{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0003369768960215665, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.6848844801078327e-05, "eval_loss": 2.3428099155426025, "eval_runtime": 1498.8521, "eval_samples_per_second": 16.673, "eval_steps_per_second": 8.336, "step": 1 }, { "epoch": 5.0546534403234975e-05, "grad_norm": 2.6809027194976807, "learning_rate": 6e-05, "loss": 8.7832, "step": 3 }, { "epoch": 0.00010109306880646995, "grad_norm": 3.4458863735198975, "learning_rate": 0.00012, "loss": 9.3747, "step": 6 }, { "epoch": 0.00013479075840862662, "eval_loss": 2.295600652694702, "eval_runtime": 1503.1751, "eval_samples_per_second": 16.625, "eval_steps_per_second": 8.312, "step": 8 }, { "epoch": 0.00015163960320970494, "grad_norm": 4.538784503936768, "learning_rate": 0.00018, "loss": 9.3501, "step": 9 }, { "epoch": 0.0002021861376129399, "grad_norm": 6.206903457641602, "learning_rate": 0.00019510565162951537, "loss": 8.3669, "step": 12 }, { "epoch": 0.0002527326720161749, "grad_norm": 5.715407848358154, "learning_rate": 0.00017071067811865476, "loss": 9.2975, "step": 15 }, { "epoch": 0.00026958151681725324, "eval_loss": 2.2501394748687744, "eval_runtime": 1502.938, "eval_samples_per_second": 16.627, "eval_steps_per_second": 8.314, "step": 16 }, { "epoch": 0.0003032792064194099, "grad_norm": 3.972928524017334, "learning_rate": 0.00013090169943749476, "loss": 8.8518, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1200474229309440.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }