{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0002118127998474948, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 4.236255996949896e-05, "grad_norm": 0.10746237635612488, "learning_rate": 1e-05, "loss": 10.3916, "step": 1 }, { "epoch": 4.236255996949896e-05, "eval_loss": 10.403565406799316, "eval_runtime": 148.5035, "eval_samples_per_second": 267.724, "eval_steps_per_second": 133.862, "step": 1 }, { "epoch": 8.472511993899791e-05, "grad_norm": 0.11559087038040161, "learning_rate": 2e-05, "loss": 10.3937, "step": 2 }, { "epoch": 8.472511993899791e-05, "eval_loss": 10.40353012084961, "eval_runtime": 155.8604, "eval_samples_per_second": 255.087, "eval_steps_per_second": 127.544, "step": 2 }, { "epoch": 0.00012708767990849687, "grad_norm": 0.10860913246870041, "learning_rate": 3e-05, "loss": 10.4081, "step": 3 }, { "epoch": 0.00016945023987799583, "grad_norm": 0.12747277319431305, "learning_rate": 4e-05, "loss": 10.3774, "step": 4 }, { "epoch": 0.00016945023987799583, "eval_loss": 10.403369903564453, "eval_runtime": 94.2286, "eval_samples_per_second": 421.931, "eval_steps_per_second": 210.966, "step": 4 }, { "epoch": 0.0002118127998474948, "grad_norm": 0.11898418515920639, "learning_rate": 5e-05, "loss": 10.4027, "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 }