{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.03720238095238095, "eval_steps": 50, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.018601190476190476, "grad_norm": 0.9360167980194092, "learning_rate": 0.0001, "loss": 0.992, "step": 50 }, { "epoch": 0.018601190476190476, "eval_loss": 0.7505561113357544, "eval_runtime": 1889.2709, "eval_samples_per_second": 2.845, "eval_steps_per_second": 0.356, "step": 50 }, { "epoch": 0.03720238095238095, "grad_norm": 0.8820974826812744, "learning_rate": 0.0, "loss": 0.726, "step": 100 }, { "epoch": 0.03720238095238095, "eval_loss": 0.7126273512840271, "eval_runtime": 1885.3137, "eval_samples_per_second": 2.851, "eval_steps_per_second": 0.356, "step": 100 } ], "logging_steps": 50, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 209379546759168.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }