| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 438790, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.994302513730942e-05, | |
| "loss": 0.6256, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.988605027461884e-05, | |
| "loss": 0.5415, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.982907541192826e-05, | |
| "loss": 0.5189, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9772100549237675e-05, | |
| "loss": 0.5029, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.97151256865471e-05, | |
| "loss": 0.4908, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.965815082385652e-05, | |
| "loss": 0.4818, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.9601175961165935e-05, | |
| "loss": 0.474, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9544201098475354e-05, | |
| "loss": 0.468, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.9487226235784774e-05, | |
| "loss": 0.4617, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.9430251373094194e-05, | |
| "loss": 0.4573, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.937327651040361e-05, | |
| "loss": 0.4533, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.9316301647713034e-05, | |
| "loss": 0.4494, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.9259326785022454e-05, | |
| "loss": 0.4462, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.9202351922331867e-05, | |
| "loss": 0.4433, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.914537705964129e-05, | |
| "loss": 0.4401, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.9088402196950706e-05, | |
| "loss": 0.4383, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.9031427334260126e-05, | |
| "loss": 0.4354, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.8974452471569546e-05, | |
| "loss": 0.4331, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.8917477608878966e-05, | |
| "loss": 0.4314, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.8860502746188386e-05, | |
| "loss": 0.4292, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.88035278834978e-05, | |
| "loss": 0.4278, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.8746553020807225e-05, | |
| "loss": 0.4258, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.868957815811664e-05, | |
| "loss": 0.424, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.863260329542606e-05, | |
| "loss": 0.4224, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.8575628432735485e-05, | |
| "loss": 0.4209, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.85186535700449e-05, | |
| "loss": 0.4196, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.846167870735432e-05, | |
| "loss": 0.4184, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.840470384466374e-05, | |
| "loss": 0.417, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.834772898197316e-05, | |
| "loss": 0.4155, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.829075411928258e-05, | |
| "loss": 0.4145, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.823377925659199e-05, | |
| "loss": 0.4133, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.817680439390142e-05, | |
| "loss": 0.4123, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.811982953121083e-05, | |
| "loss": 0.411, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.806285466852025e-05, | |
| "loss": 0.4102, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.800587980582967e-05, | |
| "loss": 0.4087, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.794890494313909e-05, | |
| "loss": 0.4079, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.789193008044851e-05, | |
| "loss": 0.4072, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.783495521775793e-05, | |
| "loss": 0.406, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.777798035506735e-05, | |
| "loss": 0.4045, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.772100549237676e-05, | |
| "loss": 0.4044, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.766403062968618e-05, | |
| "loss": 0.4029, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.760705576699561e-05, | |
| "loss": 0.4018, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.755008090430502e-05, | |
| "loss": 0.4017, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.749310604161444e-05, | |
| "loss": 0.4007, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.743613117892386e-05, | |
| "loss": 0.3998, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.737915631623328e-05, | |
| "loss": 0.3992, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.7322181453542694e-05, | |
| "loss": 0.3984, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.726520659085212e-05, | |
| "loss": 0.3971, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.720823172816154e-05, | |
| "loss": 0.3965, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.7151256865470954e-05, | |
| "loss": 0.396, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.7094282002780374e-05, | |
| "loss": 0.3949, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.7037307140089793e-05, | |
| "loss": 0.3946, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.698033227739921e-05, | |
| "loss": 0.3938, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.692335741470863e-05, | |
| "loss": 0.3927, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.686638255201805e-05, | |
| "loss": 0.3923, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.680940768932747e-05, | |
| "loss": 0.3919, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.6752432826636886e-05, | |
| "loss": 0.3913, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.669545796394631e-05, | |
| "loss": 0.3904, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.6638483101255726e-05, | |
| "loss": 0.3899, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.6581508238565145e-05, | |
| "loss": 0.3891, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.6524533375874565e-05, | |
| "loss": 0.3887, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.6467558513183985e-05, | |
| "loss": 0.388, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.6410583650493405e-05, | |
| "loss": 0.3873, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.635360878780282e-05, | |
| "loss": 0.3864, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.6296633925112245e-05, | |
| "loss": 0.3859, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.6239659062421664e-05, | |
| "loss": 0.3857, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.618268419973108e-05, | |
| "loss": 0.385, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.6125709337040504e-05, | |
| "loss": 0.3841, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.606873447434992e-05, | |
| "loss": 0.3839, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.601175961165934e-05, | |
| "loss": 0.383, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.595478474896876e-05, | |
| "loss": 0.3825, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.589780988627818e-05, | |
| "loss": 0.382, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.5840835023587597e-05, | |
| "loss": 0.3814, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.5783860160897016e-05, | |
| "loss": 0.381, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.5726885298206436e-05, | |
| "loss": 0.3805, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.566991043551585e-05, | |
| "loss": 0.3797, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.561293557282527e-05, | |
| "loss": 0.3795, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.5555960710134696e-05, | |
| "loss": 0.3791, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.549898584744411e-05, | |
| "loss": 0.3783, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.544201098475353e-05, | |
| "loss": 0.3776, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.538503612206295e-05, | |
| "loss": 0.3772, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.532806125937237e-05, | |
| "loss": 0.3769, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.527108639668179e-05, | |
| "loss": 0.3766, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.521411153399121e-05, | |
| "loss": 0.3761, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.515713667130063e-05, | |
| "loss": 0.3756, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.510016180861004e-05, | |
| "loss": 0.3752, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.504318694591946e-05, | |
| "loss": 0.3747, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8869798506974093, | |
| "eval_loss": 0.3538902997970581, | |
| "eval_runtime": 2232.0077, | |
| "eval_samples_per_second": 279.414, | |
| "eval_steps_per_second": 2.183, | |
| "step": 43879 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.498621208322888e-05, | |
| "loss": 0.3739, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.49292372205383e-05, | |
| "loss": 0.3732, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.487226235784772e-05, | |
| "loss": 0.3729, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.481528749515714e-05, | |
| "loss": 0.3726, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.475831263246656e-05, | |
| "loss": 0.372, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.470133776977597e-05, | |
| "loss": 0.3715, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.46443629070854e-05, | |
| "loss": 0.3713, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.458738804439482e-05, | |
| "loss": 0.3707, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.453041318170423e-05, | |
| "loss": 0.3701, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.447343831901365e-05, | |
| "loss": 0.3699, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.441646345632307e-05, | |
| "loss": 0.3696, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.435948859363249e-05, | |
| "loss": 0.3697, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.4302513730941905e-05, | |
| "loss": 0.3689, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.424553886825133e-05, | |
| "loss": 0.3685, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.418856400556075e-05, | |
| "loss": 0.368, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.4131589142870165e-05, | |
| "loss": 0.3678, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.407461428017959e-05, | |
| "loss": 0.3674, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.4017639417489004e-05, | |
| "loss": 0.3674, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.3960664554798424e-05, | |
| "loss": 0.3667, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.3903689692107844e-05, | |
| "loss": 0.3661, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.3846714829417264e-05, | |
| "loss": 0.3662, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.3789739966726684e-05, | |
| "loss": 0.3658, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.37327651040361e-05, | |
| "loss": 0.3656, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.367579024134552e-05, | |
| "loss": 0.365, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.3618815378654936e-05, | |
| "loss": 0.3649, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.3561840515964356e-05, | |
| "loss": 0.3643, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.350486565327378e-05, | |
| "loss": 0.364, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.3447890790583196e-05, | |
| "loss": 0.3636, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.3390915927892616e-05, | |
| "loss": 0.3634, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.3333941065202036e-05, | |
| "loss": 0.3631, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.3276966202511455e-05, | |
| "loss": 0.3629, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.3219991339820875e-05, | |
| "loss": 0.3627, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.316301647713029e-05, | |
| "loss": 0.3623, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.3106041614439715e-05, | |
| "loss": 0.362, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.304906675174913e-05, | |
| "loss": 0.3616, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.299209188905855e-05, | |
| "loss": 0.3614, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.293511702636797e-05, | |
| "loss": 0.3609, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.287814216367739e-05, | |
| "loss": 0.3609, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.282116730098681e-05, | |
| "loss": 0.3602, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.276419243829623e-05, | |
| "loss": 0.3606, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.270721757560565e-05, | |
| "loss": 0.3603, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.265024271291506e-05, | |
| "loss": 0.3595, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.259326785022448e-05, | |
| "loss": 0.3593, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 4.2536292987533907e-05, | |
| "loss": 0.3594, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 4.247931812484332e-05, | |
| "loss": 0.3589, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.242234326215274e-05, | |
| "loss": 0.3587, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.236536839946216e-05, | |
| "loss": 0.3581, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.230839353677158e-05, | |
| "loss": 0.3582, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.225141867408099e-05, | |
| "loss": 0.3579, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.219444381139042e-05, | |
| "loss": 0.3576, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.213746894869984e-05, | |
| "loss": 0.357, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.208049408600925e-05, | |
| "loss": 0.3573, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.202351922331867e-05, | |
| "loss": 0.357, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.196654436062809e-05, | |
| "loss": 0.3567, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.190956949793751e-05, | |
| "loss": 0.3565, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.185259463524693e-05, | |
| "loss": 0.3562, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.179561977255635e-05, | |
| "loss": 0.3557, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.173864490986577e-05, | |
| "loss": 0.3556, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.1681670047175184e-05, | |
| "loss": 0.3553, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.162469518448461e-05, | |
| "loss": 0.3555, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.156772032179403e-05, | |
| "loss": 0.355, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.1510745459103443e-05, | |
| "loss": 0.3547, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.145377059641286e-05, | |
| "loss": 0.3546, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.139679573372228e-05, | |
| "loss": 0.3542, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.13398208710317e-05, | |
| "loss": 0.3541, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.128284600834112e-05, | |
| "loss": 0.3536, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 4.122587114565054e-05, | |
| "loss": 0.3537, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 4.116889628295996e-05, | |
| "loss": 0.3534, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 4.1111921420269376e-05, | |
| "loss": 0.3532, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.10549465575788e-05, | |
| "loss": 0.3532, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.0997971694888215e-05, | |
| "loss": 0.3529, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.0940996832197635e-05, | |
| "loss": 0.3527, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.0884021969507055e-05, | |
| "loss": 0.3525, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 4.0827047106816475e-05, | |
| "loss": 0.3521, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.0770072244125895e-05, | |
| "loss": 0.3521, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 4.0713097381435314e-05, | |
| "loss": 0.3519, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 4.0656122518744734e-05, | |
| "loss": 0.3517, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.059914765605415e-05, | |
| "loss": 0.3513, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.054217279336357e-05, | |
| "loss": 0.3512, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.0485197930672994e-05, | |
| "loss": 0.351, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.042822306798241e-05, | |
| "loss": 0.351, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 4.037124820529183e-05, | |
| "loss": 0.3505, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 4.0314273342601246e-05, | |
| "loss": 0.3506, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 4.0257298479910666e-05, | |
| "loss": 0.3505, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.0200323617220086e-05, | |
| "loss": 0.3502, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.0143348754529506e-05, | |
| "loss": 0.3502, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 4.0086373891838926e-05, | |
| "loss": 0.3496, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.002939902914834e-05, | |
| "loss": 0.3495, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8936252278700241, | |
| "eval_loss": 0.3322208523750305, | |
| "eval_runtime": 2074.4976, | |
| "eval_samples_per_second": 300.629, | |
| "eval_steps_per_second": 2.349, | |
| "step": 87758 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.997242416645776e-05, | |
| "loss": 0.3493, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.991544930376718e-05, | |
| "loss": 0.3487, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.98584744410766e-05, | |
| "loss": 0.3483, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.980149957838602e-05, | |
| "loss": 0.3483, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.974452471569544e-05, | |
| "loss": 0.3485, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.968754985300486e-05, | |
| "loss": 0.348, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.963057499031427e-05, | |
| "loss": 0.3481, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.95736001276237e-05, | |
| "loss": 0.3477, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.951662526493312e-05, | |
| "loss": 0.3478, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.945965040224253e-05, | |
| "loss": 0.3475, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 3.940267553955195e-05, | |
| "loss": 0.3473, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.934570067686137e-05, | |
| "loss": 0.3472, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.928872581417079e-05, | |
| "loss": 0.3472, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.92317509514802e-05, | |
| "loss": 0.3467, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 3.917477608878963e-05, | |
| "loss": 0.3468, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.911780122609905e-05, | |
| "loss": 0.3468, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.906082636340846e-05, | |
| "loss": 0.3464, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.900385150071789e-05, | |
| "loss": 0.3463, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.89468766380273e-05, | |
| "loss": 0.3463, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.888990177533672e-05, | |
| "loss": 0.346, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.883292691264614e-05, | |
| "loss": 0.3461, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.877595204995556e-05, | |
| "loss": 0.346, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.871897718726498e-05, | |
| "loss": 0.3458, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.8662002324574395e-05, | |
| "loss": 0.3455, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.860502746188382e-05, | |
| "loss": 0.3454, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.8548052599193234e-05, | |
| "loss": 0.3453, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3.8491077736502654e-05, | |
| "loss": 0.345, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 3.843410287381208e-05, | |
| "loss": 0.3446, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.8377128011121494e-05, | |
| "loss": 0.345, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.8320153148430914e-05, | |
| "loss": 0.3451, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 3.8263178285740334e-05, | |
| "loss": 0.3447, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 3.8206203423049753e-05, | |
| "loss": 0.3446, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 3.814922856035917e-05, | |
| "loss": 0.3443, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.8092253697668586e-05, | |
| "loss": 0.3441, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 3.803527883497801e-05, | |
| "loss": 0.3442, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3.7978303972287426e-05, | |
| "loss": 0.3438, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 3.7921329109596846e-05, | |
| "loss": 0.3438, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 3.786435424690627e-05, | |
| "loss": 0.3436, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.7807379384215686e-05, | |
| "loss": 0.3437, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.7750404521525105e-05, | |
| "loss": 0.3437, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.7693429658834525e-05, | |
| "loss": 0.3437, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.7636454796143945e-05, | |
| "loss": 0.3434, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.757947993345336e-05, | |
| "loss": 0.3433, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.752250507076278e-05, | |
| "loss": 0.3429, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.7465530208072205e-05, | |
| "loss": 0.3429, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.740855534538162e-05, | |
| "loss": 0.3425, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.735158048269104e-05, | |
| "loss": 0.3424, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.729460562000046e-05, | |
| "loss": 0.3426, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.723763075730988e-05, | |
| "loss": 0.3428, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.71806558946193e-05, | |
| "loss": 0.3421, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 3.712368103192872e-05, | |
| "loss": 0.3422, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.706670616923814e-05, | |
| "loss": 0.3421, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3.700973130654755e-05, | |
| "loss": 0.3422, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 3.695275644385697e-05, | |
| "loss": 0.342, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.689578158116639e-05, | |
| "loss": 0.342, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 3.683880671847581e-05, | |
| "loss": 0.3418, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.678183185578523e-05, | |
| "loss": 0.3416, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 3.672485699309465e-05, | |
| "loss": 0.3415, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3.666788213040407e-05, | |
| "loss": 0.3413, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.661090726771348e-05, | |
| "loss": 0.3413, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 3.655393240502291e-05, | |
| "loss": 0.3411, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.649695754233233e-05, | |
| "loss": 0.3412, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.643998267964174e-05, | |
| "loss": 0.3407, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 3.638300781695116e-05, | |
| "loss": 0.3409, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 3.632603295426058e-05, | |
| "loss": 0.3408, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 3.626905809157e-05, | |
| "loss": 0.3407, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 3.621208322887942e-05, | |
| "loss": 0.3406, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.615510836618884e-05, | |
| "loss": 0.3405, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 3.609813350349826e-05, | |
| "loss": 0.3402, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.6041158640807674e-05, | |
| "loss": 0.3404, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.59841837781171e-05, | |
| "loss": 0.3398, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.592720891542651e-05, | |
| "loss": 0.34, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.587023405273593e-05, | |
| "loss": 0.34, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.581325919004535e-05, | |
| "loss": 0.3401, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.575628432735477e-05, | |
| "loss": 0.3397, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.569930946466419e-05, | |
| "loss": 0.3397, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 3.564233460197361e-05, | |
| "loss": 0.3395, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 3.558535973928303e-05, | |
| "loss": 0.3395, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.5528384876592445e-05, | |
| "loss": 0.3394, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.5471410013901865e-05, | |
| "loss": 0.3393, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.541443515121129e-05, | |
| "loss": 0.3393, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 3.5357460288520705e-05, | |
| "loss": 0.3389, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.5300485425830125e-05, | |
| "loss": 0.339, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.5243510563139545e-05, | |
| "loss": 0.3388, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.5186535700448964e-05, | |
| "loss": 0.3391, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.5129560837758384e-05, | |
| "loss": 0.3387, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 3.5072585975067804e-05, | |
| "loss": 0.3385, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.5015611112377224e-05, | |
| "loss": 0.3387, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.895863102092376, | |
| "eval_loss": 0.32395124435424805, | |
| "eval_runtime": 2074.0434, | |
| "eval_samples_per_second": 300.695, | |
| "eval_steps_per_second": 2.35, | |
| "step": 131637 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.495863624968664e-05, | |
| "loss": 0.3379, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.490166138699606e-05, | |
| "loss": 0.3377, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.484468652430548e-05, | |
| "loss": 0.338, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.4787711661614896e-05, | |
| "loss": 0.3379, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.4730736798924316e-05, | |
| "loss": 0.3373, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.4673761936233736e-05, | |
| "loss": 0.3376, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.4616787073543156e-05, | |
| "loss": 0.3375, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.455981221085257e-05, | |
| "loss": 0.3375, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.4502837348161996e-05, | |
| "loss": 0.3371, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.4445862485471416e-05, | |
| "loss": 0.3374, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.438888762278083e-05, | |
| "loss": 0.337, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.433191276009025e-05, | |
| "loss": 0.3372, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 3.427493789739967e-05, | |
| "loss": 0.3371, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.421796303470909e-05, | |
| "loss": 0.3365, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 3.41609881720185e-05, | |
| "loss": 0.3366, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.410401330932793e-05, | |
| "loss": 0.3365, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 3.404703844663735e-05, | |
| "loss": 0.337, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.399006358394676e-05, | |
| "loss": 0.3367, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.393308872125619e-05, | |
| "loss": 0.3365, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.38761138585656e-05, | |
| "loss": 0.3365, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.381913899587502e-05, | |
| "loss": 0.3366, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.376216413318444e-05, | |
| "loss": 0.3362, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.370518927049386e-05, | |
| "loss": 0.3363, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.364821440780328e-05, | |
| "loss": 0.336, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 3.359123954511269e-05, | |
| "loss": 0.336, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 3.353426468242212e-05, | |
| "loss": 0.336, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.347728981973154e-05, | |
| "loss": 0.3359, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.342031495704095e-05, | |
| "loss": 0.3357, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.336334009435038e-05, | |
| "loss": 0.3359, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 3.330636523165979e-05, | |
| "loss": 0.3358, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.324939036896921e-05, | |
| "loss": 0.3356, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.319241550627863e-05, | |
| "loss": 0.3356, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.313544064358805e-05, | |
| "loss": 0.3358, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.307846578089747e-05, | |
| "loss": 0.3354, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 3.3021490918206884e-05, | |
| "loss": 0.3355, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.296451605551631e-05, | |
| "loss": 0.3355, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 3.2907541192825724e-05, | |
| "loss": 0.3354, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 3.2850566330135144e-05, | |
| "loss": 0.3352, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 3.279359146744457e-05, | |
| "loss": 0.3355, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.2736616604753984e-05, | |
| "loss": 0.3351, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 3.2679641742063403e-05, | |
| "loss": 0.3351, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 3.262266687937282e-05, | |
| "loss": 0.3346, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 3.256569201668224e-05, | |
| "loss": 0.3349, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 3.2508717153991656e-05, | |
| "loss": 0.3349, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 3.2451742291301076e-05, | |
| "loss": 0.3348, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 3.23947674286105e-05, | |
| "loss": 0.3346, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.2337792565919916e-05, | |
| "loss": 0.3344, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 3.2280817703229336e-05, | |
| "loss": 0.3346, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 3.2223842840538755e-05, | |
| "loss": 0.3346, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.2166867977848175e-05, | |
| "loss": 0.3346, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 3.2109893115157595e-05, | |
| "loss": 0.3347, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 3.2052918252467015e-05, | |
| "loss": 0.3344, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 3.1995943389776435e-05, | |
| "loss": 0.3341, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.193896852708585e-05, | |
| "loss": 0.334, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 3.188199366439527e-05, | |
| "loss": 0.3342, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 3.182501880170469e-05, | |
| "loss": 0.3337, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 3.176804393901411e-05, | |
| "loss": 0.3339, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 3.171106907632353e-05, | |
| "loss": 0.334, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 3.165409421363295e-05, | |
| "loss": 0.3337, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 3.159711935094237e-05, | |
| "loss": 0.334, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.154014448825178e-05, | |
| "loss": 0.3337, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 3.1483169625561207e-05, | |
| "loss": 0.3334, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 3.1426194762870626e-05, | |
| "loss": 0.3333, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.136921990018004e-05, | |
| "loss": 0.3336, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 3.1312245037489466e-05, | |
| "loss": 0.3332, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.125527017479888e-05, | |
| "loss": 0.3334, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 3.11982953121083e-05, | |
| "loss": 0.3332, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 3.114132044941772e-05, | |
| "loss": 0.3334, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 3.108434558672714e-05, | |
| "loss": 0.3333, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 3.102737072403656e-05, | |
| "loss": 0.3331, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.097039586134597e-05, | |
| "loss": 0.3327, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 3.09134209986554e-05, | |
| "loss": 0.3331, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 3.085644613596481e-05, | |
| "loss": 0.3329, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.079947127327423e-05, | |
| "loss": 0.333, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 3.074249641058366e-05, | |
| "loss": 0.3328, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 3.068552154789307e-05, | |
| "loss": 0.3328, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 3.062854668520249e-05, | |
| "loss": 0.3327, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 3.057157182251191e-05, | |
| "loss": 0.3329, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 3.051459695982133e-05, | |
| "loss": 0.3323, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.0457622097130743e-05, | |
| "loss": 0.3325, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.0400647234440167e-05, | |
| "loss": 0.3327, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.0343672371749586e-05, | |
| "loss": 0.3325, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 3.0286697509059003e-05, | |
| "loss": 0.3327, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 3.0229722646368426e-05, | |
| "loss": 0.3323, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 3.017274778367784e-05, | |
| "loss": 0.3322, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.0115772920987262e-05, | |
| "loss": 0.3325, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 3.0058798058296682e-05, | |
| "loss": 0.3323, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.00018231956061e-05, | |
| "loss": 0.3322, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.89709477182372, | |
| "eval_loss": 0.3193678855895996, | |
| "eval_runtime": 2084.1738, | |
| "eval_samples_per_second": 299.234, | |
| "eval_steps_per_second": 2.338, | |
| "step": 175516 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 2.9944848332915522e-05, | |
| "loss": 0.3314, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 2.9887873470224935e-05, | |
| "loss": 0.3315, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.9830898607534358e-05, | |
| "loss": 0.3314, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 2.9773923744843778e-05, | |
| "loss": 0.3314, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.9716948882153194e-05, | |
| "loss": 0.3315, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 2.9659974019462618e-05, | |
| "loss": 0.3314, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 2.960299915677203e-05, | |
| "loss": 0.3313, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.9546024294081454e-05, | |
| "loss": 0.331, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.948904943139087e-05, | |
| "loss": 0.3313, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 2.943207456870029e-05, | |
| "loss": 0.3309, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 2.9375099706009714e-05, | |
| "loss": 0.3312, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 2.9318124843319127e-05, | |
| "loss": 0.3308, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 2.926114998062855e-05, | |
| "loss": 0.331, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 2.9204175117937966e-05, | |
| "loss": 0.3313, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 2.9147200255247386e-05, | |
| "loss": 0.3308, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 2.909022539255681e-05, | |
| "loss": 0.3311, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 2.9033250529866222e-05, | |
| "loss": 0.3306, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 2.8976275667175646e-05, | |
| "loss": 0.3308, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 2.8919300804485062e-05, | |
| "loss": 0.331, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 2.8862325941794482e-05, | |
| "loss": 0.3307, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 2.88053510791039e-05, | |
| "loss": 0.3305, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 2.8748376216413318e-05, | |
| "loss": 0.3304, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 2.869140135372274e-05, | |
| "loss": 0.3307, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 2.8634426491032158e-05, | |
| "loss": 0.3305, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 2.8577451628341578e-05, | |
| "loss": 0.3307, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 2.8520476765650994e-05, | |
| "loss": 0.3305, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 2.8463501902960414e-05, | |
| "loss": 0.3304, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 2.8406527040269837e-05, | |
| "loss": 0.3306, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 2.8349552177579254e-05, | |
| "loss": 0.3304, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 2.8292577314888674e-05, | |
| "loss": 0.33, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.823560245219809e-05, | |
| "loss": 0.3304, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 2.817862758950751e-05, | |
| "loss": 0.33, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 2.8121652726816926e-05, | |
| "loss": 0.3302, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 2.806467786412635e-05, | |
| "loss": 0.3301, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 2.800770300143577e-05, | |
| "loss": 0.33, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 2.7950728138745186e-05, | |
| "loss": 0.3299, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 2.7893753276054606e-05, | |
| "loss": 0.3299, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.7836778413364022e-05, | |
| "loss": 0.3299, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 2.7779803550673445e-05, | |
| "loss": 0.3295, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.7722828687982865e-05, | |
| "loss": 0.3298, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 2.766585382529228e-05, | |
| "loss": 0.3296, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 2.76088789626017e-05, | |
| "loss": 0.3296, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 2.7551904099911118e-05, | |
| "loss": 0.3294, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.749492923722054e-05, | |
| "loss": 0.3297, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.7437954374529958e-05, | |
| "loss": 0.3294, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 2.7380979511839377e-05, | |
| "loss": 0.3296, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 2.7324004649148797e-05, | |
| "loss": 0.3296, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 2.7267029786458214e-05, | |
| "loss": 0.3292, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 2.7210054923767637e-05, | |
| "loss": 0.3294, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2.7153080061077053e-05, | |
| "loss": 0.3293, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.7096105198386473e-05, | |
| "loss": 0.3295, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.7039130335695893e-05, | |
| "loss": 0.3293, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.698215547300531e-05, | |
| "loss": 0.3294, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.6925180610314733e-05, | |
| "loss": 0.3292, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.686820574762415e-05, | |
| "loss": 0.329, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.681123088493357e-05, | |
| "loss": 0.3293, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.6754256022242986e-05, | |
| "loss": 0.3293, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.6697281159552405e-05, | |
| "loss": 0.3292, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.664030629686183e-05, | |
| "loss": 0.3291, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.6583331434171245e-05, | |
| "loss": 0.329, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.6526356571480665e-05, | |
| "loss": 0.329, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 2.646938170879008e-05, | |
| "loss": 0.3291, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.64124068460995e-05, | |
| "loss": 0.3289, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.6355431983408924e-05, | |
| "loss": 0.3284, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.629845712071834e-05, | |
| "loss": 0.3287, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.624148225802776e-05, | |
| "loss": 0.3288, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.6184507395337177e-05, | |
| "loss": 0.3293, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.6127532532646597e-05, | |
| "loss": 0.3286, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.6070557669956013e-05, | |
| "loss": 0.3288, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.6013582807265437e-05, | |
| "loss": 0.3287, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.5956607944574857e-05, | |
| "loss": 0.3286, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 2.5899633081884273e-05, | |
| "loss": 0.3283, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.5842658219193693e-05, | |
| "loss": 0.3285, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.578568335650311e-05, | |
| "loss": 0.3285, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.5728708493812532e-05, | |
| "loss": 0.3287, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 2.5671733631121952e-05, | |
| "loss": 0.3281, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 2.561475876843137e-05, | |
| "loss": 0.3283, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.555778390574079e-05, | |
| "loss": 0.3282, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.5500809043050205e-05, | |
| "loss": 0.3285, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 2.5443834180359628e-05, | |
| "loss": 0.3284, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 2.5386859317669048e-05, | |
| "loss": 0.328, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.5329884454978465e-05, | |
| "loss": 0.3282, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 2.5272909592287884e-05, | |
| "loss": 0.3283, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 2.52159347295973e-05, | |
| "loss": 0.3281, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 2.5158959866906724e-05, | |
| "loss": 0.3279, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 2.5101985004216137e-05, | |
| "loss": 0.3278, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 2.504501014152556e-05, | |
| "loss": 0.3279, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8978495640426417, | |
| "eval_loss": 0.316384881734848, | |
| "eval_runtime": 2067.9229, | |
| "eval_samples_per_second": 301.585, | |
| "eval_steps_per_second": 2.356, | |
| "step": 219395 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.498803527883498e-05, | |
| "loss": 0.3278, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2.4931060416144397e-05, | |
| "loss": 0.3272, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 2.487408555345382e-05, | |
| "loss": 0.3273, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.4817110690763236e-05, | |
| "loss": 0.3274, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 2.4760135828072656e-05, | |
| "loss": 0.3274, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.4703160965382076e-05, | |
| "loss": 0.3271, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.4646186102691493e-05, | |
| "loss": 0.3275, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 2.4589211240000912e-05, | |
| "loss": 0.3271, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.4532236377310332e-05, | |
| "loss": 0.3269, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 2.4475261514619752e-05, | |
| "loss": 0.3272, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.4418286651929172e-05, | |
| "loss": 0.3272, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2.436131178923859e-05, | |
| "loss": 0.327, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.4304336926548008e-05, | |
| "loss": 0.3271, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 2.4247362063857425e-05, | |
| "loss": 0.3271, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.4190387201166848e-05, | |
| "loss": 0.3271, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.4133412338476268e-05, | |
| "loss": 0.327, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.4076437475785684e-05, | |
| "loss": 0.3267, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 2.4019462613095104e-05, | |
| "loss": 0.3266, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.396248775040452e-05, | |
| "loss": 0.3269, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 2.390551288771394e-05, | |
| "loss": 0.327, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 2.3848538025023363e-05, | |
| "loss": 0.3271, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.379156316233278e-05, | |
| "loss": 0.3267, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 2.37345882996422e-05, | |
| "loss": 0.3269, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.3677613436951616e-05, | |
| "loss": 0.3269, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 2.3620638574261036e-05, | |
| "loss": 0.3267, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.3563663711570456e-05, | |
| "loss": 0.3266, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.3506688848879876e-05, | |
| "loss": 0.3265, | |
| "step": 232500 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 2.3449713986189296e-05, | |
| "loss": 0.3265, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 2.3392739123498712e-05, | |
| "loss": 0.3265, | |
| "step": 233500 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 2.3335764260808132e-05, | |
| "loss": 0.3264, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.3278789398117552e-05, | |
| "loss": 0.3265, | |
| "step": 234500 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 2.3221814535426968e-05, | |
| "loss": 0.3267, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.316483967273639e-05, | |
| "loss": 0.3263, | |
| "step": 235500 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 2.3107864810045808e-05, | |
| "loss": 0.3261, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 2.3050889947355228e-05, | |
| "loss": 0.3265, | |
| "step": 236500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.2993915084664648e-05, | |
| "loss": 0.3262, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 2.2936940221974064e-05, | |
| "loss": 0.3267, | |
| "step": 237500 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.2879965359283484e-05, | |
| "loss": 0.3261, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 2.2822990496592904e-05, | |
| "loss": 0.3265, | |
| "step": 238500 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 2.2766015633902324e-05, | |
| "loss": 0.3263, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 2.2709040771211743e-05, | |
| "loss": 0.3263, | |
| "step": 239500 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 2.265206590852116e-05, | |
| "loss": 0.326, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 2.259509104583058e-05, | |
| "loss": 0.3258, | |
| "step": 240500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 2.253811618314e-05, | |
| "loss": 0.3259, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 2.248114132044942e-05, | |
| "loss": 0.3261, | |
| "step": 241500 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 2.242416645775884e-05, | |
| "loss": 0.3261, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 2.2367191595068256e-05, | |
| "loss": 0.3262, | |
| "step": 242500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.2310216732377675e-05, | |
| "loss": 0.326, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 2.2253241869687095e-05, | |
| "loss": 0.3262, | |
| "step": 243500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 2.2196267006996512e-05, | |
| "loss": 0.326, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.2139292144305935e-05, | |
| "loss": 0.326, | |
| "step": 244500 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 2.208231728161535e-05, | |
| "loss": 0.3261, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 2.202534241892477e-05, | |
| "loss": 0.3257, | |
| "step": 245500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 2.196836755623419e-05, | |
| "loss": 0.3258, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 2.1911392693543608e-05, | |
| "loss": 0.3256, | |
| "step": 246500 | |
| }, | |
| { | |
| "epoch": 5.63, | |
| "learning_rate": 2.185441783085303e-05, | |
| "loss": 0.3256, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 2.1797442968162447e-05, | |
| "loss": 0.326, | |
| "step": 247500 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 2.1740468105471867e-05, | |
| "loss": 0.3259, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.1683493242781287e-05, | |
| "loss": 0.3257, | |
| "step": 248500 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 2.1626518380090703e-05, | |
| "loss": 0.3259, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 2.1569543517400123e-05, | |
| "loss": 0.3258, | |
| "step": 249500 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 2.1512568654709543e-05, | |
| "loss": 0.3258, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.1455593792018963e-05, | |
| "loss": 0.3259, | |
| "step": 250500 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 2.1398618929328383e-05, | |
| "loss": 0.3255, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 2.13416440666378e-05, | |
| "loss": 0.3261, | |
| "step": 251500 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.128466920394722e-05, | |
| "loss": 0.3256, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 2.122769434125664e-05, | |
| "loss": 0.3255, | |
| "step": 252500 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 2.117071947856606e-05, | |
| "loss": 0.3255, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 2.111374461587548e-05, | |
| "loss": 0.3256, | |
| "step": 253500 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 2.1056769753184895e-05, | |
| "loss": 0.3252, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 2.0999794890494315e-05, | |
| "loss": 0.3254, | |
| "step": 254500 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 2.0942820027803735e-05, | |
| "loss": 0.325, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 2.088584516511315e-05, | |
| "loss": 0.3252, | |
| "step": 255500 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 2.0828870302422574e-05, | |
| "loss": 0.3255, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 2.077189543973199e-05, | |
| "loss": 0.3254, | |
| "step": 256500 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 2.071492057704141e-05, | |
| "loss": 0.3254, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 2.065794571435083e-05, | |
| "loss": 0.325, | |
| "step": 257500 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 2.0600970851660247e-05, | |
| "loss": 0.3251, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 2.0543995988969667e-05, | |
| "loss": 0.3253, | |
| "step": 258500 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 2.0487021126279087e-05, | |
| "loss": 0.3254, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2.0430046263588506e-05, | |
| "loss": 0.325, | |
| "step": 259500 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.0373071400897926e-05, | |
| "loss": 0.3251, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 2.0316096538207343e-05, | |
| "loss": 0.3249, | |
| "step": 260500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 2.0259121675516763e-05, | |
| "loss": 0.3251, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 2.0202146812826182e-05, | |
| "loss": 0.3253, | |
| "step": 261500 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 2.0145171950135602e-05, | |
| "loss": 0.3249, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 2.0088197087445022e-05, | |
| "loss": 0.325, | |
| "step": 262500 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 2.003122222475444e-05, | |
| "loss": 0.325, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.898475571876863, | |
| "eval_loss": 0.3140411376953125, | |
| "eval_runtime": 2079.426, | |
| "eval_samples_per_second": 299.917, | |
| "eval_steps_per_second": 2.343, | |
| "step": 263274 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.997424736206386e-05, | |
| "loss": 0.325, | |
| "step": 263500 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 1.9917272499373278e-05, | |
| "loss": 0.3246, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 1.9860297636682695e-05, | |
| "loss": 0.3245, | |
| "step": 264500 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.9803322773992118e-05, | |
| "loss": 0.3244, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1.9746347911301534e-05, | |
| "loss": 0.3246, | |
| "step": 265500 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 1.9689373048610954e-05, | |
| "loss": 0.3245, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.9632398185920374e-05, | |
| "loss": 0.3244, | |
| "step": 266500 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.957542332322979e-05, | |
| "loss": 0.3244, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 1.951844846053921e-05, | |
| "loss": 0.3242, | |
| "step": 267500 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 1.946147359784863e-05, | |
| "loss": 0.3244, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 1.940449873515805e-05, | |
| "loss": 0.324, | |
| "step": 268500 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1.934752387246747e-05, | |
| "loss": 0.3241, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 1.9290549009776886e-05, | |
| "loss": 0.3242, | |
| "step": 269500 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 1.9233574147086306e-05, | |
| "loss": 0.3244, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.9176599284395723e-05, | |
| "loss": 0.3241, | |
| "step": 270500 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 1.9119624421705146e-05, | |
| "loss": 0.3244, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 1.9062649559014566e-05, | |
| "loss": 0.3239, | |
| "step": 271500 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 1.9005674696323982e-05, | |
| "loss": 0.3243, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 1.8948699833633402e-05, | |
| "loss": 0.3243, | |
| "step": 272500 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 1.889172497094282e-05, | |
| "loss": 0.3244, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 1.8834750108252238e-05, | |
| "loss": 0.3237, | |
| "step": 273500 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 1.877777524556166e-05, | |
| "loss": 0.324, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 1.8720800382871078e-05, | |
| "loss": 0.324, | |
| "step": 274500 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 1.8663825520180498e-05, | |
| "loss": 0.3239, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "learning_rate": 1.8606850657489914e-05, | |
| "loss": 0.3239, | |
| "step": 275500 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 1.8549875794799334e-05, | |
| "loss": 0.3241, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 1.8492900932108754e-05, | |
| "loss": 0.3239, | |
| "step": 276500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 1.8435926069418174e-05, | |
| "loss": 0.3242, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 1.8378951206727594e-05, | |
| "loss": 0.3239, | |
| "step": 277500 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 1.8321976344037013e-05, | |
| "loss": 0.3239, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 1.826500148134643e-05, | |
| "loss": 0.3236, | |
| "step": 278500 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 1.820802661865585e-05, | |
| "loss": 0.3239, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 1.8151051755965266e-05, | |
| "loss": 0.3237, | |
| "step": 279500 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 1.809407689327469e-05, | |
| "loss": 0.3241, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 1.803710203058411e-05, | |
| "loss": 0.324, | |
| "step": 280500 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.7980127167893526e-05, | |
| "loss": 0.3239, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.7923152305202946e-05, | |
| "loss": 0.3235, | |
| "step": 281500 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.7866177442512362e-05, | |
| "loss": 0.3238, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 1.7809202579821785e-05, | |
| "loss": 0.3237, | |
| "step": 282500 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 1.7752227717131205e-05, | |
| "loss": 0.3235, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 1.769525285444062e-05, | |
| "loss": 0.3237, | |
| "step": 283500 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 1.763827799175004e-05, | |
| "loss": 0.3239, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 1.7581303129059458e-05, | |
| "loss": 0.3237, | |
| "step": 284500 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 1.7524328266368878e-05, | |
| "loss": 0.3234, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.74673534036783e-05, | |
| "loss": 0.3236, | |
| "step": 285500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 1.7410378540987717e-05, | |
| "loss": 0.3236, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.7353403678297137e-05, | |
| "loss": 0.3235, | |
| "step": 286500 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 1.7296428815606554e-05, | |
| "loss": 0.3239, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.7239453952915973e-05, | |
| "loss": 0.3236, | |
| "step": 287500 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 1.7182479090225393e-05, | |
| "loss": 0.3235, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.7125504227534813e-05, | |
| "loss": 0.3233, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 1.7068529364844233e-05, | |
| "loss": 0.3235, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 1.701155450215365e-05, | |
| "loss": 0.3234, | |
| "step": 289500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 1.695457963946307e-05, | |
| "loss": 0.3236, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 1.689760477677249e-05, | |
| "loss": 0.323, | |
| "step": 290500 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 1.6840629914081906e-05, | |
| "loss": 0.3234, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 1.678365505139133e-05, | |
| "loss": 0.3233, | |
| "step": 291500 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.6726680188700745e-05, | |
| "loss": 0.3235, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 1.6669705326010165e-05, | |
| "loss": 0.323, | |
| "step": 292500 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 1.6612730463319585e-05, | |
| "loss": 0.3232, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 1.6555755600629e-05, | |
| "loss": 0.323, | |
| "step": 293500 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.649878073793842e-05, | |
| "loss": 0.3234, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 1.644180587524784e-05, | |
| "loss": 0.3234, | |
| "step": 294500 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 1.638483101255726e-05, | |
| "loss": 0.3231, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 1.632785614986668e-05, | |
| "loss": 0.3229, | |
| "step": 295500 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.6270881287176097e-05, | |
| "loss": 0.3231, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.6213906424485517e-05, | |
| "loss": 0.3231, | |
| "step": 296500 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 1.6156931561794937e-05, | |
| "loss": 0.3233, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 1.6099956699104357e-05, | |
| "loss": 0.3232, | |
| "step": 297500 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 1.6042981836413777e-05, | |
| "loss": 0.3233, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 1.5986006973723193e-05, | |
| "loss": 0.3228, | |
| "step": 298500 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 1.5929032111032613e-05, | |
| "loss": 0.3231, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.5872057248342033e-05, | |
| "loss": 0.3231, | |
| "step": 299500 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 1.581508238565145e-05, | |
| "loss": 0.323, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.5758107522960872e-05, | |
| "loss": 0.3229, | |
| "step": 300500 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "learning_rate": 1.570113266027029e-05, | |
| "loss": 0.323, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.564415779757971e-05, | |
| "loss": 0.3233, | |
| "step": 301500 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.558718293488913e-05, | |
| "loss": 0.323, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 1.5530208072198545e-05, | |
| "loss": 0.3231, | |
| "step": 302500 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 1.5473233209507965e-05, | |
| "loss": 0.323, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.5416258346817385e-05, | |
| "loss": 0.3231, | |
| "step": 303500 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 1.5359283484126805e-05, | |
| "loss": 0.3228, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.5302308621436224e-05, | |
| "loss": 0.3226, | |
| "step": 304500 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 1.5245333758745642e-05, | |
| "loss": 0.3227, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 1.518835889605506e-05, | |
| "loss": 0.3229, | |
| "step": 305500 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 1.5131384033364479e-05, | |
| "loss": 0.3226, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.50744091706739e-05, | |
| "loss": 0.323, | |
| "step": 306500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.5017434307983318e-05, | |
| "loss": 0.3231, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8988519434723721, | |
| "eval_loss": 0.3124924600124359, | |
| "eval_runtime": 2069.7931, | |
| "eval_samples_per_second": 301.313, | |
| "eval_steps_per_second": 2.354, | |
| "step": 307153 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.4960459445292738e-05, | |
| "loss": 0.3223, | |
| "step": 307500 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 1.4903484582602156e-05, | |
| "loss": 0.3218, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.4846509719911575e-05, | |
| "loss": 0.3223, | |
| "step": 308500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 1.4789534857220993e-05, | |
| "loss": 0.3227, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.4732559994530414e-05, | |
| "loss": 0.3221, | |
| "step": 309500 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 1.4675585131839834e-05, | |
| "loss": 0.3224, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.4618610269149252e-05, | |
| "loss": 0.3224, | |
| "step": 310500 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 1.456163540645867e-05, | |
| "loss": 0.3223, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.4504660543768089e-05, | |
| "loss": 0.3223, | |
| "step": 311500 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 1.4447685681077508e-05, | |
| "loss": 0.322, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 1.439071081838693e-05, | |
| "loss": 0.3219, | |
| "step": 312500 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 1.4333735955696348e-05, | |
| "loss": 0.322, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.4276761093005766e-05, | |
| "loss": 0.3222, | |
| "step": 313500 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.4219786230315184e-05, | |
| "loss": 0.3223, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 1.4162811367624604e-05, | |
| "loss": 0.3223, | |
| "step": 314500 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 1.4105836504934022e-05, | |
| "loss": 0.3219, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.4048861642243444e-05, | |
| "loss": 0.3223, | |
| "step": 315500 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.3991886779552862e-05, | |
| "loss": 0.3223, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 1.3934911916862282e-05, | |
| "loss": 0.3221, | |
| "step": 316500 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.38779370541717e-05, | |
| "loss": 0.3222, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 1.3820962191481118e-05, | |
| "loss": 0.3222, | |
| "step": 317500 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.376398732879054e-05, | |
| "loss": 0.322, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 1.3707012466099958e-05, | |
| "loss": 0.322, | |
| "step": 318500 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 1.3650037603409378e-05, | |
| "loss": 0.3221, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 1.3593062740718796e-05, | |
| "loss": 0.3219, | |
| "step": 319500 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 1.3536087878028214e-05, | |
| "loss": 0.3222, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.3479113015337632e-05, | |
| "loss": 0.3217, | |
| "step": 320500 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.3422138152647054e-05, | |
| "loss": 0.322, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 1.3365163289956474e-05, | |
| "loss": 0.3219, | |
| "step": 321500 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 1.3308188427265892e-05, | |
| "loss": 0.3219, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.325121356457531e-05, | |
| "loss": 0.3218, | |
| "step": 322500 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.3194238701884728e-05, | |
| "loss": 0.3219, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 1.3137263839194148e-05, | |
| "loss": 0.3221, | |
| "step": 323500 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 1.308028897650357e-05, | |
| "loss": 0.3216, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 1.3023314113812987e-05, | |
| "loss": 0.3219, | |
| "step": 324500 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.2966339251122406e-05, | |
| "loss": 0.3219, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 1.2909364388431824e-05, | |
| "loss": 0.3221, | |
| "step": 325500 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 1.2852389525741244e-05, | |
| "loss": 0.3223, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.2795414663050662e-05, | |
| "loss": 0.3217, | |
| "step": 326500 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 1.2738439800360083e-05, | |
| "loss": 0.3215, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1.2681464937669501e-05, | |
| "loss": 0.3219, | |
| "step": 327500 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 1.262449007497892e-05, | |
| "loss": 0.3216, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.256751521228834e-05, | |
| "loss": 0.3218, | |
| "step": 328500 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.2510540349597758e-05, | |
| "loss": 0.3216, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 1.2453565486907177e-05, | |
| "loss": 0.3218, | |
| "step": 329500 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 1.2396590624216596e-05, | |
| "loss": 0.3219, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.2339615761526015e-05, | |
| "loss": 0.3218, | |
| "step": 330500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 1.2282640898835435e-05, | |
| "loss": 0.3218, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 1.2225666036144853e-05, | |
| "loss": 0.3214, | |
| "step": 331500 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.2168691173454272e-05, | |
| "loss": 0.3218, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 1.2111716310763691e-05, | |
| "loss": 0.3217, | |
| "step": 332500 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.2054741448073111e-05, | |
| "loss": 0.3217, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 1.199776658538253e-05, | |
| "loss": 0.3215, | |
| "step": 333500 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.194079172269195e-05, | |
| "loss": 0.3216, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.1883816860001367e-05, | |
| "loss": 0.3217, | |
| "step": 334500 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.1826841997310787e-05, | |
| "loss": 0.3217, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 1.1769867134620207e-05, | |
| "loss": 0.3216, | |
| "step": 335500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.1712892271929625e-05, | |
| "loss": 0.3218, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.1655917409239045e-05, | |
| "loss": 0.3216, | |
| "step": 336500 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.1598942546548463e-05, | |
| "loss": 0.3215, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 1.1541967683857883e-05, | |
| "loss": 0.3216, | |
| "step": 337500 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 1.1484992821167303e-05, | |
| "loss": 0.3215, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.1428017958476721e-05, | |
| "loss": 0.3217, | |
| "step": 338500 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 1.1371043095786139e-05, | |
| "loss": 0.3216, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.1314068233095559e-05, | |
| "loss": 0.3214, | |
| "step": 339500 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.1257093370404979e-05, | |
| "loss": 0.3215, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 1.1200118507714397e-05, | |
| "loss": 0.3215, | |
| "step": 340500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 1.1143143645023817e-05, | |
| "loss": 0.3214, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 1.1086168782333235e-05, | |
| "loss": 0.3216, | |
| "step": 341500 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.1029193919642653e-05, | |
| "loss": 0.3215, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 1.0972219056952075e-05, | |
| "loss": 0.3214, | |
| "step": 342500 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 1.0915244194261493e-05, | |
| "loss": 0.3213, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.0858269331570911e-05, | |
| "loss": 0.3216, | |
| "step": 343500 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.080129446888033e-05, | |
| "loss": 0.3212, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 1.0744319606189749e-05, | |
| "loss": 0.3212, | |
| "step": 344500 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 1.0687344743499169e-05, | |
| "loss": 0.3213, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 1.0630369880808589e-05, | |
| "loss": 0.3214, | |
| "step": 345500 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 1.0573395018118007e-05, | |
| "loss": 0.3213, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 1.0516420155427425e-05, | |
| "loss": 0.3213, | |
| "step": 346500 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 1.0459445292736845e-05, | |
| "loss": 0.3214, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.0402470430046265e-05, | |
| "loss": 0.3209, | |
| "step": 347500 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 1.0345495567355683e-05, | |
| "loss": 0.3212, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 1.0288520704665103e-05, | |
| "loss": 0.3212, | |
| "step": 348500 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.023154584197452e-05, | |
| "loss": 0.3215, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.017457097928394e-05, | |
| "loss": 0.3213, | |
| "step": 349500 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 1.011759611659336e-05, | |
| "loss": 0.3213, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 1.0060621253902779e-05, | |
| "loss": 0.3214, | |
| "step": 350500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.0003646391212197e-05, | |
| "loss": 0.3213, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8991522939361593, | |
| "eval_loss": 0.311366468667984, | |
| "eval_runtime": 2069.0743, | |
| "eval_samples_per_second": 301.417, | |
| "eval_steps_per_second": 2.355, | |
| "step": 351032 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.946671528521616e-06, | |
| "loss": 0.3208, | |
| "step": 351500 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.889696665831036e-06, | |
| "loss": 0.3207, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 9.832721803140454e-06, | |
| "loss": 0.3207, | |
| "step": 352500 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 9.775746940449874e-06, | |
| "loss": 0.3206, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 9.718772077759292e-06, | |
| "loss": 0.3205, | |
| "step": 353500 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.661797215068712e-06, | |
| "loss": 0.3208, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 9.604822352378132e-06, | |
| "loss": 0.3205, | |
| "step": 354500 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 9.54784748968755e-06, | |
| "loss": 0.3207, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 9.490872626996968e-06, | |
| "loss": 0.3208, | |
| "step": 355500 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 9.433897764306388e-06, | |
| "loss": 0.321, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.376922901615808e-06, | |
| "loss": 0.3207, | |
| "step": 356500 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 9.319948038925226e-06, | |
| "loss": 0.3209, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 9.262973176234646e-06, | |
| "loss": 0.3208, | |
| "step": 357500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 9.205998313544064e-06, | |
| "loss": 0.3204, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 9.149023450853484e-06, | |
| "loss": 0.3208, | |
| "step": 358500 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 9.092048588162904e-06, | |
| "loss": 0.3208, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 9.035073725472322e-06, | |
| "loss": 0.3206, | |
| "step": 359500 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 8.97809886278174e-06, | |
| "loss": 0.3207, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 8.92112400009116e-06, | |
| "loss": 0.3207, | |
| "step": 360500 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 8.86414913740058e-06, | |
| "loss": 0.3205, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 8.807174274709998e-06, | |
| "loss": 0.3205, | |
| "step": 361500 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 8.750199412019418e-06, | |
| "loss": 0.3208, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 8.693224549328836e-06, | |
| "loss": 0.3205, | |
| "step": 362500 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 8.636249686638254e-06, | |
| "loss": 0.3207, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 8.579274823947676e-06, | |
| "loss": 0.3204, | |
| "step": 363500 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 8.522299961257094e-06, | |
| "loss": 0.3209, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 8.465325098566512e-06, | |
| "loss": 0.3205, | |
| "step": 364500 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.408350235875932e-06, | |
| "loss": 0.3206, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 8.351375373185352e-06, | |
| "loss": 0.3206, | |
| "step": 365500 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 8.29440051049477e-06, | |
| "loss": 0.3208, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 8.23742564780419e-06, | |
| "loss": 0.3204, | |
| "step": 366500 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 8.180450785113608e-06, | |
| "loss": 0.3207, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 8.38, | |
| "learning_rate": 8.123475922423026e-06, | |
| "loss": 0.3207, | |
| "step": 367500 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 8.066501059732448e-06, | |
| "loss": 0.3205, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 8.009526197041866e-06, | |
| "loss": 0.3206, | |
| "step": 368500 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 7.952551334351284e-06, | |
| "loss": 0.3201, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 7.895576471660704e-06, | |
| "loss": 0.3205, | |
| "step": 369500 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 7.838601608970122e-06, | |
| "loss": 0.3206, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 7.781626746279543e-06, | |
| "loss": 0.3208, | |
| "step": 370500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 7.724651883588961e-06, | |
| "loss": 0.3203, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 7.66767702089838e-06, | |
| "loss": 0.3204, | |
| "step": 371500 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.6107021582077994e-06, | |
| "loss": 0.3206, | |
| "step": 372000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 7.5537272955172184e-06, | |
| "loss": 0.3206, | |
| "step": 372500 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 7.496752432826637e-06, | |
| "loss": 0.3204, | |
| "step": 373000 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 7.439777570136057e-06, | |
| "loss": 0.3203, | |
| "step": 373500 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 7.382802707445475e-06, | |
| "loss": 0.3206, | |
| "step": 374000 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 7.325827844754894e-06, | |
| "loss": 0.3205, | |
| "step": 374500 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 7.268852982064314e-06, | |
| "loss": 0.3202, | |
| "step": 375000 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 7.211878119373732e-06, | |
| "loss": 0.3203, | |
| "step": 375500 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 7.154903256683151e-06, | |
| "loss": 0.3206, | |
| "step": 376000 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.097928393992571e-06, | |
| "loss": 0.3201, | |
| "step": 376500 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 7.04095353130199e-06, | |
| "loss": 0.3204, | |
| "step": 377000 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 6.983978668611408e-06, | |
| "loss": 0.3206, | |
| "step": 377500 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 6.927003805920829e-06, | |
| "loss": 0.3204, | |
| "step": 378000 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 6.870028943230247e-06, | |
| "loss": 0.3204, | |
| "step": 378500 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 6.813054080539666e-06, | |
| "loss": 0.3205, | |
| "step": 379000 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 6.756079217849086e-06, | |
| "loss": 0.3202, | |
| "step": 379500 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 6.699104355158504e-06, | |
| "loss": 0.3205, | |
| "step": 380000 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 6.642129492467923e-06, | |
| "loss": 0.3205, | |
| "step": 380500 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 6.585154629777343e-06, | |
| "loss": 0.3204, | |
| "step": 381000 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 6.528179767086762e-06, | |
| "loss": 0.3204, | |
| "step": 381500 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 6.47120490439618e-06, | |
| "loss": 0.3203, | |
| "step": 382000 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 6.4142300417056e-06, | |
| "loss": 0.3202, | |
| "step": 382500 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 6.357255179015019e-06, | |
| "loss": 0.3205, | |
| "step": 383000 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 6.300280316324437e-06, | |
| "loss": 0.3204, | |
| "step": 383500 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 6.243305453633857e-06, | |
| "loss": 0.3202, | |
| "step": 384000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 6.186330590943276e-06, | |
| "loss": 0.3201, | |
| "step": 384500 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 6.129355728252696e-06, | |
| "loss": 0.3201, | |
| "step": 385000 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 6.072380865562114e-06, | |
| "loss": 0.3205, | |
| "step": 385500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.015406002871534e-06, | |
| "loss": 0.3205, | |
| "step": 386000 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 5.958431140180953e-06, | |
| "loss": 0.3202, | |
| "step": 386500 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 5.901456277490371e-06, | |
| "loss": 0.3198, | |
| "step": 387000 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 5.844481414799791e-06, | |
| "loss": 0.3202, | |
| "step": 387500 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 5.78750655210921e-06, | |
| "loss": 0.3202, | |
| "step": 388000 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 5.730531689418629e-06, | |
| "loss": 0.3205, | |
| "step": 388500 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 5.673556826728048e-06, | |
| "loss": 0.3201, | |
| "step": 389000 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 5.616581964037467e-06, | |
| "loss": 0.32, | |
| "step": 389500 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 5.559607101346886e-06, | |
| "loss": 0.3202, | |
| "step": 390000 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 5.502632238656305e-06, | |
| "loss": 0.3203, | |
| "step": 390500 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 5.445657375965725e-06, | |
| "loss": 0.3206, | |
| "step": 391000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 5.388682513275143e-06, | |
| "loss": 0.3201, | |
| "step": 391500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 5.3317076505845626e-06, | |
| "loss": 0.3199, | |
| "step": 392000 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 5.2747327878939816e-06, | |
| "loss": 0.32, | |
| "step": 392500 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 5.2177579252034006e-06, | |
| "loss": 0.3202, | |
| "step": 393000 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 5.1607830625128195e-06, | |
| "loss": 0.3199, | |
| "step": 393500 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 5.1038081998222385e-06, | |
| "loss": 0.3199, | |
| "step": 394000 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 5.0468333371316575e-06, | |
| "loss": 0.3201, | |
| "step": 394500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.899363086505016, | |
| "eval_loss": 0.31066715717315674, | |
| "eval_runtime": 2074.8457, | |
| "eval_samples_per_second": 300.579, | |
| "eval_steps_per_second": 2.349, | |
| "step": 394911 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.9898584744410765e-06, | |
| "loss": 0.3198, | |
| "step": 395000 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.932883611750496e-06, | |
| "loss": 0.3196, | |
| "step": 395500 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.8759087490599145e-06, | |
| "loss": 0.3199, | |
| "step": 396000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.818933886369334e-06, | |
| "loss": 0.3198, | |
| "step": 396500 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 4.761959023678753e-06, | |
| "loss": 0.3199, | |
| "step": 397000 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 4.704984160988172e-06, | |
| "loss": 0.3199, | |
| "step": 397500 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 4.648009298297591e-06, | |
| "loss": 0.3198, | |
| "step": 398000 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 4.59103443560701e-06, | |
| "loss": 0.3196, | |
| "step": 398500 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.53405957291643e-06, | |
| "loss": 0.3197, | |
| "step": 399000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.477084710225848e-06, | |
| "loss": 0.3196, | |
| "step": 399500 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 4.420109847535267e-06, | |
| "loss": 0.3199, | |
| "step": 400000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 4.363134984844687e-06, | |
| "loss": 0.3201, | |
| "step": 400500 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 4.306160122154105e-06, | |
| "loss": 0.3199, | |
| "step": 401000 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.249185259463525e-06, | |
| "loss": 0.3198, | |
| "step": 401500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.192210396772944e-06, | |
| "loss": 0.3197, | |
| "step": 402000 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 4.135235534082363e-06, | |
| "loss": 0.3198, | |
| "step": 402500 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 4.078260671391782e-06, | |
| "loss": 0.3198, | |
| "step": 403000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 4.021285808701201e-06, | |
| "loss": 0.3198, | |
| "step": 403500 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 3.96431094601062e-06, | |
| "loss": 0.3197, | |
| "step": 404000 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 3.907336083320039e-06, | |
| "loss": 0.3196, | |
| "step": 404500 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.850361220629459e-06, | |
| "loss": 0.3202, | |
| "step": 405000 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 3.7933863579388775e-06, | |
| "loss": 0.3199, | |
| "step": 405500 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.7364114952482965e-06, | |
| "loss": 0.3198, | |
| "step": 406000 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 3.679436632557716e-06, | |
| "loss": 0.3196, | |
| "step": 406500 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.6224617698671345e-06, | |
| "loss": 0.3195, | |
| "step": 407000 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 3.565486907176554e-06, | |
| "loss": 0.3194, | |
| "step": 407500 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 3.5085120444859733e-06, | |
| "loss": 0.3198, | |
| "step": 408000 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 3.451537181795392e-06, | |
| "loss": 0.3197, | |
| "step": 408500 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.394562319104811e-06, | |
| "loss": 0.3197, | |
| "step": 409000 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 3.3375874564142303e-06, | |
| "loss": 0.3196, | |
| "step": 409500 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 3.280612593723649e-06, | |
| "loss": 0.3194, | |
| "step": 410000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 3.2236377310330683e-06, | |
| "loss": 0.3199, | |
| "step": 410500 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.1666628683424877e-06, | |
| "loss": 0.3197, | |
| "step": 411000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 3.1096880056519067e-06, | |
| "loss": 0.3199, | |
| "step": 411500 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 3.0527131429613257e-06, | |
| "loss": 0.3195, | |
| "step": 412000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 2.9957382802707447e-06, | |
| "loss": 0.3195, | |
| "step": 412500 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 2.9387634175801637e-06, | |
| "loss": 0.3193, | |
| "step": 413000 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 2.8817885548895827e-06, | |
| "loss": 0.3198, | |
| "step": 413500 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 2.824813692199002e-06, | |
| "loss": 0.3196, | |
| "step": 414000 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 2.767838829508421e-06, | |
| "loss": 0.3197, | |
| "step": 414500 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 2.71086396681784e-06, | |
| "loss": 0.3195, | |
| "step": 415000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.6538891041272595e-06, | |
| "loss": 0.3197, | |
| "step": 415500 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 2.596914241436678e-06, | |
| "loss": 0.3198, | |
| "step": 416000 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 2.539939378746097e-06, | |
| "loss": 0.3201, | |
| "step": 416500 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.4829645160555165e-06, | |
| "loss": 0.3198, | |
| "step": 417000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 2.4259896533649355e-06, | |
| "loss": 0.3196, | |
| "step": 417500 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 2.3690147906743544e-06, | |
| "loss": 0.3192, | |
| "step": 418000 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 2.312039927983774e-06, | |
| "loss": 0.3192, | |
| "step": 418500 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2.255065065293193e-06, | |
| "loss": 0.3198, | |
| "step": 419000 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.198090202602612e-06, | |
| "loss": 0.3195, | |
| "step": 419500 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 2.141115339912031e-06, | |
| "loss": 0.3196, | |
| "step": 420000 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.08414047722145e-06, | |
| "loss": 0.3198, | |
| "step": 420500 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 2.0271656145308693e-06, | |
| "loss": 0.3194, | |
| "step": 421000 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "learning_rate": 1.9701907518402882e-06, | |
| "loss": 0.3197, | |
| "step": 421500 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.9132158891497072e-06, | |
| "loss": 0.3195, | |
| "step": 422000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 1.8562410264591264e-06, | |
| "loss": 0.3195, | |
| "step": 422500 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 1.7992661637685454e-06, | |
| "loss": 0.3193, | |
| "step": 423000 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 1.7422913010779644e-06, | |
| "loss": 0.3195, | |
| "step": 423500 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.6853164383873836e-06, | |
| "loss": 0.3195, | |
| "step": 424000 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.6283415756968026e-06, | |
| "loss": 0.3195, | |
| "step": 424500 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "learning_rate": 1.5713667130062216e-06, | |
| "loss": 0.3196, | |
| "step": 425000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.5143918503156408e-06, | |
| "loss": 0.3193, | |
| "step": 425500 | |
| }, | |
| { | |
| "epoch": 9.71, | |
| "learning_rate": 1.4574169876250598e-06, | |
| "loss": 0.3198, | |
| "step": 426000 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 1.400442124934479e-06, | |
| "loss": 0.3198, | |
| "step": 426500 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 1.343467262243898e-06, | |
| "loss": 0.3197, | |
| "step": 427000 | |
| }, | |
| { | |
| "epoch": 9.74, | |
| "learning_rate": 1.286492399553317e-06, | |
| "loss": 0.3193, | |
| "step": 427500 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.2295175368627362e-06, | |
| "loss": 0.3195, | |
| "step": 428000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.1725426741721554e-06, | |
| "loss": 0.3195, | |
| "step": 428500 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 1.1155678114815742e-06, | |
| "loss": 0.3195, | |
| "step": 429000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 1.0585929487909934e-06, | |
| "loss": 0.3192, | |
| "step": 429500 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 1.0016180861004126e-06, | |
| "loss": 0.3195, | |
| "step": 430000 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 9.446432234098317e-07, | |
| "loss": 0.3198, | |
| "step": 430500 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 8.876683607192507e-07, | |
| "loss": 0.3193, | |
| "step": 431000 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 8.306934980286698e-07, | |
| "loss": 0.3197, | |
| "step": 431500 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 7.737186353380888e-07, | |
| "loss": 0.3195, | |
| "step": 432000 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 7.16743772647508e-07, | |
| "loss": 0.3196, | |
| "step": 432500 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 6.59768909956927e-07, | |
| "loss": 0.3193, | |
| "step": 433000 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 6.027940472663461e-07, | |
| "loss": 0.3195, | |
| "step": 433500 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 5.458191845757652e-07, | |
| "loss": 0.3193, | |
| "step": 434000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 4.888443218851842e-07, | |
| "loss": 0.3196, | |
| "step": 434500 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 4.318694591946034e-07, | |
| "loss": 0.3195, | |
| "step": 435000 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 3.7489459650402244e-07, | |
| "loss": 0.3191, | |
| "step": 435500 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 3.179197338134415e-07, | |
| "loss": 0.3194, | |
| "step": 436000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 2.609448711228606e-07, | |
| "loss": 0.3194, | |
| "step": 436500 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 2.0397000843227969e-07, | |
| "loss": 0.3196, | |
| "step": 437000 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 1.4699514574169879e-07, | |
| "loss": 0.3193, | |
| "step": 437500 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 9.002028305111786e-08, | |
| "loss": 0.3195, | |
| "step": 438000 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 3.304542036053693e-08, | |
| "loss": 0.3191, | |
| "step": 438500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8994679101285066, | |
| "eval_loss": 0.31025540828704834, | |
| "eval_runtime": 2076.139, | |
| "eval_samples_per_second": 300.392, | |
| "eval_steps_per_second": 2.347, | |
| "step": 438790 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 438790, | |
| "total_flos": 1.4675498567875953e+19, | |
| "train_loss": 0.33915139676477035, | |
| "train_runtime": 262033.2804, | |
| "train_samples_per_second": 214.341, | |
| "train_steps_per_second": 1.675 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 438790, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.4675498567875953e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |