{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.001561085266477255, "eval_steps": 13, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.12217053295451e-05, "eval_loss": 1.078559398651123, "eval_runtime": 649.5895, "eval_samples_per_second": 20.761, "eval_steps_per_second": 10.38, "step": 1 }, { "epoch": 0.000312217053295451, "grad_norm": 2.7631337642669678, "learning_rate": 0.00019396926207859084, "loss": 3.8212, "step": 10 }, { "epoch": 0.0004058821692840863, "eval_loss": 0.8642444610595703, "eval_runtime": 649.702, "eval_samples_per_second": 20.757, "eval_steps_per_second": 10.379, "step": 13 }, { "epoch": 0.000624434106590902, "grad_norm": 3.041978597640991, "learning_rate": 0.00015000000000000001, "loss": 3.4017, "step": 20 }, { "epoch": 0.0008117643385681726, "eval_loss": 0.792748749256134, "eval_runtime": 649.5224, "eval_samples_per_second": 20.763, "eval_steps_per_second": 10.381, "step": 26 }, { "epoch": 0.000936651159886353, "grad_norm": 2.656667470932007, "learning_rate": 8.263518223330697e-05, "loss": 3.0561, "step": 30 }, { "epoch": 0.001217646507852259, "eval_loss": 0.7697806358337402, "eval_runtime": 650.8696, "eval_samples_per_second": 20.72, "eval_steps_per_second": 10.36, "step": 39 }, { "epoch": 0.001248868213181804, "grad_norm": 1.9232873916625977, "learning_rate": 2.339555568810221e-05, "loss": 2.9176, "step": 40 }, { "epoch": 0.001561085266477255, "grad_norm": 1.8639222383499146, "learning_rate": 0.0, "loss": 3.3282, "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": 1.3477766699679744e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }