{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.029038112522686024, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005807622504537205, "grad_norm": 1.6035223007202148, "learning_rate": 1e-05, "loss": 5.8163, "step": 1 }, { "epoch": 0.005807622504537205, "eval_loss": 6.147349834442139, "eval_runtime": 41.5884, "eval_samples_per_second": 6.973, "eval_steps_per_second": 3.487, "step": 1 }, { "epoch": 0.01161524500907441, "grad_norm": 1.8557497262954712, "learning_rate": 2e-05, "loss": 6.5473, "step": 2 }, { "epoch": 0.01161524500907441, "eval_loss": 6.132379531860352, "eval_runtime": 8.995, "eval_samples_per_second": 32.24, "eval_steps_per_second": 16.12, "step": 2 }, { "epoch": 0.017422867513611617, "grad_norm": 1.7788299322128296, "learning_rate": 3e-05, "loss": 6.5644, "step": 3 }, { "epoch": 0.02323049001814882, "grad_norm": 1.7742470502853394, "learning_rate": 4e-05, "loss": 6.8467, "step": 4 }, { "epoch": 0.02323049001814882, "eval_loss": 6.098387718200684, "eval_runtime": 9.176, "eval_samples_per_second": 31.604, "eval_steps_per_second": 15.802, "step": 4 }, { "epoch": 0.029038112522686024, "grad_norm": 1.6816157102584839, "learning_rate": 5e-05, "loss": 6.5706, "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": 978955586764800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }