| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.96, |
| "eval_steps": 100, |
| "global_step": 12, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "completion_length": 509.0484457015991, |
| "epoch": 0.16, |
| "grad_norm": 0.0, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": -0.0, |
| "reward": 0.02109375037252903, |
| "reward_std": 0.05050475895404816, |
| "rewards/format_reward": 0.0, |
| "rewards/safety_reward": 0.02109375037252903, |
| "step": 2 |
| }, |
| { |
| "completion_length": 526.2656288146973, |
| "epoch": 0.32, |
| "grad_norm": 0.0, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": -0.0, |
| "reward": 0.018750000512227416, |
| "reward_std": 0.04200741811655462, |
| "rewards/format_reward": 0.0, |
| "rewards/safety_reward": 0.018750000512227416, |
| "step": 4 |
| }, |
| { |
| "completion_length": 618.5132894515991, |
| "epoch": 0.48, |
| "grad_norm": 0.0, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": -0.0, |
| "reward": 0.016406250302679837, |
| "reward_std": 0.039956981083378196, |
| "rewards/format_reward": 0.0, |
| "rewards/safety_reward": 0.016406250302679837, |
| "step": 6 |
| }, |
| { |
| "completion_length": 549.8492269515991, |
| "epoch": 0.64, |
| "grad_norm": 0.0, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": -0.0, |
| "reward": 0.010937500221189111, |
| "reward_std": 0.026015249313786626, |
| "rewards/format_reward": 0.0, |
| "rewards/safety_reward": 0.010937500221189111, |
| "step": 8 |
| }, |
| { |
| "completion_length": 561.9484462738037, |
| "epoch": 0.8, |
| "grad_norm": 0.0, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": -0.0, |
| "reward": 0.00703125010477379, |
| "reward_std": 0.018361149355769157, |
| "rewards/format_reward": 0.0, |
| "rewards/safety_reward": 0.00703125010477379, |
| "step": 10 |
| }, |
| { |
| "completion_length": 525.280478477478, |
| "epoch": 0.96, |
| "grad_norm": 0.0, |
| "kl": 0.0, |
| "learning_rate": 0.0, |
| "loss": -0.0, |
| "reward": 0.01406250020954758, |
| "reward_std": 0.032143609365448356, |
| "rewards/format_reward": 0.0, |
| "rewards/safety_reward": 0.01406250020954758, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.96, |
| "step": 12, |
| "total_flos": 0.0, |
| "train_loss": -1.0089328076704855e-09, |
| "train_runtime": 2799.8634, |
| "train_samples_per_second": 0.357, |
| "train_steps_per_second": 0.004 |
| } |
| ], |
| "logging_steps": 2, |
| "max_steps": 12, |
| "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 |
| } |
|
|
