{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.002148458481039854, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002148458481039854, "grad_norm": 0.0, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0002148458481039854, "eval_loss": NaN, "eval_runtime": 56.4151, "eval_samples_per_second": 34.742, "eval_steps_per_second": 17.371, "step": 1 }, { "epoch": 0.0004296916962079708, "grad_norm": 0.0, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0006445375443119562, "grad_norm": 0.0, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0006445375443119562, "eval_loss": NaN, "eval_runtime": 56.8264, "eval_samples_per_second": 34.491, "eval_steps_per_second": 17.245, "step": 3 }, { "epoch": 0.0008593833924159416, "grad_norm": 0.0, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.001074229240519927, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0012890750886239124, "grad_norm": 0.0, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0012890750886239124, "eval_loss": NaN, "eval_runtime": 56.9455, "eval_samples_per_second": 34.419, "eval_steps_per_second": 17.209, "step": 6 }, { "epoch": 0.0015039209367278977, "grad_norm": 0.0, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0017187667848318831, "grad_norm": 0.0, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0019336126329358686, "grad_norm": 0.0, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0019336126329358686, "eval_loss": NaN, "eval_runtime": 56.9204, "eval_samples_per_second": 34.434, "eval_steps_per_second": 17.217, "step": 9 }, { "epoch": 0.002148458481039854, "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": 489477793382400.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }