{ "best_metric": 5.278811454772949, "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/de_clm/childes_42/checkpoint-8000", "epoch": 8.385744234800839, "eval_steps": 2000, "global_step": 8000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.0964360587002098, "eval_loss": 7.0908098220825195, "eval_runtime": 0.9834, "eval_samples_per_second": 1398.23, "eval_steps_per_second": 87.453, "step": 2000 }, { "epoch": 4.1928721174004195, "grad_norm": 1.4699604511260986, "learning_rate": 1e-05, "loss": 6.9765, "step": 4000 }, { "epoch": 4.1928721174004195, "eval_loss": 5.874638557434082, "eval_runtime": 0.973, "eval_samples_per_second": 1413.214, "eval_steps_per_second": 88.39, "step": 4000 }, { "epoch": 6.289308176100629, "eval_loss": 5.544075965881348, "eval_runtime": 0.9898, "eval_samples_per_second": 1389.228, "eval_steps_per_second": 86.89, "step": 6000 }, { "epoch": 8.385744234800839, "grad_norm": 2.451873779296875, "learning_rate": 1.9997500000000003e-05, "loss": 5.2182, "step": 8000 }, { "epoch": 8.385744234800839, "eval_loss": 5.278811454772949, "eval_runtime": 0.9809, "eval_samples_per_second": 1401.823, "eval_steps_per_second": 87.678, "step": 8000 } ], "logging_steps": 4000, "max_steps": 100000, "num_input_tokens_seen": 0, "num_train_epochs": 105, "save_steps": 4000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2068529059479552.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }