| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 100, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 590.2106302261352, | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.0432724766433239, | |
| "kl": 0.0030604258179664614, | |
| "learning_rate": 1.9876883405951378e-05, | |
| "loss": 0.0001, | |
| "reward": 0.5212053815834224, | |
| "reward_std": 0.31612331927753984, | |
| "rewards/accuracy_reward": 0.5212053815834224, | |
| "rewards/format_reward": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 595.2769241333008, | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.040159352123737335, | |
| "kl": 0.00987396240234375, | |
| "learning_rate": 1.777145961456971e-05, | |
| "loss": 0.0004, | |
| "reward": 0.7008928878232836, | |
| "reward_std": 0.20359436981379986, | |
| "rewards/accuracy_reward": 0.7008928878232836, | |
| "rewards/format_reward": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "completion_length": 569.7097345352173, | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.04419904574751854, | |
| "kl": 0.012125396728515625, | |
| "learning_rate": 1.3583679495453e-05, | |
| "loss": 0.0005, | |
| "reward": 0.6966518178582192, | |
| "reward_std": 0.19146922109648584, | |
| "rewards/accuracy_reward": 0.6966518178582192, | |
| "rewards/format_reward": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "completion_length": 567.0804929733276, | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.07321541756391525, | |
| "kl": 0.01595458984375, | |
| "learning_rate": 8.43565534959769e-06, | |
| "loss": 0.0006, | |
| "reward": 0.6687500299885869, | |
| "reward_std": 0.22048412784934043, | |
| "rewards/accuracy_reward": 0.6687500299885869, | |
| "rewards/format_reward": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "completion_length": 611.0003625869751, | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.07246600836515427, | |
| "kl": 0.038902664184570314, | |
| "learning_rate": 3.7067960895016277e-06, | |
| "loss": 0.0016, | |
| "reward": 0.6227678848430515, | |
| "reward_std": 0.27445384091697633, | |
| "rewards/accuracy_reward": 0.6227678848430515, | |
| "rewards/format_reward": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "completion_length": 589.521010017395, | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.054785873740911484, | |
| "kl": 0.033506584167480466, | |
| "learning_rate": 6.641957350279838e-07, | |
| "loss": 0.0013, | |
| "reward": 0.6674107430502773, | |
| "reward_std": 0.2312962483149022, | |
| "rewards/accuracy_reward": 0.6674107430502773, | |
| "rewards/format_reward": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "completion_length": 574.1501061575754, | |
| "epoch": 1.0, | |
| "kl": 0.034457615443638394, | |
| "reward": 0.6944621857255697, | |
| "reward_std": 0.22318161917584284, | |
| "rewards/accuracy_reward": 0.6944621857255697, | |
| "rewards/format_reward": 0.0, | |
| "step": 67, | |
| "total_flos": 0.0, | |
| "train_loss": 0.0008235528940029108, | |
| "train_runtime": 9299.7344, | |
| "train_samples_per_second": 0.806, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 67, | |
| "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 | |
| } | |