{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0011976944382064525, "eval_steps": 4, "global_step": 4, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002994236095516131, "grad_norm": 16.735450744628906, "learning_rate": 2e-05, "loss": 10.969, "step": 1 }, { "epoch": 0.0002994236095516131, "eval_loss": 11.57262897491455, "eval_runtime": 82.9715, "eval_samples_per_second": 8.485, "eval_steps_per_second": 8.485, "step": 1 }, { "epoch": 0.0005988472191032262, "grad_norm": 10.167157173156738, "learning_rate": 4e-05, "loss": 10.7129, "step": 2 }, { "epoch": 0.0008982708286548395, "grad_norm": 15.215925216674805, "learning_rate": 6e-05, "loss": 10.434, "step": 3 }, { "epoch": 0.0011976944382064525, "grad_norm": 15.04845142364502, "learning_rate": 8e-05, "loss": 9.5194, "step": 4 }, { "epoch": 0.0011976944382064525, "eval_loss": 11.429813385009766, "eval_runtime": 85.0662, "eval_samples_per_second": 8.276, "eval_steps_per_second": 8.276, "step": 4 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 4, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1483774567120896.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }