{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.901960784313726, "global_step": 170000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 1.0000000000000002e-06, "loss": 0.6866, "step": 500 }, { "epoch": 0.03, "learning_rate": 2.0000000000000003e-06, "loss": 0.513, "step": 1000 }, { "epoch": 0.04, "learning_rate": 3e-06, "loss": 0.3957, "step": 1500 }, { "epoch": 0.06, "learning_rate": 4.000000000000001e-06, "loss": 0.4037, "step": 2000 }, { "epoch": 0.07, "learning_rate": 5e-06, "loss": 0.377, "step": 2500 }, { "epoch": 0.09, "learning_rate": 6e-06, "loss": 0.3838, "step": 3000 }, { "epoch": 0.1, "learning_rate": 7e-06, "loss": 0.3804, "step": 3500 }, { "epoch": 0.12, "learning_rate": 8.000000000000001e-06, "loss": 0.3842, "step": 4000 }, { "epoch": 0.13, "learning_rate": 9e-06, "loss": 0.368, "step": 4500 }, { "epoch": 0.14, "learning_rate": 1e-05, "loss": 0.3753, "step": 5000 }, { "epoch": 0.16, "learning_rate": 1.1000000000000001e-05, "loss": 0.3637, "step": 5500 }, { "epoch": 0.17, "learning_rate": 1.2e-05, "loss": 0.3884, "step": 6000 }, { "epoch": 0.19, "learning_rate": 1.3000000000000001e-05, "loss": 0.3814, "step": 6500 }, { "epoch": 0.2, "learning_rate": 1.4e-05, "loss": 0.3741, "step": 7000 }, { "epoch": 0.22, "learning_rate": 1.5000000000000002e-05, "loss": 0.3502, "step": 7500 }, { "epoch": 0.23, "learning_rate": 1.6000000000000003e-05, "loss": 0.3667, "step": 8000 }, { "epoch": 0.25, "learning_rate": 1.7e-05, "loss": 0.37, "step": 8500 }, { "epoch": 0.26, "learning_rate": 1.8e-05, "loss": 0.3754, "step": 9000 }, { "epoch": 0.27, "learning_rate": 1.9e-05, "loss": 0.3505, "step": 9500 }, { "epoch": 0.29, "learning_rate": 2e-05, "loss": 0.3663, "step": 10000 }, { "epoch": 0.3, "learning_rate": 1.9938800489596085e-05, "loss": 0.3551, "step": 10500 }, { "epoch": 0.32, "learning_rate": 1.987760097919217e-05, "loss": 0.3738, "step": 11000 }, { "epoch": 0.33, "learning_rate": 1.9816401468788252e-05, "loss": 0.3595, "step": 11500 }, { "epoch": 0.35, "learning_rate": 1.9755201958384335e-05, "loss": 0.3704, "step": 12000 }, { "epoch": 0.36, "learning_rate": 1.969400244798042e-05, "loss": 0.3719, "step": 12500 }, { "epoch": 0.37, "learning_rate": 1.9632802937576502e-05, "loss": 0.3682, "step": 13000 }, { "epoch": 0.39, "learning_rate": 1.9571603427172585e-05, "loss": 0.3772, "step": 13500 }, { "epoch": 0.4, "learning_rate": 1.951040391676867e-05, "loss": 0.3707, "step": 14000 }, { "epoch": 0.42, "learning_rate": 1.944920440636475e-05, "loss": 0.3637, "step": 14500 }, { "epoch": 0.43, "learning_rate": 1.9388004895960835e-05, "loss": 0.3543, "step": 15000 }, { "epoch": 0.45, "learning_rate": 1.932680538555692e-05, "loss": 0.3656, "step": 15500 }, { "epoch": 0.46, "learning_rate": 1.9265605875153e-05, "loss": 0.3551, "step": 16000 }, { "epoch": 0.48, "learning_rate": 1.9204406364749086e-05, "loss": 0.3686, "step": 16500 }, { "epoch": 0.49, "learning_rate": 1.9143206854345166e-05, "loss": 0.3533, "step": 17000 }, { "epoch": 0.5, "learning_rate": 1.908200734394125e-05, "loss": 0.3564, "step": 17500 }, { "epoch": 0.52, "learning_rate": 1.9020807833537332e-05, "loss": 0.3597, "step": 18000 }, { "epoch": 0.53, "learning_rate": 1.8959608323133416e-05, "loss": 0.3608, "step": 18500 }, { "epoch": 0.55, "learning_rate": 1.88984088127295e-05, "loss": 0.3603, "step": 19000 }, { "epoch": 0.56, "learning_rate": 1.8837209302325582e-05, "loss": 0.3622, "step": 19500 }, { "epoch": 0.58, "learning_rate": 1.8776009791921666e-05, "loss": 0.3642, "step": 20000 }, { "epoch": 0.59, "learning_rate": 1.871481028151775e-05, "loss": 0.3719, "step": 20500 }, { "epoch": 0.61, "learning_rate": 1.8653610771113833e-05, "loss": 0.3595, "step": 21000 }, { "epoch": 0.62, "learning_rate": 1.8592411260709916e-05, "loss": 0.3693, "step": 21500 }, { "epoch": 0.63, "learning_rate": 1.8531211750306e-05, "loss": 0.3625, "step": 22000 }, { "epoch": 0.65, "learning_rate": 1.8470012239902083e-05, "loss": 0.3513, "step": 22500 }, { "epoch": 0.66, "learning_rate": 1.8408812729498166e-05, "loss": 0.3613, "step": 23000 }, { "epoch": 0.68, "learning_rate": 1.834761321909425e-05, "loss": 0.3583, "step": 23500 }, { "epoch": 0.69, "learning_rate": 1.8286413708690333e-05, "loss": 0.3645, "step": 24000 }, { "epoch": 0.71, "learning_rate": 1.8225214198286416e-05, "loss": 0.3575, "step": 24500 }, { "epoch": 0.72, "learning_rate": 1.81640146878825e-05, "loss": 0.3646, "step": 25000 }, { "epoch": 0.74, "learning_rate": 1.810281517747858e-05, "loss": 0.3497, "step": 25500 }, { "epoch": 0.75, "learning_rate": 1.8041615667074666e-05, "loss": 0.357, "step": 26000 }, { "epoch": 0.76, "learning_rate": 1.798041615667075e-05, "loss": 0.3658, "step": 26500 }, { "epoch": 0.78, "learning_rate": 1.791921664626683e-05, "loss": 0.3442, "step": 27000 }, { "epoch": 0.79, "learning_rate": 1.7858017135862916e-05, "loss": 0.3582, "step": 27500 }, { "epoch": 0.81, "learning_rate": 1.7796817625458996e-05, "loss": 0.3679, "step": 28000 }, { "epoch": 0.82, "learning_rate": 1.773561811505508e-05, "loss": 0.3575, "step": 28500 }, { "epoch": 0.84, "learning_rate": 1.7674418604651163e-05, "loss": 0.3492, "step": 29000 }, { "epoch": 0.85, "learning_rate": 1.7613219094247247e-05, "loss": 0.3463, "step": 29500 }, { "epoch": 0.87, "learning_rate": 1.755201958384333e-05, "loss": 0.3457, "step": 30000 }, { "epoch": 0.88, "learning_rate": 1.7490820073439413e-05, "loss": 0.3631, "step": 30500 }, { "epoch": 0.89, "learning_rate": 1.7429620563035497e-05, "loss": 0.3587, "step": 31000 }, { "epoch": 0.91, "learning_rate": 1.736842105263158e-05, "loss": 0.3577, "step": 31500 }, { "epoch": 0.92, "learning_rate": 1.7307221542227663e-05, "loss": 0.3476, "step": 32000 }, { "epoch": 0.94, "learning_rate": 1.7246022031823747e-05, "loss": 0.357, "step": 32500 }, { "epoch": 0.95, "learning_rate": 1.718482252141983e-05, "loss": 0.3657, "step": 33000 }, { "epoch": 0.97, "learning_rate": 1.7123623011015914e-05, "loss": 0.3622, "step": 33500 }, { "epoch": 0.98, "learning_rate": 1.7062423500611997e-05, "loss": 0.3585, "step": 34000 }, { "epoch": 0.99, "learning_rate": 1.700122399020808e-05, "loss": 0.3441, "step": 34500 }, { "epoch": 1.0, "eval_accuracy": 0.8873362445414847, "eval_loss": 0.3056604862213135, "eval_runtime": 105.089, "eval_samples_per_second": 65.373, "eval_steps_per_second": 8.174, "step": 34680 }, { "epoch": 1.01, "learning_rate": 1.6940024479804164e-05, "loss": 0.3411, "step": 35000 }, { "epoch": 1.02, "learning_rate": 1.6878824969400247e-05, "loss": 0.3405, "step": 35500 }, { "epoch": 1.04, "learning_rate": 1.681762545899633e-05, "loss": 0.3493, "step": 36000 }, { "epoch": 1.05, "learning_rate": 1.675642594859241e-05, "loss": 0.3418, "step": 36500 }, { "epoch": 1.07, "learning_rate": 1.6695226438188497e-05, "loss": 0.3631, "step": 37000 }, { "epoch": 1.08, "learning_rate": 1.663402692778458e-05, "loss": 0.3478, "step": 37500 }, { "epoch": 1.1, "learning_rate": 1.657282741738066e-05, "loss": 0.3571, "step": 38000 }, { "epoch": 1.11, "learning_rate": 1.6511627906976747e-05, "loss": 0.3454, "step": 38500 }, { "epoch": 1.12, "learning_rate": 1.6450428396572827e-05, "loss": 0.3325, "step": 39000 }, { "epoch": 1.14, "learning_rate": 1.6389228886168914e-05, "loss": 0.3618, "step": 39500 }, { "epoch": 1.15, "learning_rate": 1.6328029375764994e-05, "loss": 0.3607, "step": 40000 }, { "epoch": 1.17, "learning_rate": 1.6266829865361078e-05, "loss": 0.3562, "step": 40500 }, { "epoch": 1.18, "learning_rate": 1.620563035495716e-05, "loss": 0.3476, "step": 41000 }, { "epoch": 1.2, "learning_rate": 1.6144430844553244e-05, "loss": 0.3554, "step": 41500 }, { "epoch": 1.21, "learning_rate": 1.6083231334149328e-05, "loss": 0.3462, "step": 42000 }, { "epoch": 1.23, "learning_rate": 1.602203182374541e-05, "loss": 0.3716, "step": 42500 }, { "epoch": 1.24, "learning_rate": 1.5960832313341494e-05, "loss": 0.3578, "step": 43000 }, { "epoch": 1.25, "learning_rate": 1.5899632802937578e-05, "loss": 0.3642, "step": 43500 }, { "epoch": 1.27, "learning_rate": 1.583843329253366e-05, "loss": 0.3545, "step": 44000 }, { "epoch": 1.28, "learning_rate": 1.5777233782129745e-05, "loss": 0.346, "step": 44500 }, { "epoch": 1.3, "learning_rate": 1.5716034271725828e-05, "loss": 0.3498, "step": 45000 }, { "epoch": 1.31, "learning_rate": 1.565483476132191e-05, "loss": 0.3523, "step": 45500 }, { "epoch": 1.33, "learning_rate": 1.5593635250917995e-05, "loss": 0.3527, "step": 46000 }, { "epoch": 1.34, "learning_rate": 1.5532435740514078e-05, "loss": 0.3466, "step": 46500 }, { "epoch": 1.36, "learning_rate": 1.547123623011016e-05, "loss": 0.3584, "step": 47000 }, { "epoch": 1.37, "learning_rate": 1.541003671970624e-05, "loss": 0.3737, "step": 47500 }, { "epoch": 1.38, "learning_rate": 1.5348837209302328e-05, "loss": 0.3542, "step": 48000 }, { "epoch": 1.4, "learning_rate": 1.528763769889841e-05, "loss": 0.362, "step": 48500 }, { "epoch": 1.41, "learning_rate": 1.5226438188494492e-05, "loss": 0.3588, "step": 49000 }, { "epoch": 1.43, "learning_rate": 1.5165238678090577e-05, "loss": 0.3471, "step": 49500 }, { "epoch": 1.44, "learning_rate": 1.510403916768666e-05, "loss": 0.3514, "step": 50000 }, { "epoch": 1.46, "learning_rate": 1.5042839657282743e-05, "loss": 0.3488, "step": 50500 }, { "epoch": 1.47, "learning_rate": 1.4981640146878827e-05, "loss": 0.352, "step": 51000 }, { "epoch": 1.49, "learning_rate": 1.4920440636474908e-05, "loss": 0.3617, "step": 51500 }, { "epoch": 1.5, "learning_rate": 1.4859241126070994e-05, "loss": 0.3546, "step": 52000 }, { "epoch": 1.51, "learning_rate": 1.4798041615667075e-05, "loss": 0.3501, "step": 52500 }, { "epoch": 1.53, "learning_rate": 1.4736842105263159e-05, "loss": 0.3508, "step": 53000 }, { "epoch": 1.54, "learning_rate": 1.4675642594859244e-05, "loss": 0.358, "step": 53500 }, { "epoch": 1.56, "learning_rate": 1.4614443084455325e-05, "loss": 0.3474, "step": 54000 }, { "epoch": 1.57, "learning_rate": 1.4553243574051407e-05, "loss": 0.3487, "step": 54500 }, { "epoch": 1.59, "learning_rate": 1.4492044063647492e-05, "loss": 0.3532, "step": 55000 }, { "epoch": 1.6, "learning_rate": 1.4430844553243575e-05, "loss": 0.3429, "step": 55500 }, { "epoch": 1.61, "learning_rate": 1.4369645042839659e-05, "loss": 0.3509, "step": 56000 }, { "epoch": 1.63, "learning_rate": 1.4308445532435742e-05, "loss": 0.3478, "step": 56500 }, { "epoch": 1.64, "learning_rate": 1.4247246022031824e-05, "loss": 0.3505, "step": 57000 }, { "epoch": 1.66, "learning_rate": 1.4186046511627909e-05, "loss": 0.35, "step": 57500 }, { "epoch": 1.67, "learning_rate": 1.412484700122399e-05, "loss": 0.3605, "step": 58000 }, { "epoch": 1.69, "learning_rate": 1.4063647490820074e-05, "loss": 0.3541, "step": 58500 }, { "epoch": 1.7, "learning_rate": 1.4002447980416159e-05, "loss": 0.3576, "step": 59000 }, { "epoch": 1.72, "learning_rate": 1.394124847001224e-05, "loss": 0.3477, "step": 59500 }, { "epoch": 1.73, "learning_rate": 1.3880048959608322e-05, "loss": 0.347, "step": 60000 }, { "epoch": 1.74, "learning_rate": 1.3818849449204408e-05, "loss": 0.344, "step": 60500 }, { "epoch": 1.76, "learning_rate": 1.3757649938800491e-05, "loss": 0.3617, "step": 61000 }, { "epoch": 1.77, "learning_rate": 1.3696450428396574e-05, "loss": 0.3447, "step": 61500 }, { "epoch": 1.79, "learning_rate": 1.3635250917992658e-05, "loss": 0.3481, "step": 62000 }, { "epoch": 1.8, "learning_rate": 1.357405140758874e-05, "loss": 0.3522, "step": 62500 }, { "epoch": 1.82, "learning_rate": 1.3512851897184824e-05, "loss": 0.3509, "step": 63000 }, { "epoch": 1.83, "learning_rate": 1.3451652386780906e-05, "loss": 0.3529, "step": 63500 }, { "epoch": 1.85, "learning_rate": 1.339045287637699e-05, "loss": 0.3502, "step": 64000 }, { "epoch": 1.86, "learning_rate": 1.3329253365973075e-05, "loss": 0.3455, "step": 64500 }, { "epoch": 1.87, "learning_rate": 1.3268053855569156e-05, "loss": 0.3567, "step": 65000 }, { "epoch": 1.89, "learning_rate": 1.3206854345165238e-05, "loss": 0.3316, "step": 65500 }, { "epoch": 1.9, "learning_rate": 1.3145654834761323e-05, "loss": 0.3535, "step": 66000 }, { "epoch": 1.92, "learning_rate": 1.3084455324357406e-05, "loss": 0.37, "step": 66500 }, { "epoch": 1.93, "learning_rate": 1.302325581395349e-05, "loss": 0.3531, "step": 67000 }, { "epoch": 1.95, "learning_rate": 1.2962056303549573e-05, "loss": 0.3728, "step": 67500 }, { "epoch": 1.96, "learning_rate": 1.2900856793145655e-05, "loss": 0.3517, "step": 68000 }, { "epoch": 1.98, "learning_rate": 1.283965728274174e-05, "loss": 0.3531, "step": 68500 }, { "epoch": 1.99, "learning_rate": 1.2778457772337822e-05, "loss": 0.3645, "step": 69000 }, { "epoch": 2.0, "eval_accuracy": 0.8902474526928675, "eval_loss": 0.28919732570648193, "eval_runtime": 105.8357, "eval_samples_per_second": 64.912, "eval_steps_per_second": 8.116, "step": 69360 }, { "epoch": 2.0, "learning_rate": 1.2717258261933905e-05, "loss": 0.3729, "step": 69500 }, { "epoch": 2.02, "learning_rate": 1.265605875152999e-05, "loss": 0.3533, "step": 70000 }, { "epoch": 2.03, "learning_rate": 1.2594859241126072e-05, "loss": 0.3419, "step": 70500 }, { "epoch": 2.05, "learning_rate": 1.2533659730722153e-05, "loss": 0.3424, "step": 71000 }, { "epoch": 2.06, "learning_rate": 1.2472460220318238e-05, "loss": 0.3411, "step": 71500 }, { "epoch": 2.08, "learning_rate": 1.2411260709914322e-05, "loss": 0.3358, "step": 72000 }, { "epoch": 2.09, "learning_rate": 1.2350061199510405e-05, "loss": 0.3383, "step": 72500 }, { "epoch": 2.1, "learning_rate": 1.2288861689106489e-05, "loss": 0.3483, "step": 73000 }, { "epoch": 2.12, "learning_rate": 1.222766217870257e-05, "loss": 0.3569, "step": 73500 }, { "epoch": 2.13, "learning_rate": 1.2166462668298655e-05, "loss": 0.358, "step": 74000 }, { "epoch": 2.15, "learning_rate": 1.2105263157894737e-05, "loss": 0.3548, "step": 74500 }, { "epoch": 2.16, "learning_rate": 1.204406364749082e-05, "loss": 0.3455, "step": 75000 }, { "epoch": 2.18, "learning_rate": 1.1982864137086905e-05, "loss": 0.3434, "step": 75500 }, { "epoch": 2.19, "learning_rate": 1.1921664626682987e-05, "loss": 0.3542, "step": 76000 }, { "epoch": 2.21, "learning_rate": 1.1860465116279072e-05, "loss": 0.3472, "step": 76500 }, { "epoch": 2.22, "learning_rate": 1.1799265605875154e-05, "loss": 0.3349, "step": 77000 }, { "epoch": 2.23, "learning_rate": 1.1738066095471237e-05, "loss": 0.343, "step": 77500 }, { "epoch": 2.25, "learning_rate": 1.167686658506732e-05, "loss": 0.3399, "step": 78000 }, { "epoch": 2.26, "learning_rate": 1.1615667074663404e-05, "loss": 0.3455, "step": 78500 }, { "epoch": 2.28, "learning_rate": 1.1554467564259486e-05, "loss": 0.3514, "step": 79000 }, { "epoch": 2.29, "learning_rate": 1.149326805385557e-05, "loss": 0.3436, "step": 79500 }, { "epoch": 2.31, "learning_rate": 1.1432068543451652e-05, "loss": 0.3484, "step": 80000 }, { "epoch": 2.32, "learning_rate": 1.1370869033047736e-05, "loss": 0.3398, "step": 80500 }, { "epoch": 2.34, "learning_rate": 1.1309669522643821e-05, "loss": 0.3455, "step": 81000 }, { "epoch": 2.35, "learning_rate": 1.1248470012239903e-05, "loss": 0.3629, "step": 81500 }, { "epoch": 2.36, "learning_rate": 1.1187270501835988e-05, "loss": 0.3481, "step": 82000 }, { "epoch": 2.38, "learning_rate": 1.112607099143207e-05, "loss": 0.3483, "step": 82500 }, { "epoch": 2.39, "learning_rate": 1.1064871481028153e-05, "loss": 0.3478, "step": 83000 }, { "epoch": 2.41, "learning_rate": 1.1003671970624236e-05, "loss": 0.3357, "step": 83500 }, { "epoch": 2.42, "learning_rate": 1.094247246022032e-05, "loss": 0.3733, "step": 84000 }, { "epoch": 2.44, "learning_rate": 1.0881272949816401e-05, "loss": 0.346, "step": 84500 }, { "epoch": 2.45, "learning_rate": 1.0820073439412486e-05, "loss": 0.3526, "step": 85000 }, { "epoch": 2.47, "learning_rate": 1.0758873929008568e-05, "loss": 0.3383, "step": 85500 }, { "epoch": 2.48, "learning_rate": 1.0697674418604651e-05, "loss": 0.3447, "step": 86000 }, { "epoch": 2.49, "learning_rate": 1.0636474908200736e-05, "loss": 0.3582, "step": 86500 }, { "epoch": 2.51, "learning_rate": 1.0575275397796818e-05, "loss": 0.3549, "step": 87000 }, { "epoch": 2.52, "learning_rate": 1.0514075887392903e-05, "loss": 0.376, "step": 87500 }, { "epoch": 2.54, "learning_rate": 1.0452876376988985e-05, "loss": 0.3545, "step": 88000 }, { "epoch": 2.55, "learning_rate": 1.0391676866585068e-05, "loss": 0.3642, "step": 88500 }, { "epoch": 2.57, "learning_rate": 1.0330477356181152e-05, "loss": 0.3634, "step": 89000 }, { "epoch": 2.58, "learning_rate": 1.0269277845777235e-05, "loss": 0.3633, "step": 89500 }, { "epoch": 2.6, "learning_rate": 1.0208078335373317e-05, "loss": 0.3502, "step": 90000 }, { "epoch": 2.61, "learning_rate": 1.0146878824969402e-05, "loss": 0.3485, "step": 90500 }, { "epoch": 2.62, "learning_rate": 1.0085679314565483e-05, "loss": 0.3527, "step": 91000 }, { "epoch": 2.64, "learning_rate": 1.0024479804161567e-05, "loss": 0.3552, "step": 91500 }, { "epoch": 2.65, "learning_rate": 9.963280293757652e-06, "loss": 0.3445, "step": 92000 }, { "epoch": 2.67, "learning_rate": 9.902080783353734e-06, "loss": 0.3601, "step": 92500 }, { "epoch": 2.68, "learning_rate": 9.840881272949817e-06, "loss": 0.3644, "step": 93000 }, { "epoch": 2.7, "learning_rate": 9.7796817625459e-06, "loss": 0.355, "step": 93500 }, { "epoch": 2.71, "learning_rate": 9.718482252141984e-06, "loss": 0.3531, "step": 94000 }, { "epoch": 2.72, "learning_rate": 9.657282741738067e-06, "loss": 0.3382, "step": 94500 }, { "epoch": 2.74, "learning_rate": 9.59608323133415e-06, "loss": 0.3503, "step": 95000 }, { "epoch": 2.75, "learning_rate": 9.534883720930234e-06, "loss": 0.3471, "step": 95500 }, { "epoch": 2.77, "learning_rate": 9.473684210526315e-06, "loss": 0.3496, "step": 96000 }, { "epoch": 2.78, "learning_rate": 9.412484700122399e-06, "loss": 0.3402, "step": 96500 }, { "epoch": 2.8, "learning_rate": 9.351285189718482e-06, "loss": 0.355, "step": 97000 }, { "epoch": 2.81, "learning_rate": 9.290085679314567e-06, "loss": 0.3342, "step": 97500 }, { "epoch": 2.83, "learning_rate": 9.228886168910649e-06, "loss": 0.3456, "step": 98000 }, { "epoch": 2.84, "learning_rate": 9.167686658506732e-06, "loss": 0.3553, "step": 98500 }, { "epoch": 2.85, "learning_rate": 9.106487148102816e-06, "loss": 0.3475, "step": 99000 }, { "epoch": 2.87, "learning_rate": 9.045287637698899e-06, "loss": 0.3507, "step": 99500 }, { "epoch": 2.88, "learning_rate": 8.984088127294983e-06, "loss": 0.3457, "step": 100000 }, { "epoch": 2.9, "learning_rate": 8.922888616891066e-06, "loss": 0.3445, "step": 100500 }, { "epoch": 2.91, "learning_rate": 8.86168910648715e-06, "loss": 0.3623, "step": 101000 }, { "epoch": 2.93, "learning_rate": 8.800489596083231e-06, "loss": 0.3477, "step": 101500 }, { "epoch": 2.94, "learning_rate": 8.739290085679314e-06, "loss": 0.3363, "step": 102000 }, { "epoch": 2.96, "learning_rate": 8.678090575275398e-06, "loss": 0.3445, "step": 102500 }, { "epoch": 2.97, "learning_rate": 8.616891064871483e-06, "loss": 0.3453, "step": 103000 }, { "epoch": 2.98, "learning_rate": 8.555691554467564e-06, "loss": 0.3509, "step": 103500 }, { "epoch": 3.0, "learning_rate": 8.494492044063648e-06, "loss": 0.3516, "step": 104000 }, { "epoch": 3.0, "eval_accuracy": 0.8893740902474527, "eval_loss": 0.28782936930656433, "eval_runtime": 104.9747, "eval_samples_per_second": 65.444, "eval_steps_per_second": 8.183, "step": 104040 }, { "epoch": 3.01, "learning_rate": 8.433292533659731e-06, "loss": 0.3375, "step": 104500 }, { "epoch": 3.03, "learning_rate": 8.372093023255815e-06, "loss": 0.3318, "step": 105000 }, { "epoch": 3.04, "learning_rate": 8.310893512851898e-06, "loss": 0.3481, "step": 105500 }, { "epoch": 3.06, "learning_rate": 8.249694002447981e-06, "loss": 0.3387, "step": 106000 }, { "epoch": 3.07, "learning_rate": 8.188494492044065e-06, "loss": 0.3336, "step": 106500 }, { "epoch": 3.09, "learning_rate": 8.127294981640148e-06, "loss": 0.3451, "step": 107000 }, { "epoch": 3.1, "learning_rate": 8.06609547123623e-06, "loss": 0.33, "step": 107500 }, { "epoch": 3.11, "learning_rate": 8.004895960832313e-06, "loss": 0.3304, "step": 108000 }, { "epoch": 3.13, "learning_rate": 7.943696450428398e-06, "loss": 0.3429, "step": 108500 }, { "epoch": 3.14, "learning_rate": 7.88249694002448e-06, "loss": 0.3267, "step": 109000 }, { "epoch": 3.16, "learning_rate": 7.821297429620563e-06, "loss": 0.3357, "step": 109500 }, { "epoch": 3.17, "learning_rate": 7.760097919216647e-06, "loss": 0.346, "step": 110000 }, { "epoch": 3.19, "learning_rate": 7.69889840881273e-06, "loss": 0.3401, "step": 110500 }, { "epoch": 3.2, "learning_rate": 7.637698898408813e-06, "loss": 0.3478, "step": 111000 }, { "epoch": 3.22, "learning_rate": 7.576499388004897e-06, "loss": 0.338, "step": 111500 }, { "epoch": 3.23, "learning_rate": 7.51529987760098e-06, "loss": 0.3375, "step": 112000 }, { "epoch": 3.24, "learning_rate": 7.4541003671970636e-06, "loss": 0.3342, "step": 112500 }, { "epoch": 3.26, "learning_rate": 7.392900856793146e-06, "loss": 0.3433, "step": 113000 }, { "epoch": 3.27, "learning_rate": 7.3317013463892295e-06, "loss": 0.3502, "step": 113500 }, { "epoch": 3.29, "learning_rate": 7.270501835985313e-06, "loss": 0.3409, "step": 114000 }, { "epoch": 3.3, "learning_rate": 7.209302325581395e-06, "loss": 0.3335, "step": 114500 }, { "epoch": 3.32, "learning_rate": 7.148102815177479e-06, "loss": 0.3508, "step": 115000 }, { "epoch": 3.33, "learning_rate": 7.086903304773562e-06, "loss": 0.3485, "step": 115500 }, { "epoch": 3.34, "learning_rate": 7.025703794369646e-06, "loss": 0.3517, "step": 116000 }, { "epoch": 3.36, "learning_rate": 6.964504283965728e-06, "loss": 0.3336, "step": 116500 }, { "epoch": 3.37, "learning_rate": 6.903304773561812e-06, "loss": 0.3591, "step": 117000 }, { "epoch": 3.39, "learning_rate": 6.842105263157896e-06, "loss": 0.3456, "step": 117500 }, { "epoch": 3.4, "learning_rate": 6.780905752753979e-06, "loss": 0.338, "step": 118000 }, { "epoch": 3.42, "learning_rate": 6.7197062423500616e-06, "loss": 0.3456, "step": 118500 }, { "epoch": 3.43, "learning_rate": 6.658506731946145e-06, "loss": 0.3559, "step": 119000 }, { "epoch": 3.45, "learning_rate": 6.597307221542228e-06, "loss": 0.3462, "step": 119500 }, { "epoch": 3.46, "learning_rate": 6.536107711138311e-06, "loss": 0.3343, "step": 120000 }, { "epoch": 3.47, "learning_rate": 6.474908200734394e-06, "loss": 0.3238, "step": 120500 }, { "epoch": 3.49, "learning_rate": 6.413708690330478e-06, "loss": 0.3459, "step": 121000 }, { "epoch": 3.5, "learning_rate": 6.352509179926562e-06, "loss": 0.362, "step": 121500 }, { "epoch": 3.52, "learning_rate": 6.2913096695226435e-06, "loss": 0.3579, "step": 122000 }, { "epoch": 3.53, "learning_rate": 6.230110159118728e-06, "loss": 0.3487, "step": 122500 }, { "epoch": 3.55, "learning_rate": 6.168910648714811e-06, "loss": 0.3362, "step": 123000 }, { "epoch": 3.56, "learning_rate": 6.1077111383108945e-06, "loss": 0.3466, "step": 123500 }, { "epoch": 3.58, "learning_rate": 6.046511627906977e-06, "loss": 0.3487, "step": 124000 }, { "epoch": 3.59, "learning_rate": 5.98531211750306e-06, "loss": 0.3408, "step": 124500 }, { "epoch": 3.6, "learning_rate": 5.924112607099144e-06, "loss": 0.3456, "step": 125000 }, { "epoch": 3.62, "learning_rate": 5.862913096695227e-06, "loss": 0.347, "step": 125500 }, { "epoch": 3.63, "learning_rate": 5.80171358629131e-06, "loss": 0.3368, "step": 126000 }, { "epoch": 3.65, "learning_rate": 5.740514075887393e-06, "loss": 0.3428, "step": 126500 }, { "epoch": 3.66, "learning_rate": 5.679314565483477e-06, "loss": 0.3376, "step": 127000 }, { "epoch": 3.68, "learning_rate": 5.618115055079559e-06, "loss": 0.3434, "step": 127500 }, { "epoch": 3.69, "learning_rate": 5.556915544675643e-06, "loss": 0.3393, "step": 128000 }, { "epoch": 3.71, "learning_rate": 5.4957160342717266e-06, "loss": 0.3397, "step": 128500 }, { "epoch": 3.72, "learning_rate": 5.43451652386781e-06, "loss": 0.3281, "step": 129000 }, { "epoch": 3.73, "learning_rate": 5.3733170134638925e-06, "loss": 0.3318, "step": 129500 }, { "epoch": 3.75, "learning_rate": 5.312117503059976e-06, "loss": 0.3417, "step": 130000 }, { "epoch": 3.76, "learning_rate": 5.250917992656059e-06, "loss": 0.3502, "step": 130500 }, { "epoch": 3.78, "learning_rate": 5.189718482252143e-06, "loss": 0.3476, "step": 131000 }, { "epoch": 3.79, "learning_rate": 5.128518971848225e-06, "loss": 0.3351, "step": 131500 }, { "epoch": 3.81, "learning_rate": 5.0673194614443085e-06, "loss": 0.3328, "step": 132000 }, { "epoch": 3.82, "learning_rate": 5.006119951040393e-06, "loss": 0.3388, "step": 132500 }, { "epoch": 3.84, "learning_rate": 4.944920440636475e-06, "loss": 0.3465, "step": 133000 }, { "epoch": 3.85, "learning_rate": 4.883720930232559e-06, "loss": 0.3549, "step": 133500 }, { "epoch": 3.86, "learning_rate": 4.822521419828642e-06, "loss": 0.3524, "step": 134000 }, { "epoch": 3.88, "learning_rate": 4.7613219094247246e-06, "loss": 0.3398, "step": 134500 }, { "epoch": 3.89, "learning_rate": 4.700122399020808e-06, "loss": 0.3547, "step": 135000 }, { "epoch": 3.91, "learning_rate": 4.638922888616891e-06, "loss": 0.3386, "step": 135500 }, { "epoch": 3.92, "learning_rate": 4.577723378212975e-06, "loss": 0.3498, "step": 136000 }, { "epoch": 3.94, "learning_rate": 4.516523867809058e-06, "loss": 0.3341, "step": 136500 }, { "epoch": 3.95, "learning_rate": 4.4553243574051415e-06, "loss": 0.3401, "step": 137000 }, { "epoch": 3.96, "learning_rate": 4.394124847001224e-06, "loss": 0.3359, "step": 137500 }, { "epoch": 3.98, "learning_rate": 4.332925336597308e-06, "loss": 0.3511, "step": 138000 }, { "epoch": 3.99, "learning_rate": 4.271725826193391e-06, "loss": 0.3306, "step": 138500 }, { "epoch": 4.0, "eval_accuracy": 0.8962154294032023, "eval_loss": 0.292516827583313, "eval_runtime": 105.0784, "eval_samples_per_second": 65.38, "eval_steps_per_second": 8.175, "step": 138720 }, { "epoch": 4.01, "learning_rate": 4.210526315789474e-06, "loss": 0.3299, "step": 139000 }, { "epoch": 4.02, "learning_rate": 4.1493268053855575e-06, "loss": 0.3361, "step": 139500 }, { "epoch": 4.04, "learning_rate": 4.08812729498164e-06, "loss": 0.3293, "step": 140000 }, { "epoch": 4.05, "learning_rate": 4.026927784577723e-06, "loss": 0.3197, "step": 140500 }, { "epoch": 4.07, "learning_rate": 3.965728274173807e-06, "loss": 0.3438, "step": 141000 }, { "epoch": 4.08, "learning_rate": 3.90452876376989e-06, "loss": 0.3336, "step": 141500 }, { "epoch": 4.09, "learning_rate": 3.8433292533659735e-06, "loss": 0.3318, "step": 142000 }, { "epoch": 4.11, "learning_rate": 3.782129742962057e-06, "loss": 0.3402, "step": 142500 }, { "epoch": 4.12, "learning_rate": 3.72093023255814e-06, "loss": 0.3291, "step": 143000 }, { "epoch": 4.14, "learning_rate": 3.6597307221542232e-06, "loss": 0.3319, "step": 143500 }, { "epoch": 4.15, "learning_rate": 3.598531211750306e-06, "loss": 0.3278, "step": 144000 }, { "epoch": 4.17, "learning_rate": 3.537331701346389e-06, "loss": 0.3332, "step": 144500 }, { "epoch": 4.18, "learning_rate": 3.476132190942473e-06, "loss": 0.3366, "step": 145000 }, { "epoch": 4.2, "learning_rate": 3.414932680538556e-06, "loss": 0.3364, "step": 145500 }, { "epoch": 4.21, "learning_rate": 3.3537331701346393e-06, "loss": 0.3333, "step": 146000 }, { "epoch": 4.22, "learning_rate": 3.2925336597307222e-06, "loss": 0.3264, "step": 146500 }, { "epoch": 4.24, "learning_rate": 3.2313341493268056e-06, "loss": 0.3213, "step": 147000 }, { "epoch": 4.25, "learning_rate": 3.1701346389228886e-06, "loss": 0.3323, "step": 147500 }, { "epoch": 4.27, "learning_rate": 3.1089351285189724e-06, "loss": 0.3389, "step": 148000 }, { "epoch": 4.28, "learning_rate": 3.0477356181150553e-06, "loss": 0.3235, "step": 148500 }, { "epoch": 4.3, "learning_rate": 2.9865361077111387e-06, "loss": 0.3395, "step": 149000 }, { "epoch": 4.31, "learning_rate": 2.9253365973072217e-06, "loss": 0.3305, "step": 149500 }, { "epoch": 4.33, "learning_rate": 2.8641370869033055e-06, "loss": 0.3263, "step": 150000 }, { "epoch": 4.34, "learning_rate": 2.8029375764993884e-06, "loss": 0.3425, "step": 150500 }, { "epoch": 4.35, "learning_rate": 2.7417380660954714e-06, "loss": 0.3285, "step": 151000 }, { "epoch": 4.37, "learning_rate": 2.6805385556915547e-06, "loss": 0.3256, "step": 151500 }, { "epoch": 4.38, "learning_rate": 2.6193390452876377e-06, "loss": 0.3289, "step": 152000 }, { "epoch": 4.4, "learning_rate": 2.558139534883721e-06, "loss": 0.3445, "step": 152500 }, { "epoch": 4.41, "learning_rate": 2.4969400244798045e-06, "loss": 0.3381, "step": 153000 }, { "epoch": 4.43, "learning_rate": 2.4357405140758874e-06, "loss": 0.3312, "step": 153500 }, { "epoch": 4.44, "learning_rate": 2.374541003671971e-06, "loss": 0.3235, "step": 154000 }, { "epoch": 4.46, "learning_rate": 2.313341493268054e-06, "loss": 0.3379, "step": 154500 }, { "epoch": 4.47, "learning_rate": 2.252141982864137e-06, "loss": 0.3359, "step": 155000 }, { "epoch": 4.48, "learning_rate": 2.1909424724602205e-06, "loss": 0.3199, "step": 155500 }, { "epoch": 4.5, "learning_rate": 2.129742962056304e-06, "loss": 0.3291, "step": 156000 }, { "epoch": 4.51, "learning_rate": 2.068543451652387e-06, "loss": 0.3218, "step": 156500 }, { "epoch": 4.53, "learning_rate": 2.00734394124847e-06, "loss": 0.3362, "step": 157000 }, { "epoch": 4.54, "learning_rate": 1.9461444308445536e-06, "loss": 0.3308, "step": 157500 }, { "epoch": 4.56, "learning_rate": 1.8849449204406368e-06, "loss": 0.3229, "step": 158000 }, { "epoch": 4.57, "learning_rate": 1.82374541003672e-06, "loss": 0.3406, "step": 158500 }, { "epoch": 4.58, "learning_rate": 1.7625458996328033e-06, "loss": 0.3372, "step": 159000 }, { "epoch": 4.6, "learning_rate": 1.7013463892288863e-06, "loss": 0.3181, "step": 159500 }, { "epoch": 4.61, "learning_rate": 1.6401468788249694e-06, "loss": 0.3182, "step": 160000 }, { "epoch": 4.63, "learning_rate": 1.5789473684210526e-06, "loss": 0.3362, "step": 160500 }, { "epoch": 4.64, "learning_rate": 1.517747858017136e-06, "loss": 0.3269, "step": 161000 }, { "epoch": 4.66, "learning_rate": 1.4565483476132191e-06, "loss": 0.3409, "step": 161500 }, { "epoch": 4.67, "learning_rate": 1.3953488372093025e-06, "loss": 0.3411, "step": 162000 }, { "epoch": 4.69, "learning_rate": 1.3341493268053857e-06, "loss": 0.3064, "step": 162500 }, { "epoch": 4.7, "learning_rate": 1.2729498164014688e-06, "loss": 0.3364, "step": 163000 }, { "epoch": 4.71, "learning_rate": 1.2117503059975522e-06, "loss": 0.3444, "step": 163500 }, { "epoch": 4.73, "learning_rate": 1.1505507955936354e-06, "loss": 0.33, "step": 164000 }, { "epoch": 4.74, "learning_rate": 1.0893512851897185e-06, "loss": 0.3212, "step": 164500 }, { "epoch": 4.76, "learning_rate": 1.0281517747858017e-06, "loss": 0.3356, "step": 165000 }, { "epoch": 4.77, "learning_rate": 9.66952264381885e-07, "loss": 0.319, "step": 165500 }, { "epoch": 4.79, "learning_rate": 9.057527539779683e-07, "loss": 0.3363, "step": 166000 }, { "epoch": 4.8, "learning_rate": 8.445532435740515e-07, "loss": 0.3466, "step": 166500 }, { "epoch": 4.82, "learning_rate": 7.833537331701346e-07, "loss": 0.3301, "step": 167000 }, { "epoch": 4.83, "learning_rate": 7.221542227662179e-07, "loss": 0.3286, "step": 167500 }, { "epoch": 4.84, "learning_rate": 6.609547123623011e-07, "loss": 0.3233, "step": 168000 }, { "epoch": 4.86, "learning_rate": 5.997552019583844e-07, "loss": 0.3333, "step": 168500 }, { "epoch": 4.87, "learning_rate": 5.385556915544677e-07, "loss": 0.3129, "step": 169000 }, { "epoch": 4.89, "learning_rate": 4.773561811505508e-07, "loss": 0.338, "step": 169500 }, { "epoch": 4.9, "learning_rate": 4.1615667074663406e-07, "loss": 0.3297, "step": 170000 } ], "max_steps": 173400, "num_train_epochs": 5, "total_flos": 3.578310352896e+17, "trial_name": null, "trial_params": null }