{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.008593833924159416, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008593833924159416, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0008593833924159416, "eval_loss": NaN, "eval_runtime": 177.4953, "eval_samples_per_second": 11.043, "eval_steps_per_second": 5.521, "step": 1 }, { "epoch": 0.0017187667848318831, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.002578150177247825, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.002578150177247825, "eval_loss": NaN, "eval_runtime": 43.7849, "eval_samples_per_second": 44.764, "eval_steps_per_second": 22.382, "step": 3 }, { "epoch": 0.0034375335696637662, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.004296916962079708, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.00515630035449565, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.00515630035449565, "eval_loss": NaN, "eval_runtime": 43.8551, "eval_samples_per_second": 44.693, "eval_steps_per_second": 22.346, "step": 6 }, { "epoch": 0.006015683746911591, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.0068750671393275325, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.007734450531743474, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.007734450531743474, "eval_loss": NaN, "eval_runtime": 43.8215, "eval_samples_per_second": 44.727, "eval_steps_per_second": 22.363, "step": 9 }, { "epoch": 0.008593833924159416, "grad_norm": NaN, "learning_rate": 0.0001, "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": 7229771171758080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }