{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00777000777000777, "eval_steps": 13, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001554001554001554, "eval_loss": 10.842114448547363, "eval_runtime": 8.1958, "eval_samples_per_second": 330.657, "eval_steps_per_second": 165.329, "step": 1 }, { "epoch": 0.001554001554001554, "grad_norm": 0.17869992554187775, "learning_rate": 0.00019396926207859084, "loss": 10.8419, "step": 10 }, { "epoch": 0.00202020202020202, "eval_loss": 10.832371711730957, "eval_runtime": 7.4803, "eval_samples_per_second": 362.284, "eval_steps_per_second": 181.142, "step": 13 }, { "epoch": 0.003108003108003108, "grad_norm": 0.2805086672306061, "learning_rate": 0.00015000000000000001, "loss": 10.8267, "step": 20 }, { "epoch": 0.00404040404040404, "eval_loss": 10.817840576171875, "eval_runtime": 7.553, "eval_samples_per_second": 358.798, "eval_steps_per_second": 179.399, "step": 26 }, { "epoch": 0.004662004662004662, "grad_norm": 0.2840530276298523, "learning_rate": 8.263518223330697e-05, "loss": 10.8289, "step": 30 }, { "epoch": 0.006060606060606061, "eval_loss": 10.809207916259766, "eval_runtime": 7.5221, "eval_samples_per_second": 360.272, "eval_steps_per_second": 180.136, "step": 39 }, { "epoch": 0.006216006216006216, "grad_norm": 0.2813047766685486, "learning_rate": 2.339555568810221e-05, "loss": 10.8111, "step": 40 }, { "epoch": 0.00777000777000777, "grad_norm": 0.24003192782402039, "learning_rate": 0.0, "loss": 10.8086, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6336784760832.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }