| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 391.84375, | |
| "epoch": 0.1, | |
| "grad_norm": 4.776199817657471, | |
| "kl": 0.0, | |
| "learning_rate": 4.965903258506806e-07, | |
| "loss": 0.0, | |
| "reward": 1.6934495995519683, | |
| "reward_std": 0.8525555054657161, | |
| "rewards/concensus_correctness_reward_func": 0.08275000005960464, | |
| "rewards/consensus_reward_func": 0.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5625, | |
| "rewards/question_recreation_reward_func": 0.4939496314327698, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.49174999515525997, | |
| "step": 2 | |
| }, | |
| { | |
| "completion_length": 395.4375, | |
| "epoch": 0.2, | |
| "grad_norm": 9.231148719787598, | |
| "kl": 0.0014984993867983576, | |
| "learning_rate": 4.698684378016222e-07, | |
| "loss": 0.0, | |
| "reward": 2.3257811442017555, | |
| "reward_std": 1.0566792025929317, | |
| "rewards/concensus_correctness_reward_func": 0.35550000332295895, | |
| "rewards/consensus_reward_func": 0.5, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.5732811409980059, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.7719999738037586, | |
| "step": 4 | |
| }, | |
| { | |
| "completion_length": 420.0625, | |
| "epoch": 0.3, | |
| "grad_norm": 20.898244857788086, | |
| "kl": 0.0021197714013396762, | |
| "learning_rate": 4.193203929064353e-07, | |
| "loss": 0.0, | |
| "reward": 1.476895283907652, | |
| "reward_std": 1.1881672106683254, | |
| "rewards/concensus_correctness_reward_func": 0.06462499871850014, | |
| "rewards/consensus_reward_func": 0.375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.5145827787928283, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.5226874835789204, | |
| "step": 6 | |
| }, | |
| { | |
| "completion_length": 505.6875, | |
| "epoch": 0.4, | |
| "grad_norm": 4.914966583251953, | |
| "kl": 0.005482891705469228, | |
| "learning_rate": 3.5042385616324236e-07, | |
| "loss": 0.0, | |
| "reward": 2.152218254748732, | |
| "reward_std": 1.4283872889354825, | |
| "rewards/concensus_correctness_reward_func": 0.49387499690055847, | |
| "rewards/consensus_reward_func": 0.4375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.1875, | |
| "rewards/question_recreation_reward_func": 0.5518744704313576, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.48146875761449337, | |
| "step": 8 | |
| }, | |
| { | |
| "completion_length": 425.21875, | |
| "epoch": 0.5, | |
| "grad_norm": 5.341366767883301, | |
| "kl": 0.006879790460516233, | |
| "learning_rate": 2.706448363680831e-07, | |
| "loss": 0.0, | |
| "reward": 2.214655563235283, | |
| "reward_std": 1.2052832515910268, | |
| "rewards/concensus_correctness_reward_func": 0.10068750008940697, | |
| "rewards/consensus_reward_func": 0.4375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3125, | |
| "rewards/question_recreation_reward_func": 0.5675930762663484, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.796374985948205, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 442.5625, | |
| "epoch": 0.6, | |
| "grad_norm": 26.609264373779297, | |
| "kl": 0.009219564337399788, | |
| "learning_rate": 1.886286282148002e-07, | |
| "loss": 0.0, | |
| "reward": 1.690632976591587, | |
| "reward_std": 1.378328304272145, | |
| "rewards/concensus_correctness_reward_func": 0.2481249999254942, | |
| "rewards/consensus_reward_func": 0.4375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0625, | |
| "rewards/question_recreation_reward_func": 0.4131954708136618, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.5293124988675117, | |
| "step": 12 | |
| }, | |
| { | |
| "completion_length": 428.0, | |
| "epoch": 0.7, | |
| "grad_norm": 4.339048862457275, | |
| "kl": 0.00990395323606208, | |
| "learning_rate": 1.1326296046939333e-07, | |
| "loss": 0.0, | |
| "reward": 1.9994048587977886, | |
| "reward_std": 1.3680745382444002, | |
| "rewards/concensus_correctness_reward_func": 0.1614375002682209, | |
| "rewards/consensus_reward_func": 0.375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.5740923208650202, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.6388749964535236, | |
| "step": 14 | |
| }, | |
| { | |
| "completion_length": 438.03125, | |
| "epoch": 0.8, | |
| "grad_norm": 4.747790813446045, | |
| "kl": 0.007855257164919749, | |
| "learning_rate": 5.271487265090163e-08, | |
| "loss": 0.0, | |
| "reward": 1.9228089675307274, | |
| "reward_std": 0.6404511121800169, | |
| "rewards/concensus_correctness_reward_func": 0.11306249909102917, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3125, | |
| "rewards/question_recreation_reward_func": 0.6690589864738286, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.7031874842941761, | |
| "step": 16 | |
| }, | |
| { | |
| "completion_length": 416.875, | |
| "epoch": 0.9, | |
| "grad_norm": 5.46245002746582, | |
| "kl": 0.008813429856672883, | |
| "learning_rate": 1.3545689574841341e-08, | |
| "loss": 0.0, | |
| "reward": 1.7960961200296879, | |
| "reward_std": 1.2154418476857245, | |
| "rewards/concensus_correctness_reward_func": 0.12325000017881393, | |
| "rewards/consensus_reward_func": 0.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.1875, | |
| "rewards/question_recreation_reward_func": 0.6314085975755006, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.728937485255301, | |
| "step": 18 | |
| }, | |
| { | |
| "completion_length": 418.15625, | |
| "epoch": 1.0, | |
| "grad_norm": 7.303548812866211, | |
| "kl": 0.012376634433167055, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "reward": 2.181873619556427, | |
| "reward_std": 1.3524082526564598, | |
| "rewards/concensus_correctness_reward_func": 0.18056249991059303, | |
| "rewards/consensus_reward_func": 0.25, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.5, | |
| "rewards/question_recreation_reward_func": 0.6620298526249826, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.0, | |
| "rewards/xmlcount_reward_func": 0.5892812423408031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 20, | |
| "total_flos": 0.0, | |
| "train_loss": 6.427429616451263e-06, | |
| "train_runtime": 417.5088, | |
| "train_samples_per_second": 0.766, | |
| "train_steps_per_second": 0.048 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |