{
  "best_metric": 0.20048503577709198,
  "best_model_checkpoint": "./mistral/20-04-24-Weni-WeniGPT-Agents-Mistral-1.0.6-SFT-1.0.8-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-20_ppid_9/checkpoint-180",
  "epoch": 5.806451612903226,
  "eval_steps": 30,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 27.100269317626953,
      "learning_rate": 5e-06,
      "logits/chosen": -1.7583906650543213,
      "logits/rejected": -1.8312015533447266,
      "logps/chosen": -173.15086364746094,
      "logps/rejected": -269.08062744140625,
      "loss": 0.69,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": 0.01006038673222065,
      "rewards/margins": 0.011446094140410423,
      "rewards/rejected": -0.0013857081066817045,
      "step": 10
    },
    {
      "epoch": 0.65,
      "grad_norm": NaN,
      "learning_rate": 4.741379310344828e-06,
      "logits/chosen": -1.7850843667984009,
      "logits/rejected": -1.81415593624115,
      "logps/chosen": -196.91897583007812,
      "logps/rejected": -205.7848663330078,
      "loss": 0.6264,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": 0.17185011506080627,
      "rewards/margins": 0.14982673525810242,
      "rewards/rejected": 0.022023344412446022,
      "step": 20
    },
    {
      "epoch": 0.97,
      "grad_norm": 23.862794876098633,
      "learning_rate": 4.454022988505747e-06,
      "logits/chosen": -1.7745271921157837,
      "logits/rejected": -1.8100026845932007,
      "logps/chosen": -197.96493530273438,
      "logps/rejected": -184.85069274902344,
      "loss": 0.5477,
      "rewards/accuracies": 0.75,
      "rewards/chosen": 0.3463248908519745,
      "rewards/margins": 0.35388293862342834,
      "rewards/rejected": -0.007558024022728205,
      "step": 30
    },
    {
      "epoch": 0.97,
      "eval_logits/chosen": -1.7948826551437378,
      "eval_logits/rejected": -1.8862664699554443,
      "eval_logps/chosen": -107.27352142333984,
      "eval_logps/rejected": -269.4668273925781,
      "eval_loss": 0.48426297307014465,
      "eval_rewards/accuracies": 0.8571428656578064,
      "eval_rewards/chosen": 0.4718170166015625,
      "eval_rewards/margins": 0.5826946496963501,
      "eval_rewards/rejected": -0.1108776405453682,
      "eval_runtime": 9.9214,
      "eval_samples_per_second": 2.822,
      "eval_steps_per_second": 0.706,
      "step": 30
    },
    {
      "epoch": 1.29,
      "grad_norm": 33.898590087890625,
      "learning_rate": 4.166666666666667e-06,
      "logits/chosen": -1.7890510559082031,
      "logits/rejected": -1.8475368022918701,
      "logps/chosen": -193.50033569335938,
      "logps/rejected": -206.31741333007812,
      "loss": 0.4661,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": 0.4587056636810303,
      "rewards/margins": 0.5034217238426208,
      "rewards/rejected": -0.04471604526042938,
      "step": 40
    },
    {
      "epoch": 1.61,
      "grad_norm": 29.36012840270996,
      "learning_rate": 3.8793103448275865e-06,
      "logits/chosen": -1.804456353187561,
      "logits/rejected": -1.8586517572402954,
      "logps/chosen": -136.4575958251953,
      "logps/rejected": -212.65231323242188,
      "loss": 0.4418,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.8421177864074707,
      "rewards/margins": 0.988998293876648,
      "rewards/rejected": -0.146880641579628,
      "step": 50
    },
    {
      "epoch": 1.94,
      "grad_norm": 25.15074348449707,
      "learning_rate": 3.5919540229885056e-06,
      "logits/chosen": -1.8009055852890015,
      "logits/rejected": -1.8550602197647095,
      "logps/chosen": -145.14044189453125,
      "logps/rejected": -265.5760192871094,
      "loss": 0.3542,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.742743730545044,
      "rewards/margins": 1.1478015184402466,
      "rewards/rejected": -0.4050576686859131,
      "step": 60
    },
    {
      "epoch": 1.94,
      "eval_logits/chosen": -1.7979233264923096,
      "eval_logits/rejected": -1.8902829885482788,
      "eval_logps/chosen": -105.64314270019531,
      "eval_logps/rejected": -269.93597412109375,
      "eval_loss": 0.344027042388916,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 0.96092689037323,
      "eval_rewards/margins": 1.212537407875061,
      "eval_rewards/rejected": -0.2516104578971863,
      "eval_runtime": 9.9306,
      "eval_samples_per_second": 2.82,
      "eval_steps_per_second": 0.705,
      "step": 60
    },
    {
      "epoch": 2.26,
      "grad_norm": 16.264854431152344,
      "learning_rate": 3.3045977011494256e-06,
      "logits/chosen": -1.8283793926239014,
      "logits/rejected": -1.8581088781356812,
      "logps/chosen": -245.49520874023438,
      "logps/rejected": -240.85055541992188,
      "loss": 0.3242,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": 0.9433773756027222,
      "rewards/margins": 0.9048371315002441,
      "rewards/rejected": 0.0385403148829937,
      "step": 70
    },
    {
      "epoch": 2.58,
      "grad_norm": 18.855249404907227,
      "learning_rate": 3.017241379310345e-06,
      "logits/chosen": -1.912719964981079,
      "logits/rejected": -1.9267578125,
      "logps/chosen": -184.6862030029297,
      "logps/rejected": -150.09349060058594,
      "loss": 0.3063,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 0.9958856701850891,
      "rewards/margins": 1.2241456508636475,
      "rewards/rejected": -0.2282601296901703,
      "step": 80
    },
    {
      "epoch": 2.9,
      "grad_norm": 18.644786834716797,
      "learning_rate": 2.729885057471265e-06,
      "logits/chosen": -1.8041893243789673,
      "logits/rejected": -1.8382984399795532,
      "logps/chosen": -122.60682678222656,
      "logps/rejected": -190.001220703125,
      "loss": 0.2892,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 1.1825361251831055,
      "rewards/margins": 1.4003632068634033,
      "rewards/rejected": -0.2178269922733307,
      "step": 90
    },
    {
      "epoch": 2.9,
      "eval_logits/chosen": -1.799451470375061,
      "eval_logits/rejected": -1.8927640914916992,
      "eval_logps/chosen": -104.44667053222656,
      "eval_logps/rejected": -270.4913635253906,
      "eval_loss": 0.275594562292099,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.319871187210083,
      "eval_rewards/margins": 1.7381019592285156,
      "eval_rewards/rejected": -0.4182307720184326,
      "eval_runtime": 9.9268,
      "eval_samples_per_second": 2.821,
      "eval_steps_per_second": 0.705,
      "step": 90
    },
    {
      "epoch": 3.23,
      "grad_norm": 12.1031494140625,
      "learning_rate": 2.4425287356321844e-06,
      "logits/chosen": -1.775871992111206,
      "logits/rejected": -1.8304792642593384,
      "logps/chosen": -152.18081665039062,
      "logps/rejected": -200.20614624023438,
      "loss": 0.2436,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.6016706228256226,
      "rewards/margins": 1.9426767826080322,
      "rewards/rejected": -0.3410060703754425,
      "step": 100
    },
    {
      "epoch": 3.55,
      "grad_norm": 15.167205810546875,
      "learning_rate": 2.1551724137931035e-06,
      "logits/chosen": -1.7159019708633423,
      "logits/rejected": -1.8178460597991943,
      "logps/chosen": -141.62574768066406,
      "logps/rejected": -293.3615417480469,
      "loss": 0.2007,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7044894695281982,
      "rewards/margins": 2.599806308746338,
      "rewards/rejected": -0.8953168988227844,
      "step": 110
    },
    {
      "epoch": 3.87,
      "grad_norm": 15.17064094543457,
      "learning_rate": 1.8678160919540231e-06,
      "logits/chosen": -1.8141412734985352,
      "logits/rejected": -1.881119728088379,
      "logps/chosen": -113.6499252319336,
      "logps/rejected": -246.5932159423828,
      "loss": 0.1858,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 1.5452262163162231,
      "rewards/margins": 2.416726589202881,
      "rewards/rejected": -0.8715003728866577,
      "step": 120
    },
    {
      "epoch": 3.87,
      "eval_logits/chosen": -1.8007782697677612,
      "eval_logits/rejected": -1.8947203159332275,
      "eval_logps/chosen": -103.50943756103516,
      "eval_logps/rejected": -270.995849609375,
      "eval_loss": 0.232688769698143,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.60104238986969,
      "eval_rewards/margins": 2.170628309249878,
      "eval_rewards/rejected": -0.5695859789848328,
      "eval_runtime": 9.9278,
      "eval_samples_per_second": 2.82,
      "eval_steps_per_second": 0.705,
      "step": 120
    },
    {
      "epoch": 4.19,
      "grad_norm": 9.949838638305664,
      "learning_rate": 1.5804597701149427e-06,
      "logits/chosen": -1.7835006713867188,
      "logits/rejected": -1.8571557998657227,
      "logps/chosen": -184.62295532226562,
      "logps/rejected": -249.9383544921875,
      "loss": 0.2255,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7701829671859741,
      "rewards/margins": 2.433096408843994,
      "rewards/rejected": -0.6629135012626648,
      "step": 130
    },
    {
      "epoch": 4.52,
      "grad_norm": 10.975859642028809,
      "learning_rate": 1.2931034482758623e-06,
      "logits/chosen": -1.8018295764923096,
      "logits/rejected": -1.861405372619629,
      "logps/chosen": -129.60470581054688,
      "logps/rejected": -241.1371612548828,
      "loss": 0.1645,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7705247402191162,
      "rewards/margins": 2.5183393955230713,
      "rewards/rejected": -0.7478145956993103,
      "step": 140
    },
    {
      "epoch": 4.84,
      "grad_norm": 12.812362670898438,
      "learning_rate": 1.0057471264367817e-06,
      "logits/chosen": -1.82421875,
      "logits/rejected": -1.8583450317382812,
      "logps/chosen": -201.688232421875,
      "logps/rejected": -229.2138671875,
      "loss": 0.1811,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.555559515953064,
      "rewards/margins": 2.371445417404175,
      "rewards/rejected": -0.8158857226371765,
      "step": 150
    },
    {
      "epoch": 4.84,
      "eval_logits/chosen": -1.8010179996490479,
      "eval_logits/rejected": -1.8953866958618164,
      "eval_logps/chosen": -103.09788513183594,
      "eval_logps/rejected": -271.4054260253906,
      "eval_loss": 0.2075897753238678,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.7245090007781982,
      "eval_rewards/margins": 2.4169600009918213,
      "eval_rewards/rejected": -0.6924509406089783,
      "eval_runtime": 9.9225,
      "eval_samples_per_second": 2.822,
      "eval_steps_per_second": 0.705,
      "step": 150
    },
    {
      "epoch": 5.16,
      "grad_norm": 23.902271270751953,
      "learning_rate": 7.183908045977011e-07,
      "logits/chosen": -1.779550313949585,
      "logits/rejected": -1.8266932964324951,
      "logps/chosen": -145.10794067382812,
      "logps/rejected": -194.99497985839844,
      "loss": 0.182,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.5958274602890015,
      "rewards/margins": 2.0814337730407715,
      "rewards/rejected": -0.48560643196105957,
      "step": 160
    },
    {
      "epoch": 5.48,
      "grad_norm": 25.761934280395508,
      "learning_rate": 4.3103448275862073e-07,
      "logits/chosen": -1.8421766757965088,
      "logits/rejected": -1.8947057723999023,
      "logps/chosen": -162.1377716064453,
      "logps/rejected": -238.0432586669922,
      "loss": 0.1725,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.420178771018982,
      "rewards/margins": 2.578826427459717,
      "rewards/rejected": -1.1586474180221558,
      "step": 170
    },
    {
      "epoch": 5.81,
      "grad_norm": 22.726856231689453,
      "learning_rate": 1.4367816091954023e-07,
      "logits/chosen": -1.8062843084335327,
      "logits/rejected": -1.8762874603271484,
      "logps/chosen": -147.4128875732422,
      "logps/rejected": -218.22811889648438,
      "loss": 0.2065,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 1.3966058492660522,
      "rewards/margins": 2.1112942695617676,
      "rewards/rejected": -0.7146884202957153,
      "step": 180
    },
    {
      "epoch": 5.81,
      "eval_logits/chosen": -1.8012962341308594,
      "eval_logits/rejected": -1.8957865238189697,
      "eval_logps/chosen": -102.97270202636719,
      "eval_logps/rejected": -271.5132751464844,
      "eval_loss": 0.20048503577709198,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.7620631456375122,
      "eval_rewards/margins": 2.4868807792663574,
      "eval_rewards/rejected": -0.7248173952102661,
      "eval_runtime": 9.9214,
      "eval_samples_per_second": 2.822,
      "eval_steps_per_second": 0.706,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 90,
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}