| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5349023803155925, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010698047606311847, | |
| "grad_norm": 1.7288448810577393, | |
| "learning_rate": 2.02e-06, | |
| "loss": 2.6627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021396095212623694, | |
| "grad_norm": 1.7482303380966187, | |
| "learning_rate": 4.04e-06, | |
| "loss": 2.8135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0032094142818935543, | |
| "grad_norm": 2.0931556224823, | |
| "learning_rate": 6.06e-06, | |
| "loss": 2.6959, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004279219042524739, | |
| "grad_norm": 2.3097078800201416, | |
| "learning_rate": 8.08e-06, | |
| "loss": 2.8474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005349023803155924, | |
| "grad_norm": 2.0344951152801514, | |
| "learning_rate": 1.0100000000000002e-05, | |
| "loss": 2.7842, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006418828563787109, | |
| "grad_norm": 1.9919047355651855, | |
| "learning_rate": 1.212e-05, | |
| "loss": 3.089, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007488633324418294, | |
| "grad_norm": 0.9272979497909546, | |
| "learning_rate": 1.4140000000000002e-05, | |
| "loss": 2.3151, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008558438085049478, | |
| "grad_norm": 1.6376522779464722, | |
| "learning_rate": 1.616e-05, | |
| "loss": 2.824, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009628242845680663, | |
| "grad_norm": 1.8005309104919434, | |
| "learning_rate": 1.818e-05, | |
| "loss": 2.6834, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010698047606311848, | |
| "grad_norm": 1.8941646814346313, | |
| "learning_rate": 2.0200000000000003e-05, | |
| "loss": 2.6678, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011767852366943032, | |
| "grad_norm": 1.860886573791504, | |
| "learning_rate": 2.222e-05, | |
| "loss": 2.7923, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012837657127574217, | |
| "grad_norm": 1.6937692165374756, | |
| "learning_rate": 2.424e-05, | |
| "loss": 2.4482, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013907461888205403, | |
| "grad_norm": 0.988033652305603, | |
| "learning_rate": 2.6260000000000003e-05, | |
| "loss": 2.3207, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014977266648836588, | |
| "grad_norm": 1.067140817642212, | |
| "learning_rate": 2.8280000000000004e-05, | |
| "loss": 2.3765, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016047071409467772, | |
| "grad_norm": 1.0069628953933716, | |
| "learning_rate": 3.0299999999999998e-05, | |
| "loss": 2.2754, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017116876170098955, | |
| "grad_norm": 0.8966661095619202, | |
| "learning_rate": 3.232e-05, | |
| "loss": 1.9436, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018186680930730142, | |
| "grad_norm": 0.8621421456336975, | |
| "learning_rate": 3.434e-05, | |
| "loss": 2.0105, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019256485691361326, | |
| "grad_norm": 0.6790559887886047, | |
| "learning_rate": 3.636e-05, | |
| "loss": 2.1134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02032629045199251, | |
| "grad_norm": 0.8534191250801086, | |
| "learning_rate": 3.838e-05, | |
| "loss": 2.6721, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021396095212623697, | |
| "grad_norm": 0.6541608572006226, | |
| "learning_rate": 4.0400000000000006e-05, | |
| "loss": 2.5973, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02246589997325488, | |
| "grad_norm": 0.5651280283927917, | |
| "learning_rate": 4.242e-05, | |
| "loss": 2.068, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023535704733886064, | |
| "grad_norm": 0.6473293900489807, | |
| "learning_rate": 4.444e-05, | |
| "loss": 2.2025, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02460550949451725, | |
| "grad_norm": 0.6129287481307983, | |
| "learning_rate": 4.6460000000000006e-05, | |
| "loss": 2.2035, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.025675314255148435, | |
| "grad_norm": 0.8293673992156982, | |
| "learning_rate": 4.848e-05, | |
| "loss": 2.1585, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026745119015779622, | |
| "grad_norm": 0.6636125445365906, | |
| "learning_rate": 5.05e-05, | |
| "loss": 1.9494, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027814923776410806, | |
| "grad_norm": 0.7317002415657043, | |
| "learning_rate": 5.2520000000000005e-05, | |
| "loss": 2.3731, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02888472853704199, | |
| "grad_norm": 0.5912388563156128, | |
| "learning_rate": 5.454e-05, | |
| "loss": 1.9946, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029954533297673176, | |
| "grad_norm": 0.509111225605011, | |
| "learning_rate": 5.656000000000001e-05, | |
| "loss": 1.906, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03102433805830436, | |
| "grad_norm": 0.5736451745033264, | |
| "learning_rate": 5.858e-05, | |
| "loss": 2.1449, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.032094142818935543, | |
| "grad_norm": 0.5325722098350525, | |
| "learning_rate": 6.0599999999999996e-05, | |
| "loss": 1.8039, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03316394757956673, | |
| "grad_norm": 0.6035159826278687, | |
| "learning_rate": 6.262000000000001e-05, | |
| "loss": 2.0611, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03423375234019791, | |
| "grad_norm": 0.7616627812385559, | |
| "learning_rate": 6.464e-05, | |
| "loss": 2.519, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0353035571008291, | |
| "grad_norm": 0.5022464394569397, | |
| "learning_rate": 6.666e-05, | |
| "loss": 2.1251, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.036373361861460285, | |
| "grad_norm": 0.5941365957260132, | |
| "learning_rate": 6.868e-05, | |
| "loss": 2.0392, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03744316662209147, | |
| "grad_norm": 0.5984216928482056, | |
| "learning_rate": 7.07e-05, | |
| "loss": 2.0259, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03851297138272265, | |
| "grad_norm": 0.5933278799057007, | |
| "learning_rate": 7.272e-05, | |
| "loss": 2.0123, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.039582776143353836, | |
| "grad_norm": 0.5975232720375061, | |
| "learning_rate": 7.474e-05, | |
| "loss": 2.0471, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04065258090398502, | |
| "grad_norm": 0.7600012421607971, | |
| "learning_rate": 7.676e-05, | |
| "loss": 1.9952, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04172238566461621, | |
| "grad_norm": 0.641670286655426, | |
| "learning_rate": 7.878e-05, | |
| "loss": 2.0748, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.042792190425247394, | |
| "grad_norm": 0.616679310798645, | |
| "learning_rate": 8.080000000000001e-05, | |
| "loss": 2.0396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04386199518587858, | |
| "grad_norm": 0.7081180214881897, | |
| "learning_rate": 8.282e-05, | |
| "loss": 1.7703, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04493179994650976, | |
| "grad_norm": 0.7007136940956116, | |
| "learning_rate": 8.484e-05, | |
| "loss": 2.2135, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.046001604707140945, | |
| "grad_norm": 0.729378879070282, | |
| "learning_rate": 8.686e-05, | |
| "loss": 1.8132, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04707140946777213, | |
| "grad_norm": 0.6952872276306152, | |
| "learning_rate": 8.888e-05, | |
| "loss": 2.2158, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04814121422840332, | |
| "grad_norm": 0.605029284954071, | |
| "learning_rate": 9.09e-05, | |
| "loss": 2.333, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0492110189890345, | |
| "grad_norm": 0.6177989840507507, | |
| "learning_rate": 9.292000000000001e-05, | |
| "loss": 1.6994, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.050280823749665686, | |
| "grad_norm": 0.5986810922622681, | |
| "learning_rate": 9.494e-05, | |
| "loss": 1.8176, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05135062851029687, | |
| "grad_norm": 0.6833954453468323, | |
| "learning_rate": 9.696e-05, | |
| "loss": 1.9501, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05242043327092805, | |
| "grad_norm": 0.8341196775436401, | |
| "learning_rate": 9.898e-05, | |
| "loss": 1.8998, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.053490238031559244, | |
| "grad_norm": 1.0498520135879517, | |
| "learning_rate": 0.000101, | |
| "loss": 1.6787, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05456004279219043, | |
| "grad_norm": 0.6734796762466431, | |
| "learning_rate": 0.00010302, | |
| "loss": 1.6638, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05562984755282161, | |
| "grad_norm": 0.6819894313812256, | |
| "learning_rate": 0.00010504000000000001, | |
| "loss": 2.0493, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.056699652313452795, | |
| "grad_norm": 0.8042811155319214, | |
| "learning_rate": 0.00010706000000000001, | |
| "loss": 1.9026, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05776945707408398, | |
| "grad_norm": 0.9070219993591309, | |
| "learning_rate": 0.00010908, | |
| "loss": 2.0546, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05883926183471516, | |
| "grad_norm": 0.8149216771125793, | |
| "learning_rate": 0.00011110000000000002, | |
| "loss": 1.5653, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05990906659534635, | |
| "grad_norm": 0.8578245043754578, | |
| "learning_rate": 0.00011312000000000001, | |
| "loss": 1.7776, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.060978871355977536, | |
| "grad_norm": 0.6369242668151855, | |
| "learning_rate": 0.00011514, | |
| "loss": 1.4798, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06204867611660872, | |
| "grad_norm": 0.8663727045059204, | |
| "learning_rate": 0.00011716, | |
| "loss": 1.8753, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06311848087723991, | |
| "grad_norm": 0.844870924949646, | |
| "learning_rate": 0.00011918, | |
| "loss": 1.7667, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06418828563787109, | |
| "grad_norm": 0.8465819954872131, | |
| "learning_rate": 0.00012119999999999999, | |
| "loss": 1.6944, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06525809039850228, | |
| "grad_norm": 0.807226300239563, | |
| "learning_rate": 0.00012322, | |
| "loss": 1.723, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06632789515913345, | |
| "grad_norm": 0.8274418711662292, | |
| "learning_rate": 0.00012524000000000001, | |
| "loss": 1.6919, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06739769991976464, | |
| "grad_norm": 0.8100050091743469, | |
| "learning_rate": 0.00012726, | |
| "loss": 1.8884, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06846750468039582, | |
| "grad_norm": 1.0959488153457642, | |
| "learning_rate": 0.00012928, | |
| "loss": 1.932, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.06953730944102701, | |
| "grad_norm": 1.0040597915649414, | |
| "learning_rate": 0.00013130000000000002, | |
| "loss": 1.8512, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0706071142016582, | |
| "grad_norm": 1.096177101135254, | |
| "learning_rate": 0.00013332, | |
| "loss": 1.8671, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07167691896228938, | |
| "grad_norm": 1.0180017948150635, | |
| "learning_rate": 0.00013534000000000002, | |
| "loss": 1.8652, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07274672372292057, | |
| "grad_norm": 0.8910913467407227, | |
| "learning_rate": 0.00013736, | |
| "loss": 1.6867, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07381652848355175, | |
| "grad_norm": 0.7205930352210999, | |
| "learning_rate": 0.00013937999999999998, | |
| "loss": 1.3372, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07488633324418294, | |
| "grad_norm": 0.8050198554992676, | |
| "learning_rate": 0.0001414, | |
| "loss": 1.8053, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07595613800481413, | |
| "grad_norm": 0.9537407159805298, | |
| "learning_rate": 0.00014342, | |
| "loss": 1.9222, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0770259427654453, | |
| "grad_norm": 0.8652852773666382, | |
| "learning_rate": 0.00014544, | |
| "loss": 1.6321, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0780957475260765, | |
| "grad_norm": 0.9287482500076294, | |
| "learning_rate": 0.00014746, | |
| "loss": 1.6623, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07916555228670767, | |
| "grad_norm": 0.8908249735832214, | |
| "learning_rate": 0.00014948, | |
| "loss": 1.9778, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08023535704733886, | |
| "grad_norm": 1.09617280960083, | |
| "learning_rate": 0.0001515, | |
| "loss": 1.6459, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08130516180797004, | |
| "grad_norm": 0.7375260591506958, | |
| "learning_rate": 0.00015352, | |
| "loss": 1.5546, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.08237496656860123, | |
| "grad_norm": 0.8195641040802002, | |
| "learning_rate": 0.00015554000000000002, | |
| "loss": 1.6602, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08344477132923242, | |
| "grad_norm": 0.8275863528251648, | |
| "learning_rate": 0.00015756, | |
| "loss": 1.7362, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0845145760898636, | |
| "grad_norm": 0.8596509695053101, | |
| "learning_rate": 0.00015958000000000001, | |
| "loss": 1.8343, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08558438085049479, | |
| "grad_norm": 0.8495697975158691, | |
| "learning_rate": 0.00016160000000000002, | |
| "loss": 1.5171, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08665418561112596, | |
| "grad_norm": 0.8796412944793701, | |
| "learning_rate": 0.00016362, | |
| "loss": 1.3298, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.08772399037175715, | |
| "grad_norm": 0.7089576125144958, | |
| "learning_rate": 0.00016564, | |
| "loss": 1.5468, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.08879379513238835, | |
| "grad_norm": 0.8609843850135803, | |
| "learning_rate": 0.00016766, | |
| "loss": 1.8827, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.08986359989301952, | |
| "grad_norm": 0.8612833023071289, | |
| "learning_rate": 0.00016968, | |
| "loss": 1.7344, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.09093340465365071, | |
| "grad_norm": 0.8177778124809265, | |
| "learning_rate": 0.0001717, | |
| "loss": 1.6543, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09200320941428189, | |
| "grad_norm": 0.9328483939170837, | |
| "learning_rate": 0.00017372, | |
| "loss": 1.452, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.09307301417491308, | |
| "grad_norm": 1.2951349020004272, | |
| "learning_rate": 0.00017574, | |
| "loss": 1.5672, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.09414281893554426, | |
| "grad_norm": 1.0605595111846924, | |
| "learning_rate": 0.00017776, | |
| "loss": 1.7043, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09521262369617545, | |
| "grad_norm": 0.8237940073013306, | |
| "learning_rate": 0.00017978000000000002, | |
| "loss": 1.7331, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.09628242845680664, | |
| "grad_norm": 0.8034561276435852, | |
| "learning_rate": 0.0001818, | |
| "loss": 1.6586, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09735223321743781, | |
| "grad_norm": 0.7969396114349365, | |
| "learning_rate": 0.00018382, | |
| "loss": 1.5385, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.098422037978069, | |
| "grad_norm": 0.792550265789032, | |
| "learning_rate": 0.00018584000000000002, | |
| "loss": 1.3909, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.09949184273870018, | |
| "grad_norm": 0.8620875477790833, | |
| "learning_rate": 0.00018786, | |
| "loss": 1.8194, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.10056164749933137, | |
| "grad_norm": 0.6592405438423157, | |
| "learning_rate": 0.00018988, | |
| "loss": 1.5115, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.10163145225996256, | |
| "grad_norm": 0.9358750581741333, | |
| "learning_rate": 0.0001919, | |
| "loss": 1.5659, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.10270125702059374, | |
| "grad_norm": 0.7691030502319336, | |
| "learning_rate": 0.00019392, | |
| "loss": 1.6011, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.10377106178122493, | |
| "grad_norm": 0.8470796942710876, | |
| "learning_rate": 0.00019594, | |
| "loss": 1.9553, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1048408665418561, | |
| "grad_norm": 0.8427095413208008, | |
| "learning_rate": 0.00019796, | |
| "loss": 1.5329, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1059106713024873, | |
| "grad_norm": 0.8238065838813782, | |
| "learning_rate": 0.00019998, | |
| "loss": 1.8338, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.10698047606311849, | |
| "grad_norm": 0.8195500373840332, | |
| "learning_rate": 0.000202, | |
| "loss": 1.4167, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10805028082374966, | |
| "grad_norm": 0.7097288966178894, | |
| "learning_rate": 0.00020199688492212377, | |
| "loss": 1.9694, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.10912008558438085, | |
| "grad_norm": 0.8986706137657166, | |
| "learning_rate": 0.00020198753988064772, | |
| "loss": 1.7537, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.11018989034501203, | |
| "grad_norm": 0.8444643616676331, | |
| "learning_rate": 0.00020197196545201806, | |
| "loss": 1.8293, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.11125969510564322, | |
| "grad_norm": 0.961504340171814, | |
| "learning_rate": 0.0002019501625969389, | |
| "loss": 1.7586, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.1123294998662744, | |
| "grad_norm": 1.3284465074539185, | |
| "learning_rate": 0.00020192213266031304, | |
| "loss": 1.5878, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11339930462690559, | |
| "grad_norm": 0.8253253102302551, | |
| "learning_rate": 0.00020188787737115897, | |
| "loss": 1.3733, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.11446910938753678, | |
| "grad_norm": 0.7246334552764893, | |
| "learning_rate": 0.00020184739884250436, | |
| "loss": 1.9136, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.11553891414816796, | |
| "grad_norm": 0.7832014560699463, | |
| "learning_rate": 0.00020180069957125544, | |
| "loss": 1.5472, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.11660871890879915, | |
| "grad_norm": 1.0413076877593994, | |
| "learning_rate": 0.0002017477824380433, | |
| "loss": 1.5569, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.11767852366943032, | |
| "grad_norm": 0.8862333297729492, | |
| "learning_rate": 0.00020168865070704594, | |
| "loss": 1.4746, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11874832843006151, | |
| "grad_norm": 1.0966826677322388, | |
| "learning_rate": 0.00020162330802578706, | |
| "loss": 1.6068, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.1198181331906927, | |
| "grad_norm": 1.2533254623413086, | |
| "learning_rate": 0.00020155175842491107, | |
| "loss": 1.2275, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.12088793795132388, | |
| "grad_norm": 0.8213242888450623, | |
| "learning_rate": 0.0002014740063179344, | |
| "loss": 1.665, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.12195774271195507, | |
| "grad_norm": 0.907412052154541, | |
| "learning_rate": 0.00020139005650097317, | |
| "loss": 1.5866, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.12302754747258625, | |
| "grad_norm": 1.1394984722137451, | |
| "learning_rate": 0.00020129991415244756, | |
| "loss": 1.7026, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.12409735223321744, | |
| "grad_norm": 0.8012979626655579, | |
| "learning_rate": 0.00020120358483276227, | |
| "loss": 1.4903, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.12516715699384862, | |
| "grad_norm": 0.7759647369384766, | |
| "learning_rate": 0.00020110107448396346, | |
| "loss": 1.6247, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.12623696175447982, | |
| "grad_norm": 0.8149462342262268, | |
| "learning_rate": 0.0002009923894293723, | |
| "loss": 1.7867, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.127306766515111, | |
| "grad_norm": 0.6406301259994507, | |
| "learning_rate": 0.00020087753637319499, | |
| "loss": 1.8543, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.12837657127574217, | |
| "grad_norm": 0.6905284523963928, | |
| "learning_rate": 0.00020075652240010892, | |
| "loss": 1.7696, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12944637603637335, | |
| "grad_norm": 0.7446596622467041, | |
| "learning_rate": 0.00020062935497482606, | |
| "loss": 1.6399, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.13051618079700456, | |
| "grad_norm": 0.6539953351020813, | |
| "learning_rate": 0.00020049604194163217, | |
| "loss": 1.3393, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.13158598555763573, | |
| "grad_norm": 0.9102329611778259, | |
| "learning_rate": 0.00020035659152390313, | |
| "loss": 1.4309, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.1326557903182669, | |
| "grad_norm": 0.9899008870124817, | |
| "learning_rate": 0.00020021101232359757, | |
| "loss": 1.4651, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1337255950788981, | |
| "grad_norm": 0.9645147323608398, | |
| "learning_rate": 0.0002000593133207263, | |
| "loss": 1.3662, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1347953998395293, | |
| "grad_norm": 0.5051845908164978, | |
| "learning_rate": 0.00019990150387279835, | |
| "loss": 1.7894, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.13586520460016047, | |
| "grad_norm": 0.9146197438240051, | |
| "learning_rate": 0.00019973759371424388, | |
| "loss": 1.3153, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.13693500936079164, | |
| "grad_norm": 0.9138407707214355, | |
| "learning_rate": 0.0001995675929558135, | |
| "loss": 1.6197, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.13800481412142285, | |
| "grad_norm": 0.8355864882469177, | |
| "learning_rate": 0.0001993915120839548, | |
| "loss": 1.5158, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.13907461888205402, | |
| "grad_norm": 0.7430102825164795, | |
| "learning_rate": 0.00019920936196016534, | |
| "loss": 1.4604, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1401444236426852, | |
| "grad_norm": 0.8076910376548767, | |
| "learning_rate": 0.0001990211538203228, | |
| "loss": 1.2259, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.1412142284033164, | |
| "grad_norm": 0.5874120593070984, | |
| "learning_rate": 0.00019882689927399174, | |
| "loss": 1.3672, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.14228403316394758, | |
| "grad_norm": 0.9105700254440308, | |
| "learning_rate": 0.00019862661030370764, | |
| "loss": 1.7311, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.14335383792457876, | |
| "grad_norm": 0.8008758425712585, | |
| "learning_rate": 0.00019842029926423762, | |
| "loss": 1.6541, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.14442364268520994, | |
| "grad_norm": 0.8042259216308594, | |
| "learning_rate": 0.00019820797888181837, | |
| "loss": 1.4167, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.14549344744584114, | |
| "grad_norm": 0.7910740971565247, | |
| "learning_rate": 0.00019798966225337126, | |
| "loss": 1.7123, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.14656325220647232, | |
| "grad_norm": 1.0059454441070557, | |
| "learning_rate": 0.00019776536284569425, | |
| "loss": 1.2412, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.1476330569671035, | |
| "grad_norm": 0.5858060717582703, | |
| "learning_rate": 0.00019753509449463134, | |
| "loss": 1.5322, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.1487028617277347, | |
| "grad_norm": 0.7342561483383179, | |
| "learning_rate": 0.00019729887140421912, | |
| "loss": 1.6668, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.14977266648836587, | |
| "grad_norm": 0.8164688348770142, | |
| "learning_rate": 0.00019705670814581052, | |
| "loss": 1.3033, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15084247124899705, | |
| "grad_norm": 1.2722523212432861, | |
| "learning_rate": 0.00019680861965717597, | |
| "loss": 1.6553, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.15191227600962826, | |
| "grad_norm": 0.8512006402015686, | |
| "learning_rate": 0.0001965546212415821, | |
| "loss": 1.5321, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.15298208077025943, | |
| "grad_norm": 0.9400825500488281, | |
| "learning_rate": 0.00019629472856684755, | |
| "loss": 1.2994, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.1540518855308906, | |
| "grad_norm": 0.6759757399559021, | |
| "learning_rate": 0.00019602895766437678, | |
| "loss": 1.6195, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.15512169029152179, | |
| "grad_norm": 0.5927717089653015, | |
| "learning_rate": 0.00019575732492817092, | |
| "loss": 1.4048, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.156191495052153, | |
| "grad_norm": 0.7187090516090393, | |
| "learning_rate": 0.00019547984711381662, | |
| "loss": 1.6072, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.15726129981278417, | |
| "grad_norm": 0.7754374146461487, | |
| "learning_rate": 0.0001951965413374525, | |
| "loss": 1.407, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.15833110457341534, | |
| "grad_norm": 1.0608164072036743, | |
| "learning_rate": 0.00019490742507471338, | |
| "loss": 1.5289, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.15940090933404655, | |
| "grad_norm": 1.0499017238616943, | |
| "learning_rate": 0.0001946125161596522, | |
| "loss": 1.3187, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.16047071409467772, | |
| "grad_norm": 0.9605572819709778, | |
| "learning_rate": 0.00019431183278363997, | |
| "loss": 1.203, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1615405188553089, | |
| "grad_norm": 0.6870492696762085, | |
| "learning_rate": 0.00019400539349424367, | |
| "loss": 1.9006, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.16261032361594008, | |
| "grad_norm": 0.8582913875579834, | |
| "learning_rate": 0.0001936932171940821, | |
| "loss": 1.828, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.16368012837657128, | |
| "grad_norm": 0.8130080699920654, | |
| "learning_rate": 0.00019337532313966, | |
| "loss": 1.5142, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.16474993313720246, | |
| "grad_norm": 1.1094551086425781, | |
| "learning_rate": 0.00019305173094017996, | |
| "loss": 1.3347, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.16581973789783364, | |
| "grad_norm": 0.7829759120941162, | |
| "learning_rate": 0.0001927224605563332, | |
| "loss": 1.2676, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.16688954265846484, | |
| "grad_norm": 0.8161009550094604, | |
| "learning_rate": 0.00019238753229906797, | |
| "loss": 1.2813, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.16795934741909602, | |
| "grad_norm": 0.794654369354248, | |
| "learning_rate": 0.00019204696682833682, | |
| "loss": 1.9873, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.1690291521797272, | |
| "grad_norm": 0.7361302375793457, | |
| "learning_rate": 0.00019170078515182216, | |
| "loss": 1.6699, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.1700989569403584, | |
| "grad_norm": 0.7557123899459839, | |
| "learning_rate": 0.00019134900862364054, | |
| "loss": 1.4325, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.17116876170098957, | |
| "grad_norm": 0.863318681716919, | |
| "learning_rate": 0.00019099165894302515, | |
| "loss": 1.5635, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.17223856646162075, | |
| "grad_norm": 0.8100736141204834, | |
| "learning_rate": 0.00019062875815298763, | |
| "loss": 1.3452, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.17330837122225193, | |
| "grad_norm": 0.8432340025901794, | |
| "learning_rate": 0.00019026032863895805, | |
| "loss": 1.3103, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.17437817598288313, | |
| "grad_norm": 0.8291115164756775, | |
| "learning_rate": 0.00018988639312740433, | |
| "loss": 1.3356, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.1754479807435143, | |
| "grad_norm": 0.6323521733283997, | |
| "learning_rate": 0.0001895069746844302, | |
| "loss": 1.2827, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.17651778550414549, | |
| "grad_norm": 0.6580619812011719, | |
| "learning_rate": 0.00018912209671435252, | |
| "loss": 1.483, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1775875902647767, | |
| "grad_norm": 0.927400529384613, | |
| "learning_rate": 0.00018873178295825732, | |
| "loss": 1.214, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.17865739502540787, | |
| "grad_norm": 1.0609151124954224, | |
| "learning_rate": 0.00018833605749253566, | |
| "loss": 1.5702, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.17972719978603904, | |
| "grad_norm": 0.9172216653823853, | |
| "learning_rate": 0.00018793494472739831, | |
| "loss": 1.4003, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.18079700454667022, | |
| "grad_norm": 0.793006956577301, | |
| "learning_rate": 0.00018752846940537003, | |
| "loss": 1.5463, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.18186680930730142, | |
| "grad_norm": 0.608418345451355, | |
| "learning_rate": 0.0001871166565997633, | |
| "loss": 1.4574, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1829366140679326, | |
| "grad_norm": 1.0822337865829468, | |
| "learning_rate": 0.00018669953171313188, | |
| "loss": 1.5066, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.18400641882856378, | |
| "grad_norm": 0.8970229625701904, | |
| "learning_rate": 0.00018627712047570352, | |
| "loss": 1.5338, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.18507622358919498, | |
| "grad_norm": 0.9221557378768921, | |
| "learning_rate": 0.0001858494489437931, | |
| "loss": 1.2652, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.18614602834982616, | |
| "grad_norm": 0.8210504651069641, | |
| "learning_rate": 0.0001854165434981953, | |
| "loss": 1.6507, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.18721583311045734, | |
| "grad_norm": 0.9927299618721008, | |
| "learning_rate": 0.00018497843084255708, | |
| "loss": 1.1338, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1882856378710885, | |
| "grad_norm": 0.640484631061554, | |
| "learning_rate": 0.00018453513800173072, | |
| "loss": 1.2064, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.18935544263171972, | |
| "grad_norm": 1.0150686502456665, | |
| "learning_rate": 0.00018408669232010684, | |
| "loss": 1.4428, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.1904252473923509, | |
| "grad_norm": 1.0852081775665283, | |
| "learning_rate": 0.00018363312145992737, | |
| "loss": 1.612, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.19149505215298207, | |
| "grad_norm": 0.884283185005188, | |
| "learning_rate": 0.0001831744533995795, | |
| "loss": 1.4523, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.19256485691361327, | |
| "grad_norm": 0.7068943977355957, | |
| "learning_rate": 0.00018271071643186968, | |
| "loss": 0.9464, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.19363466167424445, | |
| "grad_norm": 0.9215288162231445, | |
| "learning_rate": 0.00018224193916227852, | |
| "loss": 1.255, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.19470446643487563, | |
| "grad_norm": 0.6173170208930969, | |
| "learning_rate": 0.00018176815050719615, | |
| "loss": 1.556, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.19577427119550683, | |
| "grad_norm": 0.7621954083442688, | |
| "learning_rate": 0.00018128937969213852, | |
| "loss": 1.7331, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.196844075956138, | |
| "grad_norm": 0.8637974858283997, | |
| "learning_rate": 0.00018080565624994474, | |
| "loss": 1.2933, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.19791388071676919, | |
| "grad_norm": 0.9591987729072571, | |
| "learning_rate": 0.00018031701001895524, | |
| "loss": 1.4638, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.19898368547740036, | |
| "grad_norm": 0.7968719601631165, | |
| "learning_rate": 0.0001798234711411713, | |
| "loss": 1.2952, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.20005349023803157, | |
| "grad_norm": 1.2682313919067383, | |
| "learning_rate": 0.00017932507006039567, | |
| "loss": 1.3475, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.20112329499866274, | |
| "grad_norm": 0.5984092354774475, | |
| "learning_rate": 0.0001788218375203547, | |
| "loss": 1.4973, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.20219309975929392, | |
| "grad_norm": 0.7179667949676514, | |
| "learning_rate": 0.00017831380456280192, | |
| "loss": 1.4728, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.20326290451992512, | |
| "grad_norm": 1.1618380546569824, | |
| "learning_rate": 0.00017780100252560313, | |
| "loss": 1.6948, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2043327092805563, | |
| "grad_norm": 0.7051059603691101, | |
| "learning_rate": 0.00017728346304080357, | |
| "loss": 1.1708, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.20540251404118748, | |
| "grad_norm": 0.8025861382484436, | |
| "learning_rate": 0.0001767612180326764, | |
| "loss": 1.2174, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.20647231880181866, | |
| "grad_norm": 0.88255774974823, | |
| "learning_rate": 0.00017623429971575384, | |
| "loss": 1.4061, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.20754212356244986, | |
| "grad_norm": 0.7437373995780945, | |
| "learning_rate": 0.0001757027405928396, | |
| "loss": 1.1144, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.20861192832308104, | |
| "grad_norm": 1.0885889530181885, | |
| "learning_rate": 0.00017516657345300425, | |
| "loss": 1.6319, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2096817330837122, | |
| "grad_norm": 0.7450828552246094, | |
| "learning_rate": 0.00017462583136956258, | |
| "loss": 1.2593, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.21075153784434342, | |
| "grad_norm": 0.7687603831291199, | |
| "learning_rate": 0.00017408054769803337, | |
| "loss": 1.4812, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2118213426049746, | |
| "grad_norm": 0.9665757417678833, | |
| "learning_rate": 0.00017353075607408209, | |
| "loss": 1.2375, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.21289114736560577, | |
| "grad_norm": 0.9301120042800903, | |
| "learning_rate": 0.00017297649041144575, | |
| "loss": 1.4734, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.21396095212623698, | |
| "grad_norm": 0.9758381843566895, | |
| "learning_rate": 0.0001724177848998413, | |
| "loss": 1.1196, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21503075688686815, | |
| "grad_norm": 0.6634808778762817, | |
| "learning_rate": 0.00017185467400285644, | |
| "loss": 1.3473, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.21610056164749933, | |
| "grad_norm": 1.0161389112472534, | |
| "learning_rate": 0.00017128719245582374, | |
| "loss": 1.5335, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.2171703664081305, | |
| "grad_norm": 1.047826886177063, | |
| "learning_rate": 0.00017071537526367817, | |
| "loss": 1.4653, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.2182401711687617, | |
| "grad_norm": 0.8670541644096375, | |
| "learning_rate": 0.00017013925769879755, | |
| "loss": 1.1689, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.2193099759293929, | |
| "grad_norm": 1.1081433296203613, | |
| "learning_rate": 0.00016955887529882714, | |
| "loss": 1.3757, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.22037978069002406, | |
| "grad_norm": 1.3014432191848755, | |
| "learning_rate": 0.0001689742638644871, | |
| "loss": 1.1107, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.22144958545065527, | |
| "grad_norm": 0.779435396194458, | |
| "learning_rate": 0.00016838545945736458, | |
| "loss": 1.4839, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.22251939021128644, | |
| "grad_norm": 1.2251975536346436, | |
| "learning_rate": 0.00016779249839768884, | |
| "loss": 1.6717, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.22358919497191762, | |
| "grad_norm": 1.197913646697998, | |
| "learning_rate": 0.00016719541726209117, | |
| "loss": 1.4974, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.2246589997325488, | |
| "grad_norm": 1.0760390758514404, | |
| "learning_rate": 0.00016659425288134854, | |
| "loss": 1.3019, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.22572880449318, | |
| "grad_norm": 1.208444356918335, | |
| "learning_rate": 0.00016598904233811168, | |
| "loss": 1.1918, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.22679860925381118, | |
| "grad_norm": 1.3097633123397827, | |
| "learning_rate": 0.00016537982296461768, | |
| "loss": 1.1058, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.22786841401444236, | |
| "grad_norm": 0.8760459423065186, | |
| "learning_rate": 0.00016476663234038717, | |
| "loss": 1.6432, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.22893821877507356, | |
| "grad_norm": 0.7652115225791931, | |
| "learning_rate": 0.00016414950828990625, | |
| "loss": 1.7073, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.23000802353570474, | |
| "grad_norm": 0.8084537386894226, | |
| "learning_rate": 0.00016352848888029326, | |
| "loss": 1.3418, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2310778282963359, | |
| "grad_norm": 1.2894420623779297, | |
| "learning_rate": 0.00016290361241895064, | |
| "loss": 1.4992, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.2321476330569671, | |
| "grad_norm": 0.9421677589416504, | |
| "learning_rate": 0.00016227491745120196, | |
| "loss": 1.3181, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.2332174378175983, | |
| "grad_norm": 1.0605345964431763, | |
| "learning_rate": 0.0001616424427579143, | |
| "loss": 1.4584, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.23428724257822947, | |
| "grad_norm": 0.8410621285438538, | |
| "learning_rate": 0.0001610062273531059, | |
| "loss": 1.5476, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.23535704733886065, | |
| "grad_norm": 0.6994707584381104, | |
| "learning_rate": 0.00016036631048153979, | |
| "loss": 1.176, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.23642685209949185, | |
| "grad_norm": 1.1372922658920288, | |
| "learning_rate": 0.0001597227316163029, | |
| "loss": 1.3494, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.23749665686012303, | |
| "grad_norm": 1.1717870235443115, | |
| "learning_rate": 0.00015907553045637116, | |
| "loss": 1.313, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.2385664616207542, | |
| "grad_norm": 1.0904631614685059, | |
| "learning_rate": 0.00015842474692416068, | |
| "loss": 1.3035, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.2396362663813854, | |
| "grad_norm": 1.2501357793807983, | |
| "learning_rate": 0.0001577704211630652, | |
| "loss": 1.2295, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.2407060711420166, | |
| "grad_norm": 1.003653645515442, | |
| "learning_rate": 0.00015711259353497981, | |
| "loss": 1.0317, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.24177587590264776, | |
| "grad_norm": 0.6239796876907349, | |
| "learning_rate": 0.0001564513046178113, | |
| "loss": 1.7061, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.24284568066327894, | |
| "grad_norm": 0.8568412065505981, | |
| "learning_rate": 0.000155786595202975, | |
| "loss": 1.37, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.24391548542391014, | |
| "grad_norm": 0.9232256412506104, | |
| "learning_rate": 0.00015511850629287865, | |
| "loss": 1.1996, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.24498529018454132, | |
| "grad_norm": 1.1868820190429688, | |
| "learning_rate": 0.00015444707909839325, | |
| "loss": 1.5739, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.2460550949451725, | |
| "grad_norm": 1.0000498294830322, | |
| "learning_rate": 0.00015377235503631083, | |
| "loss": 1.1122, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2471248997058037, | |
| "grad_norm": 1.3450075387954712, | |
| "learning_rate": 0.0001530943757267898, | |
| "loss": 1.1177, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.24819470446643488, | |
| "grad_norm": 0.6483561992645264, | |
| "learning_rate": 0.00015241318299078751, | |
| "loss": 1.5464, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.24926450922706606, | |
| "grad_norm": 0.8778035044670105, | |
| "learning_rate": 0.00015172881884748063, | |
| "loss": 1.3679, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.25033431398769723, | |
| "grad_norm": 1.1430999040603638, | |
| "learning_rate": 0.00015104132551167318, | |
| "loss": 1.7691, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.2514041187483284, | |
| "grad_norm": 1.1102079153060913, | |
| "learning_rate": 0.00015035074539119248, | |
| "loss": 1.4866, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.25247392350895964, | |
| "grad_norm": 1.0472543239593506, | |
| "learning_rate": 0.00014965712108427323, | |
| "loss": 1.1737, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.2535437282695908, | |
| "grad_norm": 1.1687076091766357, | |
| "learning_rate": 0.00014896049537693005, | |
| "loss": 1.1114, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.254613533030222, | |
| "grad_norm": 0.5792782306671143, | |
| "learning_rate": 0.00014826091124031792, | |
| "loss": 1.1166, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.25568333779085317, | |
| "grad_norm": 0.8307198286056519, | |
| "learning_rate": 0.0001475584118280817, | |
| "loss": 1.4741, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.25675314255148435, | |
| "grad_norm": 0.6716192960739136, | |
| "learning_rate": 0.00014685304047369423, | |
| "loss": 1.2407, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2578229473121155, | |
| "grad_norm": 1.034075140953064, | |
| "learning_rate": 0.00014614484068778324, | |
| "loss": 1.4235, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.2588927520727467, | |
| "grad_norm": 0.9473350644111633, | |
| "learning_rate": 0.00014543385615544744, | |
| "loss": 1.4101, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.25996255683337793, | |
| "grad_norm": 1.1106480360031128, | |
| "learning_rate": 0.00014472013073356184, | |
| "loss": 0.9895, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.2610323615940091, | |
| "grad_norm": 0.8599668145179749, | |
| "learning_rate": 0.00014400370844807234, | |
| "loss": 1.2244, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.2621021663546403, | |
| "grad_norm": 0.7908911108970642, | |
| "learning_rate": 0.00014328463349128025, | |
| "loss": 1.5923, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.26317197111527146, | |
| "grad_norm": 0.8245794773101807, | |
| "learning_rate": 0.000142562950219116, | |
| "loss": 1.4023, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.26424177587590264, | |
| "grad_norm": 0.9234296679496765, | |
| "learning_rate": 0.00014183870314840325, | |
| "loss": 1.3907, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.2653115806365338, | |
| "grad_norm": 1.1608610153198242, | |
| "learning_rate": 0.00014111193695411285, | |
| "loss": 1.4156, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.266381385397165, | |
| "grad_norm": 1.186960220336914, | |
| "learning_rate": 0.00014038269646660703, | |
| "loss": 0.9267, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.2674511901577962, | |
| "grad_norm": 1.0800729990005493, | |
| "learning_rate": 0.00013965102666887408, | |
| "loss": 1.1525, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2685209949184274, | |
| "grad_norm": 0.5610882639884949, | |
| "learning_rate": 0.0001389169726937536, | |
| "loss": 1.4339, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.2695907996790586, | |
| "grad_norm": 0.9096266627311707, | |
| "learning_rate": 0.0001381805798211525, | |
| "loss": 1.4273, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.27066060443968976, | |
| "grad_norm": 0.930641770362854, | |
| "learning_rate": 0.00013744189347525182, | |
| "loss": 1.0906, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.27173040920032093, | |
| "grad_norm": 1.0747754573822021, | |
| "learning_rate": 0.00013670095922170498, | |
| "loss": 1.3499, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.2728002139609521, | |
| "grad_norm": 1.0504320859909058, | |
| "learning_rate": 0.00013595782276482678, | |
| "loss": 0.9918, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2738700187215833, | |
| "grad_norm": 1.225920557975769, | |
| "learning_rate": 0.00013521252994477446, | |
| "loss": 1.2121, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.2749398234822145, | |
| "grad_norm": 0.6419029235839844, | |
| "learning_rate": 0.00013446512673471965, | |
| "loss": 1.4319, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.2760096282428457, | |
| "grad_norm": 0.9120138883590698, | |
| "learning_rate": 0.0001337156592380131, | |
| "loss": 1.7584, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.27707943300347687, | |
| "grad_norm": 0.8686931133270264, | |
| "learning_rate": 0.0001329641736853402, | |
| "loss": 1.1114, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.27814923776410805, | |
| "grad_norm": 1.1766819953918457, | |
| "learning_rate": 0.0001322107164318697, | |
| "loss": 1.322, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2792190425247392, | |
| "grad_norm": 1.1522575616836548, | |
| "learning_rate": 0.00013145533395439405, | |
| "loss": 1.6013, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.2802888472853704, | |
| "grad_norm": 1.0668003559112549, | |
| "learning_rate": 0.0001306980728484627, | |
| "loss": 0.9711, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.2813586520460016, | |
| "grad_norm": 0.7991006374359131, | |
| "learning_rate": 0.00012993897982550764, | |
| "loss": 1.5706, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.2824284568066328, | |
| "grad_norm": 0.7399187684059143, | |
| "learning_rate": 0.00012917810170996218, | |
| "loss": 1.4344, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.283498261567264, | |
| "grad_norm": 0.8639386296272278, | |
| "learning_rate": 0.0001284154854363725, | |
| "loss": 1.2841, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.28456806632789516, | |
| "grad_norm": 1.039579153060913, | |
| "learning_rate": 0.00012765117804650267, | |
| "loss": 1.2761, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.28563787108852634, | |
| "grad_norm": 1.2643564939498901, | |
| "learning_rate": 0.00012688522668643268, | |
| "loss": 0.9961, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.2867076758491575, | |
| "grad_norm": 1.101484775543213, | |
| "learning_rate": 0.00012611767860365038, | |
| "loss": 1.0579, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.2877774806097887, | |
| "grad_norm": 0.8096588253974915, | |
| "learning_rate": 0.00012534858114413692, | |
| "loss": 1.4865, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.28884728537041987, | |
| "grad_norm": 0.9671081900596619, | |
| "learning_rate": 0.00012457798174944645, | |
| "loss": 1.712, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2899170901310511, | |
| "grad_norm": 0.8346510529518127, | |
| "learning_rate": 0.0001238059279537795, | |
| "loss": 1.4498, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.2909868948916823, | |
| "grad_norm": 0.8946216702461243, | |
| "learning_rate": 0.00012303246738105082, | |
| "loss": 1.1354, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.29205669965231346, | |
| "grad_norm": 1.1908957958221436, | |
| "learning_rate": 0.00012225764774195186, | |
| "loss": 1.2882, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.29312650441294463, | |
| "grad_norm": 1.5412572622299194, | |
| "learning_rate": 0.00012148151683100776, | |
| "loss": 1.3073, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.2941963091735758, | |
| "grad_norm": 1.269574522972107, | |
| "learning_rate": 0.00012070412252362897, | |
| "loss": 0.7722, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.295266113934207, | |
| "grad_norm": 0.6998116970062256, | |
| "learning_rate": 0.0001199255127731582, | |
| "loss": 1.6273, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.2963359186948382, | |
| "grad_norm": 1.2294608354568481, | |
| "learning_rate": 0.00011914573560791246, | |
| "loss": 1.3577, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.2974057234554694, | |
| "grad_norm": 1.464188814163208, | |
| "learning_rate": 0.00011836483912822035, | |
| "loss": 1.5042, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.29847552821610057, | |
| "grad_norm": 0.8934053778648376, | |
| "learning_rate": 0.00011758287150345516, | |
| "loss": 1.2751, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.29954533297673175, | |
| "grad_norm": 1.2757556438446045, | |
| "learning_rate": 0.00011679988096906333, | |
| "loss": 1.0978, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3006151377373629, | |
| "grad_norm": 1.4734572172164917, | |
| "learning_rate": 0.00011601591582358924, | |
| "loss": 0.9759, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.3016849424979941, | |
| "grad_norm": 0.5812798738479614, | |
| "learning_rate": 0.00011523102442569585, | |
| "loss": 1.8345, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.3027547472586253, | |
| "grad_norm": 0.6622848510742188, | |
| "learning_rate": 0.00011444525519118179, | |
| "loss": 1.3788, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.3038245520192565, | |
| "grad_norm": 0.8406071066856384, | |
| "learning_rate": 0.00011365865658999474, | |
| "loss": 1.2666, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.3048943567798877, | |
| "grad_norm": 0.8677452802658081, | |
| "learning_rate": 0.00011287127714324162, | |
| "loss": 1.2111, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.30596416154051886, | |
| "grad_norm": 1.3912626504898071, | |
| "learning_rate": 0.00011208316542019556, | |
| "loss": 1.0299, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.30703396630115004, | |
| "grad_norm": 1.1326332092285156, | |
| "learning_rate": 0.00011129437003530006, | |
| "loss": 0.8733, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.3081037710617812, | |
| "grad_norm": 0.8693293333053589, | |
| "learning_rate": 0.00011050493964516997, | |
| "loss": 1.2772, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.3091735758224124, | |
| "grad_norm": 0.9244024753570557, | |
| "learning_rate": 0.00010971492294559029, | |
| "loss": 1.6244, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.31024338058304357, | |
| "grad_norm": 0.99155592918396, | |
| "learning_rate": 0.00010892436866851235, | |
| "loss": 1.3652, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3113131853436748, | |
| "grad_norm": 1.061529517173767, | |
| "learning_rate": 0.00010813332557904784, | |
| "loss": 1.2438, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.312382990104306, | |
| "grad_norm": 0.8850228190422058, | |
| "learning_rate": 0.00010734184247246066, | |
| "loss": 1.1902, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.31345279486493716, | |
| "grad_norm": 1.0577521324157715, | |
| "learning_rate": 0.00010654996817115704, | |
| "loss": 0.8845, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.31452259962556833, | |
| "grad_norm": 0.9758553504943848, | |
| "learning_rate": 0.00010575775152167391, | |
| "loss": 1.4599, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.3155924043861995, | |
| "grad_norm": 0.6535763740539551, | |
| "learning_rate": 0.00010496524139166594, | |
| "loss": 1.7197, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3166622091468307, | |
| "grad_norm": 0.8583334684371948, | |
| "learning_rate": 0.00010417248666689095, | |
| "loss": 1.0697, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.31773201390746186, | |
| "grad_norm": 0.9801604747772217, | |
| "learning_rate": 0.00010337953624819464, | |
| "loss": 1.3483, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.3188018186680931, | |
| "grad_norm": 0.8529968857765198, | |
| "learning_rate": 0.0001025864390484939, | |
| "loss": 0.9852, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.31987162342872427, | |
| "grad_norm": 1.1832444667816162, | |
| "learning_rate": 0.00010179324398975984, | |
| "loss": 0.9118, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.32094142818935545, | |
| "grad_norm": 1.5987980365753174, | |
| "learning_rate": 0.000101, | |
| "loss": 0.8357, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3220112329499866, | |
| "grad_norm": 0.8217248916625977, | |
| "learning_rate": 0.00010020675601024019, | |
| "loss": 1.4393, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.3230810377106178, | |
| "grad_norm": 0.8473594188690186, | |
| "learning_rate": 9.941356095150613e-05, | |
| "loss": 1.4425, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.324150842471249, | |
| "grad_norm": 1.3870422840118408, | |
| "learning_rate": 9.862046375180539e-05, | |
| "loss": 1.6543, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.32522064723188016, | |
| "grad_norm": 1.0462790727615356, | |
| "learning_rate": 9.782751333310905e-05, | |
| "loss": 1.1367, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.3262904519925114, | |
| "grad_norm": 0.9303992986679077, | |
| "learning_rate": 9.70347586083341e-05, | |
| "loss": 1.2189, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.32736025675314256, | |
| "grad_norm": 1.2022167444229126, | |
| "learning_rate": 9.62422484783261e-05, | |
| "loss": 0.9073, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.32843006151377374, | |
| "grad_norm": 0.7831782102584839, | |
| "learning_rate": 9.5450031828843e-05, | |
| "loss": 1.3442, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.3294998662744049, | |
| "grad_norm": 1.0228748321533203, | |
| "learning_rate": 9.465815752753935e-05, | |
| "loss": 1.3841, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.3305696710350361, | |
| "grad_norm": 1.2510477304458618, | |
| "learning_rate": 9.386667442095219e-05, | |
| "loss": 1.387, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.33163947579566727, | |
| "grad_norm": 1.1324783563613892, | |
| "learning_rate": 9.307563133148767e-05, | |
| "loss": 1.187, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.33270928055629845, | |
| "grad_norm": 1.0329921245574951, | |
| "learning_rate": 9.228507705440976e-05, | |
| "loss": 1.0911, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.3337790853169297, | |
| "grad_norm": 1.0315637588500977, | |
| "learning_rate": 9.149506035483005e-05, | |
| "loss": 0.8645, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.33484889007756086, | |
| "grad_norm": 0.8189682364463806, | |
| "learning_rate": 9.070562996469997e-05, | |
| "loss": 1.6589, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.33591869483819203, | |
| "grad_norm": 0.7126203775405884, | |
| "learning_rate": 8.991683457980443e-05, | |
| "loss": 1.2723, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.3369884995988232, | |
| "grad_norm": 1.3155546188354492, | |
| "learning_rate": 8.912872285675841e-05, | |
| "loss": 1.5234, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3380583043594544, | |
| "grad_norm": 1.2776226997375488, | |
| "learning_rate": 8.834134341000527e-05, | |
| "loss": 1.3699, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.33912810912008556, | |
| "grad_norm": 0.9939321279525757, | |
| "learning_rate": 8.755474480881823e-05, | |
| "loss": 1.0941, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.3401979138807168, | |
| "grad_norm": 1.078808307647705, | |
| "learning_rate": 8.676897557430415e-05, | |
| "loss": 0.9849, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.341267718641348, | |
| "grad_norm": 0.692589282989502, | |
| "learning_rate": 8.598408417641078e-05, | |
| "loss": 0.9682, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.34233752340197915, | |
| "grad_norm": 0.69404137134552, | |
| "learning_rate": 8.520011903093666e-05, | |
| "loss": 1.4386, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3434073281626103, | |
| "grad_norm": 1.0537830591201782, | |
| "learning_rate": 8.441712849654485e-05, | |
| "loss": 1.3422, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.3444771329232415, | |
| "grad_norm": 1.2558127641677856, | |
| "learning_rate": 8.363516087177962e-05, | |
| "loss": 1.1179, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.3455469376838727, | |
| "grad_norm": 0.9815801382064819, | |
| "learning_rate": 8.285426439208755e-05, | |
| "loss": 1.159, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.34661674244450386, | |
| "grad_norm": 1.1159148216247559, | |
| "learning_rate": 8.20744872268418e-05, | |
| "loss": 1.0194, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.3476865472051351, | |
| "grad_norm": 0.904017448425293, | |
| "learning_rate": 8.129587747637105e-05, | |
| "loss": 0.8047, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.34875635196576626, | |
| "grad_norm": 0.6387720108032227, | |
| "learning_rate": 8.051848316899227e-05, | |
| "loss": 1.5516, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.34982615672639744, | |
| "grad_norm": 0.9615854024887085, | |
| "learning_rate": 7.974235225804814e-05, | |
| "loss": 1.4077, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.3508959614870286, | |
| "grad_norm": 0.9426089525222778, | |
| "learning_rate": 7.896753261894923e-05, | |
| "loss": 1.4134, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.3519657662476598, | |
| "grad_norm": 1.0092761516571045, | |
| "learning_rate": 7.819407204622054e-05, | |
| "loss": 1.1219, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.35303557100829097, | |
| "grad_norm": 0.9588394165039062, | |
| "learning_rate": 7.74220182505536e-05, | |
| "loss": 0.9877, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.35410537576892215, | |
| "grad_norm": 1.3635826110839844, | |
| "learning_rate": 7.665141885586312e-05, | |
| "loss": 0.8919, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.3551751805295534, | |
| "grad_norm": 0.543036699295044, | |
| "learning_rate": 7.588232139634968e-05, | |
| "loss": 1.2026, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.35624498529018456, | |
| "grad_norm": 1.009917974472046, | |
| "learning_rate": 7.511477331356733e-05, | |
| "loss": 1.4086, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.35731479005081573, | |
| "grad_norm": 0.9390615224838257, | |
| "learning_rate": 7.434882195349736e-05, | |
| "loss": 1.2364, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.3583845948114469, | |
| "grad_norm": 1.1638097763061523, | |
| "learning_rate": 7.358451456362751e-05, | |
| "loss": 1.4135, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.3594543995720781, | |
| "grad_norm": 1.2236016988754272, | |
| "learning_rate": 7.282189829003785e-05, | |
| "loss": 1.1124, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.36052420433270926, | |
| "grad_norm": 1.398525357246399, | |
| "learning_rate": 7.206102017449237e-05, | |
| "loss": 0.8598, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.36159400909334044, | |
| "grad_norm": 1.0281710624694824, | |
| "learning_rate": 7.130192715153731e-05, | |
| "loss": 1.48, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.3626638138539717, | |
| "grad_norm": 0.7850888967514038, | |
| "learning_rate": 7.054466604560595e-05, | |
| "loss": 1.1451, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.36373361861460285, | |
| "grad_norm": 1.0542351007461548, | |
| "learning_rate": 6.978928356813031e-05, | |
| "loss": 1.2867, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.364803423375234, | |
| "grad_norm": 1.0121204853057861, | |
| "learning_rate": 6.90358263146598e-05, | |
| "loss": 0.8742, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.3658732281358652, | |
| "grad_norm": 1.2728453874588013, | |
| "learning_rate": 6.828434076198693e-05, | |
| "loss": 0.9807, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.3669430328964964, | |
| "grad_norm": 1.3085882663726807, | |
| "learning_rate": 6.753487326528033e-05, | |
| "loss": 0.9157, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.36801283765712756, | |
| "grad_norm": 0.9796567559242249, | |
| "learning_rate": 6.678747005522557e-05, | |
| "loss": 0.9743, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.36908264241775873, | |
| "grad_norm": 0.6303224563598633, | |
| "learning_rate": 6.60421772351732e-05, | |
| "loss": 1.0932, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.37015244717838997, | |
| "grad_norm": 1.1777071952819824, | |
| "learning_rate": 6.529904077829505e-05, | |
| "loss": 1.2724, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.37122225193902114, | |
| "grad_norm": 0.9197458624839783, | |
| "learning_rate": 6.455810652474817e-05, | |
| "loss": 1.4357, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.3722920566996523, | |
| "grad_norm": 1.5600042343139648, | |
| "learning_rate": 6.381942017884753e-05, | |
| "loss": 1.1761, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.3733618614602835, | |
| "grad_norm": 1.1098041534423828, | |
| "learning_rate": 6.30830273062464e-05, | |
| "loss": 1.0017, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.37443166622091467, | |
| "grad_norm": 1.2631731033325195, | |
| "learning_rate": 6.234897333112594e-05, | |
| "loss": 0.8865, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.37550147098154585, | |
| "grad_norm": 0.8299064040184021, | |
| "learning_rate": 6.161730353339302e-05, | |
| "loss": 1.2372, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.376571275742177, | |
| "grad_norm": 1.0870029926300049, | |
| "learning_rate": 6.088806304588717e-05, | |
| "loss": 1.6713, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.37764108050280826, | |
| "grad_norm": 1.1188887357711792, | |
| "learning_rate": 6.0161296851596766e-05, | |
| "loss": 1.3496, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.37871088526343943, | |
| "grad_norm": 1.0576889514923096, | |
| "learning_rate": 5.943704978088402e-05, | |
| "loss": 1.211, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.3797806900240706, | |
| "grad_norm": 1.3803176879882812, | |
| "learning_rate": 5.871536650871979e-05, | |
| "loss": 1.0773, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3808504947847018, | |
| "grad_norm": 1.1492490768432617, | |
| "learning_rate": 5.7996291551927666e-05, | |
| "loss": 0.9198, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.38192029954533296, | |
| "grad_norm": 0.6801052093505859, | |
| "learning_rate": 5.7279869266438234e-05, | |
| "loss": 1.4337, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.38299010430596414, | |
| "grad_norm": 1.2174427509307861, | |
| "learning_rate": 5.656614384455257e-05, | |
| "loss": 1.2353, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.3840599090665954, | |
| "grad_norm": 1.1382440328598022, | |
| "learning_rate": 5.585515931221677e-05, | |
| "loss": 1.3431, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.38512971382722655, | |
| "grad_norm": 0.9358460307121277, | |
| "learning_rate": 5.514695952630578e-05, | |
| "loss": 0.9496, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3861995185878577, | |
| "grad_norm": 1.1950464248657227, | |
| "learning_rate": 5.444158817191832e-05, | |
| "loss": 0.9529, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.3872693233484889, | |
| "grad_norm": 1.0980271100997925, | |
| "learning_rate": 5.373908875968211e-05, | |
| "loss": 1.1347, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.3883391281091201, | |
| "grad_norm": 0.7558470368385315, | |
| "learning_rate": 5.3039504623069965e-05, | |
| "loss": 0.9622, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.38940893286975126, | |
| "grad_norm": 1.0493141412734985, | |
| "learning_rate": 5.234287891572674e-05, | |
| "loss": 1.1268, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.39047873763038243, | |
| "grad_norm": 1.2050443887710571, | |
| "learning_rate": 5.164925460880758e-05, | |
| "loss": 1.2384, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.39154854239101367, | |
| "grad_norm": 1.2287790775299072, | |
| "learning_rate": 5.095867448832683e-05, | |
| "loss": 1.2972, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.39261834715164484, | |
| "grad_norm": 1.3510652780532837, | |
| "learning_rate": 5.027118115251938e-05, | |
| "loss": 1.3639, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.393688151912276, | |
| "grad_norm": 1.2277965545654297, | |
| "learning_rate": 4.95868170092125e-05, | |
| "loss": 1.1627, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.3947579566729072, | |
| "grad_norm": 1.1306562423706055, | |
| "learning_rate": 4.890562427321021e-05, | |
| "loss": 1.1845, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.39582776143353837, | |
| "grad_norm": 0.8683123588562012, | |
| "learning_rate": 4.822764496368917e-05, | |
| "loss": 1.1248, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.39689756619416955, | |
| "grad_norm": 1.0992448329925537, | |
| "learning_rate": 4.755292090160676e-05, | |
| "loss": 1.4496, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.3979673709548007, | |
| "grad_norm": 1.0645350217819214, | |
| "learning_rate": 4.6881493707121315e-05, | |
| "loss": 0.943, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.39903717571543196, | |
| "grad_norm": 1.105506420135498, | |
| "learning_rate": 4.621340479702503e-05, | |
| "loss": 1.0031, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.40010698047606313, | |
| "grad_norm": 0.8552220463752747, | |
| "learning_rate": 4.554869538218868e-05, | |
| "loss": 1.0468, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.4011767852366943, | |
| "grad_norm": 0.8983728289604187, | |
| "learning_rate": 4.48874064650202e-05, | |
| "loss": 0.8188, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4022465899973255, | |
| "grad_norm": 0.6168304085731506, | |
| "learning_rate": 4.422957883693483e-05, | |
| "loss": 1.394, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.40331639475795666, | |
| "grad_norm": 1.0310661792755127, | |
| "learning_rate": 4.357525307583933e-05, | |
| "loss": 1.2572, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.40438619951858784, | |
| "grad_norm": 0.9725519418716431, | |
| "learning_rate": 4.29244695436289e-05, | |
| "loss": 1.2638, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.405456004279219, | |
| "grad_norm": 0.768764317035675, | |
| "learning_rate": 4.227726838369711e-05, | |
| "loss": 1.1837, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.40652580903985025, | |
| "grad_norm": 1.267078161239624, | |
| "learning_rate": 4.1633689518460225e-05, | |
| "loss": 1.0828, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4075956138004814, | |
| "grad_norm": 1.0793355703353882, | |
| "learning_rate": 4.0993772646894116e-05, | |
| "loss": 0.9099, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.4086654185611126, | |
| "grad_norm": 0.7304561138153076, | |
| "learning_rate": 4.035755724208573e-05, | |
| "loss": 1.3844, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.4097352233217438, | |
| "grad_norm": 0.9201098680496216, | |
| "learning_rate": 3.972508254879805e-05, | |
| "loss": 1.3788, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.41080502808237496, | |
| "grad_norm": 1.1659053564071655, | |
| "learning_rate": 3.90963875810494e-05, | |
| "loss": 1.3056, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.41187483284300613, | |
| "grad_norm": 0.9076784253120422, | |
| "learning_rate": 3.847151111970676e-05, | |
| "loss": 1.2791, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.4129446376036373, | |
| "grad_norm": 1.2633960247039795, | |
| "learning_rate": 3.785049171009381e-05, | |
| "loss": 1.2781, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.41401444236426854, | |
| "grad_norm": 0.8448993563652039, | |
| "learning_rate": 3.723336765961285e-05, | |
| "loss": 0.7594, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.4150842471248997, | |
| "grad_norm": 0.9559032917022705, | |
| "learning_rate": 3.662017703538234e-05, | |
| "loss": 1.238, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.4161540518855309, | |
| "grad_norm": 0.7692968845367432, | |
| "learning_rate": 3.601095766188833e-05, | |
| "loss": 1.0494, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.4172238566461621, | |
| "grad_norm": 0.9550884962081909, | |
| "learning_rate": 3.540574711865146e-05, | |
| "loss": 1.2024, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.41829366140679325, | |
| "grad_norm": 0.9791415333747864, | |
| "learning_rate": 3.4804582737908825e-05, | |
| "loss": 1.1066, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.4193634661674244, | |
| "grad_norm": 0.876552402973175, | |
| "learning_rate": 3.420750160231118e-05, | |
| "loss": 0.9091, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.4204332709280556, | |
| "grad_norm": 1.0393965244293213, | |
| "learning_rate": 3.361454054263541e-05, | |
| "loss": 0.7999, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.42150307568868683, | |
| "grad_norm": 0.6238046288490295, | |
| "learning_rate": 3.302573613551292e-05, | |
| "loss": 0.9947, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.422572880449318, | |
| "grad_norm": 1.2074321508407593, | |
| "learning_rate": 3.244112470117288e-05, | |
| "loss": 1.4528, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4236426852099492, | |
| "grad_norm": 0.8338631987571716, | |
| "learning_rate": 3.186074230120244e-05, | |
| "loss": 1.2835, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.42471248997058036, | |
| "grad_norm": 0.9252687096595764, | |
| "learning_rate": 3.1284624736321846e-05, | |
| "loss": 1.1478, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.42578229473121154, | |
| "grad_norm": 0.896878182888031, | |
| "learning_rate": 3.071280754417626e-05, | |
| "loss": 1.0608, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.4268520994918427, | |
| "grad_norm": 1.1846908330917358, | |
| "learning_rate": 3.0145325997143577e-05, | |
| "loss": 0.9898, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.42792190425247395, | |
| "grad_norm": 0.8462516665458679, | |
| "learning_rate": 2.9582215100158706e-05, | |
| "loss": 0.6714, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4289917090131051, | |
| "grad_norm": 0.5424546003341675, | |
| "learning_rate": 2.902350958855426e-05, | |
| "loss": 1.304, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.4300615137737363, | |
| "grad_norm": 1.0380676984786987, | |
| "learning_rate": 2.846924392591794e-05, | |
| "loss": 1.4114, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.4311313185343675, | |
| "grad_norm": 1.0235589742660522, | |
| "learning_rate": 2.791945230196663e-05, | |
| "loss": 1.1948, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.43220112329499866, | |
| "grad_norm": 0.9752116799354553, | |
| "learning_rate": 2.7374168630437456e-05, | |
| "loss": 0.8311, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.43327092805562983, | |
| "grad_norm": 1.1082531213760376, | |
| "learning_rate": 2.6833426546995782e-05, | |
| "loss": 0.8029, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.434340732816261, | |
| "grad_norm": 1.0731070041656494, | |
| "learning_rate": 2.629725940716041e-05, | |
| "loss": 0.6362, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.43541053757689224, | |
| "grad_norm": 0.7748804688453674, | |
| "learning_rate": 2.57657002842462e-05, | |
| "loss": 1.3502, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.4364803423375234, | |
| "grad_norm": 0.9873160719871521, | |
| "learning_rate": 2.523878196732358e-05, | |
| "loss": 1.4015, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.4375501470981546, | |
| "grad_norm": 1.168376088142395, | |
| "learning_rate": 2.4716536959196462e-05, | |
| "loss": 0.9562, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.4386199518587858, | |
| "grad_norm": 0.9947543740272522, | |
| "learning_rate": 2.4198997474396877e-05, | |
| "loss": 1.0764, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.43968975661941695, | |
| "grad_norm": 1.0038477182388306, | |
| "learning_rate": 2.3686195437198112e-05, | |
| "loss": 1.1025, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.4407595613800481, | |
| "grad_norm": 1.073735237121582, | |
| "learning_rate": 2.31781624796453e-05, | |
| "loss": 0.9347, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.4418293661406793, | |
| "grad_norm": 0.8761813044548035, | |
| "learning_rate": 2.2674929939604332e-05, | |
| "loss": 1.3846, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.44289917090131053, | |
| "grad_norm": 0.707740068435669, | |
| "learning_rate": 2.217652885882869e-05, | |
| "loss": 1.2739, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.4439689756619417, | |
| "grad_norm": 0.8587148189544678, | |
| "learning_rate": 2.1682989981044783e-05, | |
| "loss": 1.4457, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.4450387804225729, | |
| "grad_norm": 0.9313194155693054, | |
| "learning_rate": 2.119434375005527e-05, | |
| "loss": 1.3368, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.44610858518320406, | |
| "grad_norm": 0.9590698480606079, | |
| "learning_rate": 2.071062030786149e-05, | |
| "loss": 1.0, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.44717838994383524, | |
| "grad_norm": 1.0751738548278809, | |
| "learning_rate": 2.0231849492803852e-05, | |
| "loss": 0.8612, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.4482481947044664, | |
| "grad_norm": 0.8183998465538025, | |
| "learning_rate": 1.9758060837721467e-05, | |
| "loss": 1.1862, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.4493179994650976, | |
| "grad_norm": 0.9243028163909912, | |
| "learning_rate": 1.928928356813032e-05, | |
| "loss": 1.6195, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4503878042257288, | |
| "grad_norm": 1.1141655445098877, | |
| "learning_rate": 1.882554660042052e-05, | |
| "loss": 1.2306, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.45145760898636, | |
| "grad_norm": 0.9904926419258118, | |
| "learning_rate": 1.8366878540072614e-05, | |
| "loss": 1.1581, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.4525274137469912, | |
| "grad_norm": 0.8445707559585571, | |
| "learning_rate": 1.7913307679893173e-05, | |
| "loss": 1.1488, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.45359721850762236, | |
| "grad_norm": 1.067460060119629, | |
| "learning_rate": 1.7464861998269243e-05, | |
| "loss": 0.9826, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.45466702326825353, | |
| "grad_norm": 1.1314057111740112, | |
| "learning_rate": 1.702156915744292e-05, | |
| "loss": 0.6977, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4557368280288847, | |
| "grad_norm": 0.8268198370933533, | |
| "learning_rate": 1.6583456501804725e-05, | |
| "loss": 1.6189, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.4568066327895159, | |
| "grad_norm": 0.9529428482055664, | |
| "learning_rate": 1.6150551056206867e-05, | |
| "loss": 1.2327, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.4578764375501471, | |
| "grad_norm": 1.1057630777359009, | |
| "learning_rate": 1.57228795242965e-05, | |
| "loss": 1.1263, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.4589462423107783, | |
| "grad_norm": 0.8888829350471497, | |
| "learning_rate": 1.5300468286868137e-05, | |
| "loss": 0.9244, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.4600160470714095, | |
| "grad_norm": 1.019853949546814, | |
| "learning_rate": 1.488334340023669e-05, | |
| "loss": 1.0842, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.46108585183204065, | |
| "grad_norm": 1.1532846689224243, | |
| "learning_rate": 1.4471530594629996e-05, | |
| "loss": 0.7479, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.4621556565926718, | |
| "grad_norm": 0.9575594663619995, | |
| "learning_rate": 1.4065055272601703e-05, | |
| "loss": 1.3278, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.463225461353303, | |
| "grad_norm": 0.9033411145210266, | |
| "learning_rate": 1.3663942507464348e-05, | |
| "loss": 1.6109, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.4642952661139342, | |
| "grad_norm": 0.9153274297714233, | |
| "learning_rate": 1.3268217041742701e-05, | |
| "loss": 0.9475, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.4653650708745654, | |
| "grad_norm": 1.0005955696105957, | |
| "learning_rate": 1.2877903285647486e-05, | |
| "loss": 0.9418, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.4664348756351966, | |
| "grad_norm": 1.0038702487945557, | |
| "learning_rate": 1.2493025315569801e-05, | |
| "loss": 0.8441, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.46750468039582777, | |
| "grad_norm": 1.012077808380127, | |
| "learning_rate": 1.2113606872595673e-05, | |
| "loss": 0.5747, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.46857448515645894, | |
| "grad_norm": 0.9703443646430969, | |
| "learning_rate": 1.173967136104196e-05, | |
| "loss": 1.2232, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.4696442899170901, | |
| "grad_norm": 1.00784170627594, | |
| "learning_rate": 1.1371241847012401e-05, | |
| "loss": 1.1904, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.4707140946777213, | |
| "grad_norm": 0.7357102036476135, | |
| "learning_rate": 1.1008341056974854e-05, | |
| "loss": 1.2484, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4717838994383525, | |
| "grad_norm": 1.120018482208252, | |
| "learning_rate": 1.0650991376359473e-05, | |
| "loss": 1.0129, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.4728537041989837, | |
| "grad_norm": 1.1301084756851196, | |
| "learning_rate": 1.029921484817783e-05, | |
| "loss": 1.0191, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.4739235089596149, | |
| "grad_norm": 0.9591827988624573, | |
| "learning_rate": 9.953033171663175e-06, | |
| "loss": 0.7102, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.47499331372024606, | |
| "grad_norm": 0.9715290665626526, | |
| "learning_rate": 9.612467700932045e-06, | |
| "loss": 0.9119, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.47606311848087723, | |
| "grad_norm": 0.8477181196212769, | |
| "learning_rate": 9.277539443666783e-06, | |
| "loss": 1.434, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.4771329232415084, | |
| "grad_norm": 1.0625755786895752, | |
| "learning_rate": 8.948269059820025e-06, | |
| "loss": 0.9963, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.4782027280021396, | |
| "grad_norm": 0.9794643521308899, | |
| "learning_rate": 8.624676860340025e-06, | |
| "loss": 0.9641, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.4792725327627708, | |
| "grad_norm": 1.0721542835235596, | |
| "learning_rate": 8.306782805917904e-06, | |
| "loss": 1.2077, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.480342337523402, | |
| "grad_norm": 1.1416406631469727, | |
| "learning_rate": 7.994606505756355e-06, | |
| "loss": 0.793, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.4814121422840332, | |
| "grad_norm": 1.3246476650238037, | |
| "learning_rate": 7.68816721636004e-06, | |
| "loss": 0.6877, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.48248194704466435, | |
| "grad_norm": 0.7753664255142212, | |
| "learning_rate": 7.3874838403478e-06, | |
| "loss": 1.5715, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.4835517518052955, | |
| "grad_norm": 0.8879972696304321, | |
| "learning_rate": 7.092574925286614e-06, | |
| "loss": 1.5482, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.4846215565659267, | |
| "grad_norm": 0.9376313090324402, | |
| "learning_rate": 6.803458662547507e-06, | |
| "loss": 1.0972, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.4856913613265579, | |
| "grad_norm": 1.133258581161499, | |
| "learning_rate": 6.520152886183406e-06, | |
| "loss": 0.8188, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.4867611660871891, | |
| "grad_norm": 1.023056983947754, | |
| "learning_rate": 6.242675071829111e-06, | |
| "loss": 0.9871, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.4878309708478203, | |
| "grad_norm": 1.0413668155670166, | |
| "learning_rate": 5.971042335623229e-06, | |
| "loss": 0.8659, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.48890077560845147, | |
| "grad_norm": 0.8116885423660278, | |
| "learning_rate": 5.705271433152458e-06, | |
| "loss": 1.4952, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.48997058036908264, | |
| "grad_norm": 0.7350386381149292, | |
| "learning_rate": 5.445378758417925e-06, | |
| "loss": 1.3216, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.4910403851297138, | |
| "grad_norm": 0.9509938359260559, | |
| "learning_rate": 5.191380342824035e-06, | |
| "loss": 1.033, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.492110189890345, | |
| "grad_norm": 0.8455548882484436, | |
| "learning_rate": 4.943291854189493e-06, | |
| "loss": 0.9927, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.4931799946509762, | |
| "grad_norm": 1.0387928485870361, | |
| "learning_rate": 4.701128595780878e-06, | |
| "loss": 0.8588, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.4942497994116074, | |
| "grad_norm": 0.9830685257911682, | |
| "learning_rate": 4.464905505368658e-06, | |
| "loss": 0.6431, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.4953196041722386, | |
| "grad_norm": 0.8270193338394165, | |
| "learning_rate": 4.23463715430577e-06, | |
| "loss": 1.4119, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.49638940893286976, | |
| "grad_norm": 0.9378442764282227, | |
| "learning_rate": 4.010337746628751e-06, | |
| "loss": 1.3177, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.49745921369350093, | |
| "grad_norm": 1.149201512336731, | |
| "learning_rate": 3.792021118181636e-06, | |
| "loss": 1.1545, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4985290184541321, | |
| "grad_norm": 1.167047381401062, | |
| "learning_rate": 3.5797007357623945e-06, | |
| "loss": 1.4185, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.4995988232147633, | |
| "grad_norm": 1.0257937908172607, | |
| "learning_rate": 3.3733896962923658e-06, | |
| "loss": 0.8571, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.5006686279753945, | |
| "grad_norm": 1.0537946224212646, | |
| "learning_rate": 3.1731007260082616e-06, | |
| "loss": 1.0841, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.5017384327360257, | |
| "grad_norm": 0.7948933839797974, | |
| "learning_rate": 2.9788461796772114e-06, | |
| "loss": 0.9228, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.5028082374966568, | |
| "grad_norm": 0.8775575160980225, | |
| "learning_rate": 2.790638039834668e-06, | |
| "loss": 1.0854, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.503878042257288, | |
| "grad_norm": 0.8913066387176514, | |
| "learning_rate": 2.6084879160452166e-06, | |
| "loss": 1.2876, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.5049478470179193, | |
| "grad_norm": 1.0341969728469849, | |
| "learning_rate": 2.432407044186509e-06, | |
| "loss": 1.0843, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.5060176517785504, | |
| "grad_norm": 1.077120304107666, | |
| "learning_rate": 2.26240628575615e-06, | |
| "loss": 1.1631, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.5070874565391816, | |
| "grad_norm": 1.2969963550567627, | |
| "learning_rate": 2.098496127201648e-06, | |
| "loss": 0.9719, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.5081572612998128, | |
| "grad_norm": 0.9883275032043457, | |
| "learning_rate": 1.9406866792737267e-06, | |
| "loss": 0.7292, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.509227066060444, | |
| "grad_norm": 0.8158979415893555, | |
| "learning_rate": 1.7889876764024505e-06, | |
| "loss": 1.7438, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.5102968708210751, | |
| "grad_norm": 1.0562134981155396, | |
| "learning_rate": 1.6434084760968697e-06, | |
| "loss": 1.1742, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.5113666755817063, | |
| "grad_norm": 1.1257410049438477, | |
| "learning_rate": 1.5039580583678393e-06, | |
| "loss": 1.4287, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.5124364803423376, | |
| "grad_norm": 0.9307600855827332, | |
| "learning_rate": 1.3706450251739613e-06, | |
| "loss": 1.0974, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.5135062851029687, | |
| "grad_norm": 1.2765836715698242, | |
| "learning_rate": 1.2434775998910964e-06, | |
| "loss": 0.913, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5145760898635999, | |
| "grad_norm": 0.960442304611206, | |
| "learning_rate": 1.1224636268050439e-06, | |
| "loss": 0.7802, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.515645894624231, | |
| "grad_norm": 0.7446873188018799, | |
| "learning_rate": 1.0076105706276888e-06, | |
| "loss": 1.3411, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.5167156993848623, | |
| "grad_norm": 0.8171153664588928, | |
| "learning_rate": 8.989255160365527e-07, | |
| "loss": 1.1665, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.5177855041454934, | |
| "grad_norm": 1.2924435138702393, | |
| "learning_rate": 7.964151672377458e-07, | |
| "loss": 1.0651, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.5188553089061246, | |
| "grad_norm": 0.8738812804222107, | |
| "learning_rate": 7.000858475524444e-07, | |
| "loss": 0.9887, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.5199251136667559, | |
| "grad_norm": 1.1796964406967163, | |
| "learning_rate": 6.099434990268609e-07, | |
| "loss": 1.0128, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.520994918427387, | |
| "grad_norm": 0.9124283194541931, | |
| "learning_rate": 5.259936820656257e-07, | |
| "loss": 0.5644, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.5220647231880182, | |
| "grad_norm": 0.7489669322967529, | |
| "learning_rate": 4.482415750889204e-07, | |
| "loss": 1.1193, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.5231345279486493, | |
| "grad_norm": 0.969879150390625, | |
| "learning_rate": 3.766919742129331e-07, | |
| "loss": 1.2911, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.5242043327092806, | |
| "grad_norm": 0.9446693062782288, | |
| "learning_rate": 3.1134929295407564e-07, | |
| "loss": 1.2359, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5252741374699117, | |
| "grad_norm": 0.8747495412826538, | |
| "learning_rate": 2.5221756195672563e-07, | |
| "loss": 1.0005, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.5263439422305429, | |
| "grad_norm": 1.1830285787582397, | |
| "learning_rate": 1.9930042874457254e-07, | |
| "loss": 0.8599, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.5274137469911742, | |
| "grad_norm": 0.886387825012207, | |
| "learning_rate": 1.5260115749566882e-07, | |
| "loss": 0.8124, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.5284835517518053, | |
| "grad_norm": 0.7844628691673279, | |
| "learning_rate": 1.1212262884103974e-07, | |
| "loss": 1.4931, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.5295533565124365, | |
| "grad_norm": 0.8858184218406677, | |
| "learning_rate": 7.7867339686987e-08, | |
| "loss": 1.2632, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.5306231612730676, | |
| "grad_norm": 0.9755517840385437, | |
| "learning_rate": 4.98374030611084e-08, | |
| "loss": 1.1289, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.5316929660336989, | |
| "grad_norm": 0.9477503299713135, | |
| "learning_rate": 2.8034547981943713e-08, | |
| "loss": 1.1403, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.53276277079433, | |
| "grad_norm": 0.9157533645629883, | |
| "learning_rate": 1.246011935228064e-08, | |
| "loss": 0.9965, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.5338325755549612, | |
| "grad_norm": 1.1439539194107056, | |
| "learning_rate": 3.115077876243988e-09, | |
| "loss": 1.0751, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.5349023803155925, | |
| "grad_norm": 1.0133370161056519, | |
| "learning_rate": 0.0, | |
| "loss": 0.8007, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.0690671548959293e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |