{
  "best_global_step": 100,
  "best_metric": 0.6545524597167969,
  "best_model_checkpoint": "checkpoints/ft_jais_simdpo/dpo_run/checkpoint-100",
  "epoch": 1.5625,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.8328714728355407,
      "epoch": 0.15625,
      "grad_norm": 3.5907697677612305,
      "learning_rate": 2.25e-05,
      "logits/chosen": 0.9851744980764,
      "logits/rejected": 0.9132862824057325,
      "logps/chosen": -80.49798936843872,
      "logps/rejected": -87.13544521331787,
      "loss": 0.691208028793335,
      "mean_token_accuracy": 0.8373994886875152,
      "num_tokens": 16910.0,
      "rewards/accuracies": 0.4125,
      "rewards/chosen": 0.005871815676800907,
      "rewards/margins": 0.0046546274214051666,
      "rewards/rejected": 0.0012171887326985597,
      "step": 10
    },
    {
      "entropy": 0.8236085653305054,
      "epoch": 0.3125,
      "grad_norm": 3.045801877975464,
      "learning_rate": 4.75e-05,
      "logits/chosen": 0.9432169298637705,
      "logits/rejected": 0.9300128951388309,
      "logps/chosen": -80.01706008911133,
      "logps/rejected": -86.19765682220459,
      "loss": 0.6912835597991943,
      "mean_token_accuracy": 0.8420414581894875,
      "num_tokens": 33876.0,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": 0.046248766069766134,
      "rewards/margins": 0.0050085548544302584,
      "rewards/rejected": 0.04124021101742983,
      "step": 20
    },
    {
      "entropy": 0.8710977151989937,
      "epoch": 0.46875,
      "grad_norm": 4.131756782531738,
      "learning_rate": 4.9662976890711167e-05,
      "logits/chosen": 0.952295882064034,
      "logits/rejected": 0.8837412199420139,
      "logps/chosen": -83.00751543045044,
      "logps/rejected": -89.77082118988037,
      "loss": 0.6836707592010498,
      "mean_token_accuracy": 0.830362756550312,
      "num_tokens": 51751.0,
      "rewards/accuracies": 0.55,
      "rewards/chosen": 0.19173650545999407,
      "rewards/margins": 0.02175652077421546,
      "rewards/rejected": 0.1699799854774028,
      "step": 30
    },
    {
      "entropy": 0.8702168866991997,
      "epoch": 0.625,
      "grad_norm": 3.4390907287597656,
      "learning_rate": 4.850961997099892e-05,
      "logits/chosen": 0.9335240972164126,
      "logits/rejected": 0.8931220467287231,
      "logps/chosen": -78.64973669052124,
      "logps/rejected": -83.12959709167481,
      "loss": 0.680081558227539,
      "mean_token_accuracy": 0.8323500514030456,
      "num_tokens": 68855.0,
      "rewards/accuracies": 0.575,
      "rewards/chosen": 0.5641312405467034,
      "rewards/margins": 0.03580198623239994,
      "rewards/rejected": 0.5283292587846518,
      "step": 40
    },
    {
      "entropy": 0.8412925243377686,
      "epoch": 0.78125,
      "grad_norm": 3.696289539337158,
      "learning_rate": 4.657412981885862e-05,
      "logits/chosen": 0.9247626503111631,
      "logits/rejected": 0.9220718661915835,
      "logps/chosen": -68.65432586669922,
      "logps/rejected": -82.09786891937256,
      "loss": 0.628887414932251,
      "mean_token_accuracy": 0.8538857877254487,
      "num_tokens": 86484.0,
      "rewards/accuracies": 0.775,
      "rewards/chosen": 1.0782162077724933,
      "rewards/margins": 0.16525846347212791,
      "rewards/rejected": 0.9129577524960041,
      "step": 50
    },
    {
      "epoch": 0.78125,
      "eval_entropy": 0.8311625965710344,
      "eval_logits/chosen": 0.9525682816067235,
      "eval_logits/rejected": 0.9378524862311701,
      "eval_logps/chosen": -70.774687273749,
      "eval_logps/rejected": -77.4474421534045,
      "eval_loss": 0.663590133190155,
      "eval_mean_token_accuracy": 0.8474541881988789,
      "eval_num_tokens": 86484.0,
      "eval_rewards/accuracies": 0.6724137931034483,
      "eval_rewards/chosen": 1.197298473325269,
      "eval_rewards/margins": 0.1253269150339324,
      "eval_rewards/rejected": 1.0719715516115058,
      "eval_runtime": 3.6052,
      "eval_samples_per_second": 15.811,
      "eval_steps_per_second": 8.044,
      "step": 50
    },
    {
      "entropy": 0.9258149698376655,
      "epoch": 0.9375,
      "grad_norm": 9.48177433013916,
      "learning_rate": 4.392089757165841e-05,
      "logits/chosen": 0.9196924747627211,
      "logits/rejected": 0.9150918054479149,
      "logps/chosen": -69.63652791976929,
      "logps/rejected": -74.67644653320312,
      "loss": 0.6724472045898438,
      "mean_token_accuracy": 0.8314912617206573,
      "num_tokens": 103165.0,
      "rewards/accuracies": 0.6,
      "rewards/chosen": 1.612139716744423,
      "rewards/margins": 0.10208179727196694,
      "rewards/rejected": 1.5100578874349595,
      "step": 60
    },
    {
      "entropy": 0.9276665955781936,
      "epoch": 1.09375,
      "grad_norm": 4.742893218994141,
      "learning_rate": 4.0638192674691136e-05,
      "logits/chosen": 0.9372565226225635,
      "logits/rejected": 0.8758297012073308,
      "logps/chosen": -72.57800025939942,
      "logps/rejected": -75.22021579742432,
      "loss": 0.5596485137939453,
      "mean_token_accuracy": 0.8355538666248321,
      "num_tokens": 120923.0,
      "rewards/accuracies": 0.75,
      "rewards/chosen": 1.6647123485803603,
      "rewards/margins": 0.3873647030442953,
      "rewards/rejected": 1.2773476531729102,
      "step": 70
    },
    {
      "entropy": 0.9321356564760208,
      "epoch": 1.25,
      "grad_norm": 3.8452413082122803,
      "learning_rate": 3.683522627621608e-05,
      "logits/chosen": 0.9183959182419773,
      "logits/rejected": 0.8850714484434743,
      "logps/chosen": -73.9180368423462,
      "logps/rejected": -87.95330810546875,
      "loss": 0.4759009838104248,
      "mean_token_accuracy": 0.8352961301803589,
      "num_tokens": 138825.0,
      "rewards/accuracies": 0.8,
      "rewards/chosen": 1.2514840960502625,
      "rewards/margins": 0.6839764896780253,
      "rewards/rejected": 0.5675076065585017,
      "step": 80
    },
    {
      "entropy": 0.9279324404895306,
      "epoch": 1.40625,
      "grad_norm": 5.118920803070068,
      "learning_rate": 3.263851792039109e-05,
      "logits/chosen": 0.8924988958553159,
      "logits/rejected": 0.8284702619552127,
      "logps/chosen": -71.48162698745728,
      "logps/rejected": -83.52158260345459,
      "loss": 0.39791891574859617,
      "mean_token_accuracy": 0.8307904973626137,
      "num_tokens": 155378.0,
      "rewards/accuracies": 0.8875,
      "rewards/chosen": 1.317165607213974,
      "rewards/margins": 0.9690214801579714,
      "rewards/rejected": 0.34814412128180267,
      "step": 90
    },
    {
      "entropy": 0.9241503536701202,
      "epoch": 1.5625,
      "grad_norm": 7.398733615875244,
      "learning_rate": 2.81876864133027e-05,
      "logits/chosen": 0.9289504257072073,
      "logits/rejected": 0.9161463222864651,
      "logps/chosen": -62.29160423278809,
      "logps/rejected": -79.298428440094,
      "loss": 0.41886510848999026,
      "mean_token_accuracy": 0.8381225109100342,
      "num_tokens": 171778.0,
      "rewards/accuracies": 0.7875,
      "rewards/chosen": 1.9696232751011848,
      "rewards/margins": 1.0112529575824738,
      "rewards/rejected": 0.9583703201264143,
      "step": 100
    },
    {
      "epoch": 1.5625,
      "eval_entropy": 0.8753328939964031,
      "eval_logits/chosen": 0.980303409740094,
      "eval_logits/rejected": 0.9663606126464863,
      "eval_logps/chosen": -59.93091070240941,
      "eval_logps/rejected": -69.91863198115908,
      "eval_loss": 0.6545524597167969,
      "eval_mean_token_accuracy": 0.8393763550396623,
      "eval_num_tokens": 171778.0,
      "eval_rewards/accuracies": 0.6551724137931034,
      "eval_rewards/chosen": 2.281676158822816,
      "eval_rewards/margins": 0.45682352164696005,
      "eval_rewards/rejected": 1.8248526556738491,
      "eval_runtime": 3.6534,
      "eval_samples_per_second": 15.602,
      "eval_steps_per_second": 7.938,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.070816827686912e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}