| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9988901220865705, | |
| "eval_steps": 500, | |
| "global_step": 225, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022197558268590455, | |
| "grad_norm": 4.173152160656369, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.7367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04439511653718091, | |
| "grad_norm": 3.2189546924605743, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6236, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06659267480577137, | |
| "grad_norm": 2.5798875358644615, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.3355, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08879023307436182, | |
| "grad_norm": 3.169021801096128, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11098779134295228, | |
| "grad_norm": 2.6869772888956365, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.2223, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13318534961154274, | |
| "grad_norm": 2.5246138578206296, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.1477, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15538290788013318, | |
| "grad_norm": 2.6296096882455298, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.0723, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17758046614872364, | |
| "grad_norm": 2.013904106905957, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.9628, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1997780244173141, | |
| "grad_norm": 2.9993599311041197, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.963, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22197558268590456, | |
| "grad_norm": 2.8591825849504353, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.9454, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.244173140954495, | |
| "grad_norm": 2.7350211425782365, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.9329, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2663706992230855, | |
| "grad_norm": 2.1765633333645082, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.938, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2885682574916759, | |
| "grad_norm": 2.61036019611883, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.9445, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.31076581576026635, | |
| "grad_norm": 2.272074478469258, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.9281, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33296337402885684, | |
| "grad_norm": 2.180048695923942, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.923, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3551609322974473, | |
| "grad_norm": 2.7343263244068567, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.9238, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 3.347285634649469, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.9262, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3995560488346282, | |
| "grad_norm": 1.9801889636127816, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.8858, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.42175360710321863, | |
| "grad_norm": 2.5733487656351617, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.8976, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4439511653718091, | |
| "grad_norm": 2.6122649493371104, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.8718, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.46614872364039955, | |
| "grad_norm": 2.0876959501211094, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8649, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.48834628190899, | |
| "grad_norm": 2.16104748727945, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.8705, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5105438401775805, | |
| "grad_norm": 2.324049561076729, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.8649, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.532741398446171, | |
| "grad_norm": 2.2381634375296047, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.8514, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5549389567147613, | |
| "grad_norm": 2.1550933983565534, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.8541, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5771365149833518, | |
| "grad_norm": 2.0860600049733007, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.8443, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5993340732519423, | |
| "grad_norm": 2.8122996250620313, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8305, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6215316315205327, | |
| "grad_norm": 1.8994822037248742, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.8608, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6437291897891232, | |
| "grad_norm": 2.2555867483043848, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.8134, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6659267480577137, | |
| "grad_norm": 1.8397515247154257, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8128, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6881243063263041, | |
| "grad_norm": 2.4303983539129264, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.8251, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7103218645948945, | |
| "grad_norm": 2.2313954875151016, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.8023, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.732519422863485, | |
| "grad_norm": 2.158630207915647, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.8068, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 2.0984542929723227, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.83, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7769145394006659, | |
| "grad_norm": 2.3913092010409445, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.8317, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7991120976692564, | |
| "grad_norm": 2.2309830019482333, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.8319, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8213096559378469, | |
| "grad_norm": 2.3343796415351554, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.8383, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8435072142064373, | |
| "grad_norm": 2.058761898873254, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.8052, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8657047724750278, | |
| "grad_norm": 2.4171172190014416, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.8262, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8879023307436182, | |
| "grad_norm": 2.231323330105212, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.8204, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9100998890122086, | |
| "grad_norm": 2.3595682400676714, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.8168, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9322974472807991, | |
| "grad_norm": 2.229272501664809, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.829, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9544950055493896, | |
| "grad_norm": 1.9609279896552483, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.8335, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.97669256381798, | |
| "grad_norm": 2.100020381721619, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.8238, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9988901220865705, | |
| "grad_norm": 2.933024766927132, | |
| "learning_rate": 0.0, | |
| "loss": 0.8168, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9988901220865705, | |
| "eval_loss": 0.8767702579498291, | |
| "eval_runtime": 116.7284, | |
| "eval_samples_per_second": 21.786, | |
| "eval_steps_per_second": 1.362, | |
| "step": 225 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 225, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 490142173233152.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |