{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.24096385542168675, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.024096385542168676, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.024096385542168676, "eval_loss": NaN, "eval_runtime": 1.6355, "eval_samples_per_second": 11.006, "eval_steps_per_second": 5.503, "step": 1 }, { "epoch": 0.04819277108433735, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.07228915662650602, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.07228915662650602, "eval_loss": NaN, "eval_runtime": 0.9433, "eval_samples_per_second": 19.082, "eval_steps_per_second": 9.541, "step": 3 }, { "epoch": 0.0963855421686747, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.12048192771084337, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.14457831325301204, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.14457831325301204, "eval_loss": NaN, "eval_runtime": 0.9451, "eval_samples_per_second": 19.046, "eval_steps_per_second": 9.523, "step": 6 }, { "epoch": 0.1686746987951807, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.1927710843373494, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.21686746987951808, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 1.142, "step": 9 }, { "epoch": 0.21686746987951808, "eval_loss": NaN, "eval_runtime": 0.9436, "eval_samples_per_second": 19.076, "eval_steps_per_second": 9.538, "step": 9 }, { "epoch": 0.24096385542168675, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3311008487571456.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }