{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.33613445378151263, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03361344537815126, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.03361344537815126, "eval_loss": NaN, "eval_runtime": 1.4347, "eval_samples_per_second": 9.061, "eval_steps_per_second": 4.879, "step": 1 }, { "epoch": 0.06722689075630252, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.10084033613445378, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.10084033613445378, "eval_loss": NaN, "eval_runtime": 0.4297, "eval_samples_per_second": 30.257, "eval_steps_per_second": 16.292, "step": 3 }, { "epoch": 0.13445378151260504, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.16806722689075632, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.20168067226890757, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.20168067226890757, "eval_loss": NaN, "eval_runtime": 0.4283, "eval_samples_per_second": 30.349, "eval_steps_per_second": 16.342, "step": 6 }, { "epoch": 0.23529411764705882, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.2689075630252101, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.3025210084033613, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.3025210084033613, "eval_loss": NaN, "eval_runtime": 0.4279, "eval_samples_per_second": 30.38, "eval_steps_per_second": 16.358, "step": 9 }, { "epoch": 0.33613445378151263, "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": 1768546400993280.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }