{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.4011026878015162, "eval_steps": 291, "global_step": 582, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.06891798759476224, "grad_norm": 47.0, "learning_rate": 9.88326321974139e-06, "loss": 0.6874, "step": 100 }, { "epoch": 0.13783597518952448, "grad_norm": 25.0, "learning_rate": 9.53850386931162e-06, "loss": 0.6895, "step": 200 }, { "epoch": 0.2005513439007581, "eval_accuracy": 0.569592611154865, "eval_loss": 0.6835629940032959, "eval_runtime": 378.97, "eval_samples_per_second": 221.131, "eval_steps_per_second": 27.643, "step": 291 }, { "epoch": 0.2067539627842867, "grad_norm": 21.625, "learning_rate": 8.981820387323976e-06, "loss": 0.6849, "step": 300 }, { "epoch": 0.27567195037904896, "grad_norm": 14.5, "learning_rate": 8.239206948702616e-06, "loss": 0.6902, "step": 400 }, { "epoch": 0.34458993797381116, "grad_norm": 23.875, "learning_rate": 7.345339674168113e-06, "loss": 0.6849, "step": 500 }, { "epoch": 0.4011026878015162, "eval_accuracy": 0.5740077802439083, "eval_loss": 0.6811934113502502, "eval_runtime": 377.4685, "eval_samples_per_second": 222.011, "eval_steps_per_second": 27.753, "step": 582 } ], "logging_steps": 100, "max_steps": 1451, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 291, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }