{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 6, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03333333333333333, "eval_loss": 1.7954519987106323, "eval_runtime": 12.6939, "eval_samples_per_second": 15.913, "eval_steps_per_second": 2.048, "step": 1 }, { "epoch": 0.2, "eval_loss": 1.587748646736145, "eval_runtime": 13.1935, "eval_samples_per_second": 15.311, "eval_steps_per_second": 1.971, "step": 6 }, { "epoch": 0.3333333333333333, "grad_norm": 0.7594890594482422, "learning_rate": 8.117449009293668e-05, "loss": 1.6572, "step": 10 }, { "epoch": 0.4, "eval_loss": 1.4678586721420288, "eval_runtime": 13.0056, "eval_samples_per_second": 15.532, "eval_steps_per_second": 1.999, "step": 12 }, { "epoch": 0.6, "eval_loss": 1.4380106925964355, "eval_runtime": 13.0337, "eval_samples_per_second": 15.498, "eval_steps_per_second": 1.995, "step": 18 }, { "epoch": 0.6666666666666666, "grad_norm": 0.44762611389160156, "learning_rate": 2.8305813044122097e-05, "loss": 1.4574, "step": 20 }, { "epoch": 0.8, "eval_loss": 1.4284685850143433, "eval_runtime": 13.1202, "eval_samples_per_second": 15.396, "eval_steps_per_second": 1.982, "step": 24 }, { "epoch": 1.0, "grad_norm": 0.47178900241851807, "learning_rate": 0.0, "loss": 1.438, "step": 30 }, { "epoch": 1.0, "eval_loss": 1.4299424886703491, "eval_runtime": 13.0297, "eval_samples_per_second": 15.503, "eval_steps_per_second": 1.995, "step": 30 } ], "logging_steps": 10, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 8, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.166072205279232e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }