{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 26, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "entropy": 2.211050087213516, "epoch": 0.4, "grad_norm": 3.0342631340026855, "learning_rate": 0.0001794871794871795, "loss": 5.019304656982422, "mean_token_accuracy": 0.33383559435606003, "num_tokens": 805.0, "step": 5 }, { "entropy": 2.6462666034698485, "epoch": 0.8, "grad_norm": 1.7210749387741089, "learning_rate": 0.00015384615384615385, "loss": 3.432537841796875, "mean_token_accuracy": 0.4346353054046631, "num_tokens": 1577.0, "step": 10 }, { "entropy": 2.918430633015103, "epoch": 1.16, "grad_norm": 1.6194401979446411, "learning_rate": 0.00012820512820512823, "loss": 3.254618835449219, "mean_token_accuracy": 0.44318549666139817, "num_tokens": 2308.0, "step": 15 }, { "entropy": 3.054798972606659, "epoch": 1.56, "grad_norm": 1.7785245180130005, "learning_rate": 0.00010256410256410256, "loss": 2.870156478881836, "mean_token_accuracy": 0.46648297309875486, "num_tokens": 3099.0, "step": 20 }, { "entropy": 2.8321386098861696, "epoch": 1.96, "grad_norm": 1.9145296812057495, "learning_rate": 7.692307692307693e-05, "loss": 2.439097595214844, "mean_token_accuracy": 0.5192526414990425, "num_tokens": 3890.0, "step": 25 } ], "logging_steps": 5, "max_steps": 39, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 86874990170112.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }