{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.008820286659316428, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008820286659316428, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0008820286659316428, "eval_loss": NaN, "eval_runtime": 14.9718, "eval_samples_per_second": 31.927, "eval_steps_per_second": 15.963, "step": 1 }, { "epoch": 0.0017640573318632856, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.002646085997794928, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.002646085997794928, "eval_loss": NaN, "eval_runtime": 14.2997, "eval_samples_per_second": 33.427, "eval_steps_per_second": 16.714, "step": 3 }, { "epoch": 0.0035281146637265713, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.004410143329658214, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.005292171995589856, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.005292171995589856, "eval_loss": NaN, "eval_runtime": 14.6444, "eval_samples_per_second": 32.641, "eval_steps_per_second": 16.32, "step": 6 }, { "epoch": 0.006174200661521499, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0070562293274531425, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.007938257993384785, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.007938257993384785, "eval_loss": NaN, "eval_runtime": 14.7365, "eval_samples_per_second": 32.437, "eval_steps_per_second": 16.218, "step": 9 }, { "epoch": 0.008820286659316428, "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": 1752670792581120.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }