{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.1958863858961802, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.019588638589618023, "grad_norm": 0.15741384499943922, "learning_rate": 9e-05, "loss": 1.2379, "step": 10 }, { "epoch": 0.039177277179236046, "grad_norm": 0.09727684228244954, "learning_rate": 8e-05, "loss": 0.6525, "step": 20 }, { "epoch": 0.058765915768854066, "grad_norm": 0.048326423015033655, "learning_rate": 7e-05, "loss": 0.5573, "step": 30 }, { "epoch": 0.07835455435847209, "grad_norm": 0.019410146833111586, "learning_rate": 6e-05, "loss": 0.537, "step": 40 }, { "epoch": 0.0979431929480901, "grad_norm": 0.022042703238575993, "learning_rate": 5e-05, "loss": 0.5104, "step": 50 }, { "epoch": 0.11753183153770813, "grad_norm": 0.028125711976748517, "learning_rate": 4e-05, "loss": 0.5151, "step": 60 }, { "epoch": 0.13712047012732614, "grad_norm": 0.018545984749469877, "learning_rate": 3e-05, "loss": 0.5003, "step": 70 }, { "epoch": 0.15670910871694418, "grad_norm": 0.01788486630093878, "learning_rate": 2e-05, "loss": 0.5009, "step": 80 }, { "epoch": 0.1762977473065622, "grad_norm": 0.021150819386911185, "learning_rate": 1e-05, "loss": 0.5027, "step": 90 }, { "epoch": 0.1958863858961802, "grad_norm": 0.019105309450920132, "learning_rate": 0.0, "loss": 0.4927, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "total_flos": 50865518936064.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }