{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.4819277108433735, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0963855421686747, "grad_norm": 0.037960704416036606, "learning_rate": 1e-05, "loss": 10.3789, "step": 1 }, { "epoch": 0.0963855421686747, "eval_loss": 10.373242378234863, "eval_runtime": 7.7193, "eval_samples_per_second": 2.332, "eval_steps_per_second": 1.166, "step": 1 }, { "epoch": 0.1927710843373494, "grad_norm": 0.038257721811532974, "learning_rate": 2e-05, "loss": 10.3838, "step": 2 }, { "epoch": 0.1927710843373494, "eval_loss": 10.373247146606445, "eval_runtime": 0.0356, "eval_samples_per_second": 506.287, "eval_steps_per_second": 253.143, "step": 2 }, { "epoch": 0.2891566265060241, "grad_norm": 0.042385563254356384, "learning_rate": 3e-05, "loss": 10.3788, "step": 3 }, { "epoch": 0.3855421686746988, "grad_norm": 0.03814742714166641, "learning_rate": 4e-05, "loss": 10.3801, "step": 4 }, { "epoch": 0.3855421686746988, "eval_loss": 10.37321949005127, "eval_runtime": 0.0486, "eval_samples_per_second": 370.209, "eval_steps_per_second": 185.105, "step": 4 }, { "epoch": 0.4819277108433735, "grad_norm": 0.03702155873179436, "learning_rate": 5e-05, "loss": 10.3812, "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": 258618163200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }