| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6236297198538368, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 2.0573711842298508, | |
| "epoch": 0.016240357287860333, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 2.3979, | |
| "mean_token_accuracy": 0.5674526583403349, | |
| "num_tokens": 319222.0, | |
| "step": 10 | |
| }, | |
| { | |
| "entropy": 1.6298254258930682, | |
| "epoch": 0.032480714575720666, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 6.785714285714286e-05, | |
| "loss": 1.7067, | |
| "mean_token_accuracy": 0.6522471688687801, | |
| "num_tokens": 635410.0, | |
| "step": 20 | |
| }, | |
| { | |
| "entropy": 0.8830645218491554, | |
| "epoch": 0.048721071863580996, | |
| "grad_norm": 0.28125, | |
| "learning_rate": 0.00010357142857142859, | |
| "loss": 0.8894, | |
| "mean_token_accuracy": 0.791144409775734, | |
| "num_tokens": 952489.0, | |
| "step": 30 | |
| }, | |
| { | |
| "entropy": 0.6340911261737346, | |
| "epoch": 0.06496142915144133, | |
| "grad_norm": 0.2236328125, | |
| "learning_rate": 0.0001392857142857143, | |
| "loss": 0.6371, | |
| "mean_token_accuracy": 0.840929938852787, | |
| "num_tokens": 1271722.0, | |
| "step": 40 | |
| }, | |
| { | |
| "entropy": 0.5732324108481407, | |
| "epoch": 0.08120178643930166, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 0.000175, | |
| "loss": 0.5747, | |
| "mean_token_accuracy": 0.8537561506032944, | |
| "num_tokens": 1590635.0, | |
| "step": 50 | |
| }, | |
| { | |
| "entropy": 0.5194318823516368, | |
| "epoch": 0.09744214372716199, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.0001999986169583868, | |
| "loss": 0.5268, | |
| "mean_token_accuracy": 0.8640895910561085, | |
| "num_tokens": 1908010.0, | |
| "step": 60 | |
| }, | |
| { | |
| "entropy": 0.49497435204684737, | |
| "epoch": 0.11368250101502234, | |
| "grad_norm": 0.125, | |
| "learning_rate": 0.00019997403061615897, | |
| "loss": 0.4986, | |
| "mean_token_accuracy": 0.8717949956655502, | |
| "num_tokens": 2225569.0, | |
| "step": 70 | |
| }, | |
| { | |
| "entropy": 0.4971678379923105, | |
| "epoch": 0.12992285830288267, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.0001999187187134847, | |
| "loss": 0.4924, | |
| "mean_token_accuracy": 0.8731547556817532, | |
| "num_tokens": 2539488.0, | |
| "step": 80 | |
| }, | |
| { | |
| "entropy": 0.5084386952221394, | |
| "epoch": 0.146163215590743, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00019983269824967067, | |
| "loss": 0.5163, | |
| "mean_token_accuracy": 0.8671703346073627, | |
| "num_tokens": 2857760.0, | |
| "step": 90 | |
| }, | |
| { | |
| "entropy": 0.476475191116333, | |
| "epoch": 0.16240357287860333, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.00019971599566185206, | |
| "loss": 0.4758, | |
| "mean_token_accuracy": 0.876344844698906, | |
| "num_tokens": 3174136.0, | |
| "step": 100 | |
| }, | |
| { | |
| "entropy": 0.48804047554731367, | |
| "epoch": 0.17864393016646365, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.00019956864681686744, | |
| "loss": 0.4837, | |
| "mean_token_accuracy": 0.8742976881563663, | |
| "num_tokens": 3489505.0, | |
| "step": 110 | |
| }, | |
| { | |
| "entropy": 0.4607066061347723, | |
| "epoch": 0.19488428745432398, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 0.00019939069700023563, | |
| "loss": 0.4639, | |
| "mean_token_accuracy": 0.879499676078558, | |
| "num_tokens": 3807935.0, | |
| "step": 120 | |
| }, | |
| { | |
| "entropy": 0.4422083988785744, | |
| "epoch": 0.21112464474218431, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.00019918220090223775, | |
| "loss": 0.4431, | |
| "mean_token_accuracy": 0.8831395357847214, | |
| "num_tokens": 4125137.0, | |
| "step": 130 | |
| }, | |
| { | |
| "entropy": 0.44356597438454626, | |
| "epoch": 0.22736500203004467, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 0.00019894322260110927, | |
| "loss": 0.4373, | |
| "mean_token_accuracy": 0.8849747203290462, | |
| "num_tokens": 4442538.0, | |
| "step": 140 | |
| }, | |
| { | |
| "entropy": 0.44916940554976464, | |
| "epoch": 0.243605359317905, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.00019867383554334603, | |
| "loss": 0.4473, | |
| "mean_token_accuracy": 0.8828106552362442, | |
| "num_tokens": 4761703.0, | |
| "step": 150 | |
| }, | |
| { | |
| "entropy": 0.44491727463901043, | |
| "epoch": 0.25984571660576533, | |
| "grad_norm": 0.09716796875, | |
| "learning_rate": 0.00019837412252113204, | |
| "loss": 0.446, | |
| "mean_token_accuracy": 0.8818246781826019, | |
| "num_tokens": 5080459.0, | |
| "step": 160 | |
| }, | |
| { | |
| "entropy": 0.4443864993751049, | |
| "epoch": 0.27608607389362566, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 0.00019804417564689403, | |
| "loss": 0.4424, | |
| "mean_token_accuracy": 0.8833745121955872, | |
| "num_tokens": 5394935.0, | |
| "step": 170 | |
| }, | |
| { | |
| "entropy": 0.43182576820254326, | |
| "epoch": 0.292326431181486, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00019768409632499244, | |
| "loss": 0.4337, | |
| "mean_token_accuracy": 0.8853104099631309, | |
| "num_tokens": 5711130.0, | |
| "step": 180 | |
| }, | |
| { | |
| "entropy": 0.4353721059858799, | |
| "epoch": 0.3085667884693463, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 0.00019729399522055603, | |
| "loss": 0.4351, | |
| "mean_token_accuracy": 0.8850096859037876, | |
| "num_tokens": 6028009.0, | |
| "step": 190 | |
| }, | |
| { | |
| "entropy": 0.4161925382912159, | |
| "epoch": 0.32480714575720665, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 0.0001968739922254706, | |
| "loss": 0.4118, | |
| "mean_token_accuracy": 0.8901829145848751, | |
| "num_tokens": 6345284.0, | |
| "step": 200 | |
| }, | |
| { | |
| "entropy": 0.4270293299108744, | |
| "epoch": 0.341047503045067, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 0.00019642421642153198, | |
| "loss": 0.4266, | |
| "mean_token_accuracy": 0.885687505453825, | |
| "num_tokens": 6664555.0, | |
| "step": 210 | |
| }, | |
| { | |
| "entropy": 0.4177013225853443, | |
| "epoch": 0.3572878603329273, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.0001959448060407748, | |
| "loss": 0.4185, | |
| "mean_token_accuracy": 0.8890490755438805, | |
| "num_tokens": 6984869.0, | |
| "step": 220 | |
| }, | |
| { | |
| "entropy": 0.4492575516924262, | |
| "epoch": 0.37352821762078764, | |
| "grad_norm": 0.125, | |
| "learning_rate": 0.00019543590842298857, | |
| "loss": 0.4471, | |
| "mean_token_accuracy": 0.8821755766868591, | |
| "num_tokens": 7301522.0, | |
| "step": 230 | |
| }, | |
| { | |
| "entropy": 0.4262876145541668, | |
| "epoch": 0.38976857490864797, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 0.0001948976799704351, | |
| "loss": 0.4272, | |
| "mean_token_accuracy": 0.8858069330453873, | |
| "num_tokens": 7617411.0, | |
| "step": 240 | |
| }, | |
| { | |
| "entropy": 0.4227599944919348, | |
| "epoch": 0.4060089321965083, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 0.0001943302860997807, | |
| "loss": 0.4183, | |
| "mean_token_accuracy": 0.889183484762907, | |
| "num_tokens": 7932287.0, | |
| "step": 250 | |
| }, | |
| { | |
| "entropy": 0.4225012965500355, | |
| "epoch": 0.42224928948436863, | |
| "grad_norm": 0.173828125, | |
| "learning_rate": 0.00019373390119125752, | |
| "loss": 0.4241, | |
| "mean_token_accuracy": 0.8874775715172291, | |
| "num_tokens": 8249106.0, | |
| "step": 260 | |
| }, | |
| { | |
| "entropy": 0.4166328992694616, | |
| "epoch": 0.438489646772229, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 0.00019310870853507043, | |
| "loss": 0.4183, | |
| "mean_token_accuracy": 0.8885860778391361, | |
| "num_tokens": 8564544.0, | |
| "step": 270 | |
| }, | |
| { | |
| "entropy": 0.38806356210261583, | |
| "epoch": 0.45473000406008934, | |
| "grad_norm": 0.11328125, | |
| "learning_rate": 0.00019245490027506546, | |
| "loss": 0.3836, | |
| "mean_token_accuracy": 0.8962622597813606, | |
| "num_tokens": 8883546.0, | |
| "step": 280 | |
| }, | |
| { | |
| "entropy": 0.388262290135026, | |
| "epoch": 0.4709703613479497, | |
| "grad_norm": 0.09130859375, | |
| "learning_rate": 0.0001917726773496773, | |
| "loss": 0.3847, | |
| "mean_token_accuracy": 0.8955962382256984, | |
| "num_tokens": 9199902.0, | |
| "step": 290 | |
| }, | |
| { | |
| "entropy": 0.40017246957868335, | |
| "epoch": 0.48721071863581, | |
| "grad_norm": 0.09716796875, | |
| "learning_rate": 0.00019106224943017352, | |
| "loss": 0.3984, | |
| "mean_token_accuracy": 0.8926815405488014, | |
| "num_tokens": 9518427.0, | |
| "step": 300 | |
| }, | |
| { | |
| "entropy": 0.39343364126980307, | |
| "epoch": 0.5034510759236703, | |
| "grad_norm": 0.09521484375, | |
| "learning_rate": 0.00019032383485621546, | |
| "loss": 0.3936, | |
| "mean_token_accuracy": 0.8935227513313293, | |
| "num_tokens": 9834801.0, | |
| "step": 310 | |
| }, | |
| { | |
| "entropy": 0.40088152755051853, | |
| "epoch": 0.5196914332115307, | |
| "grad_norm": 0.09423828125, | |
| "learning_rate": 0.00018955766056875456, | |
| "loss": 0.4013, | |
| "mean_token_accuracy": 0.8928539358079434, | |
| "num_tokens": 10150756.0, | |
| "step": 320 | |
| }, | |
| { | |
| "entropy": 0.3935076169669628, | |
| "epoch": 0.535931790499391, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 0.0001887639620402854, | |
| "loss": 0.3894, | |
| "mean_token_accuracy": 0.8937225684523582, | |
| "num_tokens": 10470119.0, | |
| "step": 330 | |
| }, | |
| { | |
| "entropy": 0.4141834359616041, | |
| "epoch": 0.5521721477872513, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.00018794298320247665, | |
| "loss": 0.415, | |
| "mean_token_accuracy": 0.8895114719867706, | |
| "num_tokens": 10787249.0, | |
| "step": 340 | |
| }, | |
| { | |
| "entropy": 0.41944080144166945, | |
| "epoch": 0.5684125050751117, | |
| "grad_norm": 0.1162109375, | |
| "learning_rate": 0.0001870949763712022, | |
| "loss": 0.4151, | |
| "mean_token_accuracy": 0.8887378059327602, | |
| "num_tokens": 11107800.0, | |
| "step": 350 | |
| }, | |
| { | |
| "entropy": 0.4085154063999653, | |
| "epoch": 0.584652862362972, | |
| "grad_norm": 0.123046875, | |
| "learning_rate": 0.00018622020216899575, | |
| "loss": 0.4067, | |
| "mean_token_accuracy": 0.8906957127153874, | |
| "num_tokens": 11424520.0, | |
| "step": 360 | |
| }, | |
| { | |
| "entropy": 0.41457892414182423, | |
| "epoch": 0.6008932196508323, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00018531892944495195, | |
| "loss": 0.4139, | |
| "mean_token_accuracy": 0.8893011771142483, | |
| "num_tokens": 11743854.0, | |
| "step": 370 | |
| }, | |
| { | |
| "entropy": 0.3982046090066433, | |
| "epoch": 0.6171335769386926, | |
| "grad_norm": 0.095703125, | |
| "learning_rate": 0.00018439143519209984, | |
| "loss": 0.3972, | |
| "mean_token_accuracy": 0.8931242369115353, | |
| "num_tokens": 12060493.0, | |
| "step": 380 | |
| }, | |
| { | |
| "entropy": 0.37617460917681456, | |
| "epoch": 0.633373934226553, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 0.00018343800446227285, | |
| "loss": 0.3737, | |
| "mean_token_accuracy": 0.8988998346030712, | |
| "num_tokens": 12377614.0, | |
| "step": 390 | |
| }, | |
| { | |
| "entropy": 0.38792264480143784, | |
| "epoch": 0.6496142915144133, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.00018245893027850254, | |
| "loss": 0.3863, | |
| "mean_token_accuracy": 0.8964896731078624, | |
| "num_tokens": 12695713.0, | |
| "step": 400 | |
| }, | |
| { | |
| "entropy": 0.3779356569051743, | |
| "epoch": 0.6658546488022736, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.00018145451354496198, | |
| "loss": 0.377, | |
| "mean_token_accuracy": 0.8985928252339364, | |
| "num_tokens": 13011198.0, | |
| "step": 410 | |
| }, | |
| { | |
| "entropy": 0.40948784444481134, | |
| "epoch": 0.682095006090134, | |
| "grad_norm": 0.1162109375, | |
| "learning_rate": 0.0001804250629544874, | |
| "loss": 0.4077, | |
| "mean_token_accuracy": 0.8911456301808357, | |
| "num_tokens": 13329544.0, | |
| "step": 420 | |
| }, | |
| { | |
| "entropy": 0.38341086860746143, | |
| "epoch": 0.6983353633779943, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 0.00017937089489370594, | |
| "loss": 0.3829, | |
| "mean_token_accuracy": 0.8969453655183315, | |
| "num_tokens": 13645469.0, | |
| "step": 430 | |
| }, | |
| { | |
| "entropy": 0.3890859391540289, | |
| "epoch": 0.7145757206658546, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.0001782923333457987, | |
| "loss": 0.3875, | |
| "mean_token_accuracy": 0.8961056731641293, | |
| "num_tokens": 13964383.0, | |
| "step": 440 | |
| }, | |
| { | |
| "entropy": 0.3823310313746333, | |
| "epoch": 0.730816077953715, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 0.0001771897097909294, | |
| "loss": 0.3857, | |
| "mean_token_accuracy": 0.8955351069569588, | |
| "num_tokens": 14284139.0, | |
| "step": 450 | |
| }, | |
| { | |
| "entropy": 0.372044226154685, | |
| "epoch": 0.7470564352415753, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 0.00017606336310436874, | |
| "loss": 0.3703, | |
| "mean_token_accuracy": 0.8989921748638153, | |
| "num_tokens": 14601084.0, | |
| "step": 460 | |
| }, | |
| { | |
| "entropy": 0.3764212913811207, | |
| "epoch": 0.7632967925294356, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 0.00017491363945234593, | |
| "loss": 0.3708, | |
| "mean_token_accuracy": 0.8989950515329838, | |
| "num_tokens": 14919347.0, | |
| "step": 470 | |
| }, | |
| { | |
| "entropy": 0.3796376219019294, | |
| "epoch": 0.7795371498172959, | |
| "grad_norm": 0.0986328125, | |
| "learning_rate": 0.00017374089218565972, | |
| "loss": 0.3777, | |
| "mean_token_accuracy": 0.8979221723973752, | |
| "num_tokens": 15235024.0, | |
| "step": 480 | |
| }, | |
| { | |
| "entropy": 0.3780976843088865, | |
| "epoch": 0.7957775071051563, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 0.000172545481731081, | |
| "loss": 0.3814, | |
| "mean_token_accuracy": 0.8970133177936077, | |
| "num_tokens": 15555890.0, | |
| "step": 490 | |
| }, | |
| { | |
| "entropy": 0.36868189480155705, | |
| "epoch": 0.8120178643930166, | |
| "grad_norm": 0.1318359375, | |
| "learning_rate": 0.00017132777548058102, | |
| "loss": 0.367, | |
| "mean_token_accuracy": 0.8997100129723549, | |
| "num_tokens": 15871127.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8120178643930166, | |
| "eval_entropy": 0.3875140378834637, | |
| "eval_loss": 0.38122546672821045, | |
| "eval_mean_token_accuracy": 0.8967177114868892, | |
| "eval_num_tokens": 15871127.0, | |
| "eval_runtime": 177.0916, | |
| "eval_samples_per_second": 2.953, | |
| "eval_steps_per_second": 1.479, | |
| "step": 500 | |
| }, | |
| { | |
| "entropy": 0.36098182667046785, | |
| "epoch": 0.8282582216808769, | |
| "grad_norm": 0.091796875, | |
| "learning_rate": 0.00017008814767841872, | |
| "loss": 0.358, | |
| "mean_token_accuracy": 0.9020477868616581, | |
| "num_tokens": 16186646.0, | |
| "step": 510 | |
| }, | |
| { | |
| "entropy": 0.37107769679278135, | |
| "epoch": 0.8444985789687373, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00016882697930612237, | |
| "loss": 0.3667, | |
| "mean_token_accuracy": 0.8997148185968399, | |
| "num_tokens": 16505442.0, | |
| "step": 520 | |
| }, | |
| { | |
| "entropy": 0.36859209295362233, | |
| "epoch": 0.8607389362565977, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 0.00016754465796540028, | |
| "loss": 0.3656, | |
| "mean_token_accuracy": 0.9001396887004376, | |
| "num_tokens": 16824612.0, | |
| "step": 530 | |
| }, | |
| { | |
| "entropy": 0.36337947361171247, | |
| "epoch": 0.876979293544458, | |
| "grad_norm": 0.095703125, | |
| "learning_rate": 0.0001662415777590172, | |
| "loss": 0.3653, | |
| "mean_token_accuracy": 0.9004977688193321, | |
| "num_tokens": 17147012.0, | |
| "step": 540 | |
| }, | |
| { | |
| "entropy": 0.38551054075360297, | |
| "epoch": 0.8932196508323184, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00016491813916967246, | |
| "loss": 0.3841, | |
| "mean_token_accuracy": 0.8968335554003716, | |
| "num_tokens": 17463603.0, | |
| "step": 550 | |
| }, | |
| { | |
| "entropy": 0.3718857761472464, | |
| "epoch": 0.9094600081201787, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.00016357474893691757, | |
| "loss": 0.3694, | |
| "mean_token_accuracy": 0.8994779132306576, | |
| "num_tokens": 17780634.0, | |
| "step": 560 | |
| }, | |
| { | |
| "entropy": 0.3478269662708044, | |
| "epoch": 0.925700365408039, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00016221181993215068, | |
| "loss": 0.3495, | |
| "mean_token_accuracy": 0.9044472806155681, | |
| "num_tokens": 18099787.0, | |
| "step": 570 | |
| }, | |
| { | |
| "entropy": 0.3706334102898836, | |
| "epoch": 0.9419407226958993, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 0.00016082977103172664, | |
| "loss": 0.3643, | |
| "mean_token_accuracy": 0.9007264509797096, | |
| "num_tokens": 18417572.0, | |
| "step": 580 | |
| }, | |
| { | |
| "entropy": 0.33980775382369754, | |
| "epoch": 0.9581810799837597, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.00015942902698822136, | |
| "loss": 0.339, | |
| "mean_token_accuracy": 0.9067365050315856, | |
| "num_tokens": 18734911.0, | |
| "step": 590 | |
| }, | |
| { | |
| "entropy": 0.36088257618248465, | |
| "epoch": 0.97442143727162, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 0.00015801001829989032, | |
| "loss": 0.3576, | |
| "mean_token_accuracy": 0.9025222927331924, | |
| "num_tokens": 19054345.0, | |
| "step": 600 | |
| }, | |
| { | |
| "entropy": 0.35844882633537056, | |
| "epoch": 0.9906617945594803, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.0001565731810783613, | |
| "loss": 0.3553, | |
| "mean_token_accuracy": 0.9028041236102581, | |
| "num_tokens": 19371809.0, | |
| "step": 610 | |
| }, | |
| { | |
| "entropy": 0.3564173472233308, | |
| "epoch": 1.0064961429151442, | |
| "grad_norm": 0.11181640625, | |
| "learning_rate": 0.00015511895691460188, | |
| "loss": 0.353, | |
| "mean_token_accuracy": 0.9035867773569547, | |
| "num_tokens": 19684212.0, | |
| "step": 620 | |
| }, | |
| { | |
| "entropy": 0.3372783612459898, | |
| "epoch": 1.0227365002030044, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 0.00015364779274320255, | |
| "loss": 0.3362, | |
| "mean_token_accuracy": 0.9072924487292766, | |
| "num_tokens": 20003357.0, | |
| "step": 630 | |
| }, | |
| { | |
| "entropy": 0.3311926079913974, | |
| "epoch": 1.0389768574908649, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.00015216014070501834, | |
| "loss": 0.3244, | |
| "mean_token_accuracy": 0.9089326687157154, | |
| "num_tokens": 20322614.0, | |
| "step": 640 | |
| }, | |
| { | |
| "entropy": 0.33821379821747544, | |
| "epoch": 1.055217214778725, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.0001506564580082096, | |
| "loss": 0.3388, | |
| "mean_token_accuracy": 0.9062777034938335, | |
| "num_tokens": 20635631.0, | |
| "step": 650 | |
| }, | |
| { | |
| "entropy": 0.3465416576713324, | |
| "epoch": 1.0714575720665855, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00014913720678772584, | |
| "loss": 0.3455, | |
| "mean_token_accuracy": 0.9043642178177833, | |
| "num_tokens": 20955241.0, | |
| "step": 660 | |
| }, | |
| { | |
| "entropy": 0.33202757611870765, | |
| "epoch": 1.0876979293544458, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 0.00014760285396327532, | |
| "loss": 0.3277, | |
| "mean_token_accuracy": 0.9081737406551837, | |
| "num_tokens": 21269871.0, | |
| "step": 670 | |
| }, | |
| { | |
| "entropy": 0.30594254843890667, | |
| "epoch": 1.1039382866423062, | |
| "grad_norm": 0.140625, | |
| "learning_rate": 0.000146053871095824, | |
| "loss": 0.3029, | |
| "mean_token_accuracy": 0.9145903818309307, | |
| "num_tokens": 21586356.0, | |
| "step": 680 | |
| }, | |
| { | |
| "entropy": 0.31971859056502583, | |
| "epoch": 1.1201786439301664, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.00014449073424266837, | |
| "loss": 0.3133, | |
| "mean_token_accuracy": 0.9111780665814877, | |
| "num_tokens": 21905514.0, | |
| "step": 690 | |
| }, | |
| { | |
| "entropy": 0.32340758945792913, | |
| "epoch": 1.1364190012180269, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.0001429139238111259, | |
| "loss": 0.3199, | |
| "mean_token_accuracy": 0.910588438808918, | |
| "num_tokens": 22224116.0, | |
| "step": 700 | |
| }, | |
| { | |
| "entropy": 0.30627013817429544, | |
| "epoch": 1.152659358505887, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 0.00014132392441088898, | |
| "loss": 0.3062, | |
| "mean_token_accuracy": 0.9141925357282161, | |
| "num_tokens": 22541518.0, | |
| "step": 710 | |
| }, | |
| { | |
| "entropy": 0.34387709144502876, | |
| "epoch": 1.1688997157937475, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00013972122470508726, | |
| "loss": 0.3388, | |
| "mean_token_accuracy": 0.9059014208614826, | |
| "num_tokens": 22857809.0, | |
| "step": 720 | |
| }, | |
| { | |
| "entropy": 0.3105178466066718, | |
| "epoch": 1.1851400730816077, | |
| "grad_norm": 0.103515625, | |
| "learning_rate": 0.00013810631726010405, | |
| "loss": 0.3113, | |
| "mean_token_accuracy": 0.912415674328804, | |
| "num_tokens": 23175061.0, | |
| "step": 730 | |
| }, | |
| { | |
| "entropy": 0.32021520137786863, | |
| "epoch": 1.2013804303694682, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 0.00013647969839419334, | |
| "loss": 0.3166, | |
| "mean_token_accuracy": 0.9124397613108158, | |
| "num_tokens": 23492422.0, | |
| "step": 740 | |
| }, | |
| { | |
| "entropy": 0.33215807750821114, | |
| "epoch": 1.2176207876573284, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 0.00013484186802494345, | |
| "loss": 0.3288, | |
| "mean_token_accuracy": 0.9079324699938297, | |
| "num_tokens": 23811312.0, | |
| "step": 750 | |
| }, | |
| { | |
| "entropy": 0.3269189100712538, | |
| "epoch": 1.2338611449451888, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.00013319332951563495, | |
| "loss": 0.3229, | |
| "mean_token_accuracy": 0.9100485563278198, | |
| "num_tokens": 24127363.0, | |
| "step": 760 | |
| }, | |
| { | |
| "entropy": 0.32415517419576645, | |
| "epoch": 1.250101502233049, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.0001315345895205389, | |
| "loss": 0.3218, | |
| "mean_token_accuracy": 0.9100560195744037, | |
| "num_tokens": 24443515.0, | |
| "step": 770 | |
| }, | |
| { | |
| "entropy": 0.3075957763940096, | |
| "epoch": 1.2663418595209095, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.0001298661578292044, | |
| "loss": 0.3085, | |
| "mean_token_accuracy": 0.9134799301624298, | |
| "num_tokens": 24759656.0, | |
| "step": 780 | |
| }, | |
| { | |
| "entropy": 0.33256804049015043, | |
| "epoch": 1.2825822168087697, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00012818854720978196, | |
| "loss": 0.3283, | |
| "mean_token_accuracy": 0.9092446401715278, | |
| "num_tokens": 25076124.0, | |
| "step": 790 | |
| }, | |
| { | |
| "entropy": 0.3044602788053453, | |
| "epoch": 1.2988225740966302, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 0.00012650227325143191, | |
| "loss": 0.2998, | |
| "mean_token_accuracy": 0.9158783234655857, | |
| "num_tokens": 25394550.0, | |
| "step": 800 | |
| }, | |
| { | |
| "entropy": 0.3089112024754286, | |
| "epoch": 1.3150629313844906, | |
| "grad_norm": 0.1181640625, | |
| "learning_rate": 0.0001248078542058653, | |
| "loss": 0.3065, | |
| "mean_token_accuracy": 0.9139430224895477, | |
| "num_tokens": 25713937.0, | |
| "step": 810 | |
| }, | |
| { | |
| "entropy": 0.3199151481501758, | |
| "epoch": 1.3313032886723508, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 0.00012310581082806713, | |
| "loss": 0.3153, | |
| "mean_token_accuracy": 0.9130744747817516, | |
| "num_tokens": 26033627.0, | |
| "step": 820 | |
| }, | |
| { | |
| "entropy": 0.3134147599339485, | |
| "epoch": 1.347543645960211, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 0.0001213966662162496, | |
| "loss": 0.3158, | |
| "mean_token_accuracy": 0.9115599945187569, | |
| "num_tokens": 26351334.0, | |
| "step": 830 | |
| }, | |
| { | |
| "entropy": 0.30595332104712725, | |
| "epoch": 1.3637840032480715, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 0.00011968094565108572, | |
| "loss": 0.2998, | |
| "mean_token_accuracy": 0.9158065438270568, | |
| "num_tokens": 26670167.0, | |
| "step": 840 | |
| }, | |
| { | |
| "entropy": 0.3209634754806757, | |
| "epoch": 1.380024360535932, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 0.00011795917643427179, | |
| "loss": 0.3185, | |
| "mean_token_accuracy": 0.9116993598639965, | |
| "num_tokens": 26987963.0, | |
| "step": 850 | |
| }, | |
| { | |
| "entropy": 0.31424548048526046, | |
| "epoch": 1.3962647178237921, | |
| "grad_norm": 0.1171875, | |
| "learning_rate": 0.0001162318877264691, | |
| "loss": 0.3089, | |
| "mean_token_accuracy": 0.9129889853298664, | |
| "num_tokens": 27308192.0, | |
| "step": 860 | |
| }, | |
| { | |
| "entropy": 0.33518767151981593, | |
| "epoch": 1.4125050751116524, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00011449961038467389, | |
| "loss": 0.3334, | |
| "mean_token_accuracy": 0.907250489294529, | |
| "num_tokens": 27627277.0, | |
| "step": 870 | |
| }, | |
| { | |
| "entropy": 0.32196133993566034, | |
| "epoch": 1.4287454323995128, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.00011276287679906639, | |
| "loss": 0.3235, | |
| "mean_token_accuracy": 0.9093112558126449, | |
| "num_tokens": 27943368.0, | |
| "step": 880 | |
| }, | |
| { | |
| "entropy": 0.3061803586781025, | |
| "epoch": 1.4449857896873732, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.00011102222072938832, | |
| "loss": 0.3011, | |
| "mean_token_accuracy": 0.915228334069252, | |
| "num_tokens": 28259836.0, | |
| "step": 890 | |
| }, | |
| { | |
| "entropy": 0.3232524123042822, | |
| "epoch": 1.4612261469752335, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 0.00010927817714089973, | |
| "loss": 0.3191, | |
| "mean_token_accuracy": 0.9117089517414569, | |
| "num_tokens": 28580230.0, | |
| "step": 900 | |
| }, | |
| { | |
| "entropy": 0.33082296065986155, | |
| "epoch": 1.4774665042630937, | |
| "grad_norm": 0.11962890625, | |
| "learning_rate": 0.00010753128203996519, | |
| "loss": 0.3269, | |
| "mean_token_accuracy": 0.9086541675031186, | |
| "num_tokens": 28898617.0, | |
| "step": 910 | |
| }, | |
| { | |
| "entropy": 0.3250410893931985, | |
| "epoch": 1.4937068615509541, | |
| "grad_norm": 0.150390625, | |
| "learning_rate": 0.00010578207230932, | |
| "loss": 0.319, | |
| "mean_token_accuracy": 0.9112100295722485, | |
| "num_tokens": 29215055.0, | |
| "step": 920 | |
| }, | |
| { | |
| "entropy": 0.3142668510787189, | |
| "epoch": 1.5099472188388146, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.00010403108554306717, | |
| "loss": 0.3122, | |
| "mean_token_accuracy": 0.9117408633232117, | |
| "num_tokens": 29529393.0, | |
| "step": 930 | |
| }, | |
| { | |
| "entropy": 0.3135885909199715, | |
| "epoch": 1.5261875761266748, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00010227885988145563, | |
| "loss": 0.3075, | |
| "mean_token_accuracy": 0.9139442838728428, | |
| "num_tokens": 29851116.0, | |
| "step": 940 | |
| }, | |
| { | |
| "entropy": 0.3046269157901406, | |
| "epoch": 1.542427933414535, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 0.00010052593384549082, | |
| "loss": 0.3034, | |
| "mean_token_accuracy": 0.9146199978888034, | |
| "num_tokens": 30169222.0, | |
| "step": 950 | |
| }, | |
| { | |
| "entropy": 0.31176882088184354, | |
| "epoch": 1.5586682907023954, | |
| "grad_norm": 0.11767578125, | |
| "learning_rate": 9.877284617142802e-05, | |
| "loss": 0.3083, | |
| "mean_token_accuracy": 0.9138757094740868, | |
| "num_tokens": 30484117.0, | |
| "step": 960 | |
| }, | |
| { | |
| "entropy": 0.31525961998850105, | |
| "epoch": 1.5749086479902559, | |
| "grad_norm": 0.11328125, | |
| "learning_rate": 9.702013564519954e-05, | |
| "loss": 0.311, | |
| "mean_token_accuracy": 0.9124061703681946, | |
| "num_tokens": 30804341.0, | |
| "step": 970 | |
| }, | |
| { | |
| "entropy": 0.3192242424935102, | |
| "epoch": 1.591149005278116, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 9.526834093682685e-05, | |
| "loss": 0.3172, | |
| "mean_token_accuracy": 0.9116800054907799, | |
| "num_tokens": 31119505.0, | |
| "step": 980 | |
| }, | |
| { | |
| "entropy": 0.30036033764481546, | |
| "epoch": 1.6073893625659763, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 9.351800043486823e-05, | |
| "loss": 0.298, | |
| "mean_token_accuracy": 0.9167301289737224, | |
| "num_tokens": 31433788.0, | |
| "step": 990 | |
| }, | |
| { | |
| "entropy": 0.3045342108234763, | |
| "epoch": 1.6236297198538368, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 9.176965208095265e-05, | |
| "loss": 0.3011, | |
| "mean_token_accuracy": 0.915463775396347, | |
| "num_tokens": 31754135.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6236297198538368, | |
| "eval_entropy": 0.3258335756436559, | |
| "eval_loss": 0.3386901617050171, | |
| "eval_mean_token_accuracy": 0.9073542472515398, | |
| "eval_num_tokens": 31754135.0, | |
| "eval_runtime": 177.024, | |
| "eval_samples_per_second": 2.954, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1848, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.289529077619794e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |