| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.851063829787234, | |
| "eval_steps": 100, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 517.0663162231446, | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 2.043825149536133, | |
| "kl": 0.001093578338623047, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "reward": 0.794419676065445, | |
| "reward_std": 0.3082874551415443, | |
| "rewards/accuracy_reward": 0.7933036014437675, | |
| "rewards/format_reward": 0.0011160714784637094, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "step": 5, | |
| "total_flos": 0.0, | |
| "train_loss": 4.3852842645719646e-05, | |
| "train_runtime": 520.3847, | |
| "train_samples_per_second": 1.441, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 5, | |
| "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": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |