{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.1578947368421053, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.21052631578947367, "grad_norm": 3.658212184906006, "learning_rate": 2e-05, "loss": 44.3376, "step": 1 }, { "epoch": 0.21052631578947367, "eval_loss": 11.085034370422363, "eval_runtime": 0.4358, "eval_samples_per_second": 4.589, "eval_steps_per_second": 2.295, "step": 1 }, { "epoch": 0.42105263157894735, "grad_norm": 3.631204605102539, "learning_rate": 4e-05, "loss": 44.3414, "step": 2 }, { "epoch": 0.42105263157894735, "eval_loss": 11.084892272949219, "eval_runtime": 0.0103, "eval_samples_per_second": 194.406, "eval_steps_per_second": 97.203, "step": 2 }, { "epoch": 0.631578947368421, "grad_norm": 3.649850606918335, "learning_rate": 6e-05, "loss": 44.3161, "step": 3 }, { "epoch": 0.8421052631578947, "grad_norm": 3.6602396965026855, "learning_rate": 8e-05, "loss": 44.333, "step": 4 }, { "epoch": 0.8421052631578947, "eval_loss": 11.074262619018555, "eval_runtime": 0.0091, "eval_samples_per_second": 220.364, "eval_steps_per_second": 110.182, "step": 4 }, { "epoch": 1.1578947368421053, "grad_norm": 3.7224624156951904, "learning_rate": 0.0001, "loss": 44.2848, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 96448020480.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }