| { | |
| "best_metric": 0.58837890625, | |
| "best_model_checkpoint": "/output/checkpoint-3300", | |
| "epoch": 10.0, | |
| "global_step": 17620, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.8214358287770616, | |
| "eval_loss": 0.79296875, | |
| "eval_runtime": 301.7299, | |
| "eval_samples_per_second": 14.301, | |
| "eval_steps_per_second": 1.79, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.828983212304709, | |
| "eval_loss": 0.75439453125, | |
| "eval_runtime": 295.5652, | |
| "eval_samples_per_second": 14.599, | |
| "eval_steps_per_second": 1.827, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.83275463867547, | |
| "eval_loss": 0.73583984375, | |
| "eval_runtime": 297.8323, | |
| "eval_samples_per_second": 14.488, | |
| "eval_steps_per_second": 1.813, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.8357279670702464, | |
| "eval_loss": 0.71923828125, | |
| "eval_runtime": 297.4382, | |
| "eval_samples_per_second": 14.507, | |
| "eval_steps_per_second": 1.816, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8156, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_accuracy": 0.8396754144819782, | |
| "eval_loss": 0.701171875, | |
| "eval_runtime": 295.955, | |
| "eval_samples_per_second": 14.58, | |
| "eval_steps_per_second": 1.825, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.8418578941585707, | |
| "eval_loss": 0.6904296875, | |
| "eval_runtime": 305.3997, | |
| "eval_samples_per_second": 14.129, | |
| "eval_steps_per_second": 1.768, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.8439807939976145, | |
| "eval_loss": 0.68017578125, | |
| "eval_runtime": 303.944, | |
| "eval_samples_per_second": 14.197, | |
| "eval_steps_per_second": 1.777, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.8464999110833223, | |
| "eval_loss": 0.6669921875, | |
| "eval_runtime": 297.0827, | |
| "eval_samples_per_second": 14.525, | |
| "eval_steps_per_second": 1.818, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.8485815807686252, | |
| "eval_loss": 0.6572265625, | |
| "eval_runtime": 292.5803, | |
| "eval_samples_per_second": 14.748, | |
| "eval_steps_per_second": 1.846, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7219, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_accuracy": 0.8500273546212319, | |
| "eval_loss": 0.64990234375, | |
| "eval_runtime": 292.7704, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.844, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.8521808372666221, | |
| "eval_loss": 0.64111328125, | |
| "eval_runtime": 292.5084, | |
| "eval_samples_per_second": 14.752, | |
| "eval_steps_per_second": 1.846, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.853712016437692, | |
| "eval_loss": 0.63427734375, | |
| "eval_runtime": 292.6573, | |
| "eval_samples_per_second": 14.744, | |
| "eval_steps_per_second": 1.845, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.8545884970136456, | |
| "eval_loss": 0.6298828125, | |
| "eval_runtime": 291.6972, | |
| "eval_samples_per_second": 14.793, | |
| "eval_steps_per_second": 1.851, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.856088866839063, | |
| "eval_loss": 0.6220703125, | |
| "eval_runtime": 291.6264, | |
| "eval_samples_per_second": 14.796, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5e-05, | |
| "loss": 0.662, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.857388975917739, | |
| "eval_loss": 0.61572265625, | |
| "eval_runtime": 292.8293, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.8579150001868949, | |
| "eval_loss": 0.61376953125, | |
| "eval_runtime": 292.6424, | |
| "eval_samples_per_second": 14.745, | |
| "eval_steps_per_second": 1.845, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.8595497078209298, | |
| "eval_loss": 0.60546875, | |
| "eval_runtime": 292.7935, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.844, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8597678651728665, | |
| "eval_loss": 0.6142578125, | |
| "eval_runtime": 292.6887, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_accuracy": 0.8598800021294695, | |
| "eval_loss": 0.619140625, | |
| "eval_runtime": 291.7039, | |
| "eval_samples_per_second": 14.792, | |
| "eval_steps_per_second": 1.851, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5707, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.8606622423540152, | |
| "eval_loss": 0.61181640625, | |
| "eval_runtime": 292.661, | |
| "eval_samples_per_second": 14.744, | |
| "eval_steps_per_second": 1.845, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.8611497549411055, | |
| "eval_loss": 0.6123046875, | |
| "eval_runtime": 292.734, | |
| "eval_samples_per_second": 14.74, | |
| "eval_steps_per_second": 1.845, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_accuracy": 0.8616524456617156, | |
| "eval_loss": 0.60888671875, | |
| "eval_runtime": 291.6011, | |
| "eval_samples_per_second": 14.798, | |
| "eval_steps_per_second": 1.852, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.8618950692587294, | |
| "eval_loss": 0.6064453125, | |
| "eval_runtime": 291.5809, | |
| "eval_samples_per_second": 14.799, | |
| "eval_steps_per_second": 1.852, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.8625089907787176, | |
| "eval_loss": 0.60791015625, | |
| "eval_runtime": 292.7393, | |
| "eval_samples_per_second": 14.74, | |
| "eval_steps_per_second": 1.845, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4923, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_accuracy": 0.8624713852538769, | |
| "eval_loss": 0.60400390625, | |
| "eval_runtime": 292.7894, | |
| "eval_samples_per_second": 14.738, | |
| "eval_steps_per_second": 1.844, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.8630089630276525, | |
| "eval_loss": 0.60302734375, | |
| "eval_runtime": 291.5842, | |
| "eval_samples_per_second": 14.798, | |
| "eval_steps_per_second": 1.852, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_accuracy": 0.8636167679863714, | |
| "eval_loss": 0.60205078125, | |
| "eval_runtime": 291.6586, | |
| "eval_samples_per_second": 14.795, | |
| "eval_steps_per_second": 1.851, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_accuracy": 0.8643006901519965, | |
| "eval_loss": 0.60009765625, | |
| "eval_runtime": 291.5536, | |
| "eval_samples_per_second": 14.8, | |
| "eval_steps_per_second": 1.852, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_accuracy": 0.864360949607464, | |
| "eval_loss": 0.59814453125, | |
| "eval_runtime": 292.9127, | |
| "eval_samples_per_second": 14.731, | |
| "eval_steps_per_second": 1.844, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4909, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_accuracy": 0.8647961316148062, | |
| "eval_loss": 0.59423828125, | |
| "eval_runtime": 292.7189, | |
| "eval_samples_per_second": 14.741, | |
| "eval_steps_per_second": 1.845, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.8649898227216659, | |
| "eval_loss": 0.591796875, | |
| "eval_runtime": 291.4828, | |
| "eval_samples_per_second": 14.804, | |
| "eval_steps_per_second": 1.853, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_accuracy": 0.8659145561698547, | |
| "eval_loss": 0.59228515625, | |
| "eval_runtime": 291.6085, | |
| "eval_samples_per_second": 14.797, | |
| "eval_steps_per_second": 1.852, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.8663780555904803, | |
| "eval_loss": 0.58837890625, | |
| "eval_runtime": 291.6163, | |
| "eval_samples_per_second": 14.797, | |
| "eval_steps_per_second": 1.852, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_accuracy": 0.8662514201182762, | |
| "eval_loss": 0.58837890625, | |
| "eval_runtime": 291.7936, | |
| "eval_samples_per_second": 14.788, | |
| "eval_steps_per_second": 1.851, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4964, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.8669489346422774, | |
| "eval_loss": 0.59033203125, | |
| "eval_runtime": 291.5679, | |
| "eval_samples_per_second": 14.799, | |
| "eval_steps_per_second": 1.852, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.8654691798937304, | |
| "eval_loss": 0.64208984375, | |
| "eval_runtime": 291.7326, | |
| "eval_samples_per_second": 14.791, | |
| "eval_steps_per_second": 1.851, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.8650994677459, | |
| "eval_loss": 0.64013671875, | |
| "eval_runtime": 293.0337, | |
| "eval_samples_per_second": 14.725, | |
| "eval_steps_per_second": 1.843, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_accuracy": 0.8649474598713937, | |
| "eval_loss": 0.64111328125, | |
| "eval_runtime": 291.5404, | |
| "eval_samples_per_second": 14.801, | |
| "eval_steps_per_second": 1.852, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_accuracy": 0.8645410483559476, | |
| "eval_loss": 0.638671875, | |
| "eval_runtime": 291.6679, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 5e-05, | |
| "loss": 0.345, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.8653572694764337, | |
| "eval_loss": 0.63623046875, | |
| "eval_runtime": 291.7901, | |
| "eval_samples_per_second": 14.788, | |
| "eval_steps_per_second": 1.851, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.8654186616284325, | |
| "eval_loss": 0.63623046875, | |
| "eval_runtime": 291.6935, | |
| "eval_samples_per_second": 14.793, | |
| "eval_steps_per_second": 1.851, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_accuracy": 0.8653559102405961, | |
| "eval_loss": 0.63623046875, | |
| "eval_runtime": 291.8601, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 1.85, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_accuracy": 0.8654696329723429, | |
| "eval_loss": 0.6357421875, | |
| "eval_runtime": 292.876, | |
| "eval_samples_per_second": 14.733, | |
| "eval_steps_per_second": 1.844, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_accuracy": 0.8655647794809758, | |
| "eval_loss": 0.63623046875, | |
| "eval_runtime": 291.8742, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 1.85, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3463, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_accuracy": 0.865790865708632, | |
| "eval_loss": 0.6376953125, | |
| "eval_runtime": 292.8657, | |
| "eval_samples_per_second": 14.734, | |
| "eval_steps_per_second": 1.844, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_accuracy": 0.8660047188137496, | |
| "eval_loss": 0.6357421875, | |
| "eval_runtime": 292.8962, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 1.844, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_accuracy": 0.8664827167499765, | |
| "eval_loss": 0.62939453125, | |
| "eval_runtime": 291.8634, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 1.85, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.8664838494465078, | |
| "eval_loss": 0.63330078125, | |
| "eval_runtime": 292.9139, | |
| "eval_samples_per_second": 14.731, | |
| "eval_steps_per_second": 1.844, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_accuracy": 0.8661707721252445, | |
| "eval_loss": 0.63623046875, | |
| "eval_runtime": 291.8657, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 1.85, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3508, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_accuracy": 0.8666297407597449, | |
| "eval_loss": 0.6357421875, | |
| "eval_runtime": 291.8826, | |
| "eval_samples_per_second": 14.783, | |
| "eval_steps_per_second": 1.85, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.8673172875542703, | |
| "eval_loss": 0.6298828125, | |
| "eval_runtime": 291.7729, | |
| "eval_samples_per_second": 14.789, | |
| "eval_steps_per_second": 1.851, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_accuracy": 0.866801004475284, | |
| "eval_loss": 0.63134765625, | |
| "eval_runtime": 291.9322, | |
| "eval_samples_per_second": 14.781, | |
| "eval_steps_per_second": 1.85, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_accuracy": 0.8646230555848169, | |
| "eval_loss": 0.71875, | |
| "eval_runtime": 291.8776, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 1.85, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.8655867537936839, | |
| "eval_loss": 0.70166015625, | |
| "eval_runtime": 293.0438, | |
| "eval_samples_per_second": 14.725, | |
| "eval_steps_per_second": 1.843, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.295, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_accuracy": 0.8652775276406272, | |
| "eval_loss": 0.6982421875, | |
| "eval_runtime": 291.9251, | |
| "eval_samples_per_second": 14.781, | |
| "eval_steps_per_second": 1.85, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "eval_accuracy": 0.8654533221422916, | |
| "eval_loss": 0.703125, | |
| "eval_runtime": 292.9873, | |
| "eval_samples_per_second": 14.728, | |
| "eval_steps_per_second": 1.843, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "eval_accuracy": 0.8650992412065936, | |
| "eval_loss": 0.69921875, | |
| "eval_runtime": 293.1169, | |
| "eval_samples_per_second": 14.721, | |
| "eval_steps_per_second": 1.842, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_accuracy": 0.8652641618215573, | |
| "eval_loss": 0.69970703125, | |
| "eval_runtime": 293.0467, | |
| "eval_samples_per_second": 14.725, | |
| "eval_steps_per_second": 1.843, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_accuracy": 0.865102865835494, | |
| "eval_loss": 0.7041015625, | |
| "eval_runtime": 292.9654, | |
| "eval_samples_per_second": 14.729, | |
| "eval_steps_per_second": 1.843, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2348, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_accuracy": 0.8649191424581101, | |
| "eval_loss": 0.70751953125, | |
| "eval_runtime": 291.6546, | |
| "eval_samples_per_second": 14.795, | |
| "eval_steps_per_second": 1.852, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_accuracy": 0.8649929942719536, | |
| "eval_loss": 0.69921875, | |
| "eval_runtime": 293.0033, | |
| "eval_samples_per_second": 14.727, | |
| "eval_steps_per_second": 1.843, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_accuracy": 0.8647333802269698, | |
| "eval_loss": 0.70654296875, | |
| "eval_runtime": 292.0433, | |
| "eval_samples_per_second": 14.775, | |
| "eval_steps_per_second": 1.849, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "eval_accuracy": 0.8651932550186952, | |
| "eval_loss": 0.69970703125, | |
| "eval_runtime": 292.8338, | |
| "eval_samples_per_second": 14.735, | |
| "eval_steps_per_second": 1.844, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_accuracy": 0.8651128335649698, | |
| "eval_loss": 0.70263671875, | |
| "eval_runtime": 291.8152, | |
| "eval_samples_per_second": 14.787, | |
| "eval_steps_per_second": 1.85, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2411, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "eval_accuracy": 0.8655713491208575, | |
| "eval_loss": 0.70458984375, | |
| "eval_runtime": 292.9241, | |
| "eval_samples_per_second": 14.731, | |
| "eval_steps_per_second": 1.843, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "eval_accuracy": 0.8655097304295525, | |
| "eval_loss": 0.70068359375, | |
| "eval_runtime": 293.0902, | |
| "eval_samples_per_second": 14.722, | |
| "eval_steps_per_second": 1.842, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_accuracy": 0.8651318628666963, | |
| "eval_loss": 0.70263671875, | |
| "eval_runtime": 292.9879, | |
| "eval_samples_per_second": 14.728, | |
| "eval_steps_per_second": 1.843, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_accuracy": 0.8654825457128003, | |
| "eval_loss": 0.703125, | |
| "eval_runtime": 292.8939, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 1.844, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_accuracy": 0.8657906391693256, | |
| "eval_loss": 0.701171875, | |
| "eval_runtime": 292.7957, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.844, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 5e-05, | |
| "loss": 0.251, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "eval_accuracy": 0.8656236797006056, | |
| "eval_loss": 0.705078125, | |
| "eval_runtime": 292.768, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.844, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_accuracy": 0.8650197259100934, | |
| "eval_loss": 0.7607421875, | |
| "eval_runtime": 293.0243, | |
| "eval_samples_per_second": 14.726, | |
| "eval_steps_per_second": 1.843, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_accuracy": 0.8655654590988946, | |
| "eval_loss": 0.76318359375, | |
| "eval_runtime": 293.1258, | |
| "eval_samples_per_second": 14.721, | |
| "eval_steps_per_second": 1.842, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "eval_accuracy": 0.8654986300035453, | |
| "eval_loss": 0.7587890625, | |
| "eval_runtime": 291.7489, | |
| "eval_samples_per_second": 14.79, | |
| "eval_steps_per_second": 1.851, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_accuracy": 0.8650992412065936, | |
| "eval_loss": 0.7578125, | |
| "eval_runtime": 291.7365, | |
| "eval_samples_per_second": 14.791, | |
| "eval_steps_per_second": 1.851, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1797, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "eval_accuracy": 0.8644635719132038, | |
| "eval_loss": 0.77099609375, | |
| "eval_runtime": 292.8962, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 1.844, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_accuracy": 0.8648369086899346, | |
| "eval_loss": 0.7626953125, | |
| "eval_runtime": 291.9443, | |
| "eval_samples_per_second": 14.78, | |
| "eval_steps_per_second": 1.85, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_accuracy": 0.8650006966083668, | |
| "eval_loss": 0.75830078125, | |
| "eval_runtime": 292.6223, | |
| "eval_samples_per_second": 14.746, | |
| "eval_steps_per_second": 1.845, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "eval_accuracy": 0.8648572972274987, | |
| "eval_loss": 0.7646484375, | |
| "eval_runtime": 292.6746, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_accuracy": 0.8645709515443751, | |
| "eval_loss": 0.759765625, | |
| "eval_runtime": 292.8238, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1784, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_accuracy": 0.8649886900251346, | |
| "eval_loss": 0.765625, | |
| "eval_runtime": 292.7739, | |
| "eval_samples_per_second": 14.738, | |
| "eval_steps_per_second": 1.844, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "eval_accuracy": 0.8647777819309984, | |
| "eval_loss": 0.76171875, | |
| "eval_runtime": 291.5794, | |
| "eval_samples_per_second": 14.799, | |
| "eval_steps_per_second": 1.852, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "eval_accuracy": 0.8650895000164242, | |
| "eval_loss": 0.75732421875, | |
| "eval_runtime": 292.5766, | |
| "eval_samples_per_second": 14.748, | |
| "eval_steps_per_second": 1.846, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "eval_accuracy": 0.8647773288523859, | |
| "eval_loss": 0.76708984375, | |
| "eval_runtime": 292.8751, | |
| "eval_samples_per_second": 14.733, | |
| "eval_steps_per_second": 1.844, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "eval_accuracy": 0.8651295974736336, | |
| "eval_loss": 0.75634765625, | |
| "eval_runtime": 292.7435, | |
| "eval_samples_per_second": 14.74, | |
| "eval_steps_per_second": 1.845, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1827, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "eval_accuracy": 0.8648883331124575, | |
| "eval_loss": 0.76513671875, | |
| "eval_runtime": 291.561, | |
| "eval_samples_per_second": 14.8, | |
| "eval_steps_per_second": 1.852, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "eval_accuracy": 0.8649513110396002, | |
| "eval_loss": 0.763671875, | |
| "eval_runtime": 292.871, | |
| "eval_samples_per_second": 14.733, | |
| "eval_steps_per_second": 1.844, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "eval_accuracy": 0.8653917034509865, | |
| "eval_loss": 0.7607421875, | |
| "eval_runtime": 292.9668, | |
| "eval_samples_per_second": 14.729, | |
| "eval_steps_per_second": 1.843, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.86499322081126, | |
| "eval_loss": 0.7607421875, | |
| "eval_runtime": 292.8128, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_accuracy": 0.8645997220362712, | |
| "eval_loss": 0.81494140625, | |
| "eval_runtime": 292.864, | |
| "eval_samples_per_second": 14.734, | |
| "eval_steps_per_second": 1.844, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 5e-05, | |
| "loss": 0.167, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_accuracy": 0.8647852577281052, | |
| "eval_loss": 0.80810546875, | |
| "eval_runtime": 292.7519, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.845, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "eval_accuracy": 0.8643582311357888, | |
| "eval_loss": 0.818359375, | |
| "eval_runtime": 291.6434, | |
| "eval_samples_per_second": 14.795, | |
| "eval_steps_per_second": 1.852, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_accuracy": 0.8647263575084754, | |
| "eval_loss": 0.81396484375, | |
| "eval_runtime": 292.5189, | |
| "eval_samples_per_second": 14.751, | |
| "eval_steps_per_second": 1.846, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "eval_accuracy": 0.8643802054484968, | |
| "eval_loss": 0.81689453125, | |
| "eval_runtime": 291.4921, | |
| "eval_samples_per_second": 14.803, | |
| "eval_steps_per_second": 1.853, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "eval_accuracy": 0.8644685557779417, | |
| "eval_loss": 0.81201171875, | |
| "eval_runtime": 292.6907, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1371, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "eval_accuracy": 0.8642560619086617, | |
| "eval_loss": 0.8154296875, | |
| "eval_runtime": 292.8129, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "eval_accuracy": 0.8642103009687954, | |
| "eval_loss": 0.81787109375, | |
| "eval_runtime": 292.7443, | |
| "eval_samples_per_second": 14.74, | |
| "eval_steps_per_second": 1.845, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "eval_accuracy": 0.8642599130768682, | |
| "eval_loss": 0.8154296875, | |
| "eval_runtime": 291.6813, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "eval_accuracy": 0.8645023101345757, | |
| "eval_loss": 0.81201171875, | |
| "eval_runtime": 292.6716, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "eval_accuracy": 0.8649979781366915, | |
| "eval_loss": 0.81103515625, | |
| "eval_runtime": 292.7654, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.844, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1425, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "eval_accuracy": 0.8645428606703978, | |
| "eval_loss": 0.81591796875, | |
| "eval_runtime": 292.6875, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "eval_accuracy": 0.8646024405079464, | |
| "eval_loss": 0.8173828125, | |
| "eval_runtime": 292.6736, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "eval_accuracy": 0.8649073624141841, | |
| "eval_loss": 0.81591796875, | |
| "eval_runtime": 292.7868, | |
| "eval_samples_per_second": 14.738, | |
| "eval_steps_per_second": 1.844, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "eval_accuracy": 0.8639400395764169, | |
| "eval_loss": 0.81103515625, | |
| "eval_runtime": 292.8417, | |
| "eval_samples_per_second": 14.735, | |
| "eval_steps_per_second": 1.844, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "eval_accuracy": 0.8645482976137482, | |
| "eval_loss": 0.8134765625, | |
| "eval_runtime": 292.765, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.844, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1505, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "eval_accuracy": 0.8642195890803523, | |
| "eval_loss": 0.81396484375, | |
| "eval_runtime": 292.5807, | |
| "eval_samples_per_second": 14.748, | |
| "eval_steps_per_second": 1.846, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.8639674508324753, | |
| "eval_loss": 0.86279296875, | |
| "eval_runtime": 292.6261, | |
| "eval_samples_per_second": 14.746, | |
| "eval_steps_per_second": 1.845, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "eval_accuracy": 0.8644205294450127, | |
| "eval_loss": 0.85400390625, | |
| "eval_runtime": 292.6297, | |
| "eval_samples_per_second": 14.746, | |
| "eval_steps_per_second": 1.845, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_accuracy": 0.8642433757075105, | |
| "eval_loss": 0.85302734375, | |
| "eval_runtime": 291.5398, | |
| "eval_samples_per_second": 14.801, | |
| "eval_steps_per_second": 1.852, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "eval_accuracy": 0.8646898846801662, | |
| "eval_loss": 0.85595703125, | |
| "eval_runtime": 291.664, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1086, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "eval_accuracy": 0.864855937991661, | |
| "eval_loss": 0.85546875, | |
| "eval_runtime": 292.8292, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_accuracy": 0.8643829239201721, | |
| "eval_loss": 0.8603515625, | |
| "eval_runtime": 292.6815, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "eval_accuracy": 0.8641971616890317, | |
| "eval_loss": 0.85693359375, | |
| "eval_runtime": 292.4181, | |
| "eval_samples_per_second": 14.756, | |
| "eval_steps_per_second": 1.847, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "eval_accuracy": 0.8638854436036061, | |
| "eval_loss": 0.85302734375, | |
| "eval_runtime": 293.018, | |
| "eval_samples_per_second": 14.726, | |
| "eval_steps_per_second": 1.843, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_accuracy": 0.8642818873895762, | |
| "eval_loss": 0.85888671875, | |
| "eval_runtime": 291.7384, | |
| "eval_samples_per_second": 14.791, | |
| "eval_steps_per_second": 1.851, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1076, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_accuracy": 0.8638872559180562, | |
| "eval_loss": 0.8525390625, | |
| "eval_runtime": 293.4652, | |
| "eval_samples_per_second": 14.704, | |
| "eval_steps_per_second": 1.84, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.58, | |
| "eval_accuracy": 0.8640002990318842, | |
| "eval_loss": 0.85791015625, | |
| "eval_runtime": 292.9912, | |
| "eval_samples_per_second": 14.727, | |
| "eval_steps_per_second": 1.843, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "eval_accuracy": 0.8639792308764013, | |
| "eval_loss": 0.859375, | |
| "eval_runtime": 292.1362, | |
| "eval_samples_per_second": 14.771, | |
| "eval_steps_per_second": 1.848, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_accuracy": 0.864300237073384, | |
| "eval_loss": 0.85986328125, | |
| "eval_runtime": 292.9015, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 1.844, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "eval_accuracy": 0.8639912374596336, | |
| "eval_loss": 0.8564453125, | |
| "eval_runtime": 292.927, | |
| "eval_samples_per_second": 14.731, | |
| "eval_steps_per_second": 1.843, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1109, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_accuracy": 0.8640392637925625, | |
| "eval_loss": 0.86328125, | |
| "eval_runtime": 292.9284, | |
| "eval_samples_per_second": 14.731, | |
| "eval_steps_per_second": 1.843, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_accuracy": 0.8638109121718437, | |
| "eval_loss": 0.8583984375, | |
| "eval_runtime": 292.6011, | |
| "eval_samples_per_second": 14.747, | |
| "eval_steps_per_second": 1.846, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.863599550999095, | |
| "eval_loss": 0.86474609375, | |
| "eval_runtime": 292.8714, | |
| "eval_samples_per_second": 14.733, | |
| "eval_steps_per_second": 1.844, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.8634767666950973, | |
| "eval_loss": 0.85986328125, | |
| "eval_runtime": 291.6716, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_accuracy": 0.8632459231420095, | |
| "eval_loss": 0.89794921875, | |
| "eval_runtime": 292.8834, | |
| "eval_samples_per_second": 14.733, | |
| "eval_steps_per_second": 1.844, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1028, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_accuracy": 0.8634595497078209, | |
| "eval_loss": 0.8935546875, | |
| "eval_runtime": 291.8248, | |
| "eval_samples_per_second": 14.786, | |
| "eval_steps_per_second": 1.85, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "eval_accuracy": 0.8637445361551069, | |
| "eval_loss": 0.904296875, | |
| "eval_runtime": 293.127, | |
| "eval_samples_per_second": 14.721, | |
| "eval_steps_per_second": 1.842, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_accuracy": 0.8641618215572539, | |
| "eval_loss": 0.89892578125, | |
| "eval_runtime": 291.7379, | |
| "eval_samples_per_second": 14.791, | |
| "eval_steps_per_second": 1.851, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "eval_accuracy": 0.8641742812190987, | |
| "eval_loss": 0.8935546875, | |
| "eval_runtime": 291.8762, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 1.85, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "eval_accuracy": 0.8641423391769147, | |
| "eval_loss": 0.89208984375, | |
| "eval_runtime": 293.0894, | |
| "eval_samples_per_second": 14.722, | |
| "eval_steps_per_second": 1.842, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0774, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "eval_accuracy": 0.8633791282540956, | |
| "eval_loss": 0.8955078125, | |
| "eval_runtime": 292.6585, | |
| "eval_samples_per_second": 14.744, | |
| "eval_steps_per_second": 1.845, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "eval_accuracy": 0.8636269622551535, | |
| "eval_loss": 0.89501953125, | |
| "eval_runtime": 294.4392, | |
| "eval_samples_per_second": 14.655, | |
| "eval_steps_per_second": 1.834, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "eval_accuracy": 0.8635223010956573, | |
| "eval_loss": 0.8994140625, | |
| "eval_runtime": 292.0929, | |
| "eval_samples_per_second": 14.773, | |
| "eval_steps_per_second": 1.849, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "eval_accuracy": 0.8635028187153182, | |
| "eval_loss": 0.89990234375, | |
| "eval_runtime": 291.6539, | |
| "eval_samples_per_second": 14.795, | |
| "eval_steps_per_second": 1.852, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "eval_accuracy": 0.8631285757813624, | |
| "eval_loss": 0.8935546875, | |
| "eval_runtime": 293.1835, | |
| "eval_samples_per_second": 14.718, | |
| "eval_steps_per_second": 1.842, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0852, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "eval_accuracy": 0.863441879641932, | |
| "eval_loss": 0.90478515625, | |
| "eval_runtime": 292.8044, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.844, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 7.72, | |
| "eval_accuracy": 0.8632284796154269, | |
| "eval_loss": 0.89599609375, | |
| "eval_runtime": 292.7129, | |
| "eval_samples_per_second": 14.741, | |
| "eval_steps_per_second": 1.845, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "eval_accuracy": 0.8634731420661971, | |
| "eval_loss": 0.90234375, | |
| "eval_runtime": 292.9408, | |
| "eval_samples_per_second": 14.73, | |
| "eval_steps_per_second": 1.843, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "eval_accuracy": 0.8638301680128765, | |
| "eval_loss": 0.8984375, | |
| "eval_runtime": 292.9793, | |
| "eval_samples_per_second": 14.728, | |
| "eval_steps_per_second": 1.843, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "eval_accuracy": 0.8635458611835093, | |
| "eval_loss": 0.90185546875, | |
| "eval_runtime": 292.8153, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0879, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "eval_accuracy": 0.863396345241372, | |
| "eval_loss": 0.9013671875, | |
| "eval_runtime": 292.8988, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 1.844, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8630044322415271, | |
| "eval_loss": 0.91357421875, | |
| "eval_runtime": 292.7911, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.844, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "eval_accuracy": 0.8638926928614067, | |
| "eval_loss": 0.93115234375, | |
| "eval_runtime": 292.7997, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.844, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_accuracy": 0.8635213949384323, | |
| "eval_loss": 0.9345703125, | |
| "eval_runtime": 292.7958, | |
| "eval_samples_per_second": 14.737, | |
| "eval_steps_per_second": 1.844, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "eval_accuracy": 0.8635272849603952, | |
| "eval_loss": 0.9306640625, | |
| "eval_runtime": 291.7965, | |
| "eval_samples_per_second": 14.788, | |
| "eval_steps_per_second": 1.851, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0611, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "eval_accuracy": 0.8640974843942736, | |
| "eval_loss": 0.94189453125, | |
| "eval_runtime": 292.9438, | |
| "eval_samples_per_second": 14.73, | |
| "eval_steps_per_second": 1.843, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "eval_accuracy": 0.863091196795828, | |
| "eval_loss": 0.93310546875, | |
| "eval_runtime": 292.6114, | |
| "eval_samples_per_second": 14.747, | |
| "eval_steps_per_second": 1.845, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "eval_accuracy": 0.8635660231817672, | |
| "eval_loss": 0.9375, | |
| "eval_runtime": 292.5076, | |
| "eval_samples_per_second": 14.752, | |
| "eval_steps_per_second": 1.846, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "eval_accuracy": 0.8626125192416824, | |
| "eval_loss": 0.92919921875, | |
| "eval_runtime": 292.6676, | |
| "eval_samples_per_second": 14.744, | |
| "eval_steps_per_second": 1.845, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_accuracy": 0.8637236945389302, | |
| "eval_loss": 0.94580078125, | |
| "eval_runtime": 291.6673, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 5e-05, | |
| "loss": 0.061, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "eval_accuracy": 0.8634267015084119, | |
| "eval_loss": 0.93359375, | |
| "eval_runtime": 291.6632, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "eval_accuracy": 0.8629693186490555, | |
| "eval_loss": 0.94091796875, | |
| "eval_runtime": 292.9394, | |
| "eval_samples_per_second": 14.73, | |
| "eval_steps_per_second": 1.843, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "eval_accuracy": 0.8632108095495379, | |
| "eval_loss": 0.93896484375, | |
| "eval_runtime": 292.836, | |
| "eval_samples_per_second": 14.735, | |
| "eval_steps_per_second": 1.844, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "eval_accuracy": 0.862787634125428, | |
| "eval_loss": 0.9375, | |
| "eval_runtime": 291.5974, | |
| "eval_samples_per_second": 14.798, | |
| "eval_steps_per_second": 1.852, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "eval_accuracy": 0.8629693186490555, | |
| "eval_loss": 0.9365234375, | |
| "eval_runtime": 292.847, | |
| "eval_samples_per_second": 14.735, | |
| "eval_steps_per_second": 1.844, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0646, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "eval_accuracy": 0.8628259192681874, | |
| "eval_loss": 0.93701171875, | |
| "eval_runtime": 292.6735, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "eval_accuracy": 0.8629194800016764, | |
| "eval_loss": 0.935546875, | |
| "eval_runtime": 292.789, | |
| "eval_samples_per_second": 14.738, | |
| "eval_steps_per_second": 1.844, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "eval_accuracy": 0.8632305184691833, | |
| "eval_loss": 0.9375, | |
| "eval_runtime": 291.6374, | |
| "eval_samples_per_second": 14.796, | |
| "eval_steps_per_second": 1.852, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "eval_accuracy": 0.8629763413675499, | |
| "eval_loss": 0.93896484375, | |
| "eval_runtime": 293.0327, | |
| "eval_samples_per_second": 14.725, | |
| "eval_steps_per_second": 1.843, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_accuracy": 0.8630309373403606, | |
| "eval_loss": 0.9716796875, | |
| "eval_runtime": 292.645, | |
| "eval_samples_per_second": 14.745, | |
| "eval_steps_per_second": 1.845, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0593, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "eval_accuracy": 0.8626426489694161, | |
| "eval_loss": 0.96728515625, | |
| "eval_runtime": 292.8134, | |
| "eval_samples_per_second": 14.736, | |
| "eval_steps_per_second": 1.844, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_accuracy": 0.862975661749631, | |
| "eval_loss": 0.96435546875, | |
| "eval_runtime": 292.9061, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 1.844, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "eval_accuracy": 0.8630644651576883, | |
| "eval_loss": 0.96240234375, | |
| "eval_runtime": 293.8107, | |
| "eval_samples_per_second": 14.686, | |
| "eval_steps_per_second": 1.838, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "eval_accuracy": 0.8633050499009457, | |
| "eval_loss": 0.96484375, | |
| "eval_runtime": 291.7944, | |
| "eval_samples_per_second": 14.788, | |
| "eval_steps_per_second": 1.851, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "eval_accuracy": 0.8632493212316036, | |
| "eval_loss": 0.96728515625, | |
| "eval_runtime": 291.6912, | |
| "eval_samples_per_second": 14.793, | |
| "eval_steps_per_second": 1.851, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0415, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "eval_accuracy": 0.8633073152940084, | |
| "eval_loss": 0.9658203125, | |
| "eval_runtime": 291.6781, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.851, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "eval_accuracy": 0.8627819706427713, | |
| "eval_loss": 0.96875, | |
| "eval_runtime": 292.5363, | |
| "eval_samples_per_second": 14.75, | |
| "eval_steps_per_second": 1.846, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "eval_accuracy": 0.8632289326940394, | |
| "eval_loss": 0.96533203125, | |
| "eval_runtime": 292.6096, | |
| "eval_samples_per_second": 14.747, | |
| "eval_steps_per_second": 1.845, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "eval_accuracy": 0.862821388482062, | |
| "eval_loss": 0.9658203125, | |
| "eval_runtime": 291.5436, | |
| "eval_samples_per_second": 14.801, | |
| "eval_steps_per_second": 1.852, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "eval_accuracy": 0.8629199330802889, | |
| "eval_loss": 0.966796875, | |
| "eval_runtime": 292.7541, | |
| "eval_samples_per_second": 14.739, | |
| "eval_steps_per_second": 1.845, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0471, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "eval_accuracy": 0.8625384408885325, | |
| "eval_loss": 0.96044921875, | |
| "eval_runtime": 292.6838, | |
| "eval_samples_per_second": 14.743, | |
| "eval_steps_per_second": 1.845, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_accuracy": 0.8620747149286004, | |
| "eval_loss": 0.9658203125, | |
| "eval_runtime": 291.636, | |
| "eval_samples_per_second": 14.796, | |
| "eval_steps_per_second": 1.852, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "eval_accuracy": 0.8629695451883618, | |
| "eval_loss": 0.97314453125, | |
| "eval_runtime": 291.7564, | |
| "eval_samples_per_second": 14.79, | |
| "eval_steps_per_second": 1.851, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "eval_accuracy": 0.8626276973752023, | |
| "eval_loss": 0.96923828125, | |
| "eval_runtime": 291.4249, | |
| "eval_samples_per_second": 14.807, | |
| "eval_steps_per_second": 1.853, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "eval_accuracy": 0.8622577586880655, | |
| "eval_loss": 0.96728515625, | |
| "eval_runtime": 291.5949, | |
| "eval_samples_per_second": 14.798, | |
| "eval_steps_per_second": 1.852, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0528, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "eval_accuracy": 0.8619999569575318, | |
| "eval_loss": 0.96142578125, | |
| "eval_runtime": 292.6583, | |
| "eval_samples_per_second": 14.744, | |
| "eval_steps_per_second": 1.845, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.8620715433783127, | |
| "eval_loss": 0.9697265625, | |
| "eval_runtime": 291.7031, | |
| "eval_samples_per_second": 14.792, | |
| "eval_steps_per_second": 1.851, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 17620, | |
| "total_flos": 2.179292736824279e+18, | |
| "train_loss": 0.2421213565700847, | |
| "train_runtime": 122603.1424, | |
| "train_samples_per_second": 1.149, | |
| "train_steps_per_second": 0.144 | |
| } | |
| ], | |
| "max_steps": 17620, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.179292736824279e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |