{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.028099754127151388, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005619950825430277, "grad_norm": 1.6374412775039673, "learning_rate": 1e-05, "loss": 33.9083, "step": 1 }, { "epoch": 0.005619950825430277, "eval_loss": 2.168093204498291, "eval_runtime": 74.941, "eval_samples_per_second": 4.003, "eval_steps_per_second": 2.002, "step": 1 }, { "epoch": 0.011239901650860555, "grad_norm": 2.166417360305786, "learning_rate": 2e-05, "loss": 34.7398, "step": 2 }, { "epoch": 0.011239901650860555, "eval_loss": 2.1620900630950928, "eval_runtime": 28.814, "eval_samples_per_second": 10.412, "eval_steps_per_second": 5.206, "step": 2 }, { "epoch": 0.01685985247629083, "grad_norm": 1.8182653188705444, "learning_rate": 3e-05, "loss": 35.0707, "step": 3 }, { "epoch": 0.02247980330172111, "grad_norm": 1.659819483757019, "learning_rate": 4e-05, "loss": 32.552, "step": 4 }, { "epoch": 0.02247980330172111, "eval_loss": 2.158710241317749, "eval_runtime": 25.416, "eval_samples_per_second": 11.804, "eval_steps_per_second": 5.902, "step": 4 }, { "epoch": 0.028099754127151388, "grad_norm": 1.8540648221969604, "learning_rate": 5e-05, "loss": 34.4764, "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": 6514996968161280.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }