{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.003580664412174259, "eval_steps": 3, "global_step": 9, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00039785160135269546, "grad_norm": 0.0, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00039785160135269546, "eval_loss": NaN, "eval_runtime": 30.8266, "eval_samples_per_second": 34.353, "eval_steps_per_second": 17.193, "step": 1 }, { "epoch": 0.0007957032027053909, "grad_norm": 0.0, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0011935548040580863, "grad_norm": 0.0, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0011935548040580863, "eval_loss": NaN, "eval_runtime": 28.9802, "eval_samples_per_second": 36.542, "eval_steps_per_second": 18.288, "step": 3 }, { "epoch": 0.0015914064054107818, "grad_norm": 0.0, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.001989258006763477, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0023871096081161725, "grad_norm": 0.0, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0023871096081161725, "eval_loss": NaN, "eval_runtime": 29.1428, "eval_samples_per_second": 36.338, "eval_steps_per_second": 18.186, "step": 6 }, { "epoch": 0.0027849612094688683, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0031828128108215637, "grad_norm": 0.0, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.003580664412174259, "grad_norm": 0.0, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.003580664412174259, "eval_loss": NaN, "eval_runtime": 29.0487, "eval_samples_per_second": 36.456, "eval_steps_per_second": 18.245, "step": 9 } ], "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": false }, "attributes": {} } }, "total_flos": 1478847803424768.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }