{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.030897207367795602, "eval_steps": 62, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0030897207367795603, "grad_norm": 7364.53759765625, "learning_rate": 4.0000000000000004e-11, "loss": 11.6505, "step": 1 }, { "epoch": 0.006179441473559121, "grad_norm": 7197.6689453125, "learning_rate": 8.000000000000001e-11, "loss": 11.6409, "step": 2 }, { "epoch": 0.009269162210338681, "grad_norm": 7166.62353515625, "learning_rate": 1.2e-10, "loss": 11.5128, "step": 3 }, { "epoch": 0.012358882947118241, "grad_norm": 7712.10546875, "learning_rate": 1.6000000000000002e-10, "loss": 11.9053, "step": 4 }, { "epoch": 0.015448603683897801, "grad_norm": 7366.1494140625, "learning_rate": 2e-10, "loss": 11.5439, "step": 5 }, { "epoch": 0.018538324420677363, "grad_norm": 6841.82763671875, "learning_rate": 1.9984815164333162e-10, "loss": 11.3454, "step": 6 }, { "epoch": 0.02162804515745692, "grad_norm": 7155.77978515625, "learning_rate": 1.9939306773179497e-10, "loss": 11.4832, "step": 7 }, { "epoch": 0.024717765894236483, "grad_norm": 7015.8427734375, "learning_rate": 1.9863613034027225e-10, "loss": 11.4497, "step": 8 }, { "epoch": 0.027807486631016044, "grad_norm": 6913.5205078125, "learning_rate": 1.9757963826274357e-10, "loss": 11.4214, "step": 9 }, { "epoch": 0.030897207367795602, "grad_norm": 6135.24267578125, "learning_rate": 1.9622680003092504e-10, "loss": 10.7529, "step": 10 } ], "logging_steps": 1, "max_steps": 62, "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": 1.659379307249664e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }