{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.46403712296983757, "eval_steps": 50, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02320185614849188, "grad_norm": 29.851993456423653, "learning_rate": 5e-07, "loss": 1.6448, "step": 5 }, { "epoch": 0.04640371229698376, "grad_norm": 14.665681394229273, "learning_rate": 1e-06, "loss": 1.5147, "step": 10 }, { "epoch": 0.06960556844547564, "grad_norm": 7.818944779433003, "learning_rate": 9.998470286265414e-07, "loss": 1.2888, "step": 15 }, { "epoch": 0.09280742459396751, "grad_norm": 6.011350341653904, "learning_rate": 9.993882081071305e-07, "loss": 1.2291, "step": 20 }, { "epoch": 0.11600928074245939, "grad_norm": 5.834488035843988, "learning_rate": 9.986238191873872e-07, "loss": 1.1827, "step": 25 }, { "epoch": 0.13921113689095127, "grad_norm": 4.944851583820086, "learning_rate": 9.975543295858033e-07, "loss": 1.1637, "step": 30 }, { "epoch": 0.16241299303944315, "grad_norm": 5.051276519398371, "learning_rate": 9.961803937075514e-07, "loss": 1.1448, "step": 35 }, { "epoch": 0.18561484918793503, "grad_norm": 5.008630441799495, "learning_rate": 9.945028522440653e-07, "loss": 1.1539, "step": 40 }, { "epoch": 0.2088167053364269, "grad_norm": 4.527889171881266, "learning_rate": 9.925227316586314e-07, "loss": 1.1302, "step": 45 }, { "epoch": 0.23201856148491878, "grad_norm": 4.665448898349117, "learning_rate": 9.902412435583125e-07, "loss": 1.1315, "step": 50 }, { "epoch": 0.23201856148491878, "eval_loss": 1.1243596076965332, "eval_runtime": 107.3706, "eval_samples_per_second": 57.083, "eval_steps_per_second": 0.894, "step": 50 }, { "epoch": 0.2552204176334107, "grad_norm": 4.780072580854242, "learning_rate": 9.876597839525813e-07, "loss": 1.1184, "step": 55 }, { "epoch": 0.27842227378190254, "grad_norm": 4.698899616021614, "learning_rate": 9.847799323991233e-07, "loss": 1.1112, "step": 60 }, { "epoch": 0.30162412993039445, "grad_norm": 4.798544900134018, "learning_rate": 9.816034510373285e-07, "loss": 1.1022, "step": 65 }, { "epoch": 0.3248259860788863, "grad_norm": 4.7554420584590105, "learning_rate": 9.781322835100637e-07, "loss": 1.1109, "step": 70 }, { "epoch": 0.3480278422273782, "grad_norm": 4.715791460597178, "learning_rate": 9.743685537743856e-07, "loss": 1.1044, "step": 75 }, { "epoch": 0.37122969837587005, "grad_norm": 4.781446446456838, "learning_rate": 9.70314564801922e-07, "loss": 1.0982, "step": 80 }, { "epoch": 0.39443155452436196, "grad_norm": 4.616375479434296, "learning_rate": 9.659727971697173e-07, "loss": 1.0798, "step": 85 }, { "epoch": 0.4176334106728538, "grad_norm": 4.81678899141071, "learning_rate": 9.613459075424033e-07, "loss": 1.0925, "step": 90 }, { "epoch": 0.4408352668213457, "grad_norm": 4.804913673447656, "learning_rate": 9.564367270466245e-07, "loss": 1.0726, "step": 95 }, { "epoch": 0.46403712296983757, "grad_norm": 5.428814841421836, "learning_rate": 9.51248259538713e-07, "loss": 1.0732, "step": 100 }, { "epoch": 0.46403712296983757, "eval_loss": 1.079745888710022, "eval_runtime": 106.1023, "eval_samples_per_second": 57.765, "eval_steps_per_second": 0.905, "step": 100 } ], "logging_steps": 5, "max_steps": 645, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 589411381149696.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }