{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.962406015037594, "eval_steps": 500, "global_step": 66, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.3007518796992481, "grad_norm": 12.646174141299479, "learning_rate": 9.971674001050687e-06, "loss": 2.7845, "step": 10 }, { "epoch": 0.6015037593984962, "grad_norm": 6.093140895856158, "learning_rate": 9.013558189654819e-06, "loss": 0.4368, "step": 20 }, { "epoch": 0.9022556390977443, "grad_norm": 4.555969993326182, "learning_rate": 6.944120877366605e-06, "loss": 0.3244, "step": 30 }, { "epoch": 1.1804511278195489, "grad_norm": 2.9897253896116878, "learning_rate": 4.336372363581391e-06, "loss": 0.2826, "step": 40 }, { "epoch": 1.481203007518797, "grad_norm": 3.2146230224454997, "learning_rate": 1.912376925269041e-06, "loss": 0.2758, "step": 50 }, { "epoch": 1.781954887218045, "grad_norm": 2.6872997954615556, "learning_rate": 3.433191127383079e-07, "loss": 0.2663, "step": 60 }, { "epoch": 1.962406015037594, "step": 66, "total_flos": 9474721710080.0, "train_loss": 0.6857994849031622, "train_runtime": 500.0437, "train_samples_per_second": 16.991, "train_steps_per_second": 0.132 } ], "logging_steps": 10, "max_steps": 66, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9474721710080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }