{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.015854141894569955, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0031708283789139914, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 115.749, "step": 1 }, { "epoch": 0.0031708283789139914, "eval_loss": NaN, "eval_runtime": 103.0792, "eval_samples_per_second": 5.161, "eval_steps_per_second": 2.581, "step": 1 }, { "epoch": 0.006341656757827983, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.006341656757827983, "eval_loss": NaN, "eval_runtime": 15.9484, "eval_samples_per_second": 33.358, "eval_steps_per_second": 16.679, "step": 2 }, { "epoch": 0.009512485136741973, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 237.3792, "step": 3 }, { "epoch": 0.012683313515655966, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 8167.9951, "step": 4 }, { "epoch": 0.012683313515655966, "eval_loss": NaN, "eval_runtime": 15.9776, "eval_samples_per_second": 33.297, "eval_steps_per_second": 16.648, "step": 4 }, { "epoch": 0.015854141894569955, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 12377.8818, "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": 4907475400654848.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }