{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006916825177243645, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006916825177243646, "grad_norm": 0.28342047333717346, "learning_rate": 0.0, "loss": 2.4194, "step": 1 }, { "epoch": 0.0013833650354487291, "grad_norm": 0.28588056564331055, "learning_rate": 1.3698630136986302e-06, "loss": 2.6477, "step": 2 }, { "epoch": 0.0020750475531730937, "grad_norm": 0.3255966007709503, "learning_rate": 2.7397260273972604e-06, "loss": 2.7875, "step": 3 }, { "epoch": 0.0027667300708974583, "grad_norm": 0.34641197323799133, "learning_rate": 4.10958904109589e-06, "loss": 2.7452, "step": 4 }, { "epoch": 0.0034584125886218224, "grad_norm": 0.28428879380226135, "learning_rate": 5.479452054794521e-06, "loss": 2.4148, "step": 5 }, { "epoch": 0.004150095106346187, "grad_norm": 0.29149842262268066, "learning_rate": 6.849315068493151e-06, "loss": 1.9822, "step": 6 }, { "epoch": 0.0048417776240705515, "grad_norm": 0.3635055422782898, "learning_rate": 8.21917808219178e-06, "loss": 1.9133, "step": 7 }, { "epoch": 0.0055334601417949165, "grad_norm": 0.3278924226760864, "learning_rate": 9.589041095890411e-06, "loss": 2.014, "step": 8 }, { "epoch": 0.006225142659519281, "grad_norm": 0.25329795479774475, "learning_rate": 1.0958904109589042e-05, "loss": 2.5676, "step": 9 }, { "epoch": 0.006916825177243645, "grad_norm": 0.40860116481781006, "learning_rate": 1.2328767123287671e-05, "loss": 2.7149, "step": 10 } ], "logging_steps": 1, "max_steps": 1446, "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": 347472609361920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }