{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 109, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.09195402298850575, "grad_norm": 1.2017886638641357, "learning_rate": 9e-06, "loss": 0.7641, "step": 10 }, { "epoch": 0.1839080459770115, "grad_norm": 0.3533852696418762, "learning_rate": 1.9e-05, "loss": 0.6854, "step": 20 }, { "epoch": 0.27586206896551724, "grad_norm": 0.3782903254032135, "learning_rate": 2.9e-05, "loss": 0.5897, "step": 30 }, { "epoch": 0.367816091954023, "grad_norm": 0.3457210958003998, "learning_rate": 3.9000000000000006e-05, "loss": 0.499, "step": 40 }, { "epoch": 0.45977011494252873, "grad_norm": 0.39099201560020447, "learning_rate": 4.9e-05, "loss": 0.5542, "step": 50 }, { "epoch": 0.5517241379310345, "grad_norm": 0.3361814618110657, "learning_rate": 4.7183801876414294e-05, "loss": 0.4896, "step": 60 }, { "epoch": 0.6436781609195402, "grad_norm": 0.26046183705329895, "learning_rate": 3.826052270299356e-05, "loss": 0.5246, "step": 70 }, { "epoch": 0.735632183908046, "grad_norm": 0.3294391334056854, "learning_rate": 2.566551303594437e-05, "loss": 0.5291, "step": 80 }, { "epoch": 0.8275862068965517, "grad_norm": 0.330019474029541, "learning_rate": 1.2886228241683749e-05, "loss": 0.5042, "step": 90 }, { "epoch": 0.9195402298850575, "grad_norm": 0.30832400918006897, "learning_rate": 3.4611479651548457e-06, "loss": 0.5151, "step": 100 } ], "logging_steps": 10, "max_steps": 109, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.0348514000317645e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }