| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.968503937007874, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03937007874015748, | |
| "grad_norm": 19.470706939697266, | |
| "learning_rate": 1.9790026246719162e-05, | |
| "loss": 3.7835, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07874015748031496, | |
| "grad_norm": 15.06888484954834, | |
| "learning_rate": 1.952755905511811e-05, | |
| "loss": 3.5622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11811023622047244, | |
| "grad_norm": 10.949335098266602, | |
| "learning_rate": 1.9265091863517064e-05, | |
| "loss": 3.0315, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15748031496062992, | |
| "grad_norm": 13.46808910369873, | |
| "learning_rate": 1.9002624671916013e-05, | |
| "loss": 3.1242, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1968503937007874, | |
| "grad_norm": 14.465880393981934, | |
| "learning_rate": 1.8740157480314962e-05, | |
| "loss": 3.1138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23622047244094488, | |
| "grad_norm": 16.78143310546875, | |
| "learning_rate": 1.847769028871391e-05, | |
| "loss": 2.8584, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2755905511811024, | |
| "grad_norm": 15.088367462158203, | |
| "learning_rate": 1.821522309711286e-05, | |
| "loss": 2.9588, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.31496062992125984, | |
| "grad_norm": 13.963665008544922, | |
| "learning_rate": 1.7952755905511813e-05, | |
| "loss": 3.1075, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3543307086614173, | |
| "grad_norm": 15.01663589477539, | |
| "learning_rate": 1.7690288713910762e-05, | |
| "loss": 2.8811, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3937007874015748, | |
| "grad_norm": 22.79145622253418, | |
| "learning_rate": 1.7427821522309714e-05, | |
| "loss": 2.946, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4330708661417323, | |
| "grad_norm": 17.157787322998047, | |
| "learning_rate": 1.7165354330708663e-05, | |
| "loss": 2.7091, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.47244094488188976, | |
| "grad_norm": 15.345536231994629, | |
| "learning_rate": 1.6902887139107613e-05, | |
| "loss": 2.8872, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5118110236220472, | |
| "grad_norm": 14.813170433044434, | |
| "learning_rate": 1.6640419947506562e-05, | |
| "loss": 2.7625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5511811023622047, | |
| "grad_norm": 13.589457511901855, | |
| "learning_rate": 1.6377952755905514e-05, | |
| "loss": 2.6937, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5905511811023622, | |
| "grad_norm": 16.824535369873047, | |
| "learning_rate": 1.6115485564304463e-05, | |
| "loss": 3.1951, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6299212598425197, | |
| "grad_norm": 15.816085815429688, | |
| "learning_rate": 1.5853018372703412e-05, | |
| "loss": 2.7028, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6692913385826772, | |
| "grad_norm": 12.972024917602539, | |
| "learning_rate": 1.559055118110236e-05, | |
| "loss": 2.7171, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7086614173228346, | |
| "grad_norm": 15.205809593200684, | |
| "learning_rate": 1.5328083989501314e-05, | |
| "loss": 2.7386, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7480314960629921, | |
| "grad_norm": 15.404927253723145, | |
| "learning_rate": 1.5065616797900265e-05, | |
| "loss": 2.5878, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7874015748031497, | |
| "grad_norm": 14.278895378112793, | |
| "learning_rate": 1.4803149606299214e-05, | |
| "loss": 2.535, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8267716535433071, | |
| "grad_norm": 13.026575088500977, | |
| "learning_rate": 1.4540682414698165e-05, | |
| "loss": 2.7611, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8661417322834646, | |
| "grad_norm": 14.615636825561523, | |
| "learning_rate": 1.4278215223097114e-05, | |
| "loss": 2.4755, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.905511811023622, | |
| "grad_norm": 15.044017791748047, | |
| "learning_rate": 1.4015748031496063e-05, | |
| "loss": 2.7637, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9448818897637795, | |
| "grad_norm": 15.503686904907227, | |
| "learning_rate": 1.3753280839895014e-05, | |
| "loss": 2.8203, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.984251968503937, | |
| "grad_norm": 13.733269691467285, | |
| "learning_rate": 1.3490813648293963e-05, | |
| "loss": 2.4717, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.6172032356262207, | |
| "eval_runtime": 1.7583, | |
| "eval_samples_per_second": 512.44, | |
| "eval_steps_per_second": 16.494, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.0236220472440944, | |
| "grad_norm": 12.064373970031738, | |
| "learning_rate": 1.3228346456692915e-05, | |
| "loss": 2.6106, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0629921259842519, | |
| "grad_norm": 14.499472618103027, | |
| "learning_rate": 1.2965879265091864e-05, | |
| "loss": 2.5675, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1023622047244095, | |
| "grad_norm": 13.379920959472656, | |
| "learning_rate": 1.2703412073490815e-05, | |
| "loss": 2.3713, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.141732283464567, | |
| "grad_norm": 13.791425704956055, | |
| "learning_rate": 1.2440944881889764e-05, | |
| "loss": 2.5336, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1811023622047245, | |
| "grad_norm": 13.244888305664062, | |
| "learning_rate": 1.2178477690288715e-05, | |
| "loss": 2.6234, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.220472440944882, | |
| "grad_norm": 19.034948348999023, | |
| "learning_rate": 1.1916010498687664e-05, | |
| "loss": 2.5233, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2598425196850394, | |
| "grad_norm": 15.304523468017578, | |
| "learning_rate": 1.1653543307086615e-05, | |
| "loss": 2.7615, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.2992125984251968, | |
| "grad_norm": 13.435171127319336, | |
| "learning_rate": 1.1391076115485564e-05, | |
| "loss": 2.6509, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3385826771653544, | |
| "grad_norm": 17.483469009399414, | |
| "learning_rate": 1.1128608923884517e-05, | |
| "loss": 2.5112, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3779527559055118, | |
| "grad_norm": 13.701622009277344, | |
| "learning_rate": 1.0866141732283466e-05, | |
| "loss": 2.4639, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4173228346456692, | |
| "grad_norm": 12.15971565246582, | |
| "learning_rate": 1.0603674540682417e-05, | |
| "loss": 2.3728, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.4566929133858268, | |
| "grad_norm": 16.696950912475586, | |
| "learning_rate": 1.0341207349081366e-05, | |
| "loss": 2.6276, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.4960629921259843, | |
| "grad_norm": 14.275362968444824, | |
| "learning_rate": 1.0078740157480316e-05, | |
| "loss": 2.2527, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.5354330708661417, | |
| "grad_norm": 11.532317161560059, | |
| "learning_rate": 9.816272965879266e-06, | |
| "loss": 2.3952, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.574803149606299, | |
| "grad_norm": 14.485555648803711, | |
| "learning_rate": 9.553805774278216e-06, | |
| "loss": 2.4501, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6141732283464567, | |
| "grad_norm": 12.941930770874023, | |
| "learning_rate": 9.291338582677165e-06, | |
| "loss": 2.5935, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6535433070866141, | |
| "grad_norm": 10.413193702697754, | |
| "learning_rate": 9.028871391076116e-06, | |
| "loss": 2.3981, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6929133858267718, | |
| "grad_norm": 13.350451469421387, | |
| "learning_rate": 8.766404199475065e-06, | |
| "loss": 2.5693, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.7322834645669292, | |
| "grad_norm": 12.321857452392578, | |
| "learning_rate": 8.503937007874016e-06, | |
| "loss": 2.4089, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7716535433070866, | |
| "grad_norm": 17.121238708496094, | |
| "learning_rate": 8.241469816272967e-06, | |
| "loss": 2.2449, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.811023622047244, | |
| "grad_norm": 17.085081100463867, | |
| "learning_rate": 7.979002624671916e-06, | |
| "loss": 2.5096, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8503937007874016, | |
| "grad_norm": 13.748458862304688, | |
| "learning_rate": 7.716535433070867e-06, | |
| "loss": 2.427, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.889763779527559, | |
| "grad_norm": 14.016273498535156, | |
| "learning_rate": 7.454068241469818e-06, | |
| "loss": 2.2703, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.9291338582677167, | |
| "grad_norm": 9.295332908630371, | |
| "learning_rate": 7.191601049868768e-06, | |
| "loss": 2.3936, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.968503937007874, | |
| "grad_norm": 14.30349349975586, | |
| "learning_rate": 6.929133858267717e-06, | |
| "loss": 2.603, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 762, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4206012908544000.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |