{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.34443168771526983, "eval_steps": 500, "global_step": 3000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001148105625717566, "grad_norm": 4.418115139007568, "learning_rate": 0.0, "loss": 0.3806, "step": 1 }, { "epoch": 0.0002296211251435132, "grad_norm": 3.8913075923919678, "learning_rate": 2.666666666666667e-07, "loss": 0.4263, "step": 2 }, { "epoch": 0.0003444316877152698, "grad_norm": 7.592981815338135, "learning_rate": 5.333333333333335e-07, "loss": 0.4925, "step": 3 }, { "epoch": 0.0004592422502870264, "grad_norm": 9.977195739746094, "learning_rate": 8.000000000000001e-07, "loss": 0.8364, "step": 4 }, { "epoch": 0.000574052812858783, "grad_norm": 2.7648298740386963, "learning_rate": 1.066666666666667e-06, "loss": 0.5064, "step": 5 }, { "epoch": 0.0006888633754305396, "grad_norm": 4.513233661651611, "learning_rate": 1.3333333333333334e-06, "loss": 0.4164, "step": 6 }, { "epoch": 0.0008036739380022963, "grad_norm": 7.096981525421143, "learning_rate": 1.6000000000000001e-06, "loss": 0.6678, "step": 7 }, { "epoch": 0.0009184845005740528, "grad_norm": 3.0436718463897705, "learning_rate": 1.8666666666666669e-06, "loss": 0.395, "step": 8 }, { "epoch": 0.0010332950631458094, "grad_norm": 13.203910827636719, "learning_rate": 2.133333333333334e-06, "loss": 0.6548, "step": 9 }, { "epoch": 0.001148105625717566, "grad_norm": 4.292138576507568, "learning_rate": 2.4000000000000003e-06, "loss": 0.5749, "step": 10 }, { "epoch": 0.0012629161882893227, "grad_norm": 3.3945016860961914, "learning_rate": 2.666666666666667e-06, "loss": 0.6871, "step": 11 }, { "epoch": 0.0013777267508610792, "grad_norm": 1.5931885242462158, "learning_rate": 2.9333333333333338e-06, "loss": 0.4749, "step": 12 }, { "epoch": 0.0014925373134328358, "grad_norm": 1.8116573095321655, "learning_rate": 3.2000000000000003e-06, "loss": 0.4417, "step": 13 }, { "epoch": 0.0016073478760045925, "grad_norm": 1.7128000259399414, "learning_rate": 3.4666666666666672e-06, "loss": 0.4919, "step": 14 }, { "epoch": 0.001722158438576349, "grad_norm": 0.7507789731025696, "learning_rate": 3.7333333333333337e-06, "loss": 0.2455, "step": 15 }, { "epoch": 0.0018369690011481056, "grad_norm": 1.055825114250183, "learning_rate": 4.000000000000001e-06, "loss": 0.3911, "step": 16 }, { "epoch": 0.0019517795637198623, "grad_norm": 1.1022237539291382, "learning_rate": 4.266666666666668e-06, "loss": 0.462, "step": 17 }, { "epoch": 0.0020665901262916187, "grad_norm": 2.087827444076538, "learning_rate": 4.533333333333334e-06, "loss": 0.6173, "step": 18 }, { "epoch": 0.0021814006888633756, "grad_norm": 1.8250620365142822, "learning_rate": 4.800000000000001e-06, "loss": 0.6242, "step": 19 }, { "epoch": 0.002296211251435132, "grad_norm": 1.0447895526885986, "learning_rate": 5.0666666666666676e-06, "loss": 0.3643, "step": 20 }, { "epoch": 0.0024110218140068885, "grad_norm": 0.9562773704528809, "learning_rate": 5.333333333333334e-06, "loss": 0.3286, "step": 21 }, { "epoch": 0.0025258323765786454, "grad_norm": 0.9296669363975525, "learning_rate": 5.600000000000001e-06, "loss": 0.3857, "step": 22 }, { "epoch": 0.002640642939150402, "grad_norm": 1.3571704626083374, "learning_rate": 5.8666666666666675e-06, "loss": 0.4962, "step": 23 }, { "epoch": 0.0027554535017221583, "grad_norm": 0.5348429679870605, "learning_rate": 6.133333333333334e-06, "loss": 0.254, "step": 24 }, { "epoch": 0.0028702640642939152, "grad_norm": 2.2877042293548584, "learning_rate": 6.4000000000000006e-06, "loss": 0.5419, "step": 25 }, { "epoch": 0.0029850746268656717, "grad_norm": 0.5543152093887329, "learning_rate": 6.666666666666667e-06, "loss": 0.2408, "step": 26 }, { "epoch": 0.003099885189437428, "grad_norm": 0.7590405941009521, "learning_rate": 6.9333333333333344e-06, "loss": 0.2923, "step": 27 }, { "epoch": 0.003214695752009185, "grad_norm": 1.6458890438079834, "learning_rate": 7.2000000000000005e-06, "loss": 0.5484, "step": 28 }, { "epoch": 0.0033295063145809415, "grad_norm": 1.210195779800415, "learning_rate": 7.4666666666666675e-06, "loss": 0.4193, "step": 29 }, { "epoch": 0.003444316877152698, "grad_norm": 1.2205092906951904, "learning_rate": 7.733333333333334e-06, "loss": 0.3553, "step": 30 }, { "epoch": 0.003559127439724455, "grad_norm": 0.6451629996299744, "learning_rate": 8.000000000000001e-06, "loss": 0.3202, "step": 31 }, { "epoch": 0.0036739380022962113, "grad_norm": 0.7735424041748047, "learning_rate": 8.266666666666667e-06, "loss": 0.2945, "step": 32 }, { "epoch": 0.0037887485648679677, "grad_norm": 0.573767900466919, "learning_rate": 8.533333333333335e-06, "loss": 0.2871, "step": 33 }, { "epoch": 0.0039035591274397246, "grad_norm": 1.188521146774292, "learning_rate": 8.8e-06, "loss": 0.4366, "step": 34 }, { "epoch": 0.004018369690011481, "grad_norm": 0.8439204692840576, "learning_rate": 9.066666666666667e-06, "loss": 0.3997, "step": 35 }, { "epoch": 0.0041331802525832375, "grad_norm": 0.9836714863777161, "learning_rate": 9.333333333333334e-06, "loss": 0.384, "step": 36 }, { "epoch": 0.004247990815154994, "grad_norm": 0.47878584265708923, "learning_rate": 9.600000000000001e-06, "loss": 0.2524, "step": 37 }, { "epoch": 0.004362801377726751, "grad_norm": 0.6092953085899353, "learning_rate": 9.866666666666668e-06, "loss": 0.311, "step": 38 }, { "epoch": 0.004477611940298508, "grad_norm": 0.7393455505371094, "learning_rate": 1.0133333333333335e-05, "loss": 0.3905, "step": 39 }, { "epoch": 0.004592422502870264, "grad_norm": 0.4046033024787903, "learning_rate": 1.04e-05, "loss": 0.2384, "step": 40 }, { "epoch": 0.004707233065442021, "grad_norm": 0.5748854279518127, "learning_rate": 1.0666666666666667e-05, "loss": 0.3076, "step": 41 }, { "epoch": 0.004822043628013777, "grad_norm": 0.6398459076881409, "learning_rate": 1.0933333333333334e-05, "loss": 0.3592, "step": 42 }, { "epoch": 0.0049368541905855335, "grad_norm": 0.6525903344154358, "learning_rate": 1.1200000000000001e-05, "loss": 0.3123, "step": 43 }, { "epoch": 0.005051664753157291, "grad_norm": 0.6109529733657837, "learning_rate": 1.1466666666666668e-05, "loss": 0.3298, "step": 44 }, { "epoch": 0.005166475315729047, "grad_norm": 0.7033472657203674, "learning_rate": 1.1733333333333335e-05, "loss": 0.3521, "step": 45 }, { "epoch": 0.005281285878300804, "grad_norm": 0.7002931833267212, "learning_rate": 1.2e-05, "loss": 0.4087, "step": 46 }, { "epoch": 0.00539609644087256, "grad_norm": 0.5204859375953674, "learning_rate": 1.2266666666666667e-05, "loss": 0.2811, "step": 47 }, { "epoch": 0.005510907003444317, "grad_norm": 0.4176306128501892, "learning_rate": 1.2533333333333336e-05, "loss": 0.2763, "step": 48 }, { "epoch": 0.005625717566016073, "grad_norm": 0.4888947010040283, "learning_rate": 1.2800000000000001e-05, "loss": 0.2868, "step": 49 }, { "epoch": 0.0057405281285878304, "grad_norm": 0.9276270866394043, "learning_rate": 1.3066666666666668e-05, "loss": 0.2994, "step": 50 }, { "epoch": 0.005855338691159587, "grad_norm": 0.6326467394828796, "learning_rate": 1.3333333333333333e-05, "loss": 0.3199, "step": 51 }, { "epoch": 0.005970149253731343, "grad_norm": 0.3504360616207123, "learning_rate": 1.3600000000000002e-05, "loss": 0.2347, "step": 52 }, { "epoch": 0.0060849598163031, "grad_norm": 0.4200708270072937, "learning_rate": 1.3866666666666669e-05, "loss": 0.2509, "step": 53 }, { "epoch": 0.006199770378874856, "grad_norm": 0.45336952805519104, "learning_rate": 1.4133333333333334e-05, "loss": 0.2371, "step": 54 }, { "epoch": 0.006314580941446613, "grad_norm": 0.35671666264533997, "learning_rate": 1.4400000000000001e-05, "loss": 0.2415, "step": 55 }, { "epoch": 0.00642939150401837, "grad_norm": 0.5250948071479797, "learning_rate": 1.4666666666666666e-05, "loss": 0.3056, "step": 56 }, { "epoch": 0.0065442020665901265, "grad_norm": 0.4837952256202698, "learning_rate": 1.4933333333333335e-05, "loss": 0.2931, "step": 57 }, { "epoch": 0.006659012629161883, "grad_norm": 0.5181617140769958, "learning_rate": 1.5200000000000002e-05, "loss": 0.2842, "step": 58 }, { "epoch": 0.006773823191733639, "grad_norm": 0.5281972289085388, "learning_rate": 1.546666666666667e-05, "loss": 0.3035, "step": 59 }, { "epoch": 0.006888633754305396, "grad_norm": 0.36512747406959534, "learning_rate": 1.5733333333333334e-05, "loss": 0.2228, "step": 60 }, { "epoch": 0.007003444316877152, "grad_norm": 0.4627285897731781, "learning_rate": 1.6000000000000003e-05, "loss": 0.2529, "step": 61 }, { "epoch": 0.00711825487944891, "grad_norm": 0.45041096210479736, "learning_rate": 1.6266666666666668e-05, "loss": 0.277, "step": 62 }, { "epoch": 0.007233065442020666, "grad_norm": 0.6629370450973511, "learning_rate": 1.6533333333333333e-05, "loss": 0.3389, "step": 63 }, { "epoch": 0.0073478760045924225, "grad_norm": 0.4002503454685211, "learning_rate": 1.6800000000000002e-05, "loss": 0.2691, "step": 64 }, { "epoch": 0.007462686567164179, "grad_norm": 0.4418780505657196, "learning_rate": 1.706666666666667e-05, "loss": 0.2705, "step": 65 }, { "epoch": 0.007577497129735935, "grad_norm": 0.4144102931022644, "learning_rate": 1.7333333333333336e-05, "loss": 0.2539, "step": 66 }, { "epoch": 0.007692307692307693, "grad_norm": 0.40933817625045776, "learning_rate": 1.76e-05, "loss": 0.2407, "step": 67 }, { "epoch": 0.007807118254879449, "grad_norm": 0.4080236256122589, "learning_rate": 1.7866666666666666e-05, "loss": 0.2673, "step": 68 }, { "epoch": 0.007921928817451206, "grad_norm": 1.0353654623031616, "learning_rate": 1.8133333333333335e-05, "loss": 0.3984, "step": 69 }, { "epoch": 0.008036739380022962, "grad_norm": 0.5224243998527527, "learning_rate": 1.8400000000000003e-05, "loss": 0.2856, "step": 70 }, { "epoch": 0.008151549942594719, "grad_norm": 0.5813828706741333, "learning_rate": 1.866666666666667e-05, "loss": 0.2798, "step": 71 }, { "epoch": 0.008266360505166475, "grad_norm": 0.49025219678878784, "learning_rate": 1.8933333333333334e-05, "loss": 0.2916, "step": 72 }, { "epoch": 0.008381171067738231, "grad_norm": 0.4873930811882019, "learning_rate": 1.9200000000000003e-05, "loss": 0.2643, "step": 73 }, { "epoch": 0.008495981630309988, "grad_norm": 0.41233953833580017, "learning_rate": 1.9466666666666668e-05, "loss": 0.2843, "step": 74 }, { "epoch": 0.008610792192881744, "grad_norm": 0.449044406414032, "learning_rate": 1.9733333333333336e-05, "loss": 0.2704, "step": 75 }, { "epoch": 0.008725602755453503, "grad_norm": 0.40547844767570496, "learning_rate": 2e-05, "loss": 0.2443, "step": 76 }, { "epoch": 0.008840413318025259, "grad_norm": 0.4554789364337921, "learning_rate": 2.026666666666667e-05, "loss": 0.2637, "step": 77 }, { "epoch": 0.008955223880597015, "grad_norm": 0.4546657204627991, "learning_rate": 2.0533333333333336e-05, "loss": 0.2932, "step": 78 }, { "epoch": 0.009070034443168772, "grad_norm": 0.5916562676429749, "learning_rate": 2.08e-05, "loss": 0.2693, "step": 79 }, { "epoch": 0.009184845005740528, "grad_norm": 0.46502721309661865, "learning_rate": 2.1066666666666666e-05, "loss": 0.2755, "step": 80 }, { "epoch": 0.009299655568312285, "grad_norm": 0.46486786007881165, "learning_rate": 2.1333333333333335e-05, "loss": 0.2806, "step": 81 }, { "epoch": 0.009414466130884041, "grad_norm": 0.6184506416320801, "learning_rate": 2.1600000000000003e-05, "loss": 0.3257, "step": 82 }, { "epoch": 0.009529276693455798, "grad_norm": 0.4827854335308075, "learning_rate": 2.186666666666667e-05, "loss": 0.261, "step": 83 }, { "epoch": 0.009644087256027554, "grad_norm": 0.4446679353713989, "learning_rate": 2.2133333333333337e-05, "loss": 0.2467, "step": 84 }, { "epoch": 0.00975889781859931, "grad_norm": 0.5535328984260559, "learning_rate": 2.2400000000000002e-05, "loss": 0.2882, "step": 85 }, { "epoch": 0.009873708381171067, "grad_norm": 0.7976474165916443, "learning_rate": 2.2666666666666668e-05, "loss": 0.2598, "step": 86 }, { "epoch": 0.009988518943742824, "grad_norm": 0.46472394466400146, "learning_rate": 2.2933333333333336e-05, "loss": 0.2765, "step": 87 }, { "epoch": 0.010103329506314582, "grad_norm": 0.47221845388412476, "learning_rate": 2.32e-05, "loss": 0.2382, "step": 88 }, { "epoch": 0.010218140068886338, "grad_norm": 0.5940155386924744, "learning_rate": 2.346666666666667e-05, "loss": 0.3197, "step": 89 }, { "epoch": 0.010332950631458095, "grad_norm": 0.40123406052589417, "learning_rate": 2.373333333333334e-05, "loss": 0.2477, "step": 90 }, { "epoch": 0.010447761194029851, "grad_norm": 0.4947291910648346, "learning_rate": 2.4e-05, "loss": 0.2629, "step": 91 }, { "epoch": 0.010562571756601608, "grad_norm": 0.5051809549331665, "learning_rate": 2.426666666666667e-05, "loss": 0.2797, "step": 92 }, { "epoch": 0.010677382319173364, "grad_norm": 0.43634241819381714, "learning_rate": 2.4533333333333334e-05, "loss": 0.2589, "step": 93 }, { "epoch": 0.01079219288174512, "grad_norm": 0.5158872008323669, "learning_rate": 2.4800000000000003e-05, "loss": 0.2506, "step": 94 }, { "epoch": 0.010907003444316877, "grad_norm": 0.44195061922073364, "learning_rate": 2.5066666666666672e-05, "loss": 0.2722, "step": 95 }, { "epoch": 0.011021814006888633, "grad_norm": 0.4629706144332886, "learning_rate": 2.5333333333333334e-05, "loss": 0.283, "step": 96 }, { "epoch": 0.01113662456946039, "grad_norm": 0.4265854060649872, "learning_rate": 2.5600000000000002e-05, "loss": 0.2721, "step": 97 }, { "epoch": 0.011251435132032146, "grad_norm": 0.4898284077644348, "learning_rate": 2.5866666666666667e-05, "loss": 0.2694, "step": 98 }, { "epoch": 0.011366245694603904, "grad_norm": 0.4374259114265442, "learning_rate": 2.6133333333333336e-05, "loss": 0.2852, "step": 99 }, { "epoch": 0.011481056257175661, "grad_norm": 0.5207231640815735, "learning_rate": 2.6400000000000005e-05, "loss": 0.2915, "step": 100 }, { "epoch": 0.011595866819747417, "grad_norm": 0.4511289894580841, "learning_rate": 2.6666666666666667e-05, "loss": 0.2834, "step": 101 }, { "epoch": 0.011710677382319174, "grad_norm": 0.488957017660141, "learning_rate": 2.6933333333333335e-05, "loss": 0.2785, "step": 102 }, { "epoch": 0.01182548794489093, "grad_norm": 0.4487026035785675, "learning_rate": 2.7200000000000004e-05, "loss": 0.2528, "step": 103 }, { "epoch": 0.011940298507462687, "grad_norm": 0.44897618889808655, "learning_rate": 2.746666666666667e-05, "loss": 0.2628, "step": 104 }, { "epoch": 0.012055109070034443, "grad_norm": 0.43080148100852966, "learning_rate": 2.7733333333333338e-05, "loss": 0.2494, "step": 105 }, { "epoch": 0.0121699196326062, "grad_norm": 0.5693114995956421, "learning_rate": 2.8e-05, "loss": 0.3113, "step": 106 }, { "epoch": 0.012284730195177956, "grad_norm": 0.4220447838306427, "learning_rate": 2.8266666666666668e-05, "loss": 0.2639, "step": 107 }, { "epoch": 0.012399540757749712, "grad_norm": 0.5679530501365662, "learning_rate": 2.8533333333333337e-05, "loss": 0.2565, "step": 108 }, { "epoch": 0.012514351320321469, "grad_norm": 0.407787561416626, "learning_rate": 2.8800000000000002e-05, "loss": 0.2605, "step": 109 }, { "epoch": 0.012629161882893225, "grad_norm": 0.5308208465576172, "learning_rate": 2.906666666666667e-05, "loss": 0.2791, "step": 110 }, { "epoch": 0.012743972445464984, "grad_norm": 0.4562942087650299, "learning_rate": 2.9333333333333333e-05, "loss": 0.24, "step": 111 }, { "epoch": 0.01285878300803674, "grad_norm": 0.6081907749176025, "learning_rate": 2.96e-05, "loss": 0.2788, "step": 112 }, { "epoch": 0.012973593570608496, "grad_norm": 0.46708184480667114, "learning_rate": 2.986666666666667e-05, "loss": 0.2754, "step": 113 }, { "epoch": 0.013088404133180253, "grad_norm": 0.508820652961731, "learning_rate": 3.0133333333333335e-05, "loss": 0.2797, "step": 114 }, { "epoch": 0.01320321469575201, "grad_norm": 0.46585941314697266, "learning_rate": 3.0400000000000004e-05, "loss": 0.294, "step": 115 }, { "epoch": 0.013318025258323766, "grad_norm": 0.4515591859817505, "learning_rate": 3.066666666666667e-05, "loss": 0.2874, "step": 116 }, { "epoch": 0.013432835820895522, "grad_norm": 0.4152751564979553, "learning_rate": 3.093333333333334e-05, "loss": 0.2674, "step": 117 }, { "epoch": 0.013547646383467279, "grad_norm": 0.4768984913825989, "learning_rate": 3.1200000000000006e-05, "loss": 0.2854, "step": 118 }, { "epoch": 0.013662456946039035, "grad_norm": 0.49079737067222595, "learning_rate": 3.146666666666667e-05, "loss": 0.26, "step": 119 }, { "epoch": 0.013777267508610792, "grad_norm": 0.42768675088882446, "learning_rate": 3.173333333333334e-05, "loss": 0.2653, "step": 120 }, { "epoch": 0.013892078071182548, "grad_norm": 0.4565838575363159, "learning_rate": 3.2000000000000005e-05, "loss": 0.2735, "step": 121 }, { "epoch": 0.014006888633754305, "grad_norm": 0.43560558557510376, "learning_rate": 3.226666666666667e-05, "loss": 0.2566, "step": 122 }, { "epoch": 0.014121699196326063, "grad_norm": 0.40075474977493286, "learning_rate": 3.2533333333333336e-05, "loss": 0.2727, "step": 123 }, { "epoch": 0.01423650975889782, "grad_norm": 0.6167424321174622, "learning_rate": 3.28e-05, "loss": 0.2661, "step": 124 }, { "epoch": 0.014351320321469576, "grad_norm": 0.38878029584884644, "learning_rate": 3.3066666666666666e-05, "loss": 0.2392, "step": 125 }, { "epoch": 0.014466130884041332, "grad_norm": 0.5282875895500183, "learning_rate": 3.3333333333333335e-05, "loss": 0.2724, "step": 126 }, { "epoch": 0.014580941446613089, "grad_norm": 0.4426671266555786, "learning_rate": 3.3600000000000004e-05, "loss": 0.2919, "step": 127 }, { "epoch": 0.014695752009184845, "grad_norm": 0.4682052433490753, "learning_rate": 3.386666666666667e-05, "loss": 0.2709, "step": 128 }, { "epoch": 0.014810562571756601, "grad_norm": 0.48231589794158936, "learning_rate": 3.413333333333334e-05, "loss": 0.266, "step": 129 }, { "epoch": 0.014925373134328358, "grad_norm": 0.5110646486282349, "learning_rate": 3.44e-05, "loss": 0.2749, "step": 130 }, { "epoch": 0.015040183696900114, "grad_norm": 0.47816598415374756, "learning_rate": 3.466666666666667e-05, "loss": 0.2746, "step": 131 }, { "epoch": 0.01515499425947187, "grad_norm": 0.48787957429885864, "learning_rate": 3.493333333333333e-05, "loss": 0.2618, "step": 132 }, { "epoch": 0.015269804822043627, "grad_norm": 0.5045343041419983, "learning_rate": 3.52e-05, "loss": 0.2818, "step": 133 }, { "epoch": 0.015384615384615385, "grad_norm": 0.511442244052887, "learning_rate": 3.546666666666667e-05, "loss": 0.3149, "step": 134 }, { "epoch": 0.015499425947187142, "grad_norm": 0.4752333164215088, "learning_rate": 3.573333333333333e-05, "loss": 0.2633, "step": 135 }, { "epoch": 0.015614236509758898, "grad_norm": 0.48142391443252563, "learning_rate": 3.6e-05, "loss": 0.2808, "step": 136 }, { "epoch": 0.015729047072330655, "grad_norm": 0.47842082381248474, "learning_rate": 3.626666666666667e-05, "loss": 0.2776, "step": 137 }, { "epoch": 0.01584385763490241, "grad_norm": 0.45556432008743286, "learning_rate": 3.653333333333334e-05, "loss": 0.2694, "step": 138 }, { "epoch": 0.015958668197474168, "grad_norm": 0.5921466946601868, "learning_rate": 3.680000000000001e-05, "loss": 0.2977, "step": 139 }, { "epoch": 0.016073478760045924, "grad_norm": 0.48736047744750977, "learning_rate": 3.706666666666667e-05, "loss": 0.2516, "step": 140 }, { "epoch": 0.01618828932261768, "grad_norm": 0.450741708278656, "learning_rate": 3.733333333333334e-05, "loss": 0.2535, "step": 141 }, { "epoch": 0.016303099885189437, "grad_norm": 0.47981634736061096, "learning_rate": 3.76e-05, "loss": 0.2763, "step": 142 }, { "epoch": 0.016417910447761194, "grad_norm": 0.4259398877620697, "learning_rate": 3.786666666666667e-05, "loss": 0.2777, "step": 143 }, { "epoch": 0.01653272101033295, "grad_norm": 0.4857616722583771, "learning_rate": 3.8133333333333336e-05, "loss": 0.2774, "step": 144 }, { "epoch": 0.016647531572904706, "grad_norm": 0.411296010017395, "learning_rate": 3.8400000000000005e-05, "loss": 0.227, "step": 145 }, { "epoch": 0.016762342135476463, "grad_norm": 0.4133676588535309, "learning_rate": 3.866666666666667e-05, "loss": 0.2536, "step": 146 }, { "epoch": 0.01687715269804822, "grad_norm": 0.4499123692512512, "learning_rate": 3.8933333333333336e-05, "loss": 0.2973, "step": 147 }, { "epoch": 0.016991963260619976, "grad_norm": 0.4401930570602417, "learning_rate": 3.9200000000000004e-05, "loss": 0.2805, "step": 148 }, { "epoch": 0.017106773823191732, "grad_norm": 0.4711742699146271, "learning_rate": 3.946666666666667e-05, "loss": 0.2691, "step": 149 }, { "epoch": 0.01722158438576349, "grad_norm": 0.4540013074874878, "learning_rate": 3.9733333333333335e-05, "loss": 0.2617, "step": 150 }, { "epoch": 0.017336394948335245, "grad_norm": 0.42864111065864563, "learning_rate": 4e-05, "loss": 0.2686, "step": 151 }, { "epoch": 0.017451205510907005, "grad_norm": 0.5084691047668457, "learning_rate": 4.0266666666666665e-05, "loss": 0.2775, "step": 152 }, { "epoch": 0.01756601607347876, "grad_norm": 0.5258678793907166, "learning_rate": 4.053333333333334e-05, "loss": 0.2962, "step": 153 }, { "epoch": 0.017680826636050518, "grad_norm": 0.5825367569923401, "learning_rate": 4.08e-05, "loss": 0.256, "step": 154 }, { "epoch": 0.017795637198622274, "grad_norm": 0.5059462785720825, "learning_rate": 4.106666666666667e-05, "loss": 0.2616, "step": 155 }, { "epoch": 0.01791044776119403, "grad_norm": 0.4359036087989807, "learning_rate": 4.133333333333334e-05, "loss": 0.2794, "step": 156 }, { "epoch": 0.018025258323765787, "grad_norm": 0.568906843662262, "learning_rate": 4.16e-05, "loss": 0.2597, "step": 157 }, { "epoch": 0.018140068886337544, "grad_norm": 0.5774478912353516, "learning_rate": 4.186666666666667e-05, "loss": 0.2645, "step": 158 }, { "epoch": 0.0182548794489093, "grad_norm": 0.4252183437347412, "learning_rate": 4.213333333333333e-05, "loss": 0.2816, "step": 159 }, { "epoch": 0.018369690011481057, "grad_norm": 0.5592942833900452, "learning_rate": 4.240000000000001e-05, "loss": 0.2762, "step": 160 }, { "epoch": 0.018484500574052813, "grad_norm": 0.42174553871154785, "learning_rate": 4.266666666666667e-05, "loss": 0.2633, "step": 161 }, { "epoch": 0.01859931113662457, "grad_norm": 0.4636507034301758, "learning_rate": 4.293333333333333e-05, "loss": 0.2501, "step": 162 }, { "epoch": 0.018714121699196326, "grad_norm": 0.6229949593544006, "learning_rate": 4.3200000000000007e-05, "loss": 0.2656, "step": 163 }, { "epoch": 0.018828932261768083, "grad_norm": 0.5447183847427368, "learning_rate": 4.346666666666667e-05, "loss": 0.2741, "step": 164 }, { "epoch": 0.01894374282433984, "grad_norm": 0.4680737555027008, "learning_rate": 4.373333333333334e-05, "loss": 0.277, "step": 165 }, { "epoch": 0.019058553386911595, "grad_norm": 0.4614127576351166, "learning_rate": 4.4000000000000006e-05, "loss": 0.2957, "step": 166 }, { "epoch": 0.019173363949483352, "grad_norm": 0.5221275687217712, "learning_rate": 4.4266666666666674e-05, "loss": 0.2517, "step": 167 }, { "epoch": 0.01928817451205511, "grad_norm": 0.43725505471229553, "learning_rate": 4.4533333333333336e-05, "loss": 0.2852, "step": 168 }, { "epoch": 0.019402985074626865, "grad_norm": 0.46983712911605835, "learning_rate": 4.4800000000000005e-05, "loss": 0.2801, "step": 169 }, { "epoch": 0.01951779563719862, "grad_norm": 0.4980675280094147, "learning_rate": 4.506666666666667e-05, "loss": 0.2551, "step": 170 }, { "epoch": 0.019632606199770378, "grad_norm": 0.4424477815628052, "learning_rate": 4.5333333333333335e-05, "loss": 0.268, "step": 171 }, { "epoch": 0.019747416762342134, "grad_norm": 0.5206506848335266, "learning_rate": 4.56e-05, "loss": 0.2562, "step": 172 }, { "epoch": 0.01986222732491389, "grad_norm": 0.4335957467556, "learning_rate": 4.586666666666667e-05, "loss": 0.2774, "step": 173 }, { "epoch": 0.019977037887485647, "grad_norm": 0.475669801235199, "learning_rate": 4.6133333333333334e-05, "loss": 0.2896, "step": 174 }, { "epoch": 0.020091848450057407, "grad_norm": 0.4176025688648224, "learning_rate": 4.64e-05, "loss": 0.2722, "step": 175 }, { "epoch": 0.020206659012629163, "grad_norm": 0.44975805282592773, "learning_rate": 4.666666666666667e-05, "loss": 0.2918, "step": 176 }, { "epoch": 0.02032146957520092, "grad_norm": 0.4395858645439148, "learning_rate": 4.693333333333334e-05, "loss": 0.2759, "step": 177 }, { "epoch": 0.020436280137772676, "grad_norm": 0.44236308336257935, "learning_rate": 4.72e-05, "loss": 0.2617, "step": 178 }, { "epoch": 0.020551090700344433, "grad_norm": 0.39173638820648193, "learning_rate": 4.746666666666668e-05, "loss": 0.255, "step": 179 }, { "epoch": 0.02066590126291619, "grad_norm": 0.4706268310546875, "learning_rate": 4.773333333333334e-05, "loss": 0.2819, "step": 180 }, { "epoch": 0.020780711825487946, "grad_norm": 0.49181032180786133, "learning_rate": 4.8e-05, "loss": 0.2838, "step": 181 }, { "epoch": 0.020895522388059702, "grad_norm": 0.4640403985977173, "learning_rate": 4.826666666666668e-05, "loss": 0.2642, "step": 182 }, { "epoch": 0.02101033295063146, "grad_norm": 0.46434491872787476, "learning_rate": 4.853333333333334e-05, "loss": 0.2752, "step": 183 }, { "epoch": 0.021125143513203215, "grad_norm": 0.4294697344303131, "learning_rate": 4.88e-05, "loss": 0.2645, "step": 184 }, { "epoch": 0.02123995407577497, "grad_norm": 0.44099530577659607, "learning_rate": 4.906666666666667e-05, "loss": 0.2808, "step": 185 }, { "epoch": 0.021354764638346728, "grad_norm": 0.5028365850448608, "learning_rate": 4.933333333333334e-05, "loss": 0.2647, "step": 186 }, { "epoch": 0.021469575200918484, "grad_norm": 0.39111092686653137, "learning_rate": 4.9600000000000006e-05, "loss": 0.2621, "step": 187 }, { "epoch": 0.02158438576349024, "grad_norm": 0.518873929977417, "learning_rate": 4.986666666666667e-05, "loss": 0.2649, "step": 188 }, { "epoch": 0.021699196326061997, "grad_norm": 0.41855931282043457, "learning_rate": 5.0133333333333343e-05, "loss": 0.27, "step": 189 }, { "epoch": 0.021814006888633754, "grad_norm": 0.45819664001464844, "learning_rate": 5.0400000000000005e-05, "loss": 0.3021, "step": 190 }, { "epoch": 0.02192881745120551, "grad_norm": 0.4315704107284546, "learning_rate": 5.066666666666667e-05, "loss": 0.2949, "step": 191 }, { "epoch": 0.022043628013777267, "grad_norm": 0.44109687209129333, "learning_rate": 5.093333333333334e-05, "loss": 0.2927, "step": 192 }, { "epoch": 0.022158438576349023, "grad_norm": 0.48873937129974365, "learning_rate": 5.1200000000000004e-05, "loss": 0.2852, "step": 193 }, { "epoch": 0.02227324913892078, "grad_norm": 0.47601163387298584, "learning_rate": 5.1466666666666666e-05, "loss": 0.2789, "step": 194 }, { "epoch": 0.022388059701492536, "grad_norm": 0.47825050354003906, "learning_rate": 5.1733333333333335e-05, "loss": 0.2954, "step": 195 }, { "epoch": 0.022502870264064292, "grad_norm": 0.41061073541641235, "learning_rate": 5.2000000000000004e-05, "loss": 0.2572, "step": 196 }, { "epoch": 0.02261768082663605, "grad_norm": 0.485636830329895, "learning_rate": 5.226666666666667e-05, "loss": 0.2736, "step": 197 }, { "epoch": 0.02273249138920781, "grad_norm": 0.4295192360877991, "learning_rate": 5.2533333333333334e-05, "loss": 0.2737, "step": 198 }, { "epoch": 0.022847301951779565, "grad_norm": 0.5522494912147522, "learning_rate": 5.280000000000001e-05, "loss": 0.2838, "step": 199 }, { "epoch": 0.022962112514351322, "grad_norm": 0.46381303668022156, "learning_rate": 5.306666666666667e-05, "loss": 0.2808, "step": 200 }, { "epoch": 0.023076923076923078, "grad_norm": 0.4056621789932251, "learning_rate": 5.333333333333333e-05, "loss": 0.2852, "step": 201 }, { "epoch": 0.023191733639494835, "grad_norm": 0.4292871952056885, "learning_rate": 5.360000000000001e-05, "loss": 0.2789, "step": 202 }, { "epoch": 0.02330654420206659, "grad_norm": 0.3996011018753052, "learning_rate": 5.386666666666667e-05, "loss": 0.2726, "step": 203 }, { "epoch": 0.023421354764638348, "grad_norm": 0.4846571385860443, "learning_rate": 5.413333333333333e-05, "loss": 0.2637, "step": 204 }, { "epoch": 0.023536165327210104, "grad_norm": 0.4574304521083832, "learning_rate": 5.440000000000001e-05, "loss": 0.294, "step": 205 }, { "epoch": 0.02365097588978186, "grad_norm": 0.5046505331993103, "learning_rate": 5.466666666666667e-05, "loss": 0.3043, "step": 206 }, { "epoch": 0.023765786452353617, "grad_norm": 0.3981356918811798, "learning_rate": 5.493333333333334e-05, "loss": 0.2693, "step": 207 }, { "epoch": 0.023880597014925373, "grad_norm": 0.4425088167190552, "learning_rate": 5.52e-05, "loss": 0.2563, "step": 208 }, { "epoch": 0.02399540757749713, "grad_norm": 0.4056531488895416, "learning_rate": 5.5466666666666675e-05, "loss": 0.2878, "step": 209 }, { "epoch": 0.024110218140068886, "grad_norm": 0.4597301781177521, "learning_rate": 5.573333333333334e-05, "loss": 0.281, "step": 210 }, { "epoch": 0.024225028702640643, "grad_norm": 0.4437181353569031, "learning_rate": 5.6e-05, "loss": 0.2983, "step": 211 }, { "epoch": 0.0243398392652124, "grad_norm": 0.48774316906929016, "learning_rate": 5.6266666666666675e-05, "loss": 0.2842, "step": 212 }, { "epoch": 0.024454649827784156, "grad_norm": 0.4113915264606476, "learning_rate": 5.6533333333333336e-05, "loss": 0.2622, "step": 213 }, { "epoch": 0.024569460390355912, "grad_norm": 0.47580161690711975, "learning_rate": 5.6800000000000005e-05, "loss": 0.2714, "step": 214 }, { "epoch": 0.02468427095292767, "grad_norm": 0.469209760427475, "learning_rate": 5.7066666666666674e-05, "loss": 0.2859, "step": 215 }, { "epoch": 0.024799081515499425, "grad_norm": 0.42076095938682556, "learning_rate": 5.7333333333333336e-05, "loss": 0.2695, "step": 216 }, { "epoch": 0.02491389207807118, "grad_norm": 0.46103522181510925, "learning_rate": 5.7600000000000004e-05, "loss": 0.2843, "step": 217 }, { "epoch": 0.025028702640642938, "grad_norm": 0.4203872084617615, "learning_rate": 5.786666666666667e-05, "loss": 0.2823, "step": 218 }, { "epoch": 0.025143513203214694, "grad_norm": 0.5868143439292908, "learning_rate": 5.813333333333334e-05, "loss": 0.2728, "step": 219 }, { "epoch": 0.02525832376578645, "grad_norm": 0.506485641002655, "learning_rate": 5.84e-05, "loss": 0.2709, "step": 220 }, { "epoch": 0.025373134328358207, "grad_norm": 0.44142937660217285, "learning_rate": 5.8666666666666665e-05, "loss": 0.2839, "step": 221 }, { "epoch": 0.025487944890929967, "grad_norm": 0.4691295921802521, "learning_rate": 5.893333333333334e-05, "loss": 0.2805, "step": 222 }, { "epoch": 0.025602755453501724, "grad_norm": 0.4479863941669464, "learning_rate": 5.92e-05, "loss": 0.2768, "step": 223 }, { "epoch": 0.02571756601607348, "grad_norm": 0.5412651896476746, "learning_rate": 5.946666666666667e-05, "loss": 0.2763, "step": 224 }, { "epoch": 0.025832376578645237, "grad_norm": 0.5298262238502502, "learning_rate": 5.973333333333334e-05, "loss": 0.2802, "step": 225 }, { "epoch": 0.025947187141216993, "grad_norm": 0.45570307970046997, "learning_rate": 6.000000000000001e-05, "loss": 0.2707, "step": 226 }, { "epoch": 0.02606199770378875, "grad_norm": 0.4439716041088104, "learning_rate": 6.026666666666667e-05, "loss": 0.2844, "step": 227 }, { "epoch": 0.026176808266360506, "grad_norm": 0.4932538568973541, "learning_rate": 6.053333333333334e-05, "loss": 0.2789, "step": 228 }, { "epoch": 0.026291618828932262, "grad_norm": 0.45061612129211426, "learning_rate": 6.080000000000001e-05, "loss": 0.272, "step": 229 }, { "epoch": 0.02640642939150402, "grad_norm": 0.47089678049087524, "learning_rate": 6.106666666666667e-05, "loss": 0.3001, "step": 230 }, { "epoch": 0.026521239954075775, "grad_norm": 0.4241274893283844, "learning_rate": 6.133333333333334e-05, "loss": 0.2686, "step": 231 }, { "epoch": 0.02663605051664753, "grad_norm": 0.3973875343799591, "learning_rate": 6.16e-05, "loss": 0.2774, "step": 232 }, { "epoch": 0.026750861079219288, "grad_norm": 0.4524001181125641, "learning_rate": 6.186666666666668e-05, "loss": 0.2821, "step": 233 }, { "epoch": 0.026865671641791045, "grad_norm": 0.4250802993774414, "learning_rate": 6.213333333333333e-05, "loss": 0.2879, "step": 234 }, { "epoch": 0.0269804822043628, "grad_norm": 0.4055885374546051, "learning_rate": 6.240000000000001e-05, "loss": 0.2942, "step": 235 }, { "epoch": 0.027095292766934558, "grad_norm": 0.4097164273262024, "learning_rate": 6.266666666666667e-05, "loss": 0.2928, "step": 236 }, { "epoch": 0.027210103329506314, "grad_norm": 0.41655945777893066, "learning_rate": 6.293333333333334e-05, "loss": 0.2794, "step": 237 }, { "epoch": 0.02732491389207807, "grad_norm": 0.39868399500846863, "learning_rate": 6.32e-05, "loss": 0.2816, "step": 238 }, { "epoch": 0.027439724454649827, "grad_norm": 0.3869309723377228, "learning_rate": 6.346666666666667e-05, "loss": 0.2636, "step": 239 }, { "epoch": 0.027554535017221583, "grad_norm": 0.44908303022384644, "learning_rate": 6.373333333333334e-05, "loss": 0.3148, "step": 240 }, { "epoch": 0.02766934557979334, "grad_norm": 0.36232614517211914, "learning_rate": 6.400000000000001e-05, "loss": 0.2621, "step": 241 }, { "epoch": 0.027784156142365096, "grad_norm": 0.4170331358909607, "learning_rate": 6.426666666666668e-05, "loss": 0.2964, "step": 242 }, { "epoch": 0.027898966704936853, "grad_norm": 0.38571593165397644, "learning_rate": 6.453333333333333e-05, "loss": 0.2856, "step": 243 }, { "epoch": 0.02801377726750861, "grad_norm": 0.4043962359428406, "learning_rate": 6.48e-05, "loss": 0.2884, "step": 244 }, { "epoch": 0.02812858783008037, "grad_norm": 0.38627806305885315, "learning_rate": 6.506666666666667e-05, "loss": 0.2963, "step": 245 }, { "epoch": 0.028243398392652126, "grad_norm": 0.44165581464767456, "learning_rate": 6.533333333333334e-05, "loss": 0.3029, "step": 246 }, { "epoch": 0.028358208955223882, "grad_norm": 1.637535572052002, "learning_rate": 6.56e-05, "loss": 0.3371, "step": 247 }, { "epoch": 0.02847301951779564, "grad_norm": 0.4844120740890503, "learning_rate": 6.586666666666668e-05, "loss": 0.2847, "step": 248 }, { "epoch": 0.028587830080367395, "grad_norm": 0.4545106887817383, "learning_rate": 6.613333333333333e-05, "loss": 0.2962, "step": 249 }, { "epoch": 0.02870264064293915, "grad_norm": 0.40513482689857483, "learning_rate": 6.64e-05, "loss": 0.2801, "step": 250 }, { "epoch": 0.028817451205510908, "grad_norm": 0.4347420930862427, "learning_rate": 6.666666666666667e-05, "loss": 0.2934, "step": 251 }, { "epoch": 0.028932261768082664, "grad_norm": 0.4499734342098236, "learning_rate": 6.693333333333334e-05, "loss": 0.2759, "step": 252 }, { "epoch": 0.02904707233065442, "grad_norm": 0.40916556119918823, "learning_rate": 6.720000000000001e-05, "loss": 0.2837, "step": 253 }, { "epoch": 0.029161882893226177, "grad_norm": 0.43827420473098755, "learning_rate": 6.746666666666668e-05, "loss": 0.2786, "step": 254 }, { "epoch": 0.029276693455797934, "grad_norm": 0.6091927886009216, "learning_rate": 6.773333333333334e-05, "loss": 0.3383, "step": 255 }, { "epoch": 0.02939150401836969, "grad_norm": 0.4287748336791992, "learning_rate": 6.8e-05, "loss": 0.284, "step": 256 }, { "epoch": 0.029506314580941446, "grad_norm": 0.400458961725235, "learning_rate": 6.826666666666668e-05, "loss": 0.2736, "step": 257 }, { "epoch": 0.029621125143513203, "grad_norm": 0.4452756345272064, "learning_rate": 6.853333333333334e-05, "loss": 0.2936, "step": 258 }, { "epoch": 0.02973593570608496, "grad_norm": 0.40402495861053467, "learning_rate": 6.88e-05, "loss": 0.2899, "step": 259 }, { "epoch": 0.029850746268656716, "grad_norm": 0.440560519695282, "learning_rate": 6.906666666666667e-05, "loss": 0.2561, "step": 260 }, { "epoch": 0.029965556831228472, "grad_norm": 0.4526638090610504, "learning_rate": 6.933333333333334e-05, "loss": 0.3013, "step": 261 }, { "epoch": 0.03008036739380023, "grad_norm": 0.39907002449035645, "learning_rate": 6.960000000000001e-05, "loss": 0.2846, "step": 262 }, { "epoch": 0.030195177956371985, "grad_norm": 0.4190822243690491, "learning_rate": 6.986666666666667e-05, "loss": 0.2797, "step": 263 }, { "epoch": 0.03030998851894374, "grad_norm": 0.4113008677959442, "learning_rate": 7.013333333333335e-05, "loss": 0.2782, "step": 264 }, { "epoch": 0.030424799081515498, "grad_norm": 0.4656916558742523, "learning_rate": 7.04e-05, "loss": 0.3262, "step": 265 }, { "epoch": 0.030539609644087255, "grad_norm": 0.4758545756340027, "learning_rate": 7.066666666666667e-05, "loss": 0.2823, "step": 266 }, { "epoch": 0.03065442020665901, "grad_norm": 0.43197929859161377, "learning_rate": 7.093333333333334e-05, "loss": 0.3119, "step": 267 }, { "epoch": 0.03076923076923077, "grad_norm": 0.46504074335098267, "learning_rate": 7.120000000000001e-05, "loss": 0.2909, "step": 268 }, { "epoch": 0.030884041331802527, "grad_norm": 0.4777301251888275, "learning_rate": 7.146666666666666e-05, "loss": 0.2875, "step": 269 }, { "epoch": 0.030998851894374284, "grad_norm": 0.4271126985549927, "learning_rate": 7.173333333333333e-05, "loss": 0.2903, "step": 270 }, { "epoch": 0.03111366245694604, "grad_norm": 0.5265456438064575, "learning_rate": 7.2e-05, "loss": 0.3031, "step": 271 }, { "epoch": 0.031228473019517797, "grad_norm": 0.4860847592353821, "learning_rate": 7.226666666666667e-05, "loss": 0.281, "step": 272 }, { "epoch": 0.03134328358208955, "grad_norm": 0.4602312445640564, "learning_rate": 7.253333333333334e-05, "loss": 0.2781, "step": 273 }, { "epoch": 0.03145809414466131, "grad_norm": 0.49675124883651733, "learning_rate": 7.280000000000001e-05, "loss": 0.2833, "step": 274 }, { "epoch": 0.03157290470723306, "grad_norm": 0.4255964159965515, "learning_rate": 7.306666666666668e-05, "loss": 0.2882, "step": 275 }, { "epoch": 0.03168771526980482, "grad_norm": 0.5098394155502319, "learning_rate": 7.333333333333333e-05, "loss": 0.2964, "step": 276 }, { "epoch": 0.031802525832376576, "grad_norm": 0.4089719355106354, "learning_rate": 7.360000000000001e-05, "loss": 0.2871, "step": 277 }, { "epoch": 0.031917336394948335, "grad_norm": 0.4289206266403198, "learning_rate": 7.386666666666667e-05, "loss": 0.2892, "step": 278 }, { "epoch": 0.03203214695752009, "grad_norm": 0.4785822629928589, "learning_rate": 7.413333333333334e-05, "loss": 0.2797, "step": 279 }, { "epoch": 0.03214695752009185, "grad_norm": 0.35977521538734436, "learning_rate": 7.44e-05, "loss": 0.2882, "step": 280 }, { "epoch": 0.03226176808266361, "grad_norm": 0.4253532588481903, "learning_rate": 7.466666666666667e-05, "loss": 0.2777, "step": 281 }, { "epoch": 0.03237657864523536, "grad_norm": 0.3956088721752167, "learning_rate": 7.493333333333334e-05, "loss": 0.295, "step": 282 }, { "epoch": 0.03249138920780712, "grad_norm": 0.3870704770088196, "learning_rate": 7.52e-05, "loss": 0.3057, "step": 283 }, { "epoch": 0.032606199770378874, "grad_norm": 0.42614811658859253, "learning_rate": 7.546666666666668e-05, "loss": 0.3192, "step": 284 }, { "epoch": 0.032721010332950634, "grad_norm": 0.3956279754638672, "learning_rate": 7.573333333333334e-05, "loss": 0.3024, "step": 285 }, { "epoch": 0.03283582089552239, "grad_norm": 0.4158157408237457, "learning_rate": 7.6e-05, "loss": 0.2832, "step": 286 }, { "epoch": 0.03295063145809415, "grad_norm": 0.41814324259757996, "learning_rate": 7.626666666666667e-05, "loss": 0.2951, "step": 287 }, { "epoch": 0.0330654420206659, "grad_norm": 0.4744579792022705, "learning_rate": 7.653333333333334e-05, "loss": 0.2809, "step": 288 }, { "epoch": 0.03318025258323766, "grad_norm": 0.444934606552124, "learning_rate": 7.680000000000001e-05, "loss": 0.2941, "step": 289 }, { "epoch": 0.03329506314580941, "grad_norm": 0.41019725799560547, "learning_rate": 7.706666666666668e-05, "loss": 0.2854, "step": 290 }, { "epoch": 0.03340987370838117, "grad_norm": 0.4355992376804352, "learning_rate": 7.733333333333333e-05, "loss": 0.2788, "step": 291 }, { "epoch": 0.033524684270952926, "grad_norm": 0.3505465090274811, "learning_rate": 7.76e-05, "loss": 0.2855, "step": 292 }, { "epoch": 0.033639494833524686, "grad_norm": 0.3989941477775574, "learning_rate": 7.786666666666667e-05, "loss": 0.2806, "step": 293 }, { "epoch": 0.03375430539609644, "grad_norm": 0.40356773138046265, "learning_rate": 7.813333333333334e-05, "loss": 0.2798, "step": 294 }, { "epoch": 0.0338691159586682, "grad_norm": 0.3574153780937195, "learning_rate": 7.840000000000001e-05, "loss": 0.2741, "step": 295 }, { "epoch": 0.03398392652123995, "grad_norm": 0.3971838355064392, "learning_rate": 7.866666666666666e-05, "loss": 0.2866, "step": 296 }, { "epoch": 0.03409873708381171, "grad_norm": 0.436036616563797, "learning_rate": 7.893333333333335e-05, "loss": 0.3065, "step": 297 }, { "epoch": 0.034213547646383465, "grad_norm": 0.3779606223106384, "learning_rate": 7.92e-05, "loss": 0.2846, "step": 298 }, { "epoch": 0.034328358208955224, "grad_norm": 0.3872717022895813, "learning_rate": 7.946666666666667e-05, "loss": 0.2862, "step": 299 }, { "epoch": 0.03444316877152698, "grad_norm": 0.43725553154945374, "learning_rate": 7.973333333333334e-05, "loss": 0.2951, "step": 300 }, { "epoch": 0.03455797933409874, "grad_norm": 0.356347918510437, "learning_rate": 8e-05, "loss": 0.2935, "step": 301 }, { "epoch": 0.03467278989667049, "grad_norm": 0.8948638439178467, "learning_rate": 7.999997292289908e-05, "loss": 0.2963, "step": 302 }, { "epoch": 0.03478760045924225, "grad_norm": 0.3820602595806122, "learning_rate": 7.999989169163296e-05, "loss": 0.2601, "step": 303 }, { "epoch": 0.03490241102181401, "grad_norm": 0.39433401823043823, "learning_rate": 7.999975630631162e-05, "loss": 0.2926, "step": 304 }, { "epoch": 0.03501722158438576, "grad_norm": 0.43034827709198, "learning_rate": 7.999956676711836e-05, "loss": 0.2677, "step": 305 }, { "epoch": 0.03513203214695752, "grad_norm": 0.3636143207550049, "learning_rate": 7.999932307430978e-05, "loss": 0.2717, "step": 306 }, { "epoch": 0.035246842709529276, "grad_norm": 0.4332137703895569, "learning_rate": 7.999902522821579e-05, "loss": 0.2879, "step": 307 }, { "epoch": 0.035361653272101036, "grad_norm": 0.3877200484275818, "learning_rate": 7.999867322923968e-05, "loss": 0.3249, "step": 308 }, { "epoch": 0.03547646383467279, "grad_norm": 0.380856454372406, "learning_rate": 7.999826707785793e-05, "loss": 0.3012, "step": 309 }, { "epoch": 0.03559127439724455, "grad_norm": 0.4009133577346802, "learning_rate": 7.99978067746205e-05, "loss": 0.2987, "step": 310 }, { "epoch": 0.0357060849598163, "grad_norm": 0.37173283100128174, "learning_rate": 7.99972923201505e-05, "loss": 0.2891, "step": 311 }, { "epoch": 0.03582089552238806, "grad_norm": 0.3623278737068176, "learning_rate": 7.999672371514445e-05, "loss": 0.2865, "step": 312 }, { "epoch": 0.035935706084959815, "grad_norm": 0.4112582206726074, "learning_rate": 7.999610096037218e-05, "loss": 0.3105, "step": 313 }, { "epoch": 0.036050516647531575, "grad_norm": 0.3769770860671997, "learning_rate": 7.999542405667677e-05, "loss": 0.2984, "step": 314 }, { "epoch": 0.03616532721010333, "grad_norm": 0.43831536173820496, "learning_rate": 7.999469300497469e-05, "loss": 0.3147, "step": 315 }, { "epoch": 0.03628013777267509, "grad_norm": 0.42567816376686096, "learning_rate": 7.999390780625566e-05, "loss": 0.289, "step": 316 }, { "epoch": 0.03639494833524684, "grad_norm": 0.3818572163581848, "learning_rate": 7.999306846158272e-05, "loss": 0.2795, "step": 317 }, { "epoch": 0.0365097588978186, "grad_norm": 0.38739144802093506, "learning_rate": 7.999217497209222e-05, "loss": 0.3005, "step": 318 }, { "epoch": 0.036624569460390353, "grad_norm": 0.3966415226459503, "learning_rate": 7.999122733899382e-05, "loss": 0.289, "step": 319 }, { "epoch": 0.03673938002296211, "grad_norm": 0.34615907073020935, "learning_rate": 7.999022556357049e-05, "loss": 0.3159, "step": 320 }, { "epoch": 0.036854190585533866, "grad_norm": 0.4294341206550598, "learning_rate": 7.998916964717848e-05, "loss": 0.2843, "step": 321 }, { "epoch": 0.036969001148105626, "grad_norm": 0.32626432180404663, "learning_rate": 7.998805959124734e-05, "loss": 0.267, "step": 322 }, { "epoch": 0.03708381171067738, "grad_norm": 0.3907291889190674, "learning_rate": 7.998689539727991e-05, "loss": 0.2968, "step": 323 }, { "epoch": 0.03719862227324914, "grad_norm": 0.3535075783729553, "learning_rate": 7.998567706685239e-05, "loss": 0.2848, "step": 324 }, { "epoch": 0.03731343283582089, "grad_norm": 0.3844582438468933, "learning_rate": 7.998440460161417e-05, "loss": 0.2899, "step": 325 }, { "epoch": 0.03742824339839265, "grad_norm": 0.3149040639400482, "learning_rate": 7.998307800328803e-05, "loss": 0.2772, "step": 326 }, { "epoch": 0.03754305396096441, "grad_norm": 0.3481247127056122, "learning_rate": 7.998169727366996e-05, "loss": 0.2783, "step": 327 }, { "epoch": 0.037657864523536165, "grad_norm": 0.35045212507247925, "learning_rate": 7.998026241462927e-05, "loss": 0.3072, "step": 328 }, { "epoch": 0.037772675086107925, "grad_norm": 0.3261767029762268, "learning_rate": 7.997877342810856e-05, "loss": 0.292, "step": 329 }, { "epoch": 0.03788748564867968, "grad_norm": 0.36095619201660156, "learning_rate": 7.99772303161237e-05, "loss": 0.2808, "step": 330 }, { "epoch": 0.03800229621125144, "grad_norm": 0.3843364119529724, "learning_rate": 7.997563308076384e-05, "loss": 0.3148, "step": 331 }, { "epoch": 0.03811710677382319, "grad_norm": 0.3901238739490509, "learning_rate": 7.99739817241914e-05, "loss": 0.2994, "step": 332 }, { "epoch": 0.03823191733639495, "grad_norm": 0.33234620094299316, "learning_rate": 7.997227624864208e-05, "loss": 0.2958, "step": 333 }, { "epoch": 0.038346727898966704, "grad_norm": 0.371768981218338, "learning_rate": 7.997051665642485e-05, "loss": 0.2776, "step": 334 }, { "epoch": 0.038461538461538464, "grad_norm": 0.35283026099205017, "learning_rate": 7.996870294992195e-05, "loss": 0.2932, "step": 335 }, { "epoch": 0.03857634902411022, "grad_norm": 0.3671194314956665, "learning_rate": 7.996683513158886e-05, "loss": 0.3201, "step": 336 }, { "epoch": 0.03869115958668198, "grad_norm": 0.3604862093925476, "learning_rate": 7.996491320395435e-05, "loss": 0.2943, "step": 337 }, { "epoch": 0.03880597014925373, "grad_norm": 0.37766873836517334, "learning_rate": 7.996293716962041e-05, "loss": 0.2844, "step": 338 }, { "epoch": 0.03892078071182549, "grad_norm": 0.3744168281555176, "learning_rate": 7.996090703126233e-05, "loss": 0.2909, "step": 339 }, { "epoch": 0.03903559127439724, "grad_norm": 0.38280361890792847, "learning_rate": 7.99588227916286e-05, "loss": 0.3156, "step": 340 }, { "epoch": 0.039150401836969, "grad_norm": 0.35670557618141174, "learning_rate": 7.9956684453541e-05, "loss": 0.2984, "step": 341 }, { "epoch": 0.039265212399540755, "grad_norm": 0.4166824221611023, "learning_rate": 7.99544920198945e-05, "loss": 0.347, "step": 342 }, { "epoch": 0.039380022962112515, "grad_norm": 0.3501390814781189, "learning_rate": 7.995224549365737e-05, "loss": 0.2917, "step": 343 }, { "epoch": 0.03949483352468427, "grad_norm": 0.37670186161994934, "learning_rate": 7.994994487787106e-05, "loss": 0.2982, "step": 344 }, { "epoch": 0.03960964408725603, "grad_norm": 0.3371063768863678, "learning_rate": 7.994759017565028e-05, "loss": 0.2869, "step": 345 }, { "epoch": 0.03972445464982778, "grad_norm": 0.46586692333221436, "learning_rate": 7.994518139018295e-05, "loss": 0.2964, "step": 346 }, { "epoch": 0.03983926521239954, "grad_norm": 0.3734179139137268, "learning_rate": 7.994271852473023e-05, "loss": 0.2964, "step": 347 }, { "epoch": 0.039954075774971294, "grad_norm": 0.37735623121261597, "learning_rate": 7.994020158262647e-05, "loss": 0.3108, "step": 348 }, { "epoch": 0.040068886337543054, "grad_norm": 0.3557949662208557, "learning_rate": 7.993763056727925e-05, "loss": 0.2955, "step": 349 }, { "epoch": 0.040183696900114814, "grad_norm": 0.36162814497947693, "learning_rate": 7.993500548216934e-05, "loss": 0.2783, "step": 350 }, { "epoch": 0.04029850746268657, "grad_norm": 0.3607986569404602, "learning_rate": 7.993232633085074e-05, "loss": 0.2823, "step": 351 }, { "epoch": 0.04041331802525833, "grad_norm": 0.3682713508605957, "learning_rate": 7.992959311695063e-05, "loss": 0.3012, "step": 352 }, { "epoch": 0.04052812858783008, "grad_norm": 0.30396944284439087, "learning_rate": 7.992680584416935e-05, "loss": 0.2845, "step": 353 }, { "epoch": 0.04064293915040184, "grad_norm": 0.3532613515853882, "learning_rate": 7.992396451628052e-05, "loss": 0.2929, "step": 354 }, { "epoch": 0.04075774971297359, "grad_norm": 0.2987546920776367, "learning_rate": 7.992106913713087e-05, "loss": 0.2863, "step": 355 }, { "epoch": 0.04087256027554535, "grad_norm": 0.38308921456336975, "learning_rate": 7.99181197106403e-05, "loss": 0.3133, "step": 356 }, { "epoch": 0.040987370838117106, "grad_norm": 0.3386363983154297, "learning_rate": 7.991511624080193e-05, "loss": 0.2816, "step": 357 }, { "epoch": 0.041102181400688866, "grad_norm": 0.3404191732406616, "learning_rate": 7.991205873168201e-05, "loss": 0.2752, "step": 358 }, { "epoch": 0.04121699196326062, "grad_norm": 0.38124004006385803, "learning_rate": 7.990894718741996e-05, "loss": 0.3033, "step": 359 }, { "epoch": 0.04133180252583238, "grad_norm": 0.3667595088481903, "learning_rate": 7.990578161222838e-05, "loss": 0.3048, "step": 360 }, { "epoch": 0.04144661308840413, "grad_norm": 0.3961997628211975, "learning_rate": 7.990256201039297e-05, "loss": 0.2723, "step": 361 }, { "epoch": 0.04156142365097589, "grad_norm": 0.42362603545188904, "learning_rate": 7.989928838627263e-05, "loss": 0.2984, "step": 362 }, { "epoch": 0.041676234213547644, "grad_norm": 0.34573492407798767, "learning_rate": 7.989596074429938e-05, "loss": 0.2889, "step": 363 }, { "epoch": 0.041791044776119404, "grad_norm": 0.4025217890739441, "learning_rate": 7.989257908897832e-05, "loss": 0.2795, "step": 364 }, { "epoch": 0.04190585533869116, "grad_norm": 0.3822268545627594, "learning_rate": 7.988914342488778e-05, "loss": 0.2925, "step": 365 }, { "epoch": 0.04202066590126292, "grad_norm": 0.3863513767719269, "learning_rate": 7.988565375667911e-05, "loss": 0.2522, "step": 366 }, { "epoch": 0.04213547646383467, "grad_norm": 0.4024246037006378, "learning_rate": 7.988211008907682e-05, "loss": 0.3088, "step": 367 }, { "epoch": 0.04225028702640643, "grad_norm": 0.4433460533618927, "learning_rate": 7.987851242687853e-05, "loss": 0.2843, "step": 368 }, { "epoch": 0.04236509758897818, "grad_norm": 0.41438233852386475, "learning_rate": 7.987486077495495e-05, "loss": 0.3199, "step": 369 }, { "epoch": 0.04247990815154994, "grad_norm": 0.38879531621932983, "learning_rate": 7.98711551382499e-05, "loss": 0.2909, "step": 370 }, { "epoch": 0.042594718714121696, "grad_norm": 0.4411541521549225, "learning_rate": 7.986739552178024e-05, "loss": 0.2825, "step": 371 }, { "epoch": 0.042709529276693456, "grad_norm": 0.3692376911640167, "learning_rate": 7.9863581930636e-05, "loss": 0.2966, "step": 372 }, { "epoch": 0.042824339839265216, "grad_norm": 0.4238465130329132, "learning_rate": 7.985971436998019e-05, "loss": 0.2895, "step": 373 }, { "epoch": 0.04293915040183697, "grad_norm": 0.43632417917251587, "learning_rate": 7.985579284504893e-05, "loss": 0.3001, "step": 374 }, { "epoch": 0.04305396096440873, "grad_norm": 0.3809247612953186, "learning_rate": 7.98518173611514e-05, "loss": 0.3089, "step": 375 }, { "epoch": 0.04316877152698048, "grad_norm": 0.38957175612449646, "learning_rate": 7.984778792366983e-05, "loss": 0.3176, "step": 376 }, { "epoch": 0.04328358208955224, "grad_norm": 0.34312862157821655, "learning_rate": 7.98437045380595e-05, "loss": 0.2791, "step": 377 }, { "epoch": 0.043398392652123995, "grad_norm": 0.37851688265800476, "learning_rate": 7.983956720984872e-05, "loss": 0.2599, "step": 378 }, { "epoch": 0.043513203214695755, "grad_norm": 0.34156009554862976, "learning_rate": 7.983537594463882e-05, "loss": 0.3011, "step": 379 }, { "epoch": 0.04362801377726751, "grad_norm": 0.347479909658432, "learning_rate": 7.983113074810419e-05, "loss": 0.2874, "step": 380 }, { "epoch": 0.04374282433983927, "grad_norm": 0.3354409635066986, "learning_rate": 7.982683162599218e-05, "loss": 0.309, "step": 381 }, { "epoch": 0.04385763490241102, "grad_norm": 0.3754551112651825, "learning_rate": 7.98224785841232e-05, "loss": 0.2904, "step": 382 }, { "epoch": 0.04397244546498278, "grad_norm": 0.35428735613822937, "learning_rate": 7.981807162839065e-05, "loss": 0.2925, "step": 383 }, { "epoch": 0.04408725602755453, "grad_norm": 0.3400973379611969, "learning_rate": 7.981361076476087e-05, "loss": 0.2878, "step": 384 }, { "epoch": 0.04420206659012629, "grad_norm": 0.37643805146217346, "learning_rate": 7.980909599927325e-05, "loss": 0.296, "step": 385 }, { "epoch": 0.044316877152698046, "grad_norm": 0.3097022473812103, "learning_rate": 7.980452733804013e-05, "loss": 0.2832, "step": 386 }, { "epoch": 0.044431687715269806, "grad_norm": 0.3729180693626404, "learning_rate": 7.97999047872468e-05, "loss": 0.3018, "step": 387 }, { "epoch": 0.04454649827784156, "grad_norm": 0.35724395513534546, "learning_rate": 7.979522835315154e-05, "loss": 0.2906, "step": 388 }, { "epoch": 0.04466130884041332, "grad_norm": 0.34398120641708374, "learning_rate": 7.979049804208554e-05, "loss": 0.2826, "step": 389 }, { "epoch": 0.04477611940298507, "grad_norm": 0.37519389390945435, "learning_rate": 7.978571386045298e-05, "loss": 0.2908, "step": 390 }, { "epoch": 0.04489092996555683, "grad_norm": 0.3428660035133362, "learning_rate": 7.978087581473094e-05, "loss": 0.2774, "step": 391 }, { "epoch": 0.045005740528128585, "grad_norm": 0.33966898918151855, "learning_rate": 7.977598391146943e-05, "loss": 0.3062, "step": 392 }, { "epoch": 0.045120551090700345, "grad_norm": 0.3086089789867401, "learning_rate": 7.977103815729138e-05, "loss": 0.289, "step": 393 }, { "epoch": 0.0452353616532721, "grad_norm": 0.35524773597717285, "learning_rate": 7.976603855889262e-05, "loss": 0.2973, "step": 394 }, { "epoch": 0.04535017221584386, "grad_norm": 0.30744922161102295, "learning_rate": 7.976098512304189e-05, "loss": 0.2826, "step": 395 }, { "epoch": 0.04546498277841562, "grad_norm": 0.348548948764801, "learning_rate": 7.97558778565808e-05, "loss": 0.2905, "step": 396 }, { "epoch": 0.04557979334098737, "grad_norm": 0.3618229031562805, "learning_rate": 7.975071676642386e-05, "loss": 0.3124, "step": 397 }, { "epoch": 0.04569460390355913, "grad_norm": 0.3485078513622284, "learning_rate": 7.974550185955843e-05, "loss": 0.2942, "step": 398 }, { "epoch": 0.045809414466130884, "grad_norm": 0.37058359384536743, "learning_rate": 7.974023314304474e-05, "loss": 0.3024, "step": 399 }, { "epoch": 0.045924225028702644, "grad_norm": 0.4022071063518524, "learning_rate": 7.973491062401586e-05, "loss": 0.2975, "step": 400 }, { "epoch": 0.046039035591274396, "grad_norm": 0.3409278392791748, "learning_rate": 7.972953430967773e-05, "loss": 0.2809, "step": 401 }, { "epoch": 0.046153846153846156, "grad_norm": 0.34757736325263977, "learning_rate": 7.972410420730908e-05, "loss": 0.2753, "step": 402 }, { "epoch": 0.04626865671641791, "grad_norm": 0.3405095934867859, "learning_rate": 7.971862032426148e-05, "loss": 0.2911, "step": 403 }, { "epoch": 0.04638346727898967, "grad_norm": 0.3655739426612854, "learning_rate": 7.971308266795934e-05, "loss": 0.3149, "step": 404 }, { "epoch": 0.04649827784156142, "grad_norm": 0.3317274749279022, "learning_rate": 7.970749124589981e-05, "loss": 0.2902, "step": 405 }, { "epoch": 0.04661308840413318, "grad_norm": 0.3208948075771332, "learning_rate": 7.97018460656529e-05, "loss": 0.2944, "step": 406 }, { "epoch": 0.046727898966704935, "grad_norm": 0.3960399031639099, "learning_rate": 7.969614713486132e-05, "loss": 0.2863, "step": 407 }, { "epoch": 0.046842709529276695, "grad_norm": 0.35129788517951965, "learning_rate": 7.969039446124063e-05, "loss": 0.3032, "step": 408 }, { "epoch": 0.04695752009184845, "grad_norm": 0.31074246764183044, "learning_rate": 7.968458805257913e-05, "loss": 0.2896, "step": 409 }, { "epoch": 0.04707233065442021, "grad_norm": 0.3169695734977722, "learning_rate": 7.967872791673781e-05, "loss": 0.2693, "step": 410 }, { "epoch": 0.04718714121699196, "grad_norm": 0.3128400146961212, "learning_rate": 7.967281406165047e-05, "loss": 0.282, "step": 411 }, { "epoch": 0.04730195177956372, "grad_norm": 0.30382081866264343, "learning_rate": 7.966684649532362e-05, "loss": 0.2926, "step": 412 }, { "epoch": 0.047416762342135474, "grad_norm": 0.42439278960227966, "learning_rate": 7.966082522583647e-05, "loss": 0.2975, "step": 413 }, { "epoch": 0.047531572904707234, "grad_norm": 0.34722965955734253, "learning_rate": 7.965475026134095e-05, "loss": 0.307, "step": 414 }, { "epoch": 0.04764638346727899, "grad_norm": 0.30934587121009827, "learning_rate": 7.964862161006168e-05, "loss": 0.2833, "step": 415 }, { "epoch": 0.04776119402985075, "grad_norm": 0.34362125396728516, "learning_rate": 7.964243928029594e-05, "loss": 0.2732, "step": 416 }, { "epoch": 0.0478760045924225, "grad_norm": 0.3408171832561493, "learning_rate": 7.963620328041376e-05, "loss": 0.2878, "step": 417 }, { "epoch": 0.04799081515499426, "grad_norm": 0.38200417160987854, "learning_rate": 7.962991361885775e-05, "loss": 0.2969, "step": 418 }, { "epoch": 0.04810562571756601, "grad_norm": 0.3307928144931793, "learning_rate": 7.962357030414319e-05, "loss": 0.2952, "step": 419 }, { "epoch": 0.04822043628013777, "grad_norm": 0.3471834659576416, "learning_rate": 7.961717334485803e-05, "loss": 0.2933, "step": 420 }, { "epoch": 0.04833524684270953, "grad_norm": 0.3624359369277954, "learning_rate": 7.961072274966282e-05, "loss": 0.2998, "step": 421 }, { "epoch": 0.048450057405281285, "grad_norm": 0.32929471135139465, "learning_rate": 7.960421852729072e-05, "loss": 0.3265, "step": 422 }, { "epoch": 0.048564867967853045, "grad_norm": 0.33353182673454285, "learning_rate": 7.959766068654752e-05, "loss": 0.2733, "step": 423 }, { "epoch": 0.0486796785304248, "grad_norm": 0.3401751220226288, "learning_rate": 7.959104923631157e-05, "loss": 0.3066, "step": 424 }, { "epoch": 0.04879448909299656, "grad_norm": 0.401660680770874, "learning_rate": 7.958438418553383e-05, "loss": 0.2947, "step": 425 }, { "epoch": 0.04890929965556831, "grad_norm": 0.325874388217926, "learning_rate": 7.957766554323778e-05, "loss": 0.2854, "step": 426 }, { "epoch": 0.04902411021814007, "grad_norm": 0.7577797174453735, "learning_rate": 7.957089331851954e-05, "loss": 0.3151, "step": 427 }, { "epoch": 0.049138920780711824, "grad_norm": 0.33827289938926697, "learning_rate": 7.956406752054769e-05, "loss": 0.2835, "step": 428 }, { "epoch": 0.049253731343283584, "grad_norm": 0.44211405515670776, "learning_rate": 7.955718815856337e-05, "loss": 0.2892, "step": 429 }, { "epoch": 0.04936854190585534, "grad_norm": 0.5116203427314758, "learning_rate": 7.955025524188024e-05, "loss": 0.2756, "step": 430 }, { "epoch": 0.0494833524684271, "grad_norm": 0.379065603017807, "learning_rate": 7.954326877988446e-05, "loss": 0.2967, "step": 431 }, { "epoch": 0.04959816303099885, "grad_norm": 0.40263864398002625, "learning_rate": 7.953622878203473e-05, "loss": 0.2679, "step": 432 }, { "epoch": 0.04971297359357061, "grad_norm": 0.3296280801296234, "learning_rate": 7.952913525786212e-05, "loss": 0.3341, "step": 433 }, { "epoch": 0.04982778415614236, "grad_norm": 0.3951963782310486, "learning_rate": 7.952198821697026e-05, "loss": 0.3151, "step": 434 }, { "epoch": 0.04994259471871412, "grad_norm": 0.34571677446365356, "learning_rate": 7.951478766903525e-05, "loss": 0.3094, "step": 435 }, { "epoch": 0.050057405281285876, "grad_norm": 0.34958407282829285, "learning_rate": 7.950753362380551e-05, "loss": 0.3028, "step": 436 }, { "epoch": 0.050172215843857636, "grad_norm": 0.35667264461517334, "learning_rate": 7.950022609110202e-05, "loss": 0.3175, "step": 437 }, { "epoch": 0.05028702640642939, "grad_norm": 0.3435575067996979, "learning_rate": 7.949286508081811e-05, "loss": 0.33, "step": 438 }, { "epoch": 0.05040183696900115, "grad_norm": 0.32700541615486145, "learning_rate": 7.948545060291952e-05, "loss": 0.3061, "step": 439 }, { "epoch": 0.0505166475315729, "grad_norm": 0.3278663754463196, "learning_rate": 7.947798266744438e-05, "loss": 0.2878, "step": 440 }, { "epoch": 0.05063145809414466, "grad_norm": 0.31108394265174866, "learning_rate": 7.947046128450319e-05, "loss": 0.2829, "step": 441 }, { "epoch": 0.050746268656716415, "grad_norm": 0.32764360308647156, "learning_rate": 7.946288646427878e-05, "loss": 0.2915, "step": 442 }, { "epoch": 0.050861079219288174, "grad_norm": 0.9800124764442444, "learning_rate": 7.94552582170264e-05, "loss": 0.2798, "step": 443 }, { "epoch": 0.050975889781859934, "grad_norm": 0.3105125427246094, "learning_rate": 7.944757655307361e-05, "loss": 0.2963, "step": 444 }, { "epoch": 0.05109070034443169, "grad_norm": 0.28933587670326233, "learning_rate": 7.94398414828202e-05, "loss": 0.2848, "step": 445 }, { "epoch": 0.05120551090700345, "grad_norm": 0.5111425518989563, "learning_rate": 7.943205301673839e-05, "loss": 0.2765, "step": 446 }, { "epoch": 0.0513203214695752, "grad_norm": 0.3153950572013855, "learning_rate": 7.942421116537261e-05, "loss": 0.3085, "step": 447 }, { "epoch": 0.05143513203214696, "grad_norm": 0.32123759388923645, "learning_rate": 7.941631593933962e-05, "loss": 0.2954, "step": 448 }, { "epoch": 0.05154994259471871, "grad_norm": 3.8212127685546875, "learning_rate": 7.940836734932836e-05, "loss": 0.3181, "step": 449 }, { "epoch": 0.05166475315729047, "grad_norm": 0.3960025906562805, "learning_rate": 7.940036540610012e-05, "loss": 0.2961, "step": 450 }, { "epoch": 0.051779563719862226, "grad_norm": 0.3273251950740814, "learning_rate": 7.939231012048833e-05, "loss": 0.2922, "step": 451 }, { "epoch": 0.051894374282433986, "grad_norm": 2.9411025047302246, "learning_rate": 7.93842015033987e-05, "loss": 0.3258, "step": 452 }, { "epoch": 0.05200918484500574, "grad_norm": 0.4367799758911133, "learning_rate": 7.937603956580912e-05, "loss": 0.3109, "step": 453 }, { "epoch": 0.0521239954075775, "grad_norm": 0.3471544086933136, "learning_rate": 7.936782431876968e-05, "loss": 0.3032, "step": 454 }, { "epoch": 0.05223880597014925, "grad_norm": 0.3938736915588379, "learning_rate": 7.935955577340262e-05, "loss": 0.3094, "step": 455 }, { "epoch": 0.05235361653272101, "grad_norm": 0.3470355272293091, "learning_rate": 7.935123394090236e-05, "loss": 0.2775, "step": 456 }, { "epoch": 0.052468427095292765, "grad_norm": 0.33648693561553955, "learning_rate": 7.934285883253544e-05, "loss": 0.2802, "step": 457 }, { "epoch": 0.052583237657864525, "grad_norm": 0.3747243881225586, "learning_rate": 7.933443045964056e-05, "loss": 0.3035, "step": 458 }, { "epoch": 0.05269804822043628, "grad_norm": 0.28609880805015564, "learning_rate": 7.93259488336285e-05, "loss": 0.2697, "step": 459 }, { "epoch": 0.05281285878300804, "grad_norm": 0.3929007947444916, "learning_rate": 7.931741396598218e-05, "loss": 0.3141, "step": 460 }, { "epoch": 0.05292766934557979, "grad_norm": 0.342237263917923, "learning_rate": 7.930882586825653e-05, "loss": 0.3009, "step": 461 }, { "epoch": 0.05304247990815155, "grad_norm": 2.5579562187194824, "learning_rate": 7.930018455207863e-05, "loss": 0.3179, "step": 462 }, { "epoch": 0.053157290470723303, "grad_norm": 0.48929858207702637, "learning_rate": 7.929149002914756e-05, "loss": 0.3106, "step": 463 }, { "epoch": 0.05327210103329506, "grad_norm": 0.3742031753063202, "learning_rate": 7.928274231123442e-05, "loss": 0.2958, "step": 464 }, { "epoch": 0.053386911595866816, "grad_norm": 0.422057569026947, "learning_rate": 7.927394141018238e-05, "loss": 0.2775, "step": 465 }, { "epoch": 0.053501722158438576, "grad_norm": 8.76840877532959, "learning_rate": 7.926508733790657e-05, "loss": 0.3336, "step": 466 }, { "epoch": 0.053616532721010336, "grad_norm": 0.5142157077789307, "learning_rate": 7.925618010639411e-05, "loss": 0.2997, "step": 467 }, { "epoch": 0.05373134328358209, "grad_norm": 0.3950580060482025, "learning_rate": 7.924721972770413e-05, "loss": 0.3071, "step": 468 }, { "epoch": 0.05384615384615385, "grad_norm": 2.627751588821411, "learning_rate": 7.923820621396767e-05, "loss": 0.2931, "step": 469 }, { "epoch": 0.0539609644087256, "grad_norm": 0.4960152208805084, "learning_rate": 7.922913957738772e-05, "loss": 0.2976, "step": 470 }, { "epoch": 0.05407577497129736, "grad_norm": 0.3836832642555237, "learning_rate": 7.922001983023918e-05, "loss": 0.2899, "step": 471 }, { "epoch": 0.054190585533869115, "grad_norm": 0.44324302673339844, "learning_rate": 7.921084698486889e-05, "loss": 0.2948, "step": 472 }, { "epoch": 0.054305396096440875, "grad_norm": 0.42583808302879333, "learning_rate": 7.920162105369552e-05, "loss": 0.277, "step": 473 }, { "epoch": 0.05442020665901263, "grad_norm": 0.4924968481063843, "learning_rate": 7.919234204920967e-05, "loss": 0.3082, "step": 474 }, { "epoch": 0.05453501722158439, "grad_norm": 0.3889814019203186, "learning_rate": 7.918300998397376e-05, "loss": 0.3095, "step": 475 }, { "epoch": 0.05464982778415614, "grad_norm": 0.42471879720687866, "learning_rate": 7.917362487062207e-05, "loss": 0.3103, "step": 476 }, { "epoch": 0.0547646383467279, "grad_norm": 0.3853882849216461, "learning_rate": 7.916418672186065e-05, "loss": 0.3112, "step": 477 }, { "epoch": 0.054879448909299654, "grad_norm": 0.38395148515701294, "learning_rate": 7.915469555046741e-05, "loss": 0.2941, "step": 478 }, { "epoch": 0.054994259471871414, "grad_norm": 0.36851951479911804, "learning_rate": 7.914515136929201e-05, "loss": 0.308, "step": 479 }, { "epoch": 0.05510907003444317, "grad_norm": 0.38119620084762573, "learning_rate": 7.913555419125588e-05, "loss": 0.2816, "step": 480 }, { "epoch": 0.05522388059701493, "grad_norm": 0.38007882237434387, "learning_rate": 7.912590402935223e-05, "loss": 0.2752, "step": 481 }, { "epoch": 0.05533869115958668, "grad_norm": 0.3304612934589386, "learning_rate": 7.911620089664598e-05, "loss": 0.292, "step": 482 }, { "epoch": 0.05545350172215844, "grad_norm": 0.3429339528083801, "learning_rate": 7.910644480627373e-05, "loss": 0.2796, "step": 483 }, { "epoch": 0.05556831228473019, "grad_norm": 0.32595786452293396, "learning_rate": 7.909663577144385e-05, "loss": 0.2949, "step": 484 }, { "epoch": 0.05568312284730195, "grad_norm": 0.35280129313468933, "learning_rate": 7.908677380543632e-05, "loss": 0.3157, "step": 485 }, { "epoch": 0.055797933409873705, "grad_norm": 0.3293561637401581, "learning_rate": 7.907685892160284e-05, "loss": 0.2907, "step": 486 }, { "epoch": 0.055912743972445465, "grad_norm": 0.3399439752101898, "learning_rate": 7.906689113336673e-05, "loss": 0.2798, "step": 487 }, { "epoch": 0.05602755453501722, "grad_norm": 0.2961740791797638, "learning_rate": 7.905687045422288e-05, "loss": 0.2817, "step": 488 }, { "epoch": 0.05614236509758898, "grad_norm": 0.3358234465122223, "learning_rate": 7.90467968977379e-05, "loss": 0.3144, "step": 489 }, { "epoch": 0.05625717566016074, "grad_norm": 0.3116283714771271, "learning_rate": 7.90366704775499e-05, "loss": 0.301, "step": 490 }, { "epoch": 0.05637198622273249, "grad_norm": 0.37573516368865967, "learning_rate": 7.902649120736858e-05, "loss": 0.2977, "step": 491 }, { "epoch": 0.05648679678530425, "grad_norm": 0.3581320643424988, "learning_rate": 7.901625910097519e-05, "loss": 0.2911, "step": 492 }, { "epoch": 0.056601607347876004, "grad_norm": 0.3679203689098358, "learning_rate": 7.900597417222254e-05, "loss": 0.325, "step": 493 }, { "epoch": 0.056716417910447764, "grad_norm": 0.38292962312698364, "learning_rate": 7.899563643503491e-05, "loss": 0.2869, "step": 494 }, { "epoch": 0.05683122847301952, "grad_norm": 5.0915093421936035, "learning_rate": 7.898524590340811e-05, "loss": 0.3583, "step": 495 }, { "epoch": 0.05694603903559128, "grad_norm": 0.483207106590271, "learning_rate": 7.897480259140942e-05, "loss": 0.3275, "step": 496 }, { "epoch": 0.05706084959816303, "grad_norm": 0.3240254819393158, "learning_rate": 7.896430651317755e-05, "loss": 0.3017, "step": 497 }, { "epoch": 0.05717566016073479, "grad_norm": 0.45004966855049133, "learning_rate": 7.89537576829227e-05, "loss": 0.304, "step": 498 }, { "epoch": 0.05729047072330654, "grad_norm": 0.344612181186676, "learning_rate": 7.894315611492641e-05, "loss": 0.3011, "step": 499 }, { "epoch": 0.0574052812858783, "grad_norm": 0.694592297077179, "learning_rate": 7.893250182354171e-05, "loss": 0.2802, "step": 500 }, { "epoch": 0.057520091848450056, "grad_norm": 0.4210813045501709, "learning_rate": 7.892179482319297e-05, "loss": 0.3029, "step": 501 }, { "epoch": 0.057634902411021816, "grad_norm": 0.39994993805885315, "learning_rate": 7.891103512837588e-05, "loss": 0.2771, "step": 502 }, { "epoch": 0.05774971297359357, "grad_norm": 0.45169538259506226, "learning_rate": 7.890022275365751e-05, "loss": 0.2909, "step": 503 }, { "epoch": 0.05786452353616533, "grad_norm": 0.40857359766960144, "learning_rate": 7.888935771367628e-05, "loss": 0.3081, "step": 504 }, { "epoch": 0.05797933409873708, "grad_norm": 0.4502425789833069, "learning_rate": 7.887844002314186e-05, "loss": 0.3062, "step": 505 }, { "epoch": 0.05809414466130884, "grad_norm": 0.34187939763069153, "learning_rate": 7.886746969683522e-05, "loss": 0.2887, "step": 506 }, { "epoch": 0.058208955223880594, "grad_norm": 0.33104848861694336, "learning_rate": 7.885644674960859e-05, "loss": 0.293, "step": 507 }, { "epoch": 0.058323765786452354, "grad_norm": 0.33371978998184204, "learning_rate": 7.884537119638545e-05, "loss": 0.2905, "step": 508 }, { "epoch": 0.05843857634902411, "grad_norm": 0.33918145298957825, "learning_rate": 7.883424305216048e-05, "loss": 0.2825, "step": 509 }, { "epoch": 0.05855338691159587, "grad_norm": 0.3379659652709961, "learning_rate": 7.88230623319996e-05, "loss": 0.303, "step": 510 }, { "epoch": 0.05866819747416762, "grad_norm": 1.6514071226119995, "learning_rate": 7.881182905103986e-05, "loss": 0.3055, "step": 511 }, { "epoch": 0.05878300803673938, "grad_norm": 0.3956787884235382, "learning_rate": 7.880054322448951e-05, "loss": 0.2877, "step": 512 }, { "epoch": 0.05889781859931114, "grad_norm": 0.36221209168434143, "learning_rate": 7.878920486762792e-05, "loss": 0.3026, "step": 513 }, { "epoch": 0.05901262916188289, "grad_norm": 0.36362770199775696, "learning_rate": 7.877781399580557e-05, "loss": 0.313, "step": 514 }, { "epoch": 0.05912743972445465, "grad_norm": 0.4859883189201355, "learning_rate": 7.876637062444404e-05, "loss": 0.3093, "step": 515 }, { "epoch": 0.059242250287026406, "grad_norm": 0.3473816514015198, "learning_rate": 7.875487476903603e-05, "loss": 0.2795, "step": 516 }, { "epoch": 0.059357060849598166, "grad_norm": 0.42261362075805664, "learning_rate": 7.874332644514525e-05, "loss": 0.2975, "step": 517 }, { "epoch": 0.05947187141216992, "grad_norm": 0.3398798704147339, "learning_rate": 7.873172566840644e-05, "loss": 0.3098, "step": 518 }, { "epoch": 0.05958668197474168, "grad_norm": 0.3511700928211212, "learning_rate": 7.872007245452539e-05, "loss": 0.3302, "step": 519 }, { "epoch": 0.05970149253731343, "grad_norm": 0.30582395195961, "learning_rate": 7.870836681927886e-05, "loss": 0.2935, "step": 520 }, { "epoch": 0.05981630309988519, "grad_norm": 0.3017481565475464, "learning_rate": 7.869660877851456e-05, "loss": 0.2878, "step": 521 }, { "epoch": 0.059931113662456945, "grad_norm": 0.3355499505996704, "learning_rate": 7.86847983481512e-05, "loss": 0.3096, "step": 522 }, { "epoch": 0.060045924225028705, "grad_norm": 0.4301173985004425, "learning_rate": 7.867293554417839e-05, "loss": 0.325, "step": 523 }, { "epoch": 0.06016073478760046, "grad_norm": 0.749073326587677, "learning_rate": 7.866102038265662e-05, "loss": 0.3059, "step": 524 }, { "epoch": 0.06027554535017222, "grad_norm": 0.31489408016204834, "learning_rate": 7.864905287971731e-05, "loss": 0.3019, "step": 525 }, { "epoch": 0.06039035591274397, "grad_norm": 0.38279131054878235, "learning_rate": 7.863703305156273e-05, "loss": 0.2892, "step": 526 }, { "epoch": 0.06050516647531573, "grad_norm": 0.30894938111305237, "learning_rate": 7.862496091446598e-05, "loss": 0.2766, "step": 527 }, { "epoch": 0.06061997703788748, "grad_norm": 0.32618463039398193, "learning_rate": 7.861283648477099e-05, "loss": 0.2606, "step": 528 }, { "epoch": 0.06073478760045924, "grad_norm": 0.40728962421417236, "learning_rate": 7.860065977889246e-05, "loss": 0.2849, "step": 529 }, { "epoch": 0.060849598163030996, "grad_norm": 0.3127685487270355, "learning_rate": 7.858843081331592e-05, "loss": 0.2993, "step": 530 }, { "epoch": 0.060964408725602756, "grad_norm": 0.35078856348991394, "learning_rate": 7.857614960459756e-05, "loss": 0.2972, "step": 531 }, { "epoch": 0.06107921928817451, "grad_norm": 11.365266799926758, "learning_rate": 7.85638161693644e-05, "loss": 0.7297, "step": 532 }, { "epoch": 0.06119402985074627, "grad_norm": 0.4018852710723877, "learning_rate": 7.855143052431413e-05, "loss": 0.3042, "step": 533 }, { "epoch": 0.06130884041331802, "grad_norm": 0.3675982356071472, "learning_rate": 7.85389926862151e-05, "loss": 0.3066, "step": 534 }, { "epoch": 0.06142365097588978, "grad_norm": 0.3493945002555847, "learning_rate": 7.852650267190634e-05, "loss": 0.2916, "step": 535 }, { "epoch": 0.06153846153846154, "grad_norm": 1.3728612661361694, "learning_rate": 7.851396049829751e-05, "loss": 0.3127, "step": 536 }, { "epoch": 0.061653272101033295, "grad_norm": 0.45875078439712524, "learning_rate": 7.85013661823689e-05, "loss": 0.3056, "step": 537 }, { "epoch": 0.061768082663605055, "grad_norm": 0.4065243899822235, "learning_rate": 7.848871974117142e-05, "loss": 0.3151, "step": 538 }, { "epoch": 0.06188289322617681, "grad_norm": 0.3929854929447174, "learning_rate": 7.847602119182649e-05, "loss": 0.3069, "step": 539 }, { "epoch": 0.06199770378874857, "grad_norm": 0.37497514486312866, "learning_rate": 7.846327055152609e-05, "loss": 0.2877, "step": 540 }, { "epoch": 0.06211251435132032, "grad_norm": 0.36271077394485474, "learning_rate": 7.845046783753276e-05, "loss": 0.2956, "step": 541 }, { "epoch": 0.06222732491389208, "grad_norm": 0.35947927832603455, "learning_rate": 7.843761306717952e-05, "loss": 0.3053, "step": 542 }, { "epoch": 0.062342135476463834, "grad_norm": 0.352855384349823, "learning_rate": 7.842470625786986e-05, "loss": 0.3092, "step": 543 }, { "epoch": 0.062456946039035593, "grad_norm": 0.3619791269302368, "learning_rate": 7.841174742707773e-05, "loss": 0.2985, "step": 544 }, { "epoch": 0.06257175660160735, "grad_norm": 0.3337790071964264, "learning_rate": 7.83987365923475e-05, "loss": 0.2789, "step": 545 }, { "epoch": 0.0626865671641791, "grad_norm": 0.35463792085647583, "learning_rate": 7.838567377129398e-05, "loss": 0.3099, "step": 546 }, { "epoch": 0.06280137772675086, "grad_norm": 0.3516191840171814, "learning_rate": 7.83725589816023e-05, "loss": 0.3007, "step": 547 }, { "epoch": 0.06291618828932262, "grad_norm": 0.3641863763332367, "learning_rate": 7.835939224102803e-05, "loss": 0.3103, "step": 548 }, { "epoch": 0.06303099885189438, "grad_norm": 0.3544803261756897, "learning_rate": 7.834617356739697e-05, "loss": 0.3034, "step": 549 }, { "epoch": 0.06314580941446613, "grad_norm": 0.3395732045173645, "learning_rate": 7.833290297860534e-05, "loss": 0.2973, "step": 550 }, { "epoch": 0.06326061997703789, "grad_norm": 0.36709532141685486, "learning_rate": 7.831958049261956e-05, "loss": 0.3239, "step": 551 }, { "epoch": 0.06337543053960965, "grad_norm": 0.37253034114837646, "learning_rate": 7.830620612747637e-05, "loss": 0.3277, "step": 552 }, { "epoch": 0.0634902411021814, "grad_norm": 6.828898906707764, "learning_rate": 7.829277990128269e-05, "loss": 0.6068, "step": 553 }, { "epoch": 0.06360505166475315, "grad_norm": 0.47214075922966003, "learning_rate": 7.827930183221572e-05, "loss": 0.3054, "step": 554 }, { "epoch": 0.06371986222732491, "grad_norm": 4.047971248626709, "learning_rate": 7.82657719385228e-05, "loss": 0.3359, "step": 555 }, { "epoch": 0.06383467278989667, "grad_norm": 0.70462566614151, "learning_rate": 7.825219023852142e-05, "loss": 0.3362, "step": 556 }, { "epoch": 0.06394948335246843, "grad_norm": 0.31297755241394043, "learning_rate": 7.823855675059927e-05, "loss": 0.3205, "step": 557 }, { "epoch": 0.06406429391504018, "grad_norm": 0.41818076372146606, "learning_rate": 7.82248714932141e-05, "loss": 0.2939, "step": 558 }, { "epoch": 0.06417910447761194, "grad_norm": 0.3835314214229584, "learning_rate": 7.821113448489375e-05, "loss": 0.2924, "step": 559 }, { "epoch": 0.0642939150401837, "grad_norm": 0.35698917508125305, "learning_rate": 7.819734574423616e-05, "loss": 0.2975, "step": 560 }, { "epoch": 0.06440872560275546, "grad_norm": 0.3694724440574646, "learning_rate": 7.818350528990929e-05, "loss": 0.304, "step": 561 }, { "epoch": 0.06452353616532722, "grad_norm": 0.31791746616363525, "learning_rate": 7.816961314065107e-05, "loss": 0.3192, "step": 562 }, { "epoch": 0.06463834672789896, "grad_norm": 0.394528865814209, "learning_rate": 7.815566931526951e-05, "loss": 0.2992, "step": 563 }, { "epoch": 0.06475315729047072, "grad_norm": 0.36178678274154663, "learning_rate": 7.81416738326425e-05, "loss": 0.3248, "step": 564 }, { "epoch": 0.06486796785304248, "grad_norm": 0.36553844809532166, "learning_rate": 7.812762671171789e-05, "loss": 0.3018, "step": 565 }, { "epoch": 0.06498277841561424, "grad_norm": 0.39382630586624146, "learning_rate": 7.811352797151345e-05, "loss": 0.2791, "step": 566 }, { "epoch": 0.06509758897818599, "grad_norm": 0.28608179092407227, "learning_rate": 7.809937763111683e-05, "loss": 0.279, "step": 567 }, { "epoch": 0.06521239954075775, "grad_norm": 0.3505339026451111, "learning_rate": 7.808517570968555e-05, "loss": 0.2975, "step": 568 }, { "epoch": 0.06532721010332951, "grad_norm": 0.3191947638988495, "learning_rate": 7.807092222644696e-05, "loss": 0.3084, "step": 569 }, { "epoch": 0.06544202066590127, "grad_norm": 0.2961178719997406, "learning_rate": 7.805661720069817e-05, "loss": 0.2877, "step": 570 }, { "epoch": 0.06555683122847301, "grad_norm": 0.3272779881954193, "learning_rate": 7.804226065180615e-05, "loss": 0.2954, "step": 571 }, { "epoch": 0.06567164179104477, "grad_norm": 0.2968980669975281, "learning_rate": 7.802785259920757e-05, "loss": 0.2869, "step": 572 }, { "epoch": 0.06578645235361653, "grad_norm": 0.30481263995170593, "learning_rate": 7.801339306240885e-05, "loss": 0.291, "step": 573 }, { "epoch": 0.0659012629161883, "grad_norm": 0.316026896238327, "learning_rate": 7.79988820609861e-05, "loss": 0.2831, "step": 574 }, { "epoch": 0.06601607347876004, "grad_norm": 0.3005729913711548, "learning_rate": 7.798431961458513e-05, "loss": 0.2787, "step": 575 }, { "epoch": 0.0661308840413318, "grad_norm": 0.2880862057209015, "learning_rate": 7.796970574292136e-05, "loss": 0.2531, "step": 576 }, { "epoch": 0.06624569460390356, "grad_norm": 0.3071339726448059, "learning_rate": 7.795504046577986e-05, "loss": 0.3005, "step": 577 }, { "epoch": 0.06636050516647532, "grad_norm": 0.4210788607597351, "learning_rate": 7.794032380301531e-05, "loss": 0.3742, "step": 578 }, { "epoch": 0.06647531572904707, "grad_norm": 0.3289119005203247, "learning_rate": 7.79255557745519e-05, "loss": 0.3072, "step": 579 }, { "epoch": 0.06659012629161883, "grad_norm": 0.2925910949707031, "learning_rate": 7.791073640038344e-05, "loss": 0.3002, "step": 580 }, { "epoch": 0.06670493685419059, "grad_norm": 1.1409544944763184, "learning_rate": 7.789586570057317e-05, "loss": 0.2828, "step": 581 }, { "epoch": 0.06681974741676235, "grad_norm": 0.3474898338317871, "learning_rate": 7.788094369525392e-05, "loss": 0.3002, "step": 582 }, { "epoch": 0.0669345579793341, "grad_norm": 0.3033343255519867, "learning_rate": 7.786597040462786e-05, "loss": 0.2936, "step": 583 }, { "epoch": 0.06704936854190585, "grad_norm": 0.28995487093925476, "learning_rate": 7.785094584896669e-05, "loss": 0.2884, "step": 584 }, { "epoch": 0.06716417910447761, "grad_norm": 0.33305245637893677, "learning_rate": 7.783587004861149e-05, "loss": 0.2806, "step": 585 }, { "epoch": 0.06727898966704937, "grad_norm": 0.6596775054931641, "learning_rate": 7.782074302397268e-05, "loss": 0.3062, "step": 586 }, { "epoch": 0.06739380022962113, "grad_norm": 0.31128165125846863, "learning_rate": 7.780556479553008e-05, "loss": 0.2701, "step": 587 }, { "epoch": 0.06750861079219288, "grad_norm": 0.3151427209377289, "learning_rate": 7.779033538383279e-05, "loss": 0.2915, "step": 588 }, { "epoch": 0.06762342135476464, "grad_norm": 0.2947483956813812, "learning_rate": 7.777505480949924e-05, "loss": 0.2799, "step": 589 }, { "epoch": 0.0677382319173364, "grad_norm": 0.33526095747947693, "learning_rate": 7.775972309321714e-05, "loss": 0.3106, "step": 590 }, { "epoch": 0.06785304247990816, "grad_norm": 0.3409642279148102, "learning_rate": 7.774434025574335e-05, "loss": 0.3245, "step": 591 }, { "epoch": 0.0679678530424799, "grad_norm": 0.36521831154823303, "learning_rate": 7.772890631790404e-05, "loss": 0.3049, "step": 592 }, { "epoch": 0.06808266360505166, "grad_norm": 0.30674588680267334, "learning_rate": 7.771342130059453e-05, "loss": 0.2951, "step": 593 }, { "epoch": 0.06819747416762342, "grad_norm": 0.3104851245880127, "learning_rate": 7.769788522477929e-05, "loss": 0.3039, "step": 594 }, { "epoch": 0.06831228473019518, "grad_norm": 0.2970619201660156, "learning_rate": 7.768229811149188e-05, "loss": 0.2941, "step": 595 }, { "epoch": 0.06842709529276693, "grad_norm": 0.3099854588508606, "learning_rate": 7.766665998183502e-05, "loss": 0.2736, "step": 596 }, { "epoch": 0.06854190585533869, "grad_norm": 1.8106781244277954, "learning_rate": 7.765097085698048e-05, "loss": 0.2964, "step": 597 }, { "epoch": 0.06865671641791045, "grad_norm": 0.3605826795101166, "learning_rate": 7.763523075816903e-05, "loss": 0.3135, "step": 598 }, { "epoch": 0.06877152698048221, "grad_norm": 0.31591367721557617, "learning_rate": 7.76194397067105e-05, "loss": 0.3171, "step": 599 }, { "epoch": 0.06888633754305395, "grad_norm": 0.44506749510765076, "learning_rate": 7.76035977239837e-05, "loss": 0.2813, "step": 600 }, { "epoch": 0.06900114810562571, "grad_norm": 0.31097403168678284, "learning_rate": 7.758770483143634e-05, "loss": 0.2971, "step": 601 }, { "epoch": 0.06911595866819747, "grad_norm": 0.31898438930511475, "learning_rate": 7.757176105058513e-05, "loss": 0.3004, "step": 602 }, { "epoch": 0.06923076923076923, "grad_norm": 0.3299923241138458, "learning_rate": 7.755576640301561e-05, "loss": 0.2991, "step": 603 }, { "epoch": 0.06934557979334098, "grad_norm": 0.33090996742248535, "learning_rate": 7.753972091038224e-05, "loss": 0.2789, "step": 604 }, { "epoch": 0.06946039035591274, "grad_norm": 0.33697113394737244, "learning_rate": 7.752362459440828e-05, "loss": 0.3107, "step": 605 }, { "epoch": 0.0695752009184845, "grad_norm": 0.34607380628585815, "learning_rate": 7.75074774768858e-05, "loss": 0.3005, "step": 606 }, { "epoch": 0.06969001148105626, "grad_norm": 0.3623761534690857, "learning_rate": 7.749127957967567e-05, "loss": 0.2919, "step": 607 }, { "epoch": 0.06980482204362802, "grad_norm": 0.3047460615634918, "learning_rate": 7.747503092470748e-05, "loss": 0.2948, "step": 608 }, { "epoch": 0.06991963260619977, "grad_norm": 0.3265737295150757, "learning_rate": 7.745873153397957e-05, "loss": 0.2932, "step": 609 }, { "epoch": 0.07003444316877153, "grad_norm": 0.2919953763484955, "learning_rate": 7.744238142955894e-05, "loss": 0.278, "step": 610 }, { "epoch": 0.07014925373134329, "grad_norm": 0.28476962447166443, "learning_rate": 7.742598063358127e-05, "loss": 0.3042, "step": 611 }, { "epoch": 0.07026406429391505, "grad_norm": 0.32675468921661377, "learning_rate": 7.740952916825085e-05, "loss": 0.2968, "step": 612 }, { "epoch": 0.07037887485648679, "grad_norm": 0.6846013069152832, "learning_rate": 7.739302705584058e-05, "loss": 0.286, "step": 613 }, { "epoch": 0.07049368541905855, "grad_norm": 0.3648740351200104, "learning_rate": 7.737647431869195e-05, "loss": 0.2949, "step": 614 }, { "epoch": 0.07060849598163031, "grad_norm": 0.32446420192718506, "learning_rate": 7.735987097921494e-05, "loss": 0.2978, "step": 615 }, { "epoch": 0.07072330654420207, "grad_norm": 1.7522366046905518, "learning_rate": 7.734321705988807e-05, "loss": 0.3004, "step": 616 }, { "epoch": 0.07083811710677382, "grad_norm": 0.4363382160663605, "learning_rate": 7.732651258325835e-05, "loss": 0.3004, "step": 617 }, { "epoch": 0.07095292766934558, "grad_norm": 0.2841629981994629, "learning_rate": 7.73097575719412e-05, "loss": 0.2844, "step": 618 }, { "epoch": 0.07106773823191734, "grad_norm": 0.6875150799751282, "learning_rate": 7.72929520486205e-05, "loss": 0.3107, "step": 619 }, { "epoch": 0.0711825487944891, "grad_norm": 0.26834604144096375, "learning_rate": 7.727609603604845e-05, "loss": 0.2857, "step": 620 }, { "epoch": 0.07129735935706084, "grad_norm": 0.32452455163002014, "learning_rate": 7.72591895570457e-05, "loss": 0.2979, "step": 621 }, { "epoch": 0.0714121699196326, "grad_norm": 0.320261687040329, "learning_rate": 7.724223263450114e-05, "loss": 0.2933, "step": 622 }, { "epoch": 0.07152698048220436, "grad_norm": 0.3119097948074341, "learning_rate": 7.722522529137198e-05, "loss": 0.2985, "step": 623 }, { "epoch": 0.07164179104477612, "grad_norm": 0.49086689949035645, "learning_rate": 7.720816755068372e-05, "loss": 0.3058, "step": 624 }, { "epoch": 0.07175660160734787, "grad_norm": 0.29433295130729675, "learning_rate": 7.719105943553007e-05, "loss": 0.3006, "step": 625 }, { "epoch": 0.07187141216991963, "grad_norm": 0.2978609502315521, "learning_rate": 7.71739009690729e-05, "loss": 0.2858, "step": 626 }, { "epoch": 0.07198622273249139, "grad_norm": 0.306183397769928, "learning_rate": 7.715669217454234e-05, "loss": 0.2803, "step": 627 }, { "epoch": 0.07210103329506315, "grad_norm": 0.3401281535625458, "learning_rate": 7.713943307523654e-05, "loss": 0.2872, "step": 628 }, { "epoch": 0.07221584385763491, "grad_norm": 2.1363086700439453, "learning_rate": 7.712212369452188e-05, "loss": 0.3219, "step": 629 }, { "epoch": 0.07233065442020666, "grad_norm": 0.35978227853775024, "learning_rate": 7.710476405583272e-05, "loss": 0.3144, "step": 630 }, { "epoch": 0.07244546498277842, "grad_norm": 0.30057492852211, "learning_rate": 7.70873541826715e-05, "loss": 0.3181, "step": 631 }, { "epoch": 0.07256027554535018, "grad_norm": 0.3647457957267761, "learning_rate": 7.706989409860867e-05, "loss": 0.291, "step": 632 }, { "epoch": 0.07267508610792194, "grad_norm": 2.4542667865753174, "learning_rate": 7.705238382728264e-05, "loss": 0.3028, "step": 633 }, { "epoch": 0.07278989667049368, "grad_norm": 0.4090861976146698, "learning_rate": 7.70348233923998e-05, "loss": 0.3146, "step": 634 }, { "epoch": 0.07290470723306544, "grad_norm": 0.2753853499889374, "learning_rate": 7.701721281773441e-05, "loss": 0.288, "step": 635 }, { "epoch": 0.0730195177956372, "grad_norm": 1.6179410219192505, "learning_rate": 7.699955212712864e-05, "loss": 0.3207, "step": 636 }, { "epoch": 0.07313432835820896, "grad_norm": 0.34687334299087524, "learning_rate": 7.698184134449254e-05, "loss": 0.2967, "step": 637 }, { "epoch": 0.07324913892078071, "grad_norm": 0.5439251065254211, "learning_rate": 7.696408049380389e-05, "loss": 0.3283, "step": 638 }, { "epoch": 0.07336394948335247, "grad_norm": 0.5083271265029907, "learning_rate": 7.694626959910834e-05, "loss": 0.3075, "step": 639 }, { "epoch": 0.07347876004592423, "grad_norm": 0.34471073746681213, "learning_rate": 7.692840868451924e-05, "loss": 0.2808, "step": 640 }, { "epoch": 0.07359357060849599, "grad_norm": 0.39774560928344727, "learning_rate": 7.69104977742177e-05, "loss": 0.3065, "step": 641 }, { "epoch": 0.07370838117106773, "grad_norm": 0.32151269912719727, "learning_rate": 7.689253689245249e-05, "loss": 0.3006, "step": 642 }, { "epoch": 0.07382319173363949, "grad_norm": 7.658827781677246, "learning_rate": 7.687452606354003e-05, "loss": 0.4188, "step": 643 }, { "epoch": 0.07393800229621125, "grad_norm": 0.45087534189224243, "learning_rate": 7.685646531186438e-05, "loss": 0.3017, "step": 644 }, { "epoch": 0.07405281285878301, "grad_norm": 0.3683360517024994, "learning_rate": 7.683835466187718e-05, "loss": 0.294, "step": 645 }, { "epoch": 0.07416762342135476, "grad_norm": 0.38218826055526733, "learning_rate": 7.682019413809762e-05, "loss": 0.288, "step": 646 }, { "epoch": 0.07428243398392652, "grad_norm": 0.34186333417892456, "learning_rate": 7.680198376511242e-05, "loss": 0.3, "step": 647 }, { "epoch": 0.07439724454649828, "grad_norm": 3.141179084777832, "learning_rate": 7.678372356757578e-05, "loss": 0.3476, "step": 648 }, { "epoch": 0.07451205510907004, "grad_norm": 0.6366912722587585, "learning_rate": 7.676541357020938e-05, "loss": 0.3324, "step": 649 }, { "epoch": 0.07462686567164178, "grad_norm": 0.3181123435497284, "learning_rate": 7.674705379780229e-05, "loss": 0.3045, "step": 650 }, { "epoch": 0.07474167623421354, "grad_norm": 0.41245290637016296, "learning_rate": 7.672864427521097e-05, "loss": 0.3039, "step": 651 }, { "epoch": 0.0748564867967853, "grad_norm": 0.5136778354644775, "learning_rate": 7.671018502735925e-05, "loss": 0.3346, "step": 652 }, { "epoch": 0.07497129735935706, "grad_norm": 0.3605038821697235, "learning_rate": 7.669167607923829e-05, "loss": 0.3055, "step": 653 }, { "epoch": 0.07508610792192882, "grad_norm": 0.3976781368255615, "learning_rate": 7.667311745590651e-05, "loss": 0.3017, "step": 654 }, { "epoch": 0.07520091848450057, "grad_norm": 0.3388903737068176, "learning_rate": 7.665450918248959e-05, "loss": 0.3014, "step": 655 }, { "epoch": 0.07531572904707233, "grad_norm": 0.3576614260673523, "learning_rate": 7.663585128418045e-05, "loss": 0.3019, "step": 656 }, { "epoch": 0.07543053960964409, "grad_norm": 0.35442012548446655, "learning_rate": 7.661714378623917e-05, "loss": 0.3254, "step": 657 }, { "epoch": 0.07554535017221585, "grad_norm": 0.33225390315055847, "learning_rate": 7.6598386713993e-05, "loss": 0.3177, "step": 658 }, { "epoch": 0.0756601607347876, "grad_norm": 0.3457263112068176, "learning_rate": 7.657958009283629e-05, "loss": 0.2872, "step": 659 }, { "epoch": 0.07577497129735936, "grad_norm": 0.3723585605621338, "learning_rate": 7.656072394823048e-05, "loss": 0.3127, "step": 660 }, { "epoch": 0.07588978185993112, "grad_norm": 0.3641597330570221, "learning_rate": 7.654181830570404e-05, "loss": 0.3048, "step": 661 }, { "epoch": 0.07600459242250288, "grad_norm": 0.33073219656944275, "learning_rate": 7.652286319085249e-05, "loss": 0.3, "step": 662 }, { "epoch": 0.07611940298507462, "grad_norm": 0.29730135202407837, "learning_rate": 7.650385862933832e-05, "loss": 0.2969, "step": 663 }, { "epoch": 0.07623421354764638, "grad_norm": 0.32988789677619934, "learning_rate": 7.648480464689093e-05, "loss": 0.3314, "step": 664 }, { "epoch": 0.07634902411021814, "grad_norm": 0.3111075758934021, "learning_rate": 7.646570126930664e-05, "loss": 0.2846, "step": 665 }, { "epoch": 0.0764638346727899, "grad_norm": 0.3258228302001953, "learning_rate": 7.644654852244869e-05, "loss": 0.3003, "step": 666 }, { "epoch": 0.07657864523536165, "grad_norm": 0.45169708132743835, "learning_rate": 7.642734643224708e-05, "loss": 0.3061, "step": 667 }, { "epoch": 0.07669345579793341, "grad_norm": 0.31117168068885803, "learning_rate": 7.64080950246987e-05, "loss": 0.2869, "step": 668 }, { "epoch": 0.07680826636050517, "grad_norm": 0.3634401857852936, "learning_rate": 7.638879432586714e-05, "loss": 0.2964, "step": 669 }, { "epoch": 0.07692307692307693, "grad_norm": 0.3036511242389679, "learning_rate": 7.636944436188275e-05, "loss": 0.3068, "step": 670 }, { "epoch": 0.07703788748564867, "grad_norm": 0.32979798316955566, "learning_rate": 7.635004515894258e-05, "loss": 0.2959, "step": 671 }, { "epoch": 0.07715269804822043, "grad_norm": 0.35914167761802673, "learning_rate": 7.633059674331033e-05, "loss": 0.3186, "step": 672 }, { "epoch": 0.0772675086107922, "grad_norm": 0.32867199182510376, "learning_rate": 7.631109914131635e-05, "loss": 0.3124, "step": 673 }, { "epoch": 0.07738231917336395, "grad_norm": 0.3152688145637512, "learning_rate": 7.629155237935756e-05, "loss": 0.2805, "step": 674 }, { "epoch": 0.0774971297359357, "grad_norm": 0.31493091583251953, "learning_rate": 7.627195648389744e-05, "loss": 0.2928, "step": 675 }, { "epoch": 0.07761194029850746, "grad_norm": 0.28796038031578064, "learning_rate": 7.625231148146601e-05, "loss": 0.294, "step": 676 }, { "epoch": 0.07772675086107922, "grad_norm": 0.33860617876052856, "learning_rate": 7.623261739865973e-05, "loss": 0.2943, "step": 677 }, { "epoch": 0.07784156142365098, "grad_norm": 0.3429354131221771, "learning_rate": 7.621287426214153e-05, "loss": 0.3165, "step": 678 }, { "epoch": 0.07795637198622274, "grad_norm": 0.29573866724967957, "learning_rate": 7.619308209864079e-05, "loss": 0.293, "step": 679 }, { "epoch": 0.07807118254879448, "grad_norm": 0.31570619344711304, "learning_rate": 7.61732409349532e-05, "loss": 0.3141, "step": 680 }, { "epoch": 0.07818599311136624, "grad_norm": 0.2812541127204895, "learning_rate": 7.615335079794083e-05, "loss": 0.2838, "step": 681 }, { "epoch": 0.078300803673938, "grad_norm": 0.3204561471939087, "learning_rate": 7.613341171453204e-05, "loss": 0.3213, "step": 682 }, { "epoch": 0.07841561423650976, "grad_norm": 0.26117631793022156, "learning_rate": 7.611342371172145e-05, "loss": 0.264, "step": 683 }, { "epoch": 0.07853042479908151, "grad_norm": 0.3916622996330261, "learning_rate": 7.609338681656995e-05, "loss": 0.3026, "step": 684 }, { "epoch": 0.07864523536165327, "grad_norm": 0.29057422280311584, "learning_rate": 7.607330105620456e-05, "loss": 0.3042, "step": 685 }, { "epoch": 0.07876004592422503, "grad_norm": 0.5017071962356567, "learning_rate": 7.605316645781849e-05, "loss": 0.3147, "step": 686 }, { "epoch": 0.07887485648679679, "grad_norm": 0.5662280321121216, "learning_rate": 7.603298304867109e-05, "loss": 0.3241, "step": 687 }, { "epoch": 0.07898966704936854, "grad_norm": 0.3243972063064575, "learning_rate": 7.601275085608774e-05, "loss": 0.3041, "step": 688 }, { "epoch": 0.0791044776119403, "grad_norm": 0.31497931480407715, "learning_rate": 7.599246990745994e-05, "loss": 0.2721, "step": 689 }, { "epoch": 0.07921928817451206, "grad_norm": 0.6641197204589844, "learning_rate": 7.59721402302451e-05, "loss": 0.3081, "step": 690 }, { "epoch": 0.07933409873708382, "grad_norm": 0.3070363998413086, "learning_rate": 7.595176185196669e-05, "loss": 0.2941, "step": 691 }, { "epoch": 0.07944890929965556, "grad_norm": 0.31536588072776794, "learning_rate": 7.593133480021407e-05, "loss": 0.3187, "step": 692 }, { "epoch": 0.07956371986222732, "grad_norm": 0.3025677800178528, "learning_rate": 7.591085910264252e-05, "loss": 0.2885, "step": 693 }, { "epoch": 0.07967853042479908, "grad_norm": 0.30031320452690125, "learning_rate": 7.589033478697313e-05, "loss": 0.293, "step": 694 }, { "epoch": 0.07979334098737084, "grad_norm": 0.3252509832382202, "learning_rate": 7.586976188099291e-05, "loss": 0.3287, "step": 695 }, { "epoch": 0.07990815154994259, "grad_norm": 0.247848242521286, "learning_rate": 7.584914041255455e-05, "loss": 0.2372, "step": 696 }, { "epoch": 0.08002296211251435, "grad_norm": 0.33308833837509155, "learning_rate": 7.582847040957652e-05, "loss": 0.286, "step": 697 }, { "epoch": 0.08013777267508611, "grad_norm": 1.578045129776001, "learning_rate": 7.580775190004304e-05, "loss": 0.3287, "step": 698 }, { "epoch": 0.08025258323765787, "grad_norm": 0.39746326208114624, "learning_rate": 7.578698491200395e-05, "loss": 0.3015, "step": 699 }, { "epoch": 0.08036739380022963, "grad_norm": 0.3058282434940338, "learning_rate": 7.576616947357473e-05, "loss": 0.313, "step": 700 }, { "epoch": 0.08048220436280137, "grad_norm": 0.43124037981033325, "learning_rate": 7.57453056129365e-05, "loss": 0.2991, "step": 701 }, { "epoch": 0.08059701492537313, "grad_norm": 0.899756669998169, "learning_rate": 7.572439335833588e-05, "loss": 0.3042, "step": 702 }, { "epoch": 0.0807118254879449, "grad_norm": 0.37913283705711365, "learning_rate": 7.570343273808503e-05, "loss": 0.2846, "step": 703 }, { "epoch": 0.08082663605051665, "grad_norm": 0.3197336196899414, "learning_rate": 7.568242378056158e-05, "loss": 0.2873, "step": 704 }, { "epoch": 0.0809414466130884, "grad_norm": 0.40465450286865234, "learning_rate": 7.566136651420866e-05, "loss": 0.3012, "step": 705 }, { "epoch": 0.08105625717566016, "grad_norm": 0.36130616068840027, "learning_rate": 7.564026096753472e-05, "loss": 0.3149, "step": 706 }, { "epoch": 0.08117106773823192, "grad_norm": 0.3256278932094574, "learning_rate": 7.561910716911361e-05, "loss": 0.3205, "step": 707 }, { "epoch": 0.08128587830080368, "grad_norm": 0.3221931457519531, "learning_rate": 7.559790514758452e-05, "loss": 0.2814, "step": 708 }, { "epoch": 0.08140068886337543, "grad_norm": 0.30368632078170776, "learning_rate": 7.557665493165192e-05, "loss": 0.2788, "step": 709 }, { "epoch": 0.08151549942594719, "grad_norm": 0.3560898005962372, "learning_rate": 7.555535655008548e-05, "loss": 0.3176, "step": 710 }, { "epoch": 0.08163030998851895, "grad_norm": 0.3758739233016968, "learning_rate": 7.553401003172018e-05, "loss": 0.3057, "step": 711 }, { "epoch": 0.0817451205510907, "grad_norm": 0.3116273283958435, "learning_rate": 7.551261540545605e-05, "loss": 0.2902, "step": 712 }, { "epoch": 0.08185993111366245, "grad_norm": 3.752485513687134, "learning_rate": 7.549117270025838e-05, "loss": 0.4144, "step": 713 }, { "epoch": 0.08197474167623421, "grad_norm": 0.39842647314071655, "learning_rate": 7.546968194515744e-05, "loss": 0.3271, "step": 714 }, { "epoch": 0.08208955223880597, "grad_norm": 0.291884183883667, "learning_rate": 7.544814316924859e-05, "loss": 0.2987, "step": 715 }, { "epoch": 0.08220436280137773, "grad_norm": 0.3236709535121918, "learning_rate": 7.542655640169225e-05, "loss": 0.305, "step": 716 }, { "epoch": 0.08231917336394948, "grad_norm": 1.9663692712783813, "learning_rate": 7.540492167171373e-05, "loss": 0.2971, "step": 717 }, { "epoch": 0.08243398392652124, "grad_norm": 0.36709460616111755, "learning_rate": 7.538323900860336e-05, "loss": 0.31, "step": 718 }, { "epoch": 0.082548794489093, "grad_norm": 0.3122377395629883, "learning_rate": 7.53615084417163e-05, "loss": 0.2792, "step": 719 }, { "epoch": 0.08266360505166476, "grad_norm": 0.31495001912117004, "learning_rate": 7.533973000047259e-05, "loss": 0.2902, "step": 720 }, { "epoch": 0.0827784156142365, "grad_norm": 0.3441402316093445, "learning_rate": 7.531790371435709e-05, "loss": 0.3083, "step": 721 }, { "epoch": 0.08289322617680826, "grad_norm": 0.3122592270374298, "learning_rate": 7.529602961291941e-05, "loss": 0.313, "step": 722 }, { "epoch": 0.08300803673938002, "grad_norm": 0.3442721962928772, "learning_rate": 7.527410772577392e-05, "loss": 0.3043, "step": 723 }, { "epoch": 0.08312284730195178, "grad_norm": 0.2969229519367218, "learning_rate": 7.525213808259969e-05, "loss": 0.3018, "step": 724 }, { "epoch": 0.08323765786452354, "grad_norm": 0.3393585681915283, "learning_rate": 7.523012071314043e-05, "loss": 0.3051, "step": 725 }, { "epoch": 0.08335246842709529, "grad_norm": 0.3816114664077759, "learning_rate": 7.520805564720444e-05, "loss": 0.3288, "step": 726 }, { "epoch": 0.08346727898966705, "grad_norm": 0.3066202998161316, "learning_rate": 7.518594291466468e-05, "loss": 0.3033, "step": 727 }, { "epoch": 0.08358208955223881, "grad_norm": 0.30139946937561035, "learning_rate": 7.516378254545851e-05, "loss": 0.3, "step": 728 }, { "epoch": 0.08369690011481057, "grad_norm": 0.3130766451358795, "learning_rate": 7.51415745695879e-05, "loss": 0.3067, "step": 729 }, { "epoch": 0.08381171067738231, "grad_norm": 0.3034198582172394, "learning_rate": 7.511931901711922e-05, "loss": 0.3188, "step": 730 }, { "epoch": 0.08392652123995407, "grad_norm": 0.2443494200706482, "learning_rate": 7.509701591818328e-05, "loss": 0.2674, "step": 731 }, { "epoch": 0.08404133180252583, "grad_norm": 0.30805063247680664, "learning_rate": 7.507466530297523e-05, "loss": 0.2844, "step": 732 }, { "epoch": 0.0841561423650976, "grad_norm": 0.26685383915901184, "learning_rate": 7.505226720175455e-05, "loss": 0.3048, "step": 733 }, { "epoch": 0.08427095292766934, "grad_norm": 1.7248069047927856, "learning_rate": 7.502982164484505e-05, "loss": 0.3211, "step": 734 }, { "epoch": 0.0843857634902411, "grad_norm": 0.40513208508491516, "learning_rate": 7.500732866263473e-05, "loss": 0.3403, "step": 735 }, { "epoch": 0.08450057405281286, "grad_norm": 13.524085998535156, "learning_rate": 7.498478828557584e-05, "loss": 0.3632, "step": 736 }, { "epoch": 0.08461538461538462, "grad_norm": 0.4444297254085541, "learning_rate": 7.496220054418478e-05, "loss": 0.2857, "step": 737 }, { "epoch": 0.08473019517795637, "grad_norm": 0.44925209879875183, "learning_rate": 7.493956546904211e-05, "loss": 0.361, "step": 738 }, { "epoch": 0.08484500574052813, "grad_norm": 0.40563657879829407, "learning_rate": 7.491688309079239e-05, "loss": 0.3062, "step": 739 }, { "epoch": 0.08495981630309989, "grad_norm": 0.33196893334388733, "learning_rate": 7.489415344014432e-05, "loss": 0.3062, "step": 740 }, { "epoch": 0.08507462686567165, "grad_norm": 0.39895492792129517, "learning_rate": 7.48713765478705e-05, "loss": 0.3052, "step": 741 }, { "epoch": 0.08518943742824339, "grad_norm": 0.3280685245990753, "learning_rate": 7.484855244480759e-05, "loss": 0.2955, "step": 742 }, { "epoch": 0.08530424799081515, "grad_norm": 0.36871087551116943, "learning_rate": 7.482568116185608e-05, "loss": 0.2971, "step": 743 }, { "epoch": 0.08541905855338691, "grad_norm": 0.321620374917984, "learning_rate": 7.48027627299804e-05, "loss": 0.2976, "step": 744 }, { "epoch": 0.08553386911595867, "grad_norm": 0.34138068556785583, "learning_rate": 7.477979718020876e-05, "loss": 0.2763, "step": 745 }, { "epoch": 0.08564867967853043, "grad_norm": 0.32037365436553955, "learning_rate": 7.475678454363321e-05, "loss": 0.3107, "step": 746 }, { "epoch": 0.08576349024110218, "grad_norm": 7.219040393829346, "learning_rate": 7.473372485140952e-05, "loss": 0.3611, "step": 747 }, { "epoch": 0.08587830080367394, "grad_norm": 0.408218652009964, "learning_rate": 7.471061813475715e-05, "loss": 0.2911, "step": 748 }, { "epoch": 0.0859931113662457, "grad_norm": 0.8174374103546143, "learning_rate": 7.468746442495925e-05, "loss": 0.2843, "step": 749 }, { "epoch": 0.08610792192881746, "grad_norm": 0.36331114172935486, "learning_rate": 7.46642637533626e-05, "loss": 0.3084, "step": 750 }, { "epoch": 0.0862227324913892, "grad_norm": 7.411865234375, "learning_rate": 7.464101615137756e-05, "loss": 0.3707, "step": 751 }, { "epoch": 0.08633754305396096, "grad_norm": 0.7940105199813843, "learning_rate": 7.461772165047798e-05, "loss": 0.3099, "step": 752 }, { "epoch": 0.08645235361653272, "grad_norm": 0.3989841043949127, "learning_rate": 7.459438028220125e-05, "loss": 0.3432, "step": 753 }, { "epoch": 0.08656716417910448, "grad_norm": 0.3940708339214325, "learning_rate": 7.45709920781482e-05, "loss": 0.298, "step": 754 }, { "epoch": 0.08668197474167623, "grad_norm": 0.39637166261672974, "learning_rate": 7.454755706998307e-05, "loss": 0.3268, "step": 755 }, { "epoch": 0.08679678530424799, "grad_norm": 0.374797523021698, "learning_rate": 7.452407528943345e-05, "loss": 0.2831, "step": 756 }, { "epoch": 0.08691159586681975, "grad_norm": 0.32488468289375305, "learning_rate": 7.45005467682903e-05, "loss": 0.3084, "step": 757 }, { "epoch": 0.08702640642939151, "grad_norm": 0.3303128778934479, "learning_rate": 7.447697153840781e-05, "loss": 0.3292, "step": 758 }, { "epoch": 0.08714121699196326, "grad_norm": 8.325894355773926, "learning_rate": 7.445334963170342e-05, "loss": 0.4769, "step": 759 }, { "epoch": 0.08725602755453502, "grad_norm": 0.4353140592575073, "learning_rate": 7.442968108015775e-05, "loss": 0.3143, "step": 760 }, { "epoch": 0.08737083811710677, "grad_norm": 0.28211238980293274, "learning_rate": 7.440596591581463e-05, "loss": 0.2997, "step": 761 }, { "epoch": 0.08748564867967853, "grad_norm": 0.313758909702301, "learning_rate": 7.438220417078092e-05, "loss": 0.279, "step": 762 }, { "epoch": 0.08760045924225028, "grad_norm": 0.30953410267829895, "learning_rate": 7.435839587722658e-05, "loss": 0.2936, "step": 763 }, { "epoch": 0.08771526980482204, "grad_norm": 5.524433612823486, "learning_rate": 7.433454106738462e-05, "loss": 0.3568, "step": 764 }, { "epoch": 0.0878300803673938, "grad_norm": 0.3863653540611267, "learning_rate": 7.431063977355095e-05, "loss": 0.3202, "step": 765 }, { "epoch": 0.08794489092996556, "grad_norm": 0.3130608797073364, "learning_rate": 7.42866920280845e-05, "loss": 0.2869, "step": 766 }, { "epoch": 0.0880597014925373, "grad_norm": 0.32509657740592957, "learning_rate": 7.426269786340701e-05, "loss": 0.2815, "step": 767 }, { "epoch": 0.08817451205510907, "grad_norm": 0.34580710530281067, "learning_rate": 7.423865731200313e-05, "loss": 0.2958, "step": 768 }, { "epoch": 0.08828932261768083, "grad_norm": 5.689088344573975, "learning_rate": 7.421457040642028e-05, "loss": 0.3945, "step": 769 }, { "epoch": 0.08840413318025259, "grad_norm": 0.3722037672996521, "learning_rate": 7.41904371792686e-05, "loss": 0.3066, "step": 770 }, { "epoch": 0.08851894374282435, "grad_norm": 0.31371334195137024, "learning_rate": 7.416625766322104e-05, "loss": 0.3038, "step": 771 }, { "epoch": 0.08863375430539609, "grad_norm": 0.36880406737327576, "learning_rate": 7.41420318910131e-05, "loss": 0.3303, "step": 772 }, { "epoch": 0.08874856486796785, "grad_norm": 0.3080020844936371, "learning_rate": 7.4117759895443e-05, "loss": 0.2774, "step": 773 }, { "epoch": 0.08886337543053961, "grad_norm": 0.30012673139572144, "learning_rate": 7.409344170937151e-05, "loss": 0.3015, "step": 774 }, { "epoch": 0.08897818599311137, "grad_norm": 0.2961469292640686, "learning_rate": 7.406907736572191e-05, "loss": 0.2896, "step": 775 }, { "epoch": 0.08909299655568312, "grad_norm": 0.3224990665912628, "learning_rate": 7.404466689747999e-05, "loss": 0.3038, "step": 776 }, { "epoch": 0.08920780711825488, "grad_norm": 0.29593345522880554, "learning_rate": 7.4020210337694e-05, "loss": 0.2912, "step": 777 }, { "epoch": 0.08932261768082664, "grad_norm": 0.306919127702713, "learning_rate": 7.399570771947456e-05, "loss": 0.2975, "step": 778 }, { "epoch": 0.0894374282433984, "grad_norm": 0.3186885714530945, "learning_rate": 7.397115907599467e-05, "loss": 0.2752, "step": 779 }, { "epoch": 0.08955223880597014, "grad_norm": 0.3553355634212494, "learning_rate": 7.394656444048964e-05, "loss": 0.2878, "step": 780 }, { "epoch": 0.0896670493685419, "grad_norm": 0.2943819761276245, "learning_rate": 7.392192384625704e-05, "loss": 0.3197, "step": 781 }, { "epoch": 0.08978185993111366, "grad_norm": 0.26438769698143005, "learning_rate": 7.389723732665666e-05, "loss": 0.283, "step": 782 }, { "epoch": 0.08989667049368542, "grad_norm": 0.28693610429763794, "learning_rate": 7.387250491511047e-05, "loss": 0.2995, "step": 783 }, { "epoch": 0.09001148105625717, "grad_norm": 0.259799987077713, "learning_rate": 7.384772664510257e-05, "loss": 0.2948, "step": 784 }, { "epoch": 0.09012629161882893, "grad_norm": 0.35070255398750305, "learning_rate": 7.382290255017914e-05, "loss": 0.3006, "step": 785 }, { "epoch": 0.09024110218140069, "grad_norm": 0.25889331102371216, "learning_rate": 7.379803266394842e-05, "loss": 0.2866, "step": 786 }, { "epoch": 0.09035591274397245, "grad_norm": 0.2893747389316559, "learning_rate": 7.377311702008061e-05, "loss": 0.2916, "step": 787 }, { "epoch": 0.0904707233065442, "grad_norm": 2.7846760749816895, "learning_rate": 7.37481556523079e-05, "loss": 0.2827, "step": 788 }, { "epoch": 0.09058553386911596, "grad_norm": 0.32907500863075256, "learning_rate": 7.372314859442435e-05, "loss": 0.2861, "step": 789 }, { "epoch": 0.09070034443168772, "grad_norm": 0.27642202377319336, "learning_rate": 7.369809588028591e-05, "loss": 0.2742, "step": 790 }, { "epoch": 0.09081515499425948, "grad_norm": 0.30868732929229736, "learning_rate": 7.36729975438103e-05, "loss": 0.2754, "step": 791 }, { "epoch": 0.09092996555683124, "grad_norm": 0.3307930529117584, "learning_rate": 7.364785361897705e-05, "loss": 0.2994, "step": 792 }, { "epoch": 0.09104477611940298, "grad_norm": 0.29497721791267395, "learning_rate": 7.362266413982737e-05, "loss": 0.2962, "step": 793 }, { "epoch": 0.09115958668197474, "grad_norm": 0.33250465989112854, "learning_rate": 7.359742914046418e-05, "loss": 0.319, "step": 794 }, { "epoch": 0.0912743972445465, "grad_norm": 0.31960466504096985, "learning_rate": 7.357214865505202e-05, "loss": 0.2846, "step": 795 }, { "epoch": 0.09138920780711826, "grad_norm": 0.2969323694705963, "learning_rate": 7.354682271781697e-05, "loss": 0.3034, "step": 796 }, { "epoch": 0.09150401836969001, "grad_norm": 0.3102553188800812, "learning_rate": 7.35214513630467e-05, "loss": 0.3117, "step": 797 }, { "epoch": 0.09161882893226177, "grad_norm": 0.3206898868083954, "learning_rate": 7.349603462509034e-05, "loss": 0.2976, "step": 798 }, { "epoch": 0.09173363949483353, "grad_norm": 0.3310270309448242, "learning_rate": 7.347057253835848e-05, "loss": 0.2979, "step": 799 }, { "epoch": 0.09184845005740529, "grad_norm": 1.672601580619812, "learning_rate": 7.344506513732308e-05, "loss": 0.3606, "step": 800 }, { "epoch": 0.09196326061997703, "grad_norm": 0.3583616614341736, "learning_rate": 7.341951245651747e-05, "loss": 0.2948, "step": 801 }, { "epoch": 0.09207807118254879, "grad_norm": 0.3071652054786682, "learning_rate": 7.339391453053627e-05, "loss": 0.3076, "step": 802 }, { "epoch": 0.09219288174512055, "grad_norm": 0.3392150104045868, "learning_rate": 7.336827139403537e-05, "loss": 0.3, "step": 803 }, { "epoch": 0.09230769230769231, "grad_norm": 0.4580688178539276, "learning_rate": 7.334258308173185e-05, "loss": 0.2958, "step": 804 }, { "epoch": 0.09242250287026406, "grad_norm": 0.30628418922424316, "learning_rate": 7.331684962840398e-05, "loss": 0.3035, "step": 805 }, { "epoch": 0.09253731343283582, "grad_norm": 0.31087520718574524, "learning_rate": 7.329107106889112e-05, "loss": 0.315, "step": 806 }, { "epoch": 0.09265212399540758, "grad_norm": 2.0308353900909424, "learning_rate": 7.326524743809368e-05, "loss": 0.2738, "step": 807 }, { "epoch": 0.09276693455797934, "grad_norm": 0.3669932782649994, "learning_rate": 7.323937877097313e-05, "loss": 0.2881, "step": 808 }, { "epoch": 0.09288174512055108, "grad_norm": 0.29288727045059204, "learning_rate": 7.321346510255191e-05, "loss": 0.2842, "step": 809 }, { "epoch": 0.09299655568312284, "grad_norm": 0.33061090111732483, "learning_rate": 7.318750646791335e-05, "loss": 0.2996, "step": 810 }, { "epoch": 0.0931113662456946, "grad_norm": 0.2889389097690582, "learning_rate": 7.316150290220167e-05, "loss": 0.2767, "step": 811 }, { "epoch": 0.09322617680826636, "grad_norm": 0.31812599301338196, "learning_rate": 7.313545444062196e-05, "loss": 0.2706, "step": 812 }, { "epoch": 0.09334098737083811, "grad_norm": 0.4706708788871765, "learning_rate": 7.310936111844004e-05, "loss": 0.2818, "step": 813 }, { "epoch": 0.09345579793340987, "grad_norm": 0.3318783640861511, "learning_rate": 7.308322297098248e-05, "loss": 0.3063, "step": 814 }, { "epoch": 0.09357060849598163, "grad_norm": 0.4720439910888672, "learning_rate": 7.305704003363655e-05, "loss": 0.3166, "step": 815 }, { "epoch": 0.09368541905855339, "grad_norm": 0.3042421340942383, "learning_rate": 7.303081234185017e-05, "loss": 0.3037, "step": 816 }, { "epoch": 0.09380022962112515, "grad_norm": 0.3289380967617035, "learning_rate": 7.300453993113181e-05, "loss": 0.3076, "step": 817 }, { "epoch": 0.0939150401836969, "grad_norm": 0.31327226758003235, "learning_rate": 7.297822283705051e-05, "loss": 0.2895, "step": 818 }, { "epoch": 0.09402985074626866, "grad_norm": 0.3587546944618225, "learning_rate": 7.29518610952358e-05, "loss": 0.3218, "step": 819 }, { "epoch": 0.09414466130884042, "grad_norm": 0.28843653202056885, "learning_rate": 7.292545474137769e-05, "loss": 0.2946, "step": 820 }, { "epoch": 0.09425947187141218, "grad_norm": 0.3169977366924286, "learning_rate": 7.28990038112265e-05, "loss": 0.3014, "step": 821 }, { "epoch": 0.09437428243398392, "grad_norm": 0.26648786664009094, "learning_rate": 7.287250834059298e-05, "loss": 0.2772, "step": 822 }, { "epoch": 0.09448909299655568, "grad_norm": 0.29466867446899414, "learning_rate": 7.284596836534817e-05, "loss": 0.3107, "step": 823 }, { "epoch": 0.09460390355912744, "grad_norm": 0.2602202296257019, "learning_rate": 7.281938392142333e-05, "loss": 0.2733, "step": 824 }, { "epoch": 0.0947187141216992, "grad_norm": 0.28139328956604004, "learning_rate": 7.279275504480995e-05, "loss": 0.294, "step": 825 }, { "epoch": 0.09483352468427095, "grad_norm": 0.2821626663208008, "learning_rate": 7.276608177155968e-05, "loss": 0.2954, "step": 826 }, { "epoch": 0.09494833524684271, "grad_norm": 0.25022950768470764, "learning_rate": 7.273936413778424e-05, "loss": 0.2839, "step": 827 }, { "epoch": 0.09506314580941447, "grad_norm": 0.29035526514053345, "learning_rate": 7.271260217965547e-05, "loss": 0.2941, "step": 828 }, { "epoch": 0.09517795637198623, "grad_norm": 0.27401530742645264, "learning_rate": 7.268579593340513e-05, "loss": 0.2868, "step": 829 }, { "epoch": 0.09529276693455797, "grad_norm": 0.25543543696403503, "learning_rate": 7.265894543532506e-05, "loss": 0.3137, "step": 830 }, { "epoch": 0.09540757749712973, "grad_norm": 0.2589137554168701, "learning_rate": 7.26320507217669e-05, "loss": 0.2706, "step": 831 }, { "epoch": 0.0955223880597015, "grad_norm": 0.2765255868434906, "learning_rate": 7.260511182914217e-05, "loss": 0.3151, "step": 832 }, { "epoch": 0.09563719862227325, "grad_norm": 0.2600555121898651, "learning_rate": 7.257812879392229e-05, "loss": 0.2779, "step": 833 }, { "epoch": 0.095752009184845, "grad_norm": 0.2715166211128235, "learning_rate": 7.255110165263832e-05, "loss": 0.2886, "step": 834 }, { "epoch": 0.09586681974741676, "grad_norm": 0.25423991680145264, "learning_rate": 7.252403044188111e-05, "loss": 0.2786, "step": 835 }, { "epoch": 0.09598163030998852, "grad_norm": 0.2523747980594635, "learning_rate": 7.249691519830118e-05, "loss": 0.2747, "step": 836 }, { "epoch": 0.09609644087256028, "grad_norm": 0.2555082440376282, "learning_rate": 7.24697559586086e-05, "loss": 0.3149, "step": 837 }, { "epoch": 0.09621125143513203, "grad_norm": 0.25518742203712463, "learning_rate": 7.244255275957307e-05, "loss": 0.2913, "step": 838 }, { "epoch": 0.09632606199770379, "grad_norm": 10.050409317016602, "learning_rate": 7.241530563802378e-05, "loss": 0.5881, "step": 839 }, { "epoch": 0.09644087256027555, "grad_norm": 0.33453404903411865, "learning_rate": 7.238801463084937e-05, "loss": 0.2861, "step": 840 }, { "epoch": 0.0965556831228473, "grad_norm": 0.2552434802055359, "learning_rate": 7.236067977499791e-05, "loss": 0.2879, "step": 841 }, { "epoch": 0.09667049368541906, "grad_norm": 0.27965107560157776, "learning_rate": 7.233330110747683e-05, "loss": 0.2875, "step": 842 }, { "epoch": 0.09678530424799081, "grad_norm": 1.5278956890106201, "learning_rate": 7.230587866535289e-05, "loss": 0.3314, "step": 843 }, { "epoch": 0.09690011481056257, "grad_norm": 0.27363139390945435, "learning_rate": 7.227841248575209e-05, "loss": 0.2823, "step": 844 }, { "epoch": 0.09701492537313433, "grad_norm": 2.0023953914642334, "learning_rate": 7.225090260585965e-05, "loss": 0.2966, "step": 845 }, { "epoch": 0.09712973593570609, "grad_norm": 0.3151177167892456, "learning_rate": 7.222334906291998e-05, "loss": 0.3111, "step": 846 }, { "epoch": 0.09724454649827784, "grad_norm": 0.25499817728996277, "learning_rate": 7.219575189423657e-05, "loss": 0.2721, "step": 847 }, { "epoch": 0.0973593570608496, "grad_norm": 0.33159899711608887, "learning_rate": 7.216811113717199e-05, "loss": 0.2872, "step": 848 }, { "epoch": 0.09747416762342136, "grad_norm": 0.29540571570396423, "learning_rate": 7.214042682914783e-05, "loss": 0.3011, "step": 849 }, { "epoch": 0.09758897818599312, "grad_norm": 0.25704333186149597, "learning_rate": 7.211269900764459e-05, "loss": 0.2689, "step": 850 }, { "epoch": 0.09770378874856486, "grad_norm": 0.2992681562900543, "learning_rate": 7.208492771020176e-05, "loss": 0.3082, "step": 851 }, { "epoch": 0.09781859931113662, "grad_norm": 6.727652549743652, "learning_rate": 7.205711297441763e-05, "loss": 0.4434, "step": 852 }, { "epoch": 0.09793340987370838, "grad_norm": 0.35064467787742615, "learning_rate": 7.202925483794934e-05, "loss": 0.2943, "step": 853 }, { "epoch": 0.09804822043628014, "grad_norm": 0.2743667960166931, "learning_rate": 7.200135333851276e-05, "loss": 0.3015, "step": 854 }, { "epoch": 0.09816303099885189, "grad_norm": 0.30704766511917114, "learning_rate": 7.197340851388247e-05, "loss": 0.2829, "step": 855 }, { "epoch": 0.09827784156142365, "grad_norm": 0.2917427718639374, "learning_rate": 7.194542040189171e-05, "loss": 0.2887, "step": 856 }, { "epoch": 0.09839265212399541, "grad_norm": 0.2912033498287201, "learning_rate": 7.191738904043235e-05, "loss": 0.2946, "step": 857 }, { "epoch": 0.09850746268656717, "grad_norm": 0.2969154417514801, "learning_rate": 7.188931446745476e-05, "loss": 0.2928, "step": 858 }, { "epoch": 0.09862227324913891, "grad_norm": 0.28630465269088745, "learning_rate": 7.186119672096785e-05, "loss": 0.2742, "step": 859 }, { "epoch": 0.09873708381171067, "grad_norm": 0.2616771459579468, "learning_rate": 7.183303583903899e-05, "loss": 0.282, "step": 860 }, { "epoch": 0.09885189437428243, "grad_norm": 0.3026432991027832, "learning_rate": 7.180483185979392e-05, "loss": 0.2907, "step": 861 }, { "epoch": 0.0989667049368542, "grad_norm": 0.2852618098258972, "learning_rate": 7.177658482141673e-05, "loss": 0.3014, "step": 862 }, { "epoch": 0.09908151549942595, "grad_norm": 9.608119010925293, "learning_rate": 7.174829476214983e-05, "loss": 0.3546, "step": 863 }, { "epoch": 0.0991963260619977, "grad_norm": 0.34986966848373413, "learning_rate": 7.171996172029385e-05, "loss": 0.2942, "step": 864 }, { "epoch": 0.09931113662456946, "grad_norm": 0.2767387926578522, "learning_rate": 7.169158573420764e-05, "loss": 0.284, "step": 865 }, { "epoch": 0.09942594718714122, "grad_norm": 0.46267029643058777, "learning_rate": 7.166316684230814e-05, "loss": 0.3015, "step": 866 }, { "epoch": 0.09954075774971298, "grad_norm": 0.2957901358604431, "learning_rate": 7.163470508307043e-05, "loss": 0.2707, "step": 867 }, { "epoch": 0.09965556831228473, "grad_norm": 0.3316187560558319, "learning_rate": 7.160620049502762e-05, "loss": 0.3093, "step": 868 }, { "epoch": 0.09977037887485649, "grad_norm": 0.40908801555633545, "learning_rate": 7.157765311677077e-05, "loss": 0.2978, "step": 869 }, { "epoch": 0.09988518943742825, "grad_norm": 0.2979099750518799, "learning_rate": 7.15490629869489e-05, "loss": 0.3094, "step": 870 }, { "epoch": 0.1, "grad_norm": 0.37567421793937683, "learning_rate": 7.152043014426888e-05, "loss": 0.2875, "step": 871 }, { "epoch": 0.10011481056257175, "grad_norm": 0.29294583201408386, "learning_rate": 7.149175462749546e-05, "loss": 0.3129, "step": 872 }, { "epoch": 0.10022962112514351, "grad_norm": 0.32895663380622864, "learning_rate": 7.146303647545114e-05, "loss": 0.3093, "step": 873 }, { "epoch": 0.10034443168771527, "grad_norm": 0.3269188404083252, "learning_rate": 7.143427572701608e-05, "loss": 0.3068, "step": 874 }, { "epoch": 0.10045924225028703, "grad_norm": 0.30391925573349, "learning_rate": 7.140547242112822e-05, "loss": 0.2871, "step": 875 }, { "epoch": 0.10057405281285878, "grad_norm": 0.3131577968597412, "learning_rate": 7.137662659678303e-05, "loss": 0.3014, "step": 876 }, { "epoch": 0.10068886337543054, "grad_norm": 0.28874891996383667, "learning_rate": 7.13477382930336e-05, "loss": 0.2753, "step": 877 }, { "epoch": 0.1008036739380023, "grad_norm": 0.2891666293144226, "learning_rate": 7.131880754899047e-05, "loss": 0.2861, "step": 878 }, { "epoch": 0.10091848450057406, "grad_norm": 0.3038763403892517, "learning_rate": 7.128983440382173e-05, "loss": 0.3002, "step": 879 }, { "epoch": 0.1010332950631458, "grad_norm": 0.2573010325431824, "learning_rate": 7.126081889675275e-05, "loss": 0.3018, "step": 880 }, { "epoch": 0.10114810562571756, "grad_norm": 0.2823447287082672, "learning_rate": 7.123176106706638e-05, "loss": 0.2886, "step": 881 }, { "epoch": 0.10126291618828932, "grad_norm": 0.7269818186759949, "learning_rate": 7.120266095410267e-05, "loss": 0.2819, "step": 882 }, { "epoch": 0.10137772675086108, "grad_norm": 4.418203830718994, "learning_rate": 7.117351859725897e-05, "loss": 0.3229, "step": 883 }, { "epoch": 0.10149253731343283, "grad_norm": 0.37244701385498047, "learning_rate": 7.114433403598981e-05, "loss": 0.2804, "step": 884 }, { "epoch": 0.10160734787600459, "grad_norm": 0.2561173141002655, "learning_rate": 7.111510730980686e-05, "loss": 0.2856, "step": 885 }, { "epoch": 0.10172215843857635, "grad_norm": 0.30422818660736084, "learning_rate": 7.108583845827884e-05, "loss": 0.271, "step": 886 }, { "epoch": 0.10183696900114811, "grad_norm": 0.24480925500392914, "learning_rate": 7.105652752103157e-05, "loss": 0.2599, "step": 887 }, { "epoch": 0.10195177956371987, "grad_norm": 0.3025079667568207, "learning_rate": 7.102717453774779e-05, "loss": 0.2874, "step": 888 }, { "epoch": 0.10206659012629161, "grad_norm": 0.27532798051834106, "learning_rate": 7.099777954816719e-05, "loss": 0.2748, "step": 889 }, { "epoch": 0.10218140068886337, "grad_norm": 0.28122562170028687, "learning_rate": 7.096834259208632e-05, "loss": 0.2674, "step": 890 }, { "epoch": 0.10229621125143513, "grad_norm": 0.39028802514076233, "learning_rate": 7.093886370935857e-05, "loss": 0.2832, "step": 891 }, { "epoch": 0.1024110218140069, "grad_norm": 18.860456466674805, "learning_rate": 7.090934293989405e-05, "loss": 0.4124, "step": 892 }, { "epoch": 0.10252583237657864, "grad_norm": 0.40460503101348877, "learning_rate": 7.087978032365961e-05, "loss": 0.2986, "step": 893 }, { "epoch": 0.1026406429391504, "grad_norm": 1.930730938911438, "learning_rate": 7.085017590067875e-05, "loss": 0.2985, "step": 894 }, { "epoch": 0.10275545350172216, "grad_norm": 0.3709445297718048, "learning_rate": 7.082052971103158e-05, "loss": 0.3054, "step": 895 }, { "epoch": 0.10287026406429392, "grad_norm": 0.2917740046977997, "learning_rate": 7.079084179485472e-05, "loss": 0.3002, "step": 896 }, { "epoch": 0.10298507462686567, "grad_norm": 0.2725986838340759, "learning_rate": 7.076111219234131e-05, "loss": 0.2811, "step": 897 }, { "epoch": 0.10309988518943743, "grad_norm": 0.2881290316581726, "learning_rate": 7.073134094374094e-05, "loss": 0.3087, "step": 898 }, { "epoch": 0.10321469575200919, "grad_norm": 0.31051307916641235, "learning_rate": 7.070152808935955e-05, "loss": 0.2882, "step": 899 }, { "epoch": 0.10332950631458095, "grad_norm": 0.3139895796775818, "learning_rate": 7.067167366955943e-05, "loss": 0.3024, "step": 900 }, { "epoch": 0.10344431687715269, "grad_norm": 0.3089105188846588, "learning_rate": 7.064177772475912e-05, "loss": 0.3093, "step": 901 }, { "epoch": 0.10355912743972445, "grad_norm": 0.2735717296600342, "learning_rate": 7.061184029543343e-05, "loss": 0.2826, "step": 902 }, { "epoch": 0.10367393800229621, "grad_norm": 0.2644566595554352, "learning_rate": 7.058186142211327e-05, "loss": 0.2827, "step": 903 }, { "epoch": 0.10378874856486797, "grad_norm": 0.29907122254371643, "learning_rate": 7.05518411453857e-05, "loss": 0.3109, "step": 904 }, { "epoch": 0.10390355912743972, "grad_norm": 0.2780683934688568, "learning_rate": 7.05217795058938e-05, "loss": 0.2981, "step": 905 }, { "epoch": 0.10401836969001148, "grad_norm": 1.0872058868408203, "learning_rate": 7.049167654433673e-05, "loss": 0.2982, "step": 906 }, { "epoch": 0.10413318025258324, "grad_norm": 0.2934883236885071, "learning_rate": 7.046153230146948e-05, "loss": 0.2832, "step": 907 }, { "epoch": 0.104247990815155, "grad_norm": 0.27279818058013916, "learning_rate": 7.0431346818103e-05, "loss": 0.2805, "step": 908 }, { "epoch": 0.10436280137772676, "grad_norm": 0.30134764313697815, "learning_rate": 7.040112013510407e-05, "loss": 0.2981, "step": 909 }, { "epoch": 0.1044776119402985, "grad_norm": 0.29230108857154846, "learning_rate": 7.037085229339523e-05, "loss": 0.305, "step": 910 }, { "epoch": 0.10459242250287026, "grad_norm": 0.29053428769111633, "learning_rate": 7.034054333395477e-05, "loss": 0.2709, "step": 911 }, { "epoch": 0.10470723306544202, "grad_norm": 0.39417487382888794, "learning_rate": 7.031019329781659e-05, "loss": 0.3087, "step": 912 }, { "epoch": 0.10482204362801378, "grad_norm": 0.26472753286361694, "learning_rate": 7.027980222607026e-05, "loss": 0.2566, "step": 913 }, { "epoch": 0.10493685419058553, "grad_norm": 0.29654961824417114, "learning_rate": 7.024937015986089e-05, "loss": 0.2683, "step": 914 }, { "epoch": 0.10505166475315729, "grad_norm": 0.3086019456386566, "learning_rate": 7.021889714038909e-05, "loss": 0.2946, "step": 915 }, { "epoch": 0.10516647531572905, "grad_norm": 0.30156973004341125, "learning_rate": 7.018838320891089e-05, "loss": 0.2759, "step": 916 }, { "epoch": 0.10528128587830081, "grad_norm": 0.2956296503543854, "learning_rate": 7.015782840673774e-05, "loss": 0.2847, "step": 917 }, { "epoch": 0.10539609644087256, "grad_norm": 0.2946214973926544, "learning_rate": 7.012723277523642e-05, "loss": 0.2729, "step": 918 }, { "epoch": 0.10551090700344432, "grad_norm": 0.2762398421764374, "learning_rate": 7.009659635582898e-05, "loss": 0.2969, "step": 919 }, { "epoch": 0.10562571756601608, "grad_norm": 0.32009562849998474, "learning_rate": 7.006591918999269e-05, "loss": 0.297, "step": 920 }, { "epoch": 0.10574052812858784, "grad_norm": 0.28615397214889526, "learning_rate": 7.003520131925997e-05, "loss": 0.2928, "step": 921 }, { "epoch": 0.10585533869115958, "grad_norm": 0.25491634011268616, "learning_rate": 7.000444278521839e-05, "loss": 0.2671, "step": 922 }, { "epoch": 0.10597014925373134, "grad_norm": 0.32191500067710876, "learning_rate": 6.997364362951052e-05, "loss": 0.3199, "step": 923 }, { "epoch": 0.1060849598163031, "grad_norm": 0.25138869881629944, "learning_rate": 6.994280389383398e-05, "loss": 0.2754, "step": 924 }, { "epoch": 0.10619977037887486, "grad_norm": 0.3310253620147705, "learning_rate": 6.991192361994129e-05, "loss": 0.2987, "step": 925 }, { "epoch": 0.10631458094144661, "grad_norm": 0.2823406159877777, "learning_rate": 6.988100284963985e-05, "loss": 0.3041, "step": 926 }, { "epoch": 0.10642939150401837, "grad_norm": 0.25814491510391235, "learning_rate": 6.985004162479191e-05, "loss": 0.2772, "step": 927 }, { "epoch": 0.10654420206659013, "grad_norm": 0.28782039880752563, "learning_rate": 6.981903998731449e-05, "loss": 0.2863, "step": 928 }, { "epoch": 0.10665901262916189, "grad_norm": 0.2988532483577728, "learning_rate": 6.978799797917932e-05, "loss": 0.2922, "step": 929 }, { "epoch": 0.10677382319173363, "grad_norm": 0.2941644787788391, "learning_rate": 6.975691564241274e-05, "loss": 0.2716, "step": 930 }, { "epoch": 0.10688863375430539, "grad_norm": 0.3009587824344635, "learning_rate": 6.972579301909577e-05, "loss": 0.2808, "step": 931 }, { "epoch": 0.10700344431687715, "grad_norm": 0.28304407000541687, "learning_rate": 6.969463015136391e-05, "loss": 0.2739, "step": 932 }, { "epoch": 0.10711825487944891, "grad_norm": 0.2693120837211609, "learning_rate": 6.966342708140719e-05, "loss": 0.2753, "step": 933 }, { "epoch": 0.10723306544202067, "grad_norm": 0.27009931206703186, "learning_rate": 6.963218385147e-05, "loss": 0.3092, "step": 934 }, { "epoch": 0.10734787600459242, "grad_norm": 0.30220264196395874, "learning_rate": 6.960090050385119e-05, "loss": 0.2811, "step": 935 }, { "epoch": 0.10746268656716418, "grad_norm": 0.30022332072257996, "learning_rate": 6.956957708090384e-05, "loss": 0.2857, "step": 936 }, { "epoch": 0.10757749712973594, "grad_norm": 0.24674537777900696, "learning_rate": 6.953821362503537e-05, "loss": 0.2785, "step": 937 }, { "epoch": 0.1076923076923077, "grad_norm": 0.27303028106689453, "learning_rate": 6.950681017870729e-05, "loss": 0.2862, "step": 938 }, { "epoch": 0.10780711825487944, "grad_norm": 0.25801393389701843, "learning_rate": 6.947536678443537e-05, "loss": 0.3021, "step": 939 }, { "epoch": 0.1079219288174512, "grad_norm": 0.25481051206588745, "learning_rate": 6.944388348478939e-05, "loss": 0.2851, "step": 940 }, { "epoch": 0.10803673938002296, "grad_norm": 0.3100113868713379, "learning_rate": 6.941236032239316e-05, "loss": 0.2872, "step": 941 }, { "epoch": 0.10815154994259472, "grad_norm": 0.2488914579153061, "learning_rate": 6.938079733992448e-05, "loss": 0.2819, "step": 942 }, { "epoch": 0.10826636050516647, "grad_norm": 0.2713686227798462, "learning_rate": 6.934919458011506e-05, "loss": 0.2779, "step": 943 }, { "epoch": 0.10838117106773823, "grad_norm": 0.8217819929122925, "learning_rate": 6.931755208575046e-05, "loss": 0.2761, "step": 944 }, { "epoch": 0.10849598163030999, "grad_norm": 0.2579963207244873, "learning_rate": 6.928586989967001e-05, "loss": 0.2763, "step": 945 }, { "epoch": 0.10861079219288175, "grad_norm": 0.27462202310562134, "learning_rate": 6.925414806476683e-05, "loss": 0.303, "step": 946 }, { "epoch": 0.1087256027554535, "grad_norm": 2.1155333518981934, "learning_rate": 6.922238662398766e-05, "loss": 0.2924, "step": 947 }, { "epoch": 0.10884041331802526, "grad_norm": 1.7216750383377075, "learning_rate": 6.919058562033287e-05, "loss": 0.297, "step": 948 }, { "epoch": 0.10895522388059702, "grad_norm": 0.35788658261299133, "learning_rate": 6.915874509685646e-05, "loss": 0.3158, "step": 949 }, { "epoch": 0.10907003444316878, "grad_norm": 0.2948894500732422, "learning_rate": 6.912686509666585e-05, "loss": 0.2804, "step": 950 }, { "epoch": 0.10918484500574052, "grad_norm": 0.30967047810554504, "learning_rate": 6.909494566292195e-05, "loss": 0.2657, "step": 951 }, { "epoch": 0.10929965556831228, "grad_norm": 1.5363909006118774, "learning_rate": 6.906298683883905e-05, "loss": 0.3554, "step": 952 }, { "epoch": 0.10941446613088404, "grad_norm": 0.36822429299354553, "learning_rate": 6.903098866768474e-05, "loss": 0.301, "step": 953 }, { "epoch": 0.1095292766934558, "grad_norm": 0.2651078701019287, "learning_rate": 6.899895119277993e-05, "loss": 0.2934, "step": 954 }, { "epoch": 0.10964408725602756, "grad_norm": 0.2794734239578247, "learning_rate": 6.896687445749871e-05, "loss": 0.2917, "step": 955 }, { "epoch": 0.10975889781859931, "grad_norm": 0.27656397223472595, "learning_rate": 6.893475850526832e-05, "loss": 0.2815, "step": 956 }, { "epoch": 0.10987370838117107, "grad_norm": 0.28293851017951965, "learning_rate": 6.890260337956913e-05, "loss": 0.296, "step": 957 }, { "epoch": 0.10998851894374283, "grad_norm": 5.222631454467773, "learning_rate": 6.887040912393449e-05, "loss": 0.4611, "step": 958 }, { "epoch": 0.11010332950631459, "grad_norm": 2.557804822921753, "learning_rate": 6.883817578195078e-05, "loss": 0.3691, "step": 959 }, { "epoch": 0.11021814006888633, "grad_norm": 0.3786827623844147, "learning_rate": 6.880590339725725e-05, "loss": 0.2882, "step": 960 }, { "epoch": 0.1103329506314581, "grad_norm": 0.34763237833976746, "learning_rate": 6.877359201354606e-05, "loss": 0.2951, "step": 961 }, { "epoch": 0.11044776119402985, "grad_norm": 0.34259483218193054, "learning_rate": 6.87412416745621e-05, "loss": 0.2888, "step": 962 }, { "epoch": 0.11056257175660161, "grad_norm": 0.3114844560623169, "learning_rate": 6.870885242410307e-05, "loss": 0.2791, "step": 963 }, { "epoch": 0.11067738231917336, "grad_norm": 0.3578057587146759, "learning_rate": 6.867642430601932e-05, "loss": 0.2985, "step": 964 }, { "epoch": 0.11079219288174512, "grad_norm": 0.3261001408100128, "learning_rate": 6.86439573642138e-05, "loss": 0.3081, "step": 965 }, { "epoch": 0.11090700344431688, "grad_norm": 3.673293113708496, "learning_rate": 6.861145164264207e-05, "loss": 0.2919, "step": 966 }, { "epoch": 0.11102181400688864, "grad_norm": 0.38675379753112793, "learning_rate": 6.857890718531213e-05, "loss": 0.2659, "step": 967 }, { "epoch": 0.11113662456946038, "grad_norm": 0.2793339788913727, "learning_rate": 6.85463240362845e-05, "loss": 0.2785, "step": 968 }, { "epoch": 0.11125143513203214, "grad_norm": 0.353410005569458, "learning_rate": 6.851370223967202e-05, "loss": 0.2924, "step": 969 }, { "epoch": 0.1113662456946039, "grad_norm": 0.2848592698574066, "learning_rate": 6.848104183963988e-05, "loss": 0.281, "step": 970 }, { "epoch": 0.11148105625717566, "grad_norm": 0.3216843605041504, "learning_rate": 6.844834288040548e-05, "loss": 0.3059, "step": 971 }, { "epoch": 0.11159586681974741, "grad_norm": 0.2879785895347595, "learning_rate": 6.841560540623856e-05, "loss": 0.295, "step": 972 }, { "epoch": 0.11171067738231917, "grad_norm": 0.2948487401008606, "learning_rate": 6.838282946146084e-05, "loss": 0.2879, "step": 973 }, { "epoch": 0.11182548794489093, "grad_norm": 0.29160627722740173, "learning_rate": 6.835001509044623e-05, "loss": 0.285, "step": 974 }, { "epoch": 0.11194029850746269, "grad_norm": 1.4655203819274902, "learning_rate": 6.831716233762063e-05, "loss": 0.3718, "step": 975 }, { "epoch": 0.11205510907003444, "grad_norm": 0.3602631688117981, "learning_rate": 6.828427124746191e-05, "loss": 0.2962, "step": 976 }, { "epoch": 0.1121699196326062, "grad_norm": 0.2976577877998352, "learning_rate": 6.825134186449981e-05, "loss": 0.3017, "step": 977 }, { "epoch": 0.11228473019517796, "grad_norm": 0.3193801939487457, "learning_rate": 6.821837423331598e-05, "loss": 0.3272, "step": 978 }, { "epoch": 0.11239954075774972, "grad_norm": 0.4227851927280426, "learning_rate": 6.818536839854379e-05, "loss": 0.2888, "step": 979 }, { "epoch": 0.11251435132032148, "grad_norm": 0.3625994622707367, "learning_rate": 6.815232440486837e-05, "loss": 0.2896, "step": 980 }, { "epoch": 0.11262916188289322, "grad_norm": 0.27800679206848145, "learning_rate": 6.811924229702648e-05, "loss": 0.2685, "step": 981 }, { "epoch": 0.11274397244546498, "grad_norm": 0.29960405826568604, "learning_rate": 6.808612211980651e-05, "loss": 0.2895, "step": 982 }, { "epoch": 0.11285878300803674, "grad_norm": 0.27302882075309753, "learning_rate": 6.805296391804836e-05, "loss": 0.2672, "step": 983 }, { "epoch": 0.1129735935706085, "grad_norm": 0.27410271763801575, "learning_rate": 6.801976773664347e-05, "loss": 0.2783, "step": 984 }, { "epoch": 0.11308840413318025, "grad_norm": 0.30808863043785095, "learning_rate": 6.798653362053462e-05, "loss": 0.3085, "step": 985 }, { "epoch": 0.11320321469575201, "grad_norm": 0.3312918245792389, "learning_rate": 6.7953261614716e-05, "loss": 0.2946, "step": 986 }, { "epoch": 0.11331802525832377, "grad_norm": 0.3060612678527832, "learning_rate": 6.79199517642331e-05, "loss": 0.2958, "step": 987 }, { "epoch": 0.11343283582089553, "grad_norm": 0.27072757482528687, "learning_rate": 6.78866041141826e-05, "loss": 0.2801, "step": 988 }, { "epoch": 0.11354764638346727, "grad_norm": 0.2740454077720642, "learning_rate": 6.785321870971238e-05, "loss": 0.2834, "step": 989 }, { "epoch": 0.11366245694603903, "grad_norm": 0.2750706076622009, "learning_rate": 6.781979559602146e-05, "loss": 0.3215, "step": 990 }, { "epoch": 0.1137772675086108, "grad_norm": 0.2648540437221527, "learning_rate": 6.778633481835989e-05, "loss": 0.315, "step": 991 }, { "epoch": 0.11389207807118255, "grad_norm": 0.599629282951355, "learning_rate": 6.775283642202871e-05, "loss": 0.2927, "step": 992 }, { "epoch": 0.1140068886337543, "grad_norm": 0.2738407254219055, "learning_rate": 6.771930045237989e-05, "loss": 0.2981, "step": 993 }, { "epoch": 0.11412169919632606, "grad_norm": 0.3279378414154053, "learning_rate": 6.768572695481628e-05, "loss": 0.2818, "step": 994 }, { "epoch": 0.11423650975889782, "grad_norm": 0.9017176032066345, "learning_rate": 6.76521159747915e-05, "loss": 0.284, "step": 995 }, { "epoch": 0.11435132032146958, "grad_norm": 0.26213809847831726, "learning_rate": 6.761846755780999e-05, "loss": 0.289, "step": 996 }, { "epoch": 0.11446613088404133, "grad_norm": 0.24953387677669525, "learning_rate": 6.75847817494268e-05, "loss": 0.2914, "step": 997 }, { "epoch": 0.11458094144661309, "grad_norm": 4.524369716644287, "learning_rate": 6.755105859524764e-05, "loss": 0.37, "step": 998 }, { "epoch": 0.11469575200918485, "grad_norm": 0.34678250551223755, "learning_rate": 6.751729814092874e-05, "loss": 0.2916, "step": 999 }, { "epoch": 0.1148105625717566, "grad_norm": 0.2670215964317322, "learning_rate": 6.748350043217693e-05, "loss": 0.2687, "step": 1000 }, { "epoch": 0.11492537313432835, "grad_norm": 0.2807745039463043, "learning_rate": 6.744966551474936e-05, "loss": 0.2879, "step": 1001 }, { "epoch": 0.11504018369690011, "grad_norm": 0.3273930549621582, "learning_rate": 6.74157934344536e-05, "loss": 0.3164, "step": 1002 }, { "epoch": 0.11515499425947187, "grad_norm": 0.2841406464576721, "learning_rate": 6.738188423714756e-05, "loss": 0.2928, "step": 1003 }, { "epoch": 0.11526980482204363, "grad_norm": 0.49369269609451294, "learning_rate": 6.734793796873936e-05, "loss": 0.2846, "step": 1004 }, { "epoch": 0.11538461538461539, "grad_norm": 2.274894952774048, "learning_rate": 6.731395467518734e-05, "loss": 0.3059, "step": 1005 }, { "epoch": 0.11549942594718714, "grad_norm": 0.3366522490978241, "learning_rate": 6.727993440249995e-05, "loss": 0.2928, "step": 1006 }, { "epoch": 0.1156142365097589, "grad_norm": 0.2826286852359772, "learning_rate": 6.724587719673571e-05, "loss": 0.2903, "step": 1007 }, { "epoch": 0.11572904707233066, "grad_norm": 1.9895967245101929, "learning_rate": 6.721178310400313e-05, "loss": 0.3394, "step": 1008 }, { "epoch": 0.11584385763490242, "grad_norm": 0.32216668128967285, "learning_rate": 6.717765217046067e-05, "loss": 0.2883, "step": 1009 }, { "epoch": 0.11595866819747416, "grad_norm": 0.2953006625175476, "learning_rate": 6.714348444231667e-05, "loss": 0.2972, "step": 1010 }, { "epoch": 0.11607347876004592, "grad_norm": 3.6414523124694824, "learning_rate": 6.71092799658293e-05, "loss": 0.3629, "step": 1011 }, { "epoch": 0.11618828932261768, "grad_norm": 0.561702311038971, "learning_rate": 6.707503878730643e-05, "loss": 0.3023, "step": 1012 }, { "epoch": 0.11630309988518944, "grad_norm": 6.134464740753174, "learning_rate": 6.704076095310567e-05, "loss": 0.318, "step": 1013 }, { "epoch": 0.11641791044776119, "grad_norm": 0.4212198555469513, "learning_rate": 6.700644650963427e-05, "loss": 0.3042, "step": 1014 }, { "epoch": 0.11653272101033295, "grad_norm": 0.32747888565063477, "learning_rate": 6.697209550334893e-05, "loss": 0.307, "step": 1015 }, { "epoch": 0.11664753157290471, "grad_norm": 0.32408398389816284, "learning_rate": 6.693770798075601e-05, "loss": 0.2868, "step": 1016 }, { "epoch": 0.11676234213547647, "grad_norm": 0.3437534272670746, "learning_rate": 6.690328398841122e-05, "loss": 0.2952, "step": 1017 }, { "epoch": 0.11687715269804821, "grad_norm": 0.26557785272598267, "learning_rate": 6.686882357291962e-05, "loss": 0.269, "step": 1018 }, { "epoch": 0.11699196326061997, "grad_norm": 0.3058113157749176, "learning_rate": 6.683432678093564e-05, "loss": 0.2918, "step": 1019 }, { "epoch": 0.11710677382319173, "grad_norm": 0.2702030837535858, "learning_rate": 6.679979365916293e-05, "loss": 0.2715, "step": 1020 }, { "epoch": 0.1172215843857635, "grad_norm": 0.29631319642066956, "learning_rate": 6.676522425435433e-05, "loss": 0.3111, "step": 1021 }, { "epoch": 0.11733639494833524, "grad_norm": 3.122999668121338, "learning_rate": 6.673061861331181e-05, "loss": 0.3952, "step": 1022 }, { "epoch": 0.117451205510907, "grad_norm": 0.3681066334247589, "learning_rate": 6.66959767828864e-05, "loss": 0.2757, "step": 1023 }, { "epoch": 0.11756601607347876, "grad_norm": 0.3060511648654938, "learning_rate": 6.66612988099781e-05, "loss": 0.2899, "step": 1024 }, { "epoch": 0.11768082663605052, "grad_norm": 0.29683372378349304, "learning_rate": 6.662658474153588e-05, "loss": 0.2917, "step": 1025 }, { "epoch": 0.11779563719862228, "grad_norm": 0.2730123996734619, "learning_rate": 6.659183462455751e-05, "loss": 0.3027, "step": 1026 }, { "epoch": 0.11791044776119403, "grad_norm": 0.3012874126434326, "learning_rate": 6.655704850608967e-05, "loss": 0.2885, "step": 1027 }, { "epoch": 0.11802525832376579, "grad_norm": 0.30258709192276, "learning_rate": 6.652222643322768e-05, "loss": 0.28, "step": 1028 }, { "epoch": 0.11814006888633755, "grad_norm": 0.30155739188194275, "learning_rate": 6.648736845311561e-05, "loss": 0.2936, "step": 1029 }, { "epoch": 0.1182548794489093, "grad_norm": 0.29328420758247375, "learning_rate": 6.645247461294608e-05, "loss": 0.2966, "step": 1030 }, { "epoch": 0.11836969001148105, "grad_norm": 0.31318962574005127, "learning_rate": 6.641754495996031e-05, "loss": 0.2926, "step": 1031 }, { "epoch": 0.11848450057405281, "grad_norm": 0.41378119587898254, "learning_rate": 6.6382579541448e-05, "loss": 0.303, "step": 1032 }, { "epoch": 0.11859931113662457, "grad_norm": 0.30762556195259094, "learning_rate": 6.634757840474721e-05, "loss": 0.284, "step": 1033 }, { "epoch": 0.11871412169919633, "grad_norm": 0.2755800783634186, "learning_rate": 6.631254159724448e-05, "loss": 0.301, "step": 1034 }, { "epoch": 0.11882893226176808, "grad_norm": 5.052371025085449, "learning_rate": 6.627746916637451e-05, "loss": 0.6564, "step": 1035 }, { "epoch": 0.11894374282433984, "grad_norm": 0.41972628235816956, "learning_rate": 6.62423611596203e-05, "loss": 0.282, "step": 1036 }, { "epoch": 0.1190585533869116, "grad_norm": 0.26415354013442993, "learning_rate": 6.6207217624513e-05, "loss": 0.2902, "step": 1037 }, { "epoch": 0.11917336394948336, "grad_norm": 0.3349628150463104, "learning_rate": 6.617203860863189e-05, "loss": 0.2816, "step": 1038 }, { "epoch": 0.1192881745120551, "grad_norm": 0.30530571937561035, "learning_rate": 6.613682415960423e-05, "loss": 0.2955, "step": 1039 }, { "epoch": 0.11940298507462686, "grad_norm": 0.27225252985954285, "learning_rate": 6.610157432510528e-05, "loss": 0.296, "step": 1040 }, { "epoch": 0.11951779563719862, "grad_norm": 0.32068997621536255, "learning_rate": 6.606628915285822e-05, "loss": 0.2953, "step": 1041 }, { "epoch": 0.11963260619977038, "grad_norm": 0.3619413673877716, "learning_rate": 6.603096869063404e-05, "loss": 0.3011, "step": 1042 }, { "epoch": 0.11974741676234213, "grad_norm": 4.945443630218506, "learning_rate": 6.599561298625156e-05, "loss": 0.3158, "step": 1043 }, { "epoch": 0.11986222732491389, "grad_norm": 0.3700699806213379, "learning_rate": 6.596022208757724e-05, "loss": 0.2599, "step": 1044 }, { "epoch": 0.11997703788748565, "grad_norm": 3.396380662918091, "learning_rate": 6.592479604252525e-05, "loss": 0.4557, "step": 1045 }, { "epoch": 0.12009184845005741, "grad_norm": 0.33735668659210205, "learning_rate": 6.58893348990573e-05, "loss": 0.2809, "step": 1046 }, { "epoch": 0.12020665901262916, "grad_norm": 2.1303937435150146, "learning_rate": 6.585383870518266e-05, "loss": 0.2959, "step": 1047 }, { "epoch": 0.12032146957520092, "grad_norm": 0.3016626238822937, "learning_rate": 6.581830750895803e-05, "loss": 0.3039, "step": 1048 }, { "epoch": 0.12043628013777267, "grad_norm": 0.45184311270713806, "learning_rate": 6.578274135848749e-05, "loss": 0.3281, "step": 1049 }, { "epoch": 0.12055109070034443, "grad_norm": 0.30768200755119324, "learning_rate": 6.574714030192244e-05, "loss": 0.3029, "step": 1050 }, { "epoch": 0.1206659012629162, "grad_norm": 0.29460078477859497, "learning_rate": 6.571150438746157e-05, "loss": 0.2671, "step": 1051 }, { "epoch": 0.12078071182548794, "grad_norm": 18.638893127441406, "learning_rate": 6.567583366335075e-05, "loss": 0.6236, "step": 1052 }, { "epoch": 0.1208955223880597, "grad_norm": 0.38345688581466675, "learning_rate": 6.564012817788294e-05, "loss": 0.2622, "step": 1053 }, { "epoch": 0.12101033295063146, "grad_norm": 0.32559671998023987, "learning_rate": 6.560438797939823e-05, "loss": 0.2864, "step": 1054 }, { "epoch": 0.12112514351320322, "grad_norm": 0.34540948271751404, "learning_rate": 6.556861311628362e-05, "loss": 0.2816, "step": 1055 }, { "epoch": 0.12123995407577497, "grad_norm": 0.3018190860748291, "learning_rate": 6.553280363697314e-05, "loss": 0.3109, "step": 1056 }, { "epoch": 0.12135476463834673, "grad_norm": 2.6995463371276855, "learning_rate": 6.54969595899476e-05, "loss": 0.3741, "step": 1057 }, { "epoch": 0.12146957520091849, "grad_norm": 0.3678658604621887, "learning_rate": 6.546108102373465e-05, "loss": 0.2976, "step": 1058 }, { "epoch": 0.12158438576349025, "grad_norm": 0.3117091953754425, "learning_rate": 6.542516798690868e-05, "loss": 0.2882, "step": 1059 }, { "epoch": 0.12169919632606199, "grad_norm": 0.33670875430107117, "learning_rate": 6.538922052809071e-05, "loss": 0.293, "step": 1060 }, { "epoch": 0.12181400688863375, "grad_norm": 4.833683490753174, "learning_rate": 6.53532386959484e-05, "loss": 0.4344, "step": 1061 }, { "epoch": 0.12192881745120551, "grad_norm": 6.093814373016357, "learning_rate": 6.531722253919597e-05, "loss": 0.4397, "step": 1062 }, { "epoch": 0.12204362801377727, "grad_norm": 0.496830016374588, "learning_rate": 6.528117210659405e-05, "loss": 0.289, "step": 1063 }, { "epoch": 0.12215843857634902, "grad_norm": 0.29621434211730957, "learning_rate": 6.524508744694967e-05, "loss": 0.2955, "step": 1064 }, { "epoch": 0.12227324913892078, "grad_norm": 0.3745307922363281, "learning_rate": 6.520896860911627e-05, "loss": 0.3245, "step": 1065 }, { "epoch": 0.12238805970149254, "grad_norm": 0.3304233253002167, "learning_rate": 6.51728156419935e-05, "loss": 0.3314, "step": 1066 }, { "epoch": 0.1225028702640643, "grad_norm": 0.36154448986053467, "learning_rate": 6.513662859452725e-05, "loss": 0.3055, "step": 1067 }, { "epoch": 0.12261768082663604, "grad_norm": 0.3069334030151367, "learning_rate": 6.510040751570953e-05, "loss": 0.3078, "step": 1068 }, { "epoch": 0.1227324913892078, "grad_norm": 0.3152971863746643, "learning_rate": 6.506415245457842e-05, "loss": 0.2937, "step": 1069 }, { "epoch": 0.12284730195177956, "grad_norm": 0.31675952672958374, "learning_rate": 6.502786346021804e-05, "loss": 0.3, "step": 1070 }, { "epoch": 0.12296211251435132, "grad_norm": 0.2654459476470947, "learning_rate": 6.499154058175841e-05, "loss": 0.2794, "step": 1071 }, { "epoch": 0.12307692307692308, "grad_norm": 0.4949955940246582, "learning_rate": 6.495518386837546e-05, "loss": 0.3057, "step": 1072 }, { "epoch": 0.12319173363949483, "grad_norm": 0.2764497399330139, "learning_rate": 6.491879336929088e-05, "loss": 0.3053, "step": 1073 }, { "epoch": 0.12330654420206659, "grad_norm": 0.3874606788158417, "learning_rate": 6.488236913377217e-05, "loss": 0.277, "step": 1074 }, { "epoch": 0.12342135476463835, "grad_norm": 0.2727513909339905, "learning_rate": 6.484591121113242e-05, "loss": 0.2895, "step": 1075 }, { "epoch": 0.12353616532721011, "grad_norm": 0.3332230746746063, "learning_rate": 6.480941965073041e-05, "loss": 0.3085, "step": 1076 }, { "epoch": 0.12365097588978186, "grad_norm": 0.30431073904037476, "learning_rate": 6.477289450197041e-05, "loss": 0.2957, "step": 1077 }, { "epoch": 0.12376578645235362, "grad_norm": 0.33410096168518066, "learning_rate": 6.473633581430217e-05, "loss": 0.29, "step": 1078 }, { "epoch": 0.12388059701492538, "grad_norm": 0.28216007351875305, "learning_rate": 6.469974363722086e-05, "loss": 0.2888, "step": 1079 }, { "epoch": 0.12399540757749714, "grad_norm": 0.3899376690387726, "learning_rate": 6.4663118020267e-05, "loss": 0.2872, "step": 1080 }, { "epoch": 0.12411021814006888, "grad_norm": 0.267685204744339, "learning_rate": 6.462645901302633e-05, "loss": 0.2984, "step": 1081 }, { "epoch": 0.12422502870264064, "grad_norm": 0.2540953755378723, "learning_rate": 6.458976666512987e-05, "loss": 0.2682, "step": 1082 }, { "epoch": 0.1243398392652124, "grad_norm": 0.42375648021698, "learning_rate": 6.455304102625371e-05, "loss": 0.289, "step": 1083 }, { "epoch": 0.12445464982778416, "grad_norm": 8.473679542541504, "learning_rate": 6.451628214611907e-05, "loss": 0.503, "step": 1084 }, { "epoch": 0.12456946039035591, "grad_norm": 1.0285022258758545, "learning_rate": 6.447949007449211e-05, "loss": 0.2975, "step": 1085 }, { "epoch": 0.12468427095292767, "grad_norm": 0.33209526538848877, "learning_rate": 6.4442664861184e-05, "loss": 0.2946, "step": 1086 }, { "epoch": 0.12479908151549943, "grad_norm": 0.3694206178188324, "learning_rate": 6.440580655605073e-05, "loss": 0.3035, "step": 1087 }, { "epoch": 0.12491389207807119, "grad_norm": 0.6370159387588501, "learning_rate": 6.436891520899305e-05, "loss": 0.3078, "step": 1088 }, { "epoch": 0.12502870264064295, "grad_norm": 0.3137515187263489, "learning_rate": 6.433199086995658e-05, "loss": 0.3004, "step": 1089 }, { "epoch": 0.1251435132032147, "grad_norm": 0.3838232755661011, "learning_rate": 6.429503358893148e-05, "loss": 0.3034, "step": 1090 }, { "epoch": 0.12525832376578644, "grad_norm": 0.35137689113616943, "learning_rate": 6.425804341595255e-05, "loss": 0.2768, "step": 1091 }, { "epoch": 0.1253731343283582, "grad_norm": 0.3320390284061432, "learning_rate": 6.422102040109913e-05, "loss": 0.2969, "step": 1092 }, { "epoch": 0.12548794489092996, "grad_norm": 0.41607046127319336, "learning_rate": 6.418396459449501e-05, "loss": 0.3427, "step": 1093 }, { "epoch": 0.12560275545350172, "grad_norm": 0.31903061270713806, "learning_rate": 6.414687604630838e-05, "loss": 0.2725, "step": 1094 }, { "epoch": 0.12571756601607348, "grad_norm": 0.2705884873867035, "learning_rate": 6.410975480675175e-05, "loss": 0.2942, "step": 1095 }, { "epoch": 0.12583237657864524, "grad_norm": 0.29530569911003113, "learning_rate": 6.407260092608195e-05, "loss": 0.2969, "step": 1096 }, { "epoch": 0.125947187141217, "grad_norm": 0.2871039807796478, "learning_rate": 6.403541445459988e-05, "loss": 0.3287, "step": 1097 }, { "epoch": 0.12606199770378876, "grad_norm": 0.2824048697948456, "learning_rate": 6.399819544265066e-05, "loss": 0.308, "step": 1098 }, { "epoch": 0.12617680826636052, "grad_norm": 0.2678207457065582, "learning_rate": 6.396094394062344e-05, "loss": 0.2761, "step": 1099 }, { "epoch": 0.12629161882893225, "grad_norm": 0.25959643721580505, "learning_rate": 6.392365999895136e-05, "loss": 0.2936, "step": 1100 }, { "epoch": 0.126406429391504, "grad_norm": 0.29813313484191895, "learning_rate": 6.388634366811146e-05, "loss": 0.2872, "step": 1101 }, { "epoch": 0.12652123995407577, "grad_norm": 7.32001256942749, "learning_rate": 6.384899499862463e-05, "loss": 0.4333, "step": 1102 }, { "epoch": 0.12663605051664753, "grad_norm": 0.3411814570426941, "learning_rate": 6.38116140410556e-05, "loss": 0.312, "step": 1103 }, { "epoch": 0.1267508610792193, "grad_norm": 0.4236845374107361, "learning_rate": 6.377420084601272e-05, "loss": 0.2706, "step": 1104 }, { "epoch": 0.12686567164179105, "grad_norm": 1.7648584842681885, "learning_rate": 6.373675546414807e-05, "loss": 0.3419, "step": 1105 }, { "epoch": 0.1269804822043628, "grad_norm": 0.3100890815258026, "learning_rate": 6.369927794615723e-05, "loss": 0.2936, "step": 1106 }, { "epoch": 0.12709529276693457, "grad_norm": 0.28817853331565857, "learning_rate": 6.366176834277936e-05, "loss": 0.3098, "step": 1107 }, { "epoch": 0.1272101033295063, "grad_norm": 0.29280102252960205, "learning_rate": 6.362422670479702e-05, "loss": 0.3136, "step": 1108 }, { "epoch": 0.12732491389207806, "grad_norm": 0.36914220452308655, "learning_rate": 6.358665308303613e-05, "loss": 0.2869, "step": 1109 }, { "epoch": 0.12743972445464982, "grad_norm": 0.2721240818500519, "learning_rate": 6.354904752836595e-05, "loss": 0.2994, "step": 1110 }, { "epoch": 0.12755453501722158, "grad_norm": 0.23335929214954376, "learning_rate": 6.351141009169893e-05, "loss": 0.2581, "step": 1111 }, { "epoch": 0.12766934557979334, "grad_norm": 0.2548462450504303, "learning_rate": 6.347374082399071e-05, "loss": 0.2664, "step": 1112 }, { "epoch": 0.1277841561423651, "grad_norm": 0.2619427442550659, "learning_rate": 6.343603977624002e-05, "loss": 0.2886, "step": 1113 }, { "epoch": 0.12789896670493686, "grad_norm": 0.2497786581516266, "learning_rate": 6.339830699948863e-05, "loss": 0.2976, "step": 1114 }, { "epoch": 0.12801377726750862, "grad_norm": 0.28319862484931946, "learning_rate": 6.336054254482122e-05, "loss": 0.2686, "step": 1115 }, { "epoch": 0.12812858783008035, "grad_norm": 1.6808079481124878, "learning_rate": 6.332274646336539e-05, "loss": 0.2923, "step": 1116 }, { "epoch": 0.1282433983926521, "grad_norm": 0.254387229681015, "learning_rate": 6.328491880629159e-05, "loss": 0.2737, "step": 1117 }, { "epoch": 0.12835820895522387, "grad_norm": 0.27317166328430176, "learning_rate": 6.324705962481294e-05, "loss": 0.2765, "step": 1118 }, { "epoch": 0.12847301951779563, "grad_norm": 0.2413185089826584, "learning_rate": 6.320916897018532e-05, "loss": 0.2682, "step": 1119 }, { "epoch": 0.1285878300803674, "grad_norm": 0.2630564868450165, "learning_rate": 6.317124689370715e-05, "loss": 0.2923, "step": 1120 }, { "epoch": 0.12870264064293915, "grad_norm": 0.25741004943847656, "learning_rate": 6.313329344671946e-05, "loss": 0.3023, "step": 1121 }, { "epoch": 0.1288174512055109, "grad_norm": 0.3351610600948334, "learning_rate": 6.30953086806057e-05, "loss": 0.2745, "step": 1122 }, { "epoch": 0.12893226176808267, "grad_norm": 0.23889876902103424, "learning_rate": 6.305729264679173e-05, "loss": 0.2786, "step": 1123 }, { "epoch": 0.12904707233065443, "grad_norm": 0.251903235912323, "learning_rate": 6.301924539674577e-05, "loss": 0.2897, "step": 1124 }, { "epoch": 0.12916188289322617, "grad_norm": 0.23469239473342896, "learning_rate": 6.298116698197825e-05, "loss": 0.2682, "step": 1125 }, { "epoch": 0.12927669345579793, "grad_norm": 0.2626992464065552, "learning_rate": 6.294305745404185e-05, "loss": 0.2838, "step": 1126 }, { "epoch": 0.12939150401836969, "grad_norm": 0.2413730025291443, "learning_rate": 6.290491686453134e-05, "loss": 0.2681, "step": 1127 }, { "epoch": 0.12950631458094145, "grad_norm": 4.284842491149902, "learning_rate": 6.286674526508354e-05, "loss": 0.3178, "step": 1128 }, { "epoch": 0.1296211251435132, "grad_norm": 0.3203372359275818, "learning_rate": 6.282854270737728e-05, "loss": 0.2943, "step": 1129 }, { "epoch": 0.12973593570608496, "grad_norm": 0.2689608931541443, "learning_rate": 6.279030924313327e-05, "loss": 0.3029, "step": 1130 }, { "epoch": 0.12985074626865672, "grad_norm": 0.26036083698272705, "learning_rate": 6.275204492411408e-05, "loss": 0.2839, "step": 1131 }, { "epoch": 0.12996555683122848, "grad_norm": 0.9790170192718506, "learning_rate": 6.271374980212406e-05, "loss": 0.3015, "step": 1132 }, { "epoch": 0.13008036739380022, "grad_norm": 0.2699030935764313, "learning_rate": 6.267542392900924e-05, "loss": 0.2648, "step": 1133 }, { "epoch": 0.13019517795637198, "grad_norm": 0.3067716360092163, "learning_rate": 6.263706735665732e-05, "loss": 0.2831, "step": 1134 }, { "epoch": 0.13030998851894374, "grad_norm": 0.25938481092453003, "learning_rate": 6.259868013699752e-05, "loss": 0.2867, "step": 1135 }, { "epoch": 0.1304247990815155, "grad_norm": 0.3162797689437866, "learning_rate": 6.256026232200059e-05, "loss": 0.3052, "step": 1136 }, { "epoch": 0.13053960964408726, "grad_norm": 0.2600966691970825, "learning_rate": 6.252181396367865e-05, "loss": 0.2732, "step": 1137 }, { "epoch": 0.13065442020665902, "grad_norm": 0.3096303641796112, "learning_rate": 6.248333511408522e-05, "loss": 0.2982, "step": 1138 }, { "epoch": 0.13076923076923078, "grad_norm": 0.23929855227470398, "learning_rate": 6.244482582531511e-05, "loss": 0.2702, "step": 1139 }, { "epoch": 0.13088404133180254, "grad_norm": 0.777955174446106, "learning_rate": 6.240628614950428e-05, "loss": 0.2997, "step": 1140 }, { "epoch": 0.13099885189437427, "grad_norm": 0.2622903883457184, "learning_rate": 6.236771613882987e-05, "loss": 0.2842, "step": 1141 }, { "epoch": 0.13111366245694603, "grad_norm": 1.6218301057815552, "learning_rate": 6.23291158455101e-05, "loss": 0.2771, "step": 1142 }, { "epoch": 0.1312284730195178, "grad_norm": 7.193299293518066, "learning_rate": 6.229048532180418e-05, "loss": 0.5129, "step": 1143 }, { "epoch": 0.13134328358208955, "grad_norm": 0.3245515823364258, "learning_rate": 6.22518246200122e-05, "loss": 0.2764, "step": 1144 }, { "epoch": 0.1314580941446613, "grad_norm": 0.27722641825675964, "learning_rate": 6.221313379247518e-05, "loss": 0.2955, "step": 1145 }, { "epoch": 0.13157290470723307, "grad_norm": 0.2892187535762787, "learning_rate": 6.217441289157487e-05, "loss": 0.3004, "step": 1146 }, { "epoch": 0.13168771526980483, "grad_norm": 0.2808791697025299, "learning_rate": 6.213566196973376e-05, "loss": 0.3202, "step": 1147 }, { "epoch": 0.1318025258323766, "grad_norm": 0.28695037961006165, "learning_rate": 6.209688107941502e-05, "loss": 0.2937, "step": 1148 }, { "epoch": 0.13191733639494835, "grad_norm": 0.2773708701133728, "learning_rate": 6.205807027312229e-05, "loss": 0.2848, "step": 1149 }, { "epoch": 0.13203214695752008, "grad_norm": 0.26091432571411133, "learning_rate": 6.201922960339983e-05, "loss": 0.2797, "step": 1150 }, { "epoch": 0.13214695752009184, "grad_norm": 0.2626723647117615, "learning_rate": 6.198035912283225e-05, "loss": 0.2768, "step": 1151 }, { "epoch": 0.1322617680826636, "grad_norm": 0.2627013623714447, "learning_rate": 6.194145888404455e-05, "loss": 0.3071, "step": 1152 }, { "epoch": 0.13237657864523536, "grad_norm": 0.2459690421819687, "learning_rate": 6.190252893970202e-05, "loss": 0.2581, "step": 1153 }, { "epoch": 0.13249138920780712, "grad_norm": 2.0040340423583984, "learning_rate": 6.186356934251015e-05, "loss": 0.3856, "step": 1154 }, { "epoch": 0.13260619977037888, "grad_norm": 0.27928709983825684, "learning_rate": 6.18245801452146e-05, "loss": 0.3195, "step": 1155 }, { "epoch": 0.13272101033295064, "grad_norm": 0.2619757652282715, "learning_rate": 6.178556140060109e-05, "loss": 0.2973, "step": 1156 }, { "epoch": 0.1328358208955224, "grad_norm": 0.25841814279556274, "learning_rate": 6.174651316149534e-05, "loss": 0.288, "step": 1157 }, { "epoch": 0.13295063145809413, "grad_norm": 0.26226112246513367, "learning_rate": 6.1707435480763e-05, "loss": 0.2779, "step": 1158 }, { "epoch": 0.1330654420206659, "grad_norm": 0.3300917446613312, "learning_rate": 6.16683284113096e-05, "loss": 0.3248, "step": 1159 }, { "epoch": 0.13318025258323765, "grad_norm": 0.2814222574234009, "learning_rate": 6.162919200608043e-05, "loss": 0.2877, "step": 1160 }, { "epoch": 0.1332950631458094, "grad_norm": 0.2698640525341034, "learning_rate": 6.159002631806052e-05, "loss": 0.29, "step": 1161 }, { "epoch": 0.13340987370838117, "grad_norm": 0.24884332716464996, "learning_rate": 6.155083140027453e-05, "loss": 0.2847, "step": 1162 }, { "epoch": 0.13352468427095293, "grad_norm": 0.420303076505661, "learning_rate": 6.151160730578669e-05, "loss": 0.2823, "step": 1163 }, { "epoch": 0.1336394948335247, "grad_norm": 0.26126691699028015, "learning_rate": 6.147235408770074e-05, "loss": 0.2947, "step": 1164 }, { "epoch": 0.13375430539609645, "grad_norm": 0.24885931611061096, "learning_rate": 6.143307179915987e-05, "loss": 0.31, "step": 1165 }, { "epoch": 0.1338691159586682, "grad_norm": 0.2535688877105713, "learning_rate": 6.139376049334659e-05, "loss": 0.2785, "step": 1166 }, { "epoch": 0.13398392652123994, "grad_norm": 0.2702586352825165, "learning_rate": 6.135442022348268e-05, "loss": 0.285, "step": 1167 }, { "epoch": 0.1340987370838117, "grad_norm": 0.2556895315647125, "learning_rate": 6.13150510428292e-05, "loss": 0.2913, "step": 1168 }, { "epoch": 0.13421354764638346, "grad_norm": 0.2635878622531891, "learning_rate": 6.127565300468632e-05, "loss": 0.2925, "step": 1169 }, { "epoch": 0.13432835820895522, "grad_norm": 0.27510976791381836, "learning_rate": 6.123622616239324e-05, "loss": 0.3006, "step": 1170 }, { "epoch": 0.13444316877152698, "grad_norm": 0.515387773513794, "learning_rate": 6.11967705693282e-05, "loss": 0.3041, "step": 1171 }, { "epoch": 0.13455797933409874, "grad_norm": 0.2702702283859253, "learning_rate": 6.115728627890837e-05, "loss": 0.3164, "step": 1172 }, { "epoch": 0.1346727898966705, "grad_norm": 0.24712960422039032, "learning_rate": 6.111777334458975e-05, "loss": 0.2641, "step": 1173 }, { "epoch": 0.13478760045924226, "grad_norm": 0.2543458640575409, "learning_rate": 6.107823181986711e-05, "loss": 0.2632, "step": 1174 }, { "epoch": 0.134902411021814, "grad_norm": 2.2480084896087646, "learning_rate": 6.103866175827396e-05, "loss": 0.2906, "step": 1175 }, { "epoch": 0.13501722158438575, "grad_norm": 0.26198309659957886, "learning_rate": 6.099906321338241e-05, "loss": 0.2661, "step": 1176 }, { "epoch": 0.13513203214695751, "grad_norm": 0.26382705569267273, "learning_rate": 6.0959436238803175e-05, "loss": 0.3031, "step": 1177 }, { "epoch": 0.13524684270952927, "grad_norm": 5.5204033851623535, "learning_rate": 6.091978088818542e-05, "loss": 0.461, "step": 1178 }, { "epoch": 0.13536165327210103, "grad_norm": 0.26730573177337646, "learning_rate": 6.0880097215216725e-05, "loss": 0.2926, "step": 1179 }, { "epoch": 0.1354764638346728, "grad_norm": 0.23008641600608826, "learning_rate": 6.084038527362307e-05, "loss": 0.2577, "step": 1180 }, { "epoch": 0.13559127439724455, "grad_norm": 0.7007781863212585, "learning_rate": 6.0800645117168616e-05, "loss": 0.2874, "step": 1181 }, { "epoch": 0.13570608495981631, "grad_norm": 0.25795868039131165, "learning_rate": 6.0760876799655824e-05, "loss": 0.2932, "step": 1182 }, { "epoch": 0.13582089552238805, "grad_norm": 4.759474277496338, "learning_rate": 6.072108037492522e-05, "loss": 0.3874, "step": 1183 }, { "epoch": 0.1359357060849598, "grad_norm": 0.2938721776008606, "learning_rate": 6.0681255896855366e-05, "loss": 0.2764, "step": 1184 }, { "epoch": 0.13605051664753157, "grad_norm": 0.2623700499534607, "learning_rate": 6.064140341936286e-05, "loss": 0.2887, "step": 1185 }, { "epoch": 0.13616532721010333, "grad_norm": 0.23595507442951202, "learning_rate": 6.060152299640218e-05, "loss": 0.2802, "step": 1186 }, { "epoch": 0.1362801377726751, "grad_norm": 0.24451620876789093, "learning_rate": 6.0561614681965624e-05, "loss": 0.2812, "step": 1187 }, { "epoch": 0.13639494833524685, "grad_norm": 0.257756769657135, "learning_rate": 6.0521678530083254e-05, "loss": 0.304, "step": 1188 }, { "epoch": 0.1365097588978186, "grad_norm": 0.6079787611961365, "learning_rate": 6.048171459482286e-05, "loss": 0.2881, "step": 1189 }, { "epoch": 0.13662456946039037, "grad_norm": 0.2294529229402542, "learning_rate": 6.0441722930289816e-05, "loss": 0.2557, "step": 1190 }, { "epoch": 0.13673938002296213, "grad_norm": 0.27978312969207764, "learning_rate": 6.040170359062702e-05, "loss": 0.289, "step": 1191 }, { "epoch": 0.13685419058553386, "grad_norm": 0.29741984605789185, "learning_rate": 6.036165663001486e-05, "loss": 0.2855, "step": 1192 }, { "epoch": 0.13696900114810562, "grad_norm": 0.25580427050590515, "learning_rate": 6.032158210267112e-05, "loss": 0.2683, "step": 1193 }, { "epoch": 0.13708381171067738, "grad_norm": 0.23868480324745178, "learning_rate": 6.028148006285091e-05, "loss": 0.2755, "step": 1194 }, { "epoch": 0.13719862227324914, "grad_norm": 0.23218998312950134, "learning_rate": 6.024135056484655e-05, "loss": 0.2966, "step": 1195 }, { "epoch": 0.1373134328358209, "grad_norm": 0.22921469807624817, "learning_rate": 6.020119366298761e-05, "loss": 0.2725, "step": 1196 }, { "epoch": 0.13742824339839266, "grad_norm": 0.24760554730892181, "learning_rate": 6.016100941164067e-05, "loss": 0.2908, "step": 1197 }, { "epoch": 0.13754305396096442, "grad_norm": 0.25539276003837585, "learning_rate": 6.0120797865209414e-05, "loss": 0.2734, "step": 1198 }, { "epoch": 0.13765786452353618, "grad_norm": 0.24391262233257294, "learning_rate": 6.0080559078134415e-05, "loss": 0.2755, "step": 1199 }, { "epoch": 0.1377726750861079, "grad_norm": 0.2593858242034912, "learning_rate": 6.004029310489318e-05, "loss": 0.293, "step": 1200 }, { "epoch": 0.13788748564867967, "grad_norm": 0.22880403697490692, "learning_rate": 6.000000000000001e-05, "loss": 0.2633, "step": 1201 }, { "epoch": 0.13800229621125143, "grad_norm": 0.26349151134490967, "learning_rate": 5.99596798180059e-05, "loss": 0.2995, "step": 1202 }, { "epoch": 0.1381171067738232, "grad_norm": 0.2354852855205536, "learning_rate": 5.9919332613498545e-05, "loss": 0.2806, "step": 1203 }, { "epoch": 0.13823191733639495, "grad_norm": 0.27383556962013245, "learning_rate": 5.9878958441102225e-05, "loss": 0.3008, "step": 1204 }, { "epoch": 0.1383467278989667, "grad_norm": 0.24368318915367126, "learning_rate": 5.9838557355477694e-05, "loss": 0.2849, "step": 1205 }, { "epoch": 0.13846153846153847, "grad_norm": 0.5748787522315979, "learning_rate": 5.979812941132217e-05, "loss": 0.2888, "step": 1206 }, { "epoch": 0.13857634902411023, "grad_norm": 0.2679786682128906, "learning_rate": 5.975767466336924e-05, "loss": 0.3026, "step": 1207 }, { "epoch": 0.13869115958668196, "grad_norm": 0.22813990712165833, "learning_rate": 5.971719316638878e-05, "loss": 0.2556, "step": 1208 }, { "epoch": 0.13880597014925372, "grad_norm": 0.2570175230503082, "learning_rate": 5.9676684975186823e-05, "loss": 0.2979, "step": 1209 }, { "epoch": 0.13892078071182548, "grad_norm": 0.26417917013168335, "learning_rate": 5.963615014460564e-05, "loss": 0.2924, "step": 1210 }, { "epoch": 0.13903559127439724, "grad_norm": 0.2602080702781677, "learning_rate": 5.959558872952349e-05, "loss": 0.2883, "step": 1211 }, { "epoch": 0.139150401836969, "grad_norm": 0.26228225231170654, "learning_rate": 5.9555000784854645e-05, "loss": 0.2789, "step": 1212 }, { "epoch": 0.13926521239954076, "grad_norm": 0.2612108290195465, "learning_rate": 5.9514386365549315e-05, "loss": 0.2864, "step": 1213 }, { "epoch": 0.13938002296211252, "grad_norm": 0.2596648931503296, "learning_rate": 5.947374552659352e-05, "loss": 0.2862, "step": 1214 }, { "epoch": 0.13949483352468428, "grad_norm": 0.26262959837913513, "learning_rate": 5.943307832300909e-05, "loss": 0.2769, "step": 1215 }, { "epoch": 0.13960964408725604, "grad_norm": 0.2729921042919159, "learning_rate": 5.9392384809853493e-05, "loss": 0.2743, "step": 1216 }, { "epoch": 0.13972445464982777, "grad_norm": 0.24538424611091614, "learning_rate": 5.935166504221986e-05, "loss": 0.301, "step": 1217 }, { "epoch": 0.13983926521239953, "grad_norm": 0.26619282364845276, "learning_rate": 5.931091907523686e-05, "loss": 0.2772, "step": 1218 }, { "epoch": 0.1399540757749713, "grad_norm": 0.24530892074108124, "learning_rate": 5.9270146964068614e-05, "loss": 0.2844, "step": 1219 }, { "epoch": 0.14006888633754305, "grad_norm": 0.2479047030210495, "learning_rate": 5.9229348763914665e-05, "loss": 0.2815, "step": 1220 }, { "epoch": 0.1401836969001148, "grad_norm": 0.2378263622522354, "learning_rate": 5.918852453000986e-05, "loss": 0.2724, "step": 1221 }, { "epoch": 0.14029850746268657, "grad_norm": 0.23920938372612, "learning_rate": 5.914767431762428e-05, "loss": 0.2691, "step": 1222 }, { "epoch": 0.14041331802525833, "grad_norm": 0.2673453688621521, "learning_rate": 5.91067981820632e-05, "loss": 0.3006, "step": 1223 }, { "epoch": 0.1405281285878301, "grad_norm": 0.2691871225833893, "learning_rate": 5.906589617866699e-05, "loss": 0.2813, "step": 1224 }, { "epoch": 0.14064293915040182, "grad_norm": 0.2607962191104889, "learning_rate": 5.902496836281102e-05, "loss": 0.3205, "step": 1225 }, { "epoch": 0.14075774971297358, "grad_norm": 0.2496766895055771, "learning_rate": 5.8984014789905625e-05, "loss": 0.2706, "step": 1226 }, { "epoch": 0.14087256027554534, "grad_norm": 0.24020129442214966, "learning_rate": 5.8943035515396e-05, "loss": 0.2831, "step": 1227 }, { "epoch": 0.1409873708381171, "grad_norm": 0.2678104341030121, "learning_rate": 5.890203059476217e-05, "loss": 0.2849, "step": 1228 }, { "epoch": 0.14110218140068886, "grad_norm": 0.2685883939266205, "learning_rate": 5.886100008351882e-05, "loss": 0.3238, "step": 1229 }, { "epoch": 0.14121699196326062, "grad_norm": 0.253319650888443, "learning_rate": 5.881994403721533e-05, "loss": 0.2975, "step": 1230 }, { "epoch": 0.14133180252583238, "grad_norm": 0.28245842456817627, "learning_rate": 5.877886251143564e-05, "loss": 0.2696, "step": 1231 }, { "epoch": 0.14144661308840414, "grad_norm": 0.24007947742938995, "learning_rate": 5.873775556179817e-05, "loss": 0.2843, "step": 1232 }, { "epoch": 0.14156142365097588, "grad_norm": 0.23778389394283295, "learning_rate": 5.8696623243955774e-05, "loss": 0.2906, "step": 1233 }, { "epoch": 0.14167623421354764, "grad_norm": 0.262528657913208, "learning_rate": 5.865546561359566e-05, "loss": 0.3165, "step": 1234 }, { "epoch": 0.1417910447761194, "grad_norm": 0.23582066595554352, "learning_rate": 5.8614282726439264e-05, "loss": 0.3054, "step": 1235 }, { "epoch": 0.14190585533869116, "grad_norm": 0.2172984778881073, "learning_rate": 5.8573074638242286e-05, "loss": 0.2531, "step": 1236 }, { "epoch": 0.14202066590126292, "grad_norm": 0.23548755049705505, "learning_rate": 5.853184140479448e-05, "loss": 0.2533, "step": 1237 }, { "epoch": 0.14213547646383468, "grad_norm": 0.24330075085163116, "learning_rate": 5.849058308191966e-05, "loss": 0.2924, "step": 1238 }, { "epoch": 0.14225028702640644, "grad_norm": 0.2386588156223297, "learning_rate": 5.8449299725475635e-05, "loss": 0.2765, "step": 1239 }, { "epoch": 0.1423650975889782, "grad_norm": 0.24728284776210785, "learning_rate": 5.840799139135407e-05, "loss": 0.285, "step": 1240 }, { "epoch": 0.14247990815154996, "grad_norm": 0.2609119713306427, "learning_rate": 5.836665813548047e-05, "loss": 0.3133, "step": 1241 }, { "epoch": 0.1425947187141217, "grad_norm": 0.230215385556221, "learning_rate": 5.832530001381408e-05, "loss": 0.2626, "step": 1242 }, { "epoch": 0.14270952927669345, "grad_norm": 0.8604128360748291, "learning_rate": 5.828391708234778e-05, "loss": 0.33, "step": 1243 }, { "epoch": 0.1428243398392652, "grad_norm": 0.2541469931602478, "learning_rate": 5.824250939710807e-05, "loss": 0.2974, "step": 1244 }, { "epoch": 0.14293915040183697, "grad_norm": 0.23985984921455383, "learning_rate": 5.8201077014154955e-05, "loss": 0.2631, "step": 1245 }, { "epoch": 0.14305396096440873, "grad_norm": 0.2588805556297302, "learning_rate": 5.8159619989581874e-05, "loss": 0.2965, "step": 1246 }, { "epoch": 0.1431687715269805, "grad_norm": 0.3705866038799286, "learning_rate": 5.811813837951564e-05, "loss": 0.298, "step": 1247 }, { "epoch": 0.14328358208955225, "grad_norm": 0.24969229102134705, "learning_rate": 5.8076632240116324e-05, "loss": 0.2759, "step": 1248 }, { "epoch": 0.143398392652124, "grad_norm": 0.24983544647693634, "learning_rate": 5.803510162757723e-05, "loss": 0.2936, "step": 1249 }, { "epoch": 0.14351320321469574, "grad_norm": 0.24835067987442017, "learning_rate": 5.799354659812479e-05, "loss": 0.2765, "step": 1250 }, { "epoch": 0.1436280137772675, "grad_norm": 0.2546713650226593, "learning_rate": 5.79519672080185e-05, "loss": 0.2744, "step": 1251 }, { "epoch": 0.14374282433983926, "grad_norm": 3.924189329147339, "learning_rate": 5.791036351355079e-05, "loss": 0.3432, "step": 1252 }, { "epoch": 0.14385763490241102, "grad_norm": 0.27377840876579285, "learning_rate": 5.7868735571047075e-05, "loss": 0.2887, "step": 1253 }, { "epoch": 0.14397244546498278, "grad_norm": 0.2368551343679428, "learning_rate": 5.782708343686553e-05, "loss": 0.2779, "step": 1254 }, { "epoch": 0.14408725602755454, "grad_norm": 0.23604263365268707, "learning_rate": 5.7785407167397105e-05, "loss": 0.2651, "step": 1255 }, { "epoch": 0.1442020665901263, "grad_norm": 0.9954649806022644, "learning_rate": 5.7743706819065455e-05, "loss": 0.2806, "step": 1256 }, { "epoch": 0.14431687715269806, "grad_norm": 0.29828935861587524, "learning_rate": 5.770198244832676e-05, "loss": 0.2645, "step": 1257 }, { "epoch": 0.14443168771526982, "grad_norm": 0.47663414478302, "learning_rate": 5.7660234111669815e-05, "loss": 0.2986, "step": 1258 }, { "epoch": 0.14454649827784155, "grad_norm": 0.2406795471906662, "learning_rate": 5.7618461865615804e-05, "loss": 0.2668, "step": 1259 }, { "epoch": 0.1446613088404133, "grad_norm": 0.4023730754852295, "learning_rate": 5.757666576671828e-05, "loss": 0.2672, "step": 1260 }, { "epoch": 0.14477611940298507, "grad_norm": 4.091226577758789, "learning_rate": 5.75348458715631e-05, "loss": 0.3471, "step": 1261 }, { "epoch": 0.14489092996555683, "grad_norm": 0.29043909907341003, "learning_rate": 5.7493002236768354e-05, "loss": 0.2723, "step": 1262 }, { "epoch": 0.1450057405281286, "grad_norm": 0.4969189465045929, "learning_rate": 5.745113491898427e-05, "loss": 0.3112, "step": 1263 }, { "epoch": 0.14512055109070035, "grad_norm": 1.285409688949585, "learning_rate": 5.740924397489311e-05, "loss": 0.2665, "step": 1264 }, { "epoch": 0.1452353616532721, "grad_norm": 0.3085136115550995, "learning_rate": 5.736732946120913e-05, "loss": 0.2953, "step": 1265 }, { "epoch": 0.14535017221584387, "grad_norm": 0.27771779894828796, "learning_rate": 5.7325391434678525e-05, "loss": 0.3142, "step": 1266 }, { "epoch": 0.1454649827784156, "grad_norm": 0.2558147609233856, "learning_rate": 5.7283429952079304e-05, "loss": 0.2827, "step": 1267 }, { "epoch": 0.14557979334098736, "grad_norm": 0.2592664957046509, "learning_rate": 5.724144507022121e-05, "loss": 0.2896, "step": 1268 }, { "epoch": 0.14569460390355912, "grad_norm": 0.29151278734207153, "learning_rate": 5.7199436845945714e-05, "loss": 0.2873, "step": 1269 }, { "epoch": 0.14580941446613088, "grad_norm": 0.510013222694397, "learning_rate": 5.7157405336125845e-05, "loss": 0.2899, "step": 1270 }, { "epoch": 0.14592422502870264, "grad_norm": 0.224667027592659, "learning_rate": 5.711535059766617e-05, "loss": 0.2601, "step": 1271 }, { "epoch": 0.1460390355912744, "grad_norm": 0.25748109817504883, "learning_rate": 5.707327268750273e-05, "loss": 0.2789, "step": 1272 }, { "epoch": 0.14615384615384616, "grad_norm": 0.2771781086921692, "learning_rate": 5.703117166260291e-05, "loss": 0.2969, "step": 1273 }, { "epoch": 0.14626865671641792, "grad_norm": 0.24597865343093872, "learning_rate": 5.698904757996538e-05, "loss": 0.2659, "step": 1274 }, { "epoch": 0.14638346727898965, "grad_norm": 0.25752925872802734, "learning_rate": 5.694690049662006e-05, "loss": 0.2676, "step": 1275 }, { "epoch": 0.14649827784156141, "grad_norm": 0.2642858028411865, "learning_rate": 5.6904730469627985e-05, "loss": 0.2719, "step": 1276 }, { "epoch": 0.14661308840413317, "grad_norm": 0.2643939256668091, "learning_rate": 5.686253755608126e-05, "loss": 0.2922, "step": 1277 }, { "epoch": 0.14672789896670493, "grad_norm": 0.29105445742607117, "learning_rate": 5.6820321813102955e-05, "loss": 0.2912, "step": 1278 }, { "epoch": 0.1468427095292767, "grad_norm": 0.22982721030712128, "learning_rate": 5.677808329784709e-05, "loss": 0.2739, "step": 1279 }, { "epoch": 0.14695752009184845, "grad_norm": 0.281003475189209, "learning_rate": 5.67358220674985e-05, "loss": 0.2932, "step": 1280 }, { "epoch": 0.1470723306544202, "grad_norm": 0.31435278058052063, "learning_rate": 5.669353817927272e-05, "loss": 0.2976, "step": 1281 }, { "epoch": 0.14718714121699197, "grad_norm": 0.24312126636505127, "learning_rate": 5.6651231690416056e-05, "loss": 0.2842, "step": 1282 }, { "epoch": 0.14730195177956373, "grad_norm": 0.24897611141204834, "learning_rate": 5.6608902658205334e-05, "loss": 0.2788, "step": 1283 }, { "epoch": 0.14741676234213547, "grad_norm": 0.25493836402893066, "learning_rate": 5.6566551139947936e-05, "loss": 0.2761, "step": 1284 }, { "epoch": 0.14753157290470723, "grad_norm": 2.719048023223877, "learning_rate": 5.652417719298168e-05, "loss": 0.3399, "step": 1285 }, { "epoch": 0.14764638346727899, "grad_norm": 0.30437523126602173, "learning_rate": 5.6481780874674747e-05, "loss": 0.2861, "step": 1286 }, { "epoch": 0.14776119402985075, "grad_norm": 0.2592029273509979, "learning_rate": 5.643936224242559e-05, "loss": 0.2973, "step": 1287 }, { "epoch": 0.1478760045924225, "grad_norm": 0.2499929964542389, "learning_rate": 5.639692135366291e-05, "loss": 0.2812, "step": 1288 }, { "epoch": 0.14799081515499427, "grad_norm": 0.263041615486145, "learning_rate": 5.635445826584552e-05, "loss": 0.2809, "step": 1289 }, { "epoch": 0.14810562571756603, "grad_norm": 0.2823820114135742, "learning_rate": 5.631197303646227e-05, "loss": 0.2893, "step": 1290 }, { "epoch": 0.14822043628013779, "grad_norm": 0.2508090138435364, "learning_rate": 5.626946572303202e-05, "loss": 0.2734, "step": 1291 }, { "epoch": 0.14833524684270952, "grad_norm": 0.2687009572982788, "learning_rate": 5.622693638310348e-05, "loss": 0.2902, "step": 1292 }, { "epoch": 0.14845005740528128, "grad_norm": 0.24800026416778564, "learning_rate": 5.6184385074255254e-05, "loss": 0.2766, "step": 1293 }, { "epoch": 0.14856486796785304, "grad_norm": 0.2545938789844513, "learning_rate": 5.614181185409561e-05, "loss": 0.2593, "step": 1294 }, { "epoch": 0.1486796785304248, "grad_norm": 0.2450823038816452, "learning_rate": 5.609921678026252e-05, "loss": 0.2708, "step": 1295 }, { "epoch": 0.14879448909299656, "grad_norm": 0.27576446533203125, "learning_rate": 5.605659991042357e-05, "loss": 0.2948, "step": 1296 }, { "epoch": 0.14890929965556832, "grad_norm": 1.875989317893982, "learning_rate": 5.601396130227581e-05, "loss": 0.3167, "step": 1297 }, { "epoch": 0.14902411021814008, "grad_norm": 0.27556803822517395, "learning_rate": 5.597130101354571e-05, "loss": 0.2791, "step": 1298 }, { "epoch": 0.14913892078071184, "grad_norm": 0.30744197964668274, "learning_rate": 5.592861910198915e-05, "loss": 0.3196, "step": 1299 }, { "epoch": 0.14925373134328357, "grad_norm": 0.24750792980194092, "learning_rate": 5.5885915625391226e-05, "loss": 0.2824, "step": 1300 }, { "epoch": 0.14936854190585533, "grad_norm": 0.971184492111206, "learning_rate": 5.584319064156628e-05, "loss": 0.2912, "step": 1301 }, { "epoch": 0.1494833524684271, "grad_norm": 0.2609614133834839, "learning_rate": 5.580044420835773e-05, "loss": 0.2847, "step": 1302 }, { "epoch": 0.14959816303099885, "grad_norm": 0.26515257358551025, "learning_rate": 5.575767638363805e-05, "loss": 0.2833, "step": 1303 }, { "epoch": 0.1497129735935706, "grad_norm": 0.38715997338294983, "learning_rate": 5.571488722530869e-05, "loss": 0.3154, "step": 1304 }, { "epoch": 0.14982778415614237, "grad_norm": 0.24490578472614288, "learning_rate": 5.567207679129994e-05, "loss": 0.2564, "step": 1305 }, { "epoch": 0.14994259471871413, "grad_norm": 0.2777301073074341, "learning_rate": 5.562924513957095e-05, "loss": 0.2765, "step": 1306 }, { "epoch": 0.1500574052812859, "grad_norm": 0.2675664722919464, "learning_rate": 5.558639232810956e-05, "loss": 0.2734, "step": 1307 }, { "epoch": 0.15017221584385765, "grad_norm": 0.2588570713996887, "learning_rate": 5.5543518414932266e-05, "loss": 0.289, "step": 1308 }, { "epoch": 0.15028702640642938, "grad_norm": 0.248687282204628, "learning_rate": 5.5500623458084123e-05, "loss": 0.2766, "step": 1309 }, { "epoch": 0.15040183696900114, "grad_norm": 0.24268268048763275, "learning_rate": 5.5457707515638695e-05, "loss": 0.2576, "step": 1310 }, { "epoch": 0.1505166475315729, "grad_norm": 4.096673488616943, "learning_rate": 5.541477064569794e-05, "loss": 0.4863, "step": 1311 }, { "epoch": 0.15063145809414466, "grad_norm": 0.3137546181678772, "learning_rate": 5.5371812906392146e-05, "loss": 0.2972, "step": 1312 }, { "epoch": 0.15074626865671642, "grad_norm": 0.2542623281478882, "learning_rate": 5.53288343558799e-05, "loss": 0.2915, "step": 1313 }, { "epoch": 0.15086107921928818, "grad_norm": 0.34175315499305725, "learning_rate": 5.528583505234789e-05, "loss": 0.2766, "step": 1314 }, { "epoch": 0.15097588978185994, "grad_norm": 0.2453455626964569, "learning_rate": 5.5242815054010975e-05, "loss": 0.2854, "step": 1315 }, { "epoch": 0.1510907003444317, "grad_norm": 0.28374943137168884, "learning_rate": 5.519977441911197e-05, "loss": 0.304, "step": 1316 }, { "epoch": 0.15120551090700343, "grad_norm": 0.3106485903263092, "learning_rate": 5.515671320592166e-05, "loss": 0.2883, "step": 1317 }, { "epoch": 0.1513203214695752, "grad_norm": 0.23940198123455048, "learning_rate": 5.5113631472738695e-05, "loss": 0.277, "step": 1318 }, { "epoch": 0.15143513203214695, "grad_norm": 0.2687324285507202, "learning_rate": 5.5070529277889494e-05, "loss": 0.2797, "step": 1319 }, { "epoch": 0.1515499425947187, "grad_norm": 0.2575906813144684, "learning_rate": 5.502740667972816e-05, "loss": 0.2767, "step": 1320 }, { "epoch": 0.15166475315729047, "grad_norm": 0.26368585228919983, "learning_rate": 5.4984263736636494e-05, "loss": 0.285, "step": 1321 }, { "epoch": 0.15177956371986223, "grad_norm": 0.24153181910514832, "learning_rate": 5.494110050702373e-05, "loss": 0.2737, "step": 1322 }, { "epoch": 0.151894374282434, "grad_norm": 0.24548019468784332, "learning_rate": 5.489791704932665e-05, "loss": 0.2811, "step": 1323 }, { "epoch": 0.15200918484500575, "grad_norm": 0.22945649921894073, "learning_rate": 5.48547134220094e-05, "loss": 0.2658, "step": 1324 }, { "epoch": 0.15212399540757748, "grad_norm": 0.26264309883117676, "learning_rate": 5.4811489683563414e-05, "loss": 0.2656, "step": 1325 }, { "epoch": 0.15223880597014924, "grad_norm": 0.23550395667552948, "learning_rate": 5.476824589250738e-05, "loss": 0.2792, "step": 1326 }, { "epoch": 0.152353616532721, "grad_norm": 0.25308024883270264, "learning_rate": 5.472498210738713e-05, "loss": 0.2818, "step": 1327 }, { "epoch": 0.15246842709529276, "grad_norm": 0.23072241246700287, "learning_rate": 5.4681698386775535e-05, "loss": 0.2735, "step": 1328 }, { "epoch": 0.15258323765786452, "grad_norm": 0.2512732446193695, "learning_rate": 5.463839478927249e-05, "loss": 0.2707, "step": 1329 }, { "epoch": 0.15269804822043628, "grad_norm": 0.24971982836723328, "learning_rate": 5.4595071373504785e-05, "loss": 0.2867, "step": 1330 }, { "epoch": 0.15281285878300804, "grad_norm": 0.24566338956356049, "learning_rate": 5.4551728198126066e-05, "loss": 0.2823, "step": 1331 }, { "epoch": 0.1529276693455798, "grad_norm": 0.2488914579153061, "learning_rate": 5.450836532181669e-05, "loss": 0.2858, "step": 1332 }, { "epoch": 0.15304247990815156, "grad_norm": 0.23325024545192719, "learning_rate": 5.446498280328369e-05, "loss": 0.2888, "step": 1333 }, { "epoch": 0.1531572904707233, "grad_norm": 0.2559974789619446, "learning_rate": 5.442158070126075e-05, "loss": 0.297, "step": 1334 }, { "epoch": 0.15327210103329506, "grad_norm": 0.22732633352279663, "learning_rate": 5.4378159074508e-05, "loss": 0.2652, "step": 1335 }, { "epoch": 0.15338691159586682, "grad_norm": 0.24941979348659515, "learning_rate": 5.4334717981812e-05, "loss": 0.2752, "step": 1336 }, { "epoch": 0.15350172215843857, "grad_norm": 0.30699422955513, "learning_rate": 5.4291257481985764e-05, "loss": 0.2952, "step": 1337 }, { "epoch": 0.15361653272101033, "grad_norm": 0.23494204878807068, "learning_rate": 5.424777763386845e-05, "loss": 0.2942, "step": 1338 }, { "epoch": 0.1537313432835821, "grad_norm": 0.23667410016059875, "learning_rate": 5.4204278496325486e-05, "loss": 0.2619, "step": 1339 }, { "epoch": 0.15384615384615385, "grad_norm": 0.28673186898231506, "learning_rate": 5.416076012824841e-05, "loss": 0.2867, "step": 1340 }, { "epoch": 0.15396096440872561, "grad_norm": 0.3141176402568817, "learning_rate": 5.4117222588554756e-05, "loss": 0.2972, "step": 1341 }, { "epoch": 0.15407577497129735, "grad_norm": 0.26883649826049805, "learning_rate": 5.407366593618807e-05, "loss": 0.2987, "step": 1342 }, { "epoch": 0.1541905855338691, "grad_norm": 0.2294219434261322, "learning_rate": 5.403009023011775e-05, "loss": 0.2735, "step": 1343 }, { "epoch": 0.15430539609644087, "grad_norm": 0.23157599568367004, "learning_rate": 5.398649552933895e-05, "loss": 0.2764, "step": 1344 }, { "epoch": 0.15442020665901263, "grad_norm": 0.23513400554656982, "learning_rate": 5.394288189287261e-05, "loss": 0.2664, "step": 1345 }, { "epoch": 0.1545350172215844, "grad_norm": 0.24730955064296722, "learning_rate": 5.389924937976526e-05, "loss": 0.2938, "step": 1346 }, { "epoch": 0.15464982778415615, "grad_norm": 1.520772933959961, "learning_rate": 5.3855598049088996e-05, "loss": 0.3186, "step": 1347 }, { "epoch": 0.1547646383467279, "grad_norm": 0.28783807158470154, "learning_rate": 5.381192795994139e-05, "loss": 0.2785, "step": 1348 }, { "epoch": 0.15487944890929967, "grad_norm": 0.23742395639419556, "learning_rate": 5.376823917144542e-05, "loss": 0.2673, "step": 1349 }, { "epoch": 0.1549942594718714, "grad_norm": 0.23027139902114868, "learning_rate": 5.372453174274936e-05, "loss": 0.2614, "step": 1350 }, { "epoch": 0.15510907003444316, "grad_norm": 0.24529673159122467, "learning_rate": 5.368080573302676e-05, "loss": 0.2802, "step": 1351 }, { "epoch": 0.15522388059701492, "grad_norm": 0.23884376883506775, "learning_rate": 5.363706120147626e-05, "loss": 0.2772, "step": 1352 }, { "epoch": 0.15533869115958668, "grad_norm": 0.4630930423736572, "learning_rate": 5.359329820732166e-05, "loss": 0.2632, "step": 1353 }, { "epoch": 0.15545350172215844, "grad_norm": 0.24640625715255737, "learning_rate": 5.3549516809811667e-05, "loss": 0.2958, "step": 1354 }, { "epoch": 0.1555683122847302, "grad_norm": 0.2515295743942261, "learning_rate": 5.3505717068219964e-05, "loss": 0.2695, "step": 1355 }, { "epoch": 0.15568312284730196, "grad_norm": 0.23770581185817719, "learning_rate": 5.346189904184506e-05, "loss": 0.2662, "step": 1356 }, { "epoch": 0.15579793340987372, "grad_norm": 0.23293152451515198, "learning_rate": 5.341806279001021e-05, "loss": 0.2688, "step": 1357 }, { "epoch": 0.15591274397244548, "grad_norm": 0.22205205261707306, "learning_rate": 5.337420837206333e-05, "loss": 0.25, "step": 1358 }, { "epoch": 0.1560275545350172, "grad_norm": 0.21357578039169312, "learning_rate": 5.3330335847376974e-05, "loss": 0.2573, "step": 1359 }, { "epoch": 0.15614236509758897, "grad_norm": 0.24024204909801483, "learning_rate": 5.328644527534813e-05, "loss": 0.2704, "step": 1360 }, { "epoch": 0.15625717566016073, "grad_norm": 0.21728745102882385, "learning_rate": 5.324253671539833e-05, "loss": 0.276, "step": 1361 }, { "epoch": 0.1563719862227325, "grad_norm": 0.23538458347320557, "learning_rate": 5.3198610226973364e-05, "loss": 0.2738, "step": 1362 }, { "epoch": 0.15648679678530425, "grad_norm": 0.2306198924779892, "learning_rate": 5.3154665869543334e-05, "loss": 0.2645, "step": 1363 }, { "epoch": 0.156601607347876, "grad_norm": 0.23702073097229004, "learning_rate": 5.311070370260254e-05, "loss": 0.276, "step": 1364 }, { "epoch": 0.15671641791044777, "grad_norm": 0.22862176597118378, "learning_rate": 5.306672378566938e-05, "loss": 0.2704, "step": 1365 }, { "epoch": 0.15683122847301953, "grad_norm": 0.23135103285312653, "learning_rate": 5.3022726178286274e-05, "loss": 0.278, "step": 1366 }, { "epoch": 0.15694603903559126, "grad_norm": 0.22080884873867035, "learning_rate": 5.2978710940019617e-05, "loss": 0.2561, "step": 1367 }, { "epoch": 0.15706084959816302, "grad_norm": 0.2618998885154724, "learning_rate": 5.2934678130459655e-05, "loss": 0.2892, "step": 1368 }, { "epoch": 0.15717566016073478, "grad_norm": 0.24040620028972626, "learning_rate": 5.289062780922045e-05, "loss": 0.2889, "step": 1369 }, { "epoch": 0.15729047072330654, "grad_norm": 0.25382867455482483, "learning_rate": 5.284656003593974e-05, "loss": 0.31, "step": 1370 }, { "epoch": 0.1574052812858783, "grad_norm": 0.2400381863117218, "learning_rate": 5.280247487027886e-05, "loss": 0.2813, "step": 1371 }, { "epoch": 0.15752009184845006, "grad_norm": 0.22186416387557983, "learning_rate": 5.2758372371922805e-05, "loss": 0.2774, "step": 1372 }, { "epoch": 0.15763490241102182, "grad_norm": 0.2242974042892456, "learning_rate": 5.271425260057992e-05, "loss": 0.2612, "step": 1373 }, { "epoch": 0.15774971297359358, "grad_norm": 0.24204474687576294, "learning_rate": 5.267011561598199e-05, "loss": 0.2715, "step": 1374 }, { "epoch": 0.15786452353616534, "grad_norm": 0.2586979568004608, "learning_rate": 5.2625961477884104e-05, "loss": 0.2694, "step": 1375 }, { "epoch": 0.15797933409873707, "grad_norm": 0.2493760585784912, "learning_rate": 5.258179024606455e-05, "loss": 0.2888, "step": 1376 }, { "epoch": 0.15809414466130883, "grad_norm": 0.22568711638450623, "learning_rate": 5.253760198032479e-05, "loss": 0.269, "step": 1377 }, { "epoch": 0.1582089552238806, "grad_norm": 0.5132721066474915, "learning_rate": 5.249339674048931e-05, "loss": 0.2787, "step": 1378 }, { "epoch": 0.15832376578645235, "grad_norm": 0.21333734691143036, "learning_rate": 5.244917458640561e-05, "loss": 0.2619, "step": 1379 }, { "epoch": 0.1584385763490241, "grad_norm": 0.2387758046388626, "learning_rate": 5.240493557794407e-05, "loss": 0.2934, "step": 1380 }, { "epoch": 0.15855338691159587, "grad_norm": 0.24574913084506989, "learning_rate": 5.23606797749979e-05, "loss": 0.2672, "step": 1381 }, { "epoch": 0.15866819747416763, "grad_norm": 0.22970762848854065, "learning_rate": 5.231640723748304e-05, "loss": 0.2493, "step": 1382 }, { "epoch": 0.1587830080367394, "grad_norm": 0.2380184531211853, "learning_rate": 5.22721180253381e-05, "loss": 0.2491, "step": 1383 }, { "epoch": 0.15889781859931112, "grad_norm": 0.2179725617170334, "learning_rate": 5.2227812198524236e-05, "loss": 0.2606, "step": 1384 }, { "epoch": 0.15901262916188288, "grad_norm": 0.3066486418247223, "learning_rate": 5.2183489817025114e-05, "loss": 0.3085, "step": 1385 }, { "epoch": 0.15912743972445464, "grad_norm": 0.24104993045330048, "learning_rate": 5.2139150940846834e-05, "loss": 0.279, "step": 1386 }, { "epoch": 0.1592422502870264, "grad_norm": 0.2303232103586197, "learning_rate": 5.209479563001779e-05, "loss": 0.2728, "step": 1387 }, { "epoch": 0.15935706084959816, "grad_norm": 0.21893827617168427, "learning_rate": 5.205042394458864e-05, "loss": 0.2445, "step": 1388 }, { "epoch": 0.15947187141216992, "grad_norm": 0.24121429026126862, "learning_rate": 5.200603594463223e-05, "loss": 0.2686, "step": 1389 }, { "epoch": 0.15958668197474168, "grad_norm": 0.2306353747844696, "learning_rate": 5.1961631690243475e-05, "loss": 0.2584, "step": 1390 }, { "epoch": 0.15970149253731344, "grad_norm": 0.2250334471464157, "learning_rate": 5.191721124153928e-05, "loss": 0.2812, "step": 1391 }, { "epoch": 0.15981630309988518, "grad_norm": 0.22869716584682465, "learning_rate": 5.187277465865853e-05, "loss": 0.274, "step": 1392 }, { "epoch": 0.15993111366245694, "grad_norm": 0.23550455272197723, "learning_rate": 5.1828322001761876e-05, "loss": 0.2765, "step": 1393 }, { "epoch": 0.1600459242250287, "grad_norm": 0.23987962305545807, "learning_rate": 5.1783853331031794e-05, "loss": 0.2966, "step": 1394 }, { "epoch": 0.16016073478760046, "grad_norm": 1.0540456771850586, "learning_rate": 5.173936870667242e-05, "loss": 0.2797, "step": 1395 }, { "epoch": 0.16027554535017222, "grad_norm": 0.2282911092042923, "learning_rate": 5.1694868188909473e-05, "loss": 0.2794, "step": 1396 }, { "epoch": 0.16039035591274398, "grad_norm": 0.23112855851650238, "learning_rate": 5.165035183799022e-05, "loss": 0.2627, "step": 1397 }, { "epoch": 0.16050516647531574, "grad_norm": 0.226750910282135, "learning_rate": 5.1605819714183336e-05, "loss": 0.2448, "step": 1398 }, { "epoch": 0.1606199770378875, "grad_norm": 0.22528071701526642, "learning_rate": 5.1561271877778865e-05, "loss": 0.2757, "step": 1399 }, { "epoch": 0.16073478760045926, "grad_norm": 0.24951405823230743, "learning_rate": 5.151670838908813e-05, "loss": 0.2771, "step": 1400 }, { "epoch": 0.160849598163031, "grad_norm": 0.2326967418193817, "learning_rate": 5.1472129308443616e-05, "loss": 0.2677, "step": 1401 }, { "epoch": 0.16096440872560275, "grad_norm": 0.7572515606880188, "learning_rate": 5.1427534696198946e-05, "loss": 0.2599, "step": 1402 }, { "epoch": 0.1610792192881745, "grad_norm": 0.24547997117042542, "learning_rate": 5.1382924612728765e-05, "loss": 0.2844, "step": 1403 }, { "epoch": 0.16119402985074627, "grad_norm": 0.2532497048377991, "learning_rate": 5.133829911842865e-05, "loss": 0.2634, "step": 1404 }, { "epoch": 0.16130884041331803, "grad_norm": 0.22745762765407562, "learning_rate": 5.129365827371507e-05, "loss": 0.2691, "step": 1405 }, { "epoch": 0.1614236509758898, "grad_norm": 0.26159870624542236, "learning_rate": 5.124900213902523e-05, "loss": 0.2774, "step": 1406 }, { "epoch": 0.16153846153846155, "grad_norm": 0.22803176939487457, "learning_rate": 5.120433077481709e-05, "loss": 0.2663, "step": 1407 }, { "epoch": 0.1616532721010333, "grad_norm": 0.23847559094429016, "learning_rate": 5.115964424156918e-05, "loss": 0.2671, "step": 1408 }, { "epoch": 0.16176808266360504, "grad_norm": 0.22861114144325256, "learning_rate": 5.11149425997806e-05, "loss": 0.2682, "step": 1409 }, { "epoch": 0.1618828932261768, "grad_norm": 0.3541654646396637, "learning_rate": 5.107022590997089e-05, "loss": 0.2576, "step": 1410 }, { "epoch": 0.16199770378874856, "grad_norm": 0.22283612191677094, "learning_rate": 5.102549423267997e-05, "loss": 0.2612, "step": 1411 }, { "epoch": 0.16211251435132032, "grad_norm": 0.2351577877998352, "learning_rate": 5.098074762846804e-05, "loss": 0.2636, "step": 1412 }, { "epoch": 0.16222732491389208, "grad_norm": 0.2564998269081116, "learning_rate": 5.0935986157915534e-05, "loss": 0.3072, "step": 1413 }, { "epoch": 0.16234213547646384, "grad_norm": 0.24639877676963806, "learning_rate": 5.089120988162298e-05, "loss": 0.2797, "step": 1414 }, { "epoch": 0.1624569460390356, "grad_norm": 0.23452652990818024, "learning_rate": 5.084641886021096e-05, "loss": 0.2615, "step": 1415 }, { "epoch": 0.16257175660160736, "grad_norm": 0.26960232853889465, "learning_rate": 5.080161315432004e-05, "loss": 0.2892, "step": 1416 }, { "epoch": 0.1626865671641791, "grad_norm": 0.23563115298748016, "learning_rate": 5.075679282461063e-05, "loss": 0.2571, "step": 1417 }, { "epoch": 0.16280137772675085, "grad_norm": 0.25673729181289673, "learning_rate": 5.071195793176299e-05, "loss": 0.2902, "step": 1418 }, { "epoch": 0.1629161882893226, "grad_norm": 0.2737683355808258, "learning_rate": 5.066710853647703e-05, "loss": 0.2626, "step": 1419 }, { "epoch": 0.16303099885189437, "grad_norm": 0.23632065951824188, "learning_rate": 5.062224469947236e-05, "loss": 0.2632, "step": 1420 }, { "epoch": 0.16314580941446613, "grad_norm": 0.2537015378475189, "learning_rate": 5.05773664814881e-05, "loss": 0.2764, "step": 1421 }, { "epoch": 0.1632606199770379, "grad_norm": 0.24051780998706818, "learning_rate": 5.053247394328285e-05, "loss": 0.2793, "step": 1422 }, { "epoch": 0.16337543053960965, "grad_norm": 0.25599405169487, "learning_rate": 5.0487567145634593e-05, "loss": 0.2706, "step": 1423 }, { "epoch": 0.1634902411021814, "grad_norm": 6.585512161254883, "learning_rate": 5.044264614934065e-05, "loss": 0.3506, "step": 1424 }, { "epoch": 0.16360505166475317, "grad_norm": 0.2827751338481903, "learning_rate": 5.0397711015217506e-05, "loss": 0.2827, "step": 1425 }, { "epoch": 0.1637198622273249, "grad_norm": 0.27135640382766724, "learning_rate": 5.0352761804100835e-05, "loss": 0.3003, "step": 1426 }, { "epoch": 0.16383467278989666, "grad_norm": 0.6302012801170349, "learning_rate": 5.030779857684536e-05, "loss": 0.2897, "step": 1427 }, { "epoch": 0.16394948335246842, "grad_norm": 0.24983415007591248, "learning_rate": 5.026282139432476e-05, "loss": 0.2589, "step": 1428 }, { "epoch": 0.16406429391504018, "grad_norm": 0.2638097405433655, "learning_rate": 5.021783031743162e-05, "loss": 0.2779, "step": 1429 }, { "epoch": 0.16417910447761194, "grad_norm": 0.2490818053483963, "learning_rate": 5.0172825407077363e-05, "loss": 0.2662, "step": 1430 }, { "epoch": 0.1642939150401837, "grad_norm": 0.24498531222343445, "learning_rate": 5.012780672419208e-05, "loss": 0.2676, "step": 1431 }, { "epoch": 0.16440872560275546, "grad_norm": 0.26289212703704834, "learning_rate": 5.008277432972456e-05, "loss": 0.2863, "step": 1432 }, { "epoch": 0.16452353616532722, "grad_norm": 0.27019238471984863, "learning_rate": 5.003772828464211e-05, "loss": 0.2704, "step": 1433 }, { "epoch": 0.16463834672789895, "grad_norm": 0.2804107367992401, "learning_rate": 4.9992668649930595e-05, "loss": 0.2755, "step": 1434 }, { "epoch": 0.16475315729047071, "grad_norm": 0.22498483955860138, "learning_rate": 4.9947595486594206e-05, "loss": 0.2549, "step": 1435 }, { "epoch": 0.16486796785304247, "grad_norm": 0.2644616961479187, "learning_rate": 4.9902508855655445e-05, "loss": 0.2842, "step": 1436 }, { "epoch": 0.16498277841561423, "grad_norm": 0.2436988353729248, "learning_rate": 4.985740881815512e-05, "loss": 0.27, "step": 1437 }, { "epoch": 0.165097588978186, "grad_norm": 0.2391366958618164, "learning_rate": 4.981229543515211e-05, "loss": 0.2911, "step": 1438 }, { "epoch": 0.16521239954075775, "grad_norm": 0.26629865169525146, "learning_rate": 4.976716876772342e-05, "loss": 0.2629, "step": 1439 }, { "epoch": 0.1653272101033295, "grad_norm": 0.4183271527290344, "learning_rate": 4.972202887696399e-05, "loss": 0.2955, "step": 1440 }, { "epoch": 0.16544202066590127, "grad_norm": 0.24829895794391632, "learning_rate": 4.967687582398671e-05, "loss": 0.2786, "step": 1441 }, { "epoch": 0.165556831228473, "grad_norm": 0.25825172662734985, "learning_rate": 4.963170966992227e-05, "loss": 0.2806, "step": 1442 }, { "epoch": 0.16567164179104477, "grad_norm": 0.23007546365261078, "learning_rate": 4.958653047591909e-05, "loss": 0.27, "step": 1443 }, { "epoch": 0.16578645235361653, "grad_norm": 0.24464385211467743, "learning_rate": 4.954133830314324e-05, "loss": 0.2827, "step": 1444 }, { "epoch": 0.16590126291618829, "grad_norm": 0.2509040832519531, "learning_rate": 4.949613321277839e-05, "loss": 0.2688, "step": 1445 }, { "epoch": 0.16601607347876005, "grad_norm": 0.2438354343175888, "learning_rate": 4.945091526602567e-05, "loss": 0.2626, "step": 1446 }, { "epoch": 0.1661308840413318, "grad_norm": 0.2589867413043976, "learning_rate": 4.94056845241036e-05, "loss": 0.2974, "step": 1447 }, { "epoch": 0.16624569460390357, "grad_norm": 0.2514035701751709, "learning_rate": 4.9360441048248096e-05, "loss": 0.271, "step": 1448 }, { "epoch": 0.16636050516647533, "grad_norm": 0.24341627955436707, "learning_rate": 4.931518489971224e-05, "loss": 0.2702, "step": 1449 }, { "epoch": 0.16647531572904709, "grad_norm": 0.22165843844413757, "learning_rate": 4.926991613976629e-05, "loss": 0.2692, "step": 1450 }, { "epoch": 0.16659012629161882, "grad_norm": 0.2519007623195648, "learning_rate": 4.922463482969761e-05, "loss": 0.2761, "step": 1451 }, { "epoch": 0.16670493685419058, "grad_norm": 2.7339231967926025, "learning_rate": 4.9179341030810516e-05, "loss": 0.28, "step": 1452 }, { "epoch": 0.16681974741676234, "grad_norm": 0.27117013931274414, "learning_rate": 4.9134034804426235e-05, "loss": 0.2864, "step": 1453 }, { "epoch": 0.1669345579793341, "grad_norm": 0.25372567772865295, "learning_rate": 4.9088716211882846e-05, "loss": 0.2956, "step": 1454 }, { "epoch": 0.16704936854190586, "grad_norm": 0.25908783078193665, "learning_rate": 4.9043385314535146e-05, "loss": 0.2712, "step": 1455 }, { "epoch": 0.16716417910447762, "grad_norm": 0.25963306427001953, "learning_rate": 4.899804217375461e-05, "loss": 0.2431, "step": 1456 }, { "epoch": 0.16727898966704938, "grad_norm": 13.250956535339355, "learning_rate": 4.895268685092926e-05, "loss": 0.4457, "step": 1457 }, { "epoch": 0.16739380022962114, "grad_norm": 0.3132189214229584, "learning_rate": 4.8907319407463645e-05, "loss": 0.2951, "step": 1458 }, { "epoch": 0.16750861079219287, "grad_norm": 0.2506791353225708, "learning_rate": 4.88619399047787e-05, "loss": 0.2514, "step": 1459 }, { "epoch": 0.16762342135476463, "grad_norm": 0.26605525612831116, "learning_rate": 4.8816548404311696e-05, "loss": 0.2937, "step": 1460 }, { "epoch": 0.1677382319173364, "grad_norm": 0.25981491804122925, "learning_rate": 4.877114496751613e-05, "loss": 0.284, "step": 1461 }, { "epoch": 0.16785304247990815, "grad_norm": 0.2548394501209259, "learning_rate": 4.872572965586171e-05, "loss": 0.286, "step": 1462 }, { "epoch": 0.1679678530424799, "grad_norm": 0.26226866245269775, "learning_rate": 4.868030253083415e-05, "loss": 0.3025, "step": 1463 }, { "epoch": 0.16808266360505167, "grad_norm": 0.35079824924468994, "learning_rate": 4.86348636539352e-05, "loss": 0.2803, "step": 1464 }, { "epoch": 0.16819747416762343, "grad_norm": 0.23164790868759155, "learning_rate": 4.8589413086682534e-05, "loss": 0.2728, "step": 1465 }, { "epoch": 0.1683122847301952, "grad_norm": 0.23649361729621887, "learning_rate": 4.854395089060961e-05, "loss": 0.2602, "step": 1466 }, { "epoch": 0.16842709529276692, "grad_norm": 0.24146297574043274, "learning_rate": 4.849847712726565e-05, "loss": 0.2628, "step": 1467 }, { "epoch": 0.16854190585533868, "grad_norm": 0.23815584182739258, "learning_rate": 4.845299185821556e-05, "loss": 0.2782, "step": 1468 }, { "epoch": 0.16865671641791044, "grad_norm": 0.2602613866329193, "learning_rate": 4.840749514503976e-05, "loss": 0.3094, "step": 1469 }, { "epoch": 0.1687715269804822, "grad_norm": 0.2229202389717102, "learning_rate": 4.836198704933426e-05, "loss": 0.2722, "step": 1470 }, { "epoch": 0.16888633754305396, "grad_norm": 0.3084302842617035, "learning_rate": 4.831646763271037e-05, "loss": 0.2687, "step": 1471 }, { "epoch": 0.16900114810562572, "grad_norm": 0.23603180050849915, "learning_rate": 4.827093695679483e-05, "loss": 0.2514, "step": 1472 }, { "epoch": 0.16911595866819748, "grad_norm": 0.2514212727546692, "learning_rate": 4.8225395083229546e-05, "loss": 0.2866, "step": 1473 }, { "epoch": 0.16923076923076924, "grad_norm": 0.23738686740398407, "learning_rate": 4.817984207367161e-05, "loss": 0.2849, "step": 1474 }, { "epoch": 0.169345579793341, "grad_norm": 0.23262366652488708, "learning_rate": 4.813427798979322e-05, "loss": 0.2518, "step": 1475 }, { "epoch": 0.16946039035591273, "grad_norm": 0.2304033786058426, "learning_rate": 4.808870289328153e-05, "loss": 0.2573, "step": 1476 }, { "epoch": 0.1695752009184845, "grad_norm": 0.2246014028787613, "learning_rate": 4.8043116845838595e-05, "loss": 0.2643, "step": 1477 }, { "epoch": 0.16969001148105625, "grad_norm": 0.24553042650222778, "learning_rate": 4.7997519909181335e-05, "loss": 0.2856, "step": 1478 }, { "epoch": 0.169804822043628, "grad_norm": 6.684046268463135, "learning_rate": 4.7951912145041385e-05, "loss": 0.2671, "step": 1479 }, { "epoch": 0.16991963260619977, "grad_norm": 0.2902458906173706, "learning_rate": 4.790629361516505e-05, "loss": 0.2778, "step": 1480 }, { "epoch": 0.17003444316877153, "grad_norm": 0.2269684374332428, "learning_rate": 4.786066438131321e-05, "loss": 0.2513, "step": 1481 }, { "epoch": 0.1701492537313433, "grad_norm": 4.894654273986816, "learning_rate": 4.7815024505261226e-05, "loss": 0.381, "step": 1482 }, { "epoch": 0.17026406429391505, "grad_norm": 0.3518950939178467, "learning_rate": 4.776937404879888e-05, "loss": 0.2683, "step": 1483 }, { "epoch": 0.17037887485648678, "grad_norm": 0.24022218585014343, "learning_rate": 4.7723713073730275e-05, "loss": 0.2828, "step": 1484 }, { "epoch": 0.17049368541905854, "grad_norm": 0.2996067702770233, "learning_rate": 4.767804164187374e-05, "loss": 0.2674, "step": 1485 }, { "epoch": 0.1706084959816303, "grad_norm": 0.2580016553401947, "learning_rate": 4.76323598150618e-05, "loss": 0.2759, "step": 1486 }, { "epoch": 0.17072330654420206, "grad_norm": 0.26663389801979065, "learning_rate": 4.7586667655140993e-05, "loss": 0.2782, "step": 1487 }, { "epoch": 0.17083811710677382, "grad_norm": 0.39858728647232056, "learning_rate": 4.7540965223971905e-05, "loss": 0.3075, "step": 1488 }, { "epoch": 0.17095292766934558, "grad_norm": 0.2387685328722, "learning_rate": 4.7495252583429e-05, "loss": 0.2926, "step": 1489 }, { "epoch": 0.17106773823191734, "grad_norm": 0.25238630175590515, "learning_rate": 4.744952979540054e-05, "loss": 0.2603, "step": 1490 }, { "epoch": 0.1711825487944891, "grad_norm": 0.24193820357322693, "learning_rate": 4.740379692178858e-05, "loss": 0.2663, "step": 1491 }, { "epoch": 0.17129735935706086, "grad_norm": 0.22916558384895325, "learning_rate": 4.735805402450881e-05, "loss": 0.2666, "step": 1492 }, { "epoch": 0.1714121699196326, "grad_norm": 0.23951399326324463, "learning_rate": 4.7312301165490465e-05, "loss": 0.2562, "step": 1493 }, { "epoch": 0.17152698048220436, "grad_norm": 0.2503959536552429, "learning_rate": 4.726653840667628e-05, "loss": 0.2962, "step": 1494 }, { "epoch": 0.17164179104477612, "grad_norm": 0.22729742527008057, "learning_rate": 4.722076581002241e-05, "loss": 0.2768, "step": 1495 }, { "epoch": 0.17175660160734788, "grad_norm": 0.2362053245306015, "learning_rate": 4.71749834374983e-05, "loss": 0.2606, "step": 1496 }, { "epoch": 0.17187141216991964, "grad_norm": 0.2162116914987564, "learning_rate": 4.712919135108667e-05, "loss": 0.2531, "step": 1497 }, { "epoch": 0.1719862227324914, "grad_norm": 0.2430081069469452, "learning_rate": 4.7083389612783343e-05, "loss": 0.2648, "step": 1498 }, { "epoch": 0.17210103329506315, "grad_norm": 0.5914977192878723, "learning_rate": 4.703757828459724e-05, "loss": 0.2621, "step": 1499 }, { "epoch": 0.17221584385763491, "grad_norm": 0.4267650842666626, "learning_rate": 4.699175742855027e-05, "loss": 0.2817, "step": 1500 }, { "epoch": 0.17233065442020665, "grad_norm": 0.2349022775888443, "learning_rate": 4.694592710667723e-05, "loss": 0.2604, "step": 1501 }, { "epoch": 0.1724454649827784, "grad_norm": 0.24351797997951508, "learning_rate": 4.69000873810257e-05, "loss": 0.2779, "step": 1502 }, { "epoch": 0.17256027554535017, "grad_norm": 0.25288307666778564, "learning_rate": 4.685423831365608e-05, "loss": 0.2747, "step": 1503 }, { "epoch": 0.17267508610792193, "grad_norm": 0.22769084572792053, "learning_rate": 4.6808379966641304e-05, "loss": 0.2625, "step": 1504 }, { "epoch": 0.1727898966704937, "grad_norm": 0.25527358055114746, "learning_rate": 4.676251240206696e-05, "loss": 0.2652, "step": 1505 }, { "epoch": 0.17290470723306545, "grad_norm": 1.8126394748687744, "learning_rate": 4.6716635682031093e-05, "loss": 0.3201, "step": 1506 }, { "epoch": 0.1730195177956372, "grad_norm": 0.2649509012699127, "learning_rate": 4.66707498686441e-05, "loss": 0.2642, "step": 1507 }, { "epoch": 0.17313432835820897, "grad_norm": 0.27573540806770325, "learning_rate": 4.662485502402874e-05, "loss": 0.286, "step": 1508 }, { "epoch": 0.1732491389207807, "grad_norm": 0.23825789988040924, "learning_rate": 4.6578951210319956e-05, "loss": 0.2547, "step": 1509 }, { "epoch": 0.17336394948335246, "grad_norm": 0.23106752336025238, "learning_rate": 4.6533038489664895e-05, "loss": 0.267, "step": 1510 }, { "epoch": 0.17347876004592422, "grad_norm": 0.22900208830833435, "learning_rate": 4.648711692422271e-05, "loss": 0.2771, "step": 1511 }, { "epoch": 0.17359357060849598, "grad_norm": 0.233150914311409, "learning_rate": 4.644118657616452e-05, "loss": 0.2766, "step": 1512 }, { "epoch": 0.17370838117106774, "grad_norm": 0.24061378836631775, "learning_rate": 4.63952475076734e-05, "loss": 0.2537, "step": 1513 }, { "epoch": 0.1738231917336395, "grad_norm": 0.24055956304073334, "learning_rate": 4.634929978094416e-05, "loss": 0.2895, "step": 1514 }, { "epoch": 0.17393800229621126, "grad_norm": 0.24024417996406555, "learning_rate": 4.6303343458183376e-05, "loss": 0.2674, "step": 1515 }, { "epoch": 0.17405281285878302, "grad_norm": 1.0799020528793335, "learning_rate": 4.625737860160924e-05, "loss": 0.3456, "step": 1516 }, { "epoch": 0.17416762342135478, "grad_norm": 0.24199385941028595, "learning_rate": 4.6211405273451505e-05, "loss": 0.2739, "step": 1517 }, { "epoch": 0.1742824339839265, "grad_norm": 0.2832304537296295, "learning_rate": 4.61654235359514e-05, "loss": 0.2604, "step": 1518 }, { "epoch": 0.17439724454649827, "grad_norm": 0.2370271533727646, "learning_rate": 4.611943345136153e-05, "loss": 0.2696, "step": 1519 }, { "epoch": 0.17451205510907003, "grad_norm": 0.26521191000938416, "learning_rate": 4.60734350819458e-05, "loss": 0.2572, "step": 1520 }, { "epoch": 0.1746268656716418, "grad_norm": 0.22508454322814941, "learning_rate": 4.602742848997933e-05, "loss": 0.2664, "step": 1521 }, { "epoch": 0.17474167623421355, "grad_norm": 0.2197568714618683, "learning_rate": 4.598141373774839e-05, "loss": 0.2657, "step": 1522 }, { "epoch": 0.1748564867967853, "grad_norm": 0.23496170341968536, "learning_rate": 4.593539088755027e-05, "loss": 0.2645, "step": 1523 }, { "epoch": 0.17497129735935707, "grad_norm": 0.23925618827342987, "learning_rate": 4.588936000169325e-05, "loss": 0.2759, "step": 1524 }, { "epoch": 0.17508610792192883, "grad_norm": 0.23542775213718414, "learning_rate": 4.5843321142496474e-05, "loss": 0.2635, "step": 1525 }, { "epoch": 0.17520091848450056, "grad_norm": 3.6822502613067627, "learning_rate": 4.579727437228987e-05, "loss": 0.3386, "step": 1526 }, { "epoch": 0.17531572904707232, "grad_norm": 0.3005432188510895, "learning_rate": 4.575121975341412e-05, "loss": 0.275, "step": 1527 }, { "epoch": 0.17543053960964408, "grad_norm": 0.23601855337619781, "learning_rate": 4.5705157348220476e-05, "loss": 0.2901, "step": 1528 }, { "epoch": 0.17554535017221584, "grad_norm": 0.24434241652488708, "learning_rate": 4.565908721907076e-05, "loss": 0.279, "step": 1529 }, { "epoch": 0.1756601607347876, "grad_norm": 0.2482203096151352, "learning_rate": 4.561300942833726e-05, "loss": 0.2659, "step": 1530 }, { "epoch": 0.17577497129735936, "grad_norm": 0.21558161079883575, "learning_rate": 4.556692403840262e-05, "loss": 0.2563, "step": 1531 }, { "epoch": 0.17588978185993112, "grad_norm": 0.2489292174577713, "learning_rate": 4.5520831111659784e-05, "loss": 0.2748, "step": 1532 }, { "epoch": 0.17600459242250288, "grad_norm": 0.25402674078941345, "learning_rate": 4.5474730710511886e-05, "loss": 0.2764, "step": 1533 }, { "epoch": 0.1761194029850746, "grad_norm": 0.2731718420982361, "learning_rate": 4.5428622897372184e-05, "loss": 0.282, "step": 1534 }, { "epoch": 0.17623421354764637, "grad_norm": 0.2620679438114166, "learning_rate": 4.5382507734663985e-05, "loss": 0.2774, "step": 1535 }, { "epoch": 0.17634902411021813, "grad_norm": 0.24564851820468903, "learning_rate": 4.5336385284820515e-05, "loss": 0.2856, "step": 1536 }, { "epoch": 0.1764638346727899, "grad_norm": 0.23737935721874237, "learning_rate": 4.529025561028491e-05, "loss": 0.2722, "step": 1537 }, { "epoch": 0.17657864523536165, "grad_norm": 0.24749360978603363, "learning_rate": 4.5244118773510046e-05, "loss": 0.286, "step": 1538 }, { "epoch": 0.1766934557979334, "grad_norm": 0.2363158017396927, "learning_rate": 4.519797483695851e-05, "loss": 0.2794, "step": 1539 }, { "epoch": 0.17680826636050517, "grad_norm": 0.22538098692893982, "learning_rate": 4.515182386310252e-05, "loss": 0.2817, "step": 1540 }, { "epoch": 0.17692307692307693, "grad_norm": 0.2259102612733841, "learning_rate": 4.51056659144238e-05, "loss": 0.2726, "step": 1541 }, { "epoch": 0.1770378874856487, "grad_norm": 0.2215685397386551, "learning_rate": 4.50595010534135e-05, "loss": 0.2767, "step": 1542 }, { "epoch": 0.17715269804822042, "grad_norm": 0.2383941262960434, "learning_rate": 4.501332934257217e-05, "loss": 0.284, "step": 1543 }, { "epoch": 0.17726750861079218, "grad_norm": 0.24015940725803375, "learning_rate": 4.496715084440962e-05, "loss": 0.2727, "step": 1544 }, { "epoch": 0.17738231917336394, "grad_norm": 0.23093557357788086, "learning_rate": 4.4920965621444834e-05, "loss": 0.3009, "step": 1545 }, { "epoch": 0.1774971297359357, "grad_norm": 0.2394888550043106, "learning_rate": 4.48747737362059e-05, "loss": 0.2801, "step": 1546 }, { "epoch": 0.17761194029850746, "grad_norm": 0.2469424158334732, "learning_rate": 4.4828575251229957e-05, "loss": 0.2705, "step": 1547 }, { "epoch": 0.17772675086107922, "grad_norm": 0.2229158878326416, "learning_rate": 4.478237022906303e-05, "loss": 0.2611, "step": 1548 }, { "epoch": 0.17784156142365098, "grad_norm": 0.20878252387046814, "learning_rate": 4.4736158732260056e-05, "loss": 0.2621, "step": 1549 }, { "epoch": 0.17795637198622274, "grad_norm": 0.22772900760173798, "learning_rate": 4.4689940823384644e-05, "loss": 0.2918, "step": 1550 }, { "epoch": 0.17807118254879448, "grad_norm": 0.22175177931785583, "learning_rate": 4.464371656500921e-05, "loss": 0.2744, "step": 1551 }, { "epoch": 0.17818599311136624, "grad_norm": 0.21903268992900848, "learning_rate": 4.459748601971467e-05, "loss": 0.2668, "step": 1552 }, { "epoch": 0.178300803673938, "grad_norm": 0.2088279277086258, "learning_rate": 4.455124925009047e-05, "loss": 0.2565, "step": 1553 }, { "epoch": 0.17841561423650976, "grad_norm": 0.22400367259979248, "learning_rate": 4.450500631873452e-05, "loss": 0.2852, "step": 1554 }, { "epoch": 0.17853042479908152, "grad_norm": 0.2077559232711792, "learning_rate": 4.445875728825302e-05, "loss": 0.2606, "step": 1555 }, { "epoch": 0.17864523536165328, "grad_norm": 0.20728732645511627, "learning_rate": 4.441250222126048e-05, "loss": 0.2677, "step": 1556 }, { "epoch": 0.17876004592422504, "grad_norm": 0.2056913822889328, "learning_rate": 4.436624118037952e-05, "loss": 0.2505, "step": 1557 }, { "epoch": 0.1788748564867968, "grad_norm": 0.20980848371982574, "learning_rate": 4.431997422824091e-05, "loss": 0.2587, "step": 1558 }, { "epoch": 0.17898966704936853, "grad_norm": 2.0558900833129883, "learning_rate": 4.427370142748341e-05, "loss": 0.3792, "step": 1559 }, { "epoch": 0.1791044776119403, "grad_norm": 0.24645403027534485, "learning_rate": 4.422742284075365e-05, "loss": 0.2906, "step": 1560 }, { "epoch": 0.17921928817451205, "grad_norm": 0.23036924004554749, "learning_rate": 4.418113853070614e-05, "loss": 0.2552, "step": 1561 }, { "epoch": 0.1793340987370838, "grad_norm": 0.3493366539478302, "learning_rate": 4.413484856000315e-05, "loss": 0.262, "step": 1562 }, { "epoch": 0.17944890929965557, "grad_norm": 0.22963947057724, "learning_rate": 4.408855299131455e-05, "loss": 0.2752, "step": 1563 }, { "epoch": 0.17956371986222733, "grad_norm": 0.6620345115661621, "learning_rate": 4.404225188731786e-05, "loss": 0.2852, "step": 1564 }, { "epoch": 0.1796785304247991, "grad_norm": 0.24732281267642975, "learning_rate": 4.399594531069806e-05, "loss": 0.2855, "step": 1565 }, { "epoch": 0.17979334098737085, "grad_norm": 0.22338686883449554, "learning_rate": 4.3949633324147515e-05, "loss": 0.258, "step": 1566 }, { "epoch": 0.1799081515499426, "grad_norm": 0.2261311262845993, "learning_rate": 4.3903315990365983e-05, "loss": 0.2569, "step": 1567 }, { "epoch": 0.18002296211251434, "grad_norm": 0.2270963340997696, "learning_rate": 4.38569933720604e-05, "loss": 0.255, "step": 1568 }, { "epoch": 0.1801377726750861, "grad_norm": 0.29400408267974854, "learning_rate": 4.3810665531944865e-05, "loss": 0.2823, "step": 1569 }, { "epoch": 0.18025258323765786, "grad_norm": 0.2370021939277649, "learning_rate": 4.3764332532740584e-05, "loss": 0.2799, "step": 1570 }, { "epoch": 0.18036739380022962, "grad_norm": 0.24385014176368713, "learning_rate": 4.37179944371757e-05, "loss": 0.2829, "step": 1571 }, { "epoch": 0.18048220436280138, "grad_norm": 0.24222372472286224, "learning_rate": 4.3671651307985276e-05, "loss": 0.2773, "step": 1572 }, { "epoch": 0.18059701492537314, "grad_norm": 0.22242967784404755, "learning_rate": 4.3625303207911215e-05, "loss": 0.2727, "step": 1573 }, { "epoch": 0.1807118254879449, "grad_norm": 0.24096070230007172, "learning_rate": 4.35789501997021e-05, "loss": 0.2733, "step": 1574 }, { "epoch": 0.18082663605051666, "grad_norm": 0.21844108402729034, "learning_rate": 4.35325923461132e-05, "loss": 0.2561, "step": 1575 }, { "epoch": 0.1809414466130884, "grad_norm": 0.4216061234474182, "learning_rate": 4.348622970990634e-05, "loss": 0.2803, "step": 1576 }, { "epoch": 0.18105625717566015, "grad_norm": 0.24507209658622742, "learning_rate": 4.343986235384977e-05, "loss": 0.277, "step": 1577 }, { "epoch": 0.1811710677382319, "grad_norm": 0.22257757186889648, "learning_rate": 4.339349034071821e-05, "loss": 0.2667, "step": 1578 }, { "epoch": 0.18128587830080367, "grad_norm": 0.23245356976985931, "learning_rate": 4.334711373329264e-05, "loss": 0.255, "step": 1579 }, { "epoch": 0.18140068886337543, "grad_norm": 0.2209201157093048, "learning_rate": 4.330073259436022e-05, "loss": 0.2553, "step": 1580 }, { "epoch": 0.1815154994259472, "grad_norm": 0.2235264629125595, "learning_rate": 4.3254346986714334e-05, "loss": 0.2549, "step": 1581 }, { "epoch": 0.18163030998851895, "grad_norm": 0.22670318186283112, "learning_rate": 4.3207956973154354e-05, "loss": 0.2609, "step": 1582 }, { "epoch": 0.1817451205510907, "grad_norm": 0.21879272162914276, "learning_rate": 4.3161562616485656e-05, "loss": 0.2331, "step": 1583 }, { "epoch": 0.18185993111366247, "grad_norm": 0.2411651760339737, "learning_rate": 4.311516397951944e-05, "loss": 0.2818, "step": 1584 }, { "epoch": 0.1819747416762342, "grad_norm": 0.21215607225894928, "learning_rate": 4.3068761125072746e-05, "loss": 0.2434, "step": 1585 }, { "epoch": 0.18208955223880596, "grad_norm": 0.22328943014144897, "learning_rate": 4.302235411596833e-05, "loss": 0.237, "step": 1586 }, { "epoch": 0.18220436280137772, "grad_norm": 0.2309630811214447, "learning_rate": 4.2975943015034544e-05, "loss": 0.2761, "step": 1587 }, { "epoch": 0.18231917336394948, "grad_norm": 0.2130618691444397, "learning_rate": 4.292952788510527e-05, "loss": 0.2695, "step": 1588 }, { "epoch": 0.18243398392652124, "grad_norm": 0.24842330813407898, "learning_rate": 4.2883108789019896e-05, "loss": 0.2698, "step": 1589 }, { "epoch": 0.182548794489093, "grad_norm": 0.5396479964256287, "learning_rate": 4.283668578962314e-05, "loss": 0.2992, "step": 1590 }, { "epoch": 0.18266360505166476, "grad_norm": 0.23231300711631775, "learning_rate": 4.2790258949765014e-05, "loss": 0.2774, "step": 1591 }, { "epoch": 0.18277841561423652, "grad_norm": 0.2254294455051422, "learning_rate": 4.274382833230073e-05, "loss": 0.2684, "step": 1592 }, { "epoch": 0.18289322617680825, "grad_norm": 0.2205961048603058, "learning_rate": 4.269739400009061e-05, "loss": 0.2597, "step": 1593 }, { "epoch": 0.18300803673938001, "grad_norm": 0.2258167862892151, "learning_rate": 4.265095601600002e-05, "loss": 0.2471, "step": 1594 }, { "epoch": 0.18312284730195177, "grad_norm": 0.22563354671001434, "learning_rate": 4.260451444289923e-05, "loss": 0.2761, "step": 1595 }, { "epoch": 0.18323765786452353, "grad_norm": 0.2321418821811676, "learning_rate": 4.255806934366343e-05, "loss": 0.2802, "step": 1596 }, { "epoch": 0.1833524684270953, "grad_norm": 0.23973673582077026, "learning_rate": 4.251162078117254e-05, "loss": 0.274, "step": 1597 }, { "epoch": 0.18346727898966705, "grad_norm": 0.2190077304840088, "learning_rate": 4.2465168818311185e-05, "loss": 0.2537, "step": 1598 }, { "epoch": 0.18358208955223881, "grad_norm": 0.2500179708003998, "learning_rate": 4.241871351796857e-05, "loss": 0.2978, "step": 1599 }, { "epoch": 0.18369690011481057, "grad_norm": 0.23683488368988037, "learning_rate": 4.2372254943038475e-05, "loss": 0.2633, "step": 1600 }, { "epoch": 0.1838117106773823, "grad_norm": 0.22067631781101227, "learning_rate": 4.2325793156419035e-05, "loss": 0.2404, "step": 1601 }, { "epoch": 0.18392652123995407, "grad_norm": 0.24336367845535278, "learning_rate": 4.22793282210128e-05, "loss": 0.2734, "step": 1602 }, { "epoch": 0.18404133180252583, "grad_norm": 0.24330227077007294, "learning_rate": 4.223286019972656e-05, "loss": 0.2855, "step": 1603 }, { "epoch": 0.18415614236509759, "grad_norm": 0.2267785519361496, "learning_rate": 4.218638915547126e-05, "loss": 0.2674, "step": 1604 }, { "epoch": 0.18427095292766935, "grad_norm": 0.2619016766548157, "learning_rate": 4.2139915151161975e-05, "loss": 0.2657, "step": 1605 }, { "epoch": 0.1843857634902411, "grad_norm": 1.188586950302124, "learning_rate": 4.2093438249717764e-05, "loss": 0.2751, "step": 1606 }, { "epoch": 0.18450057405281287, "grad_norm": 0.2377811074256897, "learning_rate": 4.204695851406161e-05, "loss": 0.2763, "step": 1607 }, { "epoch": 0.18461538461538463, "grad_norm": 0.22386434674263, "learning_rate": 4.200047600712034e-05, "loss": 0.2506, "step": 1608 }, { "epoch": 0.18473019517795639, "grad_norm": 0.231813445687294, "learning_rate": 4.195399079182454e-05, "loss": 0.2715, "step": 1609 }, { "epoch": 0.18484500574052812, "grad_norm": 0.22278103232383728, "learning_rate": 4.190750293110844e-05, "loss": 0.2742, "step": 1610 }, { "epoch": 0.18495981630309988, "grad_norm": 0.2317253053188324, "learning_rate": 4.186101248790988e-05, "loss": 0.2768, "step": 1611 }, { "epoch": 0.18507462686567164, "grad_norm": 0.23330894112586975, "learning_rate": 4.181451952517015e-05, "loss": 0.2845, "step": 1612 }, { "epoch": 0.1851894374282434, "grad_norm": 0.23789595067501068, "learning_rate": 4.1768024105834025e-05, "loss": 0.2722, "step": 1613 }, { "epoch": 0.18530424799081516, "grad_norm": 0.5126968622207642, "learning_rate": 4.172152629284954e-05, "loss": 0.2681, "step": 1614 }, { "epoch": 0.18541905855338692, "grad_norm": 0.2263520359992981, "learning_rate": 4.1675026149167985e-05, "loss": 0.2604, "step": 1615 }, { "epoch": 0.18553386911595868, "grad_norm": 0.22465376555919647, "learning_rate": 4.162852373774384e-05, "loss": 0.2694, "step": 1616 }, { "epoch": 0.18564867967853044, "grad_norm": 0.29199230670928955, "learning_rate": 4.158201912153461e-05, "loss": 0.2558, "step": 1617 }, { "epoch": 0.18576349024110217, "grad_norm": 0.2368212193250656, "learning_rate": 4.15355123635008e-05, "loss": 0.2792, "step": 1618 }, { "epoch": 0.18587830080367393, "grad_norm": 0.21470138430595398, "learning_rate": 4.148900352660584e-05, "loss": 0.2561, "step": 1619 }, { "epoch": 0.1859931113662457, "grad_norm": 0.21820876002311707, "learning_rate": 4.144249267381593e-05, "loss": 0.2635, "step": 1620 }, { "epoch": 0.18610792192881745, "grad_norm": 0.22343812882900238, "learning_rate": 4.139597986810005e-05, "loss": 0.2674, "step": 1621 }, { "epoch": 0.1862227324913892, "grad_norm": 0.2162877917289734, "learning_rate": 4.1349465172429764e-05, "loss": 0.2473, "step": 1622 }, { "epoch": 0.18633754305396097, "grad_norm": 0.22538504004478455, "learning_rate": 4.1302948649779254e-05, "loss": 0.2727, "step": 1623 }, { "epoch": 0.18645235361653273, "grad_norm": 0.22187893092632294, "learning_rate": 4.1256430363125134e-05, "loss": 0.2836, "step": 1624 }, { "epoch": 0.1865671641791045, "grad_norm": 0.24427808821201324, "learning_rate": 4.120991037544643e-05, "loss": 0.2899, "step": 1625 }, { "epoch": 0.18668197474167622, "grad_norm": 0.21399398148059845, "learning_rate": 4.116338874972446e-05, "loss": 0.2624, "step": 1626 }, { "epoch": 0.18679678530424798, "grad_norm": 0.26826420426368713, "learning_rate": 4.1116865548942765e-05, "loss": 0.2568, "step": 1627 }, { "epoch": 0.18691159586681974, "grad_norm": 0.2282026708126068, "learning_rate": 4.107034083608699e-05, "loss": 0.2786, "step": 1628 }, { "epoch": 0.1870264064293915, "grad_norm": 0.23457761108875275, "learning_rate": 4.102381467414489e-05, "loss": 0.2753, "step": 1629 }, { "epoch": 0.18714121699196326, "grad_norm": 0.2275431752204895, "learning_rate": 4.097728712610613e-05, "loss": 0.2738, "step": 1630 }, { "epoch": 0.18725602755453502, "grad_norm": 0.22232778370380402, "learning_rate": 4.093075825496225e-05, "loss": 0.2671, "step": 1631 }, { "epoch": 0.18737083811710678, "grad_norm": 0.6370220184326172, "learning_rate": 4.088422812370663e-05, "loss": 0.263, "step": 1632 }, { "epoch": 0.18748564867967854, "grad_norm": 0.22029873728752136, "learning_rate": 4.0837696795334284e-05, "loss": 0.2465, "step": 1633 }, { "epoch": 0.1876004592422503, "grad_norm": 0.25207239389419556, "learning_rate": 4.079116433284191e-05, "loss": 0.2806, "step": 1634 }, { "epoch": 0.18771526980482203, "grad_norm": 0.23074626922607422, "learning_rate": 4.0744630799227714e-05, "loss": 0.2651, "step": 1635 }, { "epoch": 0.1878300803673938, "grad_norm": 0.2622438669204712, "learning_rate": 4.0698096257491346e-05, "loss": 0.262, "step": 1636 }, { "epoch": 0.18794489092996555, "grad_norm": 0.24344556033611298, "learning_rate": 4.0651560770633834e-05, "loss": 0.2758, "step": 1637 }, { "epoch": 0.1880597014925373, "grad_norm": 0.31197330355644226, "learning_rate": 4.06050244016575e-05, "loss": 0.2666, "step": 1638 }, { "epoch": 0.18817451205510907, "grad_norm": 0.2525644302368164, "learning_rate": 4.055848721356582e-05, "loss": 0.2729, "step": 1639 }, { "epoch": 0.18828932261768083, "grad_norm": 0.2145899087190628, "learning_rate": 4.0511949269363404e-05, "loss": 0.2619, "step": 1640 }, { "epoch": 0.1884041331802526, "grad_norm": 0.22694031894207, "learning_rate": 4.046541063205589e-05, "loss": 0.2555, "step": 1641 }, { "epoch": 0.18851894374282435, "grad_norm": 0.2385634034872055, "learning_rate": 4.041887136464984e-05, "loss": 0.2669, "step": 1642 }, { "epoch": 0.18863375430539608, "grad_norm": 0.24210183322429657, "learning_rate": 4.037233153015268e-05, "loss": 0.2802, "step": 1643 }, { "epoch": 0.18874856486796784, "grad_norm": 0.21241499483585358, "learning_rate": 4.0325791191572596e-05, "loss": 0.2712, "step": 1644 }, { "epoch": 0.1888633754305396, "grad_norm": 0.21716392040252686, "learning_rate": 4.027925041191847e-05, "loss": 0.2716, "step": 1645 }, { "epoch": 0.18897818599311136, "grad_norm": 0.28241944313049316, "learning_rate": 4.023270925419976e-05, "loss": 0.2744, "step": 1646 }, { "epoch": 0.18909299655568312, "grad_norm": 0.2188311070203781, "learning_rate": 4.018616778142645e-05, "loss": 0.2494, "step": 1647 }, { "epoch": 0.18920780711825488, "grad_norm": 0.22581282258033752, "learning_rate": 4.0139626056608956e-05, "loss": 0.2782, "step": 1648 }, { "epoch": 0.18932261768082664, "grad_norm": 0.2132854461669922, "learning_rate": 4.0093084142758025e-05, "loss": 0.2601, "step": 1649 }, { "epoch": 0.1894374282433984, "grad_norm": 5.8168487548828125, "learning_rate": 4.004654210288464e-05, "loss": 0.3394, "step": 1650 }, { "epoch": 0.18955223880597014, "grad_norm": 0.24661482870578766, "learning_rate": 4e-05, "loss": 0.264, "step": 1651 }, { "epoch": 0.1896670493685419, "grad_norm": 0.23738990724086761, "learning_rate": 3.9953457897115375e-05, "loss": 0.2729, "step": 1652 }, { "epoch": 0.18978185993111366, "grad_norm": 0.24492168426513672, "learning_rate": 3.9906915857241995e-05, "loss": 0.2593, "step": 1653 }, { "epoch": 0.18989667049368542, "grad_norm": 0.2530516982078552, "learning_rate": 3.9860373943391065e-05, "loss": 0.2936, "step": 1654 }, { "epoch": 0.19001148105625718, "grad_norm": 0.23346896469593048, "learning_rate": 3.9813832218573554e-05, "loss": 0.2642, "step": 1655 }, { "epoch": 0.19012629161882894, "grad_norm": 0.23553533852100372, "learning_rate": 3.9767290745800246e-05, "loss": 0.2397, "step": 1656 }, { "epoch": 0.1902411021814007, "grad_norm": 0.30423933267593384, "learning_rate": 3.972074958808154e-05, "loss": 0.2809, "step": 1657 }, { "epoch": 0.19035591274397246, "grad_norm": 2.5839176177978516, "learning_rate": 3.967420880842741e-05, "loss": 0.3011, "step": 1658 }, { "epoch": 0.19047072330654422, "grad_norm": 0.25621646642684937, "learning_rate": 3.962766846984734e-05, "loss": 0.2796, "step": 1659 }, { "epoch": 0.19058553386911595, "grad_norm": 1.30938720703125, "learning_rate": 3.958112863535018e-05, "loss": 0.2484, "step": 1660 }, { "epoch": 0.1907003444316877, "grad_norm": 0.2624160647392273, "learning_rate": 3.953458936794413e-05, "loss": 0.2574, "step": 1661 }, { "epoch": 0.19081515499425947, "grad_norm": 1.0318065881729126, "learning_rate": 3.94880507306366e-05, "loss": 0.2811, "step": 1662 }, { "epoch": 0.19092996555683123, "grad_norm": 0.2568487524986267, "learning_rate": 3.9441512786434196e-05, "loss": 0.2652, "step": 1663 }, { "epoch": 0.191044776119403, "grad_norm": 3.5598549842834473, "learning_rate": 3.939497559834251e-05, "loss": 0.3037, "step": 1664 }, { "epoch": 0.19115958668197475, "grad_norm": 0.3261290192604065, "learning_rate": 3.934843922936617e-05, "loss": 0.2855, "step": 1665 }, { "epoch": 0.1912743972445465, "grad_norm": 0.2607508897781372, "learning_rate": 3.930190374250866e-05, "loss": 0.2709, "step": 1666 }, { "epoch": 0.19138920780711827, "grad_norm": 0.24883858859539032, "learning_rate": 3.9255369200772306e-05, "loss": 0.2835, "step": 1667 }, { "epoch": 0.19150401836969, "grad_norm": 0.2802751958370209, "learning_rate": 3.9208835667158114e-05, "loss": 0.2394, "step": 1668 }, { "epoch": 0.19161882893226176, "grad_norm": 0.23556050658226013, "learning_rate": 3.916230320466573e-05, "loss": 0.2439, "step": 1669 }, { "epoch": 0.19173363949483352, "grad_norm": 0.26861482858657837, "learning_rate": 3.911577187629338e-05, "loss": 0.2757, "step": 1670 }, { "epoch": 0.19184845005740528, "grad_norm": 0.25366002321243286, "learning_rate": 3.9069241745037753e-05, "loss": 0.2728, "step": 1671 }, { "epoch": 0.19196326061997704, "grad_norm": 0.2550499439239502, "learning_rate": 3.902271287389388e-05, "loss": 0.2667, "step": 1672 }, { "epoch": 0.1920780711825488, "grad_norm": 0.25516101717948914, "learning_rate": 3.897618532585512e-05, "loss": 0.2618, "step": 1673 }, { "epoch": 0.19219288174512056, "grad_norm": 0.3245916962623596, "learning_rate": 3.8929659163913014e-05, "loss": 0.2667, "step": 1674 }, { "epoch": 0.19230769230769232, "grad_norm": 0.24037069082260132, "learning_rate": 3.8883134451057255e-05, "loss": 0.2899, "step": 1675 }, { "epoch": 0.19242250287026405, "grad_norm": 0.2295733243227005, "learning_rate": 3.8836611250275546e-05, "loss": 0.2555, "step": 1676 }, { "epoch": 0.1925373134328358, "grad_norm": 0.2292187213897705, "learning_rate": 3.879008962455358e-05, "loss": 0.2682, "step": 1677 }, { "epoch": 0.19265212399540757, "grad_norm": 0.24891330301761627, "learning_rate": 3.874356963687487e-05, "loss": 0.2487, "step": 1678 }, { "epoch": 0.19276693455797933, "grad_norm": 0.226259246468544, "learning_rate": 3.869705135022076e-05, "loss": 0.2552, "step": 1679 }, { "epoch": 0.1928817451205511, "grad_norm": 0.2323441207408905, "learning_rate": 3.865053482757024e-05, "loss": 0.2801, "step": 1680 }, { "epoch": 0.19299655568312285, "grad_norm": 0.24377909302711487, "learning_rate": 3.860402013189998e-05, "loss": 0.2631, "step": 1681 }, { "epoch": 0.1931113662456946, "grad_norm": 0.24247518181800842, "learning_rate": 3.855750732618407e-05, "loss": 0.2524, "step": 1682 }, { "epoch": 0.19322617680826637, "grad_norm": 0.22628475725650787, "learning_rate": 3.8510996473394165e-05, "loss": 0.2513, "step": 1683 }, { "epoch": 0.19334098737083813, "grad_norm": 0.23508435487747192, "learning_rate": 3.8464487636499204e-05, "loss": 0.2599, "step": 1684 }, { "epoch": 0.19345579793340986, "grad_norm": 0.25114455819129944, "learning_rate": 3.84179808784654e-05, "loss": 0.2832, "step": 1685 }, { "epoch": 0.19357060849598162, "grad_norm": 0.22607333958148956, "learning_rate": 3.837147626225617e-05, "loss": 0.2744, "step": 1686 }, { "epoch": 0.19368541905855338, "grad_norm": 0.21880818903446198, "learning_rate": 3.832497385083203e-05, "loss": 0.2484, "step": 1687 }, { "epoch": 0.19380022962112514, "grad_norm": 0.24711894989013672, "learning_rate": 3.827847370715048e-05, "loss": 0.2623, "step": 1688 }, { "epoch": 0.1939150401836969, "grad_norm": 0.21781985461711884, "learning_rate": 3.8231975894165974e-05, "loss": 0.253, "step": 1689 }, { "epoch": 0.19402985074626866, "grad_norm": 0.2197829931974411, "learning_rate": 3.818548047482985e-05, "loss": 0.2657, "step": 1690 }, { "epoch": 0.19414466130884042, "grad_norm": 0.23113003373146057, "learning_rate": 3.813898751209013e-05, "loss": 0.2762, "step": 1691 }, { "epoch": 0.19425947187141218, "grad_norm": 0.22286556661128998, "learning_rate": 3.8092497068891575e-05, "loss": 0.2775, "step": 1692 }, { "epoch": 0.1943742824339839, "grad_norm": 0.2406434416770935, "learning_rate": 3.804600920817547e-05, "loss": 0.2811, "step": 1693 }, { "epoch": 0.19448909299655567, "grad_norm": 0.2509253919124603, "learning_rate": 3.799952399287968e-05, "loss": 0.2668, "step": 1694 }, { "epoch": 0.19460390355912743, "grad_norm": 0.24639376997947693, "learning_rate": 3.795304148593841e-05, "loss": 0.2621, "step": 1695 }, { "epoch": 0.1947187141216992, "grad_norm": 0.2312578558921814, "learning_rate": 3.790656175028225e-05, "loss": 0.2572, "step": 1696 }, { "epoch": 0.19483352468427095, "grad_norm": 0.23044703900814056, "learning_rate": 3.786008484883803e-05, "loss": 0.2628, "step": 1697 }, { "epoch": 0.1949483352468427, "grad_norm": 0.2257474809885025, "learning_rate": 3.781361084452875e-05, "loss": 0.2911, "step": 1698 }, { "epoch": 0.19506314580941447, "grad_norm": 0.24441657960414886, "learning_rate": 3.776713980027345e-05, "loss": 0.2744, "step": 1699 }, { "epoch": 0.19517795637198623, "grad_norm": 5.839631080627441, "learning_rate": 3.7720671778987206e-05, "loss": 0.3356, "step": 1700 }, { "epoch": 0.195292766934558, "grad_norm": 0.25873228907585144, "learning_rate": 3.767420684358097e-05, "loss": 0.2751, "step": 1701 }, { "epoch": 0.19540757749712973, "grad_norm": 0.22712041437625885, "learning_rate": 3.7627745056961545e-05, "loss": 0.2628, "step": 1702 }, { "epoch": 0.19552238805970149, "grad_norm": 0.22486735880374908, "learning_rate": 3.758128648203143e-05, "loss": 0.27, "step": 1703 }, { "epoch": 0.19563719862227325, "grad_norm": 0.22988343238830566, "learning_rate": 3.753483118168883e-05, "loss": 0.255, "step": 1704 }, { "epoch": 0.195752009184845, "grad_norm": 0.23074789345264435, "learning_rate": 3.7488379218827466e-05, "loss": 0.2727, "step": 1705 }, { "epoch": 0.19586681974741676, "grad_norm": 0.20790636539459229, "learning_rate": 3.744193065633658e-05, "loss": 0.2755, "step": 1706 }, { "epoch": 0.19598163030998852, "grad_norm": 0.20323920249938965, "learning_rate": 3.7395485557100776e-05, "loss": 0.2595, "step": 1707 }, { "epoch": 0.19609644087256028, "grad_norm": 0.2229001373052597, "learning_rate": 3.7349043984000006e-05, "loss": 0.258, "step": 1708 }, { "epoch": 0.19621125143513204, "grad_norm": 0.22278419137001038, "learning_rate": 3.73026059999094e-05, "loss": 0.2819, "step": 1709 }, { "epoch": 0.19632606199770378, "grad_norm": 0.24653026461601257, "learning_rate": 3.7256171667699265e-05, "loss": 0.2684, "step": 1710 }, { "epoch": 0.19644087256027554, "grad_norm": 0.22047047317028046, "learning_rate": 3.720974105023499e-05, "loss": 0.2529, "step": 1711 }, { "epoch": 0.1965556831228473, "grad_norm": 0.22468745708465576, "learning_rate": 3.716331421037687e-05, "loss": 0.2658, "step": 1712 }, { "epoch": 0.19667049368541906, "grad_norm": 0.23574762046337128, "learning_rate": 3.711689121098011e-05, "loss": 0.2854, "step": 1713 }, { "epoch": 0.19678530424799082, "grad_norm": 0.232737198472023, "learning_rate": 3.707047211489475e-05, "loss": 0.2574, "step": 1714 }, { "epoch": 0.19690011481056258, "grad_norm": 1.0176092386245728, "learning_rate": 3.7024056984965476e-05, "loss": 0.2848, "step": 1715 }, { "epoch": 0.19701492537313434, "grad_norm": 0.2348310798406601, "learning_rate": 3.697764588403169e-05, "loss": 0.282, "step": 1716 }, { "epoch": 0.1971297359357061, "grad_norm": 0.25206485390663147, "learning_rate": 3.693123887492726e-05, "loss": 0.2723, "step": 1717 }, { "epoch": 0.19724454649827783, "grad_norm": 0.25360268354415894, "learning_rate": 3.688483602048057e-05, "loss": 0.2723, "step": 1718 }, { "epoch": 0.1973593570608496, "grad_norm": 0.22434546053409576, "learning_rate": 3.683843738351436e-05, "loss": 0.2433, "step": 1719 }, { "epoch": 0.19747416762342135, "grad_norm": 0.24909572303295135, "learning_rate": 3.679204302684565e-05, "loss": 0.2553, "step": 1720 }, { "epoch": 0.1975889781859931, "grad_norm": 0.2385416179895401, "learning_rate": 3.674565301328568e-05, "loss": 0.2725, "step": 1721 }, { "epoch": 0.19770378874856487, "grad_norm": 0.2218288630247116, "learning_rate": 3.6699267405639795e-05, "loss": 0.268, "step": 1722 }, { "epoch": 0.19781859931113663, "grad_norm": 0.24399681389331818, "learning_rate": 3.665288626670739e-05, "loss": 0.2643, "step": 1723 }, { "epoch": 0.1979334098737084, "grad_norm": 0.21770501136779785, "learning_rate": 3.660650965928179e-05, "loss": 0.2613, "step": 1724 }, { "epoch": 0.19804822043628015, "grad_norm": 0.23543162643909454, "learning_rate": 3.656013764615023e-05, "loss": 0.2634, "step": 1725 }, { "epoch": 0.1981630309988519, "grad_norm": 0.2142120599746704, "learning_rate": 3.6513770290093674e-05, "loss": 0.2486, "step": 1726 }, { "epoch": 0.19827784156142364, "grad_norm": 0.21906417608261108, "learning_rate": 3.6467407653886804e-05, "loss": 0.2606, "step": 1727 }, { "epoch": 0.1983926521239954, "grad_norm": 0.25988245010375977, "learning_rate": 3.6421049800297914e-05, "loss": 0.2526, "step": 1728 }, { "epoch": 0.19850746268656716, "grad_norm": 0.21301066875457764, "learning_rate": 3.6374696792088805e-05, "loss": 0.2651, "step": 1729 }, { "epoch": 0.19862227324913892, "grad_norm": 0.23091940581798553, "learning_rate": 3.6328348692014744e-05, "loss": 0.266, "step": 1730 }, { "epoch": 0.19873708381171068, "grad_norm": 0.2200506627559662, "learning_rate": 3.628200556282432e-05, "loss": 0.2561, "step": 1731 }, { "epoch": 0.19885189437428244, "grad_norm": 0.3053419888019562, "learning_rate": 3.623566746725943e-05, "loss": 0.2929, "step": 1732 }, { "epoch": 0.1989667049368542, "grad_norm": 0.22053688764572144, "learning_rate": 3.618933446805514e-05, "loss": 0.273, "step": 1733 }, { "epoch": 0.19908151549942596, "grad_norm": 0.22124840319156647, "learning_rate": 3.6143006627939614e-05, "loss": 0.262, "step": 1734 }, { "epoch": 0.1991963260619977, "grad_norm": 0.21697455644607544, "learning_rate": 3.609668400963403e-05, "loss": 0.2448, "step": 1735 }, { "epoch": 0.19931113662456945, "grad_norm": 0.24776528775691986, "learning_rate": 3.605036667585249e-05, "loss": 0.2768, "step": 1736 }, { "epoch": 0.1994259471871412, "grad_norm": 0.21794867515563965, "learning_rate": 3.6004054689301966e-05, "loss": 0.2691, "step": 1737 }, { "epoch": 0.19954075774971297, "grad_norm": 0.22514374554157257, "learning_rate": 3.595774811268215e-05, "loss": 0.2536, "step": 1738 }, { "epoch": 0.19965556831228473, "grad_norm": 0.2166399359703064, "learning_rate": 3.591144700868546e-05, "loss": 0.2602, "step": 1739 }, { "epoch": 0.1997703788748565, "grad_norm": 3.569232225418091, "learning_rate": 3.5865151439996864e-05, "loss": 0.3194, "step": 1740 }, { "epoch": 0.19988518943742825, "grad_norm": 0.2652512192726135, "learning_rate": 3.581886146929387e-05, "loss": 0.2795, "step": 1741 }, { "epoch": 0.2, "grad_norm": 0.22314698994159698, "learning_rate": 3.577257715924636e-05, "loss": 0.2623, "step": 1742 }, { "epoch": 0.20011481056257174, "grad_norm": 0.2311611771583557, "learning_rate": 3.572629857251661e-05, "loss": 0.2607, "step": 1743 }, { "epoch": 0.2002296211251435, "grad_norm": 0.23568882048130035, "learning_rate": 3.5680025771759087e-05, "loss": 0.2618, "step": 1744 }, { "epoch": 0.20034443168771526, "grad_norm": 0.34325963258743286, "learning_rate": 3.563375881962048e-05, "loss": 0.2527, "step": 1745 }, { "epoch": 0.20045924225028702, "grad_norm": 0.22802019119262695, "learning_rate": 3.558749777873953e-05, "loss": 0.2529, "step": 1746 }, { "epoch": 0.20057405281285878, "grad_norm": 0.23855996131896973, "learning_rate": 3.5541242711746986e-05, "loss": 0.274, "step": 1747 }, { "epoch": 0.20068886337543054, "grad_norm": 0.2256990671157837, "learning_rate": 3.549499368126549e-05, "loss": 0.2654, "step": 1748 }, { "epoch": 0.2008036739380023, "grad_norm": 0.24797429144382477, "learning_rate": 3.544875074990954e-05, "loss": 0.2595, "step": 1749 }, { "epoch": 0.20091848450057406, "grad_norm": 0.23811288177967072, "learning_rate": 3.5402513980285346e-05, "loss": 0.2591, "step": 1750 }, { "epoch": 0.20103329506314582, "grad_norm": 0.2397937774658203, "learning_rate": 3.535628343499079e-05, "loss": 0.2618, "step": 1751 }, { "epoch": 0.20114810562571755, "grad_norm": 0.23439116775989532, "learning_rate": 3.5310059176615355e-05, "loss": 0.2566, "step": 1752 }, { "epoch": 0.20126291618828931, "grad_norm": 0.9496923685073853, "learning_rate": 3.5263841267739964e-05, "loss": 0.2689, "step": 1753 }, { "epoch": 0.20137772675086107, "grad_norm": 0.22432298958301544, "learning_rate": 3.521762977093698e-05, "loss": 0.2387, "step": 1754 }, { "epoch": 0.20149253731343283, "grad_norm": 0.2388668656349182, "learning_rate": 3.5171424748770064e-05, "loss": 0.2612, "step": 1755 }, { "epoch": 0.2016073478760046, "grad_norm": 1.8942376375198364, "learning_rate": 3.512522626379411e-05, "loss": 0.2898, "step": 1756 }, { "epoch": 0.20172215843857635, "grad_norm": 0.23643659055233002, "learning_rate": 3.5079034378555186e-05, "loss": 0.2676, "step": 1757 }, { "epoch": 0.20183696900114811, "grad_norm": 0.2099037915468216, "learning_rate": 3.5032849155590386e-05, "loss": 0.2493, "step": 1758 }, { "epoch": 0.20195177956371987, "grad_norm": 0.2194226235151291, "learning_rate": 3.498667065742783e-05, "loss": 0.2791, "step": 1759 }, { "epoch": 0.2020665901262916, "grad_norm": 0.24080833792686462, "learning_rate": 3.494049894658651e-05, "loss": 0.2703, "step": 1760 }, { "epoch": 0.20218140068886337, "grad_norm": 0.22449448704719543, "learning_rate": 3.4894334085576215e-05, "loss": 0.2533, "step": 1761 }, { "epoch": 0.20229621125143513, "grad_norm": 0.243299663066864, "learning_rate": 3.4848176136897496e-05, "loss": 0.2915, "step": 1762 }, { "epoch": 0.2024110218140069, "grad_norm": 0.22585278749465942, "learning_rate": 3.480202516304151e-05, "loss": 0.2585, "step": 1763 }, { "epoch": 0.20252583237657865, "grad_norm": 0.22923649847507477, "learning_rate": 3.4755881226489975e-05, "loss": 0.2768, "step": 1764 }, { "epoch": 0.2026406429391504, "grad_norm": 0.22153505682945251, "learning_rate": 3.47097443897151e-05, "loss": 0.2672, "step": 1765 }, { "epoch": 0.20275545350172217, "grad_norm": 0.22682736814022064, "learning_rate": 3.466361471517949e-05, "loss": 0.274, "step": 1766 }, { "epoch": 0.20287026406429393, "grad_norm": 0.220785990357399, "learning_rate": 3.461749226533603e-05, "loss": 0.2716, "step": 1767 }, { "epoch": 0.20298507462686566, "grad_norm": 0.22159342467784882, "learning_rate": 3.457137710262783e-05, "loss": 0.2882, "step": 1768 }, { "epoch": 0.20309988518943742, "grad_norm": 1.1938377618789673, "learning_rate": 3.452526928948813e-05, "loss": 0.3122, "step": 1769 }, { "epoch": 0.20321469575200918, "grad_norm": 0.235874205827713, "learning_rate": 3.4479168888340236e-05, "loss": 0.2592, "step": 1770 }, { "epoch": 0.20332950631458094, "grad_norm": 0.23469369113445282, "learning_rate": 3.44330759615974e-05, "loss": 0.2578, "step": 1771 }, { "epoch": 0.2034443168771527, "grad_norm": 0.23559895157814026, "learning_rate": 3.438699057166275e-05, "loss": 0.2777, "step": 1772 }, { "epoch": 0.20355912743972446, "grad_norm": 0.2284477949142456, "learning_rate": 3.4340912780929244e-05, "loss": 0.2544, "step": 1773 }, { "epoch": 0.20367393800229622, "grad_norm": 0.22807462513446808, "learning_rate": 3.429484265177954e-05, "loss": 0.26, "step": 1774 }, { "epoch": 0.20378874856486798, "grad_norm": 0.22027039527893066, "learning_rate": 3.4248780246585896e-05, "loss": 0.2395, "step": 1775 }, { "epoch": 0.20390355912743974, "grad_norm": 0.23222993314266205, "learning_rate": 3.4202725627710136e-05, "loss": 0.2642, "step": 1776 }, { "epoch": 0.20401836969001147, "grad_norm": 0.23172692954540253, "learning_rate": 3.415667885750354e-05, "loss": 0.2424, "step": 1777 }, { "epoch": 0.20413318025258323, "grad_norm": 0.6029019355773926, "learning_rate": 3.411063999830677e-05, "loss": 0.2675, "step": 1778 }, { "epoch": 0.204247990815155, "grad_norm": 0.22548621892929077, "learning_rate": 3.406460911244973e-05, "loss": 0.268, "step": 1779 }, { "epoch": 0.20436280137772675, "grad_norm": 0.23414108157157898, "learning_rate": 3.401858626225163e-05, "loss": 0.2775, "step": 1780 }, { "epoch": 0.2044776119402985, "grad_norm": 0.26109474897384644, "learning_rate": 3.397257151002068e-05, "loss": 0.2469, "step": 1781 }, { "epoch": 0.20459242250287027, "grad_norm": 0.2124873250722885, "learning_rate": 3.392656491805422e-05, "loss": 0.2436, "step": 1782 }, { "epoch": 0.20470723306544203, "grad_norm": 0.22689960896968842, "learning_rate": 3.388056654863848e-05, "loss": 0.2716, "step": 1783 }, { "epoch": 0.2048220436280138, "grad_norm": 0.21825358271598816, "learning_rate": 3.383457646404862e-05, "loss": 0.2572, "step": 1784 }, { "epoch": 0.20493685419058552, "grad_norm": 0.22925369441509247, "learning_rate": 3.378859472654851e-05, "loss": 0.2605, "step": 1785 }, { "epoch": 0.20505166475315728, "grad_norm": 0.28769394755363464, "learning_rate": 3.374262139839076e-05, "loss": 0.2502, "step": 1786 }, { "epoch": 0.20516647531572904, "grad_norm": 0.2200111448764801, "learning_rate": 3.369665654181663e-05, "loss": 0.2694, "step": 1787 }, { "epoch": 0.2052812858783008, "grad_norm": 0.2168581634759903, "learning_rate": 3.365070021905585e-05, "loss": 0.2587, "step": 1788 }, { "epoch": 0.20539609644087256, "grad_norm": 0.21235212683677673, "learning_rate": 3.3604752492326614e-05, "loss": 0.2731, "step": 1789 }, { "epoch": 0.20551090700344432, "grad_norm": 0.20412328839302063, "learning_rate": 3.355881342383549e-05, "loss": 0.2539, "step": 1790 }, { "epoch": 0.20562571756601608, "grad_norm": 0.21417833864688873, "learning_rate": 3.351288307577731e-05, "loss": 0.2475, "step": 1791 }, { "epoch": 0.20574052812858784, "grad_norm": 0.23459742963314056, "learning_rate": 3.3466961510335125e-05, "loss": 0.2778, "step": 1792 }, { "epoch": 0.20585533869115957, "grad_norm": 0.20970244705677032, "learning_rate": 3.3421048789680043e-05, "loss": 0.2551, "step": 1793 }, { "epoch": 0.20597014925373133, "grad_norm": 0.20398445427417755, "learning_rate": 3.3375144975971276e-05, "loss": 0.2628, "step": 1794 }, { "epoch": 0.2060849598163031, "grad_norm": 0.2367313802242279, "learning_rate": 3.3329250131355914e-05, "loss": 0.291, "step": 1795 }, { "epoch": 0.20619977037887485, "grad_norm": 0.22901400923728943, "learning_rate": 3.328336431796892e-05, "loss": 0.262, "step": 1796 }, { "epoch": 0.2063145809414466, "grad_norm": 0.21343430876731873, "learning_rate": 3.3237487597933045e-05, "loss": 0.2784, "step": 1797 }, { "epoch": 0.20642939150401837, "grad_norm": 0.23068155348300934, "learning_rate": 3.319162003335871e-05, "loss": 0.2907, "step": 1798 }, { "epoch": 0.20654420206659013, "grad_norm": 0.319488525390625, "learning_rate": 3.314576168634394e-05, "loss": 0.2671, "step": 1799 }, { "epoch": 0.2066590126291619, "grad_norm": 0.19479598104953766, "learning_rate": 3.30999126189743e-05, "loss": 0.2285, "step": 1800 }, { "epoch": 0.20677382319173365, "grad_norm": 0.2127942591905594, "learning_rate": 3.305407289332279e-05, "loss": 0.2413, "step": 1801 }, { "epoch": 0.20688863375430538, "grad_norm": 0.21598105132579803, "learning_rate": 3.300824257144974e-05, "loss": 0.2528, "step": 1802 }, { "epoch": 0.20700344431687714, "grad_norm": 0.28398001194000244, "learning_rate": 3.296242171540277e-05, "loss": 0.2712, "step": 1803 }, { "epoch": 0.2071182548794489, "grad_norm": 0.1984858363866806, "learning_rate": 3.291661038721668e-05, "loss": 0.2612, "step": 1804 }, { "epoch": 0.20723306544202066, "grad_norm": 0.24176955223083496, "learning_rate": 3.287080864891335e-05, "loss": 0.2735, "step": 1805 }, { "epoch": 0.20734787600459242, "grad_norm": 0.21210023760795593, "learning_rate": 3.28250165625017e-05, "loss": 0.2352, "step": 1806 }, { "epoch": 0.20746268656716418, "grad_norm": 0.2341444194316864, "learning_rate": 3.2779234189977604e-05, "loss": 0.2719, "step": 1807 }, { "epoch": 0.20757749712973594, "grad_norm": 0.22857381403446198, "learning_rate": 3.2733461593323724e-05, "loss": 0.2541, "step": 1808 }, { "epoch": 0.2076923076923077, "grad_norm": 0.2300165444612503, "learning_rate": 3.268769883450955e-05, "loss": 0.2808, "step": 1809 }, { "epoch": 0.20780711825487944, "grad_norm": 0.20939932763576508, "learning_rate": 3.26419459754912e-05, "loss": 0.2671, "step": 1810 }, { "epoch": 0.2079219288174512, "grad_norm": 0.217063307762146, "learning_rate": 3.2596203078211424e-05, "loss": 0.2541, "step": 1811 }, { "epoch": 0.20803673938002296, "grad_norm": 0.227998748421669, "learning_rate": 3.255047020459947e-05, "loss": 0.2638, "step": 1812 }, { "epoch": 0.20815154994259472, "grad_norm": 0.2113308310508728, "learning_rate": 3.250474741657101e-05, "loss": 0.2594, "step": 1813 }, { "epoch": 0.20826636050516648, "grad_norm": 0.20635007321834564, "learning_rate": 3.24590347760281e-05, "loss": 0.2679, "step": 1814 }, { "epoch": 0.20838117106773824, "grad_norm": 0.22136038541793823, "learning_rate": 3.241333234485901e-05, "loss": 0.2612, "step": 1815 }, { "epoch": 0.20849598163031, "grad_norm": 0.22155484557151794, "learning_rate": 3.236764018493821e-05, "loss": 0.2473, "step": 1816 }, { "epoch": 0.20861079219288176, "grad_norm": 0.22638213634490967, "learning_rate": 3.232195835812627e-05, "loss": 0.2614, "step": 1817 }, { "epoch": 0.20872560275545352, "grad_norm": 0.2067272663116455, "learning_rate": 3.227628692626974e-05, "loss": 0.2583, "step": 1818 }, { "epoch": 0.20884041331802525, "grad_norm": 0.21903648972511292, "learning_rate": 3.223062595120113e-05, "loss": 0.2691, "step": 1819 }, { "epoch": 0.208955223880597, "grad_norm": 0.22642278671264648, "learning_rate": 3.2184975494738774e-05, "loss": 0.2739, "step": 1820 }, { "epoch": 0.20907003444316877, "grad_norm": 3.4150588512420654, "learning_rate": 3.213933561868679e-05, "loss": 0.3539, "step": 1821 }, { "epoch": 0.20918484500574053, "grad_norm": 0.22557063400745392, "learning_rate": 3.2093706384834956e-05, "loss": 0.2635, "step": 1822 }, { "epoch": 0.2092996555683123, "grad_norm": 0.2474813610315323, "learning_rate": 3.2048087854958635e-05, "loss": 0.2713, "step": 1823 }, { "epoch": 0.20941446613088405, "grad_norm": 0.20022502541542053, "learning_rate": 3.200248009081868e-05, "loss": 0.2527, "step": 1824 }, { "epoch": 0.2095292766934558, "grad_norm": 0.2229076772928238, "learning_rate": 3.1956883154161425e-05, "loss": 0.2584, "step": 1825 }, { "epoch": 0.20964408725602757, "grad_norm": 0.22377021610736847, "learning_rate": 3.191129710671849e-05, "loss": 0.2476, "step": 1826 }, { "epoch": 0.2097588978185993, "grad_norm": 0.22549568116664886, "learning_rate": 3.1865722010206777e-05, "loss": 0.2973, "step": 1827 }, { "epoch": 0.20987370838117106, "grad_norm": 0.20619456470012665, "learning_rate": 3.182015792632839e-05, "loss": 0.2525, "step": 1828 }, { "epoch": 0.20998851894374282, "grad_norm": 0.21147136390209198, "learning_rate": 3.177460491677046e-05, "loss": 0.2749, "step": 1829 }, { "epoch": 0.21010332950631458, "grad_norm": 0.2244318127632141, "learning_rate": 3.172906304320518e-05, "loss": 0.2793, "step": 1830 }, { "epoch": 0.21021814006888634, "grad_norm": 0.22842170298099518, "learning_rate": 3.168353236728964e-05, "loss": 0.2647, "step": 1831 }, { "epoch": 0.2103329506314581, "grad_norm": 0.22856798768043518, "learning_rate": 3.163801295066576e-05, "loss": 0.27, "step": 1832 }, { "epoch": 0.21044776119402986, "grad_norm": 0.20925022661685944, "learning_rate": 3.159250485496025e-05, "loss": 0.2706, "step": 1833 }, { "epoch": 0.21056257175660162, "grad_norm": 0.221757709980011, "learning_rate": 3.154700814178446e-05, "loss": 0.259, "step": 1834 }, { "epoch": 0.21067738231917335, "grad_norm": 0.2050991654396057, "learning_rate": 3.1501522872734356e-05, "loss": 0.2525, "step": 1835 }, { "epoch": 0.2107921928817451, "grad_norm": 0.3261232078075409, "learning_rate": 3.145604910939041e-05, "loss": 0.262, "step": 1836 }, { "epoch": 0.21090700344431687, "grad_norm": 0.22663664817810059, "learning_rate": 3.141058691331747e-05, "loss": 0.2627, "step": 1837 }, { "epoch": 0.21102181400688863, "grad_norm": 1.5937424898147583, "learning_rate": 3.1365136346064805e-05, "loss": 0.3038, "step": 1838 }, { "epoch": 0.2111366245694604, "grad_norm": 0.2258502095937729, "learning_rate": 3.131969746916587e-05, "loss": 0.2677, "step": 1839 }, { "epoch": 0.21125143513203215, "grad_norm": 0.21987420320510864, "learning_rate": 3.127427034413831e-05, "loss": 0.2574, "step": 1840 }, { "epoch": 0.2113662456946039, "grad_norm": 0.2169165015220642, "learning_rate": 3.122885503248386e-05, "loss": 0.2682, "step": 1841 }, { "epoch": 0.21148105625717567, "grad_norm": 0.2204608917236328, "learning_rate": 3.118345159568832e-05, "loss": 0.2601, "step": 1842 }, { "epoch": 0.21159586681974743, "grad_norm": 0.2136821299791336, "learning_rate": 3.113806009522131e-05, "loss": 0.255, "step": 1843 }, { "epoch": 0.21171067738231916, "grad_norm": 0.3230203092098236, "learning_rate": 3.109268059253637e-05, "loss": 0.2695, "step": 1844 }, { "epoch": 0.21182548794489092, "grad_norm": 0.22603587806224823, "learning_rate": 3.104731314907075e-05, "loss": 0.262, "step": 1845 }, { "epoch": 0.21194029850746268, "grad_norm": 0.2091800719499588, "learning_rate": 3.1001957826245405e-05, "loss": 0.2629, "step": 1846 }, { "epoch": 0.21205510907003444, "grad_norm": 0.19685199856758118, "learning_rate": 3.0956614685464875e-05, "loss": 0.2513, "step": 1847 }, { "epoch": 0.2121699196326062, "grad_norm": 0.21950745582580566, "learning_rate": 3.0911283788117154e-05, "loss": 0.2582, "step": 1848 }, { "epoch": 0.21228473019517796, "grad_norm": 0.9157978892326355, "learning_rate": 3.086596519557377e-05, "loss": 0.285, "step": 1849 }, { "epoch": 0.21239954075774972, "grad_norm": 0.2070590704679489, "learning_rate": 3.0820658969189504e-05, "loss": 0.2373, "step": 1850 }, { "epoch": 0.21251435132032148, "grad_norm": 0.5194852352142334, "learning_rate": 3.07753651703024e-05, "loss": 0.2171, "step": 1851 }, { "epoch": 0.21262916188289321, "grad_norm": 0.21551884710788727, "learning_rate": 3.073008386023372e-05, "loss": 0.2705, "step": 1852 }, { "epoch": 0.21274397244546497, "grad_norm": 0.23168368637561798, "learning_rate": 3.068481510028777e-05, "loss": 0.2731, "step": 1853 }, { "epoch": 0.21285878300803673, "grad_norm": 0.20125722885131836, "learning_rate": 3.063955895175192e-05, "loss": 0.2506, "step": 1854 }, { "epoch": 0.2129735935706085, "grad_norm": 0.2250179797410965, "learning_rate": 3.05943154758964e-05, "loss": 0.2602, "step": 1855 }, { "epoch": 0.21308840413318025, "grad_norm": 0.2072318196296692, "learning_rate": 3.054908473397435e-05, "loss": 0.2425, "step": 1856 }, { "epoch": 0.213203214695752, "grad_norm": 0.21490205824375153, "learning_rate": 3.0503866787221625e-05, "loss": 0.2535, "step": 1857 }, { "epoch": 0.21331802525832377, "grad_norm": 0.6238004565238953, "learning_rate": 3.0458661696856774e-05, "loss": 0.2516, "step": 1858 }, { "epoch": 0.21343283582089553, "grad_norm": 0.21551378071308136, "learning_rate": 3.0413469524080926e-05, "loss": 0.2644, "step": 1859 }, { "epoch": 0.21354764638346727, "grad_norm": 0.21252921223640442, "learning_rate": 3.0368290330077746e-05, "loss": 0.2652, "step": 1860 }, { "epoch": 0.21366245694603903, "grad_norm": 1.511958360671997, "learning_rate": 3.0323124176013297e-05, "loss": 0.2646, "step": 1861 }, { "epoch": 0.21377726750861079, "grad_norm": 0.22527670860290527, "learning_rate": 3.027797112303601e-05, "loss": 0.2935, "step": 1862 }, { "epoch": 0.21389207807118255, "grad_norm": 0.501739501953125, "learning_rate": 3.0232831232276595e-05, "loss": 0.2658, "step": 1863 }, { "epoch": 0.2140068886337543, "grad_norm": 0.21468572318553925, "learning_rate": 3.01877045648479e-05, "loss": 0.2676, "step": 1864 }, { "epoch": 0.21412169919632607, "grad_norm": 0.20226424932479858, "learning_rate": 3.0142591181844896e-05, "loss": 0.253, "step": 1865 }, { "epoch": 0.21423650975889783, "grad_norm": 0.2132348120212555, "learning_rate": 3.009749114434457e-05, "loss": 0.2765, "step": 1866 }, { "epoch": 0.21435132032146959, "grad_norm": 0.21186605095863342, "learning_rate": 3.0052404513405817e-05, "loss": 0.2719, "step": 1867 }, { "epoch": 0.21446613088404134, "grad_norm": 0.22309675812721252, "learning_rate": 3.0007331350069404e-05, "loss": 0.2688, "step": 1868 }, { "epoch": 0.21458094144661308, "grad_norm": 1.6950936317443848, "learning_rate": 2.9962271715357888e-05, "loss": 0.266, "step": 1869 }, { "epoch": 0.21469575200918484, "grad_norm": 0.2160518318414688, "learning_rate": 2.9917225670275454e-05, "loss": 0.2648, "step": 1870 }, { "epoch": 0.2148105625717566, "grad_norm": 0.21203674376010895, "learning_rate": 2.9872193275807933e-05, "loss": 0.2782, "step": 1871 }, { "epoch": 0.21492537313432836, "grad_norm": 0.21599116921424866, "learning_rate": 2.982717459292265e-05, "loss": 0.2649, "step": 1872 }, { "epoch": 0.21504018369690012, "grad_norm": 0.2164108008146286, "learning_rate": 2.9782169682568388e-05, "loss": 0.2622, "step": 1873 }, { "epoch": 0.21515499425947188, "grad_norm": 0.23976142704486847, "learning_rate": 2.973717860567526e-05, "loss": 0.2481, "step": 1874 }, { "epoch": 0.21526980482204364, "grad_norm": 0.20850960910320282, "learning_rate": 2.969220142315465e-05, "loss": 0.2585, "step": 1875 }, { "epoch": 0.2153846153846154, "grad_norm": 0.21413646638393402, "learning_rate": 2.9647238195899168e-05, "loss": 0.2634, "step": 1876 }, { "epoch": 0.21549942594718713, "grad_norm": 0.2141532003879547, "learning_rate": 2.960228898478251e-05, "loss": 0.2703, "step": 1877 }, { "epoch": 0.2156142365097589, "grad_norm": 0.2082514762878418, "learning_rate": 2.9557353850659364e-05, "loss": 0.2615, "step": 1878 }, { "epoch": 0.21572904707233065, "grad_norm": 0.24763162434101105, "learning_rate": 2.951243285436542e-05, "loss": 0.2616, "step": 1879 }, { "epoch": 0.2158438576349024, "grad_norm": 0.23579436540603638, "learning_rate": 2.9467526056717167e-05, "loss": 0.2599, "step": 1880 }, { "epoch": 0.21595866819747417, "grad_norm": 0.2066401243209839, "learning_rate": 2.9422633518511926e-05, "loss": 0.2519, "step": 1881 }, { "epoch": 0.21607347876004593, "grad_norm": 0.21510553359985352, "learning_rate": 2.9377755300527648e-05, "loss": 0.2637, "step": 1882 }, { "epoch": 0.2161882893226177, "grad_norm": 0.2041855752468109, "learning_rate": 2.933289146352298e-05, "loss": 0.2455, "step": 1883 }, { "epoch": 0.21630309988518945, "grad_norm": 0.2956349849700928, "learning_rate": 2.9288042068237025e-05, "loss": 0.26, "step": 1884 }, { "epoch": 0.21641791044776118, "grad_norm": 0.20441268384456635, "learning_rate": 2.9243207175389377e-05, "loss": 0.2538, "step": 1885 }, { "epoch": 0.21653272101033294, "grad_norm": 0.20767536759376526, "learning_rate": 2.9198386845679975e-05, "loss": 0.2427, "step": 1886 }, { "epoch": 0.2166475315729047, "grad_norm": 0.23535972833633423, "learning_rate": 2.9153581139789052e-05, "loss": 0.2532, "step": 1887 }, { "epoch": 0.21676234213547646, "grad_norm": 0.21221484243869781, "learning_rate": 2.910879011837703e-05, "loss": 0.2644, "step": 1888 }, { "epoch": 0.21687715269804822, "grad_norm": 0.21474778652191162, "learning_rate": 2.9064013842084463e-05, "loss": 0.2536, "step": 1889 }, { "epoch": 0.21699196326061998, "grad_norm": 0.23032385110855103, "learning_rate": 2.9019252371531955e-05, "loss": 0.2788, "step": 1890 }, { "epoch": 0.21710677382319174, "grad_norm": 0.21780522167682648, "learning_rate": 2.8974505767320037e-05, "loss": 0.2773, "step": 1891 }, { "epoch": 0.2172215843857635, "grad_norm": 0.21778292953968048, "learning_rate": 2.892977409002912e-05, "loss": 0.2627, "step": 1892 }, { "epoch": 0.21733639494833526, "grad_norm": 0.2375197410583496, "learning_rate": 2.888505740021942e-05, "loss": 0.259, "step": 1893 }, { "epoch": 0.217451205510907, "grad_norm": 0.20985817909240723, "learning_rate": 2.8840355758430837e-05, "loss": 0.2404, "step": 1894 }, { "epoch": 0.21756601607347875, "grad_norm": 0.19607439637184143, "learning_rate": 2.8795669225182938e-05, "loss": 0.2279, "step": 1895 }, { "epoch": 0.2176808266360505, "grad_norm": 0.25742465257644653, "learning_rate": 2.8750997860974776e-05, "loss": 0.2779, "step": 1896 }, { "epoch": 0.21779563719862227, "grad_norm": 0.21443529427051544, "learning_rate": 2.870634172628494e-05, "loss": 0.2567, "step": 1897 }, { "epoch": 0.21791044776119403, "grad_norm": 0.19820645451545715, "learning_rate": 2.8661700881571356e-05, "loss": 0.2474, "step": 1898 }, { "epoch": 0.2180252583237658, "grad_norm": 0.2133588045835495, "learning_rate": 2.861707538727125e-05, "loss": 0.271, "step": 1899 }, { "epoch": 0.21814006888633755, "grad_norm": 0.33753159642219543, "learning_rate": 2.8572465303801064e-05, "loss": 0.2688, "step": 1900 }, { "epoch": 0.2182548794489093, "grad_norm": 0.21100272238254547, "learning_rate": 2.8527870691556404e-05, "loss": 0.2285, "step": 1901 }, { "epoch": 0.21836969001148104, "grad_norm": 0.21952016651630402, "learning_rate": 2.848329161091189e-05, "loss": 0.2638, "step": 1902 }, { "epoch": 0.2184845005740528, "grad_norm": 0.20814211666584015, "learning_rate": 2.843872812222113e-05, "loss": 0.2527, "step": 1903 }, { "epoch": 0.21859931113662456, "grad_norm": 0.20413827896118164, "learning_rate": 2.8394180285816674e-05, "loss": 0.2542, "step": 1904 }, { "epoch": 0.21871412169919632, "grad_norm": 0.2153455764055252, "learning_rate": 2.8349648162009785e-05, "loss": 0.2713, "step": 1905 }, { "epoch": 0.21882893226176808, "grad_norm": 0.20827679336071014, "learning_rate": 2.8305131811090537e-05, "loss": 0.2579, "step": 1906 }, { "epoch": 0.21894374282433984, "grad_norm": 0.2041427493095398, "learning_rate": 2.8260631293327594e-05, "loss": 0.2366, "step": 1907 }, { "epoch": 0.2190585533869116, "grad_norm": 0.19989615678787231, "learning_rate": 2.821614666896822e-05, "loss": 0.2393, "step": 1908 }, { "epoch": 0.21917336394948336, "grad_norm": 0.25029799342155457, "learning_rate": 2.817167799823815e-05, "loss": 0.255, "step": 1909 }, { "epoch": 0.21928817451205512, "grad_norm": 0.27168893814086914, "learning_rate": 2.8127225341341487e-05, "loss": 0.2566, "step": 1910 }, { "epoch": 0.21940298507462686, "grad_norm": 0.2127864509820938, "learning_rate": 2.808278875846072e-05, "loss": 0.2562, "step": 1911 }, { "epoch": 0.21951779563719861, "grad_norm": 0.21291004121303558, "learning_rate": 2.803836830975654e-05, "loss": 0.255, "step": 1912 }, { "epoch": 0.21963260619977037, "grad_norm": 0.21204964816570282, "learning_rate": 2.7993964055367774e-05, "loss": 0.2507, "step": 1913 }, { "epoch": 0.21974741676234213, "grad_norm": 0.23964549601078033, "learning_rate": 2.7949576055411373e-05, "loss": 0.292, "step": 1914 }, { "epoch": 0.2198622273249139, "grad_norm": 0.20267213881015778, "learning_rate": 2.7905204369982225e-05, "loss": 0.2427, "step": 1915 }, { "epoch": 0.21997703788748565, "grad_norm": 1.3882126808166504, "learning_rate": 2.7860849059153186e-05, "loss": 0.2915, "step": 1916 }, { "epoch": 0.22009184845005741, "grad_norm": 0.2777697741985321, "learning_rate": 2.7816510182974886e-05, "loss": 0.2716, "step": 1917 }, { "epoch": 0.22020665901262917, "grad_norm": 0.32412394881248474, "learning_rate": 2.7772187801475778e-05, "loss": 0.2555, "step": 1918 }, { "epoch": 0.2203214695752009, "grad_norm": 0.22419683635234833, "learning_rate": 2.772788197466191e-05, "loss": 0.2551, "step": 1919 }, { "epoch": 0.22043628013777267, "grad_norm": 0.23552727699279785, "learning_rate": 2.7683592762516967e-05, "loss": 0.2528, "step": 1920 }, { "epoch": 0.22055109070034443, "grad_norm": 0.2165617048740387, "learning_rate": 2.7639320225002108e-05, "loss": 0.269, "step": 1921 }, { "epoch": 0.2206659012629162, "grad_norm": 2.3390657901763916, "learning_rate": 2.7595064422055946e-05, "loss": 0.271, "step": 1922 }, { "epoch": 0.22078071182548795, "grad_norm": 0.244068905711174, "learning_rate": 2.755082541359441e-05, "loss": 0.2584, "step": 1923 }, { "epoch": 0.2208955223880597, "grad_norm": 0.7586172223091125, "learning_rate": 2.75066032595107e-05, "loss": 0.2688, "step": 1924 }, { "epoch": 0.22101033295063147, "grad_norm": 0.23893283307552338, "learning_rate": 2.746239801967522e-05, "loss": 0.2676, "step": 1925 }, { "epoch": 0.22112514351320323, "grad_norm": 0.22780030965805054, "learning_rate": 2.7418209753935464e-05, "loss": 0.2648, "step": 1926 }, { "epoch": 0.22123995407577496, "grad_norm": 0.2324698269367218, "learning_rate": 2.737403852211591e-05, "loss": 0.2721, "step": 1927 }, { "epoch": 0.22135476463834672, "grad_norm": 0.21948707103729248, "learning_rate": 2.732988438401802e-05, "loss": 0.2586, "step": 1928 }, { "epoch": 0.22146957520091848, "grad_norm": 0.24277962744235992, "learning_rate": 2.728574739942009e-05, "loss": 0.2693, "step": 1929 }, { "epoch": 0.22158438576349024, "grad_norm": 0.20629137754440308, "learning_rate": 2.72416276280772e-05, "loss": 0.2394, "step": 1930 }, { "epoch": 0.221699196326062, "grad_norm": 0.24851064383983612, "learning_rate": 2.7197525129721138e-05, "loss": 0.2574, "step": 1931 }, { "epoch": 0.22181400688863376, "grad_norm": 0.5961745381355286, "learning_rate": 2.715343996406028e-05, "loss": 0.2902, "step": 1932 }, { "epoch": 0.22192881745120552, "grad_norm": 0.2814508378505707, "learning_rate": 2.7109372190779564e-05, "loss": 0.2498, "step": 1933 }, { "epoch": 0.22204362801377728, "grad_norm": 0.2274850606918335, "learning_rate": 2.706532186954035e-05, "loss": 0.2543, "step": 1934 }, { "epoch": 0.22215843857634904, "grad_norm": 0.21804305911064148, "learning_rate": 2.7021289059980397e-05, "loss": 0.245, "step": 1935 }, { "epoch": 0.22227324913892077, "grad_norm": 0.2246781438589096, "learning_rate": 2.6977273821713743e-05, "loss": 0.2597, "step": 1936 }, { "epoch": 0.22238805970149253, "grad_norm": 0.23735620081424713, "learning_rate": 2.6933276214330635e-05, "loss": 0.2867, "step": 1937 }, { "epoch": 0.2225028702640643, "grad_norm": 0.23082168400287628, "learning_rate": 2.688929629739747e-05, "loss": 0.2463, "step": 1938 }, { "epoch": 0.22261768082663605, "grad_norm": 0.235172301530838, "learning_rate": 2.6845334130456672e-05, "loss": 0.2606, "step": 1939 }, { "epoch": 0.2227324913892078, "grad_norm": 0.2274804264307022, "learning_rate": 2.6801389773026642e-05, "loss": 0.2874, "step": 1940 }, { "epoch": 0.22284730195177957, "grad_norm": 0.23293572664260864, "learning_rate": 2.6757463284601682e-05, "loss": 0.2566, "step": 1941 }, { "epoch": 0.22296211251435133, "grad_norm": 0.22622771561145782, "learning_rate": 2.671355472465188e-05, "loss": 0.2698, "step": 1942 }, { "epoch": 0.2230769230769231, "grad_norm": 0.19905918836593628, "learning_rate": 2.6669664152623053e-05, "loss": 0.2319, "step": 1943 }, { "epoch": 0.22319173363949482, "grad_norm": 0.21717073023319244, "learning_rate": 2.662579162793667e-05, "loss": 0.2588, "step": 1944 }, { "epoch": 0.22330654420206658, "grad_norm": 0.2184678018093109, "learning_rate": 2.6581937209989806e-05, "loss": 0.2414, "step": 1945 }, { "epoch": 0.22342135476463834, "grad_norm": 0.2039106786251068, "learning_rate": 2.6538100958154945e-05, "loss": 0.25, "step": 1946 }, { "epoch": 0.2235361653272101, "grad_norm": 0.22602881491184235, "learning_rate": 2.649428293178005e-05, "loss": 0.2468, "step": 1947 }, { "epoch": 0.22365097588978186, "grad_norm": 0.22573672235012054, "learning_rate": 2.6450483190188347e-05, "loss": 0.2724, "step": 1948 }, { "epoch": 0.22376578645235362, "grad_norm": 0.2052389681339264, "learning_rate": 2.6406701792678364e-05, "loss": 0.248, "step": 1949 }, { "epoch": 0.22388059701492538, "grad_norm": 0.22454118728637695, "learning_rate": 2.6362938798523755e-05, "loss": 0.2653, "step": 1950 }, { "epoch": 0.22399540757749714, "grad_norm": 0.23892787098884583, "learning_rate": 2.6319194266973256e-05, "loss": 0.2545, "step": 1951 }, { "epoch": 0.22411021814006887, "grad_norm": 0.21624861657619476, "learning_rate": 2.6275468257250644e-05, "loss": 0.2628, "step": 1952 }, { "epoch": 0.22422502870264063, "grad_norm": 3.0560247898101807, "learning_rate": 2.6231760828554594e-05, "loss": 0.3081, "step": 1953 }, { "epoch": 0.2243398392652124, "grad_norm": 0.23642711341381073, "learning_rate": 2.6188072040058615e-05, "loss": 0.282, "step": 1954 }, { "epoch": 0.22445464982778415, "grad_norm": 0.23321858048439026, "learning_rate": 2.6144401950911017e-05, "loss": 0.2601, "step": 1955 }, { "epoch": 0.2245694603903559, "grad_norm": 0.20993788540363312, "learning_rate": 2.610075062023475e-05, "loss": 0.2448, "step": 1956 }, { "epoch": 0.22468427095292767, "grad_norm": 0.2193962186574936, "learning_rate": 2.6057118107127402e-05, "loss": 0.2602, "step": 1957 }, { "epoch": 0.22479908151549943, "grad_norm": 0.22194808721542358, "learning_rate": 2.601350447066105e-05, "loss": 0.2507, "step": 1958 }, { "epoch": 0.2249138920780712, "grad_norm": 0.22372685372829437, "learning_rate": 2.5969909769882264e-05, "loss": 0.2527, "step": 1959 }, { "epoch": 0.22502870264064295, "grad_norm": 3.5437211990356445, "learning_rate": 2.592633406381193e-05, "loss": 0.3243, "step": 1960 }, { "epoch": 0.22514351320321468, "grad_norm": 0.32749542593955994, "learning_rate": 2.5882777411445254e-05, "loss": 0.264, "step": 1961 }, { "epoch": 0.22525832376578644, "grad_norm": 0.22948352992534637, "learning_rate": 2.583923987175161e-05, "loss": 0.2501, "step": 1962 }, { "epoch": 0.2253731343283582, "grad_norm": 0.21154186129570007, "learning_rate": 2.5795721503674527e-05, "loss": 0.2682, "step": 1963 }, { "epoch": 0.22548794489092996, "grad_norm": 0.22514931857585907, "learning_rate": 2.575222236613156e-05, "loss": 0.238, "step": 1964 }, { "epoch": 0.22560275545350172, "grad_norm": 0.22758300602436066, "learning_rate": 2.5708742518014242e-05, "loss": 0.2567, "step": 1965 }, { "epoch": 0.22571756601607348, "grad_norm": 0.22797608375549316, "learning_rate": 2.566528201818799e-05, "loss": 0.2685, "step": 1966 }, { "epoch": 0.22583237657864524, "grad_norm": 0.2498752772808075, "learning_rate": 2.5621840925492012e-05, "loss": 0.2779, "step": 1967 }, { "epoch": 0.225947187141217, "grad_norm": 0.21452689170837402, "learning_rate": 2.557841929873926e-05, "loss": 0.2473, "step": 1968 }, { "epoch": 0.22606199770378874, "grad_norm": 0.2671981751918793, "learning_rate": 2.5535017196716316e-05, "loss": 0.2717, "step": 1969 }, { "epoch": 0.2261768082663605, "grad_norm": 0.24177256226539612, "learning_rate": 2.5491634678183327e-05, "loss": 0.2735, "step": 1970 }, { "epoch": 0.22629161882893226, "grad_norm": 0.2059987336397171, "learning_rate": 2.5448271801873957e-05, "loss": 0.2562, "step": 1971 }, { "epoch": 0.22640642939150402, "grad_norm": 0.21532423794269562, "learning_rate": 2.5404928626495212e-05, "loss": 0.2623, "step": 1972 }, { "epoch": 0.22652123995407578, "grad_norm": 0.2113221287727356, "learning_rate": 2.5361605210727515e-05, "loss": 0.2641, "step": 1973 }, { "epoch": 0.22663605051664754, "grad_norm": 0.21115635335445404, "learning_rate": 2.5318301613224478e-05, "loss": 0.2559, "step": 1974 }, { "epoch": 0.2267508610792193, "grad_norm": 0.2364681363105774, "learning_rate": 2.5275017892612885e-05, "loss": 0.263, "step": 1975 }, { "epoch": 0.22686567164179106, "grad_norm": 0.21078121662139893, "learning_rate": 2.523175410749263e-05, "loss": 0.2507, "step": 1976 }, { "epoch": 0.2269804822043628, "grad_norm": 0.2154187113046646, "learning_rate": 2.51885103164366e-05, "loss": 0.2686, "step": 1977 }, { "epoch": 0.22709529276693455, "grad_norm": 0.22576214373111725, "learning_rate": 2.514528657799062e-05, "loss": 0.2891, "step": 1978 }, { "epoch": 0.2272101033295063, "grad_norm": 0.22592754662036896, "learning_rate": 2.5102082950673353e-05, "loss": 0.2988, "step": 1979 }, { "epoch": 0.22732491389207807, "grad_norm": 0.22682155668735504, "learning_rate": 2.505889949297628e-05, "loss": 0.2859, "step": 1980 }, { "epoch": 0.22743972445464983, "grad_norm": 0.213525652885437, "learning_rate": 2.501573626336352e-05, "loss": 0.2645, "step": 1981 }, { "epoch": 0.2275545350172216, "grad_norm": 0.20588089525699615, "learning_rate": 2.4972593320271844e-05, "loss": 0.2451, "step": 1982 }, { "epoch": 0.22766934557979335, "grad_norm": 0.21978680789470673, "learning_rate": 2.4929470722110526e-05, "loss": 0.2633, "step": 1983 }, { "epoch": 0.2277841561423651, "grad_norm": 0.20583631098270416, "learning_rate": 2.488636852726132e-05, "loss": 0.235, "step": 1984 }, { "epoch": 0.22789896670493687, "grad_norm": 0.2160022258758545, "learning_rate": 2.4843286794078367e-05, "loss": 0.2625, "step": 1985 }, { "epoch": 0.2280137772675086, "grad_norm": 0.2213529497385025, "learning_rate": 2.4800225580888048e-05, "loss": 0.2604, "step": 1986 }, { "epoch": 0.22812858783008036, "grad_norm": 0.22390983998775482, "learning_rate": 2.475718494598904e-05, "loss": 0.2706, "step": 1987 }, { "epoch": 0.22824339839265212, "grad_norm": 0.2111867517232895, "learning_rate": 2.4714164947652116e-05, "loss": 0.249, "step": 1988 }, { "epoch": 0.22835820895522388, "grad_norm": 0.2247517853975296, "learning_rate": 2.467116564412011e-05, "loss": 0.2515, "step": 1989 }, { "epoch": 0.22847301951779564, "grad_norm": 0.20712877810001373, "learning_rate": 2.4628187093607858e-05, "loss": 0.2476, "step": 1990 }, { "epoch": 0.2285878300803674, "grad_norm": 3.852858304977417, "learning_rate": 2.4585229354302077e-05, "loss": 0.3835, "step": 1991 }, { "epoch": 0.22870264064293916, "grad_norm": 0.23145267367362976, "learning_rate": 2.454229248436131e-05, "loss": 0.2558, "step": 1992 }, { "epoch": 0.22881745120551092, "grad_norm": 0.22415417432785034, "learning_rate": 2.4499376541915883e-05, "loss": 0.244, "step": 1993 }, { "epoch": 0.22893226176808265, "grad_norm": 0.22326064109802246, "learning_rate": 2.4456481585067744e-05, "loss": 0.2538, "step": 1994 }, { "epoch": 0.2290470723306544, "grad_norm": 0.22245830297470093, "learning_rate": 2.4413607671890446e-05, "loss": 0.2477, "step": 1995 }, { "epoch": 0.22916188289322617, "grad_norm": 0.2230609953403473, "learning_rate": 2.437075486042906e-05, "loss": 0.2583, "step": 1996 }, { "epoch": 0.22927669345579793, "grad_norm": 0.22539827227592468, "learning_rate": 2.4327923208700063e-05, "loss": 0.2667, "step": 1997 }, { "epoch": 0.2293915040183697, "grad_norm": 0.19865399599075317, "learning_rate": 2.4285112774691334e-05, "loss": 0.2616, "step": 1998 }, { "epoch": 0.22950631458094145, "grad_norm": 0.2167324721813202, "learning_rate": 2.424232361636196e-05, "loss": 0.2604, "step": 1999 }, { "epoch": 0.2296211251435132, "grad_norm": 0.22417600452899933, "learning_rate": 2.4199555791642276e-05, "loss": 0.2523, "step": 2000 }, { "epoch": 0.22973593570608497, "grad_norm": 0.22933663427829742, "learning_rate": 2.4156809358433728e-05, "loss": 0.28, "step": 2001 }, { "epoch": 0.2298507462686567, "grad_norm": 0.22136111557483673, "learning_rate": 2.411408437460878e-05, "loss": 0.2673, "step": 2002 }, { "epoch": 0.22996555683122846, "grad_norm": 0.21853789687156677, "learning_rate": 2.4071380898010866e-05, "loss": 0.2714, "step": 2003 }, { "epoch": 0.23008036739380022, "grad_norm": 0.21940599381923676, "learning_rate": 2.4028698986454303e-05, "loss": 0.2778, "step": 2004 }, { "epoch": 0.23019517795637198, "grad_norm": 0.22515974938869476, "learning_rate": 2.398603869772421e-05, "loss": 0.2466, "step": 2005 }, { "epoch": 0.23030998851894374, "grad_norm": 0.2139429748058319, "learning_rate": 2.3943400089576426e-05, "loss": 0.2641, "step": 2006 }, { "epoch": 0.2304247990815155, "grad_norm": 0.2024344801902771, "learning_rate": 2.3900783219737477e-05, "loss": 0.2575, "step": 2007 }, { "epoch": 0.23053960964408726, "grad_norm": 0.21743996441364288, "learning_rate": 2.38581881459044e-05, "loss": 0.2609, "step": 2008 }, { "epoch": 0.23065442020665902, "grad_norm": 0.2277800738811493, "learning_rate": 2.3815614925744762e-05, "loss": 0.2465, "step": 2009 }, { "epoch": 0.23076923076923078, "grad_norm": 0.20104661583900452, "learning_rate": 2.377306361689653e-05, "loss": 0.2505, "step": 2010 }, { "epoch": 0.23088404133180251, "grad_norm": 0.21505054831504822, "learning_rate": 2.3730534276968e-05, "loss": 0.2517, "step": 2011 }, { "epoch": 0.23099885189437427, "grad_norm": 0.19809038937091827, "learning_rate": 2.3688026963537744e-05, "loss": 0.2578, "step": 2012 }, { "epoch": 0.23111366245694603, "grad_norm": 0.2203531265258789, "learning_rate": 2.3645541734154485e-05, "loss": 0.2522, "step": 2013 }, { "epoch": 0.2312284730195178, "grad_norm": 0.1924166977405548, "learning_rate": 2.360307864633709e-05, "loss": 0.2357, "step": 2014 }, { "epoch": 0.23134328358208955, "grad_norm": 0.2087625414133072, "learning_rate": 2.3560637757574417e-05, "loss": 0.2684, "step": 2015 }, { "epoch": 0.2314580941446613, "grad_norm": 0.20556922256946564, "learning_rate": 2.3518219125325267e-05, "loss": 0.2522, "step": 2016 }, { "epoch": 0.23157290470723307, "grad_norm": 0.24676840007305145, "learning_rate": 2.3475822807018335e-05, "loss": 0.2551, "step": 2017 }, { "epoch": 0.23168771526980483, "grad_norm": 0.20037531852722168, "learning_rate": 2.3433448860052074e-05, "loss": 0.2461, "step": 2018 }, { "epoch": 0.23180252583237657, "grad_norm": 0.20775377750396729, "learning_rate": 2.3391097341794683e-05, "loss": 0.2578, "step": 2019 }, { "epoch": 0.23191733639494833, "grad_norm": 0.21024958789348602, "learning_rate": 2.334876830958396e-05, "loss": 0.2685, "step": 2020 }, { "epoch": 0.23203214695752009, "grad_norm": 0.205267533659935, "learning_rate": 2.330646182072729e-05, "loss": 0.2619, "step": 2021 }, { "epoch": 0.23214695752009185, "grad_norm": 0.20531371235847473, "learning_rate": 2.3264177932501523e-05, "loss": 0.2599, "step": 2022 }, { "epoch": 0.2322617680826636, "grad_norm": 0.22959962487220764, "learning_rate": 2.3221916702152914e-05, "loss": 0.2691, "step": 2023 }, { "epoch": 0.23237657864523537, "grad_norm": 0.21381907165050507, "learning_rate": 2.3179678186897062e-05, "loss": 0.2673, "step": 2024 }, { "epoch": 0.23249138920780713, "grad_norm": 0.22534750401973724, "learning_rate": 2.313746244391877e-05, "loss": 0.2689, "step": 2025 }, { "epoch": 0.23260619977037889, "grad_norm": 0.2065858542919159, "learning_rate": 2.3095269530372032e-05, "loss": 0.2476, "step": 2026 }, { "epoch": 0.23272101033295065, "grad_norm": 0.22911454737186432, "learning_rate": 2.3053099503379946e-05, "loss": 0.2641, "step": 2027 }, { "epoch": 0.23283582089552238, "grad_norm": 0.20432275533676147, "learning_rate": 2.3010952420034622e-05, "loss": 0.2495, "step": 2028 }, { "epoch": 0.23295063145809414, "grad_norm": 0.20431137084960938, "learning_rate": 2.2968828337397095e-05, "loss": 0.2474, "step": 2029 }, { "epoch": 0.2330654420206659, "grad_norm": 0.24288056790828705, "learning_rate": 2.292672731249728e-05, "loss": 0.2747, "step": 2030 }, { "epoch": 0.23318025258323766, "grad_norm": 0.1947949379682541, "learning_rate": 2.288464940233384e-05, "loss": 0.2467, "step": 2031 }, { "epoch": 0.23329506314580942, "grad_norm": 0.20914281904697418, "learning_rate": 2.2842594663874172e-05, "loss": 0.2586, "step": 2032 }, { "epoch": 0.23340987370838118, "grad_norm": 0.20378351211547852, "learning_rate": 2.28005631540543e-05, "loss": 0.2462, "step": 2033 }, { "epoch": 0.23352468427095294, "grad_norm": 0.19955675303936005, "learning_rate": 2.2758554929778796e-05, "loss": 0.2441, "step": 2034 }, { "epoch": 0.2336394948335247, "grad_norm": 0.21162179112434387, "learning_rate": 2.2716570047920703e-05, "loss": 0.253, "step": 2035 }, { "epoch": 0.23375430539609643, "grad_norm": 0.20563583076000214, "learning_rate": 2.267460856532149e-05, "loss": 0.2454, "step": 2036 }, { "epoch": 0.2338691159586682, "grad_norm": 0.21722018718719482, "learning_rate": 2.263267053879088e-05, "loss": 0.2684, "step": 2037 }, { "epoch": 0.23398392652123995, "grad_norm": 0.23463919758796692, "learning_rate": 2.2590756025106907e-05, "loss": 0.2604, "step": 2038 }, { "epoch": 0.2340987370838117, "grad_norm": 0.2181900441646576, "learning_rate": 2.2548865081015735e-05, "loss": 0.2788, "step": 2039 }, { "epoch": 0.23421354764638347, "grad_norm": 0.20115943253040314, "learning_rate": 2.250699776323166e-05, "loss": 0.2488, "step": 2040 }, { "epoch": 0.23432835820895523, "grad_norm": 0.18986301124095917, "learning_rate": 2.24651541284369e-05, "loss": 0.2186, "step": 2041 }, { "epoch": 0.234443168771527, "grad_norm": 0.20556855201721191, "learning_rate": 2.242333423328173e-05, "loss": 0.2413, "step": 2042 }, { "epoch": 0.23455797933409875, "grad_norm": 0.19772908091545105, "learning_rate": 2.2381538134384216e-05, "loss": 0.243, "step": 2043 }, { "epoch": 0.23467278989667048, "grad_norm": 0.20830367505550385, "learning_rate": 2.2339765888330195e-05, "loss": 0.2599, "step": 2044 }, { "epoch": 0.23478760045924224, "grad_norm": 0.19054578244686127, "learning_rate": 2.2298017551673245e-05, "loss": 0.2089, "step": 2045 }, { "epoch": 0.234902411021814, "grad_norm": 0.21905316412448883, "learning_rate": 2.225629318093458e-05, "loss": 0.262, "step": 2046 }, { "epoch": 0.23501722158438576, "grad_norm": 0.20357553660869598, "learning_rate": 2.221459283260291e-05, "loss": 0.253, "step": 2047 }, { "epoch": 0.23513203214695752, "grad_norm": 0.21129566431045532, "learning_rate": 2.2172916563134476e-05, "loss": 0.2692, "step": 2048 }, { "epoch": 0.23524684270952928, "grad_norm": 0.220637246966362, "learning_rate": 2.2131264428952942e-05, "loss": 0.2585, "step": 2049 }, { "epoch": 0.23536165327210104, "grad_norm": 0.21446821093559265, "learning_rate": 2.2089636486449217e-05, "loss": 0.2647, "step": 2050 }, { "epoch": 0.2354764638346728, "grad_norm": 0.19844506680965424, "learning_rate": 2.2048032791981515e-05, "loss": 0.2683, "step": 2051 }, { "epoch": 0.23559127439724456, "grad_norm": 0.19950367510318756, "learning_rate": 2.2006453401875207e-05, "loss": 0.2468, "step": 2052 }, { "epoch": 0.2357060849598163, "grad_norm": 0.621609091758728, "learning_rate": 2.196489837242278e-05, "loss": 0.2399, "step": 2053 }, { "epoch": 0.23582089552238805, "grad_norm": 0.2087603509426117, "learning_rate": 2.1923367759883673e-05, "loss": 0.2532, "step": 2054 }, { "epoch": 0.2359357060849598, "grad_norm": 0.20004218816757202, "learning_rate": 2.188186162048437e-05, "loss": 0.2447, "step": 2055 }, { "epoch": 0.23605051664753157, "grad_norm": 0.2121310979127884, "learning_rate": 2.1840380010418133e-05, "loss": 0.2561, "step": 2056 }, { "epoch": 0.23616532721010333, "grad_norm": 0.214610293507576, "learning_rate": 2.1798922985845055e-05, "loss": 0.2705, "step": 2057 }, { "epoch": 0.2362801377726751, "grad_norm": 0.20610269904136658, "learning_rate": 2.175749060289194e-05, "loss": 0.2452, "step": 2058 }, { "epoch": 0.23639494833524685, "grad_norm": 0.20413218438625336, "learning_rate": 2.1716082917652247e-05, "loss": 0.2334, "step": 2059 }, { "epoch": 0.2365097588978186, "grad_norm": 0.21889778971672058, "learning_rate": 2.1674699986185944e-05, "loss": 0.2459, "step": 2060 }, { "epoch": 0.23662456946039034, "grad_norm": 0.20800697803497314, "learning_rate": 2.1633341864519526e-05, "loss": 0.2694, "step": 2061 }, { "epoch": 0.2367393800229621, "grad_norm": 0.20843686163425446, "learning_rate": 2.1592008608645937e-05, "loss": 0.2566, "step": 2062 }, { "epoch": 0.23685419058553386, "grad_norm": 0.21228651702404022, "learning_rate": 2.155070027452437e-05, "loss": 0.2583, "step": 2063 }, { "epoch": 0.23696900114810562, "grad_norm": 0.21435168385505676, "learning_rate": 2.1509416918080344e-05, "loss": 0.2556, "step": 2064 }, { "epoch": 0.23708381171067738, "grad_norm": 0.20719367265701294, "learning_rate": 2.1468158595205543e-05, "loss": 0.2647, "step": 2065 }, { "epoch": 0.23719862227324914, "grad_norm": 0.2098635584115982, "learning_rate": 2.1426925361757727e-05, "loss": 0.2501, "step": 2066 }, { "epoch": 0.2373134328358209, "grad_norm": 0.21878725290298462, "learning_rate": 2.138571727356074e-05, "loss": 0.2577, "step": 2067 }, { "epoch": 0.23742824339839266, "grad_norm": 0.20182645320892334, "learning_rate": 2.1344534386404357e-05, "loss": 0.2472, "step": 2068 }, { "epoch": 0.2375430539609644, "grad_norm": 0.21685220301151276, "learning_rate": 2.1303376756044232e-05, "loss": 0.2517, "step": 2069 }, { "epoch": 0.23765786452353616, "grad_norm": 0.2053937017917633, "learning_rate": 2.126224443820184e-05, "loss": 0.2426, "step": 2070 }, { "epoch": 0.23777267508610792, "grad_norm": 0.19665224850177765, "learning_rate": 2.122113748856438e-05, "loss": 0.2447, "step": 2071 }, { "epoch": 0.23788748564867968, "grad_norm": 0.201670840382576, "learning_rate": 2.1180055962784686e-05, "loss": 0.2533, "step": 2072 }, { "epoch": 0.23800229621125144, "grad_norm": 0.22306306660175323, "learning_rate": 2.1138999916481195e-05, "loss": 0.273, "step": 2073 }, { "epoch": 0.2381171067738232, "grad_norm": 0.20890365540981293, "learning_rate": 2.1097969405237847e-05, "loss": 0.2687, "step": 2074 }, { "epoch": 0.23823191733639495, "grad_norm": 0.1824914664030075, "learning_rate": 2.1056964484604002e-05, "loss": 0.2272, "step": 2075 }, { "epoch": 0.23834672789896671, "grad_norm": 0.2000630497932434, "learning_rate": 2.1015985210094385e-05, "loss": 0.2457, "step": 2076 }, { "epoch": 0.23846153846153847, "grad_norm": 0.1969236135482788, "learning_rate": 2.0975031637188988e-05, "loss": 0.2419, "step": 2077 }, { "epoch": 0.2385763490241102, "grad_norm": 0.20078693330287933, "learning_rate": 2.093410382133303e-05, "loss": 0.2546, "step": 2078 }, { "epoch": 0.23869115958668197, "grad_norm": 0.1980312317609787, "learning_rate": 2.0893201817936814e-05, "loss": 0.2428, "step": 2079 }, { "epoch": 0.23880597014925373, "grad_norm": 0.20566290616989136, "learning_rate": 2.085232568237573e-05, "loss": 0.2591, "step": 2080 }, { "epoch": 0.2389207807118255, "grad_norm": 0.20957884192466736, "learning_rate": 2.0811475469990167e-05, "loss": 0.2581, "step": 2081 }, { "epoch": 0.23903559127439725, "grad_norm": 0.21094214916229248, "learning_rate": 2.0770651236085335e-05, "loss": 0.2638, "step": 2082 }, { "epoch": 0.239150401836969, "grad_norm": 0.19940218329429626, "learning_rate": 2.0729853035931386e-05, "loss": 0.2495, "step": 2083 }, { "epoch": 0.23926521239954077, "grad_norm": 0.20633064210414886, "learning_rate": 2.0689080924763155e-05, "loss": 0.2549, "step": 2084 }, { "epoch": 0.23938002296211253, "grad_norm": 0.191897913813591, "learning_rate": 2.0648334957780154e-05, "loss": 0.2455, "step": 2085 }, { "epoch": 0.23949483352468426, "grad_norm": 0.21078728139400482, "learning_rate": 2.0607615190146523e-05, "loss": 0.2503, "step": 2086 }, { "epoch": 0.23960964408725602, "grad_norm": 0.19875584542751312, "learning_rate": 2.056692167699094e-05, "loss": 0.2615, "step": 2087 }, { "epoch": 0.23972445464982778, "grad_norm": 0.20043672621250153, "learning_rate": 2.0526254473406495e-05, "loss": 0.2421, "step": 2088 }, { "epoch": 0.23983926521239954, "grad_norm": 0.20100829005241394, "learning_rate": 2.0485613634450688e-05, "loss": 0.2512, "step": 2089 }, { "epoch": 0.2399540757749713, "grad_norm": 0.20918972790241241, "learning_rate": 2.0444999215145368e-05, "loss": 0.2472, "step": 2090 }, { "epoch": 0.24006888633754306, "grad_norm": 0.20218582451343536, "learning_rate": 2.0404411270476527e-05, "loss": 0.2483, "step": 2091 }, { "epoch": 0.24018369690011482, "grad_norm": 0.23158149421215057, "learning_rate": 2.036384985539437e-05, "loss": 0.2708, "step": 2092 }, { "epoch": 0.24029850746268658, "grad_norm": 0.22157633304595947, "learning_rate": 2.0323315024813176e-05, "loss": 0.2841, "step": 2093 }, { "epoch": 0.2404133180252583, "grad_norm": 0.21044223010540009, "learning_rate": 2.0282806833611247e-05, "loss": 0.2502, "step": 2094 }, { "epoch": 0.24052812858783007, "grad_norm": 0.2058117389678955, "learning_rate": 2.024232533663077e-05, "loss": 0.2511, "step": 2095 }, { "epoch": 0.24064293915040183, "grad_norm": 0.22106823325157166, "learning_rate": 2.020187058867784e-05, "loss": 0.272, "step": 2096 }, { "epoch": 0.2407577497129736, "grad_norm": 0.2057214081287384, "learning_rate": 2.016144264452232e-05, "loss": 0.2422, "step": 2097 }, { "epoch": 0.24087256027554535, "grad_norm": 0.1983131766319275, "learning_rate": 2.012104155889779e-05, "loss": 0.2496, "step": 2098 }, { "epoch": 0.2409873708381171, "grad_norm": 0.19927173852920532, "learning_rate": 2.008066738650146e-05, "loss": 0.259, "step": 2099 }, { "epoch": 0.24110218140068887, "grad_norm": 0.19547420740127563, "learning_rate": 2.004032018199412e-05, "loss": 0.2421, "step": 2100 }, { "epoch": 0.24121699196326063, "grad_norm": 0.2534225583076477, "learning_rate": 2.0000000000000012e-05, "loss": 0.2753, "step": 2101 }, { "epoch": 0.2413318025258324, "grad_norm": 0.20591586828231812, "learning_rate": 1.995970689510683e-05, "loss": 0.2573, "step": 2102 }, { "epoch": 0.24144661308840412, "grad_norm": 0.1996408849954605, "learning_rate": 1.991944092186559e-05, "loss": 0.2401, "step": 2103 }, { "epoch": 0.24156142365097588, "grad_norm": 0.2128698229789734, "learning_rate": 1.98792021347906e-05, "loss": 0.2563, "step": 2104 }, { "epoch": 0.24167623421354764, "grad_norm": 0.20772746205329895, "learning_rate": 1.983899058835933e-05, "loss": 0.2535, "step": 2105 }, { "epoch": 0.2417910447761194, "grad_norm": 0.21757011115550995, "learning_rate": 1.979880633701241e-05, "loss": 0.2658, "step": 2106 }, { "epoch": 0.24190585533869116, "grad_norm": 0.1955757886171341, "learning_rate": 1.9758649435153458e-05, "loss": 0.2523, "step": 2107 }, { "epoch": 0.24202066590126292, "grad_norm": 0.1978452354669571, "learning_rate": 1.971851993714911e-05, "loss": 0.2595, "step": 2108 }, { "epoch": 0.24213547646383468, "grad_norm": 0.25492963194847107, "learning_rate": 1.967841789732889e-05, "loss": 0.2623, "step": 2109 }, { "epoch": 0.24225028702640644, "grad_norm": 0.2007281631231308, "learning_rate": 1.963834336998515e-05, "loss": 0.2649, "step": 2110 }, { "epoch": 0.24236509758897817, "grad_norm": 0.1998305767774582, "learning_rate": 1.959829640937299e-05, "loss": 0.265, "step": 2111 }, { "epoch": 0.24247990815154993, "grad_norm": 0.2111186534166336, "learning_rate": 1.955827706971019e-05, "loss": 0.2599, "step": 2112 }, { "epoch": 0.2425947187141217, "grad_norm": 0.2020568698644638, "learning_rate": 1.9518285405177148e-05, "loss": 0.249, "step": 2113 }, { "epoch": 0.24270952927669345, "grad_norm": 0.21348898112773895, "learning_rate": 1.947832146991675e-05, "loss": 0.2407, "step": 2114 }, { "epoch": 0.2428243398392652, "grad_norm": 0.2183825820684433, "learning_rate": 1.9438385318034392e-05, "loss": 0.2707, "step": 2115 }, { "epoch": 0.24293915040183697, "grad_norm": 0.20943233370780945, "learning_rate": 1.939847700359783e-05, "loss": 0.2604, "step": 2116 }, { "epoch": 0.24305396096440873, "grad_norm": 0.20719246566295624, "learning_rate": 1.9358596580637142e-05, "loss": 0.2519, "step": 2117 }, { "epoch": 0.2431687715269805, "grad_norm": 0.23434090614318848, "learning_rate": 1.9318744103144634e-05, "loss": 0.2501, "step": 2118 }, { "epoch": 0.24328358208955222, "grad_norm": 0.21274711191654205, "learning_rate": 1.92789196250748e-05, "loss": 0.2636, "step": 2119 }, { "epoch": 0.24339839265212398, "grad_norm": 0.22150346636772156, "learning_rate": 1.9239123200344183e-05, "loss": 0.2711, "step": 2120 }, { "epoch": 0.24351320321469574, "grad_norm": 0.20408597588539124, "learning_rate": 1.9199354882831387e-05, "loss": 0.2516, "step": 2121 }, { "epoch": 0.2436280137772675, "grad_norm": 0.2099815309047699, "learning_rate": 1.915961472637696e-05, "loss": 0.2548, "step": 2122 }, { "epoch": 0.24374282433983926, "grad_norm": 0.20885130763053894, "learning_rate": 1.9119902784783278e-05, "loss": 0.2545, "step": 2123 }, { "epoch": 0.24385763490241102, "grad_norm": 0.20811530947685242, "learning_rate": 1.908021911181459e-05, "loss": 0.2392, "step": 2124 }, { "epoch": 0.24397244546498278, "grad_norm": 0.2182954102754593, "learning_rate": 1.904056376119684e-05, "loss": 0.2656, "step": 2125 }, { "epoch": 0.24408725602755454, "grad_norm": 0.2029140144586563, "learning_rate": 1.90009367866176e-05, "loss": 0.253, "step": 2126 }, { "epoch": 0.2442020665901263, "grad_norm": 0.22218787670135498, "learning_rate": 1.8961338241726054e-05, "loss": 0.2879, "step": 2127 }, { "epoch": 0.24431687715269804, "grad_norm": 0.21819061040878296, "learning_rate": 1.8921768180132898e-05, "loss": 0.243, "step": 2128 }, { "epoch": 0.2444316877152698, "grad_norm": 0.1999558061361313, "learning_rate": 1.8882226655410277e-05, "loss": 0.2365, "step": 2129 }, { "epoch": 0.24454649827784156, "grad_norm": 0.2080967277288437, "learning_rate": 1.8842713721091627e-05, "loss": 0.2672, "step": 2130 }, { "epoch": 0.24466130884041332, "grad_norm": 0.2102326899766922, "learning_rate": 1.880322943067181e-05, "loss": 0.2416, "step": 2131 }, { "epoch": 0.24477611940298508, "grad_norm": 0.20729194581508636, "learning_rate": 1.8763773837606773e-05, "loss": 0.2581, "step": 2132 }, { "epoch": 0.24489092996555684, "grad_norm": 0.19718819856643677, "learning_rate": 1.8724346995313697e-05, "loss": 0.2368, "step": 2133 }, { "epoch": 0.2450057405281286, "grad_norm": 0.20305311679840088, "learning_rate": 1.8684948957170797e-05, "loss": 0.2572, "step": 2134 }, { "epoch": 0.24512055109070036, "grad_norm": 0.20980051159858704, "learning_rate": 1.8645579776517335e-05, "loss": 0.2622, "step": 2135 }, { "epoch": 0.2452353616532721, "grad_norm": 0.2019481360912323, "learning_rate": 1.860623950665344e-05, "loss": 0.2374, "step": 2136 }, { "epoch": 0.24535017221584385, "grad_norm": 0.20496627688407898, "learning_rate": 1.8566928200840128e-05, "loss": 0.2453, "step": 2137 }, { "epoch": 0.2454649827784156, "grad_norm": 0.20696932077407837, "learning_rate": 1.852764591229926e-05, "loss": 0.2662, "step": 2138 }, { "epoch": 0.24557979334098737, "grad_norm": 0.21435528993606567, "learning_rate": 1.8488392694213315e-05, "loss": 0.2313, "step": 2139 }, { "epoch": 0.24569460390355913, "grad_norm": 0.20147587358951569, "learning_rate": 1.8449168599725475e-05, "loss": 0.2374, "step": 2140 }, { "epoch": 0.2458094144661309, "grad_norm": 0.20724155008792877, "learning_rate": 1.8409973681939498e-05, "loss": 0.2622, "step": 2141 }, { "epoch": 0.24592422502870265, "grad_norm": 0.2112211436033249, "learning_rate": 1.8370807993919583e-05, "loss": 0.2506, "step": 2142 }, { "epoch": 0.2460390355912744, "grad_norm": 0.1897684782743454, "learning_rate": 1.8331671588690412e-05, "loss": 0.2349, "step": 2143 }, { "epoch": 0.24615384615384617, "grad_norm": 0.21940523386001587, "learning_rate": 1.8292564519237007e-05, "loss": 0.251, "step": 2144 }, { "epoch": 0.2462686567164179, "grad_norm": 0.20602937042713165, "learning_rate": 1.825348683850467e-05, "loss": 0.2434, "step": 2145 }, { "epoch": 0.24638346727898966, "grad_norm": 0.20886342227458954, "learning_rate": 1.8214438599398918e-05, "loss": 0.2474, "step": 2146 }, { "epoch": 0.24649827784156142, "grad_norm": 0.20574451982975006, "learning_rate": 1.8175419854785414e-05, "loss": 0.2396, "step": 2147 }, { "epoch": 0.24661308840413318, "grad_norm": 0.19280332326889038, "learning_rate": 1.8136430657489864e-05, "loss": 0.2391, "step": 2148 }, { "epoch": 0.24672789896670494, "grad_norm": 0.23758620023727417, "learning_rate": 1.8097471060297997e-05, "loss": 0.249, "step": 2149 }, { "epoch": 0.2468427095292767, "grad_norm": 0.21634730696678162, "learning_rate": 1.8058541115955465e-05, "loss": 0.2528, "step": 2150 }, { "epoch": 0.24695752009184846, "grad_norm": 0.202601358294487, "learning_rate": 1.8019640877167763e-05, "loss": 0.2518, "step": 2151 }, { "epoch": 0.24707233065442022, "grad_norm": 0.2117662876844406, "learning_rate": 1.798077039660018e-05, "loss": 0.2626, "step": 2152 }, { "epoch": 0.24718714121699195, "grad_norm": 0.20489239692687988, "learning_rate": 1.7941929726877706e-05, "loss": 0.2541, "step": 2153 }, { "epoch": 0.2473019517795637, "grad_norm": 0.2188180536031723, "learning_rate": 1.7903118920585006e-05, "loss": 0.2741, "step": 2154 }, { "epoch": 0.24741676234213547, "grad_norm": 0.2097206562757492, "learning_rate": 1.786433803026624e-05, "loss": 0.2723, "step": 2155 }, { "epoch": 0.24753157290470723, "grad_norm": 0.1949864774942398, "learning_rate": 1.7825587108425142e-05, "loss": 0.2255, "step": 2156 }, { "epoch": 0.247646383467279, "grad_norm": 0.35695117712020874, "learning_rate": 1.7786866207524852e-05, "loss": 0.244, "step": 2157 }, { "epoch": 0.24776119402985075, "grad_norm": 0.20163697004318237, "learning_rate": 1.774817537998781e-05, "loss": 0.2459, "step": 2158 }, { "epoch": 0.2478760045924225, "grad_norm": 0.19183699786663055, "learning_rate": 1.770951467819583e-05, "loss": 0.2395, "step": 2159 }, { "epoch": 0.24799081515499427, "grad_norm": 0.19902539253234863, "learning_rate": 1.7670884154489906e-05, "loss": 0.257, "step": 2160 }, { "epoch": 0.248105625717566, "grad_norm": 0.23125576972961426, "learning_rate": 1.7632283861170135e-05, "loss": 0.2429, "step": 2161 }, { "epoch": 0.24822043628013776, "grad_norm": 0.21232996881008148, "learning_rate": 1.759371385049573e-05, "loss": 0.2583, "step": 2162 }, { "epoch": 0.24833524684270952, "grad_norm": 0.20771148800849915, "learning_rate": 1.75551741746849e-05, "loss": 0.2677, "step": 2163 }, { "epoch": 0.24845005740528128, "grad_norm": 0.20135726034641266, "learning_rate": 1.7516664885914788e-05, "loss": 0.2522, "step": 2164 }, { "epoch": 0.24856486796785304, "grad_norm": 0.21911580860614777, "learning_rate": 1.7478186036321352e-05, "loss": 0.2565, "step": 2165 }, { "epoch": 0.2486796785304248, "grad_norm": 0.20177797973155975, "learning_rate": 1.7439737677999435e-05, "loss": 0.2555, "step": 2166 }, { "epoch": 0.24879448909299656, "grad_norm": 0.19869282841682434, "learning_rate": 1.7401319863002487e-05, "loss": 0.2506, "step": 2167 }, { "epoch": 0.24890929965556832, "grad_norm": 0.20635315775871277, "learning_rate": 1.7362932643342686e-05, "loss": 0.2727, "step": 2168 }, { "epoch": 0.24902411021814008, "grad_norm": 0.2042180448770523, "learning_rate": 1.732457607099076e-05, "loss": 0.2528, "step": 2169 }, { "epoch": 0.24913892078071181, "grad_norm": 0.1976262480020523, "learning_rate": 1.7286250197875964e-05, "loss": 0.2512, "step": 2170 }, { "epoch": 0.24925373134328357, "grad_norm": 0.20061518251895905, "learning_rate": 1.7247955075885938e-05, "loss": 0.2455, "step": 2171 }, { "epoch": 0.24936854190585533, "grad_norm": 0.19962383806705475, "learning_rate": 1.7209690756866735e-05, "loss": 0.2455, "step": 2172 }, { "epoch": 0.2494833524684271, "grad_norm": 0.207987442612648, "learning_rate": 1.7171457292622736e-05, "loss": 0.265, "step": 2173 }, { "epoch": 0.24959816303099885, "grad_norm": 0.1961619108915329, "learning_rate": 1.7133254734916466e-05, "loss": 0.2283, "step": 2174 }, { "epoch": 0.24971297359357061, "grad_norm": 0.196563720703125, "learning_rate": 1.7095083135468668e-05, "loss": 0.2373, "step": 2175 }, { "epoch": 0.24982778415614237, "grad_norm": 0.20655861496925354, "learning_rate": 1.7056942545958167e-05, "loss": 0.2437, "step": 2176 }, { "epoch": 0.24994259471871413, "grad_norm": 0.1960250735282898, "learning_rate": 1.701883301802176e-05, "loss": 0.2395, "step": 2177 }, { "epoch": 0.2500574052812859, "grad_norm": 0.20660938322544098, "learning_rate": 1.6980754603254235e-05, "loss": 0.2428, "step": 2178 }, { "epoch": 0.2501722158438576, "grad_norm": 0.1915784329175949, "learning_rate": 1.6942707353208276e-05, "loss": 0.2349, "step": 2179 }, { "epoch": 0.2502870264064294, "grad_norm": 0.2049112319946289, "learning_rate": 1.6904691319394304e-05, "loss": 0.261, "step": 2180 }, { "epoch": 0.25040183696900115, "grad_norm": 0.2047334611415863, "learning_rate": 1.686670655328054e-05, "loss": 0.2447, "step": 2181 }, { "epoch": 0.2505166475315729, "grad_norm": 0.20869405567646027, "learning_rate": 1.6828753106292855e-05, "loss": 0.2696, "step": 2182 }, { "epoch": 0.25063145809414467, "grad_norm": 0.20649346709251404, "learning_rate": 1.67908310298147e-05, "loss": 0.2391, "step": 2183 }, { "epoch": 0.2507462686567164, "grad_norm": 0.21329057216644287, "learning_rate": 1.675294037518707e-05, "loss": 0.2623, "step": 2184 }, { "epoch": 0.2508610792192882, "grad_norm": 0.20865562558174133, "learning_rate": 1.671508119370843e-05, "loss": 0.2553, "step": 2185 }, { "epoch": 0.2509758897818599, "grad_norm": 0.23388494551181793, "learning_rate": 1.6677253536634612e-05, "loss": 0.2647, "step": 2186 }, { "epoch": 0.2510907003444317, "grad_norm": 0.2077063024044037, "learning_rate": 1.663945745517879e-05, "loss": 0.2268, "step": 2187 }, { "epoch": 0.25120551090700344, "grad_norm": 0.2043086141347885, "learning_rate": 1.6601693000511382e-05, "loss": 0.2439, "step": 2188 }, { "epoch": 0.2513203214695752, "grad_norm": 0.208144411444664, "learning_rate": 1.656396022375999e-05, "loss": 0.2513, "step": 2189 }, { "epoch": 0.25143513203214696, "grad_norm": 0.20578321814537048, "learning_rate": 1.6526259176009295e-05, "loss": 0.2442, "step": 2190 }, { "epoch": 0.2515499425947187, "grad_norm": 0.2082953304052353, "learning_rate": 1.648858990830108e-05, "loss": 0.2577, "step": 2191 }, { "epoch": 0.2516647531572905, "grad_norm": 0.20705674588680267, "learning_rate": 1.6450952471634058e-05, "loss": 0.2506, "step": 2192 }, { "epoch": 0.2517795637198622, "grad_norm": 0.20695850253105164, "learning_rate": 1.641334691696387e-05, "loss": 0.242, "step": 2193 }, { "epoch": 0.251894374282434, "grad_norm": 0.21438610553741455, "learning_rate": 1.6375773295202982e-05, "loss": 0.2623, "step": 2194 }, { "epoch": 0.25200918484500573, "grad_norm": 0.19849523901939392, "learning_rate": 1.633823165722065e-05, "loss": 0.2679, "step": 2195 }, { "epoch": 0.2521239954075775, "grad_norm": 0.20355848968029022, "learning_rate": 1.630072205384278e-05, "loss": 0.2494, "step": 2196 }, { "epoch": 0.25223880597014925, "grad_norm": 0.1978885382413864, "learning_rate": 1.626324453585195e-05, "loss": 0.2491, "step": 2197 }, { "epoch": 0.25235361653272104, "grad_norm": 1.2584017515182495, "learning_rate": 1.6225799153987297e-05, "loss": 0.2689, "step": 2198 }, { "epoch": 0.25246842709529277, "grad_norm": 0.21804337203502655, "learning_rate": 1.618838595894441e-05, "loss": 0.2667, "step": 2199 }, { "epoch": 0.2525832376578645, "grad_norm": 0.1926289051771164, "learning_rate": 1.6151005001375363e-05, "loss": 0.2489, "step": 2200 }, { "epoch": 0.2526980482204363, "grad_norm": 0.2095218449831009, "learning_rate": 1.6113656331888563e-05, "loss": 0.2446, "step": 2201 }, { "epoch": 0.252812858783008, "grad_norm": 0.2057516723871231, "learning_rate": 1.6076340001048657e-05, "loss": 0.2569, "step": 2202 }, { "epoch": 0.2529276693455798, "grad_norm": 0.1991659551858902, "learning_rate": 1.6039056059376572e-05, "loss": 0.2539, "step": 2203 }, { "epoch": 0.25304247990815154, "grad_norm": 0.19571810960769653, "learning_rate": 1.600180455734935e-05, "loss": 0.2449, "step": 2204 }, { "epoch": 0.25315729047072333, "grad_norm": 0.20508286356925964, "learning_rate": 1.5964585545400146e-05, "loss": 0.254, "step": 2205 }, { "epoch": 0.25327210103329506, "grad_norm": 0.18781785666942596, "learning_rate": 1.5927399073918065e-05, "loss": 0.2345, "step": 2206 }, { "epoch": 0.2533869115958668, "grad_norm": 0.20255830883979797, "learning_rate": 1.589024519324825e-05, "loss": 0.2487, "step": 2207 }, { "epoch": 0.2535017221584386, "grad_norm": 0.19473080337047577, "learning_rate": 1.585312395369164e-05, "loss": 0.2274, "step": 2208 }, { "epoch": 0.2536165327210103, "grad_norm": 0.19510534405708313, "learning_rate": 1.5816035405505007e-05, "loss": 0.236, "step": 2209 }, { "epoch": 0.2537313432835821, "grad_norm": 0.19794075191020966, "learning_rate": 1.5778979598900885e-05, "loss": 0.251, "step": 2210 }, { "epoch": 0.25384615384615383, "grad_norm": 0.20039841532707214, "learning_rate": 1.5741956584047478e-05, "loss": 0.2501, "step": 2211 }, { "epoch": 0.2539609644087256, "grad_norm": 0.20652689039707184, "learning_rate": 1.5704966411068542e-05, "loss": 0.2583, "step": 2212 }, { "epoch": 0.25407577497129735, "grad_norm": 0.21619105339050293, "learning_rate": 1.5668009130043418e-05, "loss": 0.2574, "step": 2213 }, { "epoch": 0.25419058553386914, "grad_norm": 0.1969800889492035, "learning_rate": 1.563108479100695e-05, "loss": 0.2513, "step": 2214 }, { "epoch": 0.25430539609644087, "grad_norm": 0.1963292956352234, "learning_rate": 1.55941934439493e-05, "loss": 0.2452, "step": 2215 }, { "epoch": 0.2544202066590126, "grad_norm": 0.20561347901821136, "learning_rate": 1.555733513881601e-05, "loss": 0.2424, "step": 2216 }, { "epoch": 0.2545350172215844, "grad_norm": 0.4288316071033478, "learning_rate": 1.55205099255079e-05, "loss": 0.2343, "step": 2217 }, { "epoch": 0.2546498277841561, "grad_norm": 0.1991819441318512, "learning_rate": 1.548371785388095e-05, "loss": 0.2534, "step": 2218 }, { "epoch": 0.2547646383467279, "grad_norm": 0.2005099505186081, "learning_rate": 1.54469589737463e-05, "loss": 0.2522, "step": 2219 }, { "epoch": 0.25487944890929964, "grad_norm": 0.21347767114639282, "learning_rate": 1.5410233334870143e-05, "loss": 0.2569, "step": 2220 }, { "epoch": 0.25499425947187143, "grad_norm": 0.19610808789730072, "learning_rate": 1.537354098697367e-05, "loss": 0.2379, "step": 2221 }, { "epoch": 0.25510907003444316, "grad_norm": 0.20846650004386902, "learning_rate": 1.533688197973301e-05, "loss": 0.2533, "step": 2222 }, { "epoch": 0.25522388059701495, "grad_norm": 0.208777517080307, "learning_rate": 1.530025636277914e-05, "loss": 0.2666, "step": 2223 }, { "epoch": 0.2553386911595867, "grad_norm": 0.19761130213737488, "learning_rate": 1.526366418569784e-05, "loss": 0.2725, "step": 2224 }, { "epoch": 0.2554535017221584, "grad_norm": 0.21184933185577393, "learning_rate": 1.5227105498029607e-05, "loss": 0.2602, "step": 2225 }, { "epoch": 0.2555683122847302, "grad_norm": 0.2107085883617401, "learning_rate": 1.5190580349269604e-05, "loss": 0.2511, "step": 2226 }, { "epoch": 0.25568312284730194, "grad_norm": 0.2159254103899002, "learning_rate": 1.515408878886759e-05, "loss": 0.2494, "step": 2227 }, { "epoch": 0.2557979334098737, "grad_norm": 0.20476049184799194, "learning_rate": 1.5117630866227848e-05, "loss": 0.2582, "step": 2228 }, { "epoch": 0.25591274397244546, "grad_norm": 0.19709748029708862, "learning_rate": 1.508120663070912e-05, "loss": 0.2435, "step": 2229 }, { "epoch": 0.25602755453501724, "grad_norm": 0.20635037124156952, "learning_rate": 1.5044816131624562e-05, "loss": 0.2523, "step": 2230 }, { "epoch": 0.256142365097589, "grad_norm": 0.19646242260932922, "learning_rate": 1.5008459418241601e-05, "loss": 0.2417, "step": 2231 }, { "epoch": 0.2562571756601607, "grad_norm": 0.21437597274780273, "learning_rate": 1.497213653978197e-05, "loss": 0.2438, "step": 2232 }, { "epoch": 0.2563719862227325, "grad_norm": 0.2058180719614029, "learning_rate": 1.4935847545421593e-05, "loss": 0.2464, "step": 2233 }, { "epoch": 0.2564867967853042, "grad_norm": 0.9084138870239258, "learning_rate": 1.4899592484290475e-05, "loss": 0.2586, "step": 2234 }, { "epoch": 0.256601607347876, "grad_norm": 0.1976976841688156, "learning_rate": 1.486337140547275e-05, "loss": 0.2478, "step": 2235 }, { "epoch": 0.25671641791044775, "grad_norm": 0.2082531452178955, "learning_rate": 1.482718435800651e-05, "loss": 0.2563, "step": 2236 }, { "epoch": 0.25683122847301953, "grad_norm": 0.20809870958328247, "learning_rate": 1.4791031390883741e-05, "loss": 0.2495, "step": 2237 }, { "epoch": 0.25694603903559127, "grad_norm": 0.21111494302749634, "learning_rate": 1.4754912553050335e-05, "loss": 0.242, "step": 2238 }, { "epoch": 0.25706084959816305, "grad_norm": 0.20854097604751587, "learning_rate": 1.4718827893405964e-05, "loss": 0.2498, "step": 2239 }, { "epoch": 0.2571756601607348, "grad_norm": 0.1988600641489029, "learning_rate": 1.468277746080403e-05, "loss": 0.2536, "step": 2240 }, { "epoch": 0.2572904707233065, "grad_norm": 0.20106631517410278, "learning_rate": 1.4646761304051587e-05, "loss": 0.2522, "step": 2241 }, { "epoch": 0.2574052812858783, "grad_norm": 0.20257671177387238, "learning_rate": 1.4610779471909302e-05, "loss": 0.2566, "step": 2242 }, { "epoch": 0.25752009184845004, "grad_norm": 0.2198648452758789, "learning_rate": 1.4574832013091342e-05, "loss": 0.2425, "step": 2243 }, { "epoch": 0.2576349024110218, "grad_norm": 0.18812988698482513, "learning_rate": 1.4538918976265364e-05, "loss": 0.2357, "step": 2244 }, { "epoch": 0.25774971297359356, "grad_norm": 0.20371440052986145, "learning_rate": 1.4503040410052412e-05, "loss": 0.2559, "step": 2245 }, { "epoch": 0.25786452353616535, "grad_norm": 0.2029658406972885, "learning_rate": 1.4467196363026883e-05, "loss": 0.2395, "step": 2246 }, { "epoch": 0.2579793340987371, "grad_norm": 0.20840534567832947, "learning_rate": 1.4431386883716374e-05, "loss": 0.2407, "step": 2247 }, { "epoch": 0.25809414466130887, "grad_norm": 0.19651900231838226, "learning_rate": 1.4395612020601775e-05, "loss": 0.2654, "step": 2248 }, { "epoch": 0.2582089552238806, "grad_norm": 0.19646702706813812, "learning_rate": 1.4359871822117062e-05, "loss": 0.2562, "step": 2249 }, { "epoch": 0.25832376578645233, "grad_norm": 0.21937638521194458, "learning_rate": 1.4324166336649258e-05, "loss": 0.2563, "step": 2250 }, { "epoch": 0.2584385763490241, "grad_norm": 0.20771096646785736, "learning_rate": 1.4288495612538427e-05, "loss": 0.2504, "step": 2251 }, { "epoch": 0.25855338691159585, "grad_norm": 0.19910936057567596, "learning_rate": 1.4252859698077575e-05, "loss": 0.2563, "step": 2252 }, { "epoch": 0.25866819747416764, "grad_norm": 0.19585715234279633, "learning_rate": 1.4217258641512532e-05, "loss": 0.2574, "step": 2253 }, { "epoch": 0.25878300803673937, "grad_norm": 0.19926783442497253, "learning_rate": 1.4181692491041972e-05, "loss": 0.2547, "step": 2254 }, { "epoch": 0.25889781859931116, "grad_norm": 0.19942638278007507, "learning_rate": 1.414616129481735e-05, "loss": 0.257, "step": 2255 }, { "epoch": 0.2590126291618829, "grad_norm": 0.20065665245056152, "learning_rate": 1.4110665100942708e-05, "loss": 0.2385, "step": 2256 }, { "epoch": 0.2591274397244546, "grad_norm": 0.20078839361667633, "learning_rate": 1.4075203957474766e-05, "loss": 0.2549, "step": 2257 }, { "epoch": 0.2592422502870264, "grad_norm": 0.2064119279384613, "learning_rate": 1.4039777912422782e-05, "loss": 0.2506, "step": 2258 }, { "epoch": 0.25935706084959814, "grad_norm": 0.20424555242061615, "learning_rate": 1.4004387013748467e-05, "loss": 0.2516, "step": 2259 }, { "epoch": 0.25947187141216993, "grad_norm": 0.20695561170578003, "learning_rate": 1.3969031309365968e-05, "loss": 0.25, "step": 2260 }, { "epoch": 0.25958668197474166, "grad_norm": 0.19544735550880432, "learning_rate": 1.3933710847141795e-05, "loss": 0.2664, "step": 2261 }, { "epoch": 0.25970149253731345, "grad_norm": 0.21040570735931396, "learning_rate": 1.3898425674894731e-05, "loss": 0.2786, "step": 2262 }, { "epoch": 0.2598163030998852, "grad_norm": 0.1996784657239914, "learning_rate": 1.3863175840395781e-05, "loss": 0.242, "step": 2263 }, { "epoch": 0.25993111366245697, "grad_norm": 0.25493523478507996, "learning_rate": 1.382796139136812e-05, "loss": 0.2368, "step": 2264 }, { "epoch": 0.2600459242250287, "grad_norm": 0.1965230405330658, "learning_rate": 1.3792782375487005e-05, "loss": 0.2569, "step": 2265 }, { "epoch": 0.26016073478760043, "grad_norm": 0.22014400362968445, "learning_rate": 1.3757638840379714e-05, "loss": 0.2531, "step": 2266 }, { "epoch": 0.2602755453501722, "grad_norm": 0.20458880066871643, "learning_rate": 1.3722530833625505e-05, "loss": 0.256, "step": 2267 }, { "epoch": 0.26039035591274395, "grad_norm": 0.22061578929424286, "learning_rate": 1.3687458402755534e-05, "loss": 0.2605, "step": 2268 }, { "epoch": 0.26050516647531574, "grad_norm": 0.20829658210277557, "learning_rate": 1.3652421595252779e-05, "loss": 0.27, "step": 2269 }, { "epoch": 0.2606199770378875, "grad_norm": 0.19437745213508606, "learning_rate": 1.361742045855201e-05, "loss": 0.2509, "step": 2270 }, { "epoch": 0.26073478760045926, "grad_norm": 0.1937023252248764, "learning_rate": 1.3582455040039699e-05, "loss": 0.2561, "step": 2271 }, { "epoch": 0.260849598163031, "grad_norm": 0.1931077539920807, "learning_rate": 1.3547525387053933e-05, "loss": 0.24, "step": 2272 }, { "epoch": 0.2609644087256028, "grad_norm": 0.2004092037677765, "learning_rate": 1.3512631546884406e-05, "loss": 0.2361, "step": 2273 }, { "epoch": 0.2610792192881745, "grad_norm": 0.20046071708202362, "learning_rate": 1.3477773566772321e-05, "loss": 0.2402, "step": 2274 }, { "epoch": 0.26119402985074625, "grad_norm": 0.20349793136119843, "learning_rate": 1.3442951493910337e-05, "loss": 0.2565, "step": 2275 }, { "epoch": 0.26130884041331803, "grad_norm": 0.19835014641284943, "learning_rate": 1.3408165375442486e-05, "loss": 0.2505, "step": 2276 }, { "epoch": 0.26142365097588977, "grad_norm": 0.19148039817810059, "learning_rate": 1.3373415258464144e-05, "loss": 0.2409, "step": 2277 }, { "epoch": 0.26153846153846155, "grad_norm": 0.1995910108089447, "learning_rate": 1.3338701190021905e-05, "loss": 0.2324, "step": 2278 }, { "epoch": 0.2616532721010333, "grad_norm": 0.21203410625457764, "learning_rate": 1.3304023217113606e-05, "loss": 0.2695, "step": 2279 }, { "epoch": 0.2617680826636051, "grad_norm": 0.20853792130947113, "learning_rate": 1.326938138668819e-05, "loss": 0.2708, "step": 2280 }, { "epoch": 0.2618828932261768, "grad_norm": 0.22627653181552887, "learning_rate": 1.3234775745645684e-05, "loss": 0.2543, "step": 2281 }, { "epoch": 0.26199770378874854, "grad_norm": 0.21279744803905487, "learning_rate": 1.3200206340837074e-05, "loss": 0.2615, "step": 2282 }, { "epoch": 0.2621125143513203, "grad_norm": 0.20223018527030945, "learning_rate": 1.3165673219064368e-05, "loss": 0.2575, "step": 2283 }, { "epoch": 0.26222732491389206, "grad_norm": 0.19632381200790405, "learning_rate": 1.3131176427080399e-05, "loss": 0.2146, "step": 2284 }, { "epoch": 0.26234213547646384, "grad_norm": 0.19958281517028809, "learning_rate": 1.30967160115888e-05, "loss": 0.2397, "step": 2285 }, { "epoch": 0.2624569460390356, "grad_norm": 0.19664008915424347, "learning_rate": 1.3062292019243987e-05, "loss": 0.2458, "step": 2286 }, { "epoch": 0.26257175660160736, "grad_norm": 0.21329550445079803, "learning_rate": 1.3027904496651077e-05, "loss": 0.2557, "step": 2287 }, { "epoch": 0.2626865671641791, "grad_norm": 0.18880535662174225, "learning_rate": 1.299355349036576e-05, "loss": 0.2407, "step": 2288 }, { "epoch": 0.2628013777267509, "grad_norm": 0.19786784052848816, "learning_rate": 1.2959239046894317e-05, "loss": 0.2485, "step": 2289 }, { "epoch": 0.2629161882893226, "grad_norm": 0.20476093888282776, "learning_rate": 1.2924961212693577e-05, "loss": 0.2631, "step": 2290 }, { "epoch": 0.26303099885189435, "grad_norm": 0.2174743413925171, "learning_rate": 1.2890720034170712e-05, "loss": 0.2619, "step": 2291 }, { "epoch": 0.26314580941446614, "grad_norm": 0.208529993891716, "learning_rate": 1.2856515557683334e-05, "loss": 0.2532, "step": 2292 }, { "epoch": 0.26326061997703787, "grad_norm": 0.21110981702804565, "learning_rate": 1.282234782953935e-05, "loss": 0.2722, "step": 2293 }, { "epoch": 0.26337543053960966, "grad_norm": 0.2008129060268402, "learning_rate": 1.2788216895996897e-05, "loss": 0.2568, "step": 2294 }, { "epoch": 0.2634902411021814, "grad_norm": 0.21321310102939606, "learning_rate": 1.2754122803264313e-05, "loss": 0.2657, "step": 2295 }, { "epoch": 0.2636050516647532, "grad_norm": 0.413690984249115, "learning_rate": 1.2720065597500066e-05, "loss": 0.2795, "step": 2296 }, { "epoch": 0.2637198622273249, "grad_norm": 0.19694431126117706, "learning_rate": 1.268604532481267e-05, "loss": 0.2496, "step": 2297 }, { "epoch": 0.2638346727898967, "grad_norm": 0.2187911719083786, "learning_rate": 1.265206203126065e-05, "loss": 0.2596, "step": 2298 }, { "epoch": 0.26394948335246843, "grad_norm": 0.198244109749794, "learning_rate": 1.2618115762852451e-05, "loss": 0.2391, "step": 2299 }, { "epoch": 0.26406429391504016, "grad_norm": 0.20163051784038544, "learning_rate": 1.258420656554642e-05, "loss": 0.2501, "step": 2300 }, { "epoch": 0.26417910447761195, "grad_norm": 0.19722776114940643, "learning_rate": 1.2550334485250661e-05, "loss": 0.2486, "step": 2301 }, { "epoch": 0.2642939150401837, "grad_norm": 0.21926645934581757, "learning_rate": 1.2516499567823087e-05, "loss": 0.2745, "step": 2302 }, { "epoch": 0.26440872560275547, "grad_norm": 0.20079495012760162, "learning_rate": 1.2482701859071255e-05, "loss": 0.2381, "step": 2303 }, { "epoch": 0.2645235361653272, "grad_norm": 0.1908002495765686, "learning_rate": 1.2448941404752377e-05, "loss": 0.2328, "step": 2304 }, { "epoch": 0.264638346727899, "grad_norm": 0.1934284120798111, "learning_rate": 1.2415218250573208e-05, "loss": 0.2346, "step": 2305 }, { "epoch": 0.2647531572904707, "grad_norm": 0.2058946192264557, "learning_rate": 1.2381532442190026e-05, "loss": 0.2643, "step": 2306 }, { "epoch": 0.2648679678530425, "grad_norm": 0.21381627023220062, "learning_rate": 1.23478840252085e-05, "loss": 0.2643, "step": 2307 }, { "epoch": 0.26498277841561424, "grad_norm": 0.19387322664260864, "learning_rate": 1.2314273045183734e-05, "loss": 0.2505, "step": 2308 }, { "epoch": 0.26509758897818597, "grad_norm": 0.20377394556999207, "learning_rate": 1.2280699547620114e-05, "loss": 0.2588, "step": 2309 }, { "epoch": 0.26521239954075776, "grad_norm": 0.2024417519569397, "learning_rate": 1.2247163577971289e-05, "loss": 0.2718, "step": 2310 }, { "epoch": 0.2653272101033295, "grad_norm": 0.2079058289527893, "learning_rate": 1.2213665181640106e-05, "loss": 0.2521, "step": 2311 }, { "epoch": 0.2654420206659013, "grad_norm": 1.4321072101593018, "learning_rate": 1.2180204403978549e-05, "loss": 0.267, "step": 2312 }, { "epoch": 0.265556831228473, "grad_norm": 0.2135702669620514, "learning_rate": 1.214678129028763e-05, "loss": 0.2551, "step": 2313 }, { "epoch": 0.2656716417910448, "grad_norm": 0.1963745653629303, "learning_rate": 1.2113395885817423e-05, "loss": 0.2504, "step": 2314 }, { "epoch": 0.26578645235361653, "grad_norm": 0.20112532377243042, "learning_rate": 1.2080048235766917e-05, "loss": 0.2504, "step": 2315 }, { "epoch": 0.26590126291618826, "grad_norm": 0.19519901275634766, "learning_rate": 1.2046738385283998e-05, "loss": 0.245, "step": 2316 }, { "epoch": 0.26601607347876005, "grad_norm": 0.20863103866577148, "learning_rate": 1.201346637946538e-05, "loss": 0.2681, "step": 2317 }, { "epoch": 0.2661308840413318, "grad_norm": 0.19267426431179047, "learning_rate": 1.1980232263356543e-05, "loss": 0.2478, "step": 2318 }, { "epoch": 0.26624569460390357, "grad_norm": 0.20980094373226166, "learning_rate": 1.1947036081951647e-05, "loss": 0.2623, "step": 2319 }, { "epoch": 0.2663605051664753, "grad_norm": 0.1869364231824875, "learning_rate": 1.1913877880193504e-05, "loss": 0.2274, "step": 2320 }, { "epoch": 0.2664753157290471, "grad_norm": 0.21062302589416504, "learning_rate": 1.1880757702973531e-05, "loss": 0.2634, "step": 2321 }, { "epoch": 0.2665901262916188, "grad_norm": 0.18122752010822296, "learning_rate": 1.1847675595131656e-05, "loss": 0.2134, "step": 2322 }, { "epoch": 0.2667049368541906, "grad_norm": 0.19397689402103424, "learning_rate": 1.1814631601456212e-05, "loss": 0.2549, "step": 2323 }, { "epoch": 0.26681974741676234, "grad_norm": 0.19124677777290344, "learning_rate": 1.178162576668402e-05, "loss": 0.2362, "step": 2324 }, { "epoch": 0.2669345579793341, "grad_norm": 0.2010711282491684, "learning_rate": 1.1748658135500191e-05, "loss": 0.2563, "step": 2325 }, { "epoch": 0.26704936854190586, "grad_norm": 0.25416818261146545, "learning_rate": 1.1715728752538103e-05, "loss": 0.26, "step": 2326 }, { "epoch": 0.2671641791044776, "grad_norm": 0.18476533889770508, "learning_rate": 1.1682837662379374e-05, "loss": 0.2355, "step": 2327 }, { "epoch": 0.2672789896670494, "grad_norm": 0.19212590157985687, "learning_rate": 1.1649984909553784e-05, "loss": 0.2441, "step": 2328 }, { "epoch": 0.2673938002296211, "grad_norm": 0.19766515493392944, "learning_rate": 1.1617170538539173e-05, "loss": 0.2397, "step": 2329 }, { "epoch": 0.2675086107921929, "grad_norm": 0.2830692529678345, "learning_rate": 1.1584394593761448e-05, "loss": 0.2504, "step": 2330 }, { "epoch": 0.26762342135476463, "grad_norm": 0.2009068727493286, "learning_rate": 1.1551657119594517e-05, "loss": 0.2627, "step": 2331 }, { "epoch": 0.2677382319173364, "grad_norm": 0.19522349536418915, "learning_rate": 1.1518958160360145e-05, "loss": 0.2368, "step": 2332 }, { "epoch": 0.26785304247990815, "grad_norm": 0.1934908926486969, "learning_rate": 1.148629776032799e-05, "loss": 0.2477, "step": 2333 }, { "epoch": 0.2679678530424799, "grad_norm": 0.18579351902008057, "learning_rate": 1.1453675963715503e-05, "loss": 0.2296, "step": 2334 }, { "epoch": 0.2680826636050517, "grad_norm": 0.21738775074481964, "learning_rate": 1.1421092814687876e-05, "loss": 0.2407, "step": 2335 }, { "epoch": 0.2681974741676234, "grad_norm": 0.2530551850795746, "learning_rate": 1.1388548357357946e-05, "loss": 0.2535, "step": 2336 }, { "epoch": 0.2683122847301952, "grad_norm": 0.18610554933547974, "learning_rate": 1.1356042635786206e-05, "loss": 0.2392, "step": 2337 }, { "epoch": 0.2684270952927669, "grad_norm": 0.21244366466999054, "learning_rate": 1.1323575693980691e-05, "loss": 0.2665, "step": 2338 }, { "epoch": 0.2685419058553387, "grad_norm": 0.20640131831169128, "learning_rate": 1.1291147575896933e-05, "loss": 0.2331, "step": 2339 }, { "epoch": 0.26865671641791045, "grad_norm": 0.21012625098228455, "learning_rate": 1.1258758325437902e-05, "loss": 0.2753, "step": 2340 }, { "epoch": 0.2687715269804822, "grad_norm": 0.1983303725719452, "learning_rate": 1.1226407986453963e-05, "loss": 0.2651, "step": 2341 }, { "epoch": 0.26888633754305397, "grad_norm": 0.19089290499687195, "learning_rate": 1.119409660274276e-05, "loss": 0.2547, "step": 2342 }, { "epoch": 0.2690011481056257, "grad_norm": 0.2029133141040802, "learning_rate": 1.1161824218049233e-05, "loss": 0.2411, "step": 2343 }, { "epoch": 0.2691159586681975, "grad_norm": 0.20336458086967468, "learning_rate": 1.1129590876065515e-05, "loss": 0.2421, "step": 2344 }, { "epoch": 0.2692307692307692, "grad_norm": 0.188243567943573, "learning_rate": 1.1097396620430879e-05, "loss": 0.2487, "step": 2345 }, { "epoch": 0.269345579793341, "grad_norm": 0.1854294240474701, "learning_rate": 1.106524149473168e-05, "loss": 0.2332, "step": 2346 }, { "epoch": 0.26946039035591274, "grad_norm": 0.19422656297683716, "learning_rate": 1.103312554250131e-05, "loss": 0.228, "step": 2347 }, { "epoch": 0.2695752009184845, "grad_norm": 0.19768263399600983, "learning_rate": 1.1001048807220088e-05, "loss": 0.2631, "step": 2348 }, { "epoch": 0.26969001148105626, "grad_norm": 0.22463013231754303, "learning_rate": 1.0969011332315272e-05, "loss": 0.2843, "step": 2349 }, { "epoch": 0.269804822043628, "grad_norm": 0.1972094178199768, "learning_rate": 1.0937013161160967e-05, "loss": 0.2421, "step": 2350 }, { "epoch": 0.2699196326061998, "grad_norm": 0.20677612721920013, "learning_rate": 1.0905054337078051e-05, "loss": 0.2575, "step": 2351 }, { "epoch": 0.2700344431687715, "grad_norm": 0.2138136923313141, "learning_rate": 1.0873134903334149e-05, "loss": 0.2588, "step": 2352 }, { "epoch": 0.2701492537313433, "grad_norm": 0.20407184958457947, "learning_rate": 1.0841254903143547e-05, "loss": 0.2551, "step": 2353 }, { "epoch": 0.27026406429391503, "grad_norm": 0.904679536819458, "learning_rate": 1.080941437966713e-05, "loss": 0.2982, "step": 2354 }, { "epoch": 0.2703788748564868, "grad_norm": 0.19781924784183502, "learning_rate": 1.0777613376012358e-05, "loss": 0.2467, "step": 2355 }, { "epoch": 0.27049368541905855, "grad_norm": 1.5132635831832886, "learning_rate": 1.0745851935233183e-05, "loss": 0.2527, "step": 2356 }, { "epoch": 0.27060849598163034, "grad_norm": 0.20310653746128082, "learning_rate": 1.0714130100329992e-05, "loss": 0.2385, "step": 2357 }, { "epoch": 0.27072330654420207, "grad_norm": 0.20085614919662476, "learning_rate": 1.0682447914249545e-05, "loss": 0.2557, "step": 2358 }, { "epoch": 0.2708381171067738, "grad_norm": 4.3380961418151855, "learning_rate": 1.0650805419884942e-05, "loss": 0.2684, "step": 2359 }, { "epoch": 0.2709529276693456, "grad_norm": 0.20743142068386078, "learning_rate": 1.0619202660075536e-05, "loss": 0.2524, "step": 2360 }, { "epoch": 0.2710677382319173, "grad_norm": 0.1958545446395874, "learning_rate": 1.0587639677606857e-05, "loss": 0.2434, "step": 2361 }, { "epoch": 0.2711825487944891, "grad_norm": 0.20147891342639923, "learning_rate": 1.0556116515210629e-05, "loss": 0.2608, "step": 2362 }, { "epoch": 0.27129735935706084, "grad_norm": 1.206524133682251, "learning_rate": 1.052463321556465e-05, "loss": 0.2807, "step": 2363 }, { "epoch": 0.27141216991963263, "grad_norm": 0.1939450204372406, "learning_rate": 1.0493189821292708e-05, "loss": 0.2545, "step": 2364 }, { "epoch": 0.27152698048220436, "grad_norm": 0.19798894226551056, "learning_rate": 1.0461786374964644e-05, "loss": 0.2527, "step": 2365 }, { "epoch": 0.2716417910447761, "grad_norm": 0.19498437643051147, "learning_rate": 1.0430422919096164e-05, "loss": 0.244, "step": 2366 }, { "epoch": 0.2717566016073479, "grad_norm": 0.2843725383281708, "learning_rate": 1.0399099496148821e-05, "loss": 0.2293, "step": 2367 }, { "epoch": 0.2718714121699196, "grad_norm": 0.19077357649803162, "learning_rate": 1.0367816148530002e-05, "loss": 0.2315, "step": 2368 }, { "epoch": 0.2719862227324914, "grad_norm": 0.2053355872631073, "learning_rate": 1.0336572918592829e-05, "loss": 0.2605, "step": 2369 }, { "epoch": 0.27210103329506313, "grad_norm": 0.19677236676216125, "learning_rate": 1.0305369848636096e-05, "loss": 0.245, "step": 2370 }, { "epoch": 0.2722158438576349, "grad_norm": 0.18368124961853027, "learning_rate": 1.0274206980904226e-05, "loss": 0.2294, "step": 2371 }, { "epoch": 0.27233065442020665, "grad_norm": 0.19621294736862183, "learning_rate": 1.0243084357587266e-05, "loss": 0.2376, "step": 2372 }, { "epoch": 0.27244546498277844, "grad_norm": 0.2061464488506317, "learning_rate": 1.0212002020820697e-05, "loss": 0.2353, "step": 2373 }, { "epoch": 0.2725602755453502, "grad_norm": 0.2042684704065323, "learning_rate": 1.0180960012685515e-05, "loss": 0.2614, "step": 2374 }, { "epoch": 0.2726750861079219, "grad_norm": 0.1909642070531845, "learning_rate": 1.014995837520809e-05, "loss": 0.2416, "step": 2375 }, { "epoch": 0.2727898966704937, "grad_norm": 0.1935507208108902, "learning_rate": 1.0118997150360169e-05, "loss": 0.263, "step": 2376 }, { "epoch": 0.2729047072330654, "grad_norm": 0.30353328585624695, "learning_rate": 1.0088076380058732e-05, "loss": 0.2527, "step": 2377 }, { "epoch": 0.2730195177956372, "grad_norm": 0.1971125304698944, "learning_rate": 1.0057196106166032e-05, "loss": 0.2502, "step": 2378 }, { "epoch": 0.27313432835820894, "grad_norm": 0.187750443816185, "learning_rate": 1.0026356370489484e-05, "loss": 0.247, "step": 2379 }, { "epoch": 0.27324913892078073, "grad_norm": 0.2042965292930603, "learning_rate": 9.995557214781618e-06, "loss": 0.2761, "step": 2380 }, { "epoch": 0.27336394948335246, "grad_norm": 0.1873829960823059, "learning_rate": 9.964798680740033e-06, "loss": 0.2357, "step": 2381 }, { "epoch": 0.27347876004592425, "grad_norm": 0.20862402021884918, "learning_rate": 9.93408081000733e-06, "loss": 0.2713, "step": 2382 }, { "epoch": 0.273593570608496, "grad_norm": 0.2334602028131485, "learning_rate": 9.90340364417103e-06, "loss": 0.2628, "step": 2383 }, { "epoch": 0.2737083811710677, "grad_norm": 0.1949683278799057, "learning_rate": 9.872767224763589e-06, "loss": 0.2561, "step": 2384 }, { "epoch": 0.2738231917336395, "grad_norm": 0.17971479892730713, "learning_rate": 9.842171593262267e-06, "loss": 0.2244, "step": 2385 }, { "epoch": 0.27393800229621124, "grad_norm": 0.3006226122379303, "learning_rate": 9.81161679108912e-06, "loss": 0.2383, "step": 2386 }, { "epoch": 0.274052812858783, "grad_norm": 0.19475826621055603, "learning_rate": 9.781102859610923e-06, "loss": 0.2347, "step": 2387 }, { "epoch": 0.27416762342135476, "grad_norm": 0.19181475043296814, "learning_rate": 9.750629840139121e-06, "loss": 0.2311, "step": 2388 }, { "epoch": 0.27428243398392654, "grad_norm": 0.19583167135715485, "learning_rate": 9.720197773929749e-06, "loss": 0.2372, "step": 2389 }, { "epoch": 0.2743972445464983, "grad_norm": 0.2894524931907654, "learning_rate": 9.68980670218342e-06, "loss": 0.2559, "step": 2390 }, { "epoch": 0.27451205510907, "grad_norm": 0.19555266201496124, "learning_rate": 9.659456666045247e-06, "loss": 0.263, "step": 2391 }, { "epoch": 0.2746268656716418, "grad_norm": 0.19733336567878723, "learning_rate": 9.629147706604769e-06, "loss": 0.2439, "step": 2392 }, { "epoch": 0.2747416762342135, "grad_norm": 0.39099061489105225, "learning_rate": 9.59887986489593e-06, "loss": 0.2576, "step": 2393 }, { "epoch": 0.2748564867967853, "grad_norm": 0.1871742308139801, "learning_rate": 9.568653181897e-06, "loss": 0.226, "step": 2394 }, { "epoch": 0.27497129735935705, "grad_norm": 0.20047034323215485, "learning_rate": 9.538467698530538e-06, "loss": 0.2684, "step": 2395 }, { "epoch": 0.27508610792192884, "grad_norm": 0.2007465362548828, "learning_rate": 9.508323455663286e-06, "loss": 0.2674, "step": 2396 }, { "epoch": 0.27520091848450057, "grad_norm": 0.19155146181583405, "learning_rate": 9.478220494106197e-06, "loss": 0.2612, "step": 2397 }, { "epoch": 0.27531572904707236, "grad_norm": 0.20328858494758606, "learning_rate": 9.448158854614325e-06, "loss": 0.2755, "step": 2398 }, { "epoch": 0.2754305396096441, "grad_norm": 0.19650639593601227, "learning_rate": 9.418138577886737e-06, "loss": 0.2538, "step": 2399 }, { "epoch": 0.2755453501722158, "grad_norm": 0.19174811244010925, "learning_rate": 9.388159704566577e-06, "loss": 0.2396, "step": 2400 }, { "epoch": 0.2756601607347876, "grad_norm": 0.18490532040596008, "learning_rate": 9.358222275240884e-06, "loss": 0.2335, "step": 2401 }, { "epoch": 0.27577497129735934, "grad_norm": 0.19579729437828064, "learning_rate": 9.328326330440585e-06, "loss": 0.2552, "step": 2402 }, { "epoch": 0.2758897818599311, "grad_norm": 0.18353700637817383, "learning_rate": 9.298471910640456e-06, "loss": 0.2248, "step": 2403 }, { "epoch": 0.27600459242250286, "grad_norm": 0.20709817111492157, "learning_rate": 9.268659056259076e-06, "loss": 0.2325, "step": 2404 }, { "epoch": 0.27611940298507465, "grad_norm": 0.19576938450336456, "learning_rate": 9.2388878076587e-06, "loss": 0.2574, "step": 2405 }, { "epoch": 0.2762342135476464, "grad_norm": 0.19348037242889404, "learning_rate": 9.209158205145283e-06, "loss": 0.2556, "step": 2406 }, { "epoch": 0.27634902411021817, "grad_norm": 3.0169143676757812, "learning_rate": 9.179470288968435e-06, "loss": 0.2757, "step": 2407 }, { "epoch": 0.2764638346727899, "grad_norm": 0.23013056814670563, "learning_rate": 9.149824099321255e-06, "loss": 0.2545, "step": 2408 }, { "epoch": 0.27657864523536163, "grad_norm": 0.2039015293121338, "learning_rate": 9.120219676340399e-06, "loss": 0.248, "step": 2409 }, { "epoch": 0.2766934557979334, "grad_norm": 0.22437313199043274, "learning_rate": 9.09065706010596e-06, "loss": 0.2638, "step": 2410 }, { "epoch": 0.27680826636050515, "grad_norm": 0.19280332326889038, "learning_rate": 9.061136290641448e-06, "loss": 0.2501, "step": 2411 }, { "epoch": 0.27692307692307694, "grad_norm": 0.18707957863807678, "learning_rate": 9.031657407913687e-06, "loss": 0.2292, "step": 2412 }, { "epoch": 0.27703788748564867, "grad_norm": 0.17992828786373138, "learning_rate": 9.002220451832819e-06, "loss": 0.2324, "step": 2413 }, { "epoch": 0.27715269804822046, "grad_norm": 0.22309572994709015, "learning_rate": 8.972825462252222e-06, "loss": 0.2625, "step": 2414 }, { "epoch": 0.2772675086107922, "grad_norm": 0.20081090927124023, "learning_rate": 8.943472478968438e-06, "loss": 0.2459, "step": 2415 }, { "epoch": 0.2773823191733639, "grad_norm": 0.20161473751068115, "learning_rate": 8.914161541721165e-06, "loss": 0.2394, "step": 2416 }, { "epoch": 0.2774971297359357, "grad_norm": 1.6374458074569702, "learning_rate": 8.884892690193166e-06, "loss": 0.2447, "step": 2417 }, { "epoch": 0.27761194029850744, "grad_norm": 0.19602170586585999, "learning_rate": 8.855665964010205e-06, "loss": 0.24, "step": 2418 }, { "epoch": 0.27772675086107923, "grad_norm": 0.19495603442192078, "learning_rate": 8.826481402741028e-06, "loss": 0.2407, "step": 2419 }, { "epoch": 0.27784156142365096, "grad_norm": 0.19426853954792023, "learning_rate": 8.797339045897342e-06, "loss": 0.2413, "step": 2420 }, { "epoch": 0.27795637198622275, "grad_norm": 0.1982569694519043, "learning_rate": 8.768238932933632e-06, "loss": 0.2517, "step": 2421 }, { "epoch": 0.2780711825487945, "grad_norm": 0.21523986756801605, "learning_rate": 8.739181103247247e-06, "loss": 0.2884, "step": 2422 }, { "epoch": 0.27818599311136627, "grad_norm": 0.19510294497013092, "learning_rate": 8.710165596178291e-06, "loss": 0.2456, "step": 2423 }, { "epoch": 0.278300803673938, "grad_norm": 0.1912461221218109, "learning_rate": 8.68119245100953e-06, "loss": 0.2443, "step": 2424 }, { "epoch": 0.27841561423650973, "grad_norm": 0.1864234358072281, "learning_rate": 8.652261706966412e-06, "loss": 0.2305, "step": 2425 }, { "epoch": 0.2785304247990815, "grad_norm": 0.21625946462154388, "learning_rate": 8.623373403216972e-06, "loss": 0.2554, "step": 2426 }, { "epoch": 0.27864523536165325, "grad_norm": 0.19971448183059692, "learning_rate": 8.59452757887179e-06, "loss": 0.2586, "step": 2427 }, { "epoch": 0.27876004592422504, "grad_norm": 0.19653300940990448, "learning_rate": 8.565724272983922e-06, "loss": 0.2443, "step": 2428 }, { "epoch": 0.2788748564867968, "grad_norm": 0.32569456100463867, "learning_rate": 8.536963524548887e-06, "loss": 0.2788, "step": 2429 }, { "epoch": 0.27898966704936856, "grad_norm": 0.19611451029777527, "learning_rate": 8.508245372504547e-06, "loss": 0.2493, "step": 2430 }, { "epoch": 0.2791044776119403, "grad_norm": 0.19063369929790497, "learning_rate": 8.479569855731125e-06, "loss": 0.2585, "step": 2431 }, { "epoch": 0.2792192881745121, "grad_norm": 0.18836039304733276, "learning_rate": 8.450937013051118e-06, "loss": 0.2383, "step": 2432 }, { "epoch": 0.2793340987370838, "grad_norm": 0.19237014651298523, "learning_rate": 8.42234688322924e-06, "loss": 0.2534, "step": 2433 }, { "epoch": 0.27944890929965555, "grad_norm": 0.19855153560638428, "learning_rate": 8.393799504972384e-06, "loss": 0.2615, "step": 2434 }, { "epoch": 0.27956371986222733, "grad_norm": 0.18614575266838074, "learning_rate": 8.365294916929564e-06, "loss": 0.2441, "step": 2435 }, { "epoch": 0.27967853042479907, "grad_norm": 0.18990978598594666, "learning_rate": 8.336833157691871e-06, "loss": 0.2456, "step": 2436 }, { "epoch": 0.27979334098737085, "grad_norm": 0.19129794836044312, "learning_rate": 8.308414265792378e-06, "loss": 0.2467, "step": 2437 }, { "epoch": 0.2799081515499426, "grad_norm": 0.19379858672618866, "learning_rate": 8.280038279706155e-06, "loss": 0.2286, "step": 2438 }, { "epoch": 0.2800229621125144, "grad_norm": 0.18408910930156708, "learning_rate": 8.25170523785019e-06, "loss": 0.2222, "step": 2439 }, { "epoch": 0.2801377726750861, "grad_norm": 0.2116410881280899, "learning_rate": 8.22341517858327e-06, "loss": 0.2329, "step": 2440 }, { "epoch": 0.28025258323765784, "grad_norm": 0.19038823246955872, "learning_rate": 8.195168140206084e-06, "loss": 0.2417, "step": 2441 }, { "epoch": 0.2803673938002296, "grad_norm": 0.19268962740898132, "learning_rate": 8.16696416096102e-06, "loss": 0.2464, "step": 2442 }, { "epoch": 0.28048220436280136, "grad_norm": 0.1915421187877655, "learning_rate": 8.13880327903215e-06, "loss": 0.2492, "step": 2443 }, { "epoch": 0.28059701492537314, "grad_norm": 0.19374746084213257, "learning_rate": 8.110685532545246e-06, "loss": 0.2451, "step": 2444 }, { "epoch": 0.2807118254879449, "grad_norm": 0.19418975710868835, "learning_rate": 8.082610959567656e-06, "loss": 0.2585, "step": 2445 }, { "epoch": 0.28082663605051666, "grad_norm": 0.1955515593290329, "learning_rate": 8.054579598108296e-06, "loss": 0.2441, "step": 2446 }, { "epoch": 0.2809414466130884, "grad_norm": 0.18580861389636993, "learning_rate": 8.02659148611753e-06, "loss": 0.2343, "step": 2447 }, { "epoch": 0.2810562571756602, "grad_norm": 0.18861593306064606, "learning_rate": 7.99864666148725e-06, "loss": 0.2471, "step": 2448 }, { "epoch": 0.2811710677382319, "grad_norm": 0.19754278659820557, "learning_rate": 7.970745162050665e-06, "loss": 0.2641, "step": 2449 }, { "epoch": 0.28128587830080365, "grad_norm": 0.19685518741607666, "learning_rate": 7.942887025582373e-06, "loss": 0.2464, "step": 2450 }, { "epoch": 0.28140068886337544, "grad_norm": 0.5258341431617737, "learning_rate": 7.915072289798247e-06, "loss": 0.2465, "step": 2451 }, { "epoch": 0.28151549942594717, "grad_norm": 0.19329696893692017, "learning_rate": 7.887300992355427e-06, "loss": 0.2384, "step": 2452 }, { "epoch": 0.28163030998851896, "grad_norm": 0.1878589242696762, "learning_rate": 7.859573170852196e-06, "loss": 0.2384, "step": 2453 }, { "epoch": 0.2817451205510907, "grad_norm": 0.1932166963815689, "learning_rate": 7.83188886282801e-06, "loss": 0.2446, "step": 2454 }, { "epoch": 0.2818599311136625, "grad_norm": 0.18449051678180695, "learning_rate": 7.80424810576344e-06, "loss": 0.2585, "step": 2455 }, { "epoch": 0.2819747416762342, "grad_norm": 0.902416467666626, "learning_rate": 7.776650937080027e-06, "loss": 0.2536, "step": 2456 }, { "epoch": 0.282089552238806, "grad_norm": 0.19386357069015503, "learning_rate": 7.749097394140355e-06, "loss": 0.2575, "step": 2457 }, { "epoch": 0.28220436280137773, "grad_norm": 0.19626358151435852, "learning_rate": 7.721587514247933e-06, "loss": 0.2449, "step": 2458 }, { "epoch": 0.28231917336394946, "grad_norm": 0.18902921676635742, "learning_rate": 7.694121334647131e-06, "loss": 0.2444, "step": 2459 }, { "epoch": 0.28243398392652125, "grad_norm": 0.20545221865177155, "learning_rate": 7.666698892523184e-06, "loss": 0.2499, "step": 2460 }, { "epoch": 0.282548794489093, "grad_norm": 0.1992800533771515, "learning_rate": 7.639320225002106e-06, "loss": 0.2457, "step": 2461 }, { "epoch": 0.28266360505166477, "grad_norm": 0.196416437625885, "learning_rate": 7.611985369150643e-06, "loss": 0.2452, "step": 2462 }, { "epoch": 0.2827784156142365, "grad_norm": 25.021320343017578, "learning_rate": 7.584694361976228e-06, "loss": 0.3478, "step": 2463 }, { "epoch": 0.2828932261768083, "grad_norm": 0.19982187449932098, "learning_rate": 7.557447240426943e-06, "loss": 0.2525, "step": 2464 }, { "epoch": 0.28300803673938, "grad_norm": 0.21139998733997345, "learning_rate": 7.5302440413914126e-06, "loss": 0.2521, "step": 2465 }, { "epoch": 0.28312284730195175, "grad_norm": 0.1865197867155075, "learning_rate": 7.503084801698839e-06, "loss": 0.2326, "step": 2466 }, { "epoch": 0.28323765786452354, "grad_norm": 0.19301673769950867, "learning_rate": 7.475969558118899e-06, "loss": 0.2526, "step": 2467 }, { "epoch": 0.28335246842709527, "grad_norm": 0.19108465313911438, "learning_rate": 7.4488983473616975e-06, "loss": 0.2425, "step": 2468 }, { "epoch": 0.28346727898966706, "grad_norm": 0.18615028262138367, "learning_rate": 7.421871206077726e-06, "loss": 0.2412, "step": 2469 }, { "epoch": 0.2835820895522388, "grad_norm": 0.19666951894760132, "learning_rate": 7.394888170857828e-06, "loss": 0.2628, "step": 2470 }, { "epoch": 0.2836969001148106, "grad_norm": 0.21668192744255066, "learning_rate": 7.367949278233126e-06, "loss": 0.2569, "step": 2471 }, { "epoch": 0.2838117106773823, "grad_norm": 0.19469870626926422, "learning_rate": 7.3410545646749496e-06, "loss": 0.252, "step": 2472 }, { "epoch": 0.2839265212399541, "grad_norm": 0.20098167657852173, "learning_rate": 7.314204066594861e-06, "loss": 0.2607, "step": 2473 }, { "epoch": 0.28404133180252583, "grad_norm": 0.18765415251255035, "learning_rate": 7.28739782034455e-06, "loss": 0.238, "step": 2474 }, { "epoch": 0.28415614236509756, "grad_norm": 0.19192758202552795, "learning_rate": 7.2606358622157565e-06, "loss": 0.2511, "step": 2475 }, { "epoch": 0.28427095292766935, "grad_norm": 0.2043314427137375, "learning_rate": 7.233918228440324e-06, "loss": 0.2568, "step": 2476 }, { "epoch": 0.2843857634902411, "grad_norm": 0.20405782759189606, "learning_rate": 7.2072449551900555e-06, "loss": 0.2712, "step": 2477 }, { "epoch": 0.28450057405281287, "grad_norm": 0.20883788168430328, "learning_rate": 7.180616078576679e-06, "loss": 0.2518, "step": 2478 }, { "epoch": 0.2846153846153846, "grad_norm": 0.1910858452320099, "learning_rate": 7.154031634651839e-06, "loss": 0.2518, "step": 2479 }, { "epoch": 0.2847301951779564, "grad_norm": 0.23848608136177063, "learning_rate": 7.127491659407035e-06, "loss": 0.2521, "step": 2480 }, { "epoch": 0.2848450057405281, "grad_norm": 0.18581311404705048, "learning_rate": 7.1009961887735075e-06, "loss": 0.2251, "step": 2481 }, { "epoch": 0.2849598163030999, "grad_norm": 0.19068825244903564, "learning_rate": 7.074545258622323e-06, "loss": 0.2493, "step": 2482 }, { "epoch": 0.28507462686567164, "grad_norm": 1.6357544660568237, "learning_rate": 7.048138904764199e-06, "loss": 0.2775, "step": 2483 }, { "epoch": 0.2851894374282434, "grad_norm": 0.1879637986421585, "learning_rate": 7.0217771629494945e-06, "loss": 0.2535, "step": 2484 }, { "epoch": 0.28530424799081516, "grad_norm": 0.18660259246826172, "learning_rate": 6.995460068868198e-06, "loss": 0.2312, "step": 2485 }, { "epoch": 0.2854190585533869, "grad_norm": 0.22051848471164703, "learning_rate": 6.969187658149836e-06, "loss": 0.2357, "step": 2486 }, { "epoch": 0.2855338691159587, "grad_norm": 0.19056639075279236, "learning_rate": 6.9429599663634586e-06, "loss": 0.2362, "step": 2487 }, { "epoch": 0.2856486796785304, "grad_norm": 0.19373387098312378, "learning_rate": 6.9167770290175226e-06, "loss": 0.2413, "step": 2488 }, { "epoch": 0.2857634902411022, "grad_norm": 0.19308824837207794, "learning_rate": 6.8906388815599765e-06, "loss": 0.2619, "step": 2489 }, { "epoch": 0.28587830080367393, "grad_norm": 0.5823530554771423, "learning_rate": 6.864545559378055e-06, "loss": 0.2542, "step": 2490 }, { "epoch": 0.28599311136624567, "grad_norm": 0.1886119544506073, "learning_rate": 6.838497097798336e-06, "loss": 0.244, "step": 2491 }, { "epoch": 0.28610792192881745, "grad_norm": 0.1826237589120865, "learning_rate": 6.812493532086661e-06, "loss": 0.2379, "step": 2492 }, { "epoch": 0.2862227324913892, "grad_norm": 0.1885431557893753, "learning_rate": 6.786534897448107e-06, "loss": 0.2419, "step": 2493 }, { "epoch": 0.286337543053961, "grad_norm": 0.19254732131958008, "learning_rate": 6.7606212290268755e-06, "loss": 0.2486, "step": 2494 }, { "epoch": 0.2864523536165327, "grad_norm": 0.18497808277606964, "learning_rate": 6.734752561906317e-06, "loss": 0.2339, "step": 2495 }, { "epoch": 0.2865671641791045, "grad_norm": 0.19410161674022675, "learning_rate": 6.708928931108896e-06, "loss": 0.2489, "step": 2496 }, { "epoch": 0.2866819747416762, "grad_norm": 0.19207218289375305, "learning_rate": 6.6831503715960235e-06, "loss": 0.2452, "step": 2497 }, { "epoch": 0.286796785304248, "grad_norm": 0.1898481845855713, "learning_rate": 6.657416918268147e-06, "loss": 0.2403, "step": 2498 }, { "epoch": 0.28691159586681975, "grad_norm": 0.19766604900360107, "learning_rate": 6.6317286059646425e-06, "loss": 0.2629, "step": 2499 }, { "epoch": 0.2870264064293915, "grad_norm": 0.20199012756347656, "learning_rate": 6.606085469463744e-06, "loss": 0.2392, "step": 2500 }, { "epoch": 0.28714121699196327, "grad_norm": 0.2025163620710373, "learning_rate": 6.58048754348255e-06, "loss": 0.2609, "step": 2501 }, { "epoch": 0.287256027554535, "grad_norm": 0.19625048339366913, "learning_rate": 6.554934862676936e-06, "loss": 0.2664, "step": 2502 }, { "epoch": 0.2873708381171068, "grad_norm": 0.18549422919750214, "learning_rate": 6.529427461641535e-06, "loss": 0.2305, "step": 2503 }, { "epoch": 0.2874856486796785, "grad_norm": 0.19489063322544098, "learning_rate": 6.503965374909667e-06, "loss": 0.2508, "step": 2504 }, { "epoch": 0.2876004592422503, "grad_norm": 0.19194214046001434, "learning_rate": 6.478548636953306e-06, "loss": 0.2488, "step": 2505 }, { "epoch": 0.28771526980482204, "grad_norm": 0.1970548927783966, "learning_rate": 6.453177282183043e-06, "loss": 0.2476, "step": 2506 }, { "epoch": 0.2878300803673938, "grad_norm": 0.20742444694042206, "learning_rate": 6.427851344947997e-06, "loss": 0.2551, "step": 2507 }, { "epoch": 0.28794489092996556, "grad_norm": 0.18940387666225433, "learning_rate": 6.402570859535822e-06, "loss": 0.2325, "step": 2508 }, { "epoch": 0.2880597014925373, "grad_norm": 0.21152867376804352, "learning_rate": 6.377335860172631e-06, "loss": 0.2602, "step": 2509 }, { "epoch": 0.2881745120551091, "grad_norm": 0.18349693715572357, "learning_rate": 6.352146381022955e-06, "loss": 0.2379, "step": 2510 }, { "epoch": 0.2882893226176808, "grad_norm": 0.19272592663764954, "learning_rate": 6.327002456189699e-06, "loss": 0.2515, "step": 2511 }, { "epoch": 0.2884041331802526, "grad_norm": 0.19148500263690948, "learning_rate": 6.301904119714102e-06, "loss": 0.2517, "step": 2512 }, { "epoch": 0.28851894374282433, "grad_norm": 0.1904744654893875, "learning_rate": 6.276851405575657e-06, "loss": 0.2404, "step": 2513 }, { "epoch": 0.2886337543053961, "grad_norm": 0.19613316655158997, "learning_rate": 6.251844347692109e-06, "loss": 0.2624, "step": 2514 }, { "epoch": 0.28874856486796785, "grad_norm": 0.19290554523468018, "learning_rate": 6.226882979919407e-06, "loss": 0.2579, "step": 2515 }, { "epoch": 0.28886337543053964, "grad_norm": 0.1778699904680252, "learning_rate": 6.201967336051593e-06, "loss": 0.23, "step": 2516 }, { "epoch": 0.28897818599311137, "grad_norm": 0.19358386099338531, "learning_rate": 6.177097449820864e-06, "loss": 0.2641, "step": 2517 }, { "epoch": 0.2890929965556831, "grad_norm": 0.19390511512756348, "learning_rate": 6.152273354897444e-06, "loss": 0.2517, "step": 2518 }, { "epoch": 0.2892078071182549, "grad_norm": 0.18399809300899506, "learning_rate": 6.127495084889541e-06, "loss": 0.2475, "step": 2519 }, { "epoch": 0.2893226176808266, "grad_norm": 0.1959884613752365, "learning_rate": 6.1027626733433455e-06, "loss": 0.2509, "step": 2520 }, { "epoch": 0.2894374282433984, "grad_norm": 0.20412577688694, "learning_rate": 6.078076153742962e-06, "loss": 0.2552, "step": 2521 }, { "epoch": 0.28955223880597014, "grad_norm": 0.18974485993385315, "learning_rate": 6.053435559510368e-06, "loss": 0.2429, "step": 2522 }, { "epoch": 0.28966704936854193, "grad_norm": 0.19186483323574066, "learning_rate": 6.028840924005326e-06, "loss": 0.2562, "step": 2523 }, { "epoch": 0.28978185993111366, "grad_norm": 0.21893392503261566, "learning_rate": 6.00429228052545e-06, "loss": 0.253, "step": 2524 }, { "epoch": 0.2898966704936854, "grad_norm": 0.1980101466178894, "learning_rate": 5.979789662306008e-06, "loss": 0.2684, "step": 2525 }, { "epoch": 0.2900114810562572, "grad_norm": 0.18801693618297577, "learning_rate": 5.955333102520011e-06, "loss": 0.2445, "step": 2526 }, { "epoch": 0.2901262916188289, "grad_norm": 0.18448050320148468, "learning_rate": 5.930922634278094e-06, "loss": 0.2562, "step": 2527 }, { "epoch": 0.2902411021814007, "grad_norm": 0.18830512464046478, "learning_rate": 5.906558290628503e-06, "loss": 0.2495, "step": 2528 }, { "epoch": 0.29035591274397243, "grad_norm": 0.19109919667243958, "learning_rate": 5.882240104557002e-06, "loss": 0.2519, "step": 2529 }, { "epoch": 0.2904707233065442, "grad_norm": 0.18688417971134186, "learning_rate": 5.857968108986898e-06, "loss": 0.2504, "step": 2530 }, { "epoch": 0.29058553386911595, "grad_norm": 0.18487288057804108, "learning_rate": 5.833742336778981e-06, "loss": 0.2393, "step": 2531 }, { "epoch": 0.29070034443168774, "grad_norm": 0.2047719657421112, "learning_rate": 5.809562820731401e-06, "loss": 0.2491, "step": 2532 }, { "epoch": 0.2908151549942595, "grad_norm": 0.45274385809898376, "learning_rate": 5.785429593579736e-06, "loss": 0.2497, "step": 2533 }, { "epoch": 0.2909299655568312, "grad_norm": 0.20143021643161774, "learning_rate": 5.7613426879968804e-06, "loss": 0.2505, "step": 2534 }, { "epoch": 0.291044776119403, "grad_norm": 0.20069867372512817, "learning_rate": 5.7373021365929944e-06, "loss": 0.2612, "step": 2535 }, { "epoch": 0.2911595866819747, "grad_norm": 0.181847482919693, "learning_rate": 5.7133079719155115e-06, "loss": 0.2262, "step": 2536 }, { "epoch": 0.2912743972445465, "grad_norm": 0.2005425989627838, "learning_rate": 5.689360226449054e-06, "loss": 0.2751, "step": 2537 }, { "epoch": 0.29138920780711824, "grad_norm": 0.1889486014842987, "learning_rate": 5.665458932615396e-06, "loss": 0.2519, "step": 2538 }, { "epoch": 0.29150401836969003, "grad_norm": 0.19163532555103302, "learning_rate": 5.641604122773423e-06, "loss": 0.2574, "step": 2539 }, { "epoch": 0.29161882893226176, "grad_norm": 0.18771761655807495, "learning_rate": 5.6177958292191035e-06, "loss": 0.24, "step": 2540 }, { "epoch": 0.29173363949483355, "grad_norm": 0.1888563632965088, "learning_rate": 5.5940340841853915e-06, "loss": 0.2268, "step": 2541 }, { "epoch": 0.2918484500574053, "grad_norm": 0.1910495012998581, "learning_rate": 5.5703189198422595e-06, "loss": 0.2512, "step": 2542 }, { "epoch": 0.291963260619977, "grad_norm": 0.1916400045156479, "learning_rate": 5.546650368296598e-06, "loss": 0.2298, "step": 2543 }, { "epoch": 0.2920780711825488, "grad_norm": 0.18685738742351532, "learning_rate": 5.5230284615922015e-06, "loss": 0.252, "step": 2544 }, { "epoch": 0.29219288174512054, "grad_norm": 0.19370315968990326, "learning_rate": 5.499453231709702e-06, "loss": 0.2543, "step": 2545 }, { "epoch": 0.2923076923076923, "grad_norm": 0.18278498947620392, "learning_rate": 5.475924710566544e-06, "loss": 0.2379, "step": 2546 }, { "epoch": 0.29242250287026406, "grad_norm": 0.1865372657775879, "learning_rate": 5.452442930016948e-06, "loss": 0.2387, "step": 2547 }, { "epoch": 0.29253731343283584, "grad_norm": 0.18981270492076874, "learning_rate": 5.429007921851815e-06, "loss": 0.2375, "step": 2548 }, { "epoch": 0.2926521239954076, "grad_norm": 0.18955397605895996, "learning_rate": 5.405619717798765e-06, "loss": 0.2514, "step": 2549 }, { "epoch": 0.2927669345579793, "grad_norm": 0.18475624918937683, "learning_rate": 5.382278349522034e-06, "loss": 0.2575, "step": 2550 }, { "epoch": 0.2928817451205511, "grad_norm": 0.1914256364107132, "learning_rate": 5.358983848622452e-06, "loss": 0.2318, "step": 2551 }, { "epoch": 0.29299655568312283, "grad_norm": 0.18861176073551178, "learning_rate": 5.335736246637395e-06, "loss": 0.2364, "step": 2552 }, { "epoch": 0.2931113662456946, "grad_norm": 0.19095931947231293, "learning_rate": 5.312535575040758e-06, "loss": 0.2498, "step": 2553 }, { "epoch": 0.29322617680826635, "grad_norm": 0.18617072701454163, "learning_rate": 5.289381865242868e-06, "loss": 0.2399, "step": 2554 }, { "epoch": 0.29334098737083814, "grad_norm": 0.19042162597179413, "learning_rate": 5.266275148590496e-06, "loss": 0.2444, "step": 2555 }, { "epoch": 0.29345579793340987, "grad_norm": 0.1982312798500061, "learning_rate": 5.243215456366795e-06, "loss": 0.2563, "step": 2556 }, { "epoch": 0.29357060849598166, "grad_norm": 0.18686668574810028, "learning_rate": 5.22020281979124e-06, "loss": 0.2234, "step": 2557 }, { "epoch": 0.2936854190585534, "grad_norm": 0.18549717962741852, "learning_rate": 5.197237270019609e-06, "loss": 0.242, "step": 2558 }, { "epoch": 0.2938002296211251, "grad_norm": 0.20223559439182281, "learning_rate": 5.17431883814393e-06, "loss": 0.2546, "step": 2559 }, { "epoch": 0.2939150401836969, "grad_norm": 0.19112686812877655, "learning_rate": 5.151447555192426e-06, "loss": 0.2496, "step": 2560 }, { "epoch": 0.29402985074626864, "grad_norm": 0.18622076511383057, "learning_rate": 5.128623452129508e-06, "loss": 0.2345, "step": 2561 }, { "epoch": 0.2941446613088404, "grad_norm": 0.18546120822429657, "learning_rate": 5.105846559855701e-06, "loss": 0.2287, "step": 2562 }, { "epoch": 0.29425947187141216, "grad_norm": 0.1927817463874817, "learning_rate": 5.0831169092076195e-06, "loss": 0.2432, "step": 2563 }, { "epoch": 0.29437428243398395, "grad_norm": 0.18967169523239136, "learning_rate": 5.060434530957898e-06, "loss": 0.2564, "step": 2564 }, { "epoch": 0.2944890929965557, "grad_norm": 0.1900019496679306, "learning_rate": 5.037799455815213e-06, "loss": 0.2373, "step": 2565 }, { "epoch": 0.29460390355912747, "grad_norm": 0.1905706524848938, "learning_rate": 5.015211714424171e-06, "loss": 0.2504, "step": 2566 }, { "epoch": 0.2947187141216992, "grad_norm": 0.18315638601779938, "learning_rate": 4.9926713373652865e-06, "loss": 0.2357, "step": 2567 }, { "epoch": 0.29483352468427093, "grad_norm": 0.19717951118946075, "learning_rate": 4.970178355154969e-06, "loss": 0.2526, "step": 2568 }, { "epoch": 0.2949483352468427, "grad_norm": 0.1932404339313507, "learning_rate": 4.947732798245466e-06, "loss": 0.2663, "step": 2569 }, { "epoch": 0.29506314580941445, "grad_norm": 0.18520262837409973, "learning_rate": 4.925334697024786e-06, "loss": 0.2238, "step": 2570 }, { "epoch": 0.29517795637198624, "grad_norm": 0.30613118410110474, "learning_rate": 4.902984081816717e-06, "loss": 0.238, "step": 2571 }, { "epoch": 0.29529276693455797, "grad_norm": 0.19685639441013336, "learning_rate": 4.880680982880779e-06, "loss": 0.2572, "step": 2572 }, { "epoch": 0.29540757749712976, "grad_norm": 0.180955171585083, "learning_rate": 4.858425430412106e-06, "loss": 0.2336, "step": 2573 }, { "epoch": 0.2955223880597015, "grad_norm": 0.18672312796115875, "learning_rate": 4.836217454541498e-06, "loss": 0.2446, "step": 2574 }, { "epoch": 0.2956371986222732, "grad_norm": 0.1759180873632431, "learning_rate": 4.8140570853353466e-06, "loss": 0.2206, "step": 2575 }, { "epoch": 0.295752009184845, "grad_norm": 0.4850091338157654, "learning_rate": 4.791944352795561e-06, "loss": 0.2462, "step": 2576 }, { "epoch": 0.29586681974741674, "grad_norm": 0.1900922656059265, "learning_rate": 4.769879286859582e-06, "loss": 0.2381, "step": 2577 }, { "epoch": 0.29598163030998853, "grad_norm": 0.19270797073841095, "learning_rate": 4.747861917400313e-06, "loss": 0.2424, "step": 2578 }, { "epoch": 0.29609644087256026, "grad_norm": 0.186348095536232, "learning_rate": 4.72589227422608e-06, "loss": 0.2583, "step": 2579 }, { "epoch": 0.29621125143513205, "grad_norm": 0.19499871134757996, "learning_rate": 4.7039703870805965e-06, "loss": 0.2635, "step": 2580 }, { "epoch": 0.2963260619977038, "grad_norm": 0.2004646509885788, "learning_rate": 4.6820962856429205e-06, "loss": 0.2653, "step": 2581 }, { "epoch": 0.29644087256027557, "grad_norm": 0.22623299062252045, "learning_rate": 4.660269999527422e-06, "loss": 0.2792, "step": 2582 }, { "epoch": 0.2965556831228473, "grad_norm": 0.18958459794521332, "learning_rate": 4.638491558283708e-06, "loss": 0.2364, "step": 2583 }, { "epoch": 0.29667049368541903, "grad_norm": 0.1952737718820572, "learning_rate": 4.616760991396643e-06, "loss": 0.2414, "step": 2584 }, { "epoch": 0.2967853042479908, "grad_norm": 0.19117124378681183, "learning_rate": 4.595078328286269e-06, "loss": 0.2568, "step": 2585 }, { "epoch": 0.29690011481056255, "grad_norm": 0.1834212690591812, "learning_rate": 4.5734435983077585e-06, "loss": 0.2301, "step": 2586 }, { "epoch": 0.29701492537313434, "grad_norm": 0.19618701934814453, "learning_rate": 4.551856830751411e-06, "loss": 0.2563, "step": 2587 }, { "epoch": 0.2971297359357061, "grad_norm": 0.19034399092197418, "learning_rate": 4.530318054842582e-06, "loss": 0.2625, "step": 2588 }, { "epoch": 0.29724454649827786, "grad_norm": 0.18098846077919006, "learning_rate": 4.508827299741634e-06, "loss": 0.2336, "step": 2589 }, { "epoch": 0.2973593570608496, "grad_norm": 0.18527115881443024, "learning_rate": 4.487384594543951e-06, "loss": 0.2538, "step": 2590 }, { "epoch": 0.2974741676234214, "grad_norm": 0.18544486165046692, "learning_rate": 4.4659899682798446e-06, "loss": 0.2503, "step": 2591 }, { "epoch": 0.2975889781859931, "grad_norm": 0.18628478050231934, "learning_rate": 4.444643449914523e-06, "loss": 0.2394, "step": 2592 }, { "epoch": 0.29770378874856485, "grad_norm": 0.18544574081897736, "learning_rate": 4.423345068348099e-06, "loss": 0.2284, "step": 2593 }, { "epoch": 0.29781859931113663, "grad_norm": 0.20829959213733673, "learning_rate": 4.40209485241549e-06, "loss": 0.2389, "step": 2594 }, { "epoch": 0.29793340987370837, "grad_norm": 0.18042786419391632, "learning_rate": 4.380892830886394e-06, "loss": 0.2267, "step": 2595 }, { "epoch": 0.29804822043628015, "grad_norm": 0.1809576004743576, "learning_rate": 4.359739032465289e-06, "loss": 0.2305, "step": 2596 }, { "epoch": 0.2981630309988519, "grad_norm": 0.18896441161632538, "learning_rate": 4.338633485791342e-06, "loss": 0.2645, "step": 2597 }, { "epoch": 0.2982778415614237, "grad_norm": 0.1849934607744217, "learning_rate": 4.317576219438419e-06, "loss": 0.2474, "step": 2598 }, { "epoch": 0.2983926521239954, "grad_norm": 0.19031201303005219, "learning_rate": 4.296567261914977e-06, "loss": 0.2528, "step": 2599 }, { "epoch": 0.29850746268656714, "grad_norm": 0.18740856647491455, "learning_rate": 4.2756066416641366e-06, "loss": 0.2294, "step": 2600 }, { "epoch": 0.2986222732491389, "grad_norm": 0.17892394959926605, "learning_rate": 4.254694387063514e-06, "loss": 0.2445, "step": 2601 }, { "epoch": 0.29873708381171066, "grad_norm": 0.18679313361644745, "learning_rate": 4.233830526425276e-06, "loss": 0.2507, "step": 2602 }, { "epoch": 0.29885189437428245, "grad_norm": 0.19517973065376282, "learning_rate": 4.213015087996066e-06, "loss": 0.2635, "step": 2603 }, { "epoch": 0.2989667049368542, "grad_norm": 0.18721416592597961, "learning_rate": 4.192248099956979e-06, "loss": 0.2449, "step": 2604 }, { "epoch": 0.29908151549942597, "grad_norm": 0.1778426617383957, "learning_rate": 4.171529590423484e-06, "loss": 0.2313, "step": 2605 }, { "epoch": 0.2991963260619977, "grad_norm": 0.19948677718639374, "learning_rate": 4.1508595874454635e-06, "loss": 0.2465, "step": 2606 }, { "epoch": 0.2993111366245695, "grad_norm": 0.19211682677268982, "learning_rate": 4.130238119007101e-06, "loss": 0.2462, "step": 2607 }, { "epoch": 0.2994259471871412, "grad_norm": 3.167423725128174, "learning_rate": 4.109665213026866e-06, "loss": 0.2727, "step": 2608 }, { "epoch": 0.29954075774971295, "grad_norm": 0.4416728913784027, "learning_rate": 4.089140897357493e-06, "loss": 0.2652, "step": 2609 }, { "epoch": 0.29965556831228474, "grad_norm": 0.20166738331317902, "learning_rate": 4.068665199785944e-06, "loss": 0.2589, "step": 2610 }, { "epoch": 0.29977037887485647, "grad_norm": 0.1951931267976761, "learning_rate": 4.048238148033328e-06, "loss": 0.2599, "step": 2611 }, { "epoch": 0.29988518943742826, "grad_norm": 0.18360085785388947, "learning_rate": 4.02785976975491e-06, "loss": 0.2329, "step": 2612 }, { "epoch": 0.3, "grad_norm": 0.1829376518726349, "learning_rate": 4.007530092540081e-06, "loss": 0.2393, "step": 2613 }, { "epoch": 0.3001148105625718, "grad_norm": 0.18023201823234558, "learning_rate": 3.987249143912259e-06, "loss": 0.2083, "step": 2614 }, { "epoch": 0.3002296211251435, "grad_norm": 0.17967334389686584, "learning_rate": 3.9670169513289195e-06, "loss": 0.2406, "step": 2615 }, { "epoch": 0.3003444316877153, "grad_norm": 0.1855049431324005, "learning_rate": 3.94683354218151e-06, "loss": 0.2384, "step": 2616 }, { "epoch": 0.30045924225028703, "grad_norm": 0.186697319149971, "learning_rate": 3.926698943795453e-06, "loss": 0.2406, "step": 2617 }, { "epoch": 0.30057405281285876, "grad_norm": 0.19472838938236237, "learning_rate": 3.906613183430063e-06, "loss": 0.2501, "step": 2618 }, { "epoch": 0.30068886337543055, "grad_norm": 0.18304185569286346, "learning_rate": 3.88657628827855e-06, "loss": 0.2417, "step": 2619 }, { "epoch": 0.3008036739380023, "grad_norm": 0.6934216022491455, "learning_rate": 3.866588285467967e-06, "loss": 0.2547, "step": 2620 }, { "epoch": 0.30091848450057407, "grad_norm": 0.18791308999061584, "learning_rate": 3.846649202059181e-06, "loss": 0.2331, "step": 2621 }, { "epoch": 0.3010332950631458, "grad_norm": 0.1884855180978775, "learning_rate": 3.826759065046806e-06, "loss": 0.2638, "step": 2622 }, { "epoch": 0.3011481056257176, "grad_norm": 0.1902429759502411, "learning_rate": 3.806917901359226e-06, "loss": 0.2449, "step": 2623 }, { "epoch": 0.3012629161882893, "grad_norm": 0.183439701795578, "learning_rate": 3.787125737858475e-06, "loss": 0.2337, "step": 2624 }, { "epoch": 0.30137772675086105, "grad_norm": 0.18821151554584503, "learning_rate": 3.7673826013402858e-06, "loss": 0.2401, "step": 2625 }, { "epoch": 0.30149253731343284, "grad_norm": 0.1912768930196762, "learning_rate": 3.747688518534003e-06, "loss": 0.2651, "step": 2626 }, { "epoch": 0.3016073478760046, "grad_norm": 0.1866748183965683, "learning_rate": 3.7280435161025596e-06, "loss": 0.2389, "step": 2627 }, { "epoch": 0.30172215843857636, "grad_norm": 0.19400811195373535, "learning_rate": 3.7084476206424413e-06, "loss": 0.2679, "step": 2628 }, { "epoch": 0.3018369690011481, "grad_norm": 0.20139481127262115, "learning_rate": 3.688900858683657e-06, "loss": 0.2726, "step": 2629 }, { "epoch": 0.3019517795637199, "grad_norm": 0.23015835881233215, "learning_rate": 3.6694032566896787e-06, "loss": 0.2574, "step": 2630 }, { "epoch": 0.3020665901262916, "grad_norm": 0.1792864054441452, "learning_rate": 3.6499548410574303e-06, "loss": 0.229, "step": 2631 }, { "epoch": 0.3021814006888634, "grad_norm": 0.20285262167453766, "learning_rate": 3.6305556381172592e-06, "loss": 0.27, "step": 2632 }, { "epoch": 0.30229621125143513, "grad_norm": 0.19322098791599274, "learning_rate": 3.611205674132867e-06, "loss": 0.2549, "step": 2633 }, { "epoch": 0.30241102181400686, "grad_norm": 0.18395961821079254, "learning_rate": 3.5919049753013034e-06, "loss": 0.2478, "step": 2634 }, { "epoch": 0.30252583237657865, "grad_norm": 0.1896706074476242, "learning_rate": 3.5726535677529195e-06, "loss": 0.2507, "step": 2635 }, { "epoch": 0.3026406429391504, "grad_norm": 0.19398322701454163, "learning_rate": 3.5534514775513198e-06, "loss": 0.2577, "step": 2636 }, { "epoch": 0.30275545350172217, "grad_norm": 0.188791424036026, "learning_rate": 3.5342987306933617e-06, "loss": 0.2417, "step": 2637 }, { "epoch": 0.3028702640642939, "grad_norm": 0.5625783205032349, "learning_rate": 3.515195353109082e-06, "loss": 0.2473, "step": 2638 }, { "epoch": 0.3029850746268657, "grad_norm": 0.18244609236717224, "learning_rate": 3.4961413706616943e-06, "loss": 0.2189, "step": 2639 }, { "epoch": 0.3030998851894374, "grad_norm": 0.16894955933094025, "learning_rate": 3.4771368091475054e-06, "loss": 0.2107, "step": 2640 }, { "epoch": 0.3032146957520092, "grad_norm": 0.18370097875595093, "learning_rate": 3.458181694295961e-06, "loss": 0.2411, "step": 2641 }, { "epoch": 0.30332950631458094, "grad_norm": 0.1944771409034729, "learning_rate": 3.439276051769538e-06, "loss": 0.2529, "step": 2642 }, { "epoch": 0.3034443168771527, "grad_norm": 0.19063900411128998, "learning_rate": 3.4204199071637258e-06, "loss": 0.2484, "step": 2643 }, { "epoch": 0.30355912743972446, "grad_norm": 0.1874215006828308, "learning_rate": 3.4016132860070108e-06, "loss": 0.2468, "step": 2644 }, { "epoch": 0.3036739380022962, "grad_norm": 0.19860972464084625, "learning_rate": 3.382856213760839e-06, "loss": 0.2764, "step": 2645 }, { "epoch": 0.303788748564868, "grad_norm": 0.19114547967910767, "learning_rate": 3.364148715819564e-06, "loss": 0.2437, "step": 2646 }, { "epoch": 0.3039035591274397, "grad_norm": 0.1841215193271637, "learning_rate": 3.345490817510415e-06, "loss": 0.2317, "step": 2647 }, { "epoch": 0.3040183696900115, "grad_norm": 0.17988911271095276, "learning_rate": 3.326882544093506e-06, "loss": 0.2443, "step": 2648 }, { "epoch": 0.30413318025258324, "grad_norm": 0.1736048310995102, "learning_rate": 3.3083239207617203e-06, "loss": 0.2206, "step": 2649 }, { "epoch": 0.30424799081515497, "grad_norm": 0.2034609317779541, "learning_rate": 3.2898149726407545e-06, "loss": 0.2395, "step": 2650 }, { "epoch": 0.30436280137772675, "grad_norm": 0.21006806194782257, "learning_rate": 3.2713557247890447e-06, "loss": 0.2467, "step": 2651 }, { "epoch": 0.3044776119402985, "grad_norm": 0.19504907727241516, "learning_rate": 3.252946202197724e-06, "loss": 0.2382, "step": 2652 }, { "epoch": 0.3045924225028703, "grad_norm": 0.19166888296604156, "learning_rate": 3.234586429790625e-06, "loss": 0.2614, "step": 2653 }, { "epoch": 0.304707233065442, "grad_norm": 0.18213984370231628, "learning_rate": 3.216276432424219e-06, "loss": 0.2323, "step": 2654 }, { "epoch": 0.3048220436280138, "grad_norm": 0.1736111342906952, "learning_rate": 3.198016234887584e-06, "loss": 0.2281, "step": 2655 }, { "epoch": 0.3049368541905855, "grad_norm": 0.18650303781032562, "learning_rate": 3.1798058619023853e-06, "loss": 0.2444, "step": 2656 }, { "epoch": 0.3050516647531573, "grad_norm": 0.19425006210803986, "learning_rate": 3.1616453381228294e-06, "loss": 0.2627, "step": 2657 }, { "epoch": 0.30516647531572905, "grad_norm": 0.17654086649417877, "learning_rate": 3.143534688135632e-06, "loss": 0.2322, "step": 2658 }, { "epoch": 0.3052812858783008, "grad_norm": 0.19292180240154266, "learning_rate": 3.125473936459984e-06, "loss": 0.2487, "step": 2659 }, { "epoch": 0.30539609644087257, "grad_norm": 0.17477001249790192, "learning_rate": 3.1074631075475213e-06, "loss": 0.2212, "step": 2660 }, { "epoch": 0.3055109070034443, "grad_norm": 0.19013802707195282, "learning_rate": 3.0895022257823083e-06, "loss": 0.256, "step": 2661 }, { "epoch": 0.3056257175660161, "grad_norm": 0.19099119305610657, "learning_rate": 3.0715913154807644e-06, "loss": 0.2462, "step": 2662 }, { "epoch": 0.3057405281285878, "grad_norm": 0.1824878454208374, "learning_rate": 3.05373040089167e-06, "loss": 0.2348, "step": 2663 }, { "epoch": 0.3058553386911596, "grad_norm": 0.1900586634874344, "learning_rate": 3.035919506196123e-06, "loss": 0.2539, "step": 2664 }, { "epoch": 0.30597014925373134, "grad_norm": 0.1930084228515625, "learning_rate": 3.0181586555074793e-06, "loss": 0.2656, "step": 2665 }, { "epoch": 0.3060849598163031, "grad_norm": 0.1855415403842926, "learning_rate": 3.000447872871357e-06, "loss": 0.2523, "step": 2666 }, { "epoch": 0.30619977037887486, "grad_norm": 0.19015178084373474, "learning_rate": 2.9827871822655985e-06, "loss": 0.2334, "step": 2667 }, { "epoch": 0.3063145809414466, "grad_norm": 0.18821735680103302, "learning_rate": 2.965176607600211e-06, "loss": 0.2318, "step": 2668 }, { "epoch": 0.3064293915040184, "grad_norm": 0.19757704436779022, "learning_rate": 2.9476161727173625e-06, "loss": 0.2576, "step": 2669 }, { "epoch": 0.3065442020665901, "grad_norm": 0.18965724110603333, "learning_rate": 2.9301059013913426e-06, "loss": 0.2406, "step": 2670 }, { "epoch": 0.3066590126291619, "grad_norm": 0.17835666239261627, "learning_rate": 2.9126458173285077e-06, "loss": 0.2397, "step": 2671 }, { "epoch": 0.30677382319173363, "grad_norm": 0.18009917438030243, "learning_rate": 2.895235944167287e-06, "loss": 0.2458, "step": 2672 }, { "epoch": 0.3068886337543054, "grad_norm": 0.18836721777915955, "learning_rate": 2.8778763054781246e-06, "loss": 0.2333, "step": 2673 }, { "epoch": 0.30700344431687715, "grad_norm": 0.17772510647773743, "learning_rate": 2.8605669247634592e-06, "loss": 0.239, "step": 2674 }, { "epoch": 0.3071182548794489, "grad_norm": 0.19149082899093628, "learning_rate": 2.843307825457675e-06, "loss": 0.2384, "step": 2675 }, { "epoch": 0.30723306544202067, "grad_norm": 0.17104537785053253, "learning_rate": 2.8260990309270987e-06, "loss": 0.2292, "step": 2676 }, { "epoch": 0.3073478760045924, "grad_norm": 0.1973390281200409, "learning_rate": 2.8089405644699463e-06, "loss": 0.2668, "step": 2677 }, { "epoch": 0.3074626865671642, "grad_norm": 0.17447935044765472, "learning_rate": 2.791832449316281e-06, "loss": 0.2282, "step": 2678 }, { "epoch": 0.3075774971297359, "grad_norm": 0.18879814445972443, "learning_rate": 2.7747747086280184e-06, "loss": 0.25, "step": 2679 }, { "epoch": 0.3076923076923077, "grad_norm": 0.18176402151584625, "learning_rate": 2.7577673654988734e-06, "loss": 0.2294, "step": 2680 }, { "epoch": 0.30780711825487944, "grad_norm": 0.19116227328777313, "learning_rate": 2.7408104429543025e-06, "loss": 0.2393, "step": 2681 }, { "epoch": 0.30792192881745123, "grad_norm": 0.1813759058713913, "learning_rate": 2.723903963951542e-06, "loss": 0.2375, "step": 2682 }, { "epoch": 0.30803673938002296, "grad_norm": 0.18279534578323364, "learning_rate": 2.707047951379513e-06, "loss": 0.2336, "step": 2683 }, { "epoch": 0.3081515499425947, "grad_norm": 0.17892611026763916, "learning_rate": 2.6902424280588026e-06, "loss": 0.2379, "step": 2684 }, { "epoch": 0.3082663605051665, "grad_norm": 0.18422634899616241, "learning_rate": 2.6734874167416536e-06, "loss": 0.2466, "step": 2685 }, { "epoch": 0.3083811710677382, "grad_norm": 0.1868341863155365, "learning_rate": 2.656782940111935e-06, "loss": 0.25, "step": 2686 }, { "epoch": 0.30849598163031, "grad_norm": 0.1884702444076538, "learning_rate": 2.640129020785072e-06, "loss": 0.2425, "step": 2687 }, { "epoch": 0.30861079219288173, "grad_norm": 0.5080316066741943, "learning_rate": 2.623525681308059e-06, "loss": 0.2415, "step": 2688 }, { "epoch": 0.3087256027554535, "grad_norm": 0.1834314614534378, "learning_rate": 2.6069729441594225e-06, "loss": 0.2462, "step": 2689 }, { "epoch": 0.30884041331802525, "grad_norm": 0.2328319102525711, "learning_rate": 2.590470831749161e-06, "loss": 0.249, "step": 2690 }, { "epoch": 0.30895522388059704, "grad_norm": 0.18995451927185059, "learning_rate": 2.574019366418745e-06, "loss": 0.2398, "step": 2691 }, { "epoch": 0.3090700344431688, "grad_norm": 0.18372906744480133, "learning_rate": 2.5576185704410692e-06, "loss": 0.2376, "step": 2692 }, { "epoch": 0.3091848450057405, "grad_norm": 0.20205684006214142, "learning_rate": 2.5412684660204434e-06, "loss": 0.2332, "step": 2693 }, { "epoch": 0.3092996555683123, "grad_norm": 0.18738263845443726, "learning_rate": 2.5249690752925293e-06, "loss": 0.2479, "step": 2694 }, { "epoch": 0.309414466130884, "grad_norm": 0.17842596769332886, "learning_rate": 2.5087204203243422e-06, "loss": 0.2288, "step": 2695 }, { "epoch": 0.3095292766934558, "grad_norm": 0.18149890005588531, "learning_rate": 2.492522523114209e-06, "loss": 0.2358, "step": 2696 }, { "epoch": 0.30964408725602754, "grad_norm": 0.1896463930606842, "learning_rate": 2.476375405591727e-06, "loss": 0.2446, "step": 2697 }, { "epoch": 0.30975889781859933, "grad_norm": 0.1971805840730667, "learning_rate": 2.460279089617763e-06, "loss": 0.2478, "step": 2698 }, { "epoch": 0.30987370838117106, "grad_norm": 0.2001587450504303, "learning_rate": 2.4442335969843935e-06, "loss": 0.2548, "step": 2699 }, { "epoch": 0.3099885189437428, "grad_norm": 0.18204306066036224, "learning_rate": 2.4282389494148806e-06, "loss": 0.2532, "step": 2700 }, { "epoch": 0.3101033295063146, "grad_norm": 0.1858568638563156, "learning_rate": 2.4122951685636674e-06, "loss": 0.2373, "step": 2701 }, { "epoch": 0.3102181400688863, "grad_norm": 0.18342573940753937, "learning_rate": 2.3964022760163188e-06, "loss": 0.2309, "step": 2702 }, { "epoch": 0.3103329506314581, "grad_norm": 0.1855686902999878, "learning_rate": 2.3805602932895065e-06, "loss": 0.2305, "step": 2703 }, { "epoch": 0.31044776119402984, "grad_norm": 0.1889682114124298, "learning_rate": 2.364769241830982e-06, "loss": 0.2403, "step": 2704 }, { "epoch": 0.3105625717566016, "grad_norm": 0.1771862655878067, "learning_rate": 2.3490291430195413e-06, "loss": 0.2314, "step": 2705 }, { "epoch": 0.31067738231917336, "grad_norm": 0.1821395456790924, "learning_rate": 2.3333400181649913e-06, "loss": 0.2354, "step": 2706 }, { "epoch": 0.31079219288174514, "grad_norm": 0.18406909704208374, "learning_rate": 2.3177018885081324e-06, "loss": 0.252, "step": 2707 }, { "epoch": 0.3109070034443169, "grad_norm": 0.1832033097743988, "learning_rate": 2.302114775220732e-06, "loss": 0.2576, "step": 2708 }, { "epoch": 0.3110218140068886, "grad_norm": 0.18553754687309265, "learning_rate": 2.2865786994054727e-06, "loss": 0.2522, "step": 2709 }, { "epoch": 0.3111366245694604, "grad_norm": 0.18985991179943085, "learning_rate": 2.2710936820959615e-06, "loss": 0.2556, "step": 2710 }, { "epoch": 0.31125143513203213, "grad_norm": 0.18567496538162231, "learning_rate": 2.25565974425666e-06, "loss": 0.2432, "step": 2711 }, { "epoch": 0.3113662456946039, "grad_norm": 0.2862456440925598, "learning_rate": 2.240276906782883e-06, "loss": 0.2198, "step": 2712 }, { "epoch": 0.31148105625717565, "grad_norm": 0.1821151226758957, "learning_rate": 2.2249451905007603e-06, "loss": 0.2448, "step": 2713 }, { "epoch": 0.31159586681974744, "grad_norm": 0.17228983342647552, "learning_rate": 2.2096646161672155e-06, "loss": 0.2117, "step": 2714 }, { "epoch": 0.31171067738231917, "grad_norm": 0.18659812211990356, "learning_rate": 2.19443520446994e-06, "loss": 0.2429, "step": 2715 }, { "epoch": 0.31182548794489096, "grad_norm": 0.1929660439491272, "learning_rate": 2.1792569760273264e-06, "loss": 0.2562, "step": 2716 }, { "epoch": 0.3119402985074627, "grad_norm": 0.1881246417760849, "learning_rate": 2.1641299513885184e-06, "loss": 0.2489, "step": 2717 }, { "epoch": 0.3120551090700344, "grad_norm": 0.17231397330760956, "learning_rate": 2.149054151033312e-06, "loss": 0.2347, "step": 2718 }, { "epoch": 0.3121699196326062, "grad_norm": 0.17244410514831543, "learning_rate": 2.134029595372149e-06, "loss": 0.2342, "step": 2719 }, { "epoch": 0.31228473019517794, "grad_norm": 0.18939551711082458, "learning_rate": 2.1190563047460968e-06, "loss": 0.2509, "step": 2720 }, { "epoch": 0.3123995407577497, "grad_norm": 0.17653538286685944, "learning_rate": 2.104134299426832e-06, "loss": 0.2242, "step": 2721 }, { "epoch": 0.31251435132032146, "grad_norm": 0.20009692013263702, "learning_rate": 2.0892635996165776e-06, "loss": 0.2752, "step": 2722 }, { "epoch": 0.31262916188289325, "grad_norm": 0.18486210703849792, "learning_rate": 2.0744442254481e-06, "loss": 0.2441, "step": 2723 }, { "epoch": 0.312743972445465, "grad_norm": 0.18641918897628784, "learning_rate": 2.059676196984701e-06, "loss": 0.245, "step": 2724 }, { "epoch": 0.31285878300803677, "grad_norm": 0.18721936643123627, "learning_rate": 2.044959534220139e-06, "loss": 0.2484, "step": 2725 }, { "epoch": 0.3129735935706085, "grad_norm": 0.17303980886936188, "learning_rate": 2.0302942570786446e-06, "loss": 0.2264, "step": 2726 }, { "epoch": 0.31308840413318023, "grad_norm": 0.18733254075050354, "learning_rate": 2.0156803854148775e-06, "loss": 0.2336, "step": 2727 }, { "epoch": 0.313203214695752, "grad_norm": 0.17730852961540222, "learning_rate": 2.001117939013906e-06, "loss": 0.219, "step": 2728 }, { "epoch": 0.31331802525832375, "grad_norm": 0.19426977634429932, "learning_rate": 1.9866069375911534e-06, "loss": 0.2537, "step": 2729 }, { "epoch": 0.31343283582089554, "grad_norm": 0.1911400407552719, "learning_rate": 1.972147400792439e-06, "loss": 0.2322, "step": 2730 }, { "epoch": 0.31354764638346727, "grad_norm": 0.17441432178020477, "learning_rate": 1.957739348193859e-06, "loss": 0.2232, "step": 2731 }, { "epoch": 0.31366245694603906, "grad_norm": 0.19522623717784882, "learning_rate": 1.9433827993018362e-06, "loss": 0.258, "step": 2732 }, { "epoch": 0.3137772675086108, "grad_norm": 0.17633239924907684, "learning_rate": 1.929077773553054e-06, "loss": 0.2407, "step": 2733 }, { "epoch": 0.3138920780711825, "grad_norm": 0.18658313155174255, "learning_rate": 1.9148242903144564e-06, "loss": 0.2327, "step": 2734 }, { "epoch": 0.3140068886337543, "grad_norm": 0.18381841480731964, "learning_rate": 1.900622368883176e-06, "loss": 0.2488, "step": 2735 }, { "epoch": 0.31412169919632604, "grad_norm": 0.20299437642097473, "learning_rate": 1.8864720284865523e-06, "loss": 0.2523, "step": 2736 }, { "epoch": 0.31423650975889783, "grad_norm": 0.20547111332416534, "learning_rate": 1.8723732882821233e-06, "loss": 0.2605, "step": 2737 }, { "epoch": 0.31435132032146956, "grad_norm": 0.18998290598392487, "learning_rate": 1.8583261673575093e-06, "loss": 0.2474, "step": 2738 }, { "epoch": 0.31446613088404135, "grad_norm": 0.18743565678596497, "learning_rate": 1.844330684730493e-06, "loss": 0.2519, "step": 2739 }, { "epoch": 0.3145809414466131, "grad_norm": 0.1848480999469757, "learning_rate": 1.8303868593489271e-06, "loss": 0.2584, "step": 2740 }, { "epoch": 0.31469575200918487, "grad_norm": 0.18184567987918854, "learning_rate": 1.8164947100907238e-06, "loss": 0.2476, "step": 2741 }, { "epoch": 0.3148105625717566, "grad_norm": 0.1874203085899353, "learning_rate": 1.8026542557638428e-06, "loss": 0.2459, "step": 2742 }, { "epoch": 0.31492537313432833, "grad_norm": 0.19573506712913513, "learning_rate": 1.788865515106255e-06, "loss": 0.2469, "step": 2743 }, { "epoch": 0.3150401836969001, "grad_norm": 0.18444962799549103, "learning_rate": 1.7751285067859126e-06, "loss": 0.2455, "step": 2744 }, { "epoch": 0.31515499425947185, "grad_norm": 0.2133086919784546, "learning_rate": 1.7614432494007339e-06, "loss": 0.2511, "step": 2745 }, { "epoch": 0.31526980482204364, "grad_norm": 0.1718040257692337, "learning_rate": 1.7478097614785827e-06, "loss": 0.2218, "step": 2746 }, { "epoch": 0.3153846153846154, "grad_norm": 0.22442878782749176, "learning_rate": 1.7342280614772144e-06, "loss": 0.2548, "step": 2747 }, { "epoch": 0.31549942594718716, "grad_norm": 0.19543562829494476, "learning_rate": 1.7206981677842849e-06, "loss": 0.2535, "step": 2748 }, { "epoch": 0.3156142365097589, "grad_norm": 0.1825868934392929, "learning_rate": 1.7072200987173105e-06, "loss": 0.2501, "step": 2749 }, { "epoch": 0.3157290470723307, "grad_norm": 0.18062713742256165, "learning_rate": 1.6937938725236413e-06, "loss": 0.2375, "step": 2750 }, { "epoch": 0.3158438576349024, "grad_norm": 0.18741266429424286, "learning_rate": 1.6804195073804442e-06, "loss": 0.2497, "step": 2751 }, { "epoch": 0.31595866819747415, "grad_norm": 0.28466325998306274, "learning_rate": 1.6670970213946703e-06, "loss": 0.2462, "step": 2752 }, { "epoch": 0.31607347876004593, "grad_norm": 0.18836840987205505, "learning_rate": 1.653826432603034e-06, "loss": 0.2477, "step": 2753 }, { "epoch": 0.31618828932261767, "grad_norm": 0.18226750195026398, "learning_rate": 1.6406077589719904e-06, "loss": 0.2439, "step": 2754 }, { "epoch": 0.31630309988518945, "grad_norm": 0.18522575497627258, "learning_rate": 1.6274410183976996e-06, "loss": 0.2528, "step": 2755 }, { "epoch": 0.3164179104477612, "grad_norm": 0.17853641510009766, "learning_rate": 1.6143262287060356e-06, "loss": 0.2335, "step": 2756 }, { "epoch": 0.316532721010333, "grad_norm": 0.18245971202850342, "learning_rate": 1.601263407652498e-06, "loss": 0.2408, "step": 2757 }, { "epoch": 0.3166475315729047, "grad_norm": 0.19040468335151672, "learning_rate": 1.5882525729222774e-06, "loss": 0.2535, "step": 2758 }, { "epoch": 0.31676234213547644, "grad_norm": 0.17793886363506317, "learning_rate": 1.5752937421301506e-06, "loss": 0.2415, "step": 2759 }, { "epoch": 0.3168771526980482, "grad_norm": 0.1835881620645523, "learning_rate": 1.5623869328204877e-06, "loss": 0.2371, "step": 2760 }, { "epoch": 0.31699196326061996, "grad_norm": 0.2531280517578125, "learning_rate": 1.5495321624672443e-06, "loss": 0.244, "step": 2761 }, { "epoch": 0.31710677382319175, "grad_norm": 0.1833093762397766, "learning_rate": 1.5367294484739259e-06, "loss": 0.2468, "step": 2762 }, { "epoch": 0.3172215843857635, "grad_norm": 0.18277713656425476, "learning_rate": 1.5239788081735297e-06, "loss": 0.2453, "step": 2763 }, { "epoch": 0.31733639494833527, "grad_norm": 0.185713991522789, "learning_rate": 1.5112802588285846e-06, "loss": 0.2443, "step": 2764 }, { "epoch": 0.317451205510907, "grad_norm": 0.1927078515291214, "learning_rate": 1.4986338176310945e-06, "loss": 0.2633, "step": 2765 }, { "epoch": 0.3175660160734788, "grad_norm": 0.18987587094306946, "learning_rate": 1.4860395017024964e-06, "loss": 0.2497, "step": 2766 }, { "epoch": 0.3176808266360505, "grad_norm": 0.18887755274772644, "learning_rate": 1.473497328093676e-06, "loss": 0.2443, "step": 2767 }, { "epoch": 0.31779563719862225, "grad_norm": 0.18460632860660553, "learning_rate": 1.461007313784908e-06, "loss": 0.2481, "step": 2768 }, { "epoch": 0.31791044776119404, "grad_norm": 0.18088479340076447, "learning_rate": 1.4485694756858793e-06, "loss": 0.2449, "step": 2769 }, { "epoch": 0.31802525832376577, "grad_norm": 0.20531754195690155, "learning_rate": 1.4361838306356e-06, "loss": 0.2567, "step": 2770 }, { "epoch": 0.31814006888633756, "grad_norm": 0.18744909763336182, "learning_rate": 1.423850395402444e-06, "loss": 0.2729, "step": 2771 }, { "epoch": 0.3182548794489093, "grad_norm": 0.177407905459404, "learning_rate": 1.4115691866840985e-06, "loss": 0.2397, "step": 2772 }, { "epoch": 0.3183696900114811, "grad_norm": 0.18538278341293335, "learning_rate": 1.3993402211075435e-06, "loss": 0.2553, "step": 2773 }, { "epoch": 0.3184845005740528, "grad_norm": 0.18891273438930511, "learning_rate": 1.3871635152290152e-06, "loss": 0.2506, "step": 2774 }, { "epoch": 0.3185993111366246, "grad_norm": 0.19658859074115753, "learning_rate": 1.3750390855340246e-06, "loss": 0.2513, "step": 2775 }, { "epoch": 0.31871412169919633, "grad_norm": 0.19287607073783875, "learning_rate": 1.3629669484372722e-06, "loss": 0.2178, "step": 2776 }, { "epoch": 0.31882893226176806, "grad_norm": 0.17982123792171478, "learning_rate": 1.350947120282693e-06, "loss": 0.2352, "step": 2777 }, { "epoch": 0.31894374282433985, "grad_norm": 0.1872231364250183, "learning_rate": 1.33897961734339e-06, "loss": 0.2402, "step": 2778 }, { "epoch": 0.3190585533869116, "grad_norm": 0.1919689029455185, "learning_rate": 1.327064455821625e-06, "loss": 0.2565, "step": 2779 }, { "epoch": 0.31917336394948337, "grad_norm": 0.18405365943908691, "learning_rate": 1.3152016518488052e-06, "loss": 0.243, "step": 2780 }, { "epoch": 0.3192881745120551, "grad_norm": 0.18658950924873352, "learning_rate": 1.3033912214854482e-06, "loss": 0.2499, "step": 2781 }, { "epoch": 0.3194029850746269, "grad_norm": 0.3847789466381073, "learning_rate": 1.2916331807211547e-06, "loss": 0.2345, "step": 2782 }, { "epoch": 0.3195177956371986, "grad_norm": 0.18508552014827728, "learning_rate": 1.279927545474613e-06, "loss": 0.2458, "step": 2783 }, { "epoch": 0.31963260619977035, "grad_norm": 0.1826799362897873, "learning_rate": 1.2682743315935598e-06, "loss": 0.2542, "step": 2784 }, { "epoch": 0.31974741676234214, "grad_norm": 0.1758868247270584, "learning_rate": 1.256673554854757e-06, "loss": 0.2308, "step": 2785 }, { "epoch": 0.3198622273249139, "grad_norm": 0.1787307858467102, "learning_rate": 1.2451252309639705e-06, "loss": 0.2241, "step": 2786 }, { "epoch": 0.31997703788748566, "grad_norm": 0.18295878171920776, "learning_rate": 1.2336293755559559e-06, "loss": 0.2408, "step": 2787 }, { "epoch": 0.3200918484500574, "grad_norm": 0.18470624089241028, "learning_rate": 1.2221860041944455e-06, "loss": 0.2519, "step": 2788 }, { "epoch": 0.3202066590126292, "grad_norm": 0.1831522434949875, "learning_rate": 1.2107951323720957e-06, "loss": 0.2428, "step": 2789 }, { "epoch": 0.3203214695752009, "grad_norm": 0.34080228209495544, "learning_rate": 1.1994567755104946e-06, "loss": 0.2429, "step": 2790 }, { "epoch": 0.3204362801377727, "grad_norm": 0.18621386587619781, "learning_rate": 1.1881709489601413e-06, "loss": 0.236, "step": 2791 }, { "epoch": 0.32055109070034443, "grad_norm": 0.1841604858636856, "learning_rate": 1.176937668000404e-06, "loss": 0.2523, "step": 2792 }, { "epoch": 0.32066590126291616, "grad_norm": 0.18871618807315826, "learning_rate": 1.1657569478395182e-06, "loss": 0.2533, "step": 2793 }, { "epoch": 0.32078071182548795, "grad_norm": 0.18423044681549072, "learning_rate": 1.1546288036145615e-06, "loss": 0.2467, "step": 2794 }, { "epoch": 0.3208955223880597, "grad_norm": 0.1851445436477661, "learning_rate": 1.1435532503914205e-06, "loss": 0.2528, "step": 2795 }, { "epoch": 0.32101033295063147, "grad_norm": 0.1905590295791626, "learning_rate": 1.132530303164794e-06, "loss": 0.2619, "step": 2796 }, { "epoch": 0.3211251435132032, "grad_norm": 0.2519128620624542, "learning_rate": 1.121559976858153e-06, "loss": 0.2345, "step": 2797 }, { "epoch": 0.321239954075775, "grad_norm": 0.1805129498243332, "learning_rate": 1.1106422863237287e-06, "loss": 0.2401, "step": 2798 }, { "epoch": 0.3213547646383467, "grad_norm": 0.19262169301509857, "learning_rate": 1.0997772463424928e-06, "loss": 0.2578, "step": 2799 }, { "epoch": 0.3214695752009185, "grad_norm": 0.18384303152561188, "learning_rate": 1.0889648716241407e-06, "loss": 0.2471, "step": 2800 }, { "epoch": 0.32158438576349024, "grad_norm": 0.18114158511161804, "learning_rate": 1.0782051768070477e-06, "loss": 0.2372, "step": 2801 }, { "epoch": 0.321699196326062, "grad_norm": 0.2257944643497467, "learning_rate": 1.0674981764582902e-06, "loss": 0.249, "step": 2802 }, { "epoch": 0.32181400688863376, "grad_norm": 0.18819613754749298, "learning_rate": 1.0568438850735886e-06, "loss": 0.2524, "step": 2803 }, { "epoch": 0.3219288174512055, "grad_norm": 0.18267865478992462, "learning_rate": 1.0462423170773194e-06, "loss": 0.2439, "step": 2804 }, { "epoch": 0.3220436280137773, "grad_norm": 0.18363390862941742, "learning_rate": 1.0356934868224512e-06, "loss": 0.2382, "step": 2805 }, { "epoch": 0.322158438576349, "grad_norm": 0.18558350205421448, "learning_rate": 1.0251974085905946e-06, "loss": 0.2435, "step": 2806 }, { "epoch": 0.3222732491389208, "grad_norm": 0.17917074263095856, "learning_rate": 1.0147540965918945e-06, "loss": 0.2304, "step": 2807 }, { "epoch": 0.32238805970149254, "grad_norm": 0.18304049968719482, "learning_rate": 1.0043635649650984e-06, "loss": 0.2467, "step": 2808 }, { "epoch": 0.32250287026406427, "grad_norm": 0.18433739244937897, "learning_rate": 9.940258277774694e-07, "loss": 0.2379, "step": 2809 }, { "epoch": 0.32261768082663606, "grad_norm": 0.17700108885765076, "learning_rate": 9.837408990248166e-07, "loss": 0.2439, "step": 2810 }, { "epoch": 0.3227324913892078, "grad_norm": 0.1805577278137207, "learning_rate": 9.735087926314324e-07, "loss": 0.2508, "step": 2811 }, { "epoch": 0.3228473019517796, "grad_norm": 0.1818453073501587, "learning_rate": 9.633295224501026e-07, "loss": 0.2548, "step": 2812 }, { "epoch": 0.3229621125143513, "grad_norm": 0.17248715460300446, "learning_rate": 9.532031022620969e-07, "loss": 0.2331, "step": 2813 }, { "epoch": 0.3230769230769231, "grad_norm": 0.1780429184436798, "learning_rate": 9.431295457771105e-07, "loss": 0.2377, "step": 2814 }, { "epoch": 0.3231917336394948, "grad_norm": 0.19073565304279327, "learning_rate": 9.331088666332832e-07, "loss": 0.2609, "step": 2815 }, { "epoch": 0.3233065442020666, "grad_norm": 0.1792813390493393, "learning_rate": 9.231410783971628e-07, "loss": 0.2269, "step": 2816 }, { "epoch": 0.32342135476463835, "grad_norm": 0.19864891469478607, "learning_rate": 9.132261945636833e-07, "loss": 0.2601, "step": 2817 }, { "epoch": 0.3235361653272101, "grad_norm": 0.2041674107313156, "learning_rate": 9.033642285561651e-07, "loss": 0.278, "step": 2818 }, { "epoch": 0.32365097588978187, "grad_norm": 0.17795152962207794, "learning_rate": 8.935551937262788e-07, "loss": 0.2301, "step": 2819 }, { "epoch": 0.3237657864523536, "grad_norm": 0.17351852357387543, "learning_rate": 8.837991033540416e-07, "loss": 0.2233, "step": 2820 }, { "epoch": 0.3238805970149254, "grad_norm": 0.17930138111114502, "learning_rate": 8.740959706477725e-07, "loss": 0.2274, "step": 2821 }, { "epoch": 0.3239954075774971, "grad_norm": 0.17941948771476746, "learning_rate": 8.644458087441232e-07, "loss": 0.2389, "step": 2822 }, { "epoch": 0.3241102181400689, "grad_norm": 0.1800134778022766, "learning_rate": 8.548486307080028e-07, "loss": 0.2316, "step": 2823 }, { "epoch": 0.32422502870264064, "grad_norm": 0.2071455717086792, "learning_rate": 8.453044495326002e-07, "loss": 0.2234, "step": 2824 }, { "epoch": 0.3243398392652124, "grad_norm": 0.2175503373146057, "learning_rate": 8.358132781393568e-07, "loss": 0.2426, "step": 2825 }, { "epoch": 0.32445464982778416, "grad_norm": 0.17913947999477386, "learning_rate": 8.263751293779409e-07, "loss": 0.2469, "step": 2826 }, { "epoch": 0.3245694603903559, "grad_norm": 0.1870780736207962, "learning_rate": 8.169900160262379e-07, "loss": 0.2502, "step": 2827 }, { "epoch": 0.3246842709529277, "grad_norm": 0.1850549578666687, "learning_rate": 8.076579507903326e-07, "loss": 0.2639, "step": 2828 }, { "epoch": 0.3247990815154994, "grad_norm": 0.17258904874324799, "learning_rate": 7.983789463044877e-07, "loss": 0.2262, "step": 2829 }, { "epoch": 0.3249138920780712, "grad_norm": 0.1850084662437439, "learning_rate": 7.891530151311299e-07, "loss": 0.2331, "step": 2830 }, { "epoch": 0.32502870264064293, "grad_norm": 0.17884351313114166, "learning_rate": 7.799801697608278e-07, "loss": 0.2437, "step": 2831 }, { "epoch": 0.3251435132032147, "grad_norm": 0.17453505098819733, "learning_rate": 7.708604226122962e-07, "loss": 0.2326, "step": 2832 }, { "epoch": 0.32525832376578645, "grad_norm": 0.19249948859214783, "learning_rate": 7.617937860323387e-07, "loss": 0.2453, "step": 2833 }, { "epoch": 0.3253731343283582, "grad_norm": 0.19874277710914612, "learning_rate": 7.527802722958699e-07, "loss": 0.2447, "step": 2834 }, { "epoch": 0.32548794489092997, "grad_norm": 0.1794566810131073, "learning_rate": 7.438198936058927e-07, "loss": 0.2364, "step": 2835 }, { "epoch": 0.3256027554535017, "grad_norm": 0.18160340189933777, "learning_rate": 7.34912662093441e-07, "loss": 0.2512, "step": 2836 }, { "epoch": 0.3257175660160735, "grad_norm": 0.19052354991436005, "learning_rate": 7.260585898176331e-07, "loss": 0.2694, "step": 2837 }, { "epoch": 0.3258323765786452, "grad_norm": 0.18242764472961426, "learning_rate": 7.172576887655868e-07, "loss": 0.2415, "step": 2838 }, { "epoch": 0.325947187141217, "grad_norm": 0.1825741082429886, "learning_rate": 7.085099708524557e-07, "loss": 0.2499, "step": 2839 }, { "epoch": 0.32606199770378874, "grad_norm": 0.18134693801403046, "learning_rate": 6.998154479213703e-07, "loss": 0.2393, "step": 2840 }, { "epoch": 0.32617680826636053, "grad_norm": 0.17780378460884094, "learning_rate": 6.911741317434706e-07, "loss": 0.235, "step": 2841 }, { "epoch": 0.32629161882893226, "grad_norm": 0.18057462573051453, "learning_rate": 6.825860340178336e-07, "loss": 0.2441, "step": 2842 }, { "epoch": 0.326406429391504, "grad_norm": 0.1802562177181244, "learning_rate": 6.74051166371501e-07, "loss": 0.2519, "step": 2843 }, { "epoch": 0.3265212399540758, "grad_norm": 0.17685280740261078, "learning_rate": 6.655695403594475e-07, "loss": 0.2316, "step": 2844 }, { "epoch": 0.3266360505166475, "grad_norm": 0.1842121034860611, "learning_rate": 6.571411674645678e-07, "loss": 0.235, "step": 2845 }, { "epoch": 0.3267508610792193, "grad_norm": 0.1922702044248581, "learning_rate": 6.487660590976497e-07, "loss": 0.2422, "step": 2846 }, { "epoch": 0.32686567164179103, "grad_norm": 0.18128570914268494, "learning_rate": 6.404442265973832e-07, "loss": 0.2399, "step": 2847 }, { "epoch": 0.3269804822043628, "grad_norm": 0.1824776977300644, "learning_rate": 6.321756812303248e-07, "loss": 0.2518, "step": 2848 }, { "epoch": 0.32709529276693455, "grad_norm": 0.19338777661323547, "learning_rate": 6.239604341908801e-07, "loss": 0.2277, "step": 2849 }, { "epoch": 0.32721010332950634, "grad_norm": 0.19206656515598297, "learning_rate": 6.157984966013031e-07, "loss": 0.2263, "step": 2850 }, { "epoch": 0.3273249138920781, "grad_norm": 0.17170564830303192, "learning_rate": 6.076898795116792e-07, "loss": 0.2259, "step": 2851 }, { "epoch": 0.3274397244546498, "grad_norm": 0.18664321303367615, "learning_rate": 5.996345938998982e-07, "loss": 0.2492, "step": 2852 }, { "epoch": 0.3275545350172216, "grad_norm": 0.18105246126651764, "learning_rate": 5.916326506716407e-07, "loss": 0.2433, "step": 2853 }, { "epoch": 0.3276693455797933, "grad_norm": 0.17979462444782257, "learning_rate": 5.836840606603967e-07, "loss": 0.225, "step": 2854 }, { "epoch": 0.3277841561423651, "grad_norm": 0.20780827105045319, "learning_rate": 5.757888346273887e-07, "loss": 0.2514, "step": 2855 }, { "epoch": 0.32789896670493685, "grad_norm": 0.6133733987808228, "learning_rate": 5.679469832616136e-07, "loss": 0.2628, "step": 2856 }, { "epoch": 0.32801377726750863, "grad_norm": 0.18544229865074158, "learning_rate": 5.601585171798052e-07, "loss": 0.244, "step": 2857 }, { "epoch": 0.32812858783008036, "grad_norm": 0.17798718810081482, "learning_rate": 5.52423446926409e-07, "loss": 0.2221, "step": 2858 }, { "epoch": 0.3282433983926521, "grad_norm": 0.17798453569412231, "learning_rate": 5.44741782973599e-07, "loss": 0.2374, "step": 2859 }, { "epoch": 0.3283582089552239, "grad_norm": 0.18027743697166443, "learning_rate": 5.371135357212253e-07, "loss": 0.2339, "step": 2860 }, { "epoch": 0.3284730195177956, "grad_norm": 0.1857730746269226, "learning_rate": 5.295387154968312e-07, "loss": 0.2519, "step": 2861 }, { "epoch": 0.3285878300803674, "grad_norm": 0.1926034390926361, "learning_rate": 5.22017332555631e-07, "loss": 0.263, "step": 2862 }, { "epoch": 0.32870264064293914, "grad_norm": 0.18447072803974152, "learning_rate": 5.145493970804837e-07, "loss": 0.2541, "step": 2863 }, { "epoch": 0.3288174512055109, "grad_norm": 0.1809004545211792, "learning_rate": 5.07134919181893e-07, "loss": 0.2434, "step": 2864 }, { "epoch": 0.32893226176808266, "grad_norm": 0.18416014313697815, "learning_rate": 4.997739088979803e-07, "loss": 0.2432, "step": 2865 }, { "epoch": 0.32904707233065444, "grad_norm": 0.1689436435699463, "learning_rate": 4.924663761944936e-07, "loss": 0.2268, "step": 2866 }, { "epoch": 0.3291618828932262, "grad_norm": 0.2913152575492859, "learning_rate": 4.852123309647683e-07, "loss": 0.2356, "step": 2867 }, { "epoch": 0.3292766934557979, "grad_norm": 0.1735934466123581, "learning_rate": 4.780117830297349e-07, "loss": 0.2273, "step": 2868 }, { "epoch": 0.3293915040183697, "grad_norm": 0.19994190335273743, "learning_rate": 4.7086474213788867e-07, "loss": 0.2633, "step": 2869 }, { "epoch": 0.32950631458094143, "grad_norm": 0.18204596638679504, "learning_rate": 4.637712179652898e-07, "loss": 0.2286, "step": 2870 }, { "epoch": 0.3296211251435132, "grad_norm": 0.1716759204864502, "learning_rate": 4.5673122011553605e-07, "loss": 0.2187, "step": 2871 }, { "epoch": 0.32973593570608495, "grad_norm": 0.17687074840068817, "learning_rate": 4.497447581197678e-07, "loss": 0.2321, "step": 2872 }, { "epoch": 0.32985074626865674, "grad_norm": 0.2345241904258728, "learning_rate": 4.4281184143664113e-07, "loss": 0.2435, "step": 2873 }, { "epoch": 0.32996555683122847, "grad_norm": 0.19539380073547363, "learning_rate": 4.35932479452319e-07, "loss": 0.2579, "step": 2874 }, { "epoch": 0.33008036739380026, "grad_norm": 0.1730802357196808, "learning_rate": 4.291066814804667e-07, "loss": 0.2256, "step": 2875 }, { "epoch": 0.330195177956372, "grad_norm": 0.17262980341911316, "learning_rate": 4.223344567622212e-07, "loss": 0.227, "step": 2876 }, { "epoch": 0.3303099885189437, "grad_norm": 0.19441501796245575, "learning_rate": 4.156158144661904e-07, "loss": 0.2565, "step": 2877 }, { "epoch": 0.3304247990815155, "grad_norm": 0.1869421899318695, "learning_rate": 4.0895076368844046e-07, "loss": 0.2517, "step": 2878 }, { "epoch": 0.33053960964408724, "grad_norm": 0.17931365966796875, "learning_rate": 4.023393134524911e-07, "loss": 0.2475, "step": 2879 }, { "epoch": 0.330654420206659, "grad_norm": 0.1855170726776123, "learning_rate": 3.9578147270928904e-07, "loss": 0.2363, "step": 2880 }, { "epoch": 0.33076923076923076, "grad_norm": 0.20608702301979065, "learning_rate": 3.8927725033718553e-07, "loss": 0.2428, "step": 2881 }, { "epoch": 0.33088404133180255, "grad_norm": 0.18284235894680023, "learning_rate": 3.828266551419724e-07, "loss": 0.2276, "step": 2882 }, { "epoch": 0.3309988518943743, "grad_norm": 0.1773887425661087, "learning_rate": 3.7642969585681035e-07, "loss": 0.2359, "step": 2883 }, { "epoch": 0.331113662456946, "grad_norm": 0.2169237583875656, "learning_rate": 3.7008638114225617e-07, "loss": 0.2521, "step": 2884 }, { "epoch": 0.3312284730195178, "grad_norm": 0.17169393599033356, "learning_rate": 3.637967195862402e-07, "loss": 0.2267, "step": 2885 }, { "epoch": 0.33134328358208953, "grad_norm": 0.18125705420970917, "learning_rate": 3.5756071970405315e-07, "loss": 0.2436, "step": 2886 }, { "epoch": 0.3314580941446613, "grad_norm": 0.18686234951019287, "learning_rate": 3.513783899383327e-07, "loss": 0.2486, "step": 2887 }, { "epoch": 0.33157290470723305, "grad_norm": 0.1728992909193039, "learning_rate": 3.4524973865905474e-07, "loss": 0.2191, "step": 2888 }, { "epoch": 0.33168771526980484, "grad_norm": 0.17301568388938904, "learning_rate": 3.3917477416353315e-07, "loss": 0.2343, "step": 2889 }, { "epoch": 0.33180252583237657, "grad_norm": 0.19046413898468018, "learning_rate": 3.331535046763845e-07, "loss": 0.2262, "step": 2890 }, { "epoch": 0.33191733639494836, "grad_norm": 0.1667308360338211, "learning_rate": 3.2718593834953237e-07, "loss": 0.2216, "step": 2891 }, { "epoch": 0.3320321469575201, "grad_norm": 0.16964060068130493, "learning_rate": 3.212720832621985e-07, "loss": 0.2241, "step": 2892 }, { "epoch": 0.3321469575200918, "grad_norm": 0.1844148188829422, "learning_rate": 3.154119474208894e-07, "loss": 0.2482, "step": 2893 }, { "epoch": 0.3322617680826636, "grad_norm": 0.1847205013036728, "learning_rate": 3.0960553875936995e-07, "loss": 0.2533, "step": 2894 }, { "epoch": 0.33237657864523534, "grad_norm": 0.18115286529064178, "learning_rate": 3.0385286513868516e-07, "loss": 0.2343, "step": 2895 }, { "epoch": 0.33249138920780713, "grad_norm": 0.18464383482933044, "learning_rate": 2.981539343471207e-07, "loss": 0.2433, "step": 2896 }, { "epoch": 0.33260619977037886, "grad_norm": 0.17313051223754883, "learning_rate": 2.925087541001936e-07, "loss": 0.2296, "step": 2897 }, { "epoch": 0.33272101033295065, "grad_norm": 0.17917315661907196, "learning_rate": 2.869173320406704e-07, "loss": 0.2453, "step": 2898 }, { "epoch": 0.3328358208955224, "grad_norm": 0.18540658056735992, "learning_rate": 2.8137967573852234e-07, "loss": 0.2417, "step": 2899 }, { "epoch": 0.33295063145809417, "grad_norm": 0.18313151597976685, "learning_rate": 2.7589579269093003e-07, "loss": 0.2431, "step": 2900 }, { "epoch": 0.3330654420206659, "grad_norm": 0.187064066529274, "learning_rate": 2.704656903222791e-07, "loss": 0.2473, "step": 2901 }, { "epoch": 0.33318025258323763, "grad_norm": 0.17409101128578186, "learning_rate": 2.650893759841422e-07, "loss": 0.2346, "step": 2902 }, { "epoch": 0.3332950631458094, "grad_norm": 0.19003014266490936, "learning_rate": 2.5976685695527024e-07, "loss": 0.2586, "step": 2903 }, { "epoch": 0.33340987370838115, "grad_norm": 0.1796194612979889, "learning_rate": 2.544981404415747e-07, "loss": 0.2435, "step": 2904 }, { "epoch": 0.33352468427095294, "grad_norm": 0.18074390292167664, "learning_rate": 2.4928323357614524e-07, "loss": 0.2419, "step": 2905 }, { "epoch": 0.3336394948335247, "grad_norm": 0.18902379274368286, "learning_rate": 2.4412214341920093e-07, "loss": 0.2667, "step": 2906 }, { "epoch": 0.33375430539609646, "grad_norm": 0.1781543493270874, "learning_rate": 2.3901487695811684e-07, "loss": 0.2436, "step": 2907 }, { "epoch": 0.3338691159586682, "grad_norm": 0.19075490534305573, "learning_rate": 2.3396144110738427e-07, "loss": 0.2521, "step": 2908 }, { "epoch": 0.3339839265212399, "grad_norm": 0.17707423865795135, "learning_rate": 2.289618427086282e-07, "loss": 0.2408, "step": 2909 }, { "epoch": 0.3340987370838117, "grad_norm": 0.18497249484062195, "learning_rate": 2.2401608853057645e-07, "loss": 0.2501, "step": 2910 }, { "epoch": 0.33421354764638345, "grad_norm": 0.2943154573440552, "learning_rate": 2.1912418526906841e-07, "loss": 0.2569, "step": 2911 }, { "epoch": 0.33432835820895523, "grad_norm": 0.17896825075149536, "learning_rate": 2.1428613954702414e-07, "loss": 0.2363, "step": 2912 }, { "epoch": 0.33444316877152697, "grad_norm": 0.17906051874160767, "learning_rate": 2.0950195791446637e-07, "loss": 0.2419, "step": 2913 }, { "epoch": 0.33455797933409875, "grad_norm": 0.18069498240947723, "learning_rate": 2.0477164684847173e-07, "loss": 0.244, "step": 2914 }, { "epoch": 0.3346727898966705, "grad_norm": 0.18914857506752014, "learning_rate": 2.000952127532063e-07, "loss": 0.2596, "step": 2915 }, { "epoch": 0.3347876004592423, "grad_norm": 0.17821303009986877, "learning_rate": 1.954726619598768e-07, "loss": 0.2398, "step": 2916 }, { "epoch": 0.334902411021814, "grad_norm": 0.17520645260810852, "learning_rate": 1.9090400072675263e-07, "loss": 0.2224, "step": 2917 }, { "epoch": 0.33501722158438574, "grad_norm": 0.18755991756916046, "learning_rate": 1.86389235239135e-07, "loss": 0.2512, "step": 2918 }, { "epoch": 0.3351320321469575, "grad_norm": 0.4664475917816162, "learning_rate": 1.819283716093656e-07, "loss": 0.249, "step": 2919 }, { "epoch": 0.33524684270952926, "grad_norm": 0.1866346150636673, "learning_rate": 1.7752141587680016e-07, "loss": 0.2534, "step": 2920 }, { "epoch": 0.33536165327210105, "grad_norm": 0.18139131367206573, "learning_rate": 1.7316837400782604e-07, "loss": 0.2417, "step": 2921 }, { "epoch": 0.3354764638346728, "grad_norm": 0.21523842215538025, "learning_rate": 1.6886925189582237e-07, "loss": 0.2385, "step": 2922 }, { "epoch": 0.33559127439724457, "grad_norm": 0.18673475086688995, "learning_rate": 1.6462405536118665e-07, "loss": 0.271, "step": 2923 }, { "epoch": 0.3357060849598163, "grad_norm": 0.17725174129009247, "learning_rate": 1.6043279015129477e-07, "loss": 0.25, "step": 2924 }, { "epoch": 0.3358208955223881, "grad_norm": 0.17824560403823853, "learning_rate": 1.5629546194050993e-07, "loss": 0.2531, "step": 2925 }, { "epoch": 0.3359357060849598, "grad_norm": 0.18963828682899475, "learning_rate": 1.522120763301782e-07, "loss": 0.2689, "step": 2926 }, { "epoch": 0.33605051664753155, "grad_norm": 0.22846467792987823, "learning_rate": 1.4818263884861516e-07, "loss": 0.2451, "step": 2927 }, { "epoch": 0.33616532721010334, "grad_norm": 0.19012761116027832, "learning_rate": 1.4420715495108816e-07, "loss": 0.2487, "step": 2928 }, { "epoch": 0.33628013777267507, "grad_norm": 0.17997419834136963, "learning_rate": 1.402856300198252e-07, "loss": 0.2515, "step": 2929 }, { "epoch": 0.33639494833524686, "grad_norm": 0.1729002594947815, "learning_rate": 1.3641806936401049e-07, "loss": 0.2315, "step": 2930 }, { "epoch": 0.3365097588978186, "grad_norm": 0.19665226340293884, "learning_rate": 1.3260447821975775e-07, "loss": 0.2429, "step": 2931 }, { "epoch": 0.3366245694603904, "grad_norm": 0.18344591557979584, "learning_rate": 1.288448617501148e-07, "loss": 0.2481, "step": 2932 }, { "epoch": 0.3367393800229621, "grad_norm": 0.18950219452381134, "learning_rate": 1.2513922504505894e-07, "loss": 0.2434, "step": 2933 }, { "epoch": 0.33685419058553384, "grad_norm": 0.1903821974992752, "learning_rate": 1.214875731214793e-07, "loss": 0.251, "step": 2934 }, { "epoch": 0.33696900114810563, "grad_norm": 0.1710132658481598, "learning_rate": 1.1788991092319013e-07, "loss": 0.2307, "step": 2935 }, { "epoch": 0.33708381171067736, "grad_norm": 0.18124228715896606, "learning_rate": 1.1434624332090415e-07, "loss": 0.2603, "step": 2936 }, { "epoch": 0.33719862227324915, "grad_norm": 0.1810341477394104, "learning_rate": 1.1085657511223258e-07, "loss": 0.2283, "step": 2937 }, { "epoch": 0.3373134328358209, "grad_norm": 0.1782371997833252, "learning_rate": 1.0742091102167618e-07, "loss": 0.2377, "step": 2938 }, { "epoch": 0.33742824339839267, "grad_norm": 0.19403007626533508, "learning_rate": 1.0403925570062978e-07, "loss": 0.2508, "step": 2939 }, { "epoch": 0.3375430539609644, "grad_norm": 0.19140635430812836, "learning_rate": 1.0071161372736893e-07, "loss": 0.2734, "step": 2940 }, { "epoch": 0.3376578645235362, "grad_norm": 0.17850816249847412, "learning_rate": 9.74379896070321e-08, "loss": 0.2435, "step": 2941 }, { "epoch": 0.3377726750861079, "grad_norm": 0.1877817064523697, "learning_rate": 9.421838777162962e-08, "loss": 0.2437, "step": 2942 }, { "epoch": 0.33788748564867965, "grad_norm": 0.19458942115306854, "learning_rate": 9.105281258004362e-08, "loss": 0.2512, "step": 2943 }, { "epoch": 0.33800229621125144, "grad_norm": 0.5778592824935913, "learning_rate": 8.794126831800143e-08, "loss": 0.2444, "step": 2944 }, { "epoch": 0.3381171067738232, "grad_norm": 0.17636935412883759, "learning_rate": 8.488375919808001e-08, "loss": 0.2302, "step": 2945 }, { "epoch": 0.33823191733639496, "grad_norm": 0.1732562780380249, "learning_rate": 8.188028935970593e-08, "loss": 0.2273, "step": 2946 }, { "epoch": 0.3383467278989667, "grad_norm": 0.19003310799598694, "learning_rate": 7.893086286913764e-08, "loss": 0.2745, "step": 2947 }, { "epoch": 0.3384615384615385, "grad_norm": 0.16974294185638428, "learning_rate": 7.603548371947877e-08, "loss": 0.2272, "step": 2948 }, { "epoch": 0.3385763490241102, "grad_norm": 0.1850375086069107, "learning_rate": 7.319415583064704e-08, "loss": 0.2475, "step": 2949 }, { "epoch": 0.338691159586682, "grad_norm": 0.18297596275806427, "learning_rate": 7.040688304938758e-08, "loss": 0.2473, "step": 2950 }, { "epoch": 0.33880597014925373, "grad_norm": 0.1988867223262787, "learning_rate": 6.767366914927298e-08, "loss": 0.2429, "step": 2951 }, { "epoch": 0.33892078071182546, "grad_norm": 0.18325483798980713, "learning_rate": 6.499451783066768e-08, "loss": 0.2427, "step": 2952 }, { "epoch": 0.33903559127439725, "grad_norm": 0.18877427279949188, "learning_rate": 6.236943272075913e-08, "loss": 0.259, "step": 2953 }, { "epoch": 0.339150401836969, "grad_norm": 0.22190852463245392, "learning_rate": 5.979841737353553e-08, "loss": 0.243, "step": 2954 }, { "epoch": 0.33926521239954077, "grad_norm": 0.27941983938217163, "learning_rate": 5.7281475269772567e-08, "loss": 0.2533, "step": 2955 }, { "epoch": 0.3393800229621125, "grad_norm": 0.18430648744106293, "learning_rate": 5.481860981704668e-08, "loss": 0.2435, "step": 2956 }, { "epoch": 0.3394948335246843, "grad_norm": 0.17401239275932312, "learning_rate": 5.2409824349721747e-08, "loss": 0.2253, "step": 2957 }, { "epoch": 0.339609644087256, "grad_norm": 0.18754133582115173, "learning_rate": 5.00551221289447e-08, "loss": 0.2414, "step": 2958 }, { "epoch": 0.3397244546498278, "grad_norm": 0.17281067371368408, "learning_rate": 4.775450634264101e-08, "loss": 0.2326, "step": 2959 }, { "epoch": 0.33983926521239954, "grad_norm": 0.17908307909965515, "learning_rate": 4.5507980105505835e-08, "loss": 0.2161, "step": 2960 }, { "epoch": 0.3399540757749713, "grad_norm": 0.1749146282672882, "learning_rate": 4.331554645901737e-08, "loss": 0.2291, "step": 2961 }, { "epoch": 0.34006888633754306, "grad_norm": 0.1798166185617447, "learning_rate": 4.117720837141459e-08, "loss": 0.2517, "step": 2962 }, { "epoch": 0.3401836969001148, "grad_norm": 0.18746842443943024, "learning_rate": 3.909296873768842e-08, "loss": 0.2417, "step": 2963 }, { "epoch": 0.3402985074626866, "grad_norm": 0.19311566650867462, "learning_rate": 3.7062830379599454e-08, "loss": 0.2577, "step": 2964 }, { "epoch": 0.3404133180252583, "grad_norm": 0.1733102798461914, "learning_rate": 3.5086796045664674e-08, "loss": 0.234, "step": 2965 }, { "epoch": 0.3405281285878301, "grad_norm": 0.17950354516506195, "learning_rate": 3.316486841114852e-08, "loss": 0.2425, "step": 2966 }, { "epoch": 0.34064293915040184, "grad_norm": 0.1815367192029953, "learning_rate": 3.12970500780585e-08, "loss": 0.2368, "step": 2967 }, { "epoch": 0.34075774971297357, "grad_norm": 0.18568190932273865, "learning_rate": 2.9483343575154033e-08, "loss": 0.2541, "step": 2968 }, { "epoch": 0.34087256027554536, "grad_norm": 0.5942342877388, "learning_rate": 2.7723751357924268e-08, "loss": 0.2571, "step": 2969 }, { "epoch": 0.3409873708381171, "grad_norm": 0.1894172877073288, "learning_rate": 2.6018275808610272e-08, "loss": 0.2573, "step": 2970 }, { "epoch": 0.3411021814006889, "grad_norm": 0.18250656127929688, "learning_rate": 2.4366919236169518e-08, "loss": 0.2461, "step": 2971 }, { "epoch": 0.3412169919632606, "grad_norm": 0.19131872057914734, "learning_rate": 2.2769683876306958e-08, "loss": 0.2428, "step": 2972 }, { "epoch": 0.3413318025258324, "grad_norm": 0.18958744406700134, "learning_rate": 2.1226571891448388e-08, "loss": 0.2503, "step": 2973 }, { "epoch": 0.3414466130884041, "grad_norm": 0.1853991597890854, "learning_rate": 1.9737585370736002e-08, "loss": 0.2709, "step": 2974 }, { "epoch": 0.3415614236509759, "grad_norm": 0.18549253046512604, "learning_rate": 1.830272633005059e-08, "loss": 0.2514, "step": 2975 }, { "epoch": 0.34167623421354765, "grad_norm": 0.23898102343082428, "learning_rate": 1.6921996711976028e-08, "loss": 0.2464, "step": 2976 }, { "epoch": 0.3417910447761194, "grad_norm": 0.1883680820465088, "learning_rate": 1.559539838582591e-08, "loss": 0.2279, "step": 2977 }, { "epoch": 0.34190585533869117, "grad_norm": 7.0991129875183105, "learning_rate": 1.4322933147616902e-08, "loss": 0.3745, "step": 2978 }, { "epoch": 0.3420206659012629, "grad_norm": 0.1870366930961609, "learning_rate": 1.3104602720086512e-08, "loss": 0.2485, "step": 2979 }, { "epoch": 0.3421354764638347, "grad_norm": 0.17578932642936707, "learning_rate": 1.1940408752675326e-08, "loss": 0.2371, "step": 2980 }, { "epoch": 0.3422502870264064, "grad_norm": 0.1796652376651764, "learning_rate": 1.0830352821531442e-08, "loss": 0.2364, "step": 2981 }, { "epoch": 0.3423650975889782, "grad_norm": 0.18284156918525696, "learning_rate": 9.774436429514921e-09, "loss": 0.2551, "step": 2982 }, { "epoch": 0.34247990815154994, "grad_norm": 0.182993546128273, "learning_rate": 8.772661006180017e-09, "loss": 0.2453, "step": 2983 }, { "epoch": 0.3425947187141217, "grad_norm": 0.18078787624835968, "learning_rate": 7.825027907788496e-09, "loss": 0.2435, "step": 2984 }, { "epoch": 0.34270952927669346, "grad_norm": 0.18325120210647583, "learning_rate": 6.931538417291883e-09, "loss": 0.2477, "step": 2985 }, { "epoch": 0.3428243398392652, "grad_norm": 0.17932027578353882, "learning_rate": 6.092193744349217e-09, "loss": 0.2524, "step": 2986 }, { "epoch": 0.342939150401837, "grad_norm": 0.17661520838737488, "learning_rate": 5.306995025313733e-09, "loss": 0.2305, "step": 2987 }, { "epoch": 0.3430539609644087, "grad_norm": 0.18424822390079498, "learning_rate": 4.575943323228415e-09, "loss": 0.2617, "step": 2988 }, { "epoch": 0.3431687715269805, "grad_norm": 0.17638655006885529, "learning_rate": 3.899039627830448e-09, "loss": 0.235, "step": 2989 }, { "epoch": 0.34328358208955223, "grad_norm": 0.18207785487174988, "learning_rate": 3.276284855551204e-09, "loss": 0.2441, "step": 2990 }, { "epoch": 0.343398392652124, "grad_norm": 0.18294726312160492, "learning_rate": 2.7076798495118127e-09, "loss": 0.2507, "step": 2991 }, { "epoch": 0.34351320321469575, "grad_norm": 0.29683995246887207, "learning_rate": 2.1932253795142746e-09, "loss": 0.2624, "step": 2992 }, { "epoch": 0.3436280137772675, "grad_norm": 0.17832671105861664, "learning_rate": 1.7329221420636643e-09, "loss": 0.2395, "step": 2993 }, { "epoch": 0.34374282433983927, "grad_norm": 0.18761184811592102, "learning_rate": 1.3267707603370484e-09, "loss": 0.2542, "step": 2994 }, { "epoch": 0.343857634902411, "grad_norm": 0.2153715342283249, "learning_rate": 9.747717842101268e-10, "loss": 0.2647, "step": 2995 }, { "epoch": 0.3439724454649828, "grad_norm": 0.19582106173038483, "learning_rate": 6.769256902305898e-10, "loss": 0.2507, "step": 2996 }, { "epoch": 0.3440872560275545, "grad_norm": 0.1800156682729721, "learning_rate": 4.332328816492037e-10, "loss": 0.2384, "step": 2997 }, { "epoch": 0.3442020665901263, "grad_norm": 0.18992789089679718, "learning_rate": 2.436936883842833e-10, "loss": 0.2486, "step": 2998 }, { "epoch": 0.34431687715269804, "grad_norm": 0.17581433057785034, "learning_rate": 1.0830836704833758e-10, "loss": 0.238, "step": 2999 }, { "epoch": 0.34443168771526983, "grad_norm": 0.2037564516067505, "learning_rate": 2.7077100925865242e-11, "loss": 0.272, "step": 3000 }, { "epoch": 0.34443168771526983, "step": 3000, "total_flos": 3.429011909561549e+19, "train_loss": 0.27564545996983847, "train_runtime": 45365.0148, "train_samples_per_second": 2.116, "train_steps_per_second": 0.066 } ], "logging_steps": 1, "max_steps": 3000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.429011909561549e+19, "train_batch_size": 4, "trial_name": null, "trial_params": null }