| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993800371977681, | |
| "eval_steps": 200, | |
| "global_step": 806, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012399256044637321, | |
| "grad_norm": 0.6019122951437104, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.4222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006199628022318661, | |
| "grad_norm": 1.5495790328852515, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.471, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012399256044637322, | |
| "grad_norm": 0.9274998509045178, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.4844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018598884066955982, | |
| "grad_norm": 0.4319451186674129, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4111, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024798512089274645, | |
| "grad_norm": 0.5038186551413125, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.3561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030998140111593304, | |
| "grad_norm": 0.44167588919852313, | |
| "learning_rate": 6.17283950617284e-05, | |
| "loss": 0.347, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.037197768133911964, | |
| "grad_norm": 0.33451826071357504, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.3322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04339739615623062, | |
| "grad_norm": 0.34868148088717704, | |
| "learning_rate": 8.641975308641975e-05, | |
| "loss": 0.3399, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04959702417854929, | |
| "grad_norm": 0.3356513986019191, | |
| "learning_rate": 9.876543209876543e-05, | |
| "loss": 0.3602, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05579665220086795, | |
| "grad_norm": 0.37808175632129626, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.321, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06199628022318661, | |
| "grad_norm": 0.41761376999084465, | |
| "learning_rate": 0.0001234567901234568, | |
| "loss": 0.3504, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06819590824550527, | |
| "grad_norm": 0.35639408007374757, | |
| "learning_rate": 0.00013580246913580247, | |
| "loss": 0.3108, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07439553626782393, | |
| "grad_norm": 0.34681060518951073, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 0.305, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08059516429014259, | |
| "grad_norm": 0.29992433196050555, | |
| "learning_rate": 0.00016049382716049385, | |
| "loss": 0.3127, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08679479231246125, | |
| "grad_norm": 0.37053951666137375, | |
| "learning_rate": 0.0001728395061728395, | |
| "loss": 0.2985, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0929944203347799, | |
| "grad_norm": 0.3241692211944496, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 0.3187, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09919404835709858, | |
| "grad_norm": 0.3336770081253457, | |
| "learning_rate": 0.00019753086419753085, | |
| "loss": 0.3013, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10539367637941724, | |
| "grad_norm": 0.340347188617851, | |
| "learning_rate": 0.0001999849788616454, | |
| "loss": 0.3127, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1115933044017359, | |
| "grad_norm": 0.24966989402744666, | |
| "learning_rate": 0.00019992396322115213, | |
| "loss": 0.3132, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11779293242405456, | |
| "grad_norm": 0.36652120591883697, | |
| "learning_rate": 0.00019981604287632102, | |
| "loss": 0.2848, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.12399256044637322, | |
| "grad_norm": 0.37152546200115255, | |
| "learning_rate": 0.0001996612684853896, | |
| "loss": 0.3074, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13019218846869188, | |
| "grad_norm": 0.37937877581455376, | |
| "learning_rate": 0.00019945971270007043, | |
| "loss": 0.2966, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.13639181649101054, | |
| "grad_norm": 0.32819913975467047, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 0.2973, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1425914445133292, | |
| "grad_norm": 0.2497292935586131, | |
| "learning_rate": 0.00019891665730556725, | |
| "loss": 0.3072, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14879107253564786, | |
| "grad_norm": 0.3383083276284943, | |
| "learning_rate": 0.0001985754126087376, | |
| "loss": 0.2657, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15499070055796652, | |
| "grad_norm": 0.4050699278620848, | |
| "learning_rate": 0.00019818789622257196, | |
| "loss": 0.2882, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.16119032858028517, | |
| "grad_norm": 0.3123213984265953, | |
| "learning_rate": 0.0001977542900487977, | |
| "loss": 0.2765, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16738995660260383, | |
| "grad_norm": 0.33824727842613916, | |
| "learning_rate": 0.00019727479762387116, | |
| "loss": 0.3042, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1735895846249225, | |
| "grad_norm": 0.2424449276469738, | |
| "learning_rate": 0.00019674964402343684, | |
| "loss": 0.3264, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17978921264724115, | |
| "grad_norm": 0.3067543075934479, | |
| "learning_rate": 0.00019617907575667602, | |
| "loss": 0.2886, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1859888406695598, | |
| "grad_norm": 0.362577361435356, | |
| "learning_rate": 0.00019556336065059432, | |
| "loss": 0.3086, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1921884686918785, | |
| "grad_norm": 0.3238274733762567, | |
| "learning_rate": 0.00019490278772430256, | |
| "loss": 0.2963, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.19838809671419716, | |
| "grad_norm": 0.3597604834062663, | |
| "learning_rate": 0.00019419766705335026, | |
| "loss": 0.313, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.20458772473651582, | |
| "grad_norm": 0.27740278103597305, | |
| "learning_rate": 0.00019344832962417475, | |
| "loss": 0.3236, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.21078735275883448, | |
| "grad_norm": 0.31990061265265674, | |
| "learning_rate": 0.00019265512717873498, | |
| "loss": 0.2907, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21698698078115314, | |
| "grad_norm": 0.3521599467310119, | |
| "learning_rate": 0.00019181843204940232, | |
| "loss": 0.2933, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2231866088034718, | |
| "grad_norm": 0.32261509567312185, | |
| "learning_rate": 0.00019093863698418627, | |
| "loss": 0.2852, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22938623682579046, | |
| "grad_norm": 0.29712733472005987, | |
| "learning_rate": 0.00019001615496237712, | |
| "loss": 0.2868, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.23558586484810912, | |
| "grad_norm": 0.24705896150819331, | |
| "learning_rate": 0.00018905141900069178, | |
| "loss": 0.314, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.24178549287042778, | |
| "grad_norm": 0.31936683972288543, | |
| "learning_rate": 0.00018804488195001392, | |
| "loss": 0.2696, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.24798512089274644, | |
| "grad_norm": 0.32950608272624643, | |
| "learning_rate": 0.00018699701628282407, | |
| "loss": 0.2844, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24798512089274644, | |
| "eval_loss": 0.3114877939224243, | |
| "eval_runtime": 1124.0065, | |
| "eval_samples_per_second": 3.559, | |
| "eval_steps_per_second": 0.111, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2541847489150651, | |
| "grad_norm": 0.37057110121612846, | |
| "learning_rate": 0.0001859083138714191, | |
| "loss": 0.2852, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.26038437693738375, | |
| "grad_norm": 0.2869667980293731, | |
| "learning_rate": 0.0001847792857570255, | |
| "loss": 0.2905, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2665840049597024, | |
| "grad_norm": 0.24148834606008088, | |
| "learning_rate": 0.00018361046190991455, | |
| "loss": 0.2841, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2727836329820211, | |
| "grad_norm": 0.3669480816784026, | |
| "learning_rate": 0.0001824023909806322, | |
| "loss": 0.2745, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.27898326100433973, | |
| "grad_norm": 0.3054046475344961, | |
| "learning_rate": 0.00018115564004246023, | |
| "loss": 0.2803, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2851828890266584, | |
| "grad_norm": 0.3589718511823372, | |
| "learning_rate": 0.00017987079432522996, | |
| "loss": 0.2834, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.29138251704897705, | |
| "grad_norm": 0.32815022889743933, | |
| "learning_rate": 0.00017854845694061292, | |
| "loss": 0.2956, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2975821450712957, | |
| "grad_norm": 0.22811456346947673, | |
| "learning_rate": 0.00017718924859901793, | |
| "loss": 0.2992, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.30378177309361437, | |
| "grad_norm": 0.3261921325400897, | |
| "learning_rate": 0.00017579380731822712, | |
| "loss": 0.2696, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.30998140111593303, | |
| "grad_norm": 0.3265151909802919, | |
| "learning_rate": 0.00017436278812390786, | |
| "loss": 0.2762, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3161810291382517, | |
| "grad_norm": 0.25119517956050147, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 0.2758, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.32238065716057035, | |
| "grad_norm": 0.30203405562074537, | |
| "learning_rate": 0.00017139671928411072, | |
| "loss": 0.2888, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.328580285182889, | |
| "grad_norm": 0.231597052058556, | |
| "learning_rate": 0.00016986306192310084, | |
| "loss": 0.2994, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.33477991320520767, | |
| "grad_norm": 0.3462354390170321, | |
| "learning_rate": 0.00016829661056395474, | |
| "loss": 0.273, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.34097954122752633, | |
| "grad_norm": 0.3416446609085483, | |
| "learning_rate": 0.00016669810050514827, | |
| "loss": 0.2794, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.347179169249845, | |
| "grad_norm": 0.3004081195597297, | |
| "learning_rate": 0.00016506828209363796, | |
| "loss": 0.2785, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.35337879727216365, | |
| "grad_norm": 0.3372149956322208, | |
| "learning_rate": 0.00016340792037264527, | |
| "loss": 0.2924, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.3595784252944823, | |
| "grad_norm": 0.2773063250024901, | |
| "learning_rate": 0.00016171779472254206, | |
| "loss": 0.2824, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.36577805331680097, | |
| "grad_norm": 0.29747563137485017, | |
| "learning_rate": 0.0001599986984950065, | |
| "loss": 0.2787, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3719776813391196, | |
| "grad_norm": 0.3237809552896745, | |
| "learning_rate": 0.0001582514386406206, | |
| "loss": 0.2821, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37817730936143834, | |
| "grad_norm": 0.29633580280256444, | |
| "learning_rate": 0.00015647683533008455, | |
| "loss": 0.2777, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.384376937383757, | |
| "grad_norm": 0.3580023136614935, | |
| "learning_rate": 0.00015467572156922503, | |
| "loss": 0.2717, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.39057656540607566, | |
| "grad_norm": 0.2483260531032943, | |
| "learning_rate": 0.0001528489428079793, | |
| "loss": 0.3054, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3967761934283943, | |
| "grad_norm": 0.3058237506306256, | |
| "learning_rate": 0.00015099735654353747, | |
| "loss": 0.2724, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.402975821450713, | |
| "grad_norm": 0.3309948471867418, | |
| "learning_rate": 0.00014912183191782995, | |
| "loss": 0.2607, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.40917544947303164, | |
| "grad_norm": 0.3163723023278254, | |
| "learning_rate": 0.00014722324930954885, | |
| "loss": 0.2881, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4153750774953503, | |
| "grad_norm": 0.30350103196436556, | |
| "learning_rate": 0.0001453024999208946, | |
| "loss": 0.2817, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.42157470551766896, | |
| "grad_norm": 0.22626437910720568, | |
| "learning_rate": 0.00014336048535924223, | |
| "loss": 0.2838, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.4277743335399876, | |
| "grad_norm": 0.3445629260554824, | |
| "learning_rate": 0.00014139811721392324, | |
| "loss": 0.2552, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.4339739615623063, | |
| "grad_norm": 0.33697169212335193, | |
| "learning_rate": 0.00013941631662832199, | |
| "loss": 0.2738, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.44017358958462494, | |
| "grad_norm": 0.27110424764249635, | |
| "learning_rate": 0.00013741601386748728, | |
| "loss": 0.2837, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.4463732176069436, | |
| "grad_norm": 0.3176558105393564, | |
| "learning_rate": 0.00013539814788146235, | |
| "loss": 0.277, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.45257284562926225, | |
| "grad_norm": 0.21215927511567548, | |
| "learning_rate": 0.00013336366586453783, | |
| "loss": 0.2827, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.4587724736515809, | |
| "grad_norm": 0.31096775561405154, | |
| "learning_rate": 0.0001313135228106353, | |
| "loss": 0.2651, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4649721016738996, | |
| "grad_norm": 0.31585451791739527, | |
| "learning_rate": 0.0001292486810650289, | |
| "loss": 0.2773, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.47117172969621823, | |
| "grad_norm": 0.3080807025298427, | |
| "learning_rate": 0.00012717010987261715, | |
| "loss": 0.2873, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4773713577185369, | |
| "grad_norm": 0.3591626086115439, | |
| "learning_rate": 0.0001250787849229552, | |
| "loss": 0.2827, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.48357098574085555, | |
| "grad_norm": 0.25352609144718685, | |
| "learning_rate": 0.00012297568789226238, | |
| "loss": 0.2958, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4897706137631742, | |
| "grad_norm": 0.30645533387883167, | |
| "learning_rate": 0.00012086180598261956, | |
| "loss": 0.2597, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.49597024178549287, | |
| "grad_norm": 0.33773747309079233, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 0.2638, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.49597024178549287, | |
| "eval_loss": 0.29208001494407654, | |
| "eval_runtime": 1119.5912, | |
| "eval_samples_per_second": 3.573, | |
| "eval_steps_per_second": 0.112, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5021698698078115, | |
| "grad_norm": 0.3152505586487655, | |
| "learning_rate": 0.00011660566118135894, | |
| "loss": 0.2656, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.5083694978301302, | |
| "grad_norm": 0.29454612946664416, | |
| "learning_rate": 0.00011446539614097813, | |
| "loss": 0.27, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5145691258524488, | |
| "grad_norm": 0.1892793890960918, | |
| "learning_rate": 0.0001123183409863219, | |
| "loss": 0.2978, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.5207687538747675, | |
| "grad_norm": 0.3335006508167189, | |
| "learning_rate": 0.00011016550355358872, | |
| "loss": 0.2538, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5269683818970862, | |
| "grad_norm": 0.32122639513136675, | |
| "learning_rate": 0.00010800789439320128, | |
| "loss": 0.2778, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.5331680099194048, | |
| "grad_norm": 0.2771952164280048, | |
| "learning_rate": 0.00010584652629545011, | |
| "loss": 0.2634, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5393676379417235, | |
| "grad_norm": 0.34208078840367095, | |
| "learning_rate": 0.0001036824138150859, | |
| "loss": 0.2759, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.5455672659640421, | |
| "grad_norm": 0.21374327433641943, | |
| "learning_rate": 0.00010151657279508336, | |
| "loss": 0.2818, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5517668939863608, | |
| "grad_norm": 0.28462533877594465, | |
| "learning_rate": 9.935001988980061e-05, | |
| "loss": 0.2661, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.5579665220086795, | |
| "grad_norm": 0.3047348276188714, | |
| "learning_rate": 9.718377208775744e-05, | |
| "loss": 0.2677, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5641661500309981, | |
| "grad_norm": 0.30754878782389855, | |
| "learning_rate": 9.50188462342571e-05, | |
| "loss": 0.2614, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.5703657780533168, | |
| "grad_norm": 0.31116409658881644, | |
| "learning_rate": 9.285625855407484e-05, | |
| "loss": 0.2673, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5765654060756354, | |
| "grad_norm": 0.2651806274866606, | |
| "learning_rate": 9.069702417443821e-05, | |
| "loss": 0.2869, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5827650340979541, | |
| "grad_norm": 0.2909752165016893, | |
| "learning_rate": 8.854215664852206e-05, | |
| "loss": 0.2669, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5889646621202728, | |
| "grad_norm": 0.30706363315844515, | |
| "learning_rate": 8.63926674796829e-05, | |
| "loss": 0.2674, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5951642901425914, | |
| "grad_norm": 0.30444202963242784, | |
| "learning_rate": 8.424956564665508e-05, | |
| "loss": 0.2802, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6013639181649101, | |
| "grad_norm": 0.2789382860436405, | |
| "learning_rate": 8.211385712993218e-05, | |
| "loss": 0.2545, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.6075635461872287, | |
| "grad_norm": 0.23185325685334424, | |
| "learning_rate": 7.998654443955586e-05, | |
| "loss": 0.266, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6137631742095474, | |
| "grad_norm": 0.3567624100649805, | |
| "learning_rate": 7.786862614453355e-05, | |
| "loss": 0.2665, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.6199628022318661, | |
| "grad_norm": 0.31757337819796233, | |
| "learning_rate": 7.576109640410633e-05, | |
| "loss": 0.2692, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6261624302541847, | |
| "grad_norm": 0.26049216875661646, | |
| "learning_rate": 7.366494450108659e-05, | |
| "loss": 0.253, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.6323620582765034, | |
| "grad_norm": 0.3279613920140163, | |
| "learning_rate": 7.158115437748468e-05, | |
| "loss": 0.2664, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.638561686298822, | |
| "grad_norm": 0.24958219949066954, | |
| "learning_rate": 6.951070417264277e-05, | |
| "loss": 0.282, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.6447613143211407, | |
| "grad_norm": 0.3076230934858842, | |
| "learning_rate": 6.745456576409227e-05, | |
| "loss": 0.2541, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6509609423434594, | |
| "grad_norm": 0.3039043398796431, | |
| "learning_rate": 6.541370431135072e-05, | |
| "loss": 0.2648, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.657160570365778, | |
| "grad_norm": 0.2823892989212078, | |
| "learning_rate": 6.338907780287197e-05, | |
| "loss": 0.2628, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6633601983880967, | |
| "grad_norm": 0.336100443174608, | |
| "learning_rate": 6.138163660636284e-05, | |
| "loss": 0.2609, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.6695598264104153, | |
| "grad_norm": 0.22183756693967047, | |
| "learning_rate": 5.9392323022676454e-05, | |
| "loss": 0.2679, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.675759454432734, | |
| "grad_norm": 0.30501277104459634, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 0.2551, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6819590824550527, | |
| "grad_norm": 0.35227300737647005, | |
| "learning_rate": 5.547180491299279e-05, | |
| "loss": 0.2715, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6881587104773713, | |
| "grad_norm": 0.2645763624948684, | |
| "learning_rate": 5.35424406937333e-05, | |
| "loss": 0.2633, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.69435833849969, | |
| "grad_norm": 0.2707425078158492, | |
| "learning_rate": 5.163488383692499e-05, | |
| "loss": 0.2677, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7005579665220086, | |
| "grad_norm": 0.24608132828527818, | |
| "learning_rate": 4.975002975731613e-05, | |
| "loss": 0.2763, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.7067575945443273, | |
| "grad_norm": 0.2726783082526773, | |
| "learning_rate": 4.78887632128814e-05, | |
| "loss": 0.2428, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.712957222566646, | |
| "grad_norm": 0.2981132504685635, | |
| "learning_rate": 4.6051957889513e-05, | |
| "loss": 0.2608, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.7191568505889646, | |
| "grad_norm": 0.28491523081281545, | |
| "learning_rate": 4.4240475990909106e-05, | |
| "loss": 0.2569, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7253564786112833, | |
| "grad_norm": 0.3291243871750603, | |
| "learning_rate": 4.24551678338518e-05, | |
| "loss": 0.2612, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.7315561066336019, | |
| "grad_norm": 0.2259584584201018, | |
| "learning_rate": 4.069687144906532e-05, | |
| "loss": 0.2696, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7377557346559206, | |
| "grad_norm": 0.330497624658356, | |
| "learning_rate": 3.8966412187840804e-05, | |
| "loss": 0.2478, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.7439553626782393, | |
| "grad_norm": 0.2741703824563164, | |
| "learning_rate": 3.726460233461339e-05, | |
| "loss": 0.2596, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7439553626782393, | |
| "eval_loss": 0.2790033519268036, | |
| "eval_runtime": 1119.6634, | |
| "eval_samples_per_second": 3.573, | |
| "eval_steps_per_second": 0.112, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.750154990700558, | |
| "grad_norm": 0.25878146862151746, | |
| "learning_rate": 3.5592240725672476e-05, | |
| "loss": 0.2631, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.7563546187228767, | |
| "grad_norm": 0.30340990736911533, | |
| "learning_rate": 3.395011237418494e-05, | |
| "loss": 0.2649, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7625542467451953, | |
| "grad_norm": 0.21196981539625306, | |
| "learning_rate": 3.2338988101706726e-05, | |
| "loss": 0.2519, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.768753874767514, | |
| "grad_norm": 0.2881373960219632, | |
| "learning_rate": 3.075962417635634e-05, | |
| "loss": 0.2371, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7749535027898327, | |
| "grad_norm": 0.31620268309069777, | |
| "learning_rate": 2.9212761957819347e-05, | |
| "loss": 0.2726, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7811531308121513, | |
| "grad_norm": 0.2675293914015534, | |
| "learning_rate": 2.7699127549351456e-05, | |
| "loss": 0.2723, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.78735275883447, | |
| "grad_norm": 0.3208257587309821, | |
| "learning_rate": 2.6219431456942535e-05, | |
| "loss": 0.2662, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.7935523868567886, | |
| "grad_norm": 0.20931592628778878, | |
| "learning_rate": 2.4774368255802483e-05, | |
| "loss": 0.2662, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7997520148791073, | |
| "grad_norm": 0.2722392147736918, | |
| "learning_rate": 2.3364616264324722e-05, | |
| "loss": 0.2528, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.805951642901426, | |
| "grad_norm": 0.29854156869280446, | |
| "learning_rate": 2.199083722568095e-05, | |
| "loss": 0.2612, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8121512709237446, | |
| "grad_norm": 0.2760187147243271, | |
| "learning_rate": 2.065367599719621e-05, | |
| "loss": 0.2646, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.8183508989460633, | |
| "grad_norm": 0.29187099026880386, | |
| "learning_rate": 1.93537602476504e-05, | |
| "loss": 0.2574, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8245505269683819, | |
| "grad_norm": 0.21386029056799546, | |
| "learning_rate": 1.809170016264794e-05, | |
| "loss": 0.2563, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.8307501549907006, | |
| "grad_norm": 0.2823252915248677, | |
| "learning_rate": 1.686808815819435e-05, | |
| "loss": 0.2669, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.8369497830130193, | |
| "grad_norm": 0.33535005943488133, | |
| "learning_rate": 1.568349860261369e-05, | |
| "loss": 0.2507, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.8431494110353379, | |
| "grad_norm": 0.29068903551261105, | |
| "learning_rate": 1.4538487546937952e-05, | |
| "loss": 0.2679, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8493490390576566, | |
| "grad_norm": 0.31428561712386854, | |
| "learning_rate": 1.3433592463894373e-05, | |
| "loss": 0.256, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.8555486670799752, | |
| "grad_norm": 0.2492283063735335, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 0.2701, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8617482951022939, | |
| "grad_norm": 0.29516035417057684, | |
| "learning_rate": 1.1346205710177304e-05, | |
| "loss": 0.2317, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.8679479231246126, | |
| "grad_norm": 0.34660496611894304, | |
| "learning_rate": 1.0364693867118424e-05, | |
| "loss": 0.2581, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8741475511469312, | |
| "grad_norm": 0.27935452297059005, | |
| "learning_rate": 9.425257191985859e-06, | |
| "loss": 0.2501, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.8803471791692499, | |
| "grad_norm": 0.2975961434950699, | |
| "learning_rate": 8.528336660077974e-06, | |
| "loss": 0.2598, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.8865468071915685, | |
| "grad_norm": 0.21801979336484165, | |
| "learning_rate": 7.674353289446945e-06, | |
| "loss": 0.2662, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.8927464352138872, | |
| "grad_norm": 0.34419068158586147, | |
| "learning_rate": 6.863707943271325e-06, | |
| "loss": 0.235, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8989460632362059, | |
| "grad_norm": 0.3428004067461644, | |
| "learning_rate": 6.096781141689223e-06, | |
| "loss": 0.2548, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.9051456912585245, | |
| "grad_norm": 0.25288813676576166, | |
| "learning_rate": 5.373932883180655e-06, | |
| "loss": 0.248, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.9113453192808432, | |
| "grad_norm": 0.279501011714134, | |
| "learning_rate": 4.695502475582814e-06, | |
| "loss": 0.2486, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.9175449473031618, | |
| "grad_norm": 0.2244165751957654, | |
| "learning_rate": 4.0618083768177e-06, | |
| "loss": 0.2594, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9237445753254805, | |
| "grad_norm": 0.30028321537895275, | |
| "learning_rate": 3.4731480454065825e-06, | |
| "loss": 0.243, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.9299442033477991, | |
| "grad_norm": 0.34186025440033796, | |
| "learning_rate": 2.92979780084196e-06, | |
| "loss": 0.2454, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9361438313701178, | |
| "grad_norm": 0.27131508037063784, | |
| "learning_rate": 2.4320126938819023e-06, | |
| "loss": 0.2464, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.9423434593924365, | |
| "grad_norm": 0.30864982789113204, | |
| "learning_rate": 1.980026386828371e-06, | |
| "loss": 0.2577, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9485430874147551, | |
| "grad_norm": 0.22799699963033782, | |
| "learning_rate": 1.5740510438451371e-06, | |
| "loss": 0.2658, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.9547427154370738, | |
| "grad_norm": 0.2796812629005932, | |
| "learning_rate": 1.214277231367078e-06, | |
| "loss": 0.2615, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.9609423434593924, | |
| "grad_norm": 0.2906770373909308, | |
| "learning_rate": 9.008738286475749e-07, | |
| "loss": 0.2557, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9671419714817111, | |
| "grad_norm": 0.30664325433457473, | |
| "learning_rate": 6.339879484858924e-07, | |
| "loss": 0.2485, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9733415995040298, | |
| "grad_norm": 0.3437865129781069, | |
| "learning_rate": 4.1374486817183924e-07, | |
| "loss": 0.2514, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.9795412275263484, | |
| "grad_norm": 0.2189635610441498, | |
| "learning_rate": 2.402479706801741e-07, | |
| "loss": 0.2845, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9857408555486671, | |
| "grad_norm": 0.30929816396563364, | |
| "learning_rate": 1.1357869614212479e-07, | |
| "loss": 0.2564, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.9919404835709857, | |
| "grad_norm": 0.31984749573339155, | |
| "learning_rate": 3.379650361716724e-08, | |
| "loss": 0.2458, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9919404835709857, | |
| "eval_loss": 0.2757934629917145, | |
| "eval_runtime": 1122.4404, | |
| "eval_samples_per_second": 3.564, | |
| "eval_steps_per_second": 0.111, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9981401115933044, | |
| "grad_norm": 0.28178798746795625, | |
| "learning_rate": 9.388431826629073e-10, | |
| "loss": 0.2537, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.9993800371977681, | |
| "step": 806, | |
| "total_flos": 2.076935220048691e+16, | |
| "train_loss": 0.28037568409153013, | |
| "train_runtime": 38684.7769, | |
| "train_samples_per_second": 1.334, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 806, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.076935220048691e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |