| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8034817542684968, | |
| "eval_steps": 300, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013391362571141614, | |
| "grad_norm": 2.4009346961975098, | |
| "learning_rate": 2.2321428571428573e-06, | |
| "loss": 1.3329, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026782725142283227, | |
| "grad_norm": 2.416130781173706, | |
| "learning_rate": 4.464285714285715e-06, | |
| "loss": 1.2931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.040174087713424844, | |
| "grad_norm": 2.9514546394348145, | |
| "learning_rate": 6.696428571428572e-06, | |
| "loss": 1.2808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.053565450284566454, | |
| "grad_norm": 1.845926284790039, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 1.2348, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06695681285570806, | |
| "grad_norm": 0.8614177107810974, | |
| "learning_rate": 1.1160714285714287e-05, | |
| "loss": 1.1273, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08034817542684969, | |
| "grad_norm": 0.729676365852356, | |
| "learning_rate": 1.3392857142857144e-05, | |
| "loss": 0.9001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0937395379979913, | |
| "grad_norm": 0.6786935329437256, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.7691, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10713090056913291, | |
| "grad_norm": 0.6628158092498779, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.6629, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12052226314027452, | |
| "grad_norm": 0.39596471190452576, | |
| "learning_rate": 2.0089285714285717e-05, | |
| "loss": 0.6795, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13391362571141613, | |
| "grad_norm": 0.45973294973373413, | |
| "learning_rate": 2.2321428571428575e-05, | |
| "loss": 0.6835, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14730498828255775, | |
| "grad_norm": 0.43911251425743103, | |
| "learning_rate": 2.455357142857143e-05, | |
| "loss": 0.6344, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16069635085369938, | |
| "grad_norm": 0.5540445446968079, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 0.5985, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17408771342484097, | |
| "grad_norm": 0.5015535354614258, | |
| "learning_rate": 2.9017857142857146e-05, | |
| "loss": 0.5375, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1874790759959826, | |
| "grad_norm": 0.6995676755905151, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.5493, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2008704385671242, | |
| "grad_norm": 0.5413327813148499, | |
| "learning_rate": 3.348214285714286e-05, | |
| "loss": 0.5474, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21426180113826582, | |
| "grad_norm": 0.5784323811531067, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.5712, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.22765316370940744, | |
| "grad_norm": 0.9611849188804626, | |
| "learning_rate": 3.794642857142857e-05, | |
| "loss": 0.5432, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.24104452628054904, | |
| "grad_norm": 0.5728833079338074, | |
| "learning_rate": 4.017857142857143e-05, | |
| "loss": 0.4972, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.25443588885169066, | |
| "grad_norm": 0.6023485660552979, | |
| "learning_rate": 4.2410714285714285e-05, | |
| "loss": 0.4769, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.26782725142283226, | |
| "grad_norm": 0.607907235622406, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 0.5039, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2812186139939739, | |
| "grad_norm": 0.6248412728309631, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.4767, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2946099765651155, | |
| "grad_norm": 0.6133660078048706, | |
| "learning_rate": 4.910714285714286e-05, | |
| "loss": 0.5234, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3080013391362571, | |
| "grad_norm": 0.6181973218917847, | |
| "learning_rate": 4.9998905060416096e-05, | |
| "loss": 0.4192, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.32139270170739875, | |
| "grad_norm": 0.6632351875305176, | |
| "learning_rate": 4.999221411028925e-05, | |
| "loss": 0.4418, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.33478406427854035, | |
| "grad_norm": 0.8785191774368286, | |
| "learning_rate": 4.997944213585113e-05, | |
| "loss": 0.4684, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.34817542684968195, | |
| "grad_norm": 0.6774404644966125, | |
| "learning_rate": 4.996059224473704e-05, | |
| "loss": 0.4394, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.36156678942082354, | |
| "grad_norm": 0.792456328868866, | |
| "learning_rate": 4.9935669023441236e-05, | |
| "loss": 0.421, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3749581519919652, | |
| "grad_norm": 0.9153772592544556, | |
| "learning_rate": 4.99046785362009e-05, | |
| "loss": 0.4788, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3883495145631068, | |
| "grad_norm": 0.5768759250640869, | |
| "learning_rate": 4.986762832352069e-05, | |
| "loss": 0.4175, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4017408771342484, | |
| "grad_norm": 0.736320972442627, | |
| "learning_rate": 4.982452740033793e-05, | |
| "loss": 0.4136, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4017408771342484, | |
| "eval_loss": 0.4803064167499542, | |
| "eval_runtime": 38.84, | |
| "eval_samples_per_second": 17.096, | |
| "eval_steps_per_second": 17.096, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.41513223970539004, | |
| "grad_norm": 0.9251226186752319, | |
| "learning_rate": 4.977538625382916e-05, | |
| "loss": 0.4248, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.42852360227653163, | |
| "grad_norm": 0.9105271100997925, | |
| "learning_rate": 4.972021684085846e-05, | |
| "loss": 0.4959, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.44191496484767323, | |
| "grad_norm": 0.525224506855011, | |
| "learning_rate": 4.965903258506806e-05, | |
| "loss": 0.4622, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4553063274188149, | |
| "grad_norm": 0.7840506434440613, | |
| "learning_rate": 4.9591848373612247e-05, | |
| "loss": 0.32, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.4686976899899565, | |
| "grad_norm": 0.7537767887115479, | |
| "learning_rate": 4.9518680553535004e-05, | |
| "loss": 0.3984, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4820890525610981, | |
| "grad_norm": 0.8291546702384949, | |
| "learning_rate": 4.94395469277925e-05, | |
| "loss": 0.4221, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4954804151322397, | |
| "grad_norm": 0.7584542632102966, | |
| "learning_rate": 4.935446675092137e-05, | |
| "loss": 0.4015, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5088717777033813, | |
| "grad_norm": 0.9720783233642578, | |
| "learning_rate": 4.926346072435373e-05, | |
| "loss": 0.4589, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5222631402745229, | |
| "grad_norm": 1.1246592998504639, | |
| "learning_rate": 4.916655099138019e-05, | |
| "loss": 0.4344, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5356545028456645, | |
| "grad_norm": 0.6652913093566895, | |
| "learning_rate": 4.906376113176202e-05, | |
| "loss": 0.4007, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5490458654168061, | |
| "grad_norm": 0.8961889743804932, | |
| "learning_rate": 4.895511615599379e-05, | |
| "loss": 0.3503, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5624372279879478, | |
| "grad_norm": 0.8319832682609558, | |
| "learning_rate": 4.884064249921789e-05, | |
| "loss": 0.3853, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5758285905590894, | |
| "grad_norm": 0.5967663526535034, | |
| "learning_rate": 4.872036801479246e-05, | |
| "loss": 0.3836, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.589219953130231, | |
| "grad_norm": 0.7453261613845825, | |
| "learning_rate": 4.859432196751414e-05, | |
| "loss": 0.399, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6026113157013726, | |
| "grad_norm": 0.8149186372756958, | |
| "learning_rate": 4.8462535026497496e-05, | |
| "loss": 0.3674, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6160026782725142, | |
| "grad_norm": 0.6484460234642029, | |
| "learning_rate": 4.8325039257712704e-05, | |
| "loss": 0.3836, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.6293940408436558, | |
| "grad_norm": 0.689203679561615, | |
| "learning_rate": 4.818186811618336e-05, | |
| "loss": 0.3912, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6427854034147975, | |
| "grad_norm": 0.7593767642974854, | |
| "learning_rate": 4.8033056437846305e-05, | |
| "loss": 0.3931, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6561767659859391, | |
| "grad_norm": 1.0037031173706055, | |
| "learning_rate": 4.787864043107546e-05, | |
| "loss": 0.4235, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6695681285570807, | |
| "grad_norm": 0.7254366874694824, | |
| "learning_rate": 4.771865766787175e-05, | |
| "loss": 0.397, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6829594911282223, | |
| "grad_norm": 0.909480631351471, | |
| "learning_rate": 4.755314707472114e-05, | |
| "loss": 0.4276, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6963508536993639, | |
| "grad_norm": 0.6278852820396423, | |
| "learning_rate": 4.738214892312325e-05, | |
| "loss": 0.3438, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7097422162705055, | |
| "grad_norm": 0.7583978176116943, | |
| "learning_rate": 4.7205704819792576e-05, | |
| "loss": 0.4145, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.7231335788416471, | |
| "grad_norm": 1.1025863885879517, | |
| "learning_rate": 4.702385769653488e-05, | |
| "loss": 0.3728, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.7365249414127888, | |
| "grad_norm": 1.1275866031646729, | |
| "learning_rate": 4.683665179980119e-05, | |
| "loss": 0.3926, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7499163039839304, | |
| "grad_norm": 0.9416183233261108, | |
| "learning_rate": 4.664413267992187e-05, | |
| "loss": 0.3751, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.763307666555072, | |
| "grad_norm": 1.1021020412445068, | |
| "learning_rate": 4.644634718002346e-05, | |
| "loss": 0.3818, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7766990291262136, | |
| "grad_norm": 1.04265296459198, | |
| "learning_rate": 4.624334342463099e-05, | |
| "loss": 0.3823, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7900903916973552, | |
| "grad_norm": 0.622381865978241, | |
| "learning_rate": 4.603517080795844e-05, | |
| "loss": 0.3784, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8034817542684968, | |
| "grad_norm": 1.0999802350997925, | |
| "learning_rate": 4.582187998189034e-05, | |
| "loss": 0.3555, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8034817542684968, | |
| "eval_loss": 0.4139007329940796, | |
| "eval_runtime": 38.554, | |
| "eval_samples_per_second": 17.223, | |
| "eval_steps_per_second": 17.223, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2238, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 300, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.717600085324595e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |