{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.928, "eval_steps": 500, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.096, "grad_norm": 5.721948623657227, "learning_rate": 1e-05, "loss": 0.8813, "step": 1 }, { "epoch": 0.192, "grad_norm": 5.702053546905518, "learning_rate": 2e-05, "loss": 0.8951, "step": 2 }, { "epoch": 0.288, "grad_norm": 2.4727985858917236, "learning_rate": 1.9848077530122083e-05, "loss": 0.8225, "step": 3 }, { "epoch": 0.384, "grad_norm": 7.1428422927856445, "learning_rate": 1.9396926207859085e-05, "loss": 0.8228, "step": 4 }, { "epoch": 0.48, "grad_norm": 11.155190467834473, "learning_rate": 1.866025403784439e-05, "loss": 0.8376, "step": 5 }, { "epoch": 0.576, "grad_norm": 6.886716842651367, "learning_rate": 1.766044443118978e-05, "loss": 0.8424, "step": 6 }, { "epoch": 0.672, "grad_norm": 4.017711162567139, "learning_rate": 1.6427876096865394e-05, "loss": 0.734, "step": 7 }, { "epoch": 0.768, "grad_norm": 2.7139785289764404, "learning_rate": 1.5000000000000002e-05, "loss": 0.7404, "step": 8 }, { "epoch": 0.864, "grad_norm": 2.1397907733917236, "learning_rate": 1.342020143325669e-05, "loss": 0.6981, "step": 9 }, { "epoch": 0.96, "grad_norm": 1.5976896286010742, "learning_rate": 1.1736481776669307e-05, "loss": 0.7054, "step": 10 }, { "epoch": 1.064, "grad_norm": 2.214726209640503, "learning_rate": 1e-05, "loss": 1.067, "step": 11 }, { "epoch": 1.16, "grad_norm": 1.026247501373291, "learning_rate": 8.263518223330698e-06, "loss": 0.6036, "step": 12 }, { "epoch": 1.256, "grad_norm": 0.7755782008171082, "learning_rate": 6.579798566743314e-06, "loss": 0.5737, "step": 13 }, { "epoch": 1.3519999999999999, "grad_norm": 0.9321668744087219, "learning_rate": 5.000000000000003e-06, "loss": 0.6661, "step": 14 }, { "epoch": 1.448, "grad_norm": 0.7070825695991516, "learning_rate": 3.5721239031346067e-06, "loss": 0.6214, "step": 15 }, { "epoch": 1.544, "grad_norm": 0.6577689051628113, "learning_rate": 2.339555568810221e-06, "loss": 0.5964, "step": 16 }, { "epoch": 1.6400000000000001, "grad_norm": 0.6352306008338928, "learning_rate": 1.339745962155613e-06, "loss": 0.6102, "step": 17 }, { "epoch": 1.736, "grad_norm": 0.5766989588737488, "learning_rate": 6.030737921409169e-07, "loss": 0.6004, "step": 18 }, { "epoch": 1.8319999999999999, "grad_norm": 0.5633364319801331, "learning_rate": 1.519224698779198e-07, "loss": 0.5862, "step": 19 }, { "epoch": 1.928, "grad_norm": 0.6367772221565247, "learning_rate": 0.0, "loss": 0.5677, "step": 20 }, { "epoch": 1.928, "step": 20, "total_flos": 20410757742592.0, "train_loss": 0.7236149907112122, "train_runtime": 1902.1245, "train_samples_per_second": 1.051, "train_steps_per_second": 0.011 } ], "logging_steps": 1, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 20410757742592.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }