{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008757206451142086, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00029190688170473617, "grad_norm": 1.1034588813781738, "learning_rate": 2e-05, "loss": 2.8594, "step": 1 }, { "epoch": 0.00029190688170473617, "eval_loss": 3.0735156536102295, "eval_runtime": 157.4323, "eval_samples_per_second": 4.586, "eval_steps_per_second": 4.586, "step": 1 }, { "epoch": 0.0005838137634094723, "grad_norm": 1.5020511150360107, "learning_rate": 4e-05, "loss": 2.6109, "step": 2 }, { "epoch": 0.0008757206451142086, "grad_norm": 0.7591434717178345, "learning_rate": 6e-05, "loss": 2.0645, "step": 3 }, { "epoch": 0.0008757206451142086, "eval_loss": 2.9684507846832275, "eval_runtime": 156.9028, "eval_samples_per_second": 4.602, "eval_steps_per_second": 4.602, "step": 3 } ], "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": false }, "attributes": {} } }, "total_flos": 2097116079980544.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }