{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.098901098901099, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.10989010989010989, "grad_norm": 5.355079650878906, "learning_rate": 2.9795419551040836e-05, "loss": 2.2017, "step": 10 }, { "epoch": 0.21978021978021978, "grad_norm": 6.180635929107666, "learning_rate": 2.8192106268097336e-05, "loss": 1.9709, "step": 20 }, { "epoch": 0.32967032967032966, "grad_norm": 4.256494522094727, "learning_rate": 2.5159223574386117e-05, "loss": 1.9663, "step": 30 }, { "epoch": 0.43956043956043955, "grad_norm": 4.6599531173706055, "learning_rate": 2.1025431369794546e-05, "loss": 2.0236, "step": 40 }, { "epoch": 0.5494505494505495, "grad_norm": 4.803452968597412, "learning_rate": 1.623869018208499e-05, "loss": 2.0234, "step": 50 }, { "epoch": 0.6593406593406593, "grad_norm": 4.006745338439941, "learning_rate": 1.1317717692888014e-05, "loss": 1.9578, "step": 60 }, { "epoch": 0.7692307692307693, "grad_norm": 6.697165489196777, "learning_rate": 6.795777628163599e-06, "loss": 1.872, "step": 70 }, { "epoch": 0.8791208791208791, "grad_norm": 5.062468528747559, "learning_rate": 3.162892359054098e-06, "loss": 1.8086, "step": 80 }, { "epoch": 0.989010989010989, "grad_norm": 10.192545890808105, "learning_rate": 8.127413744904805e-07, "loss": 2.059, "step": 90 }, { "epoch": 1.098901098901099, "grad_norm": 3.956005573272705, "learning_rate": 0.0, "loss": 1.682, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 3490463932489728.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }