{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.11154489682097044, "eval_steps": 100, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.022308979364194088, "grad_norm": 4.709710597991943, "learning_rate": 0.00019999446787180336, "loss": 3.676974868774414, "step": 10 }, { "epoch": 0.044617958728388175, "grad_norm": 1.4567488431930542, "learning_rate": 0.00019989613595281384, "loss": 0.9999975204467774, "step": 20 }, { "epoch": 0.06692693809258227, "grad_norm": 1.1962672472000122, "learning_rate": 0.00019967500698688952, "loss": 0.6824670314788819, "step": 30 }, { "epoch": 0.08923591745677635, "grad_norm": 0.8628137707710266, "learning_rate": 0.0001993313527961959, "loss": 0.5993218421936035, "step": 40 }, { "epoch": 0.11154489682097044, "grad_norm": 1.0308934450149536, "learning_rate": 0.00019886559581668999, "loss": 0.542162561416626, "step": 50 } ], "logging_steps": 10, "max_steps": 898, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1525113500363712.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }