{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0006588591853206174, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.588591853206174e-05, "grad_norm": 0.0, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 6.588591853206174e-05, "eval_loss": NaN, "eval_runtime": 120.3267, "eval_samples_per_second": 53.114, "eval_steps_per_second": 26.561, "step": 1 }, { "epoch": 0.00013177183706412348, "grad_norm": 0.0, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0001976577555961852, "grad_norm": 0.0, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0001976577555961852, "eval_loss": NaN, "eval_runtime": 119.6137, "eval_samples_per_second": 53.43, "eval_steps_per_second": 26.719, "step": 3 }, { "epoch": 0.00026354367412824697, "grad_norm": 0.0, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0003294295926603087, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0003953155111923704, "grad_norm": 0.0, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0003953155111923704, "eval_loss": NaN, "eval_runtime": 120.0788, "eval_samples_per_second": 53.223, "eval_steps_per_second": 26.616, "step": 6 }, { "epoch": 0.00046120142972443215, "grad_norm": 0.0, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0005270873482564939, "grad_norm": 0.0, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0005929732667885557, "grad_norm": 0.0, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0005929732667885557, "eval_loss": NaN, "eval_runtime": 119.9464, "eval_samples_per_second": 53.282, "eval_steps_per_second": 26.645, "step": 9 }, { "epoch": 0.0006588591853206174, "grad_norm": 0.0, "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 }