{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.9083969465648853, "eval_steps": 50, "global_step": 64, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.6106870229007634, "grad_norm": 2.7442173957824707, "learning_rate": 0.00016875, "loss": 8.526, "step": 10 }, { "epoch": 1.2213740458015268, "grad_norm": 3.6574127674102783, "learning_rate": 0.0001375, "loss": 7.1431, "step": 20 }, { "epoch": 1.83206106870229, "grad_norm": 0.8148283362388611, "learning_rate": 0.00010625000000000001, "loss": 6.9301, "step": 30 }, { "epoch": 2.4427480916030535, "grad_norm": 0.8494595885276794, "learning_rate": 7.500000000000001e-05, "loss": 6.6658, "step": 40 }, { "epoch": 3.053435114503817, "grad_norm": 0.6568369269371033, "learning_rate": 4.375e-05, "loss": 6.8838, "step": 50 }, { "epoch": 3.053435114503817, "eval_clap": 0.06955530494451523, "eval_loss": 5.957160949707031, "eval_runtime": 207.9947, "eval_samples_per_second": 0.038, "eval_steps_per_second": 0.038, "step": 50 }, { "epoch": 3.66412213740458, "grad_norm": 0.8757786750793457, "learning_rate": 1.25e-05, "loss": 6.7902, "step": 60 }, { "epoch": 3.9083969465648853, "step": 64, "total_flos": 18865322246328.0, "train_loss": 7.125617116689682, "train_runtime": 1106.5773, "train_samples_per_second": 0.943, "train_steps_per_second": 0.058 } ], "logging_steps": 10, "max_steps": 64, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 18865322246328.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }