diff --git "a/checkpoints/checkpoint-1000/trainer_state.json" "b/checkpoints/checkpoint-1000/trainer_state.json" --- "a/checkpoints/checkpoint-1000/trainer_state.json" +++ "b/checkpoints/checkpoint-1000/trainer_state.json" @@ -1,7 +1,7 @@ { "best_global_step": 1000, - "best_metric": 0.8388314247131348, - "best_model_checkpoint": "task2file/sft_devstral_24B_v2/checkpoints/checkpoint-1000", + "best_metric": 0.9487298727035522, + "best_model_checkpoint": "task2file/sft_qwen_14B_v2/checkpoints/checkpoint-1000", "epoch": 0.4219409282700422, "eval_steps": 100, "global_step": 1000, @@ -11,3582 +11,3582 @@ "log_history": [ { "epoch": 0.0008438818565400844, - "grad_norm": 1.597854733467102, - "learning_rate": 8.787346221441124e-08, - "loss": 1.3927901983261108, + "grad_norm": 0.5386583805084229, + "learning_rate": 1.7574692442882248e-07, + "loss": 1.6941628456115723, "step": 2 }, { "epoch": 0.0016877637130801688, - "grad_norm": 1.6547431945800781, - "learning_rate": 2.6362038664323375e-07, - "loss": 1.407160758972168, + "grad_norm": 0.5477277636528015, + "learning_rate": 5.272407732864675e-07, + "loss": 1.7132279872894287, "step": 4 }, { "epoch": 0.002531645569620253, - "grad_norm": 1.8221601247787476, - "learning_rate": 4.393673110720563e-07, - "loss": 1.376656174659729, + "grad_norm": 0.5390765070915222, + "learning_rate": 8.787346221441126e-07, + "loss": 1.641180396080017, "step": 6 }, { "epoch": 0.0033755274261603376, - "grad_norm": 1.4831048250198364, - "learning_rate": 6.151142355008788e-07, - "loss": 1.247712254524231, + "grad_norm": 0.5023683905601501, + "learning_rate": 1.2302284710017575e-06, + "loss": 1.5616240501403809, "step": 8 }, { "epoch": 0.004219409282700422, - "grad_norm": 1.668201208114624, - "learning_rate": 7.908611599297013e-07, - "loss": 1.2685163021087646, + "grad_norm": 0.4899154603481293, + "learning_rate": 1.5817223198594026e-06, + "loss": 1.572033405303955, "step": 10 }, { "epoch": 0.005063291139240506, - "grad_norm": 1.67417311668396, - "learning_rate": 9.666080843585237e-07, - "loss": 1.2942761182785034, + "grad_norm": 0.5239788293838501, + "learning_rate": 1.9332161687170474e-06, + "loss": 1.6242921352386475, "step": 12 }, { "epoch": 0.00590717299578059, - "grad_norm": 1.7154079675674438, - "learning_rate": 1.1423550087873463e-06, - "loss": 1.3638604879379272, + "grad_norm": 0.5172926783561707, + "learning_rate": 2.2847100175746925e-06, + "loss": 1.6800041198730469, "step": 14 }, { "epoch": 0.006751054852320675, - "grad_norm": 1.729427456855774, - "learning_rate": 1.3181019332161688e-06, - "loss": 1.3476728200912476, + "grad_norm": 0.5539224743843079, + "learning_rate": 2.6362038664323376e-06, + "loss": 1.6450834274291992, "step": 16 }, { "epoch": 0.007594936708860759, - "grad_norm": 1.3813447952270508, - "learning_rate": 1.4938488576449913e-06, - "loss": 1.3476393222808838, + "grad_norm": 0.5255337953567505, + "learning_rate": 2.9876977152899827e-06, + "loss": 1.6673263311386108, "step": 18 }, { "epoch": 0.008438818565400843, - "grad_norm": 1.557220458984375, - "learning_rate": 1.6695957820738139e-06, - "loss": 1.2449309825897217, + "grad_norm": 0.5074548721313477, + "learning_rate": 3.3391915641476277e-06, + "loss": 1.531802773475647, "step": 20 }, { "epoch": 0.009282700421940928, - "grad_norm": 1.1883500814437866, - "learning_rate": 1.8453427065026362e-06, - "loss": 1.3125361204147339, + "grad_norm": 0.4160279333591461, + "learning_rate": 3.6906854130052724e-06, + "loss": 1.599354863166809, "step": 22 }, { "epoch": 0.010126582278481013, - "grad_norm": 1.7290029525756836, - "learning_rate": 2.0210896309314587e-06, - "loss": 1.3724769353866577, + "grad_norm": 0.5716474652290344, + "learning_rate": 4.0421792618629174e-06, + "loss": 1.6700962781906128, "step": 24 }, { "epoch": 0.010970464135021098, - "grad_norm": 1.5627557039260864, - "learning_rate": 2.1968365553602812e-06, - "loss": 1.3401387929916382, + "grad_norm": 0.5148899555206299, + "learning_rate": 4.3936731107205625e-06, + "loss": 1.66217839717865, "step": 26 }, { "epoch": 0.01181434599156118, - "grad_norm": 1.796866774559021, - "learning_rate": 2.3725834797891038e-06, - "loss": 1.365437388420105, + "grad_norm": 0.575722336769104, + "learning_rate": 4.7451669595782076e-06, + "loss": 1.6692266464233398, "step": 28 }, { "epoch": 0.012658227848101266, - "grad_norm": 1.7030404806137085, - "learning_rate": 2.5483304042179263e-06, - "loss": 1.2706533670425415, + "grad_norm": 0.5345953106880188, + "learning_rate": 5.096660808435853e-06, + "loss": 1.5518689155578613, "step": 30 }, { "epoch": 0.01350210970464135, - "grad_norm": 1.3186293840408325, - "learning_rate": 2.724077328646749e-06, - "loss": 1.3084994554519653, + "grad_norm": 0.4462043344974518, + "learning_rate": 5.448154657293498e-06, + "loss": 1.5930007696151733, "step": 32 }, { "epoch": 0.014345991561181435, - "grad_norm": 1.5762513875961304, - "learning_rate": 2.8998242530755714e-06, - "loss": 1.3259696960449219, + "grad_norm": 0.5119605660438538, + "learning_rate": 5.799648506151143e-06, + "loss": 1.6069684028625488, "step": 34 }, { "epoch": 0.015189873417721518, - "grad_norm": 1.422295331954956, - "learning_rate": 3.075571177504394e-06, - "loss": 1.3205676078796387, + "grad_norm": 0.5328608751296997, + "learning_rate": 6.151142355008788e-06, + "loss": 1.5838109254837036, "step": 36 }, { "epoch": 0.016033755274261603, - "grad_norm": 1.495523452758789, - "learning_rate": 3.2513181019332165e-06, - "loss": 1.3740568161010742, + "grad_norm": 0.5065920352935791, + "learning_rate": 6.502636203866433e-06, + "loss": 1.608130931854248, "step": 38 }, { "epoch": 0.016877637130801686, - "grad_norm": 1.5112254619598389, - "learning_rate": 3.427065026362039e-06, - "loss": 1.321828842163086, + "grad_norm": 0.4479359984397888, + "learning_rate": 6.854130052724078e-06, + "loss": 1.5942182540893555, "step": 40 }, { "epoch": 0.017721518987341773, - "grad_norm": 1.4667807817459106, - "learning_rate": 3.602811950790861e-06, - "loss": 1.3673173189163208, + "grad_norm": 0.42844903469085693, + "learning_rate": 7.205623901581722e-06, + "loss": 1.6441553831100464, "step": 42 }, { "epoch": 0.018565400843881856, - "grad_norm": 1.6609723567962646, - "learning_rate": 3.7785588752196836e-06, - "loss": 1.3968093395233154, + "grad_norm": 0.476630836725235, + "learning_rate": 7.557117750439367e-06, + "loss": 1.6068111658096313, "step": 44 }, { "epoch": 0.019409282700421943, - "grad_norm": 1.59381103515625, - "learning_rate": 3.954305799648506e-06, - "loss": 1.4295302629470825, + "grad_norm": 0.4532654881477356, + "learning_rate": 7.908611599297012e-06, + "loss": 1.6618021726608276, "step": 46 }, { "epoch": 0.020253164556962026, - "grad_norm": 1.1470608711242676, - "learning_rate": 4.130052724077329e-06, - "loss": 1.2536572217941284, + "grad_norm": 0.3701118230819702, + "learning_rate": 8.260105448154657e-06, + "loss": 1.4730033874511719, "step": 48 }, { "epoch": 0.02109704641350211, - "grad_norm": 1.2014588117599487, - "learning_rate": 4.305799648506151e-06, - "loss": 1.242217779159546, + "grad_norm": 0.38471561670303345, + "learning_rate": 8.611599297012302e-06, + "loss": 1.4828267097473145, "step": 50 }, { "epoch": 0.021940928270042195, - "grad_norm": 1.2327464818954468, - "learning_rate": 4.481546572934974e-06, - "loss": 1.2166963815689087, + "grad_norm": 0.3602336347103119, + "learning_rate": 8.963093145869948e-06, + "loss": 1.3877452611923218, "step": 52 }, { "epoch": 0.02278481012658228, - "grad_norm": 1.9708983898162842, - "learning_rate": 4.657293497363796e-06, - "loss": 1.25709867477417, + "grad_norm": 0.40318572521209717, + "learning_rate": 9.314586994727593e-06, + "loss": 1.49052894115448, "step": 54 }, { "epoch": 0.02362869198312236, - "grad_norm": 1.180569052696228, - "learning_rate": 4.833040421792619e-06, - "loss": 1.2886158227920532, + "grad_norm": 0.3223826587200165, + "learning_rate": 9.666080843585238e-06, + "loss": 1.4912524223327637, "step": 56 }, { "epoch": 0.024472573839662448, - "grad_norm": 1.5029548406600952, - "learning_rate": 5.008787346221441e-06, - "loss": 1.29886794090271, + "grad_norm": 0.3873065114021301, + "learning_rate": 1.0017574692442883e-05, + "loss": 1.526674509048462, "step": 58 }, { "epoch": 0.02531645569620253, - "grad_norm": 1.5380216836929321, - "learning_rate": 5.184534270650264e-06, - "loss": 1.2387628555297852, + "grad_norm": 0.410159707069397, + "learning_rate": 1.0369068541300528e-05, + "loss": 1.4480271339416504, "step": 60 }, { "epoch": 0.026160337552742614, - "grad_norm": 1.572144865989685, - "learning_rate": 5.3602811950790864e-06, - "loss": 1.2177000045776367, + "grad_norm": 0.3632003962993622, + "learning_rate": 1.0720562390158173e-05, + "loss": 1.4222990274429321, "step": 62 }, { "epoch": 0.0270042194092827, - "grad_norm": 1.4882780313491821, - "learning_rate": 5.536028119507909e-06, - "loss": 1.181516170501709, + "grad_norm": 0.33118435740470886, + "learning_rate": 1.1072056239015818e-05, + "loss": 1.387171745300293, "step": 64 }, { "epoch": 0.027848101265822784, - "grad_norm": 1.2982488870620728, - "learning_rate": 5.7117750439367315e-06, - "loss": 1.2101733684539795, + "grad_norm": 0.3301764726638794, + "learning_rate": 1.1423550087873463e-05, + "loss": 1.3523777723312378, "step": 66 }, { "epoch": 0.02869198312236287, - "grad_norm": 1.5236955881118774, - "learning_rate": 5.887521968365554e-06, - "loss": 1.2277681827545166, + "grad_norm": 0.34342435002326965, + "learning_rate": 1.1775043936731108e-05, + "loss": 1.4515162706375122, "step": 68 }, { "epoch": 0.029535864978902954, - "grad_norm": 1.4521006345748901, - "learning_rate": 6.0632688927943766e-06, - "loss": 1.1688424348831177, + "grad_norm": 0.3243122100830078, + "learning_rate": 1.2126537785588753e-05, + "loss": 1.3509243726730347, "step": 70 }, { "epoch": 0.030379746835443037, - "grad_norm": 1.2352311611175537, - "learning_rate": 6.239015817223199e-06, - "loss": 1.273059368133545, + "grad_norm": 0.3450150787830353, + "learning_rate": 1.2478031634446398e-05, + "loss": 1.4936245679855347, "step": 72 }, { "epoch": 0.031223628691983123, - "grad_norm": 1.3438209295272827, - "learning_rate": 6.414762741652021e-06, - "loss": 1.1609034538269043, + "grad_norm": 0.38912028074264526, + "learning_rate": 1.2829525483304042e-05, + "loss": 1.3419109582901, "step": 74 }, { "epoch": 0.032067510548523206, - "grad_norm": 1.9009398221969604, - "learning_rate": 6.590509666080843e-06, - "loss": 1.2508260011672974, + "grad_norm": 0.3019310235977173, + "learning_rate": 1.3181019332161687e-05, + "loss": 1.4284154176712036, "step": 76 }, { "epoch": 0.03291139240506329, - "grad_norm": 1.6718412637710571, - "learning_rate": 6.766256590509666e-06, - "loss": 1.2524956464767456, + "grad_norm": 0.37803682684898376, + "learning_rate": 1.3532513181019332e-05, + "loss": 1.4256561994552612, "step": 78 }, { "epoch": 0.03375527426160337, - "grad_norm": 1.249891757965088, - "learning_rate": 6.942003514938488e-06, - "loss": 1.1472493410110474, + "grad_norm": 0.34191736578941345, + "learning_rate": 1.3884007029876977e-05, + "loss": 1.3256909847259521, "step": 80 }, { "epoch": 0.03459915611814346, - "grad_norm": 1.4398653507232666, - "learning_rate": 7.117750439367312e-06, - "loss": 1.0845389366149902, + "grad_norm": 0.35242700576782227, + "learning_rate": 1.4235500878734624e-05, + "loss": 1.2710685729980469, "step": 82 }, { "epoch": 0.035443037974683546, - "grad_norm": 1.3701167106628418, - "learning_rate": 7.293497363796134e-06, - "loss": 1.1088868379592896, + "grad_norm": 0.38094228506088257, + "learning_rate": 1.4586994727592269e-05, + "loss": 1.253411889076233, "step": 84 }, { "epoch": 0.036286919831223625, - "grad_norm": 1.277998924255371, - "learning_rate": 7.469244288224957e-06, - "loss": 1.1513772010803223, + "grad_norm": 0.36837366223335266, + "learning_rate": 1.4938488576449914e-05, + "loss": 1.3064342737197876, "step": 86 }, { "epoch": 0.03713080168776371, - "grad_norm": 1.4970002174377441, - "learning_rate": 7.644991212653779e-06, - "loss": 1.1385771036148071, + "grad_norm": 0.3443569242954254, + "learning_rate": 1.5289982425307557e-05, + "loss": 1.293562412261963, "step": 88 }, { "epoch": 0.0379746835443038, - "grad_norm": 1.3384218215942383, - "learning_rate": 7.820738137082601e-06, - "loss": 1.1632680892944336, + "grad_norm": 0.3799338936805725, + "learning_rate": 1.5641476274165202e-05, + "loss": 1.3382648229599, "step": 90 }, { "epoch": 0.038818565400843885, - "grad_norm": 1.4317446947097778, - "learning_rate": 7.996485061511425e-06, - "loss": 1.2256064414978027, + "grad_norm": 0.40501922369003296, + "learning_rate": 1.599297012302285e-05, + "loss": 1.3925724029541016, "step": 92 }, { "epoch": 0.039662447257383965, - "grad_norm": 1.8743640184402466, - "learning_rate": 8.172231985940246e-06, - "loss": 1.1935789585113525, + "grad_norm": 0.4419630467891693, + "learning_rate": 1.6344463971880492e-05, + "loss": 1.357171893119812, "step": 94 }, { "epoch": 0.04050632911392405, - "grad_norm": 1.4789546728134155, - "learning_rate": 8.347978910369069e-06, - "loss": 1.1429362297058105, + "grad_norm": 0.3619817793369293, + "learning_rate": 1.6695957820738137e-05, + "loss": 1.3029985427856445, "step": 96 }, { "epoch": 0.04135021097046414, - "grad_norm": 1.658605694770813, - "learning_rate": 8.523725834797891e-06, - "loss": 1.1831508874893188, + "grad_norm": 0.4851357340812683, + "learning_rate": 1.7047451669595782e-05, + "loss": 1.3498191833496094, "step": 98 }, { "epoch": 0.04219409282700422, - "grad_norm": 1.5077892541885376, - "learning_rate": 8.699472759226714e-06, - "loss": 1.0539867877960205, + "grad_norm": 0.418658584356308, + "learning_rate": 1.7398945518453427e-05, + "loss": 1.185287356376648, "step": 100 }, { "epoch": 0.04219409282700422, - "eval_loss": 1.138856053352356, - "eval_runtime": 859.7128, - "eval_samples_per_second": 2.451, - "eval_steps_per_second": 2.451, + "eval_loss": 1.2979938983917236, + "eval_runtime": 682.1979, + "eval_samples_per_second": 3.089, + "eval_steps_per_second": 3.089, "step": 100 }, { "epoch": 0.043037974683544304, - "grad_norm": 1.4335681200027466, - "learning_rate": 8.875219683655536e-06, - "loss": 1.0719901323318481, + "grad_norm": 0.4464418888092041, + "learning_rate": 1.7750439367311073e-05, + "loss": 1.2217272520065308, "step": 102 }, { "epoch": 0.04388185654008439, - "grad_norm": 1.7387681007385254, - "learning_rate": 9.050966608084359e-06, - "loss": 1.0654313564300537, + "grad_norm": 0.4706237316131592, + "learning_rate": 1.8101933216168718e-05, + "loss": 1.2052050828933716, "step": 104 }, { "epoch": 0.04472573839662447, - "grad_norm": 1.6071950197219849, - "learning_rate": 9.226713532513181e-06, - "loss": 1.0752698183059692, + "grad_norm": 0.46394404768943787, + "learning_rate": 1.8453427065026363e-05, + "loss": 1.221343994140625, "step": 106 }, { "epoch": 0.04556962025316456, - "grad_norm": 1.40005362033844, - "learning_rate": 9.402460456942004e-06, - "loss": 1.1029763221740723, + "grad_norm": 0.4726889431476593, + "learning_rate": 1.8804920913884008e-05, + "loss": 1.2387475967407227, "step": 108 }, { "epoch": 0.046413502109704644, - "grad_norm": 2.2338669300079346, - "learning_rate": 9.578207381370826e-06, - "loss": 1.1157960891723633, + "grad_norm": 0.42130985856056213, + "learning_rate": 1.9156414762741653e-05, + "loss": 1.2851309776306152, "step": 110 }, { "epoch": 0.04725738396624472, - "grad_norm": 1.4972727298736572, - "learning_rate": 9.753954305799649e-06, - "loss": 1.1095420122146606, + "grad_norm": 0.4504576623439789, + "learning_rate": 1.9507908611599298e-05, + "loss": 1.2753145694732666, "step": 112 }, { "epoch": 0.04810126582278481, - "grad_norm": 1.317979097366333, - "learning_rate": 9.929701230228471e-06, - "loss": 1.109113097190857, + "grad_norm": 0.396085262298584, + "learning_rate": 1.9859402460456943e-05, + "loss": 1.2427717447280884, "step": 114 }, { "epoch": 0.048945147679324896, - "grad_norm": 1.496346116065979, - "learning_rate": 1.0105448154657294e-05, - "loss": 1.1055104732513428, + "grad_norm": 0.5106491446495056, + "learning_rate": 2.0210896309314588e-05, + "loss": 1.2943825721740723, "step": 116 }, { "epoch": 0.049789029535864976, - "grad_norm": 1.385406732559204, - "learning_rate": 1.0281195079086117e-05, - "loss": 1.118395209312439, + "grad_norm": 0.42351317405700684, + "learning_rate": 2.0562390158172233e-05, + "loss": 1.263301134109497, "step": 118 }, { "epoch": 0.05063291139240506, - "grad_norm": 1.524222731590271, - "learning_rate": 1.0456942003514939e-05, - "loss": 1.1008446216583252, + "grad_norm": 0.4403539299964905, + "learning_rate": 2.0913884007029878e-05, + "loss": 1.2647849321365356, "step": 120 }, { "epoch": 0.05147679324894515, - "grad_norm": 1.6308200359344482, - "learning_rate": 1.0632688927943762e-05, - "loss": 1.0891425609588623, + "grad_norm": 0.5260752439498901, + "learning_rate": 2.1265377855887523e-05, + "loss": 1.2351393699645996, "step": 122 }, { "epoch": 0.05232067510548523, - "grad_norm": 1.3681106567382812, - "learning_rate": 1.0808435852372584e-05, - "loss": 0.9080473184585571, + "grad_norm": 0.44978851079940796, + "learning_rate": 2.1616871704745168e-05, + "loss": 1.0384471416473389, "step": 124 }, { "epoch": 0.053164556962025315, - "grad_norm": 1.9429908990859985, - "learning_rate": 1.0984182776801407e-05, - "loss": 1.0337369441986084, + "grad_norm": 0.47732362151145935, + "learning_rate": 2.1968365553602813e-05, + "loss": 1.1518068313598633, "step": 126 }, { "epoch": 0.0540084388185654, - "grad_norm": 1.5830830335617065, - "learning_rate": 1.115992970123023e-05, - "loss": 1.0703333616256714, + "grad_norm": 0.5473551750183105, + "learning_rate": 2.231985940246046e-05, + "loss": 1.2264912128448486, "step": 128 }, { "epoch": 0.05485232067510549, - "grad_norm": 1.4792555570602417, - "learning_rate": 1.1335676625659052e-05, - "loss": 1.004652738571167, + "grad_norm": 0.4473855197429657, + "learning_rate": 2.2671353251318103e-05, + "loss": 1.1615246534347534, "step": 130 }, { "epoch": 0.05569620253164557, - "grad_norm": 1.7196226119995117, - "learning_rate": 1.1511423550087874e-05, - "loss": 0.9798293709754944, + "grad_norm": 0.5980377197265625, + "learning_rate": 2.302284710017575e-05, + "loss": 1.1334880590438843, "step": 132 }, { "epoch": 0.056540084388185655, - "grad_norm": 1.8733659982681274, - "learning_rate": 1.1687170474516697e-05, - "loss": 1.0213249921798706, + "grad_norm": 0.5987792015075684, + "learning_rate": 2.3374340949033394e-05, + "loss": 1.1546804904937744, "step": 134 }, { "epoch": 0.05738396624472574, - "grad_norm": 1.3431142568588257, - "learning_rate": 1.186291739894552e-05, - "loss": 1.0358591079711914, + "grad_norm": 0.45355498790740967, + "learning_rate": 2.372583479789104e-05, + "loss": 1.194953441619873, "step": 136 }, { "epoch": 0.05822784810126582, - "grad_norm": 1.527864933013916, - "learning_rate": 1.2038664323374342e-05, - "loss": 0.9372249841690063, + "grad_norm": 0.5373698472976685, + "learning_rate": 2.4077328646748684e-05, + "loss": 1.1067466735839844, "step": 138 }, { "epoch": 0.05907172995780591, - "grad_norm": 1.5495563745498657, - "learning_rate": 1.2214411247803164e-05, - "loss": 1.0277758836746216, + "grad_norm": 0.48734328150749207, + "learning_rate": 2.442882249560633e-05, + "loss": 1.188468098640442, "step": 140 }, { "epoch": 0.059915611814345994, - "grad_norm": 1.6792418956756592, - "learning_rate": 1.2390158172231985e-05, - "loss": 1.0349801778793335, + "grad_norm": 0.4692173898220062, + "learning_rate": 2.478031634446397e-05, + "loss": 1.1624362468719482, "step": 142 }, { "epoch": 0.060759493670886074, - "grad_norm": 1.6468945741653442, - "learning_rate": 1.256590509666081e-05, - "loss": 0.9578297734260559, + "grad_norm": 0.532554030418396, + "learning_rate": 2.513181019332162e-05, + "loss": 1.0978907346725464, "step": 144 }, { "epoch": 0.06160337552742616, - "grad_norm": 1.7243824005126953, - "learning_rate": 1.2741652021089632e-05, - "loss": 1.0628854036331177, + "grad_norm": 0.5853802561759949, + "learning_rate": 2.5483304042179264e-05, + "loss": 1.2030781507492065, "step": 146 }, { "epoch": 0.06244725738396625, - "grad_norm": 1.7286981344223022, - "learning_rate": 1.2917398945518455e-05, - "loss": 0.9336449503898621, + "grad_norm": 0.5061611533164978, + "learning_rate": 2.583479789103691e-05, + "loss": 1.082366943359375, "step": 148 }, { "epoch": 0.06329113924050633, - "grad_norm": 1.6411832571029663, - "learning_rate": 1.3093145869947277e-05, - "loss": 0.953730583190918, + "grad_norm": 0.49426141381263733, + "learning_rate": 2.6186291739894554e-05, + "loss": 1.10564386844635, "step": 150 }, { "epoch": 0.06413502109704641, - "grad_norm": 1.8297001123428345, - "learning_rate": 1.3268892794376098e-05, - "loss": 1.051239013671875, + "grad_norm": 0.5846618413925171, + "learning_rate": 2.6537785588752196e-05, + "loss": 1.1992807388305664, "step": 152 }, { "epoch": 0.06497890295358649, - "grad_norm": 1.9660519361495972, - "learning_rate": 1.3444639718804922e-05, - "loss": 0.9955035448074341, + "grad_norm": 0.5517552495002747, + "learning_rate": 2.6889279437609844e-05, + "loss": 1.1757566928863525, "step": 154 }, { "epoch": 0.06582278481012659, - "grad_norm": 1.8423733711242676, - "learning_rate": 1.3620386643233743e-05, - "loss": 0.913300096988678, + "grad_norm": 0.5667305588722229, + "learning_rate": 2.7240773286467486e-05, + "loss": 1.0548783540725708, "step": 156 }, { "epoch": 0.06666666666666667, - "grad_norm": 1.9146347045898438, - "learning_rate": 1.3796133567662567e-05, - "loss": 1.0429846048355103, + "grad_norm": 0.6760414242744446, + "learning_rate": 2.7592267135325134e-05, + "loss": 1.184364914894104, "step": 158 }, { "epoch": 0.06751054852320675, - "grad_norm": 1.6221821308135986, - "learning_rate": 1.3971880492091388e-05, - "loss": 1.0360238552093506, + "grad_norm": 0.5261430740356445, + "learning_rate": 2.7943760984182776e-05, + "loss": 1.1945042610168457, "step": 160 }, { "epoch": 0.06835443037974684, - "grad_norm": 2.173283338546753, - "learning_rate": 1.4147627416520212e-05, - "loss": 1.0227266550064087, + "grad_norm": 0.6155015230178833, + "learning_rate": 2.8295254833040425e-05, + "loss": 1.2021973133087158, "step": 162 }, { "epoch": 0.06919831223628692, - "grad_norm": 1.7091665267944336, - "learning_rate": 1.4323374340949033e-05, - "loss": 1.0075194835662842, + "grad_norm": 0.6131619215011597, + "learning_rate": 2.8646748681898066e-05, + "loss": 1.144123911857605, "step": 164 }, { "epoch": 0.070042194092827, - "grad_norm": 1.7219135761260986, - "learning_rate": 1.4499121265377857e-05, - "loss": 1.0044782161712646, + "grad_norm": 0.5749185681343079, + "learning_rate": 2.8998242530755715e-05, + "loss": 1.1329256296157837, "step": 166 }, { "epoch": 0.07088607594936709, - "grad_norm": 1.6558159589767456, - "learning_rate": 1.4674868189806678e-05, - "loss": 0.9393973350524902, + "grad_norm": 0.5243118405342102, + "learning_rate": 2.9349736379613356e-05, + "loss": 1.0892387628555298, "step": 168 }, { "epoch": 0.07172995780590717, - "grad_norm": 1.9362739324569702, - "learning_rate": 1.4850615114235502e-05, - "loss": 0.9955337643623352, + "grad_norm": 0.7190104722976685, + "learning_rate": 2.9701230228471005e-05, + "loss": 1.163260817527771, "step": 170 }, { "epoch": 0.07257383966244725, - "grad_norm": 1.7792853116989136, - "learning_rate": 1.5026362038664323e-05, - "loss": 0.9659126400947571, + "grad_norm": 0.5486982464790344, + "learning_rate": 3.0052724077328647e-05, + "loss": 1.0880777835845947, "step": 172 }, { "epoch": 0.07341772151898734, - "grad_norm": 1.7184511423110962, - "learning_rate": 1.5202108963093147e-05, - "loss": 0.9077855348587036, + "grad_norm": 0.5020889043807983, + "learning_rate": 3.0404217926186295e-05, + "loss": 1.0433368682861328, "step": 174 }, { "epoch": 0.07426160337552742, - "grad_norm": 1.5701428651809692, - "learning_rate": 1.537785588752197e-05, - "loss": 0.9305018782615662, + "grad_norm": 0.47329774498939514, + "learning_rate": 3.075571177504394e-05, + "loss": 1.0528991222381592, "step": 176 }, { "epoch": 0.0751054852320675, - "grad_norm": 1.970229148864746, - "learning_rate": 1.555360281195079e-05, - "loss": 1.0211774110794067, + "grad_norm": 0.6635547876358032, + "learning_rate": 3.110720562390158e-05, + "loss": 1.1627811193466187, "step": 178 }, { "epoch": 0.0759493670886076, - "grad_norm": 1.8410269021987915, - "learning_rate": 1.5729349736379615e-05, - "loss": 0.9479315876960754, + "grad_norm": 0.5624618530273438, + "learning_rate": 3.145869947275923e-05, + "loss": 1.084869384765625, "step": 180 }, { "epoch": 0.07679324894514768, - "grad_norm": 1.8991246223449707, - "learning_rate": 1.5905096660808434e-05, - "loss": 1.0629050731658936, + "grad_norm": 0.6029536724090576, + "learning_rate": 3.181019332161687e-05, + "loss": 1.2227671146392822, "step": 182 }, { "epoch": 0.07763713080168777, - "grad_norm": 1.8052008152008057, - "learning_rate": 1.608084358523726e-05, - "loss": 0.946983814239502, + "grad_norm": 0.930959939956665, + "learning_rate": 3.216168717047452e-05, + "loss": 1.0955452919006348, "step": 184 }, { "epoch": 0.07848101265822785, - "grad_norm": 1.547108769416809, - "learning_rate": 1.625659050966608e-05, - "loss": 0.9413356184959412, + "grad_norm": 0.5326952338218689, + "learning_rate": 3.251318101933216e-05, + "loss": 1.0640798807144165, "step": 186 }, { "epoch": 0.07932489451476793, - "grad_norm": 1.9713538885116577, - "learning_rate": 1.6432337434094905e-05, - "loss": 0.9337888956069946, + "grad_norm": 0.5484727621078491, + "learning_rate": 3.286467486818981e-05, + "loss": 1.0700589418411255, "step": 188 }, { "epoch": 0.08016877637130802, - "grad_norm": 1.708789348602295, - "learning_rate": 1.6608084358523728e-05, - "loss": 0.9816337823867798, + "grad_norm": 0.605273425579071, + "learning_rate": 3.3216168717047456e-05, + "loss": 1.1593081951141357, "step": 190 }, { "epoch": 0.0810126582278481, - "grad_norm": 1.815292477607727, - "learning_rate": 1.678383128295255e-05, - "loss": 1.017122507095337, + "grad_norm": 0.5704394578933716, + "learning_rate": 3.35676625659051e-05, + "loss": 1.1617076396942139, "step": 192 }, { "epoch": 0.08185654008438818, - "grad_norm": 1.7950682640075684, - "learning_rate": 1.6959578207381373e-05, - "loss": 0.991599440574646, + "grad_norm": 0.5929452180862427, + "learning_rate": 3.3919156414762746e-05, + "loss": 1.1346839666366577, "step": 194 }, { "epoch": 0.08270042194092828, - "grad_norm": 1.692512035369873, - "learning_rate": 1.7135325131810195e-05, - "loss": 0.9570834040641785, + "grad_norm": 0.5624077916145325, + "learning_rate": 3.427065026362039e-05, + "loss": 1.0934710502624512, "step": 196 }, { "epoch": 0.08354430379746836, - "grad_norm": 2.056089162826538, - "learning_rate": 1.7311072056239018e-05, - "loss": 1.035754919052124, + "grad_norm": 0.6717425584793091, + "learning_rate": 3.4622144112478036e-05, + "loss": 1.1810534000396729, "step": 198 }, { "epoch": 0.08438818565400844, - "grad_norm": 1.7022203207015991, - "learning_rate": 1.7486818980667837e-05, - "loss": 1.0124205350875854, + "grad_norm": 0.5120199918746948, + "learning_rate": 3.4973637961335674e-05, + "loss": 1.1525514125823975, "step": 200 }, { "epoch": 0.08438818565400844, - "eval_loss": 0.995743453502655, - "eval_runtime": 846.8257, - "eval_samples_per_second": 2.488, - "eval_steps_per_second": 2.488, + "eval_loss": 1.142486810684204, + "eval_runtime": 668.2356, + "eval_samples_per_second": 3.153, + "eval_steps_per_second": 3.153, "step": 200 }, { "epoch": 0.08523206751054853, - "grad_norm": 1.6088604927062988, - "learning_rate": 1.7662565905096663e-05, - "loss": 0.8946985006332397, + "grad_norm": 0.5144487023353577, + "learning_rate": 3.5325131810193326e-05, + "loss": 1.0243735313415527, "step": 202 }, { "epoch": 0.08607594936708861, - "grad_norm": 2.02270770072937, - "learning_rate": 1.7838312829525482e-05, - "loss": 0.976133406162262, + "grad_norm": 0.6325069069862366, + "learning_rate": 3.5676625659050964e-05, + "loss": 1.118743896484375, "step": 204 }, { "epoch": 0.08691983122362869, - "grad_norm": 1.7832789421081543, - "learning_rate": 1.8014059753954308e-05, - "loss": 0.9079383611679077, + "grad_norm": 0.5501633882522583, + "learning_rate": 3.6028119507908616e-05, + "loss": 1.0380504131317139, "step": 206 }, { "epoch": 0.08776371308016878, - "grad_norm": 1.9793545007705688, - "learning_rate": 1.8189806678383127e-05, - "loss": 0.8650367856025696, + "grad_norm": 0.6133899688720703, + "learning_rate": 3.6379613356766254e-05, + "loss": 0.9837555885314941, "step": 208 }, { "epoch": 0.08860759493670886, - "grad_norm": 1.8124271631240845, - "learning_rate": 1.8365553602811953e-05, - "loss": 0.9327266812324524, + "grad_norm": 0.5799810886383057, + "learning_rate": 3.6731107205623906e-05, + "loss": 1.090720295906067, "step": 210 }, { "epoch": 0.08945147679324894, - "grad_norm": 1.8581212759017944, - "learning_rate": 1.8541300527240772e-05, - "loss": 0.9811079502105713, + "grad_norm": 0.6039511561393738, + "learning_rate": 3.7082601054481544e-05, + "loss": 1.120232343673706, "step": 212 }, { "epoch": 0.09029535864978903, - "grad_norm": 2.001699447631836, - "learning_rate": 1.8717047451669598e-05, - "loss": 0.9546971321105957, + "grad_norm": 0.5983024835586548, + "learning_rate": 3.7434094903339196e-05, + "loss": 1.096949815750122, "step": 214 }, { "epoch": 0.09113924050632911, - "grad_norm": 1.6994978189468384, - "learning_rate": 1.8892794376098417e-05, - "loss": 0.9611319899559021, + "grad_norm": 0.5641079545021057, + "learning_rate": 3.7785588752196835e-05, + "loss": 1.1226298809051514, "step": 216 }, { "epoch": 0.0919831223628692, - "grad_norm": 2.1379497051239014, - "learning_rate": 1.9068541300527243e-05, - "loss": 0.9781531095504761, + "grad_norm": 0.655717134475708, + "learning_rate": 3.8137082601054486e-05, + "loss": 1.1260643005371094, "step": 218 }, { "epoch": 0.09282700421940929, - "grad_norm": 1.8961224555969238, - "learning_rate": 1.9244288224956066e-05, - "loss": 0.9374833106994629, + "grad_norm": 0.6111898422241211, + "learning_rate": 3.848857644991213e-05, + "loss": 1.0777709484100342, "step": 220 }, { "epoch": 0.09367088607594937, - "grad_norm": 1.851464033126831, - "learning_rate": 1.9420035149384885e-05, - "loss": 0.9681299328804016, + "grad_norm": 0.6821302771568298, + "learning_rate": 3.884007029876977e-05, + "loss": 1.10588800907135, "step": 222 }, { "epoch": 0.09451476793248945, - "grad_norm": 2.0642266273498535, - "learning_rate": 1.959578207381371e-05, - "loss": 1.0086225271224976, + "grad_norm": 0.693175733089447, + "learning_rate": 3.919156414762742e-05, + "loss": 1.1498671770095825, "step": 224 }, { "epoch": 0.09535864978902954, - "grad_norm": 1.8658756017684937, - "learning_rate": 1.977152899824253e-05, - "loss": 0.9190312623977661, + "grad_norm": 0.5288166403770447, + "learning_rate": 3.954305799648506e-05, + "loss": 1.0587562322616577, "step": 226 }, { "epoch": 0.09620253164556962, - "grad_norm": 2.4398674964904785, - "learning_rate": 1.9947275922671356e-05, - "loss": 0.9740874171257019, + "grad_norm": 0.6882867813110352, + "learning_rate": 3.989455184534271e-05, + "loss": 1.1107512712478638, "step": 228 }, { "epoch": 0.0970464135021097, - "grad_norm": 1.849183440208435, - "learning_rate": 2.0123022847100175e-05, - "loss": 0.884376049041748, + "grad_norm": 0.5834154486656189, + "learning_rate": 4.024604569420035e-05, + "loss": 1.020510196685791, "step": 230 }, { "epoch": 0.09789029535864979, - "grad_norm": 2.027320384979248, - "learning_rate": 2.0298769771529e-05, - "loss": 0.9116487503051758, + "grad_norm": 0.7157064080238342, + "learning_rate": 4.0597539543058e-05, + "loss": 1.0642449855804443, "step": 232 }, { "epoch": 0.09873417721518987, - "grad_norm": 1.6800135374069214, - "learning_rate": 2.047451669595782e-05, - "loss": 0.9035115242004395, + "grad_norm": 0.6530708074569702, + "learning_rate": 4.094903339191564e-05, + "loss": 1.0359872579574585, "step": 234 }, { "epoch": 0.09957805907172995, - "grad_norm": 2.2362256050109863, - "learning_rate": 2.0650263620386646e-05, - "loss": 0.9043796062469482, + "grad_norm": 0.6329686045646667, + "learning_rate": 4.130052724077329e-05, + "loss": 1.050504446029663, "step": 236 }, { "epoch": 0.10042194092827005, - "grad_norm": 1.938215970993042, - "learning_rate": 2.0826010544815465e-05, - "loss": 1.0888828039169312, + "grad_norm": 0.6597026586532593, + "learning_rate": 4.165202108963093e-05, + "loss": 1.2621175050735474, "step": 238 }, { "epoch": 0.10126582278481013, - "grad_norm": 1.890328049659729, - "learning_rate": 2.100175746924429e-05, - "loss": 0.9960280656814575, + "grad_norm": 0.6195225119590759, + "learning_rate": 4.200351493848858e-05, + "loss": 1.1218310594558716, "step": 240 }, { "epoch": 0.1021097046413502, - "grad_norm": 2.021235227584839, - "learning_rate": 2.117750439367311e-05, - "loss": 0.9848901629447937, + "grad_norm": 0.6764137744903564, + "learning_rate": 4.235500878734622e-05, + "loss": 1.1250728368759155, "step": 242 }, { "epoch": 0.1029535864978903, - "grad_norm": 2.023920774459839, - "learning_rate": 2.1353251318101936e-05, - "loss": 0.891694188117981, + "grad_norm": 0.552363395690918, + "learning_rate": 4.270650263620387e-05, + "loss": 1.028212308883667, "step": 244 }, { "epoch": 0.10379746835443038, - "grad_norm": 1.8061069250106812, - "learning_rate": 2.1528998242530755e-05, - "loss": 0.9059976935386658, + "grad_norm": 0.5620495676994324, + "learning_rate": 4.305799648506151e-05, + "loss": 1.0425450801849365, "step": 246 }, { "epoch": 0.10464135021097046, - "grad_norm": 2.176302194595337, - "learning_rate": 2.1704745166959578e-05, - "loss": 1.0056109428405762, + "grad_norm": 0.6860032081604004, + "learning_rate": 4.3409490333919156e-05, + "loss": 1.144278883934021, "step": 248 }, { "epoch": 0.10548523206751055, - "grad_norm": 1.9820969104766846, - "learning_rate": 2.18804920913884e-05, - "loss": 0.9645357728004456, + "grad_norm": 0.6033259034156799, + "learning_rate": 4.37609841827768e-05, + "loss": 1.1223982572555542, "step": 250 }, { "epoch": 0.10632911392405063, - "grad_norm": 1.8764572143554688, - "learning_rate": 2.2056239015817223e-05, - "loss": 1.0178182125091553, + "grad_norm": 0.6292146444320679, + "learning_rate": 4.4112478031634446e-05, + "loss": 1.1609960794448853, "step": 252 }, { "epoch": 0.10717299578059072, - "grad_norm": 2.56221342086792, - "learning_rate": 2.223198594024605e-05, - "loss": 0.9546761512756348, + "grad_norm": 0.7982883453369141, + "learning_rate": 4.44639718804921e-05, + "loss": 1.063547968864441, "step": 254 }, { "epoch": 0.1080168776371308, - "grad_norm": 2.6779074668884277, - "learning_rate": 2.2407732864674868e-05, - "loss": 0.9300968647003174, + "grad_norm": 0.7719110250473022, + "learning_rate": 4.4815465729349736e-05, + "loss": 1.0719804763793945, "step": 256 }, { "epoch": 0.10886075949367088, - "grad_norm": 2.140897512435913, - "learning_rate": 2.2583479789103694e-05, - "loss": 0.926638662815094, + "grad_norm": 0.6101011633872986, + "learning_rate": 4.516695957820739e-05, + "loss": 1.0778400897979736, "step": 258 }, { "epoch": 0.10970464135021098, - "grad_norm": 2.0880508422851562, - "learning_rate": 2.2759226713532513e-05, - "loss": 1.0681840181350708, + "grad_norm": 0.7300994396209717, + "learning_rate": 4.5518453427065026e-05, + "loss": 1.2129558324813843, "step": 260 }, { "epoch": 0.11054852320675106, - "grad_norm": 2.7273616790771484, - "learning_rate": 2.293497363796134e-05, - "loss": 1.0840941667556763, + "grad_norm": 0.8348747491836548, + "learning_rate": 4.586994727592268e-05, + "loss": 1.221714735031128, "step": 262 }, { "epoch": 0.11139240506329114, - "grad_norm": 1.6723874807357788, - "learning_rate": 2.3110720562390158e-05, - "loss": 0.8637182116508484, + "grad_norm": 0.5445612072944641, + "learning_rate": 4.6221441124780316e-05, + "loss": 1.0187978744506836, "step": 264 }, { "epoch": 0.11223628691983123, - "grad_norm": 1.806243896484375, - "learning_rate": 2.3286467486818984e-05, - "loss": 0.9554686546325684, + "grad_norm": 0.6230319738388062, + "learning_rate": 4.657293497363797e-05, + "loss": 1.096561312675476, "step": 266 }, { "epoch": 0.11308016877637131, - "grad_norm": 1.9086743593215942, - "learning_rate": 2.3462214411247803e-05, - "loss": 0.9556593894958496, + "grad_norm": 0.6231237649917603, + "learning_rate": 4.6924428822495606e-05, + "loss": 1.089842438697815, "step": 268 }, { "epoch": 0.11392405063291139, - "grad_norm": 2.1822304725646973, - "learning_rate": 2.3637961335676626e-05, - "loss": 0.9177709817886353, + "grad_norm": 0.7178627252578735, + "learning_rate": 4.727592267135325e-05, + "loss": 1.0696645975112915, "step": 270 }, { "epoch": 0.11476793248945148, - "grad_norm": 2.1009039878845215, - "learning_rate": 2.3813708260105448e-05, - "loss": 0.9288759827613831, + "grad_norm": 0.6895854473114014, + "learning_rate": 4.7627416520210896e-05, + "loss": 1.0511361360549927, "step": 272 }, { "epoch": 0.11561181434599156, - "grad_norm": 1.9814810752868652, - "learning_rate": 2.398945518453427e-05, - "loss": 0.9881691932678223, + "grad_norm": 0.6046878695487976, + "learning_rate": 4.797891036906854e-05, + "loss": 1.1373958587646484, "step": 274 }, { "epoch": 0.11645569620253164, - "grad_norm": 1.9946284294128418, - "learning_rate": 2.4165202108963093e-05, - "loss": 0.9390727281570435, + "grad_norm": 0.6524552702903748, + "learning_rate": 4.833040421792619e-05, + "loss": 1.0734186172485352, "step": 276 }, { "epoch": 0.11729957805907174, - "grad_norm": 2.4489169120788574, - "learning_rate": 2.4340949033391916e-05, - "loss": 0.9625692963600159, + "grad_norm": 0.6331019997596741, + "learning_rate": 4.868189806678383e-05, + "loss": 1.123913049697876, "step": 278 }, { "epoch": 0.11814345991561181, - "grad_norm": 2.0919103622436523, - "learning_rate": 2.451669595782074e-05, - "loss": 0.9304702877998352, + "grad_norm": 0.5919018983840942, + "learning_rate": 4.903339191564148e-05, + "loss": 1.0635710954666138, "step": 280 }, { "epoch": 0.1189873417721519, - "grad_norm": 1.912914752960205, - "learning_rate": 2.469244288224956e-05, - "loss": 0.9313994646072388, + "grad_norm": 0.6067633032798767, + "learning_rate": 4.938488576449912e-05, + "loss": 1.0429247617721558, "step": 282 }, { "epoch": 0.11983122362869199, - "grad_norm": 2.1553256511688232, - "learning_rate": 2.4868189806678387e-05, - "loss": 1.004011869430542, + "grad_norm": 0.6583750247955322, + "learning_rate": 4.9736379613356774e-05, + "loss": 1.1397464275360107, "step": 284 }, { "epoch": 0.12067510548523207, - "grad_norm": 2.0129058361053467, - "learning_rate": 2.504393673110721e-05, - "loss": 0.9092531204223633, + "grad_norm": 0.6200069785118103, + "learning_rate": 5.008787346221442e-05, + "loss": 1.0590803623199463, "step": 286 }, { "epoch": 0.12151898734177215, - "grad_norm": 2.1632325649261475, - "learning_rate": 2.5219683655536032e-05, - "loss": 0.993347704410553, + "grad_norm": 0.6798665523529053, + "learning_rate": 5.0439367311072064e-05, + "loss": 1.1318789720535278, "step": 288 }, { "epoch": 0.12236286919831224, - "grad_norm": 2.3072738647460938, - "learning_rate": 2.539543057996485e-05, - "loss": 0.978348433971405, + "grad_norm": 0.7508794069290161, + "learning_rate": 5.07908611599297e-05, + "loss": 1.0934956073760986, "step": 290 }, { "epoch": 0.12320675105485232, - "grad_norm": 2.056560516357422, - "learning_rate": 2.5571177504393674e-05, - "loss": 1.0018101930618286, + "grad_norm": 0.6901452541351318, + "learning_rate": 5.114235500878735e-05, + "loss": 1.163407802581787, "step": 292 }, { "epoch": 0.1240506329113924, - "grad_norm": 1.8906747102737427, - "learning_rate": 2.5746924428822493e-05, - "loss": 0.9607775211334229, + "grad_norm": 0.6423285603523254, + "learning_rate": 5.1493848857644985e-05, + "loss": 1.09059476852417, "step": 294 }, { "epoch": 0.1248945147679325, - "grad_norm": 2.1375651359558105, - "learning_rate": 2.5922671353251322e-05, - "loss": 0.9259153008460999, + "grad_norm": 0.6839275360107422, + "learning_rate": 5.1845342706502644e-05, + "loss": 1.0690211057662964, "step": 296 }, { "epoch": 0.1257383966244726, - "grad_norm": 1.9994823932647705, - "learning_rate": 2.609841827768014e-05, - "loss": 0.8524524569511414, + "grad_norm": 0.6350128054618835, + "learning_rate": 5.219683655536028e-05, + "loss": 0.982322096824646, "step": 298 }, { "epoch": 0.12658227848101267, - "grad_norm": 2.2421181201934814, - "learning_rate": 2.6274165202108964e-05, - "loss": 1.0047069787979126, + "grad_norm": 0.7136530876159668, + "learning_rate": 5.254833040421793e-05, + "loss": 1.1132930517196655, "step": 300 }, { "epoch": 0.12658227848101267, - "eval_loss": 0.9517185688018799, - "eval_runtime": 860.0287, - "eval_samples_per_second": 2.45, - "eval_steps_per_second": 2.45, + "eval_loss": 1.0952109098434448, + "eval_runtime": 677.0652, + "eval_samples_per_second": 3.112, + "eval_steps_per_second": 3.112, "step": 300 }, { "epoch": 0.12742616033755275, - "grad_norm": 2.1206254959106445, - "learning_rate": 2.6449912126537786e-05, - "loss": 0.8475471138954163, + "grad_norm": 0.7339721322059631, + "learning_rate": 5.289982425307557e-05, + "loss": 0.973595917224884, "step": 302 }, { "epoch": 0.12827004219409283, - "grad_norm": 1.885161280632019, - "learning_rate": 2.6625659050966612e-05, - "loss": 0.8643121123313904, + "grad_norm": 0.5941481590270996, + "learning_rate": 5.3251318101933224e-05, + "loss": 0.9819849729537964, "step": 304 }, { "epoch": 0.1291139240506329, - "grad_norm": 3.1441781520843506, - "learning_rate": 2.680140597539543e-05, - "loss": 0.8804612159729004, + "grad_norm": 0.7153938412666321, + "learning_rate": 5.360281195079086e-05, + "loss": 1.0315470695495605, "step": 306 }, { "epoch": 0.12995780590717299, - "grad_norm": 1.953133225440979, - "learning_rate": 2.6977152899824254e-05, - "loss": 0.8348029255867004, + "grad_norm": 0.5167180299758911, + "learning_rate": 5.395430579964851e-05, + "loss": 0.9492001533508301, "step": 308 }, { "epoch": 0.1308016877637131, - "grad_norm": 2.3762667179107666, - "learning_rate": 2.7152899824253076e-05, - "loss": 0.8889057040214539, + "grad_norm": 0.6055944561958313, + "learning_rate": 5.430579964850615e-05, + "loss": 1.0156209468841553, "step": 310 }, { "epoch": 0.13164556962025317, - "grad_norm": 2.4651103019714355, - "learning_rate": 2.7328646748681902e-05, - "loss": 1.025565505027771, + "grad_norm": 0.7662386298179626, + "learning_rate": 5.4657293497363805e-05, + "loss": 1.1791651248931885, "step": 312 }, { "epoch": 0.13248945147679325, - "grad_norm": 1.8522284030914307, - "learning_rate": 2.7504393673110725e-05, - "loss": 0.868915855884552, + "grad_norm": 0.6065546274185181, + "learning_rate": 5.500878734622145e-05, + "loss": 1.0009297132492065, "step": 314 }, { "epoch": 0.13333333333333333, - "grad_norm": 1.8048083782196045, - "learning_rate": 2.7680140597539544e-05, - "loss": 0.8821638226509094, + "grad_norm": 0.604225754737854, + "learning_rate": 5.536028119507909e-05, + "loss": 1.0208244323730469, "step": 316 }, { "epoch": 0.1341772151898734, - "grad_norm": 1.9933605194091797, - "learning_rate": 2.7855887521968367e-05, - "loss": 0.8735360503196716, + "grad_norm": 0.6186763048171997, + "learning_rate": 5.571177504393673e-05, + "loss": 0.9968416690826416, "step": 318 }, { "epoch": 0.1350210970464135, - "grad_norm": 2.044337034225464, - "learning_rate": 2.8031634446397186e-05, - "loss": 0.8288834691047668, + "grad_norm": 0.7100363969802856, + "learning_rate": 5.606326889279437e-05, + "loss": 0.9540256857872009, "step": 320 }, { "epoch": 0.1358649789029536, - "grad_norm": 2.416067361831665, - "learning_rate": 2.8207381370826015e-05, - "loss": 0.9104969501495361, + "grad_norm": 0.6979711055755615, + "learning_rate": 5.641476274165203e-05, + "loss": 1.0631953477859497, "step": 322 }, { "epoch": 0.13670886075949368, - "grad_norm": 2.0731265544891357, - "learning_rate": 2.8383128295254834e-05, - "loss": 0.8689924478530884, + "grad_norm": 0.6237109303474426, + "learning_rate": 5.676625659050967e-05, + "loss": 1.0170501470565796, "step": 324 }, { "epoch": 0.13755274261603376, - "grad_norm": 2.049126386642456, - "learning_rate": 2.8558875219683657e-05, - "loss": 0.9312222003936768, + "grad_norm": 0.6525548696517944, + "learning_rate": 5.711775043936731e-05, + "loss": 1.0715603828430176, "step": 326 }, { "epoch": 0.13839662447257384, - "grad_norm": 2.131026268005371, - "learning_rate": 2.8734622144112476e-05, - "loss": 0.8933501839637756, + "grad_norm": 0.6869221329689026, + "learning_rate": 5.746924428822495e-05, + "loss": 1.0111541748046875, "step": 328 }, { "epoch": 0.13924050632911392, - "grad_norm": 1.766754150390625, - "learning_rate": 2.8910369068541305e-05, - "loss": 0.8998261094093323, + "grad_norm": 0.553188145160675, + "learning_rate": 5.782073813708261e-05, + "loss": 1.0311682224273682, "step": 330 }, { "epoch": 0.140084388185654, - "grad_norm": 2.197706460952759, - "learning_rate": 2.9086115992970124e-05, - "loss": 0.8826426267623901, + "grad_norm": 0.6760852932929993, + "learning_rate": 5.817223198594025e-05, + "loss": 1.0213634967803955, "step": 332 }, { "epoch": 0.1409282700421941, - "grad_norm": 1.953715443611145, - "learning_rate": 2.9261862917398947e-05, - "loss": 0.8590307831764221, + "grad_norm": 0.5907419919967651, + "learning_rate": 5.8523725834797894e-05, + "loss": 0.9748594164848328, "step": 334 }, { "epoch": 0.14177215189873418, - "grad_norm": 2.200929880142212, - "learning_rate": 2.943760984182777e-05, - "loss": 0.9317060708999634, + "grad_norm": 0.7044920921325684, + "learning_rate": 5.887521968365554e-05, + "loss": 1.05863356590271, "step": 336 }, { "epoch": 0.14261603375527426, - "grad_norm": 2.1195082664489746, - "learning_rate": 2.961335676625659e-05, - "loss": 0.9965578317642212, + "grad_norm": 0.679073691368103, + "learning_rate": 5.922671353251318e-05, + "loss": 1.1341127157211304, "step": 338 }, { "epoch": 0.14345991561181434, - "grad_norm": 2.3449771404266357, - "learning_rate": 2.9789103690685414e-05, - "loss": 0.8353848457336426, + "grad_norm": 0.7676237225532532, + "learning_rate": 5.957820738137083e-05, + "loss": 0.9540836215019226, "step": 340 }, { "epoch": 0.14430379746835442, - "grad_norm": 2.000497579574585, - "learning_rate": 2.9964850615114237e-05, - "loss": 0.9154735803604126, + "grad_norm": 0.6313899755477905, + "learning_rate": 5.9929701230228474e-05, + "loss": 1.0585911273956299, "step": 342 }, { "epoch": 0.1451476793248945, - "grad_norm": 2.141890525817871, - "learning_rate": 3.014059753954306e-05, - "loss": 0.9530655741691589, + "grad_norm": 0.7123099565505981, + "learning_rate": 6.028119507908612e-05, + "loss": 1.0760118961334229, "step": 344 }, { "epoch": 0.1459915611814346, - "grad_norm": 1.7717392444610596, - "learning_rate": 3.031634446397188e-05, - "loss": 0.896998405456543, + "grad_norm": 0.585935652256012, + "learning_rate": 6.063268892794376e-05, + "loss": 1.036866307258606, "step": 346 }, { "epoch": 0.1468354430379747, - "grad_norm": 1.8796685934066772, - "learning_rate": 3.0492091388400708e-05, - "loss": 0.9084208011627197, + "grad_norm": 0.5643263459205627, + "learning_rate": 6.0984182776801416e-05, + "loss": 1.0242938995361328, "step": 348 }, { "epoch": 0.14767932489451477, - "grad_norm": 2.0298709869384766, - "learning_rate": 3.066783831282953e-05, - "loss": 0.9183387756347656, + "grad_norm": 0.626761794090271, + "learning_rate": 6.133567662565906e-05, + "loss": 1.0497376918792725, "step": 350 }, { "epoch": 0.14852320675105485, - "grad_norm": 1.9245645999908447, - "learning_rate": 3.084358523725835e-05, - "loss": 0.8624772429466248, + "grad_norm": 0.5106956958770752, + "learning_rate": 6.16871704745167e-05, + "loss": 0.9811885356903076, "step": 352 }, { "epoch": 0.14936708860759493, - "grad_norm": 2.325681209564209, - "learning_rate": 3.101933216168717e-05, - "loss": 0.9142400026321411, + "grad_norm": 0.6948089003562927, + "learning_rate": 6.203866432337434e-05, + "loss": 1.0715330839157104, "step": 354 }, { "epoch": 0.150210970464135, - "grad_norm": 2.1200530529022217, - "learning_rate": 3.1195079086115995e-05, - "loss": 0.9064018130302429, + "grad_norm": 0.699713945388794, + "learning_rate": 6.239015817223199e-05, + "loss": 1.0405226945877075, "step": 356 }, { "epoch": 0.15105485232067511, - "grad_norm": 1.979314923286438, - "learning_rate": 3.137082601054482e-05, - "loss": 0.9199238419532776, + "grad_norm": 0.6437667012214661, + "learning_rate": 6.274165202108964e-05, + "loss": 1.0490930080413818, "step": 358 }, { "epoch": 0.1518987341772152, - "grad_norm": 2.1122689247131348, - "learning_rate": 3.154657293497364e-05, - "loss": 0.8030132055282593, + "grad_norm": 0.6952699422836304, + "learning_rate": 6.309314586994728e-05, + "loss": 0.9267548322677612, "step": 360 }, { "epoch": 0.15274261603375527, - "grad_norm": 2.105767250061035, - "learning_rate": 3.172231985940246e-05, - "loss": 0.9185854196548462, + "grad_norm": 0.6713186502456665, + "learning_rate": 6.344463971880492e-05, + "loss": 1.0427420139312744, "step": 362 }, { "epoch": 0.15358649789029535, - "grad_norm": 2.179471015930176, - "learning_rate": 3.1898066783831285e-05, - "loss": 0.9365083575248718, + "grad_norm": 0.6750379800796509, + "learning_rate": 6.379613356766257e-05, + "loss": 1.048950433731079, "step": 364 }, { "epoch": 0.15443037974683543, - "grad_norm": 2.1444311141967773, - "learning_rate": 3.207381370826011e-05, - "loss": 0.8965140581130981, + "grad_norm": 0.6053379774093628, + "learning_rate": 6.414762741652022e-05, + "loss": 1.0156004428863525, "step": 366 }, { "epoch": 0.15527426160337554, - "grad_norm": 2.4171674251556396, - "learning_rate": 3.224956063268893e-05, - "loss": 0.8787504434585571, + "grad_norm": 0.8063633441925049, + "learning_rate": 6.449912126537786e-05, + "loss": 1.0020819902420044, "step": 368 }, { "epoch": 0.15611814345991562, - "grad_norm": 2.418628215789795, - "learning_rate": 3.242530755711775e-05, - "loss": 0.8925284147262573, + "grad_norm": 0.8027494549751282, + "learning_rate": 6.48506151142355e-05, + "loss": 1.055633783340454, "step": 370 }, { "epoch": 0.1569620253164557, - "grad_norm": 2.2228314876556396, - "learning_rate": 3.2601054481546575e-05, - "loss": 0.876179039478302, + "grad_norm": 0.6580121517181396, + "learning_rate": 6.520210896309315e-05, + "loss": 1.0149940252304077, "step": 372 }, { "epoch": 0.15780590717299578, - "grad_norm": 2.324237108230591, - "learning_rate": 3.27768014059754e-05, - "loss": 0.8365707993507385, + "grad_norm": 0.6561233997344971, + "learning_rate": 6.55536028119508e-05, + "loss": 0.9769611954689026, "step": 374 }, { "epoch": 0.15864978902953586, - "grad_norm": 2.6344552040100098, - "learning_rate": 3.295254833040422e-05, - "loss": 0.7864399552345276, + "grad_norm": 0.6444346308708191, + "learning_rate": 6.590509666080844e-05, + "loss": 0.9099349975585938, "step": 376 }, { "epoch": 0.15949367088607594, - "grad_norm": 2.047536611557007, - "learning_rate": 3.312829525483304e-05, - "loss": 0.9271875023841858, + "grad_norm": 0.5879359245300293, + "learning_rate": 6.625659050966608e-05, + "loss": 1.0797548294067383, "step": 378 }, { "epoch": 0.16033755274261605, - "grad_norm": 2.120025157928467, - "learning_rate": 3.3304042179261865e-05, - "loss": 0.8799133896827698, + "grad_norm": 0.6994144916534424, + "learning_rate": 6.660808435852373e-05, + "loss": 1.0336791276931763, "step": 380 }, { "epoch": 0.16118143459915613, - "grad_norm": 2.363692045211792, - "learning_rate": 3.347978910369069e-05, - "loss": 0.8973530530929565, + "grad_norm": 0.6128669381141663, + "learning_rate": 6.695957820738138e-05, + "loss": 1.018118143081665, "step": 382 }, { "epoch": 0.1620253164556962, - "grad_norm": 2.1796772480010986, - "learning_rate": 3.365553602811951e-05, - "loss": 1.0277652740478516, + "grad_norm": 1.0237540006637573, + "learning_rate": 6.731107205623902e-05, + "loss": 1.1405497789382935, "step": 384 }, { "epoch": 0.16286919831223629, - "grad_norm": 1.9192595481872559, - "learning_rate": 3.383128295254833e-05, - "loss": 0.8909643888473511, + "grad_norm": 0.6091578006744385, + "learning_rate": 6.766256590509666e-05, + "loss": 1.0314189195632935, "step": 386 }, { "epoch": 0.16371308016877636, - "grad_norm": 1.7874376773834229, - "learning_rate": 3.4007029876977155e-05, - "loss": 0.837049663066864, + "grad_norm": 0.5916037559509277, + "learning_rate": 6.801405975395431e-05, + "loss": 0.9564052820205688, "step": 388 }, { "epoch": 0.16455696202531644, - "grad_norm": 2.3402366638183594, - "learning_rate": 3.4182776801405974e-05, - "loss": 0.8625202775001526, + "grad_norm": 0.771653950214386, + "learning_rate": 6.836555360281195e-05, + "loss": 1.0023859739303589, "step": 390 }, { "epoch": 0.16540084388185655, - "grad_norm": 2.1137185096740723, - "learning_rate": 3.43585237258348e-05, - "loss": 0.9288321137428284, + "grad_norm": 0.654658317565918, + "learning_rate": 6.87170474516696e-05, + "loss": 1.07024085521698, "step": 392 }, { "epoch": 0.16624472573839663, - "grad_norm": 2.3776895999908447, - "learning_rate": 3.453427065026362e-05, - "loss": 0.9328726530075073, + "grad_norm": 0.6611968874931335, + "learning_rate": 6.906854130052724e-05, + "loss": 1.0552500486373901, "step": 394 }, { "epoch": 0.1670886075949367, - "grad_norm": 2.34941029548645, - "learning_rate": 3.4710017574692445e-05, - "loss": 0.9273309707641602, + "grad_norm": 0.6955893039703369, + "learning_rate": 6.942003514938489e-05, + "loss": 1.0562875270843506, "step": 396 }, { "epoch": 0.1679324894514768, - "grad_norm": 2.1272573471069336, - "learning_rate": 3.4885764499121264e-05, - "loss": 0.8703887462615967, + "grad_norm": 0.6666058301925659, + "learning_rate": 6.977152899824253e-05, + "loss": 0.9850592017173767, "step": 398 }, { "epoch": 0.16877637130801687, - "grad_norm": 2.047290802001953, - "learning_rate": 3.506151142355009e-05, - "loss": 0.8808165788650513, + "grad_norm": 0.6131711006164551, + "learning_rate": 7.012302284710018e-05, + "loss": 1.0077755451202393, "step": 400 }, { "epoch": 0.16877637130801687, - "eval_loss": 0.9282881617546082, - "eval_runtime": 869.6867, - "eval_samples_per_second": 2.423, - "eval_steps_per_second": 2.423, + "eval_loss": 1.0625108480453491, + "eval_runtime": 691.0068, + "eval_samples_per_second": 3.049, + "eval_steps_per_second": 3.049, "step": 400 }, { "epoch": 0.16962025316455695, - "grad_norm": 1.9874159097671509, - "learning_rate": 3.5237258347978916e-05, - "loss": 0.9643645286560059, + "grad_norm": 0.6286499500274658, + "learning_rate": 7.047451669595783e-05, + "loss": 1.1012427806854248, "step": 402 }, { "epoch": 0.17046413502109706, - "grad_norm": 1.9299919605255127, - "learning_rate": 3.5413005272407735e-05, - "loss": 0.9173495769500732, + "grad_norm": 0.6639351844787598, + "learning_rate": 7.082601054481547e-05, + "loss": 1.0379719734191895, "step": 404 }, { "epoch": 0.17130801687763714, - "grad_norm": 2.3379697799682617, - "learning_rate": 3.5588752196836555e-05, - "loss": 0.8998411893844604, + "grad_norm": 0.750401496887207, + "learning_rate": 7.117750439367311e-05, + "loss": 1.031856656074524, "step": 406 }, { "epoch": 0.17215189873417722, - "grad_norm": 2.241370916366577, - "learning_rate": 3.5764499121265374e-05, - "loss": 0.9310802221298218, + "grad_norm": 0.8084847331047058, + "learning_rate": 7.152899824253075e-05, + "loss": 1.0493193864822388, "step": 408 }, { "epoch": 0.1729957805907173, - "grad_norm": 2.4490108489990234, - "learning_rate": 3.5940246045694206e-05, - "loss": 0.9605053067207336, + "grad_norm": 0.7448462247848511, + "learning_rate": 7.188049209138841e-05, + "loss": 1.1012418270111084, "step": 410 }, { "epoch": 0.17383966244725738, - "grad_norm": 1.8247230052947998, - "learning_rate": 3.6115992970123026e-05, - "loss": 0.8485683798789978, + "grad_norm": 0.5841867923736572, + "learning_rate": 7.223198594024605e-05, + "loss": 0.9926692247390747, "step": 412 }, { "epoch": 0.17468354430379746, - "grad_norm": 2.4608843326568604, - "learning_rate": 3.6291739894551845e-05, - "loss": 0.9325968623161316, + "grad_norm": 0.7125606536865234, + "learning_rate": 7.258347978910369e-05, + "loss": 1.0588877201080322, "step": 414 }, { "epoch": 0.17552742616033756, - "grad_norm": 1.8923161029815674, - "learning_rate": 3.646748681898067e-05, - "loss": 0.9125096201896667, + "grad_norm": 0.5750942230224609, + "learning_rate": 7.293497363796134e-05, + "loss": 1.038270354270935, "step": 416 }, { "epoch": 0.17637130801687764, - "grad_norm": 1.8502769470214844, - "learning_rate": 3.6643233743409497e-05, - "loss": 0.8852217197418213, + "grad_norm": 0.565444827079773, + "learning_rate": 7.328646748681899e-05, + "loss": 0.9843021035194397, "step": 418 }, { "epoch": 0.17721518987341772, - "grad_norm": 1.9155100584030151, - "learning_rate": 3.6818980667838316e-05, - "loss": 0.9192792773246765, + "grad_norm": 0.5825693011283875, + "learning_rate": 7.363796133567663e-05, + "loss": 1.0731632709503174, "step": 420 }, { "epoch": 0.1780590717299578, - "grad_norm": 2.181476593017578, - "learning_rate": 3.6994727592267135e-05, - "loss": 0.8787404298782349, + "grad_norm": 0.6267391443252563, + "learning_rate": 7.398945518453427e-05, + "loss": 1.0061273574829102, "step": 422 }, { "epoch": 0.17890295358649788, - "grad_norm": 2.2469847202301025, - "learning_rate": 3.717047451669596e-05, - "loss": 0.9109582901000977, + "grad_norm": 0.6621372103691101, + "learning_rate": 7.434094903339192e-05, + "loss": 1.0461612939834595, "step": 424 }, { "epoch": 0.17974683544303796, - "grad_norm": 2.08145809173584, - "learning_rate": 3.734622144112479e-05, - "loss": 0.8560389280319214, + "grad_norm": 0.6635435223579407, + "learning_rate": 7.469244288224957e-05, + "loss": 0.9789207577705383, "step": 426 }, { "epoch": 0.18059071729957807, - "grad_norm": 4.121932506561279, - "learning_rate": 3.7521968365553606e-05, - "loss": 0.9456104040145874, + "grad_norm": 0.6342346668243408, + "learning_rate": 7.504393673110721e-05, + "loss": 1.0527069568634033, "step": 428 }, { "epoch": 0.18143459915611815, - "grad_norm": 2.177459478378296, - "learning_rate": 3.7697715289982425e-05, - "loss": 0.8421300649642944, + "grad_norm": 0.6762149930000305, + "learning_rate": 7.539543057996485e-05, + "loss": 0.9708702564239502, "step": 430 }, { "epoch": 0.18227848101265823, - "grad_norm": 2.324970245361328, - "learning_rate": 3.787346221441125e-05, - "loss": 0.9199858903884888, + "grad_norm": 0.7073282599449158, + "learning_rate": 7.57469244288225e-05, + "loss": 1.0509834289550781, "step": 432 }, { "epoch": 0.1831223628691983, - "grad_norm": 2.133718490600586, - "learning_rate": 3.804920913884007e-05, - "loss": 0.8953126668930054, + "grad_norm": 0.6917856931686401, + "learning_rate": 7.609841827768014e-05, + "loss": 1.0128819942474365, "step": 434 }, { "epoch": 0.1839662447257384, - "grad_norm": 1.8527995347976685, - "learning_rate": 3.8224956063268896e-05, - "loss": 0.8732239007949829, + "grad_norm": 0.5574942231178284, + "learning_rate": 7.644991212653779e-05, + "loss": 0.989395797252655, "step": 436 }, { "epoch": 0.1848101265822785, - "grad_norm": 1.95817232131958, - "learning_rate": 3.8400702987697715e-05, - "loss": 0.8818746209144592, + "grad_norm": 0.640765905380249, + "learning_rate": 7.680140597539543e-05, + "loss": 0.9846042990684509, "step": 438 }, { "epoch": 0.18565400843881857, - "grad_norm": 2.2107293605804443, - "learning_rate": 3.857644991212654e-05, - "loss": 0.9153507947921753, + "grad_norm": 0.6699127554893494, + "learning_rate": 7.715289982425308e-05, + "loss": 1.0344442129135132, "step": 440 }, { "epoch": 0.18649789029535865, - "grad_norm": 2.004754066467285, - "learning_rate": 3.875219683655536e-05, - "loss": 0.8960154056549072, + "grad_norm": 0.6164930462837219, + "learning_rate": 7.750439367311072e-05, + "loss": 1.0179373025894165, "step": 442 }, { "epoch": 0.18734177215189873, - "grad_norm": 2.1851706504821777, - "learning_rate": 3.8927943760984186e-05, - "loss": 0.909011721611023, + "grad_norm": 0.6880720853805542, + "learning_rate": 7.785588752196837e-05, + "loss": 1.0518895387649536, "step": 444 }, { "epoch": 0.1881856540084388, - "grad_norm": 2.4492485523223877, - "learning_rate": 3.9103690685413005e-05, - "loss": 0.8880158066749573, + "grad_norm": 0.6501413583755493, + "learning_rate": 7.820738137082601e-05, + "loss": 1.0442606210708618, "step": 446 }, { "epoch": 0.1890295358649789, - "grad_norm": 2.745453119277954, - "learning_rate": 3.927943760984183e-05, - "loss": 0.8500842452049255, + "grad_norm": 0.6076085567474365, + "learning_rate": 7.855887521968366e-05, + "loss": 0.9828442335128784, "step": 448 }, { "epoch": 0.189873417721519, - "grad_norm": 2.1924264430999756, - "learning_rate": 3.945518453427065e-05, - "loss": 0.9004045724868774, + "grad_norm": 0.6418202519416809, + "learning_rate": 7.89103690685413e-05, + "loss": 1.0573710203170776, "step": 450 }, { "epoch": 0.19071729957805908, - "grad_norm": 2.4051687717437744, - "learning_rate": 3.9630931458699476e-05, - "loss": 0.9020664095878601, + "grad_norm": 0.7055076360702515, + "learning_rate": 7.926186291739895e-05, + "loss": 1.0216103792190552, "step": 452 }, { "epoch": 0.19156118143459916, - "grad_norm": 1.8077667951583862, - "learning_rate": 3.9806678383128295e-05, - "loss": 0.8639500737190247, + "grad_norm": 0.5668330192565918, + "learning_rate": 7.961335676625659e-05, + "loss": 0.9837722778320312, "step": 454 }, { "epoch": 0.19240506329113924, - "grad_norm": 2.089043378829956, - "learning_rate": 3.998242530755712e-05, - "loss": 0.8642048239707947, + "grad_norm": 0.6419380307197571, + "learning_rate": 7.996485061511424e-05, + "loss": 1.0003894567489624, "step": 456 }, { "epoch": 0.19324894514767932, - "grad_norm": 2.029578447341919, - "learning_rate": 4.015817223198594e-05, - "loss": 0.9371927380561829, + "grad_norm": 0.5949198007583618, + "learning_rate": 8.031634446397188e-05, + "loss": 1.0609031915664673, "step": 458 }, { "epoch": 0.1940928270042194, - "grad_norm": 2.26582407951355, - "learning_rate": 4.033391915641476e-05, - "loss": 0.9120588302612305, + "grad_norm": 0.7032039761543274, + "learning_rate": 8.066783831282952e-05, + "loss": 1.0543403625488281, "step": 460 }, { "epoch": 0.1949367088607595, - "grad_norm": 1.8671411275863647, - "learning_rate": 4.050966608084359e-05, - "loss": 0.8758644461631775, + "grad_norm": 0.5775868892669678, + "learning_rate": 8.101933216168718e-05, + "loss": 0.9819303154945374, "step": 462 }, { "epoch": 0.19578059071729959, - "grad_norm": 1.9403492212295532, - "learning_rate": 4.068541300527241e-05, - "loss": 0.914577305316925, + "grad_norm": 0.9301062226295471, + "learning_rate": 8.137082601054482e-05, + "loss": 1.0542067289352417, "step": 464 }, { "epoch": 0.19662447257383966, - "grad_norm": 1.9939641952514648, - "learning_rate": 4.086115992970123e-05, - "loss": 0.8592531681060791, + "grad_norm": 0.6193217039108276, + "learning_rate": 8.172231985940246e-05, + "loss": 0.9966341257095337, "step": 466 }, { "epoch": 0.19746835443037974, - "grad_norm": 2.1511380672454834, - "learning_rate": 4.103690685413005e-05, - "loss": 0.9251965880393982, + "grad_norm": 0.6286146640777588, + "learning_rate": 8.20738137082601e-05, + "loss": 1.0474121570587158, "step": 468 }, { "epoch": 0.19831223628691982, - "grad_norm": 2.2260982990264893, - "learning_rate": 4.121265377855888e-05, - "loss": 0.8465172052383423, + "grad_norm": 0.7418972253799438, + "learning_rate": 8.242530755711776e-05, + "loss": 0.9549239277839661, "step": 470 }, { "epoch": 0.1991561181434599, - "grad_norm": 2.0510010719299316, - "learning_rate": 4.13884007029877e-05, - "loss": 0.8943672180175781, + "grad_norm": 0.6122808456420898, + "learning_rate": 8.27768014059754e-05, + "loss": 1.0191338062286377, "step": 472 }, { "epoch": 0.2, - "grad_norm": 2.2040133476257324, - "learning_rate": 4.156414762741652e-05, - "loss": 0.9594319462776184, + "grad_norm": 0.6375362277030945, + "learning_rate": 8.312829525483304e-05, + "loss": 1.0987539291381836, "step": 474 }, { "epoch": 0.2008438818565401, - "grad_norm": 2.355181932449341, - "learning_rate": 4.173989455184534e-05, - "loss": 0.9031813144683838, + "grad_norm": 0.6459513306617737, + "learning_rate": 8.347978910369068e-05, + "loss": 1.0369136333465576, "step": 476 }, { "epoch": 0.20168776371308017, - "grad_norm": 2.8434665203094482, - "learning_rate": 4.1915641476274166e-05, - "loss": 0.9225798845291138, + "grad_norm": 0.7029640674591064, + "learning_rate": 8.383128295254833e-05, + "loss": 1.0582096576690674, "step": 478 }, { "epoch": 0.20253164556962025, - "grad_norm": 2.1715340614318848, - "learning_rate": 4.209138840070299e-05, - "loss": 0.894163966178894, + "grad_norm": 0.6345387697219849, + "learning_rate": 8.418277680140598e-05, + "loss": 1.022916316986084, "step": 480 }, { "epoch": 0.20337552742616033, - "grad_norm": 2.078916072845459, - "learning_rate": 4.226713532513181e-05, - "loss": 0.8424109816551208, + "grad_norm": 0.5764590501785278, + "learning_rate": 8.453427065026362e-05, + "loss": 0.973024308681488, "step": 482 }, { "epoch": 0.2042194092827004, - "grad_norm": 1.9760961532592773, - "learning_rate": 4.244288224956064e-05, - "loss": 0.9102715849876404, + "grad_norm": 0.5884482860565186, + "learning_rate": 8.488576449912127e-05, + "loss": 1.0292812585830688, "step": 484 }, { "epoch": 0.20506329113924052, - "grad_norm": 1.9684507846832275, - "learning_rate": 4.2618629173989456e-05, - "loss": 0.8693854808807373, + "grad_norm": 0.616357147693634, + "learning_rate": 8.523725834797891e-05, + "loss": 1.0083447694778442, "step": 486 }, { "epoch": 0.2059071729957806, - "grad_norm": 2.1633450984954834, - "learning_rate": 4.279437609841828e-05, - "loss": 0.8617543578147888, + "grad_norm": 0.7671196460723877, + "learning_rate": 8.558875219683656e-05, + "loss": 0.9936985373497009, "step": 488 }, { "epoch": 0.20675105485232068, - "grad_norm": 2.2695257663726807, - "learning_rate": 4.29701230228471e-05, - "loss": 0.9167086482048035, + "grad_norm": 0.6197299957275391, + "learning_rate": 8.59402460456942e-05, + "loss": 1.051513910293579, "step": 490 }, { "epoch": 0.20759493670886076, - "grad_norm": 2.4180049896240234, - "learning_rate": 4.314586994727593e-05, - "loss": 0.8333520889282227, + "grad_norm": 0.6912890672683716, + "learning_rate": 8.629173989455185e-05, + "loss": 0.9474978446960449, "step": 492 }, { "epoch": 0.20843881856540084, - "grad_norm": 2.2942769527435303, - "learning_rate": 4.3321616871704746e-05, - "loss": 0.918351411819458, + "grad_norm": 0.6941592693328857, + "learning_rate": 8.664323374340949e-05, + "loss": 1.0671660900115967, "step": 494 }, { "epoch": 0.20928270042194091, - "grad_norm": 1.826458215713501, - "learning_rate": 4.349736379613357e-05, - "loss": 0.8565171957015991, + "grad_norm": 0.5889528393745422, + "learning_rate": 8.699472759226714e-05, + "loss": 1.0020159482955933, "step": 496 }, { "epoch": 0.21012658227848102, - "grad_norm": 1.9694055318832397, - "learning_rate": 4.367311072056239e-05, - "loss": 0.8684167861938477, + "grad_norm": 0.6478549838066101, + "learning_rate": 8.734622144112478e-05, + "loss": 1.0165860652923584, "step": 498 }, { "epoch": 0.2109704641350211, - "grad_norm": 1.892659306526184, - "learning_rate": 4.384885764499122e-05, - "loss": 0.7752788662910461, + "grad_norm": 0.6018255949020386, + "learning_rate": 8.769771528998243e-05, + "loss": 0.8798263072967529, "step": 500 }, { "epoch": 0.2109704641350211, - "eval_loss": 0.9080732464790344, - "eval_runtime": 857.0753, - "eval_samples_per_second": 2.458, - "eval_steps_per_second": 2.458, + "eval_loss": 1.042096495628357, + "eval_runtime": 692.4361, + "eval_samples_per_second": 3.043, + "eval_steps_per_second": 3.043, "step": 500 }, { "epoch": 0.21181434599156118, - "grad_norm": 1.9322253465652466, - "learning_rate": 4.4024604569420036e-05, - "loss": 0.948570728302002, + "grad_norm": 0.578990638256073, + "learning_rate": 8.804920913884007e-05, + "loss": 1.092096209526062, "step": 502 }, { "epoch": 0.21265822784810126, - "grad_norm": 2.0456058979034424, - "learning_rate": 4.4200351493848855e-05, - "loss": 0.8741024732589722, + "grad_norm": 0.6597883701324463, + "learning_rate": 8.840070298769771e-05, + "loss": 1.0413451194763184, "step": 504 }, { "epoch": 0.21350210970464134, - "grad_norm": 2.2406177520751953, - "learning_rate": 4.437609841827768e-05, - "loss": 0.9053841829299927, + "grad_norm": 0.6660305261611938, + "learning_rate": 8.875219683655536e-05, + "loss": 1.0073142051696777, "step": 506 }, { "epoch": 0.21434599156118145, - "grad_norm": 2.013934850692749, - "learning_rate": 4.455184534270651e-05, - "loss": 0.8886576294898987, + "grad_norm": 0.6283115148544312, + "learning_rate": 8.910369068541301e-05, + "loss": 1.0319768190383911, "step": 508 }, { "epoch": 0.21518987341772153, - "grad_norm": 1.9771125316619873, - "learning_rate": 4.4727592267135326e-05, - "loss": 0.8834167718887329, + "grad_norm": 0.6257343292236328, + "learning_rate": 8.945518453427065e-05, + "loss": 1.0046353340148926, "step": 510 }, { "epoch": 0.2160337552742616, - "grad_norm": 1.785905361175537, - "learning_rate": 4.4903339191564146e-05, - "loss": 0.7938863039016724, + "grad_norm": 0.5530875325202942, + "learning_rate": 8.980667838312829e-05, + "loss": 0.9169099926948547, "step": 512 }, { "epoch": 0.2168776371308017, - "grad_norm": 1.7946031093597412, - "learning_rate": 4.507908611599297e-05, - "loss": 0.8071596026420593, + "grad_norm": 0.5369633436203003, + "learning_rate": 9.015817223198594e-05, + "loss": 0.9081505537033081, "step": 514 }, { "epoch": 0.21772151898734177, - "grad_norm": 2.2217721939086914, - "learning_rate": 4.52548330404218e-05, - "loss": 0.797417163848877, + "grad_norm": 0.6618232131004333, + "learning_rate": 9.05096660808436e-05, + "loss": 0.9165045022964478, "step": 516 }, { "epoch": 0.21856540084388185, - "grad_norm": 1.9022471904754639, - "learning_rate": 4.5430579964850617e-05, - "loss": 0.8109536170959473, + "grad_norm": 0.600666344165802, + "learning_rate": 9.086115992970123e-05, + "loss": 0.91348797082901, "step": 518 }, { "epoch": 0.21940928270042195, - "grad_norm": 1.8988343477249146, - "learning_rate": 4.5606326889279436e-05, - "loss": 0.8647034168243408, + "grad_norm": 0.5919831991195679, + "learning_rate": 9.121265377855887e-05, + "loss": 1.006508469581604, "step": 520 }, { "epoch": 0.22025316455696203, - "grad_norm": 2.6014881134033203, - "learning_rate": 4.578207381370827e-05, - "loss": 0.8763713240623474, + "grad_norm": 0.688058614730835, + "learning_rate": 9.156414762741654e-05, + "loss": 1.0013236999511719, "step": 522 }, { "epoch": 0.2210970464135021, - "grad_norm": 1.9512032270431519, - "learning_rate": 4.595782073813709e-05, - "loss": 0.9525764584541321, + "grad_norm": 0.6721227765083313, + "learning_rate": 9.191564147627418e-05, + "loss": 1.0909923315048218, "step": 524 }, { "epoch": 0.2219409282700422, - "grad_norm": 1.9246160984039307, - "learning_rate": 4.613356766256591e-05, - "loss": 0.8839208483695984, + "grad_norm": 0.5987313389778137, + "learning_rate": 9.226713532513181e-05, + "loss": 1.0117096900939941, "step": 526 }, { "epoch": 0.22278481012658227, - "grad_norm": 1.9713703393936157, - "learning_rate": 4.6309314586994726e-05, - "loss": 0.8888868093490601, + "grad_norm": 0.6191489696502686, + "learning_rate": 9.261862917398945e-05, + "loss": 1.0153647661209106, "step": 528 }, { "epoch": 0.22362869198312235, - "grad_norm": 2.1175239086151123, - "learning_rate": 4.648506151142355e-05, - "loss": 0.8123540878295898, + "grad_norm": 0.6821563243865967, + "learning_rate": 9.29701230228471e-05, + "loss": 0.9649755954742432, "step": 530 }, { "epoch": 0.22447257383966246, - "grad_norm": 1.7656135559082031, - "learning_rate": 4.666080843585238e-05, - "loss": 0.7447702884674072, + "grad_norm": 1.760398268699646, + "learning_rate": 9.332161687170476e-05, + "loss": 0.8673232197761536, "step": 532 }, { "epoch": 0.22531645569620254, - "grad_norm": 2.15748929977417, - "learning_rate": 4.68365553602812e-05, - "loss": 0.8778411746025085, + "grad_norm": 0.6670058369636536, + "learning_rate": 9.36731107205624e-05, + "loss": 0.9942440986633301, "step": 534 }, { "epoch": 0.22616033755274262, - "grad_norm": 2.1733345985412598, - "learning_rate": 4.7012302284710016e-05, - "loss": 0.8985894918441772, + "grad_norm": 0.7345916032791138, + "learning_rate": 9.402460456942003e-05, + "loss": 1.0364389419555664, "step": 536 }, { "epoch": 0.2270042194092827, - "grad_norm": 1.7182204723358154, - "learning_rate": 4.718804920913884e-05, - "loss": 0.8031114339828491, + "grad_norm": 0.5946128964424133, + "learning_rate": 9.437609841827768e-05, + "loss": 0.9314924478530884, "step": 538 }, { "epoch": 0.22784810126582278, - "grad_norm": 1.8586329221725464, - "learning_rate": 4.736379613356767e-05, - "loss": 0.9399706721305847, + "grad_norm": 0.5800848603248596, + "learning_rate": 9.472759226713534e-05, + "loss": 1.0694862604141235, "step": 540 }, { "epoch": 0.22869198312236286, - "grad_norm": 2.105637311935425, - "learning_rate": 4.753954305799649e-05, - "loss": 0.8672119975090027, + "grad_norm": 0.6712192893028259, + "learning_rate": 9.507908611599297e-05, + "loss": 1.03531014919281, "step": 542 }, { "epoch": 0.22953586497890296, - "grad_norm": 1.760584831237793, - "learning_rate": 4.771528998242531e-05, - "loss": 0.8663905262947083, + "grad_norm": 0.5641416311264038, + "learning_rate": 9.543057996485063e-05, + "loss": 0.9795235991477966, "step": 544 }, { "epoch": 0.23037974683544304, - "grad_norm": 1.579990267753601, - "learning_rate": 4.789103690685413e-05, - "loss": 0.8575801849365234, + "grad_norm": 0.50412517786026, + "learning_rate": 9.578207381370826e-05, + "loss": 0.9641494750976562, "step": 546 }, { "epoch": 0.23122362869198312, - "grad_norm": 1.9242485761642456, - "learning_rate": 4.806678383128295e-05, - "loss": 0.828412652015686, + "grad_norm": 0.579118549823761, + "learning_rate": 9.61335676625659e-05, + "loss": 0.9375281929969788, "step": 548 }, { "epoch": 0.2320675105485232, - "grad_norm": 1.812137246131897, - "learning_rate": 4.824253075571178e-05, - "loss": 0.8183464407920837, + "grad_norm": 0.5888341665267944, + "learning_rate": 9.648506151142355e-05, + "loss": 0.9414046406745911, "step": 550 }, { "epoch": 0.23291139240506328, - "grad_norm": 1.804733395576477, - "learning_rate": 4.84182776801406e-05, - "loss": 0.7822491526603699, + "grad_norm": 0.5595056414604187, + "learning_rate": 9.68365553602812e-05, + "loss": 0.9005617499351501, "step": 552 }, { "epoch": 0.23375527426160336, - "grad_norm": 2.052257537841797, - "learning_rate": 4.859402460456942e-05, - "loss": 0.9050943851470947, + "grad_norm": 0.6605326533317566, + "learning_rate": 9.718804920913884e-05, + "loss": 1.0283968448638916, "step": 554 }, { "epoch": 0.23459915611814347, - "grad_norm": 1.9803621768951416, - "learning_rate": 4.876977152899824e-05, - "loss": 0.8846852779388428, + "grad_norm": 0.5657313466072083, + "learning_rate": 9.753954305799648e-05, + "loss": 1.0058249235153198, "step": 556 }, { "epoch": 0.23544303797468355, - "grad_norm": 1.820125937461853, - "learning_rate": 4.894551845342707e-05, - "loss": 0.8649531602859497, + "grad_norm": 0.5433364510536194, + "learning_rate": 9.789103690685413e-05, + "loss": 0.9835494756698608, "step": 558 }, { "epoch": 0.23628691983122363, - "grad_norm": 2.0963921546936035, - "learning_rate": 4.912126537785589e-05, - "loss": 0.9307748079299927, + "grad_norm": 0.6129802465438843, + "learning_rate": 9.824253075571179e-05, + "loss": 1.054532527923584, "step": 560 }, { "epoch": 0.2371308016877637, - "grad_norm": 2.079697847366333, - "learning_rate": 4.929701230228471e-05, - "loss": 0.9092473387718201, + "grad_norm": 0.6496239304542542, + "learning_rate": 9.859402460456942e-05, + "loss": 1.0240973234176636, "step": 562 }, { "epoch": 0.2379746835443038, - "grad_norm": 2.0291287899017334, - "learning_rate": 4.947275922671353e-05, - "loss": 0.8976567983627319, + "grad_norm": 0.6380873918533325, + "learning_rate": 9.894551845342706e-05, + "loss": 1.0229179859161377, "step": 564 }, { "epoch": 0.23881856540084387, - "grad_norm": 1.9636707305908203, - "learning_rate": 4.964850615114236e-05, - "loss": 0.8931006193161011, + "grad_norm": 0.6151993870735168, + "learning_rate": 9.929701230228471e-05, + "loss": 1.0111570358276367, "step": 566 }, { "epoch": 0.23966244725738398, - "grad_norm": 1.922049880027771, - "learning_rate": 4.982425307557118e-05, - "loss": 0.829562246799469, + "grad_norm": 0.5727584958076477, + "learning_rate": 9.964850615114237e-05, + "loss": 0.9450829029083252, "step": 568 }, { "epoch": 0.24050632911392406, - "grad_norm": 2.150334596633911, - "learning_rate": 5e-05, - "loss": 0.8568030595779419, + "grad_norm": 0.6620725989341736, + "learning_rate": 0.0001, + "loss": 0.9800319075584412, "step": 570 }, { "epoch": 0.24135021097046414, - "grad_norm": 2.024437427520752, - "learning_rate": 5.017574692442882e-05, - "loss": 0.8623508810997009, + "grad_norm": 0.6151163578033447, + "learning_rate": 0.00010035149384885764, + "loss": 0.9757438898086548, "step": 572 }, { "epoch": 0.24219409282700421, - "grad_norm": 1.8312673568725586, - "learning_rate": 5.035149384885765e-05, - "loss": 0.7853795886039734, + "grad_norm": 0.5672140717506409, + "learning_rate": 0.0001007029876977153, + "loss": 0.9104921817779541, "step": 574 }, { "epoch": 0.2430379746835443, - "grad_norm": 1.9271961450576782, - "learning_rate": 5.0527240773286467e-05, - "loss": 0.9727587103843689, + "grad_norm": 0.5697256326675415, + "learning_rate": 0.00010105448154657293, + "loss": 1.1027376651763916, "step": 576 }, { "epoch": 0.2438818565400844, - "grad_norm": 1.931249976158142, - "learning_rate": 5.0702987697715286e-05, - "loss": 0.8859632015228271, + "grad_norm": 0.5590381622314453, + "learning_rate": 0.00010140597539543057, + "loss": 1.0055404901504517, "step": 578 }, { "epoch": 0.24472573839662448, - "grad_norm": 1.8195210695266724, - "learning_rate": 5.087873462214412e-05, - "loss": 0.8959492444992065, + "grad_norm": 0.5518567562103271, + "learning_rate": 0.00010175746924428824, + "loss": 1.020835518836975, "step": 580 }, { "epoch": 0.24556962025316456, - "grad_norm": 2.0018749237060547, - "learning_rate": 5.105448154657294e-05, - "loss": 0.8146185874938965, + "grad_norm": 0.6338496208190918, + "learning_rate": 0.00010210896309314588, + "loss": 0.9528344869613647, "step": 582 }, { "epoch": 0.24641350210970464, - "grad_norm": 2.09798526763916, - "learning_rate": 5.1230228471001764e-05, - "loss": 0.8545317053794861, + "grad_norm": 0.6497329473495483, + "learning_rate": 0.00010246045694200353, + "loss": 1.0088670253753662, "step": 584 }, { "epoch": 0.24725738396624472, - "grad_norm": 1.8063944578170776, - "learning_rate": 5.140597539543058e-05, - "loss": 0.8650105595588684, + "grad_norm": 0.49888095259666443, + "learning_rate": 0.00010281195079086117, + "loss": 0.9961200952529907, "step": 586 }, { "epoch": 0.2481012658227848, - "grad_norm": 1.8535740375518799, - "learning_rate": 5.15817223198594e-05, - "loss": 0.8395693302154541, + "grad_norm": 0.5680158734321594, + "learning_rate": 0.0001031634446397188, + "loss": 0.9635610580444336, "step": 588 }, { "epoch": 0.2489451476793249, - "grad_norm": 2.1443960666656494, - "learning_rate": 5.175746924428823e-05, - "loss": 0.8267397284507751, + "grad_norm": 0.658168375492096, + "learning_rate": 0.00010351493848857646, + "loss": 0.9392287135124207, "step": 590 }, { "epoch": 0.249789029535865, - "grad_norm": 1.9637391567230225, - "learning_rate": 5.193321616871705e-05, - "loss": 0.8500015139579773, + "grad_norm": 0.618262767791748, + "learning_rate": 0.0001038664323374341, + "loss": 0.9600516557693481, "step": 592 }, { "epoch": 0.25063291139240507, - "grad_norm": 1.9457582235336304, - "learning_rate": 5.2108963093145866e-05, - "loss": 0.887481153011322, + "grad_norm": 0.6003909111022949, + "learning_rate": 0.00010421792618629173, + "loss": 1.005476713180542, "step": 594 }, { "epoch": 0.2514767932489452, - "grad_norm": 1.7458715438842773, - "learning_rate": 5.228471001757469e-05, - "loss": 0.8444154858589172, + "grad_norm": 0.5437078475952148, + "learning_rate": 0.00010456942003514938, + "loss": 0.9523017406463623, "step": 596 }, { "epoch": 0.2523206751054852, - "grad_norm": 1.8341439962387085, - "learning_rate": 5.2460456942003525e-05, - "loss": 0.8301781415939331, + "grad_norm": 0.5524541735649109, + "learning_rate": 0.00010492091388400705, + "loss": 0.9526668787002563, "step": 598 }, { "epoch": 0.25316455696202533, - "grad_norm": 2.127747058868408, - "learning_rate": 5.2636203866432344e-05, - "loss": 0.8921551704406738, + "grad_norm": 0.679504930973053, + "learning_rate": 0.00010527240773286469, + "loss": 1.019660472869873, "step": 600 }, { "epoch": 0.25316455696202533, - "eval_loss": 0.8903881311416626, - "eval_runtime": 845.9969, - "eval_samples_per_second": 2.491, - "eval_steps_per_second": 2.491, + "eval_loss": 1.0193854570388794, + "eval_runtime": 677.9523, + "eval_samples_per_second": 3.108, + "eval_steps_per_second": 3.108, "step": 600 }, { "epoch": 0.2540084388185654, - "grad_norm": 2.421459674835205, - "learning_rate": 5.281195079086116e-05, - "loss": 0.8678019642829895, + "grad_norm": 0.5646136999130249, + "learning_rate": 0.00010562390158172233, + "loss": 0.9910882711410522, "step": 602 }, { "epoch": 0.2548523206751055, - "grad_norm": 1.7736057043075562, - "learning_rate": 5.298769771528999e-05, - "loss": 0.8564275503158569, + "grad_norm": 0.5238093137741089, + "learning_rate": 0.00010597539543057998, + "loss": 0.9616432785987854, "step": 604 }, { "epoch": 0.25569620253164554, - "grad_norm": 2.28430438041687, - "learning_rate": 5.316344463971881e-05, - "loss": 0.8529049158096313, + "grad_norm": 0.7483857274055481, + "learning_rate": 0.00010632688927943762, + "loss": 1.0078275203704834, "step": 606 }, { "epoch": 0.25654008438818565, - "grad_norm": 1.8892366886138916, - "learning_rate": 5.333919156414763e-05, - "loss": 0.8672881126403809, + "grad_norm": 0.578948974609375, + "learning_rate": 0.00010667838312829525, + "loss": 0.9827103018760681, "step": 608 }, { "epoch": 0.25738396624472576, - "grad_norm": 1.9059702157974243, - "learning_rate": 5.3514938488576446e-05, - "loss": 0.9094445109367371, + "grad_norm": 0.5525906085968018, + "learning_rate": 0.00010702987697715289, + "loss": 1.0423277616500854, "step": 610 }, { "epoch": 0.2582278481012658, - "grad_norm": 2.0657339096069336, - "learning_rate": 5.369068541300527e-05, - "loss": 0.8361946940422058, + "grad_norm": 0.6721326112747192, + "learning_rate": 0.00010738137082601054, + "loss": 0.9561693072319031, "step": 612 }, { "epoch": 0.2590717299578059, - "grad_norm": 1.8987553119659424, - "learning_rate": 5.3866432337434105e-05, - "loss": 0.8319925665855408, + "grad_norm": 0.5701051354408264, + "learning_rate": 0.00010773286467486821, + "loss": 0.9602992534637451, "step": 614 }, { "epoch": 0.25991561181434597, - "grad_norm": 2.1176226139068604, - "learning_rate": 5.4042179261862924e-05, - "loss": 0.9818069934844971, + "grad_norm": 0.6349860429763794, + "learning_rate": 0.00010808435852372585, + "loss": 1.1422650814056396, "step": 616 }, { "epoch": 0.2607594936708861, - "grad_norm": 2.142096519470215, - "learning_rate": 5.421792618629174e-05, - "loss": 0.8675919771194458, + "grad_norm": 0.5496085286140442, + "learning_rate": 0.00010843585237258349, + "loss": 0.9762773513793945, "step": 618 }, { "epoch": 0.2616033755274262, - "grad_norm": 1.9527089595794678, - "learning_rate": 5.439367311072057e-05, - "loss": 0.8845479488372803, + "grad_norm": 0.6080722808837891, + "learning_rate": 0.00010878734622144114, + "loss": 1.0133616924285889, "step": 620 }, { "epoch": 0.26244725738396624, - "grad_norm": 1.7071453332901, - "learning_rate": 5.456942003514939e-05, - "loss": 0.809393048286438, + "grad_norm": 0.5450218915939331, + "learning_rate": 0.00010913884007029878, + "loss": 0.9385587573051453, "step": 622 }, { "epoch": 0.26329113924050634, - "grad_norm": 1.9133527278900146, - "learning_rate": 5.474516695957821e-05, - "loss": 0.8262377977371216, + "grad_norm": 0.592106819152832, + "learning_rate": 0.00010949033391915641, + "loss": 0.9359989762306213, "step": 624 }, { "epoch": 0.2641350210970464, - "grad_norm": 2.0217554569244385, - "learning_rate": 5.492091388400703e-05, - "loss": 0.9006736278533936, + "grad_norm": 0.6449427604675293, + "learning_rate": 0.00010984182776801407, + "loss": 1.0266027450561523, "step": 626 }, { "epoch": 0.2649789029535865, - "grad_norm": 1.773273229598999, - "learning_rate": 5.509666080843585e-05, - "loss": 0.8243603110313416, + "grad_norm": 0.538299560546875, + "learning_rate": 0.0001101933216168717, + "loss": 0.9303187131881714, "step": 628 }, { "epoch": 0.26582278481012656, - "grad_norm": 1.6580880880355835, - "learning_rate": 5.527240773286467e-05, - "loss": 0.8112778663635254, + "grad_norm": 0.546316921710968, + "learning_rate": 0.00011054481546572934, + "loss": 0.9368857145309448, "step": 630 }, { "epoch": 0.26666666666666666, - "grad_norm": 1.8342082500457764, - "learning_rate": 5.5448154657293504e-05, - "loss": 0.8390820622444153, + "grad_norm": 0.5818730592727661, + "learning_rate": 0.00011089630931458701, + "loss": 0.9573145508766174, "step": 632 }, { "epoch": 0.26751054852320677, - "grad_norm": 1.863695502281189, - "learning_rate": 5.5623901581722323e-05, - "loss": 0.8264521360397339, + "grad_norm": 0.5958262085914612, + "learning_rate": 0.00011124780316344465, + "loss": 0.9345449805259705, "step": 634 }, { "epoch": 0.2683544303797468, - "grad_norm": 1.9462928771972656, - "learning_rate": 5.579964850615115e-05, - "loss": 0.9512701630592346, + "grad_norm": 0.6259077787399292, + "learning_rate": 0.0001115992970123023, + "loss": 1.0906590223312378, "step": 636 }, { "epoch": 0.26919831223628693, - "grad_norm": 1.7776058912277222, - "learning_rate": 5.597539543057997e-05, - "loss": 0.9422703981399536, + "grad_norm": 0.589672863483429, + "learning_rate": 0.00011195079086115994, + "loss": 1.0757447481155396, "step": 638 }, { "epoch": 0.270042194092827, - "grad_norm": 2.9457077980041504, - "learning_rate": 5.615114235500879e-05, - "loss": 0.7991042137145996, + "grad_norm": 0.5714080333709717, + "learning_rate": 0.00011230228471001758, + "loss": 0.9310855269432068, "step": 640 }, { "epoch": 0.2708860759493671, - "grad_norm": 1.445265531539917, - "learning_rate": 5.6326889279437614e-05, - "loss": 0.8188099265098572, + "grad_norm": 0.45342639088630676, + "learning_rate": 0.00011265377855887523, + "loss": 0.9276360273361206, "step": 642 }, { "epoch": 0.2717299578059072, - "grad_norm": 2.063850164413452, - "learning_rate": 5.650263620386643e-05, - "loss": 0.9799772500991821, + "grad_norm": 0.6386750340461731, + "learning_rate": 0.00011300527240773287, + "loss": 1.084719181060791, "step": 644 }, { "epoch": 0.27257383966244725, - "grad_norm": 2.0488009452819824, - "learning_rate": 5.667838312829525e-05, - "loss": 0.8462742567062378, + "grad_norm": 0.6446163654327393, + "learning_rate": 0.0001133567662565905, + "loss": 0.9763918519020081, "step": 646 }, { "epoch": 0.27341772151898736, - "grad_norm": 1.8747851848602295, - "learning_rate": 5.685413005272408e-05, - "loss": 0.8226412534713745, + "grad_norm": 0.5925686359405518, + "learning_rate": 0.00011370826010544816, + "loss": 0.9517921805381775, "step": 648 }, { "epoch": 0.2742616033755274, - "grad_norm": 1.849074125289917, - "learning_rate": 5.702987697715291e-05, - "loss": 0.9146338105201721, + "grad_norm": 0.5399773716926575, + "learning_rate": 0.00011405975395430582, + "loss": 1.0587927103042603, "step": 650 }, { "epoch": 0.2751054852320675, - "grad_norm": 1.7738500833511353, - "learning_rate": 5.720562390158173e-05, - "loss": 0.7574424147605896, + "grad_norm": 0.5872456431388855, + "learning_rate": 0.00011441124780316346, + "loss": 0.883341908454895, "step": 652 }, { "epoch": 0.2759493670886076, - "grad_norm": 1.911102294921875, - "learning_rate": 5.738137082601055e-05, - "loss": 0.8930003046989441, + "grad_norm": 0.5574564337730408, + "learning_rate": 0.0001147627416520211, + "loss": 1.0306891202926636, "step": 654 }, { "epoch": 0.2767932489451477, - "grad_norm": 1.5716617107391357, - "learning_rate": 5.755711775043937e-05, - "loss": 0.7578965425491333, + "grad_norm": 0.47789013385772705, + "learning_rate": 0.00011511423550087874, + "loss": 0.8814032077789307, "step": 656 }, { "epoch": 0.2776371308016878, - "grad_norm": 1.789036512374878, - "learning_rate": 5.7732864674868194e-05, - "loss": 0.8149038553237915, + "grad_norm": 0.5565530061721802, + "learning_rate": 0.00011546572934973639, + "loss": 0.9460552334785461, "step": 658 }, { "epoch": 0.27848101265822783, - "grad_norm": 1.68622624874115, - "learning_rate": 5.790861159929701e-05, - "loss": 0.8265765905380249, + "grad_norm": 0.5299761295318604, + "learning_rate": 0.00011581722319859403, + "loss": 0.9475110769271851, "step": 660 }, { "epoch": 0.27932489451476794, - "grad_norm": 2.078423261642456, - "learning_rate": 5.808435852372583e-05, - "loss": 0.9651970267295837, + "grad_norm": 0.6503344178199768, + "learning_rate": 0.00011616871704745166, + "loss": 1.0630913972854614, "step": 662 }, { "epoch": 0.280168776371308, - "grad_norm": 1.7878645658493042, - "learning_rate": 5.826010544815466e-05, - "loss": 0.8295148015022278, + "grad_norm": 0.5794585943222046, + "learning_rate": 0.00011652021089630932, + "loss": 0.9389138221740723, "step": 664 }, { "epoch": 0.2810126582278481, - "grad_norm": 1.970838189125061, - "learning_rate": 5.843585237258348e-05, - "loss": 0.7778491377830505, + "grad_norm": 0.5762867331504822, + "learning_rate": 0.00011687170474516695, + "loss": 0.8934136033058167, "step": 666 }, { "epoch": 0.2818565400843882, - "grad_norm": 1.943596363067627, - "learning_rate": 5.861159929701231e-05, - "loss": 0.9818071722984314, + "grad_norm": 0.6565435528755188, + "learning_rate": 0.00011722319859402462, + "loss": 1.1072614192962646, "step": 668 }, { "epoch": 0.28270042194092826, - "grad_norm": 1.8793812990188599, - "learning_rate": 5.878734622144113e-05, - "loss": 0.9297797083854675, + "grad_norm": 0.5819830298423767, + "learning_rate": 0.00011757469244288226, + "loss": 1.0501434803009033, "step": 670 }, { "epoch": 0.28354430379746837, - "grad_norm": 1.8813483715057373, - "learning_rate": 5.8963093145869955e-05, - "loss": 0.8748109936714172, + "grad_norm": 0.6071487069129944, + "learning_rate": 0.00011792618629173991, + "loss": 0.9880793690681458, "step": 672 }, { "epoch": 0.2843881856540084, - "grad_norm": 1.7658562660217285, - "learning_rate": 5.9138840070298774e-05, - "loss": 0.8505244851112366, + "grad_norm": 0.5765058398246765, + "learning_rate": 0.00011827768014059755, + "loss": 0.9670693874359131, "step": 674 }, { "epoch": 0.2852320675105485, - "grad_norm": 1.6767617464065552, - "learning_rate": 5.931458699472759e-05, - "loss": 0.8476597666740417, + "grad_norm": 0.5245351791381836, + "learning_rate": 0.00011862917398945519, + "loss": 0.9602360725402832, "step": 676 }, { "epoch": 0.28607594936708863, - "grad_norm": 2.703104257583618, - "learning_rate": 5.949033391915641e-05, - "loss": 0.8775192499160767, + "grad_norm": 0.6189922094345093, + "learning_rate": 0.00011898066783831282, + "loss": 0.9684560894966125, "step": 678 }, { "epoch": 0.2869198312236287, - "grad_norm": 1.9959728717803955, - "learning_rate": 5.966608084358524e-05, - "loss": 0.855262279510498, + "grad_norm": 0.6138690710067749, + "learning_rate": 0.00011933216168717048, + "loss": 0.9465792775154114, "step": 680 }, { "epoch": 0.2877637130801688, - "grad_norm": 1.9093716144561768, - "learning_rate": 5.984182776801406e-05, - "loss": 0.7574936151504517, + "grad_norm": 0.5371595621109009, + "learning_rate": 0.00011968365553602812, + "loss": 0.8495944738388062, "step": 682 }, { "epoch": 0.28860759493670884, - "grad_norm": 1.9829599857330322, - "learning_rate": 6.001757469244289e-05, - "loss": 0.8630690574645996, + "grad_norm": 0.5549944639205933, + "learning_rate": 0.00012003514938488578, + "loss": 0.9663267135620117, "step": 684 }, { "epoch": 0.28945147679324895, - "grad_norm": 1.8777490854263306, - "learning_rate": 6.019332161687171e-05, - "loss": 0.8513249158859253, + "grad_norm": 0.6484189033508301, + "learning_rate": 0.00012038664323374342, + "loss": 0.9736058712005615, "step": 686 }, { "epoch": 0.290295358649789, - "grad_norm": 1.9453173875808716, - "learning_rate": 6.0369068541300535e-05, - "loss": 0.9097008109092712, + "grad_norm": 0.540351390838623, + "learning_rate": 0.00012073813708260107, + "loss": 1.0591845512390137, "step": 688 }, { "epoch": 0.2911392405063291, - "grad_norm": 1.8527908325195312, - "learning_rate": 6.0544815465729354e-05, - "loss": 0.8291722536087036, + "grad_norm": 0.5657922029495239, + "learning_rate": 0.00012108963093145871, + "loss": 0.944908618927002, "step": 690 }, { "epoch": 0.2919831223628692, - "grad_norm": 1.9255812168121338, - "learning_rate": 6.0720562390158174e-05, - "loss": 0.880009651184082, + "grad_norm": 0.6040505170822144, + "learning_rate": 0.00012144112478031635, + "loss": 1.0018219947814941, "step": 692 }, { "epoch": 0.29282700421940927, - "grad_norm": 1.6637977361679077, - "learning_rate": 6.0896309314587e-05, - "loss": 0.8791794180870056, + "grad_norm": 0.5435477495193481, + "learning_rate": 0.000121792618629174, + "loss": 1.0351502895355225, "step": 694 }, { "epoch": 0.2936708860759494, - "grad_norm": 1.825940728187561, - "learning_rate": 6.107205623901582e-05, - "loss": 0.8662407398223877, + "grad_norm": 0.5712518692016602, + "learning_rate": 0.00012214411247803164, + "loss": 0.9935672283172607, "step": 696 }, { "epoch": 0.29451476793248943, - "grad_norm": 1.9348198175430298, - "learning_rate": 6.124780316344464e-05, - "loss": 0.8984515070915222, + "grad_norm": 0.6138222813606262, + "learning_rate": 0.00012249560632688928, + "loss": 1.0165108442306519, "step": 698 }, { "epoch": 0.29535864978902954, - "grad_norm": 1.659345030784607, - "learning_rate": 6.142355008787346e-05, - "loss": 0.827385663986206, + "grad_norm": 0.4495212435722351, + "learning_rate": 0.00012284710017574691, + "loss": 0.9334425926208496, "step": 700 }, { "epoch": 0.29535864978902954, - "eval_loss": 0.8730722069740295, - "eval_runtime": 858.184, - "eval_samples_per_second": 2.455, - "eval_steps_per_second": 2.455, + "eval_loss": 0.996929407119751, + "eval_runtime": 668.6398, + "eval_samples_per_second": 3.151, + "eval_steps_per_second": 3.151, "step": 700 }, { "epoch": 0.29620253164556964, - "grad_norm": 1.6531789302825928, - "learning_rate": 6.159929701230229e-05, - "loss": 0.9337764382362366, + "grad_norm": 0.5321539044380188, + "learning_rate": 0.00012319859402460458, + "loss": 1.0516537427902222, "step": 702 }, { "epoch": 0.2970464135021097, - "grad_norm": 1.8269121646881104, - "learning_rate": 6.177504393673111e-05, - "loss": 0.8250943422317505, + "grad_norm": 0.5716516971588135, + "learning_rate": 0.00012355008787346222, + "loss": 0.9387198686599731, "step": 704 }, { "epoch": 0.2978902953586498, - "grad_norm": 1.692808747291565, - "learning_rate": 6.195079086115994e-05, - "loss": 0.8657428026199341, + "grad_norm": 0.5617920160293579, + "learning_rate": 0.00012390158172231988, + "loss": 0.99737948179245, "step": 706 }, { "epoch": 0.29873417721518986, - "grad_norm": 1.6736913919448853, - "learning_rate": 6.212653778558876e-05, - "loss": 0.8889590501785278, + "grad_norm": 0.4922899007797241, + "learning_rate": 0.00012425307557117752, + "loss": 0.9955025911331177, "step": 708 }, { "epoch": 0.29957805907172996, - "grad_norm": 1.6841140985488892, - "learning_rate": 6.230228471001758e-05, - "loss": 0.7822914123535156, + "grad_norm": 0.543501615524292, + "learning_rate": 0.00012460456942003516, + "loss": 0.9124280214309692, "step": 710 }, { "epoch": 0.30042194092827, - "grad_norm": 1.6644599437713623, - "learning_rate": 6.24780316344464e-05, - "loss": 0.8747053742408752, + "grad_norm": 0.49590054154396057, + "learning_rate": 0.0001249560632688928, + "loss": 0.9820216298103333, "step": 712 }, { "epoch": 0.3012658227848101, - "grad_norm": 1.8187819719314575, - "learning_rate": 6.265377855887522e-05, - "loss": 0.8976446390151978, + "grad_norm": 0.5984305739402771, + "learning_rate": 0.00012530755711775044, + "loss": 1.0152074098587036, "step": 714 }, { "epoch": 0.30210970464135023, - "grad_norm": 1.7845178842544556, - "learning_rate": 6.282952548330404e-05, - "loss": 0.9401160478591919, + "grad_norm": 0.9343504905700684, + "learning_rate": 0.00012565905096660807, + "loss": 1.0577725172042847, "step": 716 }, { "epoch": 0.3029535864978903, - "grad_norm": 1.559773564338684, - "learning_rate": 6.300527240773286e-05, - "loss": 0.8754280209541321, + "grad_norm": 0.5118702054023743, + "learning_rate": 0.0001260105448154657, + "loss": 0.9830358028411865, "step": 718 }, { "epoch": 0.3037974683544304, - "grad_norm": 1.5919631719589233, - "learning_rate": 6.318101933216169e-05, - "loss": 0.8278581500053406, + "grad_norm": 0.4940392076969147, + "learning_rate": 0.00012636203866432338, + "loss": 0.9466043710708618, "step": 720 }, { "epoch": 0.30464135021097044, - "grad_norm": 1.8551076650619507, - "learning_rate": 6.335676625659052e-05, - "loss": 0.8868640065193176, + "grad_norm": 0.5965693593025208, + "learning_rate": 0.00012671353251318104, + "loss": 1.015270709991455, "step": 722 }, { "epoch": 0.30548523206751055, - "grad_norm": 1.6907769441604614, - "learning_rate": 6.353251318101934e-05, - "loss": 0.8631605505943298, + "grad_norm": 0.5020529627799988, + "learning_rate": 0.00012706502636203868, + "loss": 0.9703927636146545, "step": 724 }, { "epoch": 0.30632911392405066, - "grad_norm": 1.820867657661438, - "learning_rate": 6.370826010544816e-05, - "loss": 0.9142873883247375, + "grad_norm": 0.6067010164260864, + "learning_rate": 0.00012741652021089632, + "loss": 1.0255526304244995, "step": 726 }, { "epoch": 0.3071729957805907, - "grad_norm": 1.685154676437378, - "learning_rate": 6.388400702987698e-05, - "loss": 0.8258634805679321, + "grad_norm": 0.5931884050369263, + "learning_rate": 0.00012776801405975396, + "loss": 0.9335633516311646, "step": 728 }, { "epoch": 0.3080168776371308, - "grad_norm": 1.9294627904891968, - "learning_rate": 6.40597539543058e-05, - "loss": 0.9545516967773438, + "grad_norm": 0.5938752293586731, + "learning_rate": 0.0001281195079086116, + "loss": 1.0921578407287598, "step": 730 }, { "epoch": 0.30886075949367087, - "grad_norm": 1.6075409650802612, - "learning_rate": 6.423550087873462e-05, - "loss": 0.8370757699012756, + "grad_norm": 0.49728086590766907, + "learning_rate": 0.00012847100175746923, + "loss": 0.963066041469574, "step": 732 }, { "epoch": 0.309704641350211, - "grad_norm": 1.635750651359558, - "learning_rate": 6.441124780316345e-05, - "loss": 0.8356084823608398, + "grad_norm": 0.5452080965042114, + "learning_rate": 0.0001288224956063269, + "loss": 0.9513075351715088, "step": 734 }, { "epoch": 0.3105485232067511, - "grad_norm": 1.6376131772994995, - "learning_rate": 6.458699472759227e-05, - "loss": 0.7579531669616699, + "grad_norm": 0.5497731566429138, + "learning_rate": 0.00012917398945518454, + "loss": 0.8576077222824097, "step": 736 }, { "epoch": 0.31139240506329113, - "grad_norm": 1.7135766744613647, - "learning_rate": 6.47627416520211e-05, - "loss": 0.8436318039894104, + "grad_norm": 0.5580397248268127, + "learning_rate": 0.0001295254833040422, + "loss": 0.9542577862739563, "step": 738 }, { "epoch": 0.31223628691983124, - "grad_norm": 1.7095093727111816, - "learning_rate": 6.493848857644992e-05, - "loss": 0.7998805046081543, + "grad_norm": 0.5890427827835083, + "learning_rate": 0.00012987697715289984, + "loss": 0.8992732167243958, "step": 740 }, { "epoch": 0.3130801687763713, - "grad_norm": 1.782615303993225, - "learning_rate": 6.511423550087874e-05, - "loss": 0.915776789188385, + "grad_norm": 0.5942965745925903, + "learning_rate": 0.00013022847100175748, + "loss": 1.0322896242141724, "step": 742 }, { "epoch": 0.3139240506329114, - "grad_norm": 1.8461172580718994, - "learning_rate": 6.528998242530756e-05, - "loss": 0.8300962448120117, + "grad_norm": 0.6341713070869446, + "learning_rate": 0.00013057996485061512, + "loss": 0.9217103719711304, "step": 744 }, { "epoch": 0.31476793248945145, - "grad_norm": 1.5659871101379395, - "learning_rate": 6.546572934973638e-05, - "loss": 0.8239848017692566, + "grad_norm": 0.5294105410575867, + "learning_rate": 0.00013093145869947276, + "loss": 0.951789915561676, "step": 746 }, { "epoch": 0.31561181434599156, - "grad_norm": 1.9997349977493286, - "learning_rate": 6.56414762741652e-05, - "loss": 0.8236988186836243, + "grad_norm": 0.6372058391571045, + "learning_rate": 0.0001312829525483304, + "loss": 0.9459875226020813, "step": 748 }, { "epoch": 0.31645569620253167, - "grad_norm": 1.9811526536941528, - "learning_rate": 6.581722319859403e-05, - "loss": 0.8516603112220764, + "grad_norm": 0.5979796648025513, + "learning_rate": 0.00013163444639718806, + "loss": 0.9626097679138184, "step": 750 }, { "epoch": 0.3172995780590717, - "grad_norm": 1.9877923727035522, - "learning_rate": 6.599297012302285e-05, - "loss": 0.9037567973136902, + "grad_norm": 0.5682399868965149, + "learning_rate": 0.0001319859402460457, + "loss": 1.0261781215667725, "step": 752 }, { "epoch": 0.3181434599156118, - "grad_norm": 1.6729352474212646, - "learning_rate": 6.616871704745168e-05, - "loss": 0.8350864052772522, + "grad_norm": 0.5349125266075134, + "learning_rate": 0.00013233743409490336, + "loss": 0.9319828152656555, "step": 754 }, { "epoch": 0.3189873417721519, - "grad_norm": 1.9055802822113037, - "learning_rate": 6.63444639718805e-05, - "loss": 0.8246616125106812, + "grad_norm": 0.6093934178352356, + "learning_rate": 0.000132688927943761, + "loss": 0.9216550588607788, "step": 756 }, { "epoch": 0.319831223628692, - "grad_norm": 1.597999930381775, - "learning_rate": 6.652021089630932e-05, - "loss": 0.8014416098594666, + "grad_norm": 0.5188612341880798, + "learning_rate": 0.00013304042179261864, + "loss": 0.901739776134491, "step": 758 }, { "epoch": 0.3206751054852321, - "grad_norm": 1.7432531118392944, - "learning_rate": 6.669595782073814e-05, - "loss": 0.9199523329734802, + "grad_norm": 0.5877130627632141, + "learning_rate": 0.00013339191564147628, + "loss": 1.0362589359283447, "step": 760 }, { "epoch": 0.32151898734177214, - "grad_norm": 1.820164442062378, - "learning_rate": 6.687170474516696e-05, - "loss": 0.7764829397201538, + "grad_norm": 0.5542771816253662, + "learning_rate": 0.00013374340949033392, + "loss": 0.8787116408348083, "step": 762 }, { "epoch": 0.32236286919831225, - "grad_norm": 1.6408652067184448, - "learning_rate": 6.704745166959578e-05, - "loss": 0.8072620630264282, + "grad_norm": 0.5084902048110962, + "learning_rate": 0.00013409490333919156, + "loss": 0.9237037301063538, "step": 764 }, { "epoch": 0.3232067510548523, - "grad_norm": 1.8894155025482178, - "learning_rate": 6.722319859402461e-05, - "loss": 0.9006885886192322, + "grad_norm": 0.5461528301239014, + "learning_rate": 0.00013444639718804922, + "loss": 1.0150731801986694, "step": 766 }, { "epoch": 0.3240506329113924, - "grad_norm": 1.6903613805770874, - "learning_rate": 6.739894551845343e-05, - "loss": 0.7772189378738403, + "grad_norm": 0.53483647108078, + "learning_rate": 0.00013479789103690686, + "loss": 0.8985214829444885, "step": 768 }, { "epoch": 0.32489451476793246, - "grad_norm": 1.7540696859359741, - "learning_rate": 6.757469244288225e-05, - "loss": 0.8825590014457703, + "grad_norm": 0.5580531358718872, + "learning_rate": 0.0001351493848857645, + "loss": 1.0225775241851807, "step": 770 }, { "epoch": 0.32573839662447257, - "grad_norm": 1.603008508682251, - "learning_rate": 6.775043936731108e-05, - "loss": 0.8376453518867493, + "grad_norm": 0.5203377604484558, + "learning_rate": 0.00013550087873462216, + "loss": 0.9571293592453003, "step": 772 }, { "epoch": 0.3265822784810127, - "grad_norm": 1.5381462574005127, - "learning_rate": 6.79261862917399e-05, - "loss": 0.92608243227005, + "grad_norm": 0.5049671530723572, + "learning_rate": 0.0001358523725834798, + "loss": 1.0468909740447998, "step": 774 }, { "epoch": 0.32742616033755273, - "grad_norm": 1.4815537929534912, - "learning_rate": 6.810193321616872e-05, - "loss": 0.6842183470726013, + "grad_norm": 0.4723063111305237, + "learning_rate": 0.00013620386643233744, + "loss": 0.7743215560913086, "step": 776 }, { "epoch": 0.32827004219409284, - "grad_norm": 1.8543411493301392, - "learning_rate": 6.827768014059754e-05, - "loss": 0.8868235349655151, + "grad_norm": 0.6310980916023254, + "learning_rate": 0.00013655536028119508, + "loss": 1.021510362625122, "step": 778 }, { "epoch": 0.3291139240506329, - "grad_norm": 1.8895748853683472, - "learning_rate": 6.845342706502637e-05, - "loss": 0.8148112297058105, + "grad_norm": 0.47066664695739746, + "learning_rate": 0.00013690685413005274, + "loss": 0.9134382605552673, "step": 780 }, { "epoch": 0.329957805907173, - "grad_norm": 1.8150591850280762, - "learning_rate": 6.862917398945519e-05, - "loss": 0.8760337829589844, + "grad_norm": 0.5725092887878418, + "learning_rate": 0.00013725834797891038, + "loss": 0.9797834753990173, "step": 782 }, { "epoch": 0.3308016877637131, - "grad_norm": 1.6661378145217896, - "learning_rate": 6.880492091388401e-05, - "loss": 0.8266322612762451, + "grad_norm": 0.5139563083648682, + "learning_rate": 0.00013760984182776802, + "loss": 0.9372621178627014, "step": 784 }, { "epoch": 0.33164556962025316, - "grad_norm": 2.2849128246307373, - "learning_rate": 6.898066783831283e-05, - "loss": 0.8599053025245667, + "grad_norm": 0.5275821685791016, + "learning_rate": 0.00013796133567662566, + "loss": 0.9528245329856873, "step": 786 }, { "epoch": 0.33248945147679326, - "grad_norm": 1.7233171463012695, - "learning_rate": 6.915641476274165e-05, - "loss": 0.8312317132949829, + "grad_norm": 0.5702582001686096, + "learning_rate": 0.0001383128295254833, + "loss": 0.9750176072120667, "step": 788 }, { "epoch": 0.3333333333333333, - "grad_norm": 1.7637618780136108, - "learning_rate": 6.933216168717048e-05, - "loss": 0.8379700779914856, + "grad_norm": 0.5281293392181396, + "learning_rate": 0.00013866432337434096, + "loss": 0.9412306547164917, "step": 790 }, { "epoch": 0.3341772151898734, - "grad_norm": 1.7780474424362183, - "learning_rate": 6.95079086115993e-05, - "loss": 0.8994934558868408, + "grad_norm": 0.5578986406326294, + "learning_rate": 0.0001390158172231986, + "loss": 0.997580885887146, "step": 792 }, { "epoch": 0.33502109704641353, - "grad_norm": 1.5798883438110352, - "learning_rate": 6.968365553602812e-05, - "loss": 0.8021857738494873, + "grad_norm": 0.50461345911026, + "learning_rate": 0.00013936731107205624, + "loss": 0.9082320928573608, "step": 794 }, { "epoch": 0.3358649789029536, - "grad_norm": 1.7316070795059204, - "learning_rate": 6.985940246045695e-05, - "loss": 0.8814419507980347, + "grad_norm": 0.5258530378341675, + "learning_rate": 0.0001397188049209139, + "loss": 1.0082844495773315, "step": 796 }, { "epoch": 0.3367088607594937, - "grad_norm": 1.711315631866455, - "learning_rate": 7.003514938488577e-05, - "loss": 0.8545029163360596, + "grad_norm": 0.5548169016838074, + "learning_rate": 0.00014007029876977154, + "loss": 0.9729003310203552, "step": 798 }, { "epoch": 0.33755274261603374, - "grad_norm": 1.5023137331008911, - "learning_rate": 7.021089630931459e-05, - "loss": 0.8006189465522766, + "grad_norm": 0.48601076006889343, + "learning_rate": 0.00014042179261862918, + "loss": 0.9099526405334473, "step": 800 }, { "epoch": 0.33755274261603374, - "eval_loss": 0.8635594248771667, - "eval_runtime": 865.9348, - "eval_samples_per_second": 2.433, - "eval_steps_per_second": 2.433, + "eval_loss": 0.9800403714179993, + "eval_runtime": 678.8306, + "eval_samples_per_second": 3.104, + "eval_steps_per_second": 3.104, "step": 800 }, { "epoch": 0.33839662447257385, - "grad_norm": 1.8377124071121216, - "learning_rate": 7.038664323374341e-05, - "loss": 0.7625874280929565, + "grad_norm": 0.5413158535957336, + "learning_rate": 0.00014077328646748682, + "loss": 0.8610644936561584, "step": 802 }, { "epoch": 0.3392405063291139, - "grad_norm": 1.5361332893371582, - "learning_rate": 7.056239015817223e-05, - "loss": 0.8490484356880188, + "grad_norm": 0.5147035717964172, + "learning_rate": 0.00014112478031634446, + "loss": 0.9584825038909912, "step": 804 }, { "epoch": 0.340084388185654, - "grad_norm": 1.8727388381958008, - "learning_rate": 7.073813708260105e-05, - "loss": 0.8915753364562988, + "grad_norm": 0.5931771397590637, + "learning_rate": 0.0001414762741652021, + "loss": 1.0142558813095093, "step": 806 }, { "epoch": 0.3409282700421941, - "grad_norm": 1.567700743675232, - "learning_rate": 7.091388400702988e-05, - "loss": 0.8902620077133179, + "grad_norm": 0.5178377032279968, + "learning_rate": 0.00014182776801405976, + "loss": 1.0078763961791992, "step": 808 }, { "epoch": 0.34177215189873417, - "grad_norm": 1.5302914381027222, - "learning_rate": 7.10896309314587e-05, - "loss": 0.7897103428840637, + "grad_norm": 0.5453237295150757, + "learning_rate": 0.0001421792618629174, + "loss": 0.9107215404510498, "step": 810 }, { "epoch": 0.3426160337552743, - "grad_norm": 1.8819153308868408, - "learning_rate": 7.126537785588753e-05, - "loss": 0.8648831248283386, + "grad_norm": 0.5886152982711792, + "learning_rate": 0.00014253075571177506, + "loss": 0.9981362819671631, "step": 812 }, { "epoch": 0.3434599156118143, - "grad_norm": 1.5671379566192627, - "learning_rate": 7.144112478031635e-05, - "loss": 0.8449499607086182, + "grad_norm": 0.48040178418159485, + "learning_rate": 0.0001428822495606327, + "loss": 0.9636131525039673, "step": 814 }, { "epoch": 0.34430379746835443, - "grad_norm": 1.6570971012115479, - "learning_rate": 7.161687170474517e-05, - "loss": 0.848559558391571, + "grad_norm": 0.5011753439903259, + "learning_rate": 0.00014323374340949034, + "loss": 0.9590586423873901, "step": 816 }, { "epoch": 0.34514767932489454, - "grad_norm": 1.9108437299728394, - "learning_rate": 7.179261862917399e-05, - "loss": 0.8847543597221375, + "grad_norm": 0.57858806848526, + "learning_rate": 0.00014358523725834798, + "loss": 0.978246808052063, "step": 818 }, { "epoch": 0.3459915611814346, - "grad_norm": 1.4909496307373047, - "learning_rate": 7.196836555360281e-05, - "loss": 0.7642563581466675, + "grad_norm": 0.46092939376831055, + "learning_rate": 0.00014393673110720562, + "loss": 0.8549934029579163, "step": 820 }, { "epoch": 0.3468354430379747, - "grad_norm": 1.768518328666687, - "learning_rate": 7.214411247803163e-05, - "loss": 0.8714305758476257, + "grad_norm": 0.5756489038467407, + "learning_rate": 0.00014428822495606326, + "loss": 0.9771265387535095, "step": 822 }, { "epoch": 0.34767932489451475, - "grad_norm": 1.715343952178955, - "learning_rate": 7.231985940246046e-05, - "loss": 0.7712987661361694, + "grad_norm": 0.5501731634140015, + "learning_rate": 0.00014463971880492092, + "loss": 0.8739748001098633, "step": 824 }, { "epoch": 0.34852320675105486, - "grad_norm": 1.6687803268432617, - "learning_rate": 7.24956063268893e-05, - "loss": 0.8122798204421997, + "grad_norm": 0.5451868176460266, + "learning_rate": 0.0001449912126537786, + "loss": 0.9129468202590942, "step": 826 }, { "epoch": 0.3493670886075949, - "grad_norm": 1.5160514116287231, - "learning_rate": 7.267135325131811e-05, - "loss": 0.793245792388916, + "grad_norm": 0.4624619781970978, + "learning_rate": 0.00014534270650263623, + "loss": 0.9196704030036926, "step": 828 }, { "epoch": 0.350210970464135, - "grad_norm": 1.6449401378631592, - "learning_rate": 7.284710017574693e-05, - "loss": 0.8747497200965881, + "grad_norm": 0.520878791809082, + "learning_rate": 0.00014569420035149386, + "loss": 0.9976527690887451, "step": 830 }, { "epoch": 0.3510548523206751, - "grad_norm": 1.3907722234725952, - "learning_rate": 7.302284710017575e-05, - "loss": 0.6743978261947632, + "grad_norm": 0.4469171464443207, + "learning_rate": 0.0001460456942003515, + "loss": 0.7753443717956543, "step": 832 }, { "epoch": 0.3518987341772152, - "grad_norm": 1.633555293083191, - "learning_rate": 7.319859402460457e-05, - "loss": 0.8524789214134216, + "grad_norm": 0.5105249881744385, + "learning_rate": 0.00014639718804920914, + "loss": 0.9584846496582031, "step": 834 }, { "epoch": 0.3527426160337553, - "grad_norm": 1.5414257049560547, - "learning_rate": 7.337434094903339e-05, - "loss": 0.8045110702514648, + "grad_norm": 0.5043913125991821, + "learning_rate": 0.00014674868189806678, + "loss": 0.9013500213623047, "step": 836 }, { "epoch": 0.35358649789029534, - "grad_norm": 1.8520616292953491, - "learning_rate": 7.355008787346221e-05, - "loss": 0.8319593071937561, + "grad_norm": 0.575850784778595, + "learning_rate": 0.00014710017574692442, + "loss": 0.9775562286376953, "step": 838 }, { "epoch": 0.35443037974683544, - "grad_norm": 1.6629763841629028, - "learning_rate": 7.372583479789104e-05, - "loss": 0.8188939094543457, + "grad_norm": 0.5128876566886902, + "learning_rate": 0.00014745166959578208, + "loss": 0.9278940558433533, "step": 840 }, { "epoch": 0.35527426160337555, - "grad_norm": 1.804087519645691, - "learning_rate": 7.390158172231987e-05, - "loss": 0.8875360488891602, + "grad_norm": 0.5757885575294495, + "learning_rate": 0.00014780316344463975, + "loss": 1.0091488361358643, "step": 842 }, { "epoch": 0.3561181434599156, - "grad_norm": 1.6031663417816162, - "learning_rate": 7.407732864674869e-05, - "loss": 0.8159612417221069, + "grad_norm": 0.500934898853302, + "learning_rate": 0.00014815465729349739, + "loss": 0.9286836981773376, "step": 844 }, { "epoch": 0.3569620253164557, - "grad_norm": 1.7413033246994019, - "learning_rate": 7.425307557117751e-05, - "loss": 0.8422684669494629, + "grad_norm": 0.5220686197280884, + "learning_rate": 0.00014850615114235502, + "loss": 0.9484171867370605, "step": 846 }, { "epoch": 0.35780590717299576, - "grad_norm": 1.7699719667434692, - "learning_rate": 7.442882249560633e-05, - "loss": 0.9343502521514893, + "grad_norm": 0.5494697690010071, + "learning_rate": 0.00014885764499121266, + "loss": 1.0556397438049316, "step": 848 }, { "epoch": 0.35864978902953587, - "grad_norm": 1.4613301753997803, - "learning_rate": 7.460456942003515e-05, - "loss": 0.8168979287147522, + "grad_norm": 0.46633943915367126, + "learning_rate": 0.0001492091388400703, + "loss": 0.933089017868042, "step": 850 }, { "epoch": 0.3594936708860759, - "grad_norm": 1.542431354522705, - "learning_rate": 7.478031634446397e-05, - "loss": 0.9014382362365723, + "grad_norm": 0.4864962697029114, + "learning_rate": 0.00014956063268892794, + "loss": 1.0016963481903076, "step": 852 }, { "epoch": 0.36033755274261603, - "grad_norm": 1.6070159673690796, - "learning_rate": 7.49560632688928e-05, - "loss": 0.8162738084793091, + "grad_norm": 0.5032764673233032, + "learning_rate": 0.0001499121265377856, + "loss": 0.9085348844528198, "step": 854 }, { "epoch": 0.36118143459915614, - "grad_norm": 1.7979451417922974, - "learning_rate": 7.513181019332162e-05, - "loss": 0.8354527950286865, + "grad_norm": 0.5424998998641968, + "learning_rate": 0.00015026362038664324, + "loss": 0.923502504825592, "step": 856 }, { "epoch": 0.3620253164556962, - "grad_norm": 2.327045202255249, - "learning_rate": 7.530755711775044e-05, - "loss": 0.8214042782783508, + "grad_norm": 0.5181655287742615, + "learning_rate": 0.00015061511423550088, + "loss": 0.919174313545227, "step": 858 }, { "epoch": 0.3628691983122363, - "grad_norm": 1.5085111856460571, - "learning_rate": 7.548330404217927e-05, - "loss": 0.7472147941589355, + "grad_norm": 0.5129443407058716, + "learning_rate": 0.00015096660808435855, + "loss": 0.851981520652771, "step": 860 }, { "epoch": 0.36371308016877635, - "grad_norm": 1.6006290912628174, - "learning_rate": 7.565905096660809e-05, - "loss": 0.7586950063705444, + "grad_norm": 0.49540698528289795, + "learning_rate": 0.00015131810193321618, + "loss": 0.8633858561515808, "step": 862 }, { "epoch": 0.36455696202531646, - "grad_norm": 1.5170620679855347, - "learning_rate": 7.583479789103691e-05, - "loss": 0.8169914484024048, + "grad_norm": 0.4706701934337616, + "learning_rate": 0.00015166959578207382, + "loss": 0.9473677277565002, "step": 864 }, { "epoch": 0.36540084388185656, - "grad_norm": 1.5848352909088135, - "learning_rate": 7.601054481546573e-05, - "loss": 0.8263922929763794, + "grad_norm": 0.587704598903656, + "learning_rate": 0.00015202108963093146, + "loss": 0.942383885383606, "step": 866 }, { "epoch": 0.3662447257383966, - "grad_norm": 1.8502342700958252, - "learning_rate": 7.618629173989455e-05, - "loss": 0.8726240992546082, + "grad_norm": 0.5851273536682129, + "learning_rate": 0.0001523725834797891, + "loss": 0.9811251163482666, "step": 868 }, { "epoch": 0.3670886075949367, - "grad_norm": 1.506847620010376, - "learning_rate": 7.636203866432338e-05, - "loss": 0.7220374941825867, + "grad_norm": 0.46357613801956177, + "learning_rate": 0.00015272407732864676, + "loss": 0.8151084184646606, "step": 870 }, { "epoch": 0.3679324894514768, - "grad_norm": 1.5350452661514282, - "learning_rate": 7.65377855887522e-05, - "loss": 0.8028547167778015, + "grad_norm": 0.47250670194625854, + "learning_rate": 0.0001530755711775044, + "loss": 0.9023333191871643, "step": 872 }, { "epoch": 0.3687763713080169, - "grad_norm": 1.5011043548583984, - "learning_rate": 7.671353251318102e-05, - "loss": 0.7659649848937988, + "grad_norm": 0.47510042786598206, + "learning_rate": 0.00015342706502636204, + "loss": 0.8758499622344971, "step": 874 }, { "epoch": 0.369620253164557, - "grad_norm": 1.7019832134246826, - "learning_rate": 7.688927943760984e-05, - "loss": 0.8773653507232666, + "grad_norm": 0.5687124729156494, + "learning_rate": 0.00015377855887521968, + "loss": 0.9837421774864197, "step": 876 }, { "epoch": 0.37046413502109704, - "grad_norm": 1.4918498992919922, - "learning_rate": 7.706502636203867e-05, - "loss": 0.7977569103240967, + "grad_norm": 0.49064236879348755, + "learning_rate": 0.00015413005272407735, + "loss": 0.9084216356277466, "step": 878 }, { "epoch": 0.37130801687763715, - "grad_norm": 1.6422638893127441, - "learning_rate": 7.724077328646749e-05, - "loss": 0.7491976022720337, + "grad_norm": 0.5288164615631104, + "learning_rate": 0.00015448154657293498, + "loss": 0.8425542712211609, "step": 880 }, { "epoch": 0.3721518987341772, - "grad_norm": 1.7590434551239014, - "learning_rate": 7.741652021089631e-05, - "loss": 0.8754181265830994, + "grad_norm": 0.5446951985359192, + "learning_rate": 0.00015483304042179262, + "loss": 1.006197452545166, "step": 882 }, { "epoch": 0.3729957805907173, - "grad_norm": 3.868894100189209, - "learning_rate": 7.759226713532513e-05, - "loss": 0.8482301235198975, + "grad_norm": 0.46872642636299133, + "learning_rate": 0.00015518453427065026, + "loss": 0.9779444932937622, "step": 884 }, { "epoch": 0.37383966244725736, - "grad_norm": 2.111875534057617, - "learning_rate": 7.776801405975396e-05, - "loss": 0.8109031915664673, + "grad_norm": 0.4852714240550995, + "learning_rate": 0.00015553602811950793, + "loss": 0.9099963307380676, "step": 886 }, { "epoch": 0.37468354430379747, - "grad_norm": 2.0838418006896973, - "learning_rate": 7.794376098418278e-05, - "loss": 0.8660775423049927, + "grad_norm": 0.5219841003417969, + "learning_rate": 0.00015588752196836556, + "loss": 0.9730570316314697, "step": 888 }, { "epoch": 0.3755274261603376, - "grad_norm": 1.553022027015686, - "learning_rate": 7.81195079086116e-05, - "loss": 0.8418024778366089, + "grad_norm": 0.5258626341819763, + "learning_rate": 0.0001562390158172232, + "loss": 0.9304586052894592, "step": 890 }, { "epoch": 0.3763713080168776, - "grad_norm": 1.334747314453125, - "learning_rate": 7.829525483304042e-05, - "loss": 0.7764869928359985, + "grad_norm": 0.4266716241836548, + "learning_rate": 0.00015659050966608084, + "loss": 0.8680716156959534, "step": 892 }, { "epoch": 0.37721518987341773, - "grad_norm": 1.4692286252975464, - "learning_rate": 7.847100175746925e-05, - "loss": 0.7460401654243469, + "grad_norm": 0.46361327171325684, + "learning_rate": 0.0001569420035149385, + "loss": 0.8428018093109131, "step": 894 }, { "epoch": 0.3780590717299578, - "grad_norm": 1.5374023914337158, - "learning_rate": 7.864674868189807e-05, - "loss": 0.7662873268127441, + "grad_norm": 0.5313687920570374, + "learning_rate": 0.00015729349736379614, + "loss": 0.8465750217437744, "step": 896 }, { "epoch": 0.3789029535864979, - "grad_norm": 1.5662524700164795, - "learning_rate": 7.882249560632689e-05, - "loss": 0.8165306448936462, + "grad_norm": 0.47166210412979126, + "learning_rate": 0.00015764499121265378, + "loss": 0.9120327234268188, "step": 898 }, { "epoch": 0.379746835443038, - "grad_norm": 4.498590469360352, - "learning_rate": 7.899824253075572e-05, - "loss": 0.7913232445716858, + "grad_norm": 0.4647318720817566, + "learning_rate": 0.00015799648506151145, + "loss": 0.8950425982475281, "step": 900 }, { "epoch": 0.379746835443038, - "eval_loss": 0.8491304516792297, - "eval_runtime": 852.6211, - "eval_samples_per_second": 2.471, - "eval_steps_per_second": 2.471, + "eval_loss": 0.9643027186393738, + "eval_runtime": 691.7929, + "eval_samples_per_second": 3.046, + "eval_steps_per_second": 3.046, "step": 900 }, { "epoch": 0.38059071729957805, - "grad_norm": 1.6320613622665405, - "learning_rate": 7.917398945518454e-05, - "loss": 0.8097161054611206, + "grad_norm": 0.5445119738578796, + "learning_rate": 0.00015834797891036909, + "loss": 0.908163845539093, "step": 902 }, { "epoch": 0.38143459915611816, - "grad_norm": 1.2562934160232544, - "learning_rate": 7.934973637961336e-05, - "loss": 0.786399781703949, + "grad_norm": 0.4311858117580414, + "learning_rate": 0.00015869947275922672, + "loss": 0.8945821523666382, "step": 904 }, { "epoch": 0.3822784810126582, - "grad_norm": 1.6957594156265259, - "learning_rate": 7.952548330404218e-05, - "loss": 0.8385500311851501, + "grad_norm": 0.5590984225273132, + "learning_rate": 0.00015905096660808436, + "loss": 0.9478458762168884, "step": 906 }, { "epoch": 0.3831223628691983, - "grad_norm": 1.6662386655807495, - "learning_rate": 7.9701230228471e-05, - "loss": 0.8157848715782166, + "grad_norm": 0.5470241904258728, + "learning_rate": 0.000159402460456942, + "loss": 0.9259957671165466, "step": 908 }, { "epoch": 0.38396624472573837, - "grad_norm": 1.6717777252197266, - "learning_rate": 7.987697715289982e-05, - "loss": 0.7937968373298645, + "grad_norm": 0.5498791337013245, + "learning_rate": 0.00015975395430579964, + "loss": 0.8824930787086487, "step": 910 }, { "epoch": 0.3848101265822785, - "grad_norm": 1.399484395980835, - "learning_rate": 8.005272407732865e-05, - "loss": 0.7800109386444092, + "grad_norm": 0.4779198467731476, + "learning_rate": 0.0001601054481546573, + "loss": 0.8842340707778931, "step": 912 }, { "epoch": 0.3856540084388186, - "grad_norm": 1.5671080350875854, - "learning_rate": 8.022847100175747e-05, - "loss": 0.8135939240455627, + "grad_norm": 0.5390620827674866, + "learning_rate": 0.00016045694200351494, + "loss": 0.92950040102005, "step": 914 }, { "epoch": 0.38649789029535864, - "grad_norm": 1.4427763223648071, - "learning_rate": 8.04042179261863e-05, - "loss": 0.7482035160064697, + "grad_norm": 0.505519688129425, + "learning_rate": 0.0001608084358523726, + "loss": 0.8420897126197815, "step": 916 }, { "epoch": 0.38734177215189874, - "grad_norm": 1.3314121961593628, - "learning_rate": 8.057996485061512e-05, - "loss": 0.7201873064041138, + "grad_norm": 0.4463907778263092, + "learning_rate": 0.00016115992970123025, + "loss": 0.8256624341011047, "step": 918 }, { "epoch": 0.3881856540084388, - "grad_norm": 1.5695286989212036, - "learning_rate": 8.075571177504394e-05, - "loss": 0.7933040857315063, + "grad_norm": 0.5321422219276428, + "learning_rate": 0.00016151142355008788, + "loss": 0.8701168298721313, "step": 920 }, { "epoch": 0.3890295358649789, - "grad_norm": 1.5091747045516968, - "learning_rate": 8.093145869947276e-05, - "loss": 0.8058338165283203, + "grad_norm": 0.4343073070049286, + "learning_rate": 0.00016186291739894552, + "loss": 0.9019309878349304, "step": 922 }, { "epoch": 0.389873417721519, - "grad_norm": 1.6287630796432495, - "learning_rate": 8.110720562390158e-05, - "loss": 0.7617828249931335, + "grad_norm": 0.5311984419822693, + "learning_rate": 0.00016221441124780316, + "loss": 0.8560551404953003, "step": 924 }, { "epoch": 0.39071729957805906, - "grad_norm": 1.6129482984542847, - "learning_rate": 8.12829525483304e-05, - "loss": 0.8710150122642517, + "grad_norm": 0.588691771030426, + "learning_rate": 0.0001625659050966608, + "loss": 0.9700050354003906, "step": 926 }, { "epoch": 0.39156118143459917, - "grad_norm": 1.6457173824310303, - "learning_rate": 8.145869947275922e-05, - "loss": 0.9122233390808105, + "grad_norm": 0.5425586104393005, + "learning_rate": 0.00016291739894551844, + "loss": 1.043768048286438, "step": 928 }, { "epoch": 0.3924050632911392, - "grad_norm": 1.6768827438354492, - "learning_rate": 8.163444639718805e-05, - "loss": 0.8339303731918335, + "grad_norm": 0.5228736996650696, + "learning_rate": 0.0001632688927943761, + "loss": 0.9501712918281555, "step": 930 }, { "epoch": 0.39324894514767933, - "grad_norm": 1.5419740676879883, - "learning_rate": 8.181019332161688e-05, - "loss": 0.8220396041870117, + "grad_norm": 0.48960360884666443, + "learning_rate": 0.00016362038664323377, + "loss": 0.9223058223724365, "step": 932 }, { "epoch": 0.39409282700421944, - "grad_norm": 1.4563747644424438, - "learning_rate": 8.19859402460457e-05, - "loss": 0.8531478047370911, + "grad_norm": 0.45204755663871765, + "learning_rate": 0.0001639718804920914, + "loss": 0.9692960977554321, "step": 934 }, { "epoch": 0.3949367088607595, - "grad_norm": 1.6208328008651733, - "learning_rate": 8.216168717047452e-05, - "loss": 0.8330869078636169, + "grad_norm": 0.5299274921417236, + "learning_rate": 0.00016432337434094905, + "loss": 0.9467466473579407, "step": 936 }, { "epoch": 0.3957805907172996, - "grad_norm": 1.6492482423782349, - "learning_rate": 8.233743409490334e-05, - "loss": 0.8011296987533569, + "grad_norm": 0.5607715249061584, + "learning_rate": 0.00016467486818980668, + "loss": 0.9118053317070007, "step": 938 }, { "epoch": 0.39662447257383965, - "grad_norm": 2.1611905097961426, - "learning_rate": 8.251318101933216e-05, - "loss": 0.8111353516578674, + "grad_norm": 0.5271831154823303, + "learning_rate": 0.00016502636203866432, + "loss": 0.9131460189819336, "step": 940 }, { "epoch": 0.39746835443037976, - "grad_norm": 1.7108231782913208, - "learning_rate": 8.268892794376098e-05, - "loss": 0.8282017111778259, + "grad_norm": 0.5075286030769348, + "learning_rate": 0.00016537785588752196, + "loss": 0.9358300566673279, "step": 942 }, { "epoch": 0.3983122362869198, - "grad_norm": 1.543465495109558, - "learning_rate": 8.286467486818981e-05, - "loss": 0.7770059704780579, + "grad_norm": 0.515731155872345, + "learning_rate": 0.00016572934973637963, + "loss": 0.8908210396766663, "step": 944 }, { "epoch": 0.3991561181434599, - "grad_norm": 1.419969081878662, - "learning_rate": 8.304042179261863e-05, - "loss": 0.8646430373191833, + "grad_norm": 0.4856977164745331, + "learning_rate": 0.00016608084358523726, + "loss": 0.9775290489196777, "step": 946 }, { "epoch": 0.4, - "grad_norm": 1.5002100467681885, - "learning_rate": 8.321616871704746e-05, - "loss": 0.7949403524398804, + "grad_norm": 0.48846355080604553, + "learning_rate": 0.00016643233743409493, + "loss": 0.8957490921020508, "step": 948 }, { "epoch": 0.4008438818565401, - "grad_norm": 1.38933265209198, - "learning_rate": 8.339191564147628e-05, - "loss": 0.8124079704284668, + "grad_norm": 0.42990800738334656, + "learning_rate": 0.00016678383128295257, + "loss": 0.9036174416542053, "step": 950 }, { "epoch": 0.4016877637130802, - "grad_norm": 1.5948443412780762, - "learning_rate": 8.35676625659051e-05, - "loss": 0.8634148836135864, + "grad_norm": 0.49552062153816223, + "learning_rate": 0.0001671353251318102, + "loss": 0.991032600402832, "step": 952 }, { "epoch": 0.40253164556962023, - "grad_norm": 1.4437624216079712, - "learning_rate": 8.374340949033392e-05, - "loss": 0.7410681247711182, + "grad_norm": 0.4565040171146393, + "learning_rate": 0.00016748681898066784, + "loss": 0.823063313961029, "step": 954 }, { "epoch": 0.40337552742616034, - "grad_norm": 1.3457095623016357, - "learning_rate": 8.391915641476274e-05, - "loss": 0.7680280208587646, + "grad_norm": 0.4290153682231903, + "learning_rate": 0.00016783831282952548, + "loss": 0.8785063624382019, "step": 956 }, { "epoch": 0.40421940928270045, - "grad_norm": 1.610288143157959, - "learning_rate": 8.409490333919156e-05, - "loss": 0.7921904921531677, + "grad_norm": 0.5419702529907227, + "learning_rate": 0.00016818980667838312, + "loss": 0.8763971924781799, "step": 958 }, { "epoch": 0.4050632911392405, - "grad_norm": 1.5321530103683472, - "learning_rate": 8.427065026362039e-05, - "loss": 0.8320037126541138, + "grad_norm": 0.5177501440048218, + "learning_rate": 0.00016854130052724079, + "loss": 0.9470553398132324, "step": 960 }, { "epoch": 0.4059071729957806, - "grad_norm": 1.699881672859192, - "learning_rate": 8.444639718804921e-05, - "loss": 0.8303092122077942, + "grad_norm": 0.539725661277771, + "learning_rate": 0.00016889279437609842, + "loss": 0.9235025644302368, "step": 962 }, { "epoch": 0.40675105485232066, - "grad_norm": 1.591515064239502, - "learning_rate": 8.462214411247804e-05, - "loss": 0.9029796719551086, + "grad_norm": 0.5324983596801758, + "learning_rate": 0.0001692442882249561, + "loss": 1.0248996019363403, "step": 964 }, { "epoch": 0.40759493670886077, - "grad_norm": 1.5930429697036743, - "learning_rate": 8.479789103690686e-05, - "loss": 0.8165359497070312, + "grad_norm": 0.4936407506465912, + "learning_rate": 0.00016959578207381373, + "loss": 0.9076873660087585, "step": 966 }, { "epoch": 0.4084388185654008, - "grad_norm": 1.509774923324585, - "learning_rate": 8.497363796133568e-05, - "loss": 0.8276026248931885, + "grad_norm": 0.4960501194000244, + "learning_rate": 0.00016994727592267137, + "loss": 0.9162673950195312, "step": 968 }, { "epoch": 0.4092827004219409, - "grad_norm": 1.3617016077041626, - "learning_rate": 8.51493848857645e-05, - "loss": 0.8159419894218445, + "grad_norm": 0.45093682408332825, + "learning_rate": 0.000170298769771529, + "loss": 0.904100775718689, "step": 970 }, { "epoch": 0.41012658227848103, - "grad_norm": 1.3580708503723145, - "learning_rate": 8.532513181019332e-05, - "loss": 0.7882336378097534, + "grad_norm": 0.4560275077819824, + "learning_rate": 0.00017065026362038664, + "loss": 0.8633337020874023, "step": 972 }, { "epoch": 0.4109704641350211, - "grad_norm": 1.3337358236312866, - "learning_rate": 8.550087873462214e-05, - "loss": 0.7462319731712341, + "grad_norm": 0.44885000586509705, + "learning_rate": 0.00017100175746924428, + "loss": 0.8454209566116333, "step": 974 }, { "epoch": 0.4118143459915612, - "grad_norm": 1.450363278388977, - "learning_rate": 8.567662565905097e-05, - "loss": 0.7500866651535034, + "grad_norm": 0.47251659631729126, + "learning_rate": 0.00017135325131810195, + "loss": 0.824730396270752, "step": 976 }, { "epoch": 0.41265822784810124, - "grad_norm": 1.5305321216583252, - "learning_rate": 8.585237258347979e-05, - "loss": 0.8432503342628479, + "grad_norm": 0.6597666144371033, + "learning_rate": 0.00017170474516695959, + "loss": 0.9496501684188843, "step": 978 }, { "epoch": 0.41350210970464135, - "grad_norm": 1.2097326517105103, - "learning_rate": 8.602811950790861e-05, - "loss": 0.8330482840538025, + "grad_norm": 0.39806297421455383, + "learning_rate": 0.00017205623901581722, + "loss": 0.9419087171554565, "step": 980 }, { "epoch": 0.41434599156118146, - "grad_norm": 1.3916101455688477, - "learning_rate": 8.620386643233744e-05, - "loss": 0.8137149810791016, + "grad_norm": 0.48231109976768494, + "learning_rate": 0.0001724077328646749, + "loss": 0.9182976484298706, "step": 982 }, { "epoch": 0.4151898734177215, - "grad_norm": 1.6411453485488892, - "learning_rate": 8.637961335676626e-05, - "loss": 0.8273854851722717, + "grad_norm": 0.5438776612281799, + "learning_rate": 0.00017275922671353253, + "loss": 0.9386967420578003, "step": 984 }, { "epoch": 0.4160337552742616, - "grad_norm": 1.6734566688537598, - "learning_rate": 8.655536028119508e-05, - "loss": 0.794026255607605, + "grad_norm": 0.4959667921066284, + "learning_rate": 0.00017311072056239017, + "loss": 0.897849440574646, "step": 986 }, { "epoch": 0.41687763713080167, - "grad_norm": 1.352325677871704, - "learning_rate": 8.67311072056239e-05, - "loss": 0.7721655368804932, + "grad_norm": 0.43533357977867126, + "learning_rate": 0.0001734622144112478, + "loss": 0.8776953816413879, "step": 988 }, { "epoch": 0.4177215189873418, - "grad_norm": 1.5368729829788208, - "learning_rate": 8.690685413005273e-05, - "loss": 0.8123438954353333, + "grad_norm": 0.47513946890830994, + "learning_rate": 0.00017381370826010547, + "loss": 0.9162989854812622, "step": 990 }, { "epoch": 0.41856540084388183, - "grad_norm": 1.4903568029403687, - "learning_rate": 8.708260105448155e-05, - "loss": 0.8370974659919739, + "grad_norm": 0.4907188415527344, + "learning_rate": 0.0001741652021089631, + "loss": 0.9482660889625549, "step": 992 }, { "epoch": 0.41940928270042194, - "grad_norm": 1.3405622243881226, - "learning_rate": 8.725834797891037e-05, - "loss": 0.780426561832428, + "grad_norm": 0.44499966502189636, + "learning_rate": 0.00017451669595782075, + "loss": 0.8812930583953857, "step": 994 }, { "epoch": 0.42025316455696204, - "grad_norm": 1.4761021137237549, - "learning_rate": 8.743409490333919e-05, - "loss": 0.8304934501647949, + "grad_norm": 0.4535730481147766, + "learning_rate": 0.00017486818980667838, + "loss": 0.9439874887466431, "step": 996 }, { "epoch": 0.4210970464135021, - "grad_norm": 1.520033359527588, - "learning_rate": 8.760984182776801e-05, - "loss": 0.7960568070411682, + "grad_norm": 0.5240745544433594, + "learning_rate": 0.00017521968365553602, + "loss": 0.8818395137786865, "step": 998 }, { "epoch": 0.4219409282700422, - "grad_norm": 1.6916255950927734, - "learning_rate": 8.778558875219684e-05, - "loss": 0.7884663939476013, + "grad_norm": 0.5301211476325989, + "learning_rate": 0.0001755711775043937, + "loss": 0.886186957359314, "step": 1000 }, { "epoch": 0.4219409282700422, - "eval_loss": 0.8388314247131348, - "eval_runtime": 847.4828, - "eval_samples_per_second": 2.486, - "eval_steps_per_second": 2.486, + "eval_loss": 0.9487298727035522, + "eval_runtime": 689.4288, + "eval_samples_per_second": 3.056, + "eval_steps_per_second": 3.056, "step": 1000 } ], @@ -3616,7 +3616,7 @@ "attributes": {} } }, - "total_flos": 1.0390224045010268e+18, + "total_flos": 5.979725639330796e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null