{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0041532551136953585, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004153255113695359, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0004153255113695359, "eval_loss": NaN, "eval_runtime": 92.2099, "eval_samples_per_second": 10.997, "eval_steps_per_second": 5.498, "step": 1 }, { "epoch": 0.0008306510227390718, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0012459765341086076, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0012459765341086076, "eval_loss": NaN, "eval_runtime": 90.7861, "eval_samples_per_second": 11.169, "eval_steps_per_second": 5.585, "step": 3 }, { "epoch": 0.0016613020454781435, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0020766275568476792, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.002491953068217215, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.002491953068217215, "eval_loss": NaN, "eval_runtime": 90.8602, "eval_samples_per_second": 11.16, "eval_steps_per_second": 5.58, "step": 6 }, { "epoch": 0.002907278579586751, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.003322604090956287, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.003737929602325823, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.003737929602325823, "eval_loss": NaN, "eval_runtime": 90.7731, "eval_samples_per_second": 11.171, "eval_steps_per_second": 5.585, "step": 9 }, { "epoch": 0.0041532551136953585, "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": 6721646874329088.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }