{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.004231460911879826, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004231460911879826, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0004231460911879826, "eval_loss": NaN, "eval_runtime": 24.7738, "eval_samples_per_second": 40.163, "eval_steps_per_second": 20.102, "step": 1 }, { "epoch": 0.0008462921823759652, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0012694382735639479, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0012694382735639479, "eval_loss": NaN, "eval_runtime": 23.531, "eval_samples_per_second": 42.285, "eval_steps_per_second": 21.164, "step": 3 }, { "epoch": 0.0016925843647519305, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.002115730455939913, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0025388765471278957, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0025388765471278957, "eval_loss": NaN, "eval_runtime": 23.7377, "eval_samples_per_second": 41.917, "eval_steps_per_second": 20.979, "step": 6 }, { "epoch": 0.0029620226383158784, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.003385168729503861, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.003808314820691844, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.003808314820691844, "eval_loss": NaN, "eval_runtime": 23.5904, "eval_samples_per_second": 42.178, "eval_steps_per_second": 21.11, "step": 9 }, { "epoch": 0.004231460911879826, "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": 324298258513920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }