{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.01592990840302668, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0015929908403026682, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0015929908403026682, "eval_loss": NaN, "eval_runtime": 11.1681, "eval_samples_per_second": 23.728, "eval_steps_per_second": 11.909, "step": 1 }, { "epoch": 0.0031859816806053365, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0047789725209080045, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0047789725209080045, "eval_loss": NaN, "eval_runtime": 9.1076, "eval_samples_per_second": 29.097, "eval_steps_per_second": 14.603, "step": 3 }, { "epoch": 0.006371963361210673, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 4.2944, "step": 4 }, { "epoch": 0.00796495420151334, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 1.3276, "step": 5 }, { "epoch": 0.009557945041816009, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.009557945041816009, "eval_loss": NaN, "eval_runtime": 9.1789, "eval_samples_per_second": 28.871, "eval_steps_per_second": 14.49, "step": 6 }, { "epoch": 0.011150935882118677, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.012743926722421346, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.014336917562724014, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.014336917562724014, "eval_loss": NaN, "eval_runtime": 9.1431, "eval_samples_per_second": 28.984, "eval_steps_per_second": 14.546, "step": 9 }, { "epoch": 0.01592990840302668, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2136113493835776.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }