{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00855431993156544, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000427715996578272, "eval_loss": 2.9688284397125244, "eval_runtime": 14.9293, "eval_samples_per_second": 65.978, "eval_steps_per_second": 33.022, "step": 1 }, { "epoch": 0.0012831479897348161, "grad_norm": 1.316524863243103, "learning_rate": 6e-05, "loss": 2.7893, "step": 3 }, { "epoch": 0.0025662959794696323, "grad_norm": 1.1522525548934937, "learning_rate": 0.00012, "loss": 3.0151, "step": 6 }, { "epoch": 0.003421727972626176, "eval_loss": 2.836156129837036, "eval_runtime": 13.5098, "eval_samples_per_second": 72.91, "eval_steps_per_second": 36.492, "step": 8 }, { "epoch": 0.003849443969204448, "grad_norm": 1.1620888710021973, "learning_rate": 0.00018, "loss": 2.2736, "step": 9 }, { "epoch": 0.0051325919589392645, "grad_norm": 1.7971843481063843, "learning_rate": 0.00019510565162951537, "loss": 2.9401, "step": 12 }, { "epoch": 0.00641573994867408, "grad_norm": 1.240454077720642, "learning_rate": 0.00017071067811865476, "loss": 2.5096, "step": 15 }, { "epoch": 0.006843455945252352, "eval_loss": 2.646683692932129, "eval_runtime": 13.4282, "eval_samples_per_second": 73.353, "eval_steps_per_second": 36.714, "step": 16 }, { "epoch": 0.007698887938408896, "grad_norm": 1.0643540620803833, "learning_rate": 0.00013090169943749476, "loss": 2.3632, "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": 166605103300608.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }