| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.760827407886232, |
| "eval_steps": 25, |
| "global_step": 3775, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06464124111182935, |
| "grad_norm": 1.0677852630615234, |
| "learning_rate": 0.0001987561544441565, |
| "loss": 1.5031, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.06464124111182935, |
| "eval_loss": 0.7738007307052612, |
| "eval_runtime": 28.2735, |
| "eval_samples_per_second": 6.862, |
| "eval_steps_per_second": 0.884, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.1292824822236587, |
| "grad_norm": 0.6701745390892029, |
| "learning_rate": 0.0001974604819901529, |
| "loss": 0.6361, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1292824822236587, |
| "eval_loss": 0.7382436394691467, |
| "eval_runtime": 28.3731, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.19392372333548805, |
| "grad_norm": 0.6211751103401184, |
| "learning_rate": 0.00019616480953614927, |
| "loss": 0.7904, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.19392372333548805, |
| "eval_loss": 0.6710241436958313, |
| "eval_runtime": 28.3743, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.2585649644473174, |
| "grad_norm": 0.46665698289871216, |
| "learning_rate": 0.00019486913708214565, |
| "loss": 0.6003, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2585649644473174, |
| "eval_loss": 0.6717760562896729, |
| "eval_runtime": 28.3871, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.32320620555914675, |
| "grad_norm": 0.37890613079071045, |
| "learning_rate": 0.000193573464628142, |
| "loss": 0.7216, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.32320620555914675, |
| "eval_loss": 0.633716881275177, |
| "eval_runtime": 28.3657, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.3878474466709761, |
| "grad_norm": 0.4904387593269348, |
| "learning_rate": 0.00019227779217413838, |
| "loss": 0.5406, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3878474466709761, |
| "eval_loss": 0.6501740217208862, |
| "eval_runtime": 28.3856, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.45248868778280543, |
| "grad_norm": 0.749422013759613, |
| "learning_rate": 0.00019098211972013476, |
| "loss": 0.729, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.45248868778280543, |
| "eval_loss": 0.5998457670211792, |
| "eval_runtime": 28.3865, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.5171299288946348, |
| "grad_norm": 0.6034186482429504, |
| "learning_rate": 0.00018968644726613114, |
| "loss": 0.4798, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5171299288946348, |
| "eval_loss": 0.6037718653678894, |
| "eval_runtime": 28.3899, |
| "eval_samples_per_second": 6.833, |
| "eval_steps_per_second": 0.881, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5817711700064642, |
| "grad_norm": 0.49036094546318054, |
| "learning_rate": 0.0001883907748121275, |
| "loss": 0.6506, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.5817711700064642, |
| "eval_loss": 0.5725067257881165, |
| "eval_runtime": 28.3885, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.6464124111182935, |
| "grad_norm": 0.4539071023464203, |
| "learning_rate": 0.00018709510235812387, |
| "loss": 0.4887, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.6464124111182935, |
| "eval_loss": 0.5766528248786926, |
| "eval_runtime": 28.396, |
| "eval_samples_per_second": 6.832, |
| "eval_steps_per_second": 0.88, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7110536522301228, |
| "grad_norm": 0.5620549321174622, |
| "learning_rate": 0.00018579942990412025, |
| "loss": 0.6686, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.7110536522301228, |
| "eval_loss": 0.5523518919944763, |
| "eval_runtime": 28.378, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.7756948933419522, |
| "grad_norm": 0.5603043437004089, |
| "learning_rate": 0.0001845037574501166, |
| "loss": 0.4486, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7756948933419522, |
| "eval_loss": 0.5640637278556824, |
| "eval_runtime": 28.3883, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8403361344537815, |
| "grad_norm": 0.6995631456375122, |
| "learning_rate": 0.00018320808499611298, |
| "loss": 0.6412, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.8403361344537815, |
| "eval_loss": 0.5314977765083313, |
| "eval_runtime": 28.3685, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.9049773755656109, |
| "grad_norm": 0.7738640904426575, |
| "learning_rate": 0.00018191241254210936, |
| "loss": 0.4064, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.9049773755656109, |
| "eval_loss": 0.5507013201713562, |
| "eval_runtime": 28.4, |
| "eval_samples_per_second": 6.831, |
| "eval_steps_per_second": 0.88, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.9696186166774402, |
| "grad_norm": 0.6186261177062988, |
| "learning_rate": 0.00018061674008810574, |
| "loss": 0.6026, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.9696186166774402, |
| "eval_loss": 0.5145959258079529, |
| "eval_runtime": 28.3798, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.0342598577892697, |
| "grad_norm": 0.6407806873321533, |
| "learning_rate": 0.0001793210676341021, |
| "loss": 0.6072, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.0342598577892697, |
| "eval_loss": 0.5017822980880737, |
| "eval_runtime": 28.3852, |
| "eval_samples_per_second": 6.835, |
| "eval_steps_per_second": 0.881, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.098901098901099, |
| "grad_norm": 0.5879328846931458, |
| "learning_rate": 0.00017802539518009847, |
| "loss": 0.4294, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.098901098901099, |
| "eval_loss": 0.510532796382904, |
| "eval_runtime": 28.3905, |
| "eval_samples_per_second": 6.833, |
| "eval_steps_per_second": 0.881, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.1635423400129283, |
| "grad_norm": 0.3991760313510895, |
| "learning_rate": 0.00017672972272609485, |
| "loss": 0.467, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.1635423400129283, |
| "eval_loss": 0.4912414848804474, |
| "eval_runtime": 28.39, |
| "eval_samples_per_second": 6.833, |
| "eval_steps_per_second": 0.881, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.2281835811247577, |
| "grad_norm": 0.72346431016922, |
| "learning_rate": 0.00017543405027209123, |
| "loss": 0.4679, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.2281835811247577, |
| "eval_loss": 0.48893699049949646, |
| "eval_runtime": 28.4019, |
| "eval_samples_per_second": 6.831, |
| "eval_steps_per_second": 0.88, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.292824822236587, |
| "grad_norm": 0.6564201712608337, |
| "learning_rate": 0.00017413837781808759, |
| "loss": 0.4686, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.292824822236587, |
| "eval_loss": 0.4775838553905487, |
| "eval_runtime": 28.3874, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.3574660633484164, |
| "grad_norm": 0.756857693195343, |
| "learning_rate": 0.000172842705364084, |
| "loss": 0.4745, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.3574660633484164, |
| "eval_loss": 0.46975865960121155, |
| "eval_runtime": 28.396, |
| "eval_samples_per_second": 6.832, |
| "eval_steps_per_second": 0.88, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.4221073044602457, |
| "grad_norm": 0.640488862991333, |
| "learning_rate": 0.00017154703291008034, |
| "loss": 0.4728, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.4221073044602457, |
| "eval_loss": 0.45979756116867065, |
| "eval_runtime": 28.3738, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.486748545572075, |
| "grad_norm": 0.379324734210968, |
| "learning_rate": 0.0001702513604560767, |
| "loss": 0.4064, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.486748545572075, |
| "eval_loss": 0.46095722913742065, |
| "eval_runtime": 28.3833, |
| "eval_samples_per_second": 6.835, |
| "eval_steps_per_second": 0.881, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.5513897866839044, |
| "grad_norm": 0.5932112336158752, |
| "learning_rate": 0.00016895568800207308, |
| "loss": 0.4725, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.5513897866839044, |
| "eval_loss": 0.44522133469581604, |
| "eval_runtime": 28.344, |
| "eval_samples_per_second": 6.844, |
| "eval_steps_per_second": 0.882, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.6160310277957337, |
| "grad_norm": 0.3605249524116516, |
| "learning_rate": 0.00016766001554806945, |
| "loss": 0.3976, |
| "step": 625 |
| }, |
| { |
| "epoch": 1.6160310277957337, |
| "eval_loss": 0.43757495284080505, |
| "eval_runtime": 28.3551, |
| "eval_samples_per_second": 6.842, |
| "eval_steps_per_second": 0.882, |
| "step": 625 |
| }, |
| { |
| "epoch": 1.680672268907563, |
| "grad_norm": 0.680446445941925, |
| "learning_rate": 0.00016636434309406583, |
| "loss": 0.4467, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.680672268907563, |
| "eval_loss": 0.4373495280742645, |
| "eval_runtime": 28.342, |
| "eval_samples_per_second": 6.845, |
| "eval_steps_per_second": 0.882, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.7453135100193924, |
| "grad_norm": 0.7049732208251953, |
| "learning_rate": 0.0001650686706400622, |
| "loss": 0.4031, |
| "step": 675 |
| }, |
| { |
| "epoch": 1.7453135100193924, |
| "eval_loss": 0.42949825525283813, |
| "eval_runtime": 28.3319, |
| "eval_samples_per_second": 6.847, |
| "eval_steps_per_second": 0.882, |
| "step": 675 |
| }, |
| { |
| "epoch": 1.8099547511312217, |
| "grad_norm": 0.7730217576026917, |
| "learning_rate": 0.00016377299818605857, |
| "loss": 0.4123, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.8099547511312217, |
| "eval_loss": 0.42606624960899353, |
| "eval_runtime": 28.357, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.874595992243051, |
| "grad_norm": 0.7875500321388245, |
| "learning_rate": 0.00016247732573205495, |
| "loss": 0.3959, |
| "step": 725 |
| }, |
| { |
| "epoch": 1.874595992243051, |
| "eval_loss": 0.41709569096565247, |
| "eval_runtime": 28.3465, |
| "eval_samples_per_second": 6.844, |
| "eval_steps_per_second": 0.882, |
| "step": 725 |
| }, |
| { |
| "epoch": 1.9392372333548804, |
| "grad_norm": 0.5601785182952881, |
| "learning_rate": 0.00016118165327805132, |
| "loss": 0.3967, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.9392372333548804, |
| "eval_loss": 0.417958527803421, |
| "eval_runtime": 28.3483, |
| "eval_samples_per_second": 6.843, |
| "eval_steps_per_second": 0.882, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.0038784744667097, |
| "grad_norm": 0.5318927764892578, |
| "learning_rate": 0.00015988598082404768, |
| "loss": 0.3539, |
| "step": 775 |
| }, |
| { |
| "epoch": 2.0038784744667097, |
| "eval_loss": 0.41897284984588623, |
| "eval_runtime": 28.3398, |
| "eval_samples_per_second": 6.846, |
| "eval_steps_per_second": 0.882, |
| "step": 775 |
| }, |
| { |
| "epoch": 2.0685197155785393, |
| "grad_norm": 0.8083105087280273, |
| "learning_rate": 0.00015859030837004406, |
| "loss": 0.3937, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.0685197155785393, |
| "eval_loss": 0.4142076075077057, |
| "eval_runtime": 28.3348, |
| "eval_samples_per_second": 6.847, |
| "eval_steps_per_second": 0.882, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.1331609566903684, |
| "grad_norm": 0.5587257146835327, |
| "learning_rate": 0.00015729463591604044, |
| "loss": 0.2813, |
| "step": 825 |
| }, |
| { |
| "epoch": 2.1331609566903684, |
| "eval_loss": 0.42084425687789917, |
| "eval_runtime": 28.3605, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.882, |
| "step": 825 |
| }, |
| { |
| "epoch": 2.197802197802198, |
| "grad_norm": 0.9122255444526672, |
| "learning_rate": 0.0001559989634620368, |
| "loss": 0.3939, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.197802197802198, |
| "eval_loss": 0.40227043628692627, |
| "eval_runtime": 28.3473, |
| "eval_samples_per_second": 6.844, |
| "eval_steps_per_second": 0.882, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.262443438914027, |
| "grad_norm": 0.8314863443374634, |
| "learning_rate": 0.00015470329100803317, |
| "loss": 0.3082, |
| "step": 875 |
| }, |
| { |
| "epoch": 2.262443438914027, |
| "eval_loss": 0.40132778882980347, |
| "eval_runtime": 28.4138, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 875 |
| }, |
| { |
| "epoch": 2.3270846800258567, |
| "grad_norm": 0.5471761226654053, |
| "learning_rate": 0.00015340761855402955, |
| "loss": 0.3581, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.3270846800258567, |
| "eval_loss": 0.3944034278392792, |
| "eval_runtime": 28.3857, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.391725921137686, |
| "grad_norm": 0.8648784756660461, |
| "learning_rate": 0.00015211194610002593, |
| "loss": 0.3363, |
| "step": 925 |
| }, |
| { |
| "epoch": 2.391725921137686, |
| "eval_loss": 0.3942734897136688, |
| "eval_runtime": 28.363, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 925 |
| }, |
| { |
| "epoch": 2.4563671622495153, |
| "grad_norm": 0.537049412727356, |
| "learning_rate": 0.00015081627364602228, |
| "loss": 0.3904, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.4563671622495153, |
| "eval_loss": 0.3798774182796478, |
| "eval_runtime": 28.3597, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.5210084033613445, |
| "grad_norm": 0.753616213798523, |
| "learning_rate": 0.00014952060119201869, |
| "loss": 0.2766, |
| "step": 975 |
| }, |
| { |
| "epoch": 2.5210084033613445, |
| "eval_loss": 0.38760867714881897, |
| "eval_runtime": 28.3455, |
| "eval_samples_per_second": 6.844, |
| "eval_steps_per_second": 0.882, |
| "step": 975 |
| }, |
| { |
| "epoch": 2.585649644473174, |
| "grad_norm": 0.8063026666641235, |
| "learning_rate": 0.00014822492873801504, |
| "loss": 0.3691, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.585649644473174, |
| "eval_loss": 0.37839940190315247, |
| "eval_runtime": 28.3501, |
| "eval_samples_per_second": 6.843, |
| "eval_steps_per_second": 0.882, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.650290885585003, |
| "grad_norm": 0.6836534738540649, |
| "learning_rate": 0.00014692925628401142, |
| "loss": 0.2868, |
| "step": 1025 |
| }, |
| { |
| "epoch": 2.650290885585003, |
| "eval_loss": 0.3827487826347351, |
| "eval_runtime": 28.3583, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 1025 |
| }, |
| { |
| "epoch": 2.7149321266968327, |
| "grad_norm": 0.42256560921669006, |
| "learning_rate": 0.00014563358383000777, |
| "loss": 0.3663, |
| "step": 1050 |
| }, |
| { |
| "epoch": 2.7149321266968327, |
| "eval_loss": 0.3742258846759796, |
| "eval_runtime": 28.3655, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1050 |
| }, |
| { |
| "epoch": 2.779573367808662, |
| "grad_norm": 0.712345540523529, |
| "learning_rate": 0.00014433791137600415, |
| "loss": 0.2892, |
| "step": 1075 |
| }, |
| { |
| "epoch": 2.779573367808662, |
| "eval_loss": 0.36922118067741394, |
| "eval_runtime": 28.3607, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.882, |
| "step": 1075 |
| }, |
| { |
| "epoch": 2.8442146089204914, |
| "grad_norm": 0.601972222328186, |
| "learning_rate": 0.00014304223892200053, |
| "loss": 0.3791, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.8442146089204914, |
| "eval_loss": 0.3680700659751892, |
| "eval_runtime": 28.3607, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.882, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.9088558500323205, |
| "grad_norm": 1.0497028827667236, |
| "learning_rate": 0.00014174656646799688, |
| "loss": 0.2699, |
| "step": 1125 |
| }, |
| { |
| "epoch": 2.9088558500323205, |
| "eval_loss": 0.37244880199432373, |
| "eval_runtime": 28.3623, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 1125 |
| }, |
| { |
| "epoch": 2.97349709114415, |
| "grad_norm": 0.40736496448516846, |
| "learning_rate": 0.00014045089401399326, |
| "loss": 0.3275, |
| "step": 1150 |
| }, |
| { |
| "epoch": 2.97349709114415, |
| "eval_loss": 0.36198127269744873, |
| "eval_runtime": 28.3578, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 1150 |
| }, |
| { |
| "epoch": 3.038138332255979, |
| "grad_norm": 0.5252788662910461, |
| "learning_rate": 0.00013915522155998964, |
| "loss": 0.3048, |
| "step": 1175 |
| }, |
| { |
| "epoch": 3.038138332255979, |
| "eval_loss": 0.35509297251701355, |
| "eval_runtime": 28.3683, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1175 |
| }, |
| { |
| "epoch": 3.1027795733678087, |
| "grad_norm": 0.5078774690628052, |
| "learning_rate": 0.00013785954910598602, |
| "loss": 0.2302, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.1027795733678087, |
| "eval_loss": 0.36969441175460815, |
| "eval_runtime": 28.3773, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.167420814479638, |
| "grad_norm": 0.5727627873420715, |
| "learning_rate": 0.00013656387665198237, |
| "loss": 0.2634, |
| "step": 1225 |
| }, |
| { |
| "epoch": 3.167420814479638, |
| "eval_loss": 0.35748958587646484, |
| "eval_runtime": 28.3698, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 1225 |
| }, |
| { |
| "epoch": 3.2320620555914674, |
| "grad_norm": 0.5207127928733826, |
| "learning_rate": 0.00013526820419797878, |
| "loss": 0.246, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.2320620555914674, |
| "eval_loss": 0.3601771891117096, |
| "eval_runtime": 28.3649, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.2967032967032965, |
| "grad_norm": 0.5944882035255432, |
| "learning_rate": 0.00013397253174397513, |
| "loss": 0.2949, |
| "step": 1275 |
| }, |
| { |
| "epoch": 3.2967032967032965, |
| "eval_loss": 0.3485008180141449, |
| "eval_runtime": 28.3656, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1275 |
| }, |
| { |
| "epoch": 3.361344537815126, |
| "grad_norm": 0.5524560213088989, |
| "learning_rate": 0.0001326768592899715, |
| "loss": 0.2491, |
| "step": 1300 |
| }, |
| { |
| "epoch": 3.361344537815126, |
| "eval_loss": 0.3541901707649231, |
| "eval_runtime": 28.3634, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 1300 |
| }, |
| { |
| "epoch": 3.425985778926955, |
| "grad_norm": 0.7113463282585144, |
| "learning_rate": 0.00013138118683596786, |
| "loss": 0.2633, |
| "step": 1325 |
| }, |
| { |
| "epoch": 3.425985778926955, |
| "eval_loss": 0.34305500984191895, |
| "eval_runtime": 28.3656, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1325 |
| }, |
| { |
| "epoch": 3.490627020038785, |
| "grad_norm": 0.4575362205505371, |
| "learning_rate": 0.00013008551438196424, |
| "loss": 0.2662, |
| "step": 1350 |
| }, |
| { |
| "epoch": 3.490627020038785, |
| "eval_loss": 0.34231284260749817, |
| "eval_runtime": 28.375, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 1350 |
| }, |
| { |
| "epoch": 3.555268261150614, |
| "grad_norm": 0.5697687268257141, |
| "learning_rate": 0.00012878984192796062, |
| "loss": 0.2971, |
| "step": 1375 |
| }, |
| { |
| "epoch": 3.555268261150614, |
| "eval_loss": 0.34091299772262573, |
| "eval_runtime": 28.3758, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 1375 |
| }, |
| { |
| "epoch": 3.6199095022624435, |
| "grad_norm": 0.515760064125061, |
| "learning_rate": 0.00012749416947395697, |
| "loss": 0.2645, |
| "step": 1400 |
| }, |
| { |
| "epoch": 3.6199095022624435, |
| "eval_loss": 0.3471181094646454, |
| "eval_runtime": 28.3834, |
| "eval_samples_per_second": 6.835, |
| "eval_steps_per_second": 0.881, |
| "step": 1400 |
| }, |
| { |
| "epoch": 3.684550743374273, |
| "grad_norm": 0.5785380601882935, |
| "learning_rate": 0.00012619849701995338, |
| "loss": 0.2626, |
| "step": 1425 |
| }, |
| { |
| "epoch": 3.684550743374273, |
| "eval_loss": 0.3446151912212372, |
| "eval_runtime": 28.3682, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1425 |
| }, |
| { |
| "epoch": 3.749191984486102, |
| "grad_norm": 0.5408931374549866, |
| "learning_rate": 0.00012490282456594973, |
| "loss": 0.2584, |
| "step": 1450 |
| }, |
| { |
| "epoch": 3.749191984486102, |
| "eval_loss": 0.3404946029186249, |
| "eval_runtime": 28.3655, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1450 |
| }, |
| { |
| "epoch": 3.8138332255979313, |
| "grad_norm": 0.6690952181816101, |
| "learning_rate": 0.0001236071521119461, |
| "loss": 0.3035, |
| "step": 1475 |
| }, |
| { |
| "epoch": 3.8138332255979313, |
| "eval_loss": 0.3327294886112213, |
| "eval_runtime": 28.3682, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1475 |
| }, |
| { |
| "epoch": 3.878474466709761, |
| "grad_norm": 0.6775087118148804, |
| "learning_rate": 0.00012231147965794246, |
| "loss": 0.2442, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.878474466709761, |
| "eval_loss": 0.3373003304004669, |
| "eval_runtime": 28.3573, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.9431157078215904, |
| "grad_norm": 0.48944905400276184, |
| "learning_rate": 0.00012101580720393886, |
| "loss": 0.2633, |
| "step": 1525 |
| }, |
| { |
| "epoch": 3.9431157078215904, |
| "eval_loss": 0.32914599776268005, |
| "eval_runtime": 28.3767, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 1525 |
| }, |
| { |
| "epoch": 4.0077569489334195, |
| "grad_norm": 0.5259898900985718, |
| "learning_rate": 0.00011972013474993522, |
| "loss": 0.2366, |
| "step": 1550 |
| }, |
| { |
| "epoch": 4.0077569489334195, |
| "eval_loss": 0.3343600928783417, |
| "eval_runtime": 28.3695, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 1550 |
| }, |
| { |
| "epoch": 4.072398190045249, |
| "grad_norm": 0.5055583119392395, |
| "learning_rate": 0.0001184244622959316, |
| "loss": 0.2306, |
| "step": 1575 |
| }, |
| { |
| "epoch": 4.072398190045249, |
| "eval_loss": 0.34326639771461487, |
| "eval_runtime": 28.3731, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 1575 |
| }, |
| { |
| "epoch": 4.137039431157079, |
| "grad_norm": 1.0883666276931763, |
| "learning_rate": 0.00011712878984192797, |
| "loss": 0.2021, |
| "step": 1600 |
| }, |
| { |
| "epoch": 4.137039431157079, |
| "eval_loss": 0.34833526611328125, |
| "eval_runtime": 28.3618, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 1600 |
| }, |
| { |
| "epoch": 4.201680672268908, |
| "grad_norm": 0.6897253394126892, |
| "learning_rate": 0.00011583311738792433, |
| "loss": 0.2351, |
| "step": 1625 |
| }, |
| { |
| "epoch": 4.201680672268908, |
| "eval_loss": 0.330352783203125, |
| "eval_runtime": 28.3607, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.882, |
| "step": 1625 |
| }, |
| { |
| "epoch": 4.266321913380737, |
| "grad_norm": 0.6391870379447937, |
| "learning_rate": 0.00011453744493392071, |
| "loss": 0.1961, |
| "step": 1650 |
| }, |
| { |
| "epoch": 4.266321913380737, |
| "eval_loss": 0.3459455370903015, |
| "eval_runtime": 28.3772, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 1650 |
| }, |
| { |
| "epoch": 4.330963154492566, |
| "grad_norm": 0.5239293575286865, |
| "learning_rate": 0.00011324177247991708, |
| "loss": 0.2509, |
| "step": 1675 |
| }, |
| { |
| "epoch": 4.330963154492566, |
| "eval_loss": 0.3330725133419037, |
| "eval_runtime": 28.3775, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 1675 |
| }, |
| { |
| "epoch": 4.395604395604396, |
| "grad_norm": 0.8040793538093567, |
| "learning_rate": 0.00011194610002591346, |
| "loss": 0.2258, |
| "step": 1700 |
| }, |
| { |
| "epoch": 4.395604395604396, |
| "eval_loss": 0.33398768305778503, |
| "eval_runtime": 28.3671, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1700 |
| }, |
| { |
| "epoch": 4.460245636716225, |
| "grad_norm": 0.6493346691131592, |
| "learning_rate": 0.00011065042757190982, |
| "loss": 0.2043, |
| "step": 1725 |
| }, |
| { |
| "epoch": 4.460245636716225, |
| "eval_loss": 0.3293030261993408, |
| "eval_runtime": 28.3901, |
| "eval_samples_per_second": 6.833, |
| "eval_steps_per_second": 0.881, |
| "step": 1725 |
| }, |
| { |
| "epoch": 4.524886877828054, |
| "grad_norm": 0.6316075325012207, |
| "learning_rate": 0.0001093547551179062, |
| "loss": 0.2042, |
| "step": 1750 |
| }, |
| { |
| "epoch": 4.524886877828054, |
| "eval_loss": 0.3315393626689911, |
| "eval_runtime": 28.3842, |
| "eval_samples_per_second": 6.835, |
| "eval_steps_per_second": 0.881, |
| "step": 1750 |
| }, |
| { |
| "epoch": 4.589528118939883, |
| "grad_norm": 0.5525413751602173, |
| "learning_rate": 0.00010805908266390257, |
| "loss": 0.2546, |
| "step": 1775 |
| }, |
| { |
| "epoch": 4.589528118939883, |
| "eval_loss": 0.3223138749599457, |
| "eval_runtime": 28.3656, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1775 |
| }, |
| { |
| "epoch": 4.654169360051713, |
| "grad_norm": 0.7611283659934998, |
| "learning_rate": 0.00010676341020989895, |
| "loss": 0.22, |
| "step": 1800 |
| }, |
| { |
| "epoch": 4.654169360051713, |
| "eval_loss": 0.3281467854976654, |
| "eval_runtime": 28.3629, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 1800 |
| }, |
| { |
| "epoch": 4.7188106011635425, |
| "grad_norm": 0.4439404606819153, |
| "learning_rate": 0.00010546773775589531, |
| "loss": 0.2224, |
| "step": 1825 |
| }, |
| { |
| "epoch": 4.7188106011635425, |
| "eval_loss": 0.31960856914520264, |
| "eval_runtime": 28.374, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 1825 |
| }, |
| { |
| "epoch": 4.783451842275372, |
| "grad_norm": 0.8443394303321838, |
| "learning_rate": 0.00010417206530189169, |
| "loss": 0.2139, |
| "step": 1850 |
| }, |
| { |
| "epoch": 4.783451842275372, |
| "eval_loss": 0.32276082038879395, |
| "eval_runtime": 28.3689, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 1850 |
| }, |
| { |
| "epoch": 4.848093083387201, |
| "grad_norm": 0.5965766906738281, |
| "learning_rate": 0.00010287639284788806, |
| "loss": 0.2375, |
| "step": 1875 |
| }, |
| { |
| "epoch": 4.848093083387201, |
| "eval_loss": 0.3183542490005493, |
| "eval_runtime": 28.366, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 1875 |
| }, |
| { |
| "epoch": 4.912734324499031, |
| "grad_norm": 0.9485201239585876, |
| "learning_rate": 0.00010158072039388442, |
| "loss": 0.1954, |
| "step": 1900 |
| }, |
| { |
| "epoch": 4.912734324499031, |
| "eval_loss": 0.3283517062664032, |
| "eval_runtime": 28.3748, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 1900 |
| }, |
| { |
| "epoch": 4.97737556561086, |
| "grad_norm": 0.7058603167533875, |
| "learning_rate": 0.0001002850479398808, |
| "loss": 0.2041, |
| "step": 1925 |
| }, |
| { |
| "epoch": 4.97737556561086, |
| "eval_loss": 0.3203563392162323, |
| "eval_runtime": 28.4113, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 1925 |
| }, |
| { |
| "epoch": 5.042016806722689, |
| "grad_norm": 0.8534159660339355, |
| "learning_rate": 0.00009898937548587718, |
| "loss": 0.1975, |
| "step": 1950 |
| }, |
| { |
| "epoch": 5.042016806722689, |
| "eval_loss": 0.3240514397621155, |
| "eval_runtime": 28.4102, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 1950 |
| }, |
| { |
| "epoch": 5.106658047834518, |
| "grad_norm": 0.36803627014160156, |
| "learning_rate": 0.00009769370303187355, |
| "loss": 0.1778, |
| "step": 1975 |
| }, |
| { |
| "epoch": 5.106658047834518, |
| "eval_loss": 0.31889578700065613, |
| "eval_runtime": 28.4211, |
| "eval_samples_per_second": 6.826, |
| "eval_steps_per_second": 0.88, |
| "step": 1975 |
| }, |
| { |
| "epoch": 5.171299288946348, |
| "grad_norm": 0.4879586398601532, |
| "learning_rate": 0.00009639803057786993, |
| "loss": 0.2034, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.171299288946348, |
| "eval_loss": 0.3188428282737732, |
| "eval_runtime": 28.4244, |
| "eval_samples_per_second": 6.825, |
| "eval_steps_per_second": 0.88, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.235940530058177, |
| "grad_norm": 0.6513077020645142, |
| "learning_rate": 0.00009510235812386628, |
| "loss": 0.1768, |
| "step": 2025 |
| }, |
| { |
| "epoch": 5.235940530058177, |
| "eval_loss": 0.3176546096801758, |
| "eval_runtime": 28.4137, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 2025 |
| }, |
| { |
| "epoch": 5.300581771170006, |
| "grad_norm": 0.6740819811820984, |
| "learning_rate": 0.00009380668566986266, |
| "loss": 0.2105, |
| "step": 2050 |
| }, |
| { |
| "epoch": 5.300581771170006, |
| "eval_loss": 0.31704282760620117, |
| "eval_runtime": 28.4153, |
| "eval_samples_per_second": 6.827, |
| "eval_steps_per_second": 0.88, |
| "step": 2050 |
| }, |
| { |
| "epoch": 5.365223012281835, |
| "grad_norm": 0.5396108031272888, |
| "learning_rate": 0.00009251101321585903, |
| "loss": 0.1675, |
| "step": 2075 |
| }, |
| { |
| "epoch": 5.365223012281835, |
| "eval_loss": 0.32165488600730896, |
| "eval_runtime": 28.4069, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 2075 |
| }, |
| { |
| "epoch": 5.429864253393665, |
| "grad_norm": 0.6571661233901978, |
| "learning_rate": 0.0000912153407618554, |
| "loss": 0.2027, |
| "step": 2100 |
| }, |
| { |
| "epoch": 5.429864253393665, |
| "eval_loss": 0.31289374828338623, |
| "eval_runtime": 28.4118, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 2100 |
| }, |
| { |
| "epoch": 5.4945054945054945, |
| "grad_norm": 0.3653618395328522, |
| "learning_rate": 0.00008991966830785178, |
| "loss": 0.1666, |
| "step": 2125 |
| }, |
| { |
| "epoch": 5.4945054945054945, |
| "eval_loss": 0.32278305292129517, |
| "eval_runtime": 28.4153, |
| "eval_samples_per_second": 6.827, |
| "eval_steps_per_second": 0.88, |
| "step": 2125 |
| }, |
| { |
| "epoch": 5.559146735617324, |
| "grad_norm": 0.6637524366378784, |
| "learning_rate": 0.00008862399585384815, |
| "loss": 0.1968, |
| "step": 2150 |
| }, |
| { |
| "epoch": 5.559146735617324, |
| "eval_loss": 0.3175467550754547, |
| "eval_runtime": 28.4177, |
| "eval_samples_per_second": 6.827, |
| "eval_steps_per_second": 0.88, |
| "step": 2150 |
| }, |
| { |
| "epoch": 5.623787976729153, |
| "grad_norm": 0.4930500388145447, |
| "learning_rate": 0.00008732832339984453, |
| "loss": 0.1731, |
| "step": 2175 |
| }, |
| { |
| "epoch": 5.623787976729153, |
| "eval_loss": 0.31435704231262207, |
| "eval_runtime": 28.4306, |
| "eval_samples_per_second": 6.824, |
| "eval_steps_per_second": 0.879, |
| "step": 2175 |
| }, |
| { |
| "epoch": 5.688429217840983, |
| "grad_norm": 0.9341334700584412, |
| "learning_rate": 0.0000860326509458409, |
| "loss": 0.1951, |
| "step": 2200 |
| }, |
| { |
| "epoch": 5.688429217840983, |
| "eval_loss": 0.31132417917251587, |
| "eval_runtime": 28.4066, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 2200 |
| }, |
| { |
| "epoch": 5.753070458952812, |
| "grad_norm": 0.6325801610946655, |
| "learning_rate": 0.00008473697849183728, |
| "loss": 0.169, |
| "step": 2225 |
| }, |
| { |
| "epoch": 5.753070458952812, |
| "eval_loss": 0.31363645195961, |
| "eval_runtime": 28.4118, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 2225 |
| }, |
| { |
| "epoch": 5.817711700064641, |
| "grad_norm": 0.7663118243217468, |
| "learning_rate": 0.00008344130603783364, |
| "loss": 0.201, |
| "step": 2250 |
| }, |
| { |
| "epoch": 5.817711700064641, |
| "eval_loss": 0.3091263175010681, |
| "eval_runtime": 28.413, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 2250 |
| }, |
| { |
| "epoch": 5.882352941176471, |
| "grad_norm": 0.3682631254196167, |
| "learning_rate": 0.00008214563358383001, |
| "loss": 0.1793, |
| "step": 2275 |
| }, |
| { |
| "epoch": 5.882352941176471, |
| "eval_loss": 0.3104010820388794, |
| "eval_runtime": 28.4081, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 2275 |
| }, |
| { |
| "epoch": 5.9469941822883, |
| "grad_norm": 1.2595940828323364, |
| "learning_rate": 0.00008084996112982637, |
| "loss": 0.1866, |
| "step": 2300 |
| }, |
| { |
| "epoch": 5.9469941822883, |
| "eval_loss": 0.30893900990486145, |
| "eval_runtime": 28.4061, |
| "eval_samples_per_second": 6.83, |
| "eval_steps_per_second": 0.88, |
| "step": 2300 |
| }, |
| { |
| "epoch": 6.011635423400129, |
| "grad_norm": 0.7843431830406189, |
| "learning_rate": 0.00007955428867582275, |
| "loss": 0.1762, |
| "step": 2325 |
| }, |
| { |
| "epoch": 6.011635423400129, |
| "eval_loss": 0.30871468782424927, |
| "eval_runtime": 28.4225, |
| "eval_samples_per_second": 6.826, |
| "eval_steps_per_second": 0.88, |
| "step": 2325 |
| }, |
| { |
| "epoch": 6.076276664511958, |
| "grad_norm": 0.3346283733844757, |
| "learning_rate": 0.00007825861622181913, |
| "loss": 0.1474, |
| "step": 2350 |
| }, |
| { |
| "epoch": 6.076276664511958, |
| "eval_loss": 0.32036280632019043, |
| "eval_runtime": 28.4023, |
| "eval_samples_per_second": 6.83, |
| "eval_steps_per_second": 0.88, |
| "step": 2350 |
| }, |
| { |
| "epoch": 6.140917905623788, |
| "grad_norm": 0.5495737791061401, |
| "learning_rate": 0.0000769629437678155, |
| "loss": 0.1707, |
| "step": 2375 |
| }, |
| { |
| "epoch": 6.140917905623788, |
| "eval_loss": 0.31965798139572144, |
| "eval_runtime": 28.4045, |
| "eval_samples_per_second": 6.83, |
| "eval_steps_per_second": 0.88, |
| "step": 2375 |
| }, |
| { |
| "epoch": 6.2055591467356175, |
| "grad_norm": 0.5422093868255615, |
| "learning_rate": 0.00007566727131381188, |
| "loss": 0.1591, |
| "step": 2400 |
| }, |
| { |
| "epoch": 6.2055591467356175, |
| "eval_loss": 0.3160971999168396, |
| "eval_runtime": 28.4028, |
| "eval_samples_per_second": 6.83, |
| "eval_steps_per_second": 0.88, |
| "step": 2400 |
| }, |
| { |
| "epoch": 6.270200387847447, |
| "grad_norm": 0.9567777514457703, |
| "learning_rate": 0.00007437159885980824, |
| "loss": 0.1647, |
| "step": 2425 |
| }, |
| { |
| "epoch": 6.270200387847447, |
| "eval_loss": 0.31967228651046753, |
| "eval_runtime": 28.4114, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 2425 |
| }, |
| { |
| "epoch": 6.334841628959276, |
| "grad_norm": 0.5891268849372864, |
| "learning_rate": 0.00007307592640580462, |
| "loss": 0.1771, |
| "step": 2450 |
| }, |
| { |
| "epoch": 6.334841628959276, |
| "eval_loss": 0.31348761916160583, |
| "eval_runtime": 28.4285, |
| "eval_samples_per_second": 6.824, |
| "eval_steps_per_second": 0.879, |
| "step": 2450 |
| }, |
| { |
| "epoch": 6.399482870071106, |
| "grad_norm": 0.7958826422691345, |
| "learning_rate": 0.00007178025395180099, |
| "loss": 0.155, |
| "step": 2475 |
| }, |
| { |
| "epoch": 6.399482870071106, |
| "eval_loss": 0.3176797032356262, |
| "eval_runtime": 28.4213, |
| "eval_samples_per_second": 6.826, |
| "eval_steps_per_second": 0.88, |
| "step": 2475 |
| }, |
| { |
| "epoch": 6.464124111182935, |
| "grad_norm": 0.6539425253868103, |
| "learning_rate": 0.00007048458149779737, |
| "loss": 0.1694, |
| "step": 2500 |
| }, |
| { |
| "epoch": 6.464124111182935, |
| "eval_loss": 0.31359249353408813, |
| "eval_runtime": 28.3998, |
| "eval_samples_per_second": 6.831, |
| "eval_steps_per_second": 0.88, |
| "step": 2500 |
| }, |
| { |
| "epoch": 6.528765352294764, |
| "grad_norm": 0.6076931953430176, |
| "learning_rate": 0.00006918890904379373, |
| "loss": 0.1504, |
| "step": 2525 |
| }, |
| { |
| "epoch": 6.528765352294764, |
| "eval_loss": 0.3170049488544464, |
| "eval_runtime": 28.4246, |
| "eval_samples_per_second": 6.825, |
| "eval_steps_per_second": 0.88, |
| "step": 2525 |
| }, |
| { |
| "epoch": 6.593406593406593, |
| "grad_norm": 0.38279989361763, |
| "learning_rate": 0.0000678932365897901, |
| "loss": 0.1607, |
| "step": 2550 |
| }, |
| { |
| "epoch": 6.593406593406593, |
| "eval_loss": 0.3124084174633026, |
| "eval_runtime": 28.4024, |
| "eval_samples_per_second": 6.83, |
| "eval_steps_per_second": 0.88, |
| "step": 2550 |
| }, |
| { |
| "epoch": 6.658047834518423, |
| "grad_norm": 0.8142416477203369, |
| "learning_rate": 0.00006659756413578648, |
| "loss": 0.1591, |
| "step": 2575 |
| }, |
| { |
| "epoch": 6.658047834518423, |
| "eval_loss": 0.3090500831604004, |
| "eval_runtime": 28.4126, |
| "eval_samples_per_second": 6.828, |
| "eval_steps_per_second": 0.88, |
| "step": 2575 |
| }, |
| { |
| "epoch": 6.722689075630252, |
| "grad_norm": 0.635094940662384, |
| "learning_rate": 0.00006530189168178284, |
| "loss": 0.1679, |
| "step": 2600 |
| }, |
| { |
| "epoch": 6.722689075630252, |
| "eval_loss": 0.30714669823646545, |
| "eval_runtime": 28.4075, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 2600 |
| }, |
| { |
| "epoch": 6.787330316742081, |
| "grad_norm": 0.47772154211997986, |
| "learning_rate": 0.00006400621922777922, |
| "loss": 0.1574, |
| "step": 2625 |
| }, |
| { |
| "epoch": 6.787330316742081, |
| "eval_loss": 0.30772703886032104, |
| "eval_runtime": 28.4012, |
| "eval_samples_per_second": 6.831, |
| "eval_steps_per_second": 0.88, |
| "step": 2625 |
| }, |
| { |
| "epoch": 6.85197155785391, |
| "grad_norm": 0.6388984322547913, |
| "learning_rate": 0.00006271054677377559, |
| "loss": 0.1715, |
| "step": 2650 |
| }, |
| { |
| "epoch": 6.85197155785391, |
| "eval_loss": 0.3052230477333069, |
| "eval_runtime": 28.4096, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 2650 |
| }, |
| { |
| "epoch": 6.91661279896574, |
| "grad_norm": 0.6659560203552246, |
| "learning_rate": 0.00006141487431977197, |
| "loss": 0.1447, |
| "step": 2675 |
| }, |
| { |
| "epoch": 6.91661279896574, |
| "eval_loss": 0.30780529975891113, |
| "eval_runtime": 28.4084, |
| "eval_samples_per_second": 6.829, |
| "eval_steps_per_second": 0.88, |
| "step": 2675 |
| }, |
| { |
| "epoch": 6.98125404007757, |
| "grad_norm": 0.43088874220848083, |
| "learning_rate": 0.000060119201865768335, |
| "loss": 0.1537, |
| "step": 2700 |
| }, |
| { |
| "epoch": 6.98125404007757, |
| "eval_loss": 0.309516578912735, |
| "eval_runtime": 28.4237, |
| "eval_samples_per_second": 6.825, |
| "eval_steps_per_second": 0.88, |
| "step": 2700 |
| }, |
| { |
| "epoch": 7.045895281189399, |
| "grad_norm": 0.5778764486312866, |
| "learning_rate": 0.00005882352941176471, |
| "loss": 0.1511, |
| "step": 2725 |
| }, |
| { |
| "epoch": 7.045895281189399, |
| "eval_loss": 0.31108105182647705, |
| "eval_runtime": 28.3719, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 2725 |
| }, |
| { |
| "epoch": 7.110536522301228, |
| "grad_norm": 0.6229362487792969, |
| "learning_rate": 0.00005752785695776109, |
| "loss": 0.1377, |
| "step": 2750 |
| }, |
| { |
| "epoch": 7.110536522301228, |
| "eval_loss": 0.3154136836528778, |
| "eval_runtime": 28.379, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 2750 |
| }, |
| { |
| "epoch": 7.175177763413058, |
| "grad_norm": 0.3511144518852234, |
| "learning_rate": 0.00005623218450375746, |
| "loss": 0.1488, |
| "step": 2775 |
| }, |
| { |
| "epoch": 7.175177763413058, |
| "eval_loss": 0.31371623277664185, |
| "eval_runtime": 28.3618, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 2775 |
| }, |
| { |
| "epoch": 7.239819004524887, |
| "grad_norm": 0.6717267036437988, |
| "learning_rate": 0.00005493651204975383, |
| "loss": 0.1316, |
| "step": 2800 |
| }, |
| { |
| "epoch": 7.239819004524887, |
| "eval_loss": 0.3145770728588104, |
| "eval_runtime": 28.3623, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 2800 |
| }, |
| { |
| "epoch": 7.304460245636716, |
| "grad_norm": 0.6098523139953613, |
| "learning_rate": 0.00005364083959575019, |
| "loss": 0.1428, |
| "step": 2825 |
| }, |
| { |
| "epoch": 7.304460245636716, |
| "eval_loss": 0.31673064827919006, |
| "eval_runtime": 28.3604, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 2825 |
| }, |
| { |
| "epoch": 7.369101486748546, |
| "grad_norm": 0.5013377070426941, |
| "learning_rate": 0.000052345167141746564, |
| "loss": 0.1435, |
| "step": 2850 |
| }, |
| { |
| "epoch": 7.369101486748546, |
| "eval_loss": 0.3164031505584717, |
| "eval_runtime": 28.3626, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 2850 |
| }, |
| { |
| "epoch": 7.433742727860375, |
| "grad_norm": 0.45686689019203186, |
| "learning_rate": 0.000051049494687742936, |
| "loss": 0.1819, |
| "step": 2875 |
| }, |
| { |
| "epoch": 7.433742727860375, |
| "eval_loss": 0.30806776881217957, |
| "eval_runtime": 28.3549, |
| "eval_samples_per_second": 6.842, |
| "eval_steps_per_second": 0.882, |
| "step": 2875 |
| }, |
| { |
| "epoch": 7.498383968972204, |
| "grad_norm": 0.5245105028152466, |
| "learning_rate": 0.00004975382223373931, |
| "loss": 0.1358, |
| "step": 2900 |
| }, |
| { |
| "epoch": 7.498383968972204, |
| "eval_loss": 0.30905425548553467, |
| "eval_runtime": 28.3685, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 2900 |
| }, |
| { |
| "epoch": 7.563025210084033, |
| "grad_norm": 0.6228123903274536, |
| "learning_rate": 0.00004845814977973568, |
| "loss": 0.1473, |
| "step": 2925 |
| }, |
| { |
| "epoch": 7.563025210084033, |
| "eval_loss": 0.309784471988678, |
| "eval_runtime": 28.3689, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 2925 |
| }, |
| { |
| "epoch": 7.6276664511958625, |
| "grad_norm": 0.3951616883277893, |
| "learning_rate": 0.000047162477325732054, |
| "loss": 0.141, |
| "step": 2950 |
| }, |
| { |
| "epoch": 7.6276664511958625, |
| "eval_loss": 0.3125368356704712, |
| "eval_runtime": 28.3669, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 2950 |
| }, |
| { |
| "epoch": 7.6923076923076925, |
| "grad_norm": 0.7255076766014099, |
| "learning_rate": 0.000045866804871728434, |
| "loss": 0.1463, |
| "step": 2975 |
| }, |
| { |
| "epoch": 7.6923076923076925, |
| "eval_loss": 0.31120941042900085, |
| "eval_runtime": 28.3855, |
| "eval_samples_per_second": 6.834, |
| "eval_steps_per_second": 0.881, |
| "step": 2975 |
| }, |
| { |
| "epoch": 7.756948933419522, |
| "grad_norm": 0.3875589072704315, |
| "learning_rate": 0.000044571132417724806, |
| "loss": 0.1364, |
| "step": 3000 |
| }, |
| { |
| "epoch": 7.756948933419522, |
| "eval_loss": 0.3097626268863678, |
| "eval_runtime": 28.3619, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 3000 |
| }, |
| { |
| "epoch": 7.821590174531351, |
| "grad_norm": 0.5227969884872437, |
| "learning_rate": 0.00004327545996372117, |
| "loss": 0.1675, |
| "step": 3025 |
| }, |
| { |
| "epoch": 7.821590174531351, |
| "eval_loss": 0.30695831775665283, |
| "eval_runtime": 28.367, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 3025 |
| }, |
| { |
| "epoch": 7.886231415643181, |
| "grad_norm": 0.6316185593605042, |
| "learning_rate": 0.000041979787509717545, |
| "loss": 0.1332, |
| "step": 3050 |
| }, |
| { |
| "epoch": 7.886231415643181, |
| "eval_loss": 0.3079404830932617, |
| "eval_runtime": 28.3775, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 3050 |
| }, |
| { |
| "epoch": 7.95087265675501, |
| "grad_norm": 0.6401631832122803, |
| "learning_rate": 0.00004068411505571392, |
| "loss": 0.1467, |
| "step": 3075 |
| }, |
| { |
| "epoch": 7.95087265675501, |
| "eval_loss": 0.305776983499527, |
| "eval_runtime": 28.3519, |
| "eval_samples_per_second": 6.843, |
| "eval_steps_per_second": 0.882, |
| "step": 3075 |
| }, |
| { |
| "epoch": 8.015513897866839, |
| "grad_norm": 0.5127146244049072, |
| "learning_rate": 0.00003938844260171029, |
| "loss": 0.1474, |
| "step": 3100 |
| }, |
| { |
| "epoch": 8.015513897866839, |
| "eval_loss": 0.3077903389930725, |
| "eval_runtime": 28.3781, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 3100 |
| }, |
| { |
| "epoch": 8.080155138978668, |
| "grad_norm": 0.7487218379974365, |
| "learning_rate": 0.00003809277014770666, |
| "loss": 0.1383, |
| "step": 3125 |
| }, |
| { |
| "epoch": 8.080155138978668, |
| "eval_loss": 0.31246697902679443, |
| "eval_runtime": 28.3832, |
| "eval_samples_per_second": 6.835, |
| "eval_steps_per_second": 0.881, |
| "step": 3125 |
| }, |
| { |
| "epoch": 8.144796380090497, |
| "grad_norm": 0.8977394104003906, |
| "learning_rate": 0.00003679709769370303, |
| "loss": 0.1329, |
| "step": 3150 |
| }, |
| { |
| "epoch": 8.144796380090497, |
| "eval_loss": 0.31423434615135193, |
| "eval_runtime": 28.3756, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3150 |
| }, |
| { |
| "epoch": 8.209437621202326, |
| "grad_norm": 0.31847473978996277, |
| "learning_rate": 0.0000355014252396994, |
| "loss": 0.1245, |
| "step": 3175 |
| }, |
| { |
| "epoch": 8.209437621202326, |
| "eval_loss": 0.3135824203491211, |
| "eval_runtime": 28.3735, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3175 |
| }, |
| { |
| "epoch": 8.274078862314157, |
| "grad_norm": 0.6578637361526489, |
| "learning_rate": 0.00003420575278569578, |
| "loss": 0.1264, |
| "step": 3200 |
| }, |
| { |
| "epoch": 8.274078862314157, |
| "eval_loss": 0.31525754928588867, |
| "eval_runtime": 28.3733, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3200 |
| }, |
| { |
| "epoch": 8.338720103425986, |
| "grad_norm": 0.37949517369270325, |
| "learning_rate": 0.00003291008033169215, |
| "loss": 0.1226, |
| "step": 3225 |
| }, |
| { |
| "epoch": 8.338720103425986, |
| "eval_loss": 0.3160933554172516, |
| "eval_runtime": 28.3713, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 3225 |
| }, |
| { |
| "epoch": 8.403361344537815, |
| "grad_norm": 0.6433271169662476, |
| "learning_rate": 0.000031614407877688526, |
| "loss": 0.1328, |
| "step": 3250 |
| }, |
| { |
| "epoch": 8.403361344537815, |
| "eval_loss": 0.3180806338787079, |
| "eval_runtime": 28.391, |
| "eval_samples_per_second": 6.833, |
| "eval_steps_per_second": 0.881, |
| "step": 3250 |
| }, |
| { |
| "epoch": 8.468002585649645, |
| "grad_norm": 0.5240097641944885, |
| "learning_rate": 0.000030318735423684895, |
| "loss": 0.1231, |
| "step": 3275 |
| }, |
| { |
| "epoch": 8.468002585649645, |
| "eval_loss": 0.31489038467407227, |
| "eval_runtime": 28.3662, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 3275 |
| }, |
| { |
| "epoch": 8.532643826761474, |
| "grad_norm": 0.5526635646820068, |
| "learning_rate": 0.000029023062969681264, |
| "loss": 0.1407, |
| "step": 3300 |
| }, |
| { |
| "epoch": 8.532643826761474, |
| "eval_loss": 0.31398674845695496, |
| "eval_runtime": 28.3751, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3300 |
| }, |
| { |
| "epoch": 8.597285067873303, |
| "grad_norm": 0.5910195708274841, |
| "learning_rate": 0.000027727390515677637, |
| "loss": 0.1403, |
| "step": 3325 |
| }, |
| { |
| "epoch": 8.597285067873303, |
| "eval_loss": 0.3132157325744629, |
| "eval_runtime": 28.3747, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3325 |
| }, |
| { |
| "epoch": 8.661926308985132, |
| "grad_norm": 0.5976415872573853, |
| "learning_rate": 0.00002643171806167401, |
| "loss": 0.1333, |
| "step": 3350 |
| }, |
| { |
| "epoch": 8.661926308985132, |
| "eval_loss": 0.3119136393070221, |
| "eval_runtime": 28.3806, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 3350 |
| }, |
| { |
| "epoch": 8.726567550096961, |
| "grad_norm": 0.5139032602310181, |
| "learning_rate": 0.000025136045607670382, |
| "loss": 0.1278, |
| "step": 3375 |
| }, |
| { |
| "epoch": 8.726567550096961, |
| "eval_loss": 0.3123859763145447, |
| "eval_runtime": 28.3744, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3375 |
| }, |
| { |
| "epoch": 8.791208791208792, |
| "grad_norm": 0.5774720907211304, |
| "learning_rate": 0.000023840373153666755, |
| "loss": 0.1275, |
| "step": 3400 |
| }, |
| { |
| "epoch": 8.791208791208792, |
| "eval_loss": 0.3116264045238495, |
| "eval_runtime": 28.3831, |
| "eval_samples_per_second": 6.835, |
| "eval_steps_per_second": 0.881, |
| "step": 3400 |
| }, |
| { |
| "epoch": 8.855850032320621, |
| "grad_norm": 0.5800995230674744, |
| "learning_rate": 0.000022544700699663127, |
| "loss": 0.128, |
| "step": 3425 |
| }, |
| { |
| "epoch": 8.855850032320621, |
| "eval_loss": 0.3120003938674927, |
| "eval_runtime": 28.3785, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 3425 |
| }, |
| { |
| "epoch": 8.92049127343245, |
| "grad_norm": 0.8740974068641663, |
| "learning_rate": 0.0000212490282456595, |
| "loss": 0.1224, |
| "step": 3450 |
| }, |
| { |
| "epoch": 8.92049127343245, |
| "eval_loss": 0.31317222118377686, |
| "eval_runtime": 28.3686, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 3450 |
| }, |
| { |
| "epoch": 8.98513251454428, |
| "grad_norm": 0.4104710817337036, |
| "learning_rate": 0.00001995335579165587, |
| "loss": 0.1292, |
| "step": 3475 |
| }, |
| { |
| "epoch": 8.98513251454428, |
| "eval_loss": 0.31374239921569824, |
| "eval_runtime": 28.3767, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3475 |
| }, |
| { |
| "epoch": 9.049773755656108, |
| "grad_norm": 0.4081946909427643, |
| "learning_rate": 0.000018657683337652242, |
| "loss": 0.1345, |
| "step": 3500 |
| }, |
| { |
| "epoch": 9.049773755656108, |
| "eval_loss": 0.3125309348106384, |
| "eval_runtime": 28.3768, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3500 |
| }, |
| { |
| "epoch": 9.114414996767938, |
| "grad_norm": 0.30859458446502686, |
| "learning_rate": 0.000017362010883648614, |
| "loss": 0.1147, |
| "step": 3525 |
| }, |
| { |
| "epoch": 9.114414996767938, |
| "eval_loss": 0.3133779764175415, |
| "eval_runtime": 28.3629, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 3525 |
| }, |
| { |
| "epoch": 9.179056237879767, |
| "grad_norm": 0.6271005868911743, |
| "learning_rate": 0.000016066338429644987, |
| "loss": 0.1296, |
| "step": 3550 |
| }, |
| { |
| "epoch": 9.179056237879767, |
| "eval_loss": 0.31399643421173096, |
| "eval_runtime": 28.3738, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3550 |
| }, |
| { |
| "epoch": 9.243697478991596, |
| "grad_norm": 0.41167113184928894, |
| "learning_rate": 0.00001477066597564136, |
| "loss": 0.1154, |
| "step": 3575 |
| }, |
| { |
| "epoch": 9.243697478991596, |
| "eval_loss": 0.3143480718135834, |
| "eval_runtime": 28.38, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 3575 |
| }, |
| { |
| "epoch": 9.308338720103427, |
| "grad_norm": 0.5452168583869934, |
| "learning_rate": 0.00001347499352163773, |
| "loss": 0.1268, |
| "step": 3600 |
| }, |
| { |
| "epoch": 9.308338720103427, |
| "eval_loss": 0.3152347207069397, |
| "eval_runtime": 28.3721, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 3600 |
| }, |
| { |
| "epoch": 9.372979961215256, |
| "grad_norm": 0.4865732789039612, |
| "learning_rate": 0.000012179321067634103, |
| "loss": 0.1148, |
| "step": 3625 |
| }, |
| { |
| "epoch": 9.372979961215256, |
| "eval_loss": 0.31540754437446594, |
| "eval_runtime": 28.3777, |
| "eval_samples_per_second": 6.836, |
| "eval_steps_per_second": 0.881, |
| "step": 3625 |
| }, |
| { |
| "epoch": 9.437621202327085, |
| "grad_norm": 0.49929162859916687, |
| "learning_rate": 0.000010883648613630474, |
| "loss": 0.1321, |
| "step": 3650 |
| }, |
| { |
| "epoch": 9.437621202327085, |
| "eval_loss": 0.3150508999824524, |
| "eval_runtime": 28.3598, |
| "eval_samples_per_second": 6.841, |
| "eval_steps_per_second": 0.882, |
| "step": 3650 |
| }, |
| { |
| "epoch": 9.502262443438914, |
| "grad_norm": 0.3693055808544159, |
| "learning_rate": 0.000009587976159626847, |
| "loss": 0.1197, |
| "step": 3675 |
| }, |
| { |
| "epoch": 9.502262443438914, |
| "eval_loss": 0.31471407413482666, |
| "eval_runtime": 28.3771, |
| "eval_samples_per_second": 6.837, |
| "eval_steps_per_second": 0.881, |
| "step": 3675 |
| }, |
| { |
| "epoch": 9.566903684550743, |
| "grad_norm": 0.7790170907974243, |
| "learning_rate": 0.00000829230370562322, |
| "loss": 0.1278, |
| "step": 3700 |
| }, |
| { |
| "epoch": 9.566903684550743, |
| "eval_loss": 0.31443536281585693, |
| "eval_runtime": 28.3686, |
| "eval_samples_per_second": 6.839, |
| "eval_steps_per_second": 0.881, |
| "step": 3700 |
| }, |
| { |
| "epoch": 9.631544925662572, |
| "grad_norm": 0.4334302246570587, |
| "learning_rate": 0.000006996631251619591, |
| "loss": 0.1257, |
| "step": 3725 |
| }, |
| { |
| "epoch": 9.631544925662572, |
| "eval_loss": 0.31435123085975647, |
| "eval_runtime": 28.3701, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 3725 |
| }, |
| { |
| "epoch": 9.696186166774401, |
| "grad_norm": 0.5498323440551758, |
| "learning_rate": 0.000005700958797615963, |
| "loss": 0.1246, |
| "step": 3750 |
| }, |
| { |
| "epoch": 9.696186166774401, |
| "eval_loss": 0.31406232714653015, |
| "eval_runtime": 28.372, |
| "eval_samples_per_second": 6.838, |
| "eval_steps_per_second": 0.881, |
| "step": 3750 |
| }, |
| { |
| "epoch": 9.760827407886232, |
| "grad_norm": 0.4685628414154053, |
| "learning_rate": 0.0000044052863436123355, |
| "loss": 0.1188, |
| "step": 3775 |
| }, |
| { |
| "epoch": 9.760827407886232, |
| "eval_loss": 0.3140473961830139, |
| "eval_runtime": 28.3637, |
| "eval_samples_per_second": 6.84, |
| "eval_steps_per_second": 0.881, |
| "step": 3775 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 3860, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 25, |
| "total_flos": 23909482663833600, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
