502, "step": 1530 }, { "epoch": 4.844936708860759, "grad_norm": 0.04650588516828273, "learning_rate": 2.3415236036640422e-07, "loss": 0.2463, "step": 1531 }, { "epoch": 4.848101265822785, "grad_norm": 0.046278526195044044, "learning_rate": 2.247015109122641e-07, "loss": 0.2476, "step": 1532 }, { "epoch": 4.85126582278481, "grad_norm": 0.04591779478850221, "learning_rate": 2.1544480092084763e-07, "loss": 0.2479, "step": 1533 }, { "epoch": 4.8544303797468356, "grad_norm": 0.04562135689686307, "learning_rate": 2.0638227557328473e-07, "loss": 0.2528, "step": 1534 }, { "epoch": 4.8575949367088604, "grad_norm": 0.04546220771411278, "learning_rate": 1.9751397910290347e-07, "loss": 0.2467, "step": 1535 }, { "epoch": 4.860759493670886, "grad_norm": 0.046180474425463774, "learning_rate": 1.888399547950126e-07, "loss": 0.2452, "step": 1536 }, { "epoch": 4.863924050632911, "grad_norm": 0.04583100301195929, "learning_rate": 1.803602449867059e-07, "loss": 0.2476, "step": 1537 }, { "epoch": 4.867088607594937, "grad_norm": 0.045060736288639124, "learning_rate": 1.7207489106664478e-07, "loss": 0.246, "step": 1538 }, { "epoch": 4.870253164556962, "grad_norm": 0.04571192442943795, "learning_rate": 1.6398393347485386e-07, "loss": 0.2462, "step": 1539 }, { "epoch": 4.8734177215189876, "grad_norm": 0.047154202751260796, "learning_rate": 1.560874117025346e-07, "loss": 0.2547, "step": 1540 }, { "epoch": 4.8765822784810124, "grad_norm": 0.04586317713767183, "learning_rate": 1.4838536429185646e-07, "loss": 0.2486, "step": 1541 }, { "epoch": 4.879746835443038, "grad_norm": 0.04597208236798179, "learning_rate": 1.4087782883578373e-07, "loss": 0.2485, "step": 1542 }, { "epoch": 4.882911392405063, "grad_norm": 0.047108622910836555, "learning_rate": 1.33564841977889e-07, "loss": 0.2443, "step": 1543 }, { "epoch": 4.886075949367089, "grad_norm": 0.04683359519775253, "learning_rate": 1.2644643941216673e-07, "loss": 0.2519, "step": 1544 }, { "epoch": 4.889240506329114, "grad_norm": 0.046501455126462976, "learning_rate": 1.1952265588286437e-07, "loss": 0.2519, "step": 1545 }, { "epoch": 4.8924050632911396, "grad_norm": 0.045610788449044565, "learning_rate": 1.1279352518431374e-07, "loss": 0.2462, "step": 1546 }, { "epoch": 4.8955696202531644, "grad_norm": 0.04631715695554763, "learning_rate": 1.0625908016076214e-07, "loss": 0.2508, "step": 1547 }, { "epoch": 4.89873417721519, "grad_norm": 0.04552684429512282, "learning_rate": 9.991935270622144e-08, "loss": 0.2442, "step": 1548 }, { "epoch": 4.901898734177215, "grad_norm": 0.04734187316358231, "learning_rate": 9.377437376429488e-08, "loss": 0.252, "step": 1549 }, { "epoch": 4.905063291139241, "grad_norm": 0.046444398865033786, "learning_rate": 8.782417332804383e-08, "loss": 0.2477, "step": 1550 }, { "epoch": 4.908227848101266, "grad_norm": 0.04590135284869961, "learning_rate": 8.206878043983679e-08, "loss": 0.2482, "step": 1551 }, { "epoch": 4.911392405063291, "grad_norm": 0.04619675784455565, "learning_rate": 7.650822319119843e-08, "loss": 0.248, "step": 1552 }, { "epoch": 4.9145569620253164, "grad_norm": 0.04665149721310267, "learning_rate": 7.11425287226808e-08, "loss": 0.2484, "step": 1553 }, { "epoch": 4.917721518987342, "grad_norm": 0.04544907943375441, "learning_rate": 6.597172322373002e-08, "loss": 0.2505, "step": 1554 }, { "epoch": 4.920886075949367, "grad_norm": 0.047653386896858774, "learning_rate": 6.099583193255765e-08, "loss": 0.2526, "step": 1555 }, { "epoch": 4.924050632911392, "grad_norm": 0.04632931372430792, "learning_rate": 5.621487913602064e-08, "loss": 0.2511, "step": 1556 }, { "epoch": 4.927215189873418, "grad_norm": 0.04564638177896476, "learning_rate": 5.162888816949263e-08, "loss": 0.2449, "step": 1557 }, { "epoch": 4.930379746835443, "grad_norm": 0.049567303854180636, "learning_rate": 4.723788141676178e-08, "loss": 0.2454, "step": 1558 }, { "epoch": 4.9335443037974684, "grad_norm": 0.04709114857677133, "learning_rate": 4.304188030991974e-08, "loss": 0.2461, "step": 1559 }, { "epoch": 4.936708860759493, "grad_norm": 0.04648016267155814, "learning_rate": 3.9040905329246205e-08, "loss": 0.2469, "step": 1560 }, { "epoch": 4.939873417721519, "grad_norm": 0.047009907970197204, "learning_rate": 3.523497600312009e-08, "loss": 0.2489, "step": 1561 }, { "epoch": 4.943037974683544, "grad_norm": 0.04625049853607164, "learning_rate": 3.162411090792627e-08, "loss": 0.2498, "step": 1562 }, { "epoch": 4.94620253164557, "grad_norm": 0.04615653852071931, "learning_rate": 2.820832766795345e-08, "loss": 0.2466, "step": 1563 }, { "epoch": 4.949367088607595, "grad_norm": 0.04478949525422669, "learning_rate": 2.4987642955309755e-08, "loss": 0.2474, "step": 1564 }, { "epoch": 4.9525316455696204, "grad_norm": 0.04561037134070275, "learning_rate": 2.19620724898606e-08, "loss": 0.2499, "step": 1565 }, { "epoch": 4.955696202531645, "grad_norm": 0.04644505315856405, "learning_rate": 1.913163103912652e-08, "loss": 0.2475, "step": 1566 }, { "epoch": 4.958860759493671, "grad_norm": 0.046663932465978164, "learning_rate": 1.6496332418221016e-08, "loss": 0.2473, "step": 1567 }, { "epoch": 4.962025316455696, "grad_norm": 0.0457363158002933, "learning_rate": 1.4056189489792816e-08, "loss": 0.25, "step": 1568 }, { "epoch": 4.965189873417722, "grad_norm": 0.04489496822824893, "learning_rate": 1.1811214163941486e-08, "loss": 0.2499, "step": 1569 }, { "epoch": 4.968354430379747, "grad_norm": 0.04435332945798101, "learning_rate": 9.761417398181928e-09, "loss": 0.2499, "step": 1570 }, { "epoch": 4.9715189873417724, "grad_norm": 0.045494742369994505, "learning_rate": 7.906809197377741e-09, "loss": 0.2465, "step": 1571 }, { "epoch": 4.974683544303797, "grad_norm": 0.04639410042399373, "learning_rate": 6.2473986136968314e-09, "loss": 0.2477, "step": 1572 }, { "epoch": 4.977848101265823, "grad_norm": 0.04584011218821445, "learning_rate": 4.783193746562554e-09, "loss": 0.244, "step": 1573 }, { "epoch": 4.981012658227848, "grad_norm": 0.04692413693865667, "learning_rate": 3.514201742622625e-09, "loss": 0.2504, "step": 1574 }, { "epoch": 4.984177215189874, "grad_norm": 0.04643898448082584, "learning_rate": 2.440428795704719e-09, "loss": 0.2499, "step": 1575 }, { "epoch": 4.987341772151899, "grad_norm": 0.04434793867488091, "learning_rate": 1.561880146794259e-09, "loss": 0.2465, "step": 1576 }, { "epoch": 4.990506329113924, "grad_norm": 0.04510034628687074, "learning_rate": 8.785600840033325e-10, "loss": 0.2472, "step": 1577 }, { "epoch": 4.993670886075949, "grad_norm": 0.045894808308608724, "learning_rate": 3.90471942552928e-10, "loss": 0.2516, "step": 1578 }, { "epoch": 4.996835443037975, "grad_norm": 0.044479406851601934, "learning_rate": 9.761810475517053e-11, "loss": 0.2471, "step": 1579 }, { "epoch": 5.0, "grad_norm": 0.1563318438776402, "learning_rate": 0.0, "loss": 0.2341, "step": 1580 }, { "epoch": 5.0, "step": 1580, "total_flos": 8.900580986585088e+16, "train_loss": 0.31627833892273, "train_runtime": 68469.0969, "train_samples_per_second": 11.78, "train_steps_per_second": 0.023 } ], "logging_steps": 1, "max_steps": 1580, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8.900580986585088e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }