{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006643669349686981, "eval_steps": 10, "global_step": 26, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00025552574421873004, "eval_loss": 0.44080615043640137, "eval_runtime": 163.4805, "eval_samples_per_second": 10.081, "eval_steps_per_second": 5.04, "step": 1 }, { "epoch": 0.0012776287210936501, "grad_norm": 0.6050224304199219, "learning_rate": 5e-05, "loss": 0.3806, "step": 5 }, { "epoch": 0.0025552574421873002, "grad_norm": 0.3790658712387085, "learning_rate": 0.0001, "loss": 0.3812, "step": 10 }, { "epoch": 0.0025552574421873002, "eval_loss": 0.36030489206314087, "eval_runtime": 168.9311, "eval_samples_per_second": 9.755, "eval_steps_per_second": 4.878, "step": 10 }, { "epoch": 0.0038328861632809506, "grad_norm": 0.6246739029884338, "learning_rate": 9.619397662556435e-05, "loss": 0.2917, "step": 15 }, { "epoch": 0.0051105148843746005, "grad_norm": 0.3205125331878662, "learning_rate": 8.535533905932738e-05, "loss": 0.2045, "step": 20 }, { "epoch": 0.0051105148843746005, "eval_loss": 0.18292254209518433, "eval_runtime": 213.9892, "eval_samples_per_second": 7.701, "eval_steps_per_second": 3.851, "step": 20 }, { "epoch": 0.006388143605468251, "grad_norm": 0.29717549681663513, "learning_rate": 6.91341716182545e-05, "loss": 0.1541, "step": 25 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1154618474102784.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }