{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.016, "eval_steps": 20, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0032, "grad_norm": 0.0, "learning_rate": 2.9999999999999997e-05, "loss": 4.2451, "sae_grad_norm": 20.84289119605359, "step": 10 }, { "epoch": 0.0064, "grad_norm": 0.0, "learning_rate": 5.9999999999999995e-05, "loss": 3.3251, "sae_grad_norm": 36.11170541944039, "step": 20 }, { "epoch": 0.0064, "eval_runtime": 1.1705, "eval_samples_per_second": 34.175, "eval_steps_per_second": 17.087, "sae_grad_norm": 36.11170541944039, "step": 20 }, { "epoch": 0.0096, "grad_norm": 0.0, "learning_rate": 8.999999999999999e-05, "loss": 3.76, "sae_grad_norm": 51.673781878506645, "step": 30 }, { "epoch": 0.0128, "grad_norm": 0.0, "learning_rate": 0.00011999999999999999, "loss": 3.6995, "sae_grad_norm": 70.40541113432494, "step": 40 }, { "epoch": 0.0128, "eval_runtime": 0.9447, "eval_samples_per_second": 42.34, "eval_steps_per_second": 21.17, "sae_grad_norm": 70.40541113432494, "step": 40 }, { "epoch": 0.016, "grad_norm": 0.0, "learning_rate": 0.00015, "loss": 3.8664, "sae_grad_norm": 84.45994057300459, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 60, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1183163580297216.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }