{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0012759170653907496, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004253056884635832, "grad_norm": 2.6827280521392822, "learning_rate": 2e-05, "loss": 8.9009, "step": 1 }, { "epoch": 0.0004253056884635832, "eval_loss": 8.532660484313965, "eval_runtime": 27.5485, "eval_samples_per_second": 35.937, "eval_steps_per_second": 17.968, "step": 1 }, { "epoch": 0.0008506113769271664, "grad_norm": 2.467726707458496, "learning_rate": 4e-05, "loss": 8.2356, "step": 2 }, { "epoch": 0.0012759170653907496, "grad_norm": 2.839933156967163, "learning_rate": 6e-05, "loss": 8.982, "step": 3 }, { "epoch": 0.0012759170653907496, "eval_loss": 8.52444839477539, "eval_runtime": 27.5088, "eval_samples_per_second": 35.988, "eval_steps_per_second": 17.994, "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": 1628971204608.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }