{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0011725219481452168, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.8626097407260844e-05, "eval_loss": 1.0546101331710815, "eval_runtime": 1140.2093, "eval_samples_per_second": 6.299, "eval_steps_per_second": 3.149, "step": 1 }, { "epoch": 0.00017587829222178252, "grad_norm": 4.0905842781066895, "learning_rate": 6e-05, "loss": 4.3126, "step": 3 }, { "epoch": 0.00035175658444356505, "grad_norm": 2.7012600898742676, "learning_rate": 0.00012, "loss": 4.6228, "step": 6 }, { "epoch": 0.00046900877925808675, "eval_loss": 0.7599098682403564, "eval_runtime": 1144.7865, "eval_samples_per_second": 6.274, "eval_steps_per_second": 3.137, "step": 8 }, { "epoch": 0.0005276348766653475, "grad_norm": 3.152745008468628, "learning_rate": 0.00018, "loss": 3.6814, "step": 9 }, { "epoch": 0.0007035131688871301, "grad_norm": 3.7987024784088135, "learning_rate": 0.00019510565162951537, "loss": 2.6162, "step": 12 }, { "epoch": 0.0008793914611089126, "grad_norm": 2.854783296585083, "learning_rate": 0.00017071067811865476, "loss": 2.0406, "step": 15 }, { "epoch": 0.0009380175585161735, "eval_loss": 0.5670868754386902, "eval_runtime": 1144.568, "eval_samples_per_second": 6.275, "eval_steps_per_second": 3.137, "step": 16 }, { "epoch": 0.001055269753330695, "grad_norm": 2.479992628097534, "learning_rate": 0.00013090169943749476, "loss": 2.3954, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.26956599246848e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }