| { | |
| "best_metric": 0.7719072164948454, | |
| "best_model_checkpoint": "roberta-large-movies/checkpoint-72500", | |
| "epoch": 30.0, | |
| "global_step": 83910, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.970504111548088e-05, | |
| "loss": 1.7698, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_accuracy": 0.6738421395955643, | |
| "eval_loss": 1.6167851686477661, | |
| "eval_runtime": 0.8246, | |
| "eval_samples_per_second": 606.37, | |
| "eval_steps_per_second": 38.808, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.94082946013586e-05, | |
| "loss": 1.7761, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.6829508196721311, | |
| "eval_loss": 1.6522468328475952, | |
| "eval_runtime": 0.7873, | |
| "eval_samples_per_second": 635.049, | |
| "eval_steps_per_second": 40.643, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.9110356334167565e-05, | |
| "loss": 1.7626, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.6660117878192534, | |
| "eval_loss": 1.6534239053726196, | |
| "eval_runtime": 0.7869, | |
| "eval_samples_per_second": 635.425, | |
| "eval_steps_per_second": 40.667, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.8812418066976524e-05, | |
| "loss": 1.7602, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.6787299419597133, | |
| "eval_loss": 1.6575504541397095, | |
| "eval_runtime": 0.7882, | |
| "eval_samples_per_second": 634.385, | |
| "eval_steps_per_second": 40.601, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.851447979978549e-05, | |
| "loss": 1.7587, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.6772697150430749, | |
| "eval_loss": 1.6266298294067383, | |
| "eval_runtime": 0.7893, | |
| "eval_samples_per_second": 633.509, | |
| "eval_steps_per_second": 40.545, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.821654153259445e-05, | |
| "loss": 1.7047, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.6851971557853911, | |
| "eval_loss": 1.605985164642334, | |
| "eval_runtime": 0.8181, | |
| "eval_samples_per_second": 611.179, | |
| "eval_steps_per_second": 39.115, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.791860326540341e-05, | |
| "loss": 1.6782, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.6906354515050167, | |
| "eval_loss": 1.599035382270813, | |
| "eval_runtime": 0.8184, | |
| "eval_samples_per_second": 610.967, | |
| "eval_steps_per_second": 39.102, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 4.7620664998212375e-05, | |
| "loss": 1.6733, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.6967426710097719, | |
| "eval_loss": 1.5377483367919922, | |
| "eval_runtime": 0.819, | |
| "eval_samples_per_second": 610.521, | |
| "eval_steps_per_second": 39.073, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.7322726731021334e-05, | |
| "loss": 1.6664, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_accuracy": 0.6746607762701168, | |
| "eval_loss": 1.6434643268585205, | |
| "eval_runtime": 0.7966, | |
| "eval_samples_per_second": 627.631, | |
| "eval_steps_per_second": 40.168, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 4.70247884638303e-05, | |
| "loss": 1.6719, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_accuracy": 0.6907181571815718, | |
| "eval_loss": 1.483905553817749, | |
| "eval_runtime": 0.7989, | |
| "eval_samples_per_second": 625.841, | |
| "eval_steps_per_second": 40.054, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.672685019663926e-05, | |
| "loss": 1.6502, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.6896661367249602, | |
| "eval_loss": 1.535127878189087, | |
| "eval_runtime": 0.823, | |
| "eval_samples_per_second": 607.558, | |
| "eval_steps_per_second": 38.884, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 4.642891192944822e-05, | |
| "loss": 1.6233, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_accuracy": 0.6763219939373526, | |
| "eval_loss": 1.6817570924758911, | |
| "eval_runtime": 0.7881, | |
| "eval_samples_per_second": 634.403, | |
| "eval_steps_per_second": 40.602, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.6130973662257184e-05, | |
| "loss": 1.6127, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_accuracy": 0.685335059889932, | |
| "eval_loss": 1.5865211486816406, | |
| "eval_runtime": 0.787, | |
| "eval_samples_per_second": 635.291, | |
| "eval_steps_per_second": 40.659, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.5833035395066143e-05, | |
| "loss": 1.6274, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.7003633961017509, | |
| "eval_loss": 1.5004233121871948, | |
| "eval_runtime": 0.8009, | |
| "eval_samples_per_second": 624.318, | |
| "eval_steps_per_second": 39.956, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 4.553628888094387e-05, | |
| "loss": 1.601, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_accuracy": 0.6929970129439097, | |
| "eval_loss": 1.452188491821289, | |
| "eval_runtime": 0.7898, | |
| "eval_samples_per_second": 633.056, | |
| "eval_steps_per_second": 40.516, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 4.523835061375284e-05, | |
| "loss": 1.6123, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.689419795221843, | |
| "eval_loss": 1.5370689630508423, | |
| "eval_runtime": 0.8546, | |
| "eval_samples_per_second": 585.05, | |
| "eval_steps_per_second": 37.443, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.4940412346561796e-05, | |
| "loss": 1.6074, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.6952157912345266, | |
| "eval_loss": 1.5342369079589844, | |
| "eval_runtime": 0.8214, | |
| "eval_samples_per_second": 608.68, | |
| "eval_steps_per_second": 38.956, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 4.4642474079370755e-05, | |
| "loss": 1.563, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "eval_accuracy": 0.6875834445927904, | |
| "eval_loss": 1.568178415298462, | |
| "eval_runtime": 0.8488, | |
| "eval_samples_per_second": 589.06, | |
| "eval_steps_per_second": 37.7, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 4.4344535812179714e-05, | |
| "loss": 1.5746, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.6957663275352806, | |
| "eval_loss": 1.5704632997512817, | |
| "eval_runtime": 0.852, | |
| "eval_samples_per_second": 586.84, | |
| "eval_steps_per_second": 37.558, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 4.404778929805745e-05, | |
| "loss": 1.5539, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_accuracy": 0.7040711597673623, | |
| "eval_loss": 1.4710707664489746, | |
| "eval_runtime": 0.85, | |
| "eval_samples_per_second": 588.248, | |
| "eval_steps_per_second": 37.648, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.374985103086641e-05, | |
| "loss": 1.578, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_accuracy": 0.6888888888888889, | |
| "eval_loss": 1.5465725660324097, | |
| "eval_runtime": 0.8902, | |
| "eval_samples_per_second": 561.645, | |
| "eval_steps_per_second": 35.945, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 4.345191276367537e-05, | |
| "loss": 1.5492, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "eval_accuracy": 0.6968894771674388, | |
| "eval_loss": 1.4628891944885254, | |
| "eval_runtime": 0.8368, | |
| "eval_samples_per_second": 597.487, | |
| "eval_steps_per_second": 38.239, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 4.3153974496484326e-05, | |
| "loss": 1.5291, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_accuracy": 0.7200132538104705, | |
| "eval_loss": 1.4264894723892212, | |
| "eval_runtime": 0.8798, | |
| "eval_samples_per_second": 568.319, | |
| "eval_steps_per_second": 36.372, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 4.285603622929329e-05, | |
| "loss": 1.5079, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_accuracy": 0.6966074313408723, | |
| "eval_loss": 1.5052707195281982, | |
| "eval_runtime": 0.8186, | |
| "eval_samples_per_second": 610.796, | |
| "eval_steps_per_second": 39.091, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 4.255809796210226e-05, | |
| "loss": 1.5283, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.6902654867256637, | |
| "eval_loss": 1.5257039070129395, | |
| "eval_runtime": 0.8002, | |
| "eval_samples_per_second": 624.861, | |
| "eval_steps_per_second": 39.991, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 4.226015969491122e-05, | |
| "loss": 1.5141, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_accuracy": 0.6949898442789438, | |
| "eval_loss": 1.5063292980194092, | |
| "eval_runtime": 0.8654, | |
| "eval_samples_per_second": 577.759, | |
| "eval_steps_per_second": 36.977, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 4.1962221427720176e-05, | |
| "loss": 1.4979, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_accuracy": 0.6955945677376615, | |
| "eval_loss": 1.5636450052261353, | |
| "eval_runtime": 0.8149, | |
| "eval_samples_per_second": 613.582, | |
| "eval_steps_per_second": 39.269, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.1664283160529136e-05, | |
| "loss": 1.5294, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_accuracy": 0.6835193696651346, | |
| "eval_loss": 1.587847113609314, | |
| "eval_runtime": 0.8296, | |
| "eval_samples_per_second": 602.733, | |
| "eval_steps_per_second": 38.575, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 4.13663448933381e-05, | |
| "loss": 1.4641, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "eval_accuracy": 0.6962067807989258, | |
| "eval_loss": 1.5574804544448853, | |
| "eval_runtime": 0.81, | |
| "eval_samples_per_second": 617.287, | |
| "eval_steps_per_second": 39.506, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 4.106840662614707e-05, | |
| "loss": 1.4754, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "eval_accuracy": 0.7006847081838931, | |
| "eval_loss": 1.4779187440872192, | |
| "eval_runtime": 0.8312, | |
| "eval_samples_per_second": 601.557, | |
| "eval_steps_per_second": 38.5, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 4.077046835895603e-05, | |
| "loss": 1.4696, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "eval_accuracy": 0.6965271015903928, | |
| "eval_loss": 1.451996922492981, | |
| "eval_runtime": 0.7909, | |
| "eval_samples_per_second": 632.19, | |
| "eval_steps_per_second": 40.46, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 4.0472530091764986e-05, | |
| "loss": 1.4655, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "eval_accuracy": 0.683049147442327, | |
| "eval_loss": 1.6320295333862305, | |
| "eval_runtime": 0.8309, | |
| "eval_samples_per_second": 601.76, | |
| "eval_steps_per_second": 38.513, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 4.0174591824573945e-05, | |
| "loss": 1.4792, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "eval_accuracy": 0.7134165866154338, | |
| "eval_loss": 1.415226697921753, | |
| "eval_runtime": 0.8575, | |
| "eval_samples_per_second": 583.097, | |
| "eval_steps_per_second": 37.318, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 3.98772494339173e-05, | |
| "loss": 1.4379, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "eval_accuracy": 0.7041935483870968, | |
| "eval_loss": 1.4900156259536743, | |
| "eval_runtime": 0.8413, | |
| "eval_samples_per_second": 594.352, | |
| "eval_steps_per_second": 38.039, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 3.957931116672626e-05, | |
| "loss": 1.4281, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "eval_accuracy": 0.6989864864864865, | |
| "eval_loss": 1.5407416820526123, | |
| "eval_runtime": 0.8677, | |
| "eval_samples_per_second": 576.232, | |
| "eval_steps_per_second": 36.879, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 3.928137289953522e-05, | |
| "loss": 1.436, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "eval_accuracy": 0.6914175506268081, | |
| "eval_loss": 1.534258246421814, | |
| "eval_runtime": 0.843, | |
| "eval_samples_per_second": 593.143, | |
| "eval_steps_per_second": 37.961, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 3.8983434632344176e-05, | |
| "loss": 1.4342, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "eval_accuracy": 0.7023696682464455, | |
| "eval_loss": 1.5323561429977417, | |
| "eval_runtime": 0.7874, | |
| "eval_samples_per_second": 635.024, | |
| "eval_steps_per_second": 40.642, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 3.868549636515314e-05, | |
| "loss": 1.4176, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "eval_accuracy": 0.7132913490222075, | |
| "eval_loss": 1.4485751390457153, | |
| "eval_runtime": 0.8567, | |
| "eval_samples_per_second": 583.665, | |
| "eval_steps_per_second": 37.355, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 3.838755809796211e-05, | |
| "loss": 1.4308, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_accuracy": 0.7031503734978889, | |
| "eval_loss": 1.4598056077957153, | |
| "eval_runtime": 0.79, | |
| "eval_samples_per_second": 632.872, | |
| "eval_steps_per_second": 40.504, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 3.809021570730545e-05, | |
| "loss": 1.4014, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_accuracy": 0.6938435940099834, | |
| "eval_loss": 1.575023889541626, | |
| "eval_runtime": 0.8292, | |
| "eval_samples_per_second": 603.024, | |
| "eval_steps_per_second": 38.594, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 3.779227744011441e-05, | |
| "loss": 1.3661, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "eval_accuracy": 0.6985221674876847, | |
| "eval_loss": 1.5403505563735962, | |
| "eval_runtime": 0.8319, | |
| "eval_samples_per_second": 601.063, | |
| "eval_steps_per_second": 38.468, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 3.7494935049457754e-05, | |
| "loss": 1.3857, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "eval_accuracy": 0.7037155669442665, | |
| "eval_loss": 1.4692307710647583, | |
| "eval_runtime": 0.8177, | |
| "eval_samples_per_second": 611.5, | |
| "eval_steps_per_second": 39.136, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 3.719699678226672e-05, | |
| "loss": 1.3846, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "eval_accuracy": 0.6941445861956166, | |
| "eval_loss": 1.5511342287063599, | |
| "eval_runtime": 0.7898, | |
| "eval_samples_per_second": 633.076, | |
| "eval_steps_per_second": 40.517, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 3.689905851507568e-05, | |
| "loss": 1.3867, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "eval_accuracy": 0.6925124792013311, | |
| "eval_loss": 1.5321439504623413, | |
| "eval_runtime": 0.8379, | |
| "eval_samples_per_second": 596.713, | |
| "eval_steps_per_second": 38.19, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 3.660112024788464e-05, | |
| "loss": 1.3658, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "eval_accuracy": 0.7020917678812416, | |
| "eval_loss": 1.5499885082244873, | |
| "eval_runtime": 0.8209, | |
| "eval_samples_per_second": 609.075, | |
| "eval_steps_per_second": 38.981, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 3.6303181980693604e-05, | |
| "loss": 1.3406, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "eval_accuracy": 0.6959503592423253, | |
| "eval_loss": 1.523918628692627, | |
| "eval_runtime": 0.8298, | |
| "eval_samples_per_second": 602.525, | |
| "eval_steps_per_second": 38.562, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 3.600524371350256e-05, | |
| "loss": 1.3405, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "eval_accuracy": 0.7055256064690026, | |
| "eval_loss": 1.4414023160934448, | |
| "eval_runtime": 0.8516, | |
| "eval_samples_per_second": 587.105, | |
| "eval_steps_per_second": 37.575, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 3.570730544631153e-05, | |
| "loss": 1.3373, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "eval_accuracy": 0.6784238957737527, | |
| "eval_loss": 1.599377155303955, | |
| "eval_runtime": 0.791, | |
| "eval_samples_per_second": 632.109, | |
| "eval_steps_per_second": 40.455, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 3.540936717912049e-05, | |
| "loss": 1.3527, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_accuracy": 0.6970387243735763, | |
| "eval_loss": 1.5105814933776855, | |
| "eval_runtime": 0.8594, | |
| "eval_samples_per_second": 581.797, | |
| "eval_steps_per_second": 37.235, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 3.511142891192945e-05, | |
| "loss": 1.3436, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "eval_accuracy": 0.7079758500158881, | |
| "eval_loss": 1.471426010131836, | |
| "eval_runtime": 0.8427, | |
| "eval_samples_per_second": 593.355, | |
| "eval_steps_per_second": 37.975, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.4813490644738414e-05, | |
| "loss": 1.3069, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "eval_accuracy": 0.6953099376844867, | |
| "eval_loss": 1.4990392923355103, | |
| "eval_runtime": 0.8575, | |
| "eval_samples_per_second": 583.12, | |
| "eval_steps_per_second": 37.32, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 3.451555237754737e-05, | |
| "loss": 1.2969, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "eval_accuracy": 0.6964285714285714, | |
| "eval_loss": 1.4809668064117432, | |
| "eval_runtime": 0.8312, | |
| "eval_samples_per_second": 601.512, | |
| "eval_steps_per_second": 38.497, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 3.421761411035634e-05, | |
| "loss": 1.3009, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "eval_accuracy": 0.6875602700096431, | |
| "eval_loss": 1.5964903831481934, | |
| "eval_runtime": 0.8752, | |
| "eval_samples_per_second": 571.296, | |
| "eval_steps_per_second": 36.563, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 3.392086759623406e-05, | |
| "loss": 1.3227, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "eval_accuracy": 0.7013662979830839, | |
| "eval_loss": 1.429559588432312, | |
| "eval_runtime": 0.7904, | |
| "eval_samples_per_second": 632.561, | |
| "eval_steps_per_second": 40.484, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 3.3622929329043025e-05, | |
| "loss": 1.3259, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "eval_accuracy": 0.7189224277831873, | |
| "eval_loss": 1.413652777671814, | |
| "eval_runtime": 0.8134, | |
| "eval_samples_per_second": 614.697, | |
| "eval_steps_per_second": 39.341, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 3.3324991061851985e-05, | |
| "loss": 1.3131, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "eval_accuracy": 0.7019570099454604, | |
| "eval_loss": 1.534200668334961, | |
| "eval_runtime": 0.8056, | |
| "eval_samples_per_second": 620.653, | |
| "eval_steps_per_second": 39.722, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "learning_rate": 3.3027052794660944e-05, | |
| "loss": 1.271, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 10.19, | |
| "eval_accuracy": 0.711340206185567, | |
| "eval_loss": 1.470828890800476, | |
| "eval_runtime": 0.7815, | |
| "eval_samples_per_second": 639.779, | |
| "eval_steps_per_second": 40.946, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 3.272911452746991e-05, | |
| "loss": 1.2684, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "eval_accuracy": 0.7045747422680413, | |
| "eval_loss": 1.4341672658920288, | |
| "eval_runtime": 0.7954, | |
| "eval_samples_per_second": 628.629, | |
| "eval_steps_per_second": 40.232, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 3.2431176260278876e-05, | |
| "loss": 1.2767, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "eval_accuracy": 0.709353000335233, | |
| "eval_loss": 1.4703407287597656, | |
| "eval_runtime": 0.8179, | |
| "eval_samples_per_second": 611.351, | |
| "eval_steps_per_second": 39.126, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 3.2133237993087835e-05, | |
| "loss": 1.2861, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "eval_accuracy": 0.7308937823834197, | |
| "eval_loss": 1.3323109149932861, | |
| "eval_runtime": 0.7855, | |
| "eval_samples_per_second": 636.523, | |
| "eval_steps_per_second": 40.737, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 3.1835299725896794e-05, | |
| "loss": 1.2617, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "eval_accuracy": 0.7003344481605351, | |
| "eval_loss": 1.4562044143676758, | |
| "eval_runtime": 0.7951, | |
| "eval_samples_per_second": 628.826, | |
| "eval_steps_per_second": 40.245, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 3.153736145870575e-05, | |
| "loss": 1.2551, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "eval_accuracy": 0.7169689119170984, | |
| "eval_loss": 1.4361472129821777, | |
| "eval_runtime": 0.8647, | |
| "eval_samples_per_second": 578.22, | |
| "eval_steps_per_second": 37.006, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "learning_rate": 3.124001906804911e-05, | |
| "loss": 1.2404, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 11.26, | |
| "eval_accuracy": 0.7034617896799478, | |
| "eval_loss": 1.4536628723144531, | |
| "eval_runtime": 0.7907, | |
| "eval_samples_per_second": 632.325, | |
| "eval_steps_per_second": 40.469, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 3.0942080800858066e-05, | |
| "loss": 1.2562, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "eval_accuracy": 0.7132209980557356, | |
| "eval_loss": 1.4038574695587158, | |
| "eval_runtime": 0.7924, | |
| "eval_samples_per_second": 631.001, | |
| "eval_steps_per_second": 40.384, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 3.0644142533667025e-05, | |
| "loss": 1.2489, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "eval_accuracy": 0.706418918918919, | |
| "eval_loss": 1.4372212886810303, | |
| "eval_runtime": 0.8024, | |
| "eval_samples_per_second": 623.122, | |
| "eval_steps_per_second": 39.88, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 3.0346204266475984e-05, | |
| "loss": 1.2406, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "eval_accuracy": 0.7087442472057857, | |
| "eval_loss": 1.4926137924194336, | |
| "eval_runtime": 0.8525, | |
| "eval_samples_per_second": 586.532, | |
| "eval_steps_per_second": 37.538, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 3.0048265999284947e-05, | |
| "loss": 1.2285, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "eval_accuracy": 0.7152005392652511, | |
| "eval_loss": 1.4080321788787842, | |
| "eval_runtime": 0.8108, | |
| "eval_samples_per_second": 616.703, | |
| "eval_steps_per_second": 39.469, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 2.9750327732093913e-05, | |
| "loss": 1.2213, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "eval_accuracy": 0.7170240415854451, | |
| "eval_loss": 1.403072476387024, | |
| "eval_runtime": 0.8459, | |
| "eval_samples_per_second": 591.089, | |
| "eval_steps_per_second": 37.83, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 2.9452389464902875e-05, | |
| "loss": 1.1998, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "eval_accuracy": 0.7222584856396866, | |
| "eval_loss": 1.3541438579559326, | |
| "eval_runtime": 0.7909, | |
| "eval_samples_per_second": 632.16, | |
| "eval_steps_per_second": 40.458, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "learning_rate": 2.9154451197711835e-05, | |
| "loss": 1.2184, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "eval_accuracy": 0.7308441558441559, | |
| "eval_loss": 1.3629957437515259, | |
| "eval_runtime": 0.8716, | |
| "eval_samples_per_second": 573.677, | |
| "eval_steps_per_second": 36.715, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 2.8856512930520797e-05, | |
| "loss": 1.2195, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "eval_accuracy": 0.7281362594169669, | |
| "eval_loss": 1.312456488609314, | |
| "eval_runtime": 0.852, | |
| "eval_samples_per_second": 586.847, | |
| "eval_steps_per_second": 37.558, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "learning_rate": 2.8558574663329756e-05, | |
| "loss": 1.2178, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 12.87, | |
| "eval_accuracy": 0.7119236883942767, | |
| "eval_loss": 1.4257023334503174, | |
| "eval_runtime": 0.8597, | |
| "eval_samples_per_second": 581.571, | |
| "eval_steps_per_second": 37.221, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 2.8260636396138722e-05, | |
| "loss": 1.1918, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "eval_accuracy": 0.7152686762778506, | |
| "eval_loss": 1.4108035564422607, | |
| "eval_runtime": 0.9192, | |
| "eval_samples_per_second": 543.96, | |
| "eval_steps_per_second": 34.813, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 2.7963294005482066e-05, | |
| "loss": 1.1664, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "eval_accuracy": 0.7226588081204977, | |
| "eval_loss": 1.3577048778533936, | |
| "eval_runtime": 0.7887, | |
| "eval_samples_per_second": 633.948, | |
| "eval_steps_per_second": 40.573, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 2.7665355738291028e-05, | |
| "loss": 1.1754, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "eval_accuracy": 0.720593191776205, | |
| "eval_loss": 1.377700924873352, | |
| "eval_runtime": 0.8445, | |
| "eval_samples_per_second": 592.06, | |
| "eval_steps_per_second": 37.892, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "learning_rate": 2.7367417471099987e-05, | |
| "loss": 1.1855, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 13.59, | |
| "eval_accuracy": 0.7354008578027054, | |
| "eval_loss": 1.350059151649475, | |
| "eval_runtime": 0.8109, | |
| "eval_samples_per_second": 616.607, | |
| "eval_steps_per_second": 39.463, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.7070075080443334e-05, | |
| "loss": 1.1644, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "eval_accuracy": 0.7206685953069752, | |
| "eval_loss": 1.374656081199646, | |
| "eval_runtime": 0.8397, | |
| "eval_samples_per_second": 595.482, | |
| "eval_steps_per_second": 38.111, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "learning_rate": 2.6772136813252297e-05, | |
| "loss": 1.1709, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "eval_accuracy": 0.7183739837398374, | |
| "eval_loss": 1.3703839778900146, | |
| "eval_runtime": 0.8025, | |
| "eval_samples_per_second": 623.038, | |
| "eval_steps_per_second": 39.874, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 2.6474198546061256e-05, | |
| "loss": 1.1613, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "eval_accuracy": 0.7246875, | |
| "eval_loss": 1.4306718111038208, | |
| "eval_runtime": 0.8499, | |
| "eval_samples_per_second": 588.275, | |
| "eval_steps_per_second": 37.65, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 2.617626027887022e-05, | |
| "loss": 1.1443, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "eval_accuracy": 0.7220978573712824, | |
| "eval_loss": 1.3189983367919922, | |
| "eval_runtime": 0.7903, | |
| "eval_samples_per_second": 632.651, | |
| "eval_steps_per_second": 40.49, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 2.5878322011679178e-05, | |
| "loss": 1.1356, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "eval_accuracy": 0.7331329325317302, | |
| "eval_loss": 1.3287793397903442, | |
| "eval_runtime": 0.7921, | |
| "eval_samples_per_second": 631.257, | |
| "eval_steps_per_second": 40.4, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "learning_rate": 2.5580383744488147e-05, | |
| "loss": 1.1493, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "eval_accuracy": 0.7240227196792516, | |
| "eval_loss": 1.3504801988601685, | |
| "eval_runtime": 0.8432, | |
| "eval_samples_per_second": 592.975, | |
| "eval_steps_per_second": 37.95, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 2.5283041353831487e-05, | |
| "loss": 1.1417, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "eval_accuracy": 0.7320369149637442, | |
| "eval_loss": 1.31459379196167, | |
| "eval_runtime": 0.8272, | |
| "eval_samples_per_second": 604.463, | |
| "eval_steps_per_second": 38.686, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 2.498569896317483e-05, | |
| "loss": 1.1349, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.7333114107201578, | |
| "eval_loss": 1.3545522689819336, | |
| "eval_runtime": 0.8634, | |
| "eval_samples_per_second": 579.106, | |
| "eval_steps_per_second": 37.063, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "learning_rate": 2.4687760695983793e-05, | |
| "loss": 1.1169, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 15.19, | |
| "eval_accuracy": 0.7246922024623803, | |
| "eval_loss": 1.37086021900177, | |
| "eval_runtime": 0.8611, | |
| "eval_samples_per_second": 580.685, | |
| "eval_steps_per_second": 37.164, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 2.4390418305327136e-05, | |
| "loss": 1.1187, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "eval_accuracy": 0.7217795484727756, | |
| "eval_loss": 1.4242717027664185, | |
| "eval_runtime": 0.8265, | |
| "eval_samples_per_second": 604.985, | |
| "eval_steps_per_second": 38.719, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 2.4092480038136102e-05, | |
| "loss": 1.118, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "eval_accuracy": 0.7264245251582806, | |
| "eval_loss": 1.3835431337356567, | |
| "eval_runtime": 0.8374, | |
| "eval_samples_per_second": 597.064, | |
| "eval_steps_per_second": 38.212, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 2.379454177094506e-05, | |
| "loss": 1.1165, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "eval_accuracy": 0.7253818654533637, | |
| "eval_loss": 1.3239895105361938, | |
| "eval_runtime": 0.8499, | |
| "eval_samples_per_second": 588.29, | |
| "eval_steps_per_second": 37.651, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 2.3496603503754024e-05, | |
| "loss": 1.114, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "eval_accuracy": 0.7382113821138211, | |
| "eval_loss": 1.3263858556747437, | |
| "eval_runtime": 0.8424, | |
| "eval_samples_per_second": 593.546, | |
| "eval_steps_per_second": 37.987, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "learning_rate": 2.3198665236562986e-05, | |
| "loss": 1.105, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "eval_accuracy": 0.7333548804137039, | |
| "eval_loss": 1.3213739395141602, | |
| "eval_runtime": 0.8677, | |
| "eval_samples_per_second": 576.224, | |
| "eval_steps_per_second": 36.878, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 16.27, | |
| "learning_rate": 2.2900726969371946e-05, | |
| "loss": 1.0924, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 16.27, | |
| "eval_accuracy": 0.7282392026578073, | |
| "eval_loss": 1.384667992591858, | |
| "eval_runtime": 0.9421, | |
| "eval_samples_per_second": 530.704, | |
| "eval_steps_per_second": 33.965, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 2.260278870218091e-05, | |
| "loss": 1.0915, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "eval_accuracy": 0.7317073170731707, | |
| "eval_loss": 1.3603721857070923, | |
| "eval_runtime": 0.7951, | |
| "eval_samples_per_second": 628.874, | |
| "eval_steps_per_second": 40.248, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 2.230485043498987e-05, | |
| "loss": 1.0968, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "eval_accuracy": 0.7319177173191772, | |
| "eval_loss": 1.3539705276489258, | |
| "eval_runtime": 0.8815, | |
| "eval_samples_per_second": 567.187, | |
| "eval_steps_per_second": 36.3, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.2006912167798833e-05, | |
| "loss": 1.0772, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "eval_accuracy": 0.7306332369013179, | |
| "eval_loss": 1.2475004196166992, | |
| "eval_runtime": 0.8301, | |
| "eval_samples_per_second": 602.308, | |
| "eval_steps_per_second": 38.548, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "learning_rate": 2.1708973900607796e-05, | |
| "loss": 1.0975, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 16.98, | |
| "eval_accuracy": 0.7448207826372903, | |
| "eval_loss": 1.2635700702667236, | |
| "eval_runtime": 0.8269, | |
| "eval_samples_per_second": 604.655, | |
| "eval_steps_per_second": 38.698, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 2.1411035633416755e-05, | |
| "loss": 1.0708, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "eval_accuracy": 0.7182085648904871, | |
| "eval_loss": 1.4056382179260254, | |
| "eval_runtime": 0.8973, | |
| "eval_samples_per_second": 557.236, | |
| "eval_steps_per_second": 35.663, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 17.34, | |
| "learning_rate": 2.111309736622572e-05, | |
| "loss": 1.0654, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 17.34, | |
| "eval_accuracy": 0.727630285152409, | |
| "eval_loss": 1.3769292831420898, | |
| "eval_runtime": 0.8377, | |
| "eval_samples_per_second": 596.886, | |
| "eval_steps_per_second": 38.201, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "learning_rate": 2.081515909903468e-05, | |
| "loss": 1.0676, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 17.52, | |
| "eval_accuracy": 0.7224234441883438, | |
| "eval_loss": 1.33571457862854, | |
| "eval_runtime": 0.7909, | |
| "eval_samples_per_second": 632.166, | |
| "eval_steps_per_second": 40.459, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 2.0517220831843643e-05, | |
| "loss": 1.0507, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "eval_accuracy": 0.712369109947644, | |
| "eval_loss": 1.4087713956832886, | |
| "eval_runtime": 0.7955, | |
| "eval_samples_per_second": 628.504, | |
| "eval_steps_per_second": 40.224, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 17.88, | |
| "learning_rate": 2.0219282564652605e-05, | |
| "loss": 1.0424, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 17.88, | |
| "eval_accuracy": 0.7314667515112949, | |
| "eval_loss": 1.3146371841430664, | |
| "eval_runtime": 0.7881, | |
| "eval_samples_per_second": 634.428, | |
| "eval_steps_per_second": 40.603, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 1.9921344297461568e-05, | |
| "loss": 1.0524, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "eval_accuracy": 0.7393395319012503, | |
| "eval_loss": 1.28960382938385, | |
| "eval_runtime": 0.8581, | |
| "eval_samples_per_second": 582.683, | |
| "eval_steps_per_second": 37.292, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 1.962340603027053e-05, | |
| "loss": 1.0349, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "eval_accuracy": 0.7191558441558441, | |
| "eval_loss": 1.3986730575561523, | |
| "eval_runtime": 0.7904, | |
| "eval_samples_per_second": 632.599, | |
| "eval_steps_per_second": 40.486, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 1.932546776307949e-05, | |
| "loss": 1.0217, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "eval_accuracy": 0.7380645161290322, | |
| "eval_loss": 1.2937612533569336, | |
| "eval_runtime": 0.8575, | |
| "eval_samples_per_second": 583.089, | |
| "eval_steps_per_second": 37.318, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 1.9028125372422833e-05, | |
| "loss": 1.0238, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "eval_accuracy": 0.738654650788542, | |
| "eval_loss": 1.296163558959961, | |
| "eval_runtime": 0.8423, | |
| "eval_samples_per_second": 593.617, | |
| "eval_steps_per_second": 37.992, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "learning_rate": 1.87301871052318e-05, | |
| "loss": 1.0292, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "eval_accuracy": 0.737131757850437, | |
| "eval_loss": 1.3194587230682373, | |
| "eval_runtime": 0.8232, | |
| "eval_samples_per_second": 607.358, | |
| "eval_steps_per_second": 38.871, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "learning_rate": 1.8433440591109523e-05, | |
| "loss": 1.0426, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 18.95, | |
| "eval_accuracy": 0.7411687025420931, | |
| "eval_loss": 1.2835460901260376, | |
| "eval_runtime": 0.7859, | |
| "eval_samples_per_second": 636.221, | |
| "eval_steps_per_second": 40.718, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 1.8135502323918486e-05, | |
| "loss": 1.0196, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "eval_accuracy": 0.747275204359673, | |
| "eval_loss": 1.234621524810791, | |
| "eval_runtime": 0.8361, | |
| "eval_samples_per_second": 597.997, | |
| "eval_steps_per_second": 38.272, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 1.7837564056727445e-05, | |
| "loss": 1.012, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "eval_accuracy": 0.7338292367399741, | |
| "eval_loss": 1.3665757179260254, | |
| "eval_runtime": 0.8157, | |
| "eval_samples_per_second": 612.938, | |
| "eval_steps_per_second": 39.228, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 1.753962578953641e-05, | |
| "loss": 1.0256, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "eval_accuracy": 0.7364842991259307, | |
| "eval_loss": 1.3140363693237305, | |
| "eval_runtime": 0.7949, | |
| "eval_samples_per_second": 628.974, | |
| "eval_steps_per_second": 40.254, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 1.724168752234537e-05, | |
| "loss": 0.9824, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "eval_accuracy": 0.7416496250852079, | |
| "eval_loss": 1.2764383554458618, | |
| "eval_runtime": 0.8178, | |
| "eval_samples_per_second": 611.417, | |
| "eval_steps_per_second": 39.131, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.6943749255154336e-05, | |
| "loss": 1.0048, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "eval_accuracy": 0.7487891507910881, | |
| "eval_loss": 1.2514091730117798, | |
| "eval_runtime": 0.8164, | |
| "eval_samples_per_second": 612.474, | |
| "eval_steps_per_second": 39.198, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 1.6645810987963295e-05, | |
| "loss": 0.9947, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_accuracy": 0.7431572246976448, | |
| "eval_loss": 1.3350915908813477, | |
| "eval_runtime": 0.7912, | |
| "eval_samples_per_second": 631.988, | |
| "eval_steps_per_second": 40.447, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "learning_rate": 1.634846859730664e-05, | |
| "loss": 0.977, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "eval_accuracy": 0.7451045469631596, | |
| "eval_loss": 1.2854044437408447, | |
| "eval_runtime": 0.8499, | |
| "eval_samples_per_second": 588.28, | |
| "eval_steps_per_second": 37.65, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 20.38, | |
| "learning_rate": 1.60505303301156e-05, | |
| "loss": 0.9862, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 20.38, | |
| "eval_accuracy": 0.7285475792988314, | |
| "eval_loss": 1.366584300994873, | |
| "eval_runtime": 0.816, | |
| "eval_samples_per_second": 612.774, | |
| "eval_steps_per_second": 39.218, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "learning_rate": 1.5752592062924564e-05, | |
| "loss": 0.9699, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "eval_accuracy": 0.7347811780190853, | |
| "eval_loss": 1.3123427629470825, | |
| "eval_runtime": 0.7779, | |
| "eval_samples_per_second": 642.731, | |
| "eval_steps_per_second": 41.135, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 20.74, | |
| "learning_rate": 1.5454653795733526e-05, | |
| "loss": 0.977, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 20.74, | |
| "eval_accuracy": 0.7254770672915969, | |
| "eval_loss": 1.3425793647766113, | |
| "eval_runtime": 0.8285, | |
| "eval_samples_per_second": 603.485, | |
| "eval_steps_per_second": 38.623, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "learning_rate": 1.5157311405076868e-05, | |
| "loss": 0.9749, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.7296604740550929, | |
| "eval_loss": 1.3763371706008911, | |
| "eval_runtime": 0.7855, | |
| "eval_samples_per_second": 636.556, | |
| "eval_steps_per_second": 40.74, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 1.4859373137885832e-05, | |
| "loss": 0.9505, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "eval_accuracy": 0.7434469200524246, | |
| "eval_loss": 1.2372225522994995, | |
| "eval_runtime": 0.7967, | |
| "eval_samples_per_second": 627.592, | |
| "eval_steps_per_second": 40.166, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 1.4561434870694793e-05, | |
| "loss": 0.9438, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "eval_accuracy": 0.7159090909090909, | |
| "eval_loss": 1.433412790298462, | |
| "eval_runtime": 0.7929, | |
| "eval_samples_per_second": 630.567, | |
| "eval_steps_per_second": 40.356, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "learning_rate": 1.4263496603503754e-05, | |
| "loss": 0.944, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "eval_accuracy": 0.7507936507936508, | |
| "eval_loss": 1.269033432006836, | |
| "eval_runtime": 0.8274, | |
| "eval_samples_per_second": 604.314, | |
| "eval_steps_per_second": 38.676, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 21.63, | |
| "learning_rate": 1.3965558336312718e-05, | |
| "loss": 0.9427, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 21.63, | |
| "eval_accuracy": 0.7485941118094608, | |
| "eval_loss": 1.2185914516448975, | |
| "eval_runtime": 0.7923, | |
| "eval_samples_per_second": 631.05, | |
| "eval_steps_per_second": 40.387, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 21.81, | |
| "learning_rate": 1.3667620069121679e-05, | |
| "loss": 0.9553, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 21.81, | |
| "eval_accuracy": 0.726882430647292, | |
| "eval_loss": 1.3940554857254028, | |
| "eval_runtime": 0.7961, | |
| "eval_samples_per_second": 628.083, | |
| "eval_steps_per_second": 40.197, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "learning_rate": 1.3369681801930641e-05, | |
| "loss": 0.9571, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "eval_accuracy": 0.7273940607273941, | |
| "eval_loss": 1.4162867069244385, | |
| "eval_runtime": 0.791, | |
| "eval_samples_per_second": 632.128, | |
| "eval_steps_per_second": 40.456, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 22.17, | |
| "learning_rate": 1.3071743534739602e-05, | |
| "loss": 0.932, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 22.17, | |
| "eval_accuracy": 0.7522727272727273, | |
| "eval_loss": 1.2717351913452148, | |
| "eval_runtime": 0.796, | |
| "eval_samples_per_second": 628.103, | |
| "eval_steps_per_second": 40.199, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 22.35, | |
| "learning_rate": 1.2773805267548563e-05, | |
| "loss": 0.9166, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 22.35, | |
| "eval_accuracy": 0.73956326268465, | |
| "eval_loss": 1.217714786529541, | |
| "eval_runtime": 0.8289, | |
| "eval_samples_per_second": 603.185, | |
| "eval_steps_per_second": 38.604, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 22.52, | |
| "learning_rate": 1.2475867000357526e-05, | |
| "loss": 0.9301, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 22.52, | |
| "eval_accuracy": 0.7377950210151956, | |
| "eval_loss": 1.3264496326446533, | |
| "eval_runtime": 0.8524, | |
| "eval_samples_per_second": 586.56, | |
| "eval_steps_per_second": 37.54, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "learning_rate": 1.2177928733166488e-05, | |
| "loss": 0.9351, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "eval_accuracy": 0.752010292698617, | |
| "eval_loss": 1.2570440769195557, | |
| "eval_runtime": 0.785, | |
| "eval_samples_per_second": 636.94, | |
| "eval_steps_per_second": 40.764, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 1.1879990465975451e-05, | |
| "loss": 0.9211, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 1.2638896703720093, | |
| "eval_runtime": 0.8753, | |
| "eval_samples_per_second": 571.265, | |
| "eval_steps_per_second": 36.561, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 1.1582052198784414e-05, | |
| "loss": 0.9211, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "eval_accuracy": 0.7605543022881083, | |
| "eval_loss": 1.2376515865325928, | |
| "eval_runtime": 0.7946, | |
| "eval_samples_per_second": 629.265, | |
| "eval_steps_per_second": 40.273, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 23.24, | |
| "learning_rate": 1.1284113931593374e-05, | |
| "loss": 0.9196, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 23.24, | |
| "eval_accuracy": 0.7485168094924193, | |
| "eval_loss": 1.2738728523254395, | |
| "eval_runtime": 0.8576, | |
| "eval_samples_per_second": 583.036, | |
| "eval_steps_per_second": 37.314, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 23.42, | |
| "learning_rate": 1.098677154093672e-05, | |
| "loss": 0.9062, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 23.42, | |
| "eval_accuracy": 0.7365366010964205, | |
| "eval_loss": 1.3262896537780762, | |
| "eval_runtime": 0.8401, | |
| "eval_samples_per_second": 595.164, | |
| "eval_steps_per_second": 38.09, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 1.068883327374568e-05, | |
| "loss": 0.8965, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "eval_accuracy": 0.7455209024552091, | |
| "eval_loss": 1.2814128398895264, | |
| "eval_runtime": 0.778, | |
| "eval_samples_per_second": 642.691, | |
| "eval_steps_per_second": 41.132, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 23.78, | |
| "learning_rate": 1.0392086759623406e-05, | |
| "loss": 0.9004, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 23.78, | |
| "eval_accuracy": 0.7561779242174629, | |
| "eval_loss": 1.2108628749847412, | |
| "eval_runtime": 0.8669, | |
| "eval_samples_per_second": 576.736, | |
| "eval_steps_per_second": 36.911, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "learning_rate": 1.0094148492432369e-05, | |
| "loss": 0.9094, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 23.95, | |
| "eval_accuracy": 0.7528089887640449, | |
| "eval_loss": 1.2629289627075195, | |
| "eval_runtime": 0.8653, | |
| "eval_samples_per_second": 577.859, | |
| "eval_steps_per_second": 36.983, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "learning_rate": 9.79621022524133e-06, | |
| "loss": 0.8937, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "eval_accuracy": 0.7375168690958165, | |
| "eval_loss": 1.2770532369613647, | |
| "eval_runtime": 0.8492, | |
| "eval_samples_per_second": 588.814, | |
| "eval_steps_per_second": 37.684, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 24.31, | |
| "learning_rate": 9.498271958050292e-06, | |
| "loss": 0.8711, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 24.31, | |
| "eval_accuracy": 0.7353233830845771, | |
| "eval_loss": 1.3746039867401123, | |
| "eval_runtime": 0.7929, | |
| "eval_samples_per_second": 630.629, | |
| "eval_steps_per_second": 40.36, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "learning_rate": 9.200333690859255e-06, | |
| "loss": 0.8972, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 24.49, | |
| "eval_accuracy": 0.7453750420450723, | |
| "eval_loss": 1.2529133558273315, | |
| "eval_runtime": 0.8497, | |
| "eval_samples_per_second": 588.462, | |
| "eval_steps_per_second": 37.662, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 24.67, | |
| "learning_rate": 8.902395423668217e-06, | |
| "loss": 0.8863, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 24.67, | |
| "eval_accuracy": 0.7359154929577465, | |
| "eval_loss": 1.3219196796417236, | |
| "eval_runtime": 0.8149, | |
| "eval_samples_per_second": 613.598, | |
| "eval_steps_per_second": 39.27, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "learning_rate": 8.604457156477178e-06, | |
| "loss": 0.8823, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 24.85, | |
| "eval_accuracy": 0.7367235275185066, | |
| "eval_loss": 1.313620924949646, | |
| "eval_runtime": 0.8311, | |
| "eval_samples_per_second": 601.621, | |
| "eval_steps_per_second": 38.504, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 25.03, | |
| "learning_rate": 8.306518889286139e-06, | |
| "loss": 0.8759, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 25.03, | |
| "eval_accuracy": 0.7427812811151676, | |
| "eval_loss": 1.3151708841323853, | |
| "eval_runtime": 0.7986, | |
| "eval_samples_per_second": 626.093, | |
| "eval_steps_per_second": 40.07, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "learning_rate": 8.008580622095102e-06, | |
| "loss": 0.8722, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "eval_accuracy": 0.7569644572526417, | |
| "eval_loss": 1.3108021020889282, | |
| "eval_runtime": 0.8281, | |
| "eval_samples_per_second": 603.782, | |
| "eval_steps_per_second": 38.642, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 7.710642354904064e-06, | |
| "loss": 0.8548, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "eval_accuracy": 0.7367716008037508, | |
| "eval_loss": 1.3503183126449585, | |
| "eval_runtime": 0.7871, | |
| "eval_samples_per_second": 635.233, | |
| "eval_steps_per_second": 40.655, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "learning_rate": 7.412704087713027e-06, | |
| "loss": 0.8728, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "eval_accuracy": 0.7402768622280818, | |
| "eval_loss": 1.3091211318969727, | |
| "eval_runtime": 0.8581, | |
| "eval_samples_per_second": 582.712, | |
| "eval_steps_per_second": 37.294, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 25.74, | |
| "learning_rate": 7.114765820521989e-06, | |
| "loss": 0.8633, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 25.74, | |
| "eval_accuracy": 0.7416481069042317, | |
| "eval_loss": 1.2952070236206055, | |
| "eval_runtime": 0.8515, | |
| "eval_samples_per_second": 587.213, | |
| "eval_steps_per_second": 37.582, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 6.816827553330949e-06, | |
| "loss": 0.8612, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "eval_accuracy": 0.7719072164948454, | |
| "eval_loss": 1.1612097024917603, | |
| "eval_runtime": 0.7967, | |
| "eval_samples_per_second": 627.618, | |
| "eval_steps_per_second": 40.168, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 26.1, | |
| "learning_rate": 6.5194851626742935e-06, | |
| "loss": 0.8677, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 26.1, | |
| "eval_accuracy": 0.7449731903485255, | |
| "eval_loss": 1.2855061292648315, | |
| "eval_runtime": 0.8112, | |
| "eval_samples_per_second": 616.391, | |
| "eval_steps_per_second": 39.449, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "learning_rate": 6.2221427720176384e-06, | |
| "loss": 0.8526, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 26.28, | |
| "eval_accuracy": 0.7544929396662388, | |
| "eval_loss": 1.297914981842041, | |
| "eval_runtime": 0.8472, | |
| "eval_samples_per_second": 590.203, | |
| "eval_steps_per_second": 37.773, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 26.46, | |
| "learning_rate": 5.9242045048266e-06, | |
| "loss": 0.8594, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 26.46, | |
| "eval_accuracy": 0.7598070739549839, | |
| "eval_loss": 1.2569819688796997, | |
| "eval_runtime": 0.7923, | |
| "eval_samples_per_second": 631.066, | |
| "eval_steps_per_second": 40.388, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 5.626266237635562e-06, | |
| "loss": 0.8481, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "eval_accuracy": 0.7491992312620115, | |
| "eval_loss": 1.2336714267730713, | |
| "eval_runtime": 0.8668, | |
| "eval_samples_per_second": 576.839, | |
| "eval_steps_per_second": 36.918, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "learning_rate": 5.3283279704445245e-06, | |
| "loss": 0.855, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "eval_accuracy": 0.7443507588532884, | |
| "eval_loss": 1.2874828577041626, | |
| "eval_runtime": 0.7926, | |
| "eval_samples_per_second": 630.803, | |
| "eval_steps_per_second": 40.371, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "learning_rate": 5.030389703253486e-06, | |
| "loss": 0.835, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.7584731819677526, | |
| "eval_loss": 1.2270281314849854, | |
| "eval_runtime": 0.8172, | |
| "eval_samples_per_second": 611.826, | |
| "eval_steps_per_second": 39.157, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 27.17, | |
| "learning_rate": 4.732451436062448e-06, | |
| "loss": 0.8309, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 27.17, | |
| "eval_accuracy": 0.7389322916666666, | |
| "eval_loss": 1.2539992332458496, | |
| "eval_runtime": 0.8357, | |
| "eval_samples_per_second": 598.292, | |
| "eval_steps_per_second": 38.291, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 27.35, | |
| "learning_rate": 4.43451316887141e-06, | |
| "loss": 0.8326, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 27.35, | |
| "eval_accuracy": 0.7374631268436578, | |
| "eval_loss": 1.3610546588897705, | |
| "eval_runtime": 0.7953, | |
| "eval_samples_per_second": 628.676, | |
| "eval_steps_per_second": 40.235, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 27.53, | |
| "learning_rate": 4.136574901680372e-06, | |
| "loss": 0.8398, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 27.53, | |
| "eval_accuracy": 0.7504918032786885, | |
| "eval_loss": 1.2247506380081177, | |
| "eval_runtime": 0.859, | |
| "eval_samples_per_second": 582.099, | |
| "eval_steps_per_second": 37.254, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 27.71, | |
| "learning_rate": 3.838636634489334e-06, | |
| "loss": 0.8304, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 27.71, | |
| "eval_accuracy": 0.7607282184655396, | |
| "eval_loss": 1.2403171062469482, | |
| "eval_runtime": 0.9471, | |
| "eval_samples_per_second": 527.922, | |
| "eval_steps_per_second": 33.787, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "learning_rate": 3.5406983672982957e-06, | |
| "loss": 0.8373, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 27.89, | |
| "eval_accuracy": 0.7611295681063123, | |
| "eval_loss": 1.1708660125732422, | |
| "eval_runtime": 0.8284, | |
| "eval_samples_per_second": 603.609, | |
| "eval_steps_per_second": 38.631, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 28.07, | |
| "learning_rate": 3.2427601001072583e-06, | |
| "loss": 0.8462, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 28.07, | |
| "eval_accuracy": 0.7508185985592666, | |
| "eval_loss": 1.289104700088501, | |
| "eval_runtime": 0.8603, | |
| "eval_samples_per_second": 581.16, | |
| "eval_steps_per_second": 37.194, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 2.945417709450602e-06, | |
| "loss": 0.8259, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "eval_accuracy": 0.7500814597588791, | |
| "eval_loss": 1.2452012300491333, | |
| "eval_runtime": 0.8046, | |
| "eval_samples_per_second": 621.394, | |
| "eval_steps_per_second": 39.769, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "learning_rate": 2.647479442259564e-06, | |
| "loss": 0.8334, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 28.42, | |
| "eval_accuracy": 0.746810598626104, | |
| "eval_loss": 1.2985996007919312, | |
| "eval_runtime": 0.9197, | |
| "eval_samples_per_second": 543.676, | |
| "eval_steps_per_second": 34.795, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 28.6, | |
| "learning_rate": 2.349541175068526e-06, | |
| "loss": 0.8115, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 28.6, | |
| "eval_accuracy": 0.7514638906961614, | |
| "eval_loss": 1.2879589796066284, | |
| "eval_runtime": 0.7986, | |
| "eval_samples_per_second": 626.129, | |
| "eval_steps_per_second": 40.072, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 28.78, | |
| "learning_rate": 2.0516029078774876e-06, | |
| "loss": 0.8205, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 28.78, | |
| "eval_accuracy": 0.75615359369872, | |
| "eval_loss": 1.2727956771850586, | |
| "eval_runtime": 0.8652, | |
| "eval_samples_per_second": 577.899, | |
| "eval_steps_per_second": 36.986, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.7536646406864498e-06, | |
| "loss": 0.8261, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "eval_accuracy": 0.7523561910952227, | |
| "eval_loss": 1.2660555839538574, | |
| "eval_runtime": 0.7893, | |
| "eval_samples_per_second": 633.494, | |
| "eval_steps_per_second": 40.544, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "learning_rate": 1.4563222500297937e-06, | |
| "loss": 0.8299, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 29.14, | |
| "eval_accuracy": 0.7486106570774763, | |
| "eval_loss": 1.25924813747406, | |
| "eval_runtime": 0.8513, | |
| "eval_samples_per_second": 587.342, | |
| "eval_steps_per_second": 37.59, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "learning_rate": 1.1583839828387559e-06, | |
| "loss": 0.8276, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "eval_accuracy": 0.7529644268774703, | |
| "eval_loss": 1.2325080633163452, | |
| "eval_runtime": 0.8587, | |
| "eval_samples_per_second": 582.291, | |
| "eval_steps_per_second": 37.267, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 8.604457156477178e-07, | |
| "loss": 0.8112, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "eval_accuracy": 0.7477890599410416, | |
| "eval_loss": 1.3154096603393555, | |
| "eval_runtime": 0.8166, | |
| "eval_samples_per_second": 612.267, | |
| "eval_steps_per_second": 39.185, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "learning_rate": 5.625074484566799e-07, | |
| "loss": 0.8111, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "eval_accuracy": 0.740531561461794, | |
| "eval_loss": 1.3342524766921997, | |
| "eval_runtime": 0.8076, | |
| "eval_samples_per_second": 619.083, | |
| "eval_steps_per_second": 39.621, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 2.645691812656418e-07, | |
| "loss": 0.8148, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "eval_accuracy": 0.7484622855292975, | |
| "eval_loss": 1.2806158065795898, | |
| "eval_runtime": 0.8122, | |
| "eval_samples_per_second": 615.596, | |
| "eval_steps_per_second": 39.398, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 83910, | |
| "total_flos": 3.583580261367381e+17, | |
| "train_loss": 1.1746184680817338, | |
| "train_runtime": 16410.0948, | |
| "train_samples_per_second": 163.619, | |
| "train_steps_per_second": 5.113 | |
| } | |
| ], | |
| "max_steps": 83910, | |
| "num_train_epochs": 30, | |
| "total_flos": 3.583580261367381e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |