| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.3582089552238806, |
| "eval_steps": 500, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03980099502487562, |
| "grad_norm": 9.524229049682617, |
| "learning_rate": 4.980474401576887e-07, |
| "logits/chosen": -0.1925463080406189, |
| "logits/rejected": -0.15873177349567413, |
| "logps/chosen": -239.6322021484375, |
| "logps/rejected": -242.57594299316406, |
| "loss": 0.8819, |
| "rewards/accuracies": 0.49281251430511475, |
| "rewards/chosen": -1.3072433471679688, |
| "rewards/margins": 0.008615786209702492, |
| "rewards/rejected": -1.315859079360962, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07960199004975124, |
| "grad_norm": 7.333236217498779, |
| "learning_rate": 4.922202605502572e-07, |
| "logits/chosen": 0.046361636370420456, |
| "logits/rejected": 0.08236894011497498, |
| "logps/chosen": -231.10765075683594, |
| "logps/rejected": -233.24984741210938, |
| "loss": 0.8361, |
| "rewards/accuracies": 0.48875001072883606, |
| "rewards/chosen": -0.9621695876121521, |
| "rewards/margins": -0.021255964413285255, |
| "rewards/rejected": -0.9409136772155762, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.11940298507462686, |
| "grad_norm": 5.164106369018555, |
| "learning_rate": 4.82609484512869e-07, |
| "logits/chosen": 0.0250965878367424, |
| "logits/rejected": 0.054141998291015625, |
| "logps/chosen": -229.79965209960938, |
| "logps/rejected": -231.60562133789062, |
| "loss": 0.8114, |
| "rewards/accuracies": 0.48750001192092896, |
| "rewards/chosen": -0.8564431667327881, |
| "rewards/margins": -0.01034404058009386, |
| "rewards/rejected": -0.8460990786552429, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.15920398009950248, |
| "grad_norm": 5.328795909881592, |
| "learning_rate": 4.6936523696827614e-07, |
| "logits/chosen": 0.039505548775196075, |
| "logits/rejected": 0.05482972040772438, |
| "logps/chosen": -233.69537353515625, |
| "logps/rejected": -236.25210571289062, |
| "loss": 0.7907, |
| "rewards/accuracies": 0.49406251311302185, |
| "rewards/chosen": -0.8005841970443726, |
| "rewards/margins": 0.00799934659153223, |
| "rewards/rejected": -0.8085834980010986, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.19900497512437812, |
| "grad_norm": 8.521681785583496, |
| "learning_rate": 4.5269439940365644e-07, |
| "logits/chosen": 0.11151163280010223, |
| "logits/rejected": 0.1460810899734497, |
| "logps/chosen": -227.23020935058594, |
| "logps/rejected": -230.19451904296875, |
| "loss": 0.7849, |
| "rewards/accuracies": 0.4946874976158142, |
| "rewards/chosen": -0.7644023299217224, |
| "rewards/margins": -0.004693666007369757, |
| "rewards/rejected": -0.7597086429595947, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.23880597014925373, |
| "grad_norm": 7.143113136291504, |
| "learning_rate": 4.328573782827409e-07, |
| "logits/chosen": 0.09673156589269638, |
| "logits/rejected": 0.14390873908996582, |
| "logps/chosen": -225.45919799804688, |
| "logps/rejected": -225.44052124023438, |
| "loss": 0.77, |
| "rewards/accuracies": 0.5045312643051147, |
| "rewards/chosen": -0.7256423830986023, |
| "rewards/margins": 0.004257932770997286, |
| "rewards/rejected": -0.7299003005027771, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.27860696517412936, |
| "grad_norm": 6.525391101837158, |
| "learning_rate": 4.1016403737218373e-07, |
| "logits/chosen": 0.05486857891082764, |
| "logits/rejected": 0.09620587527751923, |
| "logps/chosen": -228.3573760986328, |
| "logps/rejected": -223.32395935058594, |
| "loss": 0.7696, |
| "rewards/accuracies": 0.5034375190734863, |
| "rewards/chosen": -0.7243590354919434, |
| "rewards/margins": 0.0008349200943484902, |
| "rewards/rejected": -0.7251940369606018, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.31840796019900497, |
| "grad_norm": 8.071100234985352, |
| "learning_rate": 3.849688575211836e-07, |
| "logits/chosen": 0.004134657327085733, |
| "logits/rejected": 0.02180260606110096, |
| "logps/chosen": -234.44007873535156, |
| "logps/rejected": -232.92913818359375, |
| "loss": 0.7682, |
| "rewards/accuracies": 0.5073437690734863, |
| "rewards/chosen": -0.7022367119789124, |
| "rewards/margins": 0.0076367598958313465, |
| "rewards/rejected": -0.7098734974861145, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3582089552238806, |
| "grad_norm": 9.765380859375, |
| "learning_rate": 3.576653995009154e-07, |
| "logits/chosen": 0.018308693543076515, |
| "logits/rejected": 0.04190211370587349, |
| "logps/chosen": -224.4905242919922, |
| "logps/rejected": -228.26222229003906, |
| "loss": 0.7467, |
| "rewards/accuracies": 0.5228124856948853, |
| "rewards/chosen": -0.7309367656707764, |
| "rewards/margins": 0.04116936773061752, |
| "rewards/rejected": -0.7721061110496521, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2512, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
