{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 4276, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.23386342376052385, "grad_norm": 0.906826913356781, "learning_rate": 5e-05, "loss": 0.7573, "step": 500 }, { "epoch": 0.4677268475210477, "grad_norm": 2.789905309677124, "learning_rate": 4.337923728813559e-05, "loss": 0.5693, "step": 1000 }, { "epoch": 0.7015902712815716, "grad_norm": 5.194443225860596, "learning_rate": 3.675847457627119e-05, "loss": 0.5281, "step": 1500 }, { "epoch": 0.9354536950420954, "grad_norm": 10.87773323059082, "learning_rate": 3.013771186440678e-05, "loss": 0.4781, "step": 2000 }, { "epoch": 1.1693171188026192, "grad_norm": 6.845210075378418, "learning_rate": 2.3516949152542376e-05, "loss": 0.4961, "step": 2500 }, { "epoch": 1.4031805425631432, "grad_norm": 9.220566749572754, "learning_rate": 1.6896186440677965e-05, "loss": 0.4666, "step": 3000 }, { "epoch": 1.637043966323667, "grad_norm": 5.579341411590576, "learning_rate": 1.027542372881356e-05, "loss": 0.4887, "step": 3500 }, { "epoch": 1.8709073900841908, "grad_norm": 5.531935691833496, "learning_rate": 3.654661016949153e-06, "loss": 0.476, "step": 4000 } ], "logging_steps": 500, "max_steps": 4276, "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": 4592688627929088.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }