|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 113040, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.977883934890305e-05, |
|
"loss": 0.4833, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.9557678697806086e-05, |
|
"loss": 0.4355, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.933651804670913e-05, |
|
"loss": 0.4192, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.9115357395612176e-05, |
|
"loss": 0.4073, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.889419674451522e-05, |
|
"loss": 0.3977, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.867303609341826e-05, |
|
"loss": 0.3892, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 4.8451875442321304e-05, |
|
"loss": 0.382, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.823071479122435e-05, |
|
"loss": 0.3749, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.800955414012739e-05, |
|
"loss": 0.3688, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 4.778839348903044e-05, |
|
"loss": 0.363, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.756723283793348e-05, |
|
"loss": 0.3576, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.734607218683652e-05, |
|
"loss": 0.3529, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 4.712491153573956e-05, |
|
"loss": 0.3481, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.6903750884642606e-05, |
|
"loss": 0.3437, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.668259023354565e-05, |
|
"loss": 0.3394, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.6461429582448696e-05, |
|
"loss": 0.3358, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 4.624026893135174e-05, |
|
"loss": 0.3323, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.601910828025478e-05, |
|
"loss": 0.3287, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.5797947629157824e-05, |
|
"loss": 0.3257, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.557678697806086e-05, |
|
"loss": 0.3227, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 4.535562632696391e-05, |
|
"loss": 0.3202, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 4.513446567586695e-05, |
|
"loss": 0.3173, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9059693079835405, |
|
"eval_loss": 0.2837291359901428, |
|
"eval_runtime": 770.0213, |
|
"eval_samples_per_second": 313.194, |
|
"eval_steps_per_second": 1.632, |
|
"step": 11304 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 4.491330502477e-05, |
|
"loss": 0.3145, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 4.469214437367304e-05, |
|
"loss": 0.3116, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 4.447098372257608e-05, |
|
"loss": 0.3098, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 4.4249823071479126e-05, |
|
"loss": 0.3078, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 4.4028662420382164e-05, |
|
"loss": 0.306, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 4.380750176928521e-05, |
|
"loss": 0.3041, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 4.3586341118188254e-05, |
|
"loss": 0.3024, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 4.33651804670913e-05, |
|
"loss": 0.3008, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 4.3144019815994344e-05, |
|
"loss": 0.2992, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 4.292285916489738e-05, |
|
"loss": 0.2979, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 4.270169851380043e-05, |
|
"loss": 0.2965, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 4.2480537862703466e-05, |
|
"loss": 0.295, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 4.225937721160652e-05, |
|
"loss": 0.2939, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 4.2038216560509556e-05, |
|
"loss": 0.2927, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.18170559094126e-05, |
|
"loss": 0.2915, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 4.1595895258315646e-05, |
|
"loss": 0.2906, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 4.1374734607218684e-05, |
|
"loss": 0.2894, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 4.115357395612173e-05, |
|
"loss": 0.2883, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 4.093241330502477e-05, |
|
"loss": 0.2875, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 4.071125265392782e-05, |
|
"loss": 0.2866, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 4.049009200283086e-05, |
|
"loss": 0.2856, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 4.02689313517339e-05, |
|
"loss": 0.2849, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 4.004777070063695e-05, |
|
"loss": 0.284, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9123534174226251, |
|
"eval_loss": 0.2612881660461426, |
|
"eval_runtime": 772.6863, |
|
"eval_samples_per_second": 312.114, |
|
"eval_steps_per_second": 1.627, |
|
"step": 22608 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 3.9826610049539986e-05, |
|
"loss": 0.283, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 3.960544939844303e-05, |
|
"loss": 0.2821, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 3.9384288747346076e-05, |
|
"loss": 0.2814, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 3.916312809624912e-05, |
|
"loss": 0.2808, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 3.894196744515216e-05, |
|
"loss": 0.2804, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 3.8720806794055204e-05, |
|
"loss": 0.2795, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 3.849964614295825e-05, |
|
"loss": 0.2788, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 3.827848549186129e-05, |
|
"loss": 0.2782, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 3.805732484076434e-05, |
|
"loss": 0.2779, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 3.783616418966738e-05, |
|
"loss": 0.2772, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 3.761500353857042e-05, |
|
"loss": 0.2767, |
|
"step": 28000 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 3.739384288747346e-05, |
|
"loss": 0.2762, |
|
"step": 28500 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 3.7172682236376506e-05, |
|
"loss": 0.2759, |
|
"step": 29000 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 3.6951521585279544e-05, |
|
"loss": 0.2755, |
|
"step": 29500 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 3.673036093418259e-05, |
|
"loss": 0.2749, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 3.650920028308564e-05, |
|
"loss": 0.2744, |
|
"step": 30500 |
|
}, |
|
{ |
|
"epoch": 2.74, |
|
"learning_rate": 3.628803963198868e-05, |
|
"loss": 0.2742, |
|
"step": 31000 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 3.6066878980891724e-05, |
|
"loss": 0.2738, |
|
"step": 31500 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 3.584571832979476e-05, |
|
"loss": 0.2732, |
|
"step": 32000 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 3.562455767869781e-05, |
|
"loss": 0.2729, |
|
"step": 32500 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 3.5403397027600845e-05, |
|
"loss": 0.2724, |
|
"step": 33000 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 3.51822363765039e-05, |
|
"loss": 0.2719, |
|
"step": 33500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9140334727013555, |
|
"eval_loss": 0.254567414522171, |
|
"eval_runtime": 778.5722, |
|
"eval_samples_per_second": 309.754, |
|
"eval_steps_per_second": 1.614, |
|
"step": 33912 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 3.4961075725406935e-05, |
|
"loss": 0.2716, |
|
"step": 34000 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 3.473991507430998e-05, |
|
"loss": 0.2709, |
|
"step": 34500 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 3.4518754423213026e-05, |
|
"loss": 0.2705, |
|
"step": 35000 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 3.4297593772116064e-05, |
|
"loss": 0.2701, |
|
"step": 35500 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 3.407643312101911e-05, |
|
"loss": 0.2701, |
|
"step": 36000 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 3.3855272469922154e-05, |
|
"loss": 0.2696, |
|
"step": 36500 |
|
}, |
|
{ |
|
"epoch": 3.27, |
|
"learning_rate": 3.36341118188252e-05, |
|
"loss": 0.2694, |
|
"step": 37000 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 3.341295116772824e-05, |
|
"loss": 0.269, |
|
"step": 37500 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 3.319179051663128e-05, |
|
"loss": 0.269, |
|
"step": 38000 |
|
}, |
|
{ |
|
"epoch": 3.41, |
|
"learning_rate": 3.297062986553433e-05, |
|
"loss": 0.2685, |
|
"step": 38500 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 3.2749469214437365e-05, |
|
"loss": 0.2683, |
|
"step": 39000 |
|
}, |
|
{ |
|
"epoch": 3.49, |
|
"learning_rate": 3.252830856334041e-05, |
|
"loss": 0.2679, |
|
"step": 39500 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 3.2307147912243455e-05, |
|
"loss": 0.2679, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 3.58, |
|
"learning_rate": 3.20859872611465e-05, |
|
"loss": 0.2676, |
|
"step": 40500 |
|
}, |
|
{ |
|
"epoch": 3.63, |
|
"learning_rate": 3.186482661004954e-05, |
|
"loss": 0.2673, |
|
"step": 41000 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 3.1643665958952584e-05, |
|
"loss": 0.2669, |
|
"step": 41500 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 3.142250530785563e-05, |
|
"loss": 0.267, |
|
"step": 42000 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 3.120134465675867e-05, |
|
"loss": 0.2667, |
|
"step": 42500 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 3.098018400566172e-05, |
|
"loss": 0.2664, |
|
"step": 43000 |
|
}, |
|
{ |
|
"epoch": 3.85, |
|
"learning_rate": 3.075902335456476e-05, |
|
"loss": 0.2662, |
|
"step": 43500 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 3.05378627034678e-05, |
|
"loss": 0.2658, |
|
"step": 44000 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 3.0316702052370844e-05, |
|
"loss": 0.2656, |
|
"step": 44500 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 3.0095541401273885e-05, |
|
"loss": 0.2654, |
|
"step": 45000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9148443813733191, |
|
"eval_loss": 0.25113189220428467, |
|
"eval_runtime": 770.8647, |
|
"eval_samples_per_second": 312.851, |
|
"eval_steps_per_second": 1.631, |
|
"step": 45216 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 2.9874380750176927e-05, |
|
"loss": 0.2652, |
|
"step": 45500 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 2.9653220099079975e-05, |
|
"loss": 0.2648, |
|
"step": 46000 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 2.9432059447983017e-05, |
|
"loss": 0.2645, |
|
"step": 46500 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 2.921089879688606e-05, |
|
"loss": 0.2644, |
|
"step": 47000 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 2.8989738145789104e-05, |
|
"loss": 0.2643, |
|
"step": 47500 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 2.8768577494692145e-05, |
|
"loss": 0.2638, |
|
"step": 48000 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 2.8547416843595187e-05, |
|
"loss": 0.2637, |
|
"step": 48500 |
|
}, |
|
{ |
|
"epoch": 4.33, |
|
"learning_rate": 2.832625619249823e-05, |
|
"loss": 0.2636, |
|
"step": 49000 |
|
}, |
|
{ |
|
"epoch": 4.38, |
|
"learning_rate": 2.8105095541401277e-05, |
|
"loss": 0.2634, |
|
"step": 49500 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 2.788393489030432e-05, |
|
"loss": 0.2634, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 2.766277423920736e-05, |
|
"loss": 0.2629, |
|
"step": 50500 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 2.7441613588110405e-05, |
|
"loss": 0.2631, |
|
"step": 51000 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 2.7220452937013447e-05, |
|
"loss": 0.2629, |
|
"step": 51500 |
|
}, |
|
{ |
|
"epoch": 4.6, |
|
"learning_rate": 2.699929228591649e-05, |
|
"loss": 0.2627, |
|
"step": 52000 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 2.6778131634819537e-05, |
|
"loss": 0.2627, |
|
"step": 52500 |
|
}, |
|
{ |
|
"epoch": 4.69, |
|
"learning_rate": 2.655697098372258e-05, |
|
"loss": 0.2624, |
|
"step": 53000 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 2.633581033262562e-05, |
|
"loss": 0.2622, |
|
"step": 53500 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 2.6114649681528662e-05, |
|
"loss": 0.262, |
|
"step": 54000 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 2.5893489030431707e-05, |
|
"loss": 0.2618, |
|
"step": 54500 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 2.567232837933475e-05, |
|
"loss": 0.262, |
|
"step": 55000 |
|
}, |
|
{ |
|
"epoch": 4.91, |
|
"learning_rate": 2.5451167728237797e-05, |
|
"loss": 0.2616, |
|
"step": 55500 |
|
}, |
|
{ |
|
"epoch": 4.95, |
|
"learning_rate": 2.523000707714084e-05, |
|
"loss": 0.2614, |
|
"step": 56000 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.500884642604388e-05, |
|
"loss": 0.2613, |
|
"step": 56500 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.9154096796494876, |
|
"eval_loss": 0.24885989725589752, |
|
"eval_runtime": 775.004, |
|
"eval_samples_per_second": 311.18, |
|
"eval_steps_per_second": 1.622, |
|
"step": 56520 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 2.4787685774946922e-05, |
|
"loss": 0.2609, |
|
"step": 57000 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 2.4566525123849964e-05, |
|
"loss": 0.2608, |
|
"step": 57500 |
|
}, |
|
{ |
|
"epoch": 5.13, |
|
"learning_rate": 2.434536447275301e-05, |
|
"loss": 0.2607, |
|
"step": 58000 |
|
}, |
|
{ |
|
"epoch": 5.18, |
|
"learning_rate": 2.4124203821656054e-05, |
|
"loss": 0.2604, |
|
"step": 58500 |
|
}, |
|
{ |
|
"epoch": 5.22, |
|
"learning_rate": 2.3903043170559095e-05, |
|
"loss": 0.2604, |
|
"step": 59000 |
|
}, |
|
{ |
|
"epoch": 5.26, |
|
"learning_rate": 2.368188251946214e-05, |
|
"loss": 0.2603, |
|
"step": 59500 |
|
}, |
|
{ |
|
"epoch": 5.31, |
|
"learning_rate": 2.3460721868365182e-05, |
|
"loss": 0.2602, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 5.35, |
|
"learning_rate": 2.3239561217268224e-05, |
|
"loss": 0.2602, |
|
"step": 60500 |
|
}, |
|
{ |
|
"epoch": 5.4, |
|
"learning_rate": 2.301840056617127e-05, |
|
"loss": 0.2602, |
|
"step": 61000 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"learning_rate": 2.279723991507431e-05, |
|
"loss": 0.26, |
|
"step": 61500 |
|
}, |
|
{ |
|
"epoch": 5.48, |
|
"learning_rate": 2.2576079263977355e-05, |
|
"loss": 0.2598, |
|
"step": 62000 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 2.2354918612880397e-05, |
|
"loss": 0.2598, |
|
"step": 62500 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"learning_rate": 2.2133757961783442e-05, |
|
"loss": 0.2595, |
|
"step": 63000 |
|
}, |
|
{ |
|
"epoch": 5.62, |
|
"learning_rate": 2.1912597310686484e-05, |
|
"loss": 0.2596, |
|
"step": 63500 |
|
}, |
|
{ |
|
"epoch": 5.66, |
|
"learning_rate": 2.1691436659589525e-05, |
|
"loss": 0.2594, |
|
"step": 64000 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 2.147027600849257e-05, |
|
"loss": 0.2592, |
|
"step": 64500 |
|
}, |
|
{ |
|
"epoch": 5.75, |
|
"learning_rate": 2.1249115357395612e-05, |
|
"loss": 0.259, |
|
"step": 65000 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 2.1027954706298657e-05, |
|
"loss": 0.259, |
|
"step": 65500 |
|
}, |
|
{ |
|
"epoch": 5.84, |
|
"learning_rate": 2.0806794055201702e-05, |
|
"loss": 0.2589, |
|
"step": 66000 |
|
}, |
|
{ |
|
"epoch": 5.88, |
|
"learning_rate": 2.0585633404104744e-05, |
|
"loss": 0.2587, |
|
"step": 66500 |
|
}, |
|
{ |
|
"epoch": 5.93, |
|
"learning_rate": 2.0364472753007785e-05, |
|
"loss": 0.2589, |
|
"step": 67000 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 2.014331210191083e-05, |
|
"loss": 0.2586, |
|
"step": 67500 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.9157895529502922, |
|
"eval_loss": 0.24735933542251587, |
|
"eval_runtime": 787.6461, |
|
"eval_samples_per_second": 306.186, |
|
"eval_steps_per_second": 1.596, |
|
"step": 67824 |
|
}, |
|
{ |
|
"epoch": 6.02, |
|
"learning_rate": 1.9922151450813872e-05, |
|
"loss": 0.2585, |
|
"step": 68000 |
|
}, |
|
{ |
|
"epoch": 6.06, |
|
"learning_rate": 1.9700990799716914e-05, |
|
"loss": 0.2581, |
|
"step": 68500 |
|
}, |
|
{ |
|
"epoch": 6.1, |
|
"learning_rate": 1.947983014861996e-05, |
|
"loss": 0.2581, |
|
"step": 69000 |
|
}, |
|
{ |
|
"epoch": 6.15, |
|
"learning_rate": 1.9258669497523004e-05, |
|
"loss": 0.2579, |
|
"step": 69500 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 1.9037508846426045e-05, |
|
"loss": 0.2579, |
|
"step": 70000 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 1.881634819532909e-05, |
|
"loss": 0.2579, |
|
"step": 70500 |
|
}, |
|
{ |
|
"epoch": 6.28, |
|
"learning_rate": 1.8595187544232132e-05, |
|
"loss": 0.2578, |
|
"step": 71000 |
|
}, |
|
{ |
|
"epoch": 6.33, |
|
"learning_rate": 1.8374026893135174e-05, |
|
"loss": 0.2577, |
|
"step": 71500 |
|
}, |
|
{ |
|
"epoch": 6.37, |
|
"learning_rate": 1.8152866242038215e-05, |
|
"loss": 0.2577, |
|
"step": 72000 |
|
}, |
|
{ |
|
"epoch": 6.41, |
|
"learning_rate": 1.793170559094126e-05, |
|
"loss": 0.2576, |
|
"step": 72500 |
|
}, |
|
{ |
|
"epoch": 6.46, |
|
"learning_rate": 1.7710544939844302e-05, |
|
"loss": 0.2575, |
|
"step": 73000 |
|
}, |
|
{ |
|
"epoch": 6.5, |
|
"learning_rate": 1.7489384288747347e-05, |
|
"loss": 0.2572, |
|
"step": 73500 |
|
}, |
|
{ |
|
"epoch": 6.55, |
|
"learning_rate": 1.7268223637650392e-05, |
|
"loss": 0.2575, |
|
"step": 74000 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"learning_rate": 1.7047062986553434e-05, |
|
"loss": 0.2571, |
|
"step": 74500 |
|
}, |
|
{ |
|
"epoch": 6.63, |
|
"learning_rate": 1.6825902335456475e-05, |
|
"loss": 0.2573, |
|
"step": 75000 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 1.660474168435952e-05, |
|
"loss": 0.2573, |
|
"step": 75500 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 1.6383581033262562e-05, |
|
"loss": 0.2572, |
|
"step": 76000 |
|
}, |
|
{ |
|
"epoch": 6.77, |
|
"learning_rate": 1.6162420382165603e-05, |
|
"loss": 0.257, |
|
"step": 76500 |
|
}, |
|
{ |
|
"epoch": 6.81, |
|
"learning_rate": 1.594125973106865e-05, |
|
"loss": 0.257, |
|
"step": 77000 |
|
}, |
|
{ |
|
"epoch": 6.86, |
|
"learning_rate": 1.5720099079971694e-05, |
|
"loss": 0.2569, |
|
"step": 77500 |
|
}, |
|
{ |
|
"epoch": 6.9, |
|
"learning_rate": 1.5498938428874735e-05, |
|
"loss": 0.257, |
|
"step": 78000 |
|
}, |
|
{ |
|
"epoch": 6.94, |
|
"learning_rate": 1.527777777777778e-05, |
|
"loss": 0.2569, |
|
"step": 78500 |
|
}, |
|
{ |
|
"epoch": 6.99, |
|
"learning_rate": 1.5056617126680822e-05, |
|
"loss": 0.2569, |
|
"step": 79000 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.9160589551288438, |
|
"eval_loss": 0.24625588953495026, |
|
"eval_runtime": 787.7182, |
|
"eval_samples_per_second": 306.158, |
|
"eval_steps_per_second": 1.596, |
|
"step": 79128 |
|
}, |
|
{ |
|
"epoch": 7.03, |
|
"learning_rate": 1.4835456475583863e-05, |
|
"loss": 0.2564, |
|
"step": 79500 |
|
}, |
|
{ |
|
"epoch": 7.08, |
|
"learning_rate": 1.461429582448691e-05, |
|
"loss": 0.2563, |
|
"step": 80000 |
|
}, |
|
{ |
|
"epoch": 7.12, |
|
"learning_rate": 1.4393135173389952e-05, |
|
"loss": 0.2562, |
|
"step": 80500 |
|
}, |
|
{ |
|
"epoch": 7.17, |
|
"learning_rate": 1.4171974522292993e-05, |
|
"loss": 0.2563, |
|
"step": 81000 |
|
}, |
|
{ |
|
"epoch": 7.21, |
|
"learning_rate": 1.3950813871196037e-05, |
|
"loss": 0.2561, |
|
"step": 81500 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 1.3729653220099082e-05, |
|
"loss": 0.256, |
|
"step": 82000 |
|
}, |
|
{ |
|
"epoch": 7.3, |
|
"learning_rate": 1.3508492569002123e-05, |
|
"loss": 0.2561, |
|
"step": 82500 |
|
}, |
|
{ |
|
"epoch": 7.34, |
|
"learning_rate": 1.3287331917905165e-05, |
|
"loss": 0.2561, |
|
"step": 83000 |
|
}, |
|
{ |
|
"epoch": 7.39, |
|
"learning_rate": 1.306617126680821e-05, |
|
"loss": 0.2559, |
|
"step": 83500 |
|
}, |
|
{ |
|
"epoch": 7.43, |
|
"learning_rate": 1.2845010615711253e-05, |
|
"loss": 0.256, |
|
"step": 84000 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 1.2623849964614295e-05, |
|
"loss": 0.2558, |
|
"step": 84500 |
|
}, |
|
{ |
|
"epoch": 7.52, |
|
"learning_rate": 1.2402689313517338e-05, |
|
"loss": 0.256, |
|
"step": 85000 |
|
}, |
|
{ |
|
"epoch": 7.56, |
|
"learning_rate": 1.2181528662420383e-05, |
|
"loss": 0.2558, |
|
"step": 85500 |
|
}, |
|
{ |
|
"epoch": 7.61, |
|
"learning_rate": 1.1960368011323427e-05, |
|
"loss": 0.2559, |
|
"step": 86000 |
|
}, |
|
{ |
|
"epoch": 7.65, |
|
"learning_rate": 1.1739207360226468e-05, |
|
"loss": 0.2557, |
|
"step": 86500 |
|
}, |
|
{ |
|
"epoch": 7.7, |
|
"learning_rate": 1.1518046709129512e-05, |
|
"loss": 0.2557, |
|
"step": 87000 |
|
}, |
|
{ |
|
"epoch": 7.74, |
|
"learning_rate": 1.1296886058032555e-05, |
|
"loss": 0.2555, |
|
"step": 87500 |
|
}, |
|
{ |
|
"epoch": 7.78, |
|
"learning_rate": 1.1075725406935598e-05, |
|
"loss": 0.2556, |
|
"step": 88000 |
|
}, |
|
{ |
|
"epoch": 7.83, |
|
"learning_rate": 1.0854564755838642e-05, |
|
"loss": 0.2556, |
|
"step": 88500 |
|
}, |
|
{ |
|
"epoch": 7.87, |
|
"learning_rate": 1.0633404104741685e-05, |
|
"loss": 0.2552, |
|
"step": 89000 |
|
}, |
|
{ |
|
"epoch": 7.92, |
|
"learning_rate": 1.0412243453644728e-05, |
|
"loss": 0.2554, |
|
"step": 89500 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 1.0191082802547772e-05, |
|
"loss": 0.2553, |
|
"step": 90000 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.9162647719016384, |
|
"eval_loss": 0.24548450112342834, |
|
"eval_runtime": 790.7594, |
|
"eval_samples_per_second": 304.98, |
|
"eval_steps_per_second": 1.59, |
|
"step": 90432 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 9.969922151450813e-06, |
|
"loss": 0.2553, |
|
"step": 90500 |
|
}, |
|
{ |
|
"epoch": 8.05, |
|
"learning_rate": 9.748761500353858e-06, |
|
"loss": 0.255, |
|
"step": 91000 |
|
}, |
|
{ |
|
"epoch": 8.09, |
|
"learning_rate": 9.527600849256902e-06, |
|
"loss": 0.2549, |
|
"step": 91500 |
|
}, |
|
{ |
|
"epoch": 8.14, |
|
"learning_rate": 9.306440198159943e-06, |
|
"loss": 0.255, |
|
"step": 92000 |
|
}, |
|
{ |
|
"epoch": 8.18, |
|
"learning_rate": 9.085279547062987e-06, |
|
"loss": 0.2549, |
|
"step": 92500 |
|
}, |
|
{ |
|
"epoch": 8.23, |
|
"learning_rate": 8.86411889596603e-06, |
|
"loss": 0.2548, |
|
"step": 93000 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 8.642958244869073e-06, |
|
"loss": 0.2551, |
|
"step": 93500 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 8.421797593772117e-06, |
|
"loss": 0.2548, |
|
"step": 94000 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"learning_rate": 8.200636942675158e-06, |
|
"loss": 0.2549, |
|
"step": 94500 |
|
}, |
|
{ |
|
"epoch": 8.4, |
|
"learning_rate": 7.979476291578203e-06, |
|
"loss": 0.2549, |
|
"step": 95000 |
|
}, |
|
{ |
|
"epoch": 8.45, |
|
"learning_rate": 7.758315640481247e-06, |
|
"loss": 0.2548, |
|
"step": 95500 |
|
}, |
|
{ |
|
"epoch": 8.49, |
|
"learning_rate": 7.537154989384289e-06, |
|
"loss": 0.2547, |
|
"step": 96000 |
|
}, |
|
{ |
|
"epoch": 8.54, |
|
"learning_rate": 7.3159943382873326e-06, |
|
"loss": 0.2546, |
|
"step": 96500 |
|
}, |
|
{ |
|
"epoch": 8.58, |
|
"learning_rate": 7.094833687190375e-06, |
|
"loss": 0.2548, |
|
"step": 97000 |
|
}, |
|
{ |
|
"epoch": 8.63, |
|
"learning_rate": 6.873673036093418e-06, |
|
"loss": 0.2547, |
|
"step": 97500 |
|
}, |
|
{ |
|
"epoch": 8.67, |
|
"learning_rate": 6.652512384996462e-06, |
|
"loss": 0.2547, |
|
"step": 98000 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 6.431351733899504e-06, |
|
"loss": 0.2547, |
|
"step": 98500 |
|
}, |
|
{ |
|
"epoch": 8.76, |
|
"learning_rate": 6.210191082802548e-06, |
|
"loss": 0.2545, |
|
"step": 99000 |
|
}, |
|
{ |
|
"epoch": 8.8, |
|
"learning_rate": 5.989030431705591e-06, |
|
"loss": 0.2544, |
|
"step": 99500 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"learning_rate": 5.767869780608635e-06, |
|
"loss": 0.2544, |
|
"step": 100000 |
|
}, |
|
{ |
|
"epoch": 8.89, |
|
"learning_rate": 5.5467091295116775e-06, |
|
"loss": 0.2545, |
|
"step": 100500 |
|
}, |
|
{ |
|
"epoch": 8.93, |
|
"learning_rate": 5.325548478414721e-06, |
|
"loss": 0.2545, |
|
"step": 101000 |
|
}, |
|
{ |
|
"epoch": 8.98, |
|
"learning_rate": 5.104387827317763e-06, |
|
"loss": 0.2545, |
|
"step": 101500 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.9164148337838057, |
|
"eval_loss": 0.24497151374816895, |
|
"eval_runtime": 789.0403, |
|
"eval_samples_per_second": 305.645, |
|
"eval_steps_per_second": 1.593, |
|
"step": 101736 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.8832271762208075e-06, |
|
"loss": 0.2543, |
|
"step": 102000 |
|
}, |
|
{ |
|
"epoch": 9.07, |
|
"learning_rate": 4.66206652512385e-06, |
|
"loss": 0.254, |
|
"step": 102500 |
|
}, |
|
{ |
|
"epoch": 9.11, |
|
"learning_rate": 4.440905874026893e-06, |
|
"loss": 0.254, |
|
"step": 103000 |
|
}, |
|
{ |
|
"epoch": 9.16, |
|
"learning_rate": 4.219745222929937e-06, |
|
"loss": 0.2542, |
|
"step": 103500 |
|
}, |
|
{ |
|
"epoch": 9.2, |
|
"learning_rate": 3.99858457183298e-06, |
|
"loss": 0.2541, |
|
"step": 104000 |
|
}, |
|
{ |
|
"epoch": 9.24, |
|
"learning_rate": 3.777423920736023e-06, |
|
"loss": 0.254, |
|
"step": 104500 |
|
}, |
|
{ |
|
"epoch": 9.29, |
|
"learning_rate": 3.556263269639066e-06, |
|
"loss": 0.2541, |
|
"step": 105000 |
|
}, |
|
{ |
|
"epoch": 9.33, |
|
"learning_rate": 3.3351026185421087e-06, |
|
"loss": 0.2541, |
|
"step": 105500 |
|
}, |
|
{ |
|
"epoch": 9.38, |
|
"learning_rate": 3.113941967445152e-06, |
|
"loss": 0.2541, |
|
"step": 106000 |
|
}, |
|
{ |
|
"epoch": 9.42, |
|
"learning_rate": 2.8927813163481954e-06, |
|
"loss": 0.2541, |
|
"step": 106500 |
|
}, |
|
{ |
|
"epoch": 9.47, |
|
"learning_rate": 2.6716206652512383e-06, |
|
"loss": 0.2539, |
|
"step": 107000 |
|
}, |
|
{ |
|
"epoch": 9.51, |
|
"learning_rate": 2.4504600141542816e-06, |
|
"loss": 0.2541, |
|
"step": 107500 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"learning_rate": 2.229299363057325e-06, |
|
"loss": 0.2541, |
|
"step": 108000 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"learning_rate": 2.0081387119603683e-06, |
|
"loss": 0.2541, |
|
"step": 108500 |
|
}, |
|
{ |
|
"epoch": 9.64, |
|
"learning_rate": 1.786978060863411e-06, |
|
"loss": 0.254, |
|
"step": 109000 |
|
}, |
|
{ |
|
"epoch": 9.69, |
|
"learning_rate": 1.5658174097664543e-06, |
|
"loss": 0.2541, |
|
"step": 109500 |
|
}, |
|
{ |
|
"epoch": 9.73, |
|
"learning_rate": 1.3446567586694977e-06, |
|
"loss": 0.254, |
|
"step": 110000 |
|
}, |
|
{ |
|
"epoch": 9.78, |
|
"learning_rate": 1.1234961075725408e-06, |
|
"loss": 0.2539, |
|
"step": 110500 |
|
}, |
|
{ |
|
"epoch": 9.82, |
|
"learning_rate": 9.023354564755839e-07, |
|
"loss": 0.2537, |
|
"step": 111000 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 6.81174805378627e-07, |
|
"loss": 0.254, |
|
"step": 111500 |
|
}, |
|
{ |
|
"epoch": 9.91, |
|
"learning_rate": 4.6001415428167025e-07, |
|
"loss": 0.2541, |
|
"step": 112000 |
|
}, |
|
{ |
|
"epoch": 9.95, |
|
"learning_rate": 2.388535031847134e-07, |
|
"loss": 0.2539, |
|
"step": 112500 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 1.7692852087756548e-08, |
|
"loss": 0.2539, |
|
"step": 113000 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.916456858900755, |
|
"eval_loss": 0.24475741386413574, |
|
"eval_runtime": 768.7642, |
|
"eval_samples_per_second": 313.706, |
|
"eval_steps_per_second": 1.635, |
|
"step": 113040 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 113040, |
|
"total_flos": 5.670998618744553e+18, |
|
"train_loss": 0.27495618251225495, |
|
"train_runtime": 96949.7276, |
|
"train_samples_per_second": 223.864, |
|
"train_steps_per_second": 1.166 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 113040, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"total_flos": 5.670998618744553e+18, |
|
"train_batch_size": 24, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|