{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0644122383252818, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01288244766505636, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 202.5386, "step": 1 }, { "epoch": 0.01288244766505636, "eval_loss": NaN, "eval_runtime": 164.6614, "eval_samples_per_second": 0.796, "eval_steps_per_second": 0.401, "step": 1 }, { "epoch": 0.02576489533011272, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.02576489533011272, "eval_loss": NaN, "eval_runtime": 5.1356, "eval_samples_per_second": 25.508, "eval_steps_per_second": 12.852, "step": 2 }, { "epoch": 0.03864734299516908, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 1512.3901, "step": 3 }, { "epoch": 0.05152979066022544, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 1690.3779, "step": 4 }, { "epoch": 0.05152979066022544, "eval_loss": NaN, "eval_runtime": 5.2163, "eval_samples_per_second": 25.114, "eval_steps_per_second": 12.653, "step": 4 }, { "epoch": 0.0644122383252818, "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": 6285103164555264.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }