{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0007958536027297779, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00015917072054595557, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00015917072054595557, "eval_loss": NaN, "eval_runtime": 28.4449, "eval_samples_per_second": 372.018, "eval_steps_per_second": 186.009, "step": 1 }, { "epoch": 0.00031834144109191113, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.00031834144109191113, "eval_loss": NaN, "eval_runtime": 18.3463, "eval_samples_per_second": 576.791, "eval_steps_per_second": 288.396, "step": 2 }, { "epoch": 0.0004775121616378667, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0006366828821838223, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 31.1623, "step": 4 }, { "epoch": 0.0006366828821838223, "eval_loss": NaN, "eval_runtime": 18.1729, "eval_samples_per_second": 582.294, "eval_steps_per_second": 291.147, "step": 4 }, { "epoch": 0.0007958536027297779, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 35202201550848.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }