{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.027382256297918947, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000547645125958379, "eval_loss": NaN, "eval_runtime": 41.254, "eval_samples_per_second": 4.921, "eval_steps_per_second": 4.921, "step": 1 }, { "epoch": 0.002738225629791895, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.00547645125958379, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.008214676889375685, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.01095290251916758, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.013691128148959474, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.013691128148959474, "eval_loss": NaN, "eval_runtime": 41.5419, "eval_samples_per_second": 4.887, "eval_steps_per_second": 4.887, "step": 25 }, { "epoch": 0.01642935377875137, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.019167579408543262, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.02190580503833516, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.024644030668127054, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 45 }, { "epoch": 0.027382256297918947, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.027382256297918947, "eval_loss": NaN, "eval_runtime": 41.4393, "eval_samples_per_second": 4.899, "eval_steps_per_second": 4.899, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2305513488384000.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }