| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.010104774920279952, |
| "eval_steps": 200, |
| "global_step": 61, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "completion_length": 870.4552083333333, |
| "epoch": 0.0016565204787344183, |
| "grad_norm": 0.5064831376075745, |
| "kl": 0.059619140625, |
| "learning_rate": 1.9848077530122083e-05, |
| "loss": 0.0024, |
| "reward": 0.041666666666666664, |
| "reward_std": 0.06621470103661219, |
| "rewards/accuracy_reward": 0.041666666666666664, |
| "rewards/format_reward": 0.0, |
| "step": 10 |
| }, |
| { |
| "completion_length": 906.740625, |
| "epoch": 0.0033130409574688366, |
| "grad_norm": 0.36804452538490295, |
| "kl": 0.0734771728515625, |
| "learning_rate": 1.7273736415730488e-05, |
| "loss": 0.0029, |
| "reward": 0.06979166666666667, |
| "reward_std": 0.09118111729621887, |
| "rewards/accuracy_reward": 0.06979166666666667, |
| "rewards/format_reward": 0.0, |
| "step": 20 |
| }, |
| { |
| "completion_length": 925.7322916666667, |
| "epoch": 0.004969561436203255, |
| "grad_norm": 0.35743197798728943, |
| "kl": 0.09958699544270834, |
| "learning_rate": 1.2306158707424402e-05, |
| "loss": 0.004, |
| "reward": 0.075, |
| "reward_std": 0.08785043035944302, |
| "rewards/accuracy_reward": 0.075, |
| "rewards/format_reward": 0.0, |
| "step": 30 |
| }, |
| { |
| "completion_length": 913.8552083333333, |
| "epoch": 0.006626081914937673, |
| "grad_norm": 0.704168975353241, |
| "kl": 0.11429850260416667, |
| "learning_rate": 6.579798566743314e-06, |
| "loss": 0.0046, |
| "reward": 0.06145833333333333, |
| "reward_std": 0.09644695445895195, |
| "rewards/accuracy_reward": 0.06145833333333333, |
| "rewards/format_reward": 0.0, |
| "step": 40 |
| }, |
| { |
| "completion_length": 949.690625, |
| "epoch": 0.008282602393672091, |
| "grad_norm": 0.28486713767051697, |
| "kl": 0.09008585611979167, |
| "learning_rate": 1.9787680724495617e-06, |
| "loss": 0.0036, |
| "reward": 0.04791666666666667, |
| "reward_std": 0.08070208380619685, |
| "rewards/accuracy_reward": 0.04791666666666667, |
| "rewards/format_reward": 0.0, |
| "step": 50 |
| }, |
| { |
| "completion_length": 888.1427083333333, |
| "epoch": 0.00993912287240651, |
| "grad_norm": 0.5252809524536133, |
| "kl": 0.10066935221354166, |
| "learning_rate": 1.6918417287318245e-08, |
| "loss": 0.004, |
| "reward": 0.08229166666666667, |
| "reward_std": 0.09388312324881554, |
| "rewards/accuracy_reward": 0.08229166666666667, |
| "rewards/format_reward": 0.0, |
| "step": 60 |
| }, |
| { |
| "completion_length": 926.375, |
| "epoch": 0.010104774920279952, |
| "kl": 0.10294596354166667, |
| "reward": 0.07291666666666667, |
| "reward_std": 0.10205466051896413, |
| "rewards/accuracy_reward": 0.07291666666666667, |
| "rewards/format_reward": 0.0, |
| "step": 61, |
| "total_flos": 0.0, |
| "train_loss": 0.003593232001742867, |
| "train_runtime": 3630.59, |
| "train_samples_per_second": 0.2, |
| "train_steps_per_second": 0.017 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 61, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
