{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5714285714285714, "eval_steps": 5, "global_step": 14, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04081632653061224, "eval_loss": 11.885836601257324, "eval_runtime": 2.4584, "eval_samples_per_second": 67.116, "eval_steps_per_second": 8.542, "step": 1 }, { "epoch": 0.20408163265306123, "eval_loss": 11.879362106323242, "eval_runtime": 1.6783, "eval_samples_per_second": 98.315, "eval_steps_per_second": 12.513, "step": 5 }, { "epoch": 0.40816326530612246, "grad_norm": 0.5947085618972778, "learning_rate": 7.300325188655761e-05, "loss": 11.8803, "step": 10 }, { "epoch": 0.40816326530612246, "eval_loss": 11.870901107788086, "eval_runtime": 1.6553, "eval_samples_per_second": 99.68, "eval_steps_per_second": 12.687, "step": 10 } ], "logging_steps": 10, "max_steps": 25, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 7, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 55694390722560.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }