| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.891891891891891, | |
| "eval_steps": 500, | |
| "global_step": 366, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 4.698714733123779, | |
| "learning_rate": 0.00010526315789473685, | |
| "loss": 0.9004, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.5324004888534546, | |
| "learning_rate": 0.00019999590166142655, | |
| "loss": 0.2857, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 1.7758814096450806, | |
| "learning_rate": 0.00019950450737506824, | |
| "loss": 0.1811, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.9645628929138184, | |
| "learning_rate": 0.00019819805815653768, | |
| "loss": 0.1416, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3513513513513513, | |
| "grad_norm": 0.9237997531890869, | |
| "learning_rate": 0.00019608725530879375, | |
| "loss": 0.1186, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6216216216216215, | |
| "grad_norm": 0.8899639844894409, | |
| "learning_rate": 0.00019318938870459984, | |
| "loss": 0.1076, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8918918918918919, | |
| "grad_norm": 0.8379050493240356, | |
| "learning_rate": 0.0001895281951628281, | |
| "loss": 0.1, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.49454841017723083, | |
| "learning_rate": 0.00018513366401695276, | |
| "loss": 0.0912, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 0.5223703384399414, | |
| "learning_rate": 0.0001800417914683471, | |
| "loss": 0.079, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.7027027027027026, | |
| "grad_norm": 0.26653391122817993, | |
| "learning_rate": 0.00017429428573651024, | |
| "loss": 0.077, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.972972972972973, | |
| "grad_norm": 0.6166922450065613, | |
| "learning_rate": 0.0001679382254213768, | |
| "loss": 0.0717, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.2432432432432434, | |
| "grad_norm": 0.5702475309371948, | |
| "learning_rate": 0.0001610256738761125, | |
| "loss": 0.0612, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.5135135135135136, | |
| "grad_norm": 0.4581798017024994, | |
| "learning_rate": 0.00015361325274911779, | |
| "loss": 0.0544, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.7837837837837838, | |
| "grad_norm": 0.44726666808128357, | |
| "learning_rate": 0.0001457616781884173, | |
| "loss": 0.0628, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.054054054054054, | |
| "grad_norm": 0.3319581151008606, | |
| "learning_rate": 0.0001375352635074461, | |
| "loss": 0.0648, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.324324324324325, | |
| "grad_norm": 0.5032352805137634, | |
| "learning_rate": 0.00012900139238596598, | |
| "loss": 0.058, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.594594594594595, | |
| "grad_norm": 0.36259725689888, | |
| "learning_rate": 0.00012022996692119424, | |
| "loss": 0.0497, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.864864864864865, | |
| "grad_norm": 0.17420651018619537, | |
| "learning_rate": 0.00011129283505023274, | |
| "loss": 0.053, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.135135135135135, | |
| "grad_norm": 0.32951629161834717, | |
| "learning_rate": 0.00010226320203385878, | |
| "loss": 0.0518, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.405405405405405, | |
| "grad_norm": 0.27635061740875244, | |
| "learning_rate": 9.321503082229282e-05, | |
| "loss": 0.048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.675675675675675, | |
| "grad_norm": 0.3280782699584961, | |
| "learning_rate": 8.422243621462969e-05, | |
| "loss": 0.0516, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.945945945945946, | |
| "grad_norm": 0.29008397459983826, | |
| "learning_rate": 7.535907777445449e-05, | |
| "loss": 0.0465, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 6.216216216216216, | |
| "grad_norm": 0.24701108038425446, | |
| "learning_rate": 6.669755647435474e-05, | |
| "loss": 0.0436, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.486486486486487, | |
| "grad_norm": 0.34741994738578796, | |
| "learning_rate": 5.830882001149517e-05, | |
| "loss": 0.0499, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.756756756756757, | |
| "grad_norm": 0.2663642168045044, | |
| "learning_rate": 5.0261581665395475e-05, | |
| "loss": 0.0439, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.027027027027027, | |
| "grad_norm": 0.34826692938804626, | |
| "learning_rate": 4.2621757458127285e-05, | |
| "loss": 0.0465, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 7.297297297297297, | |
| "grad_norm": 0.2025139331817627, | |
| "learning_rate": 3.5451926227225997e-05, | |
| "loss": 0.041, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.5675675675675675, | |
| "grad_norm": 0.2484084963798523, | |
| "learning_rate": 2.8810817033934656e-05, | |
| "loss": 0.0384, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.837837837837838, | |
| "grad_norm": 0.19896186888217926, | |
| "learning_rate": 2.275282810548811e-05, | |
| "loss": 0.0368, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 8.108108108108109, | |
| "grad_norm": 0.24585744738578796, | |
| "learning_rate": 1.73275812518469e-05, | |
| "loss": 0.0382, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.378378378378379, | |
| "grad_norm": 0.2137955129146576, | |
| "learning_rate": 1.2579515406713193e-05, | |
| "loss": 0.0417, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 8.64864864864865, | |
| "grad_norm": 0.29916706681251526, | |
| "learning_rate": 8.547522622190385e-06, | |
| "loss": 0.0349, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 8.91891891891892, | |
| "grad_norm": 0.21314117312431335, | |
| "learning_rate": 5.264629498702967e-06, | |
| "loss": 0.038, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 9.18918918918919, | |
| "grad_norm": 0.2648143470287323, | |
| "learning_rate": 2.7577266596274576e-06, | |
| "loss": 0.0386, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 9.45945945945946, | |
| "grad_norm": 0.21586932241916656, | |
| "learning_rate": 1.0473484865448525e-06, | |
| "loss": 0.0356, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 9.72972972972973, | |
| "grad_norm": 0.24431149661540985, | |
| "learning_rate": 1.4750491933247512e-07, | |
| "loss": 0.0428, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.891891891891891, | |
| "step": 366, | |
| "total_flos": 4.991850946034842e+16, | |
| "train_loss": 0.09146885374367562, | |
| "train_runtime": 453.0584, | |
| "train_samples_per_second": 51.702, | |
| "train_steps_per_second": 0.808 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 366, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.991850946034842e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |