{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 78, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2564102564102564, "grad_norm": 5.721946298566637, "learning_rate": 9.994965332706574e-06, "loss": 5.2582, "step": 10 }, { "epoch": 0.5128205128205128, "grad_norm": 2.8109843358784836, "learning_rate": 9.40297765928369e-06, "loss": 0.0252, "step": 20 }, { "epoch": 0.7692307692307693, "grad_norm": 0.23206407267268572, "learning_rate": 7.938926261462366e-06, "loss": 0.0201, "step": 30 }, { "epoch": 1.0256410256410255, "grad_norm": 0.45846925644305964, "learning_rate": 5.892784473993184e-06, "loss": 0.0238, "step": 40 }, { "epoch": 1.282051282051282, "grad_norm": 0.04034621588048863, "learning_rate": 3.669815772166625e-06, "loss": 0.0046, "step": 50 }, { "epoch": 1.5384615384615383, "grad_norm": 0.005579535835401499, "learning_rate": 1.7103063703014372e-06, "loss": 0.002, "step": 60 }, { "epoch": 1.7948717948717947, "grad_norm": 0.027412739220486586, "learning_rate": 4.0236113724274716e-07, "loss": 0.0027, "step": 70 }, { "epoch": 2.0, "step": 78, "total_flos": 8891638874112.0, "train_loss": 0.6841755338828079, "train_runtime": 566.7608, "train_samples_per_second": 4.34, "train_steps_per_second": 0.138 } ], "logging_steps": 10, "max_steps": 78, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8891638874112.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }