{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016875856977112118, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00033751713954224236, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00033751713954224236, "eval_loss": NaN, "eval_runtime": 368.5131, "eval_samples_per_second": 13.541, "eval_steps_per_second": 6.77, "step": 1 }, { "epoch": 0.0006750342790844847, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 1998.1788, "step": 2 }, { "epoch": 0.0006750342790844847, "eval_loss": NaN, "eval_runtime": 294.231, "eval_samples_per_second": 16.959, "eval_steps_per_second": 8.48, "step": 2 }, { "epoch": 0.0010125514186267272, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 3.3927, "step": 3 }, { "epoch": 0.0013500685581689694, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0013500685581689694, "eval_loss": NaN, "eval_runtime": 278.5015, "eval_samples_per_second": 17.917, "eval_steps_per_second": 8.959, "step": 4 }, { "epoch": 0.0016875856977112118, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.00751985082368e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }