{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006264355815410315, "eval_steps": 8, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00020881186051367718, "eval_loss": NaN, "eval_runtime": 68.8443, "eval_samples_per_second": 29.298, "eval_steps_per_second": 14.656, "step": 1 }, { "epoch": 0.0006264355815410315, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.001252871163082063, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0016704948841094174, "eval_loss": NaN, "eval_runtime": 67.8276, "eval_samples_per_second": 29.737, "eval_steps_per_second": 14.876, "step": 8 }, { "epoch": 0.0018793067446230946, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.002505742326164126, "grad_norm": NaN, "learning_rate": 0.00019510565162951537, "loss": 0.0, "step": 12 }, { "epoch": 0.0031321779077051574, "grad_norm": NaN, "learning_rate": 0.00017071067811865476, "loss": 0.0, "step": 15 }, { "epoch": 0.003340989768218835, "eval_loss": NaN, "eval_runtime": 67.7375, "eval_samples_per_second": 29.777, "eval_steps_per_second": 14.896, "step": 16 }, { "epoch": 0.003758613489246189, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 18 }, { "epoch": 0.004385049070787221, "grad_norm": NaN, "learning_rate": 8.435655349597689e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.005011484652328252, "grad_norm": NaN, "learning_rate": 4.12214747707527e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.005011484652328252, "eval_loss": NaN, "eval_runtime": 67.7468, "eval_samples_per_second": 29.773, "eval_steps_per_second": 14.894, "step": 24 }, { "epoch": 0.005637920233869284, "grad_norm": NaN, "learning_rate": 1.0899347581163221e-05, "loss": 0.0, "step": 27 }, { "epoch": 0.006264355815410315, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 30 } ], "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": true }, "attributes": {} } }, "total_flos": 4192264393850880.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }