{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0009804106412262675, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 7.541620317125135e-05, "eval_loss": 1.8562190532684326, "eval_runtime": 900.2586, "eval_samples_per_second": 6.203, "eval_steps_per_second": 3.101, "step": 1 }, { "epoch": 0.0003770810158562567, "grad_norm": 4.088282108306885, "learning_rate": 5e-05, "loss": 7.7757, "step": 5 }, { "epoch": 0.0007541620317125134, "grad_norm": 5.26944637298584, "learning_rate": 0.0001, "loss": 6.9662, "step": 10 }, { "epoch": 0.0007541620317125134, "eval_loss": 1.3146437406539917, "eval_runtime": 903.0345, "eval_samples_per_second": 6.184, "eval_steps_per_second": 3.092, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7345973797847040.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }