{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0031392246115209545, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003139224611520954, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0003139224611520954, "eval_loss": NaN, "eval_runtime": 26.8145, "eval_samples_per_second": 50.048, "eval_steps_per_second": 25.024, "step": 1 }, { "epoch": 0.0006278449223041908, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0009417673834562863, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0009417673834562863, "eval_loss": NaN, "eval_runtime": 26.4956, "eval_samples_per_second": 50.65, "eval_steps_per_second": 25.325, "step": 3 }, { "epoch": 0.0012556898446083817, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0015696123057604772, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0018835347669125726, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0018835347669125726, "eval_loss": NaN, "eval_runtime": 25.1869, "eval_samples_per_second": 53.282, "eval_steps_per_second": 26.641, "step": 6 }, { "epoch": 0.002197457228064668, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0025113796892167633, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.002825302150368859, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.002825302150368859, "eval_loss": NaN, "eval_runtime": 25.0843, "eval_samples_per_second": 53.5, "eval_steps_per_second": 26.75, "step": 9 }, { "epoch": 0.0031392246115209545, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "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": true }, "attributes": {} } }, "total_flos": 89038163804160.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }