| { |
| "best_global_step": 1234, |
| "best_metric": 2.5843265056610107, |
| "best_model_checkpoint": "models/gemma270m-sft-fqa/checkpoint-1234", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1851, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08115236356258876, |
| "grad_norm": 13.660741806030273, |
| "learning_rate": 8.75e-05, |
| "loss": 4.983, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16230472712517752, |
| "grad_norm": 11.402396202087402, |
| "learning_rate": 9.985847186947076e-05, |
| "loss": 4.0619, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24345709068776628, |
| "grad_norm": 10.74139404296875, |
| "learning_rate": 9.93391274588681e-05, |
| "loss": 3.7985, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.32460945425035503, |
| "grad_norm": 11.64829158782959, |
| "learning_rate": 9.844218899490987e-05, |
| "loss": 3.6412, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4057618178129438, |
| "grad_norm": 10.44972038269043, |
| "learning_rate": 9.717452077876346e-05, |
| "loss": 3.4894, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.48691418137553255, |
| "grad_norm": 10.880023002624512, |
| "learning_rate": 9.554582431924548e-05, |
| "loss": 3.3765, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5680665449381214, |
| "grad_norm": 10.3041353225708, |
| "learning_rate": 9.356856408683826e-05, |
| "loss": 3.3129, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.6492189085007101, |
| "grad_norm": 9.135042190551758, |
| "learning_rate": 9.125787212266508e-05, |
| "loss": 3.1973, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7303712720632989, |
| "grad_norm": 10.27686595916748, |
| "learning_rate": 8.863143223245465e-05, |
| "loss": 3.1488, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8115236356258876, |
| "grad_norm": 9.036040306091309, |
| "learning_rate": 8.570934465176278e-05, |
| "loss": 3.0712, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8926759991884764, |
| "grad_norm": 9.041040420532227, |
| "learning_rate": 8.251397221817252e-05, |
| "loss": 2.9367, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.9738283627510651, |
| "grad_norm": 8.38169002532959, |
| "learning_rate": 7.906976922772278e-05, |
| "loss": 2.8638, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.8626081943511963, |
| "eval_runtime": 47.5672, |
| "eval_samples_per_second": 184.224, |
| "eval_steps_per_second": 5.76, |
| "step": 617 |
| }, |
| { |
| "epoch": 1.0535605599513085, |
| "grad_norm": 10.622579574584961, |
| "learning_rate": 7.54030942853327e-05, |
| "loss": 2.1546, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.1347129235138973, |
| "grad_norm": 8.288007736206055, |
| "learning_rate": 7.154200858148418e-05, |
| "loss": 1.7795, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.2158652870764861, |
| "grad_norm": 8.66895580291748, |
| "learning_rate": 6.751606113895808e-05, |
| "loss": 1.7836, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.297017650639075, |
| "grad_norm": 8.41976261138916, |
| "learning_rate": 6.335606267313821e-05, |
| "loss": 1.7458, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.3781700142016637, |
| "grad_norm": 9.445528030395508, |
| "learning_rate": 5.9093849796538034e-05, |
| "loss": 1.763, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.4593223777642523, |
| "grad_norm": 9.660811424255371, |
| "learning_rate": 5.476204137210122e-05, |
| "loss": 1.7357, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.5404747413268411, |
| "grad_norm": 8.14544677734375, |
| "learning_rate": 5.039378887991235e-05, |
| "loss": 1.6956, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.62162710488943, |
| "grad_norm": 8.195582389831543, |
| "learning_rate": 4.602252270777026e-05, |
| "loss": 1.7108, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.7027794684520186, |
| "grad_norm": 9.13266372680664, |
| "learning_rate": 4.1681696307270946e-05, |
| "loss": 1.662, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.7839318320146074, |
| "grad_norm": 8.996973037719727, |
| "learning_rate": 3.7404530173382555e-05, |
| "loss": 1.6397, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.8650841955771962, |
| "grad_norm": 8.205750465393066, |
| "learning_rate": 3.322375760684524e-05, |
| "loss": 1.6252, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.946236559139785, |
| "grad_norm": 9.282258033752441, |
| "learning_rate": 2.917137420508569e-05, |
| "loss": 1.5914, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.5843265056610107, |
| "eval_runtime": 46.6973, |
| "eval_samples_per_second": 187.656, |
| "eval_steps_per_second": 5.868, |
| "step": 1234 |
| }, |
| { |
| "epoch": 2.0259687563400286, |
| "grad_norm": 9.058813095092773, |
| "learning_rate": 2.5278392998800394e-05, |
| "loss": 1.2762, |
| "step": 1250 |
| }, |
| { |
| "epoch": 2.107121119902617, |
| "grad_norm": 9.824188232421875, |
| "learning_rate": 2.1574607108156425e-05, |
| "loss": 0.6675, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.188273483465206, |
| "grad_norm": 8.858758926391602, |
| "learning_rate": 1.808836173500954e-05, |
| "loss": 0.6402, |
| "step": 1350 |
| }, |
| { |
| "epoch": 2.2694258470277946, |
| "grad_norm": 9.899801254272461, |
| "learning_rate": 1.484633723609154e-05, |
| "loss": 0.6364, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.3505782105903834, |
| "grad_norm": 8.896689414978027, |
| "learning_rate": 1.1873344937315002e-05, |
| "loss": 0.6221, |
| "step": 1450 |
| }, |
| { |
| "epoch": 2.4317305741529722, |
| "grad_norm": 8.655142784118652, |
| "learning_rate": 9.192137251835742e-06, |
| "loss": 0.6147, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.512882937715561, |
| "grad_norm": 10.144364356994629, |
| "learning_rate": 6.823233555045849e-06, |
| "loss": 0.6095, |
| "step": 1550 |
| }, |
| { |
| "epoch": 2.59403530127815, |
| "grad_norm": 9.760300636291504, |
| "learning_rate": 4.784763149082405e-06, |
| "loss": 0.6137, |
| "step": 1600 |
| }, |
| { |
| "epoch": 2.675187664840738, |
| "grad_norm": 9.731839179992676, |
| "learning_rate": 3.0923265186494188e-06, |
| "loss": 0.6282, |
| "step": 1650 |
| }, |
| { |
| "epoch": 2.7563400284033275, |
| "grad_norm": 8.688471794128418, |
| "learning_rate": 1.7588759399675525e-06, |
| "loss": 0.5927, |
| "step": 1700 |
| }, |
| { |
| "epoch": 2.837492391965916, |
| "grad_norm": 8.816551208496094, |
| "learning_rate": 7.94616356554978e-07, |
| "loss": 0.6152, |
| "step": 1750 |
| }, |
| { |
| "epoch": 2.9186447555285047, |
| "grad_norm": 9.027681350708008, |
| "learning_rate": 2.0692728044079957e-07, |
| "loss": 0.5801, |
| "step": 1800 |
| }, |
| { |
| "epoch": 2.9997971190910935, |
| "grad_norm": 9.38516616821289, |
| "learning_rate": 3.06316503556614e-10, |
| "loss": 0.5927, |
| "step": 1850 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 3.1965487003326416, |
| "eval_runtime": 46.5876, |
| "eval_samples_per_second": 188.097, |
| "eval_steps_per_second": 5.881, |
| "step": 1851 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1851, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0937701855920128e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
