{
  "best_metric": 0.052017249166965485,
  "best_model_checkpoint": "./mistral/22-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.21-DPO_Experiment on DPO with other hyperparameters and best SFT model of WeniGPT-2_max_steps-180_batch_8_2024-04-22_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": 0.3225806451612903,
      "grad_norm": 13.277989387512207,
      "learning_rate": 4.971264367816092e-06,
      "logits/chosen": -1.7891426086425781,
      "logits/rejected": -1.814126968383789,
      "logps/chosen": -200.95481872558594,
      "logps/rejected": -223.9504852294922,
      "loss": 0.6771,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": 0.02733452059328556,
      "rewards/margins": 0.028555069118738174,
      "rewards/rejected": -0.0012205507373437285,
      "step": 10
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 11.217987060546875,
      "learning_rate": 4.683908045977012e-06,
      "logits/chosen": -1.8347755670547485,
      "logits/rejected": -1.8467401266098022,
      "logps/chosen": -144.74403381347656,
      "logps/rejected": -191.45069885253906,
      "loss": 0.5478,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 0.37081974744796753,
      "rewards/margins": 0.4048076272010803,
      "rewards/rejected": -0.03398784250020981,
      "step": 20
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 11.224645614624023,
      "learning_rate": 4.396551724137931e-06,
      "logits/chosen": -1.785586953163147,
      "logits/rejected": -1.8152267932891846,
      "logps/chosen": -190.48626708984375,
      "logps/rejected": -248.2376251220703,
      "loss": 0.3976,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.7104076147079468,
      "rewards/margins": 0.848293662071228,
      "rewards/rejected": -0.13788609206676483,
      "step": 30
    },
    {
      "epoch": 0.967741935483871,
      "eval_logits/chosen": -1.7412782907485962,
      "eval_logits/rejected": -1.7560926675796509,
      "eval_logps/chosen": -115.03002166748047,
      "eval_logps/rejected": -160.6632080078125,
      "eval_loss": 0.3185553252696991,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 0.8372641801834106,
      "eval_rewards/margins": 0.8753501176834106,
      "eval_rewards/rejected": -0.038085997104644775,
      "eval_runtime": 10.5823,
      "eval_samples_per_second": 2.646,
      "eval_steps_per_second": 0.661,
      "step": 30
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 5.652975082397461,
      "learning_rate": 4.1091954022988515e-06,
      "logits/chosen": -1.7882213592529297,
      "logits/rejected": -1.7954260110855103,
      "logps/chosen": -159.75631713867188,
      "logps/rejected": -182.1666717529297,
      "loss": 0.2432,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": 1.2001782655715942,
      "rewards/margins": 1.2467749118804932,
      "rewards/rejected": -0.04659665375947952,
      "step": 40
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 3.635425090789795,
      "learning_rate": 3.82183908045977e-06,
      "logits/chosen": -1.8176883459091187,
      "logits/rejected": -1.8400278091430664,
      "logps/chosen": -114.22891998291016,
      "logps/rejected": -197.11019897460938,
      "loss": 0.242,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 1.5082905292510986,
      "rewards/margins": 2.3228204250335693,
      "rewards/rejected": -0.8145298957824707,
      "step": 50
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 5.051187038421631,
      "learning_rate": 3.5344827586206898e-06,
      "logits/chosen": -1.769321084022522,
      "logits/rejected": -1.7883247137069702,
      "logps/chosen": -149.78382873535156,
      "logps/rejected": -172.86285400390625,
      "loss": 0.1934,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": 1.4219303131103516,
      "rewards/margins": 1.7929319143295288,
      "rewards/rejected": -0.3710017502307892,
      "step": 60
    },
    {
      "epoch": 1.935483870967742,
      "eval_logits/chosen": -1.745606541633606,
      "eval_logits/rejected": -1.7603371143341064,
      "eval_logps/chosen": -110.98043060302734,
      "eval_logps/rejected": -163.220703125,
      "eval_loss": 0.17523464560508728,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.6471832990646362,
      "eval_rewards/margins": 2.1967694759368896,
      "eval_rewards/rejected": -0.5495859384536743,
      "eval_runtime": 10.5122,
      "eval_samples_per_second": 2.664,
      "eval_steps_per_second": 0.666,
      "step": 60
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 5.4414238929748535,
      "learning_rate": 3.24712643678161e-06,
      "logits/chosen": -1.761417031288147,
      "logits/rejected": -1.7780914306640625,
      "logps/chosen": -153.3155059814453,
      "logps/rejected": -175.71119689941406,
      "loss": 0.1552,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.9575698375701904,
      "rewards/margins": 2.617478847503662,
      "rewards/rejected": -0.6599088907241821,
      "step": 70
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 3.4745564460754395,
      "learning_rate": 2.988505747126437e-06,
      "logits/chosen": -1.8878180980682373,
      "logits/rejected": -1.895895004272461,
      "logps/chosen": -148.46951293945312,
      "logps/rejected": -211.92874145507812,
      "loss": 0.157,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 1.930851697921753,
      "rewards/margins": 2.822469711303711,
      "rewards/rejected": -0.8916179537773132,
      "step": 80
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 4.5158843994140625,
      "learning_rate": 2.7011494252873567e-06,
      "logits/chosen": -1.8586393594741821,
      "logits/rejected": -1.8672926425933838,
      "logps/chosen": -166.34080505371094,
      "logps/rejected": -204.51248168945312,
      "loss": 0.1058,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.207078695297241,
      "rewards/margins": 3.182745933532715,
      "rewards/rejected": -0.9756671190261841,
      "step": 90
    },
    {
      "epoch": 2.903225806451613,
      "eval_logits/chosen": -1.7490978240966797,
      "eval_logits/rejected": -1.7636711597442627,
      "eval_logps/chosen": -109.27593231201172,
      "eval_logps/rejected": -164.40065002441406,
      "eval_loss": 0.1095743179321289,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.9880834817886353,
      "eval_rewards/margins": 2.77366042137146,
      "eval_rewards/rejected": -0.7855769991874695,
      "eval_runtime": 10.5091,
      "eval_samples_per_second": 2.664,
      "eval_steps_per_second": 0.666,
      "step": 90
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 7.920010089874268,
      "learning_rate": 2.4137931034482762e-06,
      "logits/chosen": -1.8129634857177734,
      "logits/rejected": -1.8248703479766846,
      "logps/chosen": -188.29046630859375,
      "logps/rejected": -166.93959045410156,
      "loss": 0.0846,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.0221571922302246,
      "rewards/margins": 2.638063669204712,
      "rewards/rejected": -0.6159064769744873,
      "step": 100
    },
    {
      "epoch": 3.5483870967741935,
      "grad_norm": 2.062326192855835,
      "learning_rate": 2.1264367816091954e-06,
      "logits/chosen": -1.780647873878479,
      "logits/rejected": -1.8003911972045898,
      "logps/chosen": -181.70352172851562,
      "logps/rejected": -211.6031036376953,
      "loss": 0.0915,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.376112937927246,
      "rewards/margins": 3.2865447998046875,
      "rewards/rejected": -0.9104318618774414,
      "step": 110
    },
    {
      "epoch": 3.870967741935484,
      "grad_norm": 2.184727668762207,
      "learning_rate": 1.839080459770115e-06,
      "logits/chosen": -1.84122633934021,
      "logits/rejected": -1.8630201816558838,
      "logps/chosen": -110.26792907714844,
      "logps/rejected": -188.52102661132812,
      "loss": 0.0527,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.7806448936462402,
      "rewards/margins": 4.270835876464844,
      "rewards/rejected": -1.4901912212371826,
      "step": 120
    },
    {
      "epoch": 3.870967741935484,
      "eval_logits/chosen": -1.7532367706298828,
      "eval_logits/rejected": -1.767619013786316,
      "eval_logps/chosen": -108.33710479736328,
      "eval_logps/rejected": -165.59573364257812,
      "eval_loss": 0.07865254580974579,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 2.175847291946411,
      "eval_rewards/margins": 3.2004382610321045,
      "eval_rewards/rejected": -1.0245908498764038,
      "eval_runtime": 10.5128,
      "eval_samples_per_second": 2.663,
      "eval_steps_per_second": 0.666,
      "step": 120
    },
    {
      "epoch": 4.193548387096774,
      "grad_norm": 3.8901867866516113,
      "learning_rate": 1.5517241379310346e-06,
      "logits/chosen": -1.80022394657135,
      "logits/rejected": -1.8180515766143799,
      "logps/chosen": -133.0179901123047,
      "logps/rejected": -267.961181640625,
      "loss": 0.0702,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7386133670806885,
      "rewards/margins": 3.7656383514404297,
      "rewards/rejected": -2.0270252227783203,
      "step": 130
    },
    {
      "epoch": 4.516129032258064,
      "grad_norm": 0.9774993062019348,
      "learning_rate": 1.2643678160919542e-06,
      "logits/chosen": -1.770490050315857,
      "logits/rejected": -1.7988364696502686,
      "logps/chosen": -134.59291076660156,
      "logps/rejected": -227.28573608398438,
      "loss": 0.0389,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.5844013690948486,
      "rewards/margins": 4.34262752532959,
      "rewards/rejected": -1.7582266330718994,
      "step": 140
    },
    {
      "epoch": 4.838709677419355,
      "grad_norm": 2.1318492889404297,
      "learning_rate": 9.770114942528738e-07,
      "logits/chosen": -1.846001386642456,
      "logits/rejected": -1.853493332862854,
      "logps/chosen": -118.50834655761719,
      "logps/rejected": -196.01217651367188,
      "loss": 0.0526,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.303821086883545,
      "rewards/margins": 3.837214231491089,
      "rewards/rejected": -1.5333930253982544,
      "step": 150
    },
    {
      "epoch": 4.838709677419355,
      "eval_logits/chosen": -1.7548978328704834,
      "eval_logits/rejected": -1.7693225145339966,
      "eval_logps/chosen": -107.8351058959961,
      "eval_logps/rejected": -167.27781677246094,
      "eval_loss": 0.05771544948220253,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 2.2762484550476074,
      "eval_rewards/margins": 3.6372554302215576,
      "eval_rewards/rejected": -1.3610070943832397,
      "eval_runtime": 10.508,
      "eval_samples_per_second": 2.665,
      "eval_steps_per_second": 0.666,
      "step": 150
    },
    {
      "epoch": 5.161290322580645,
      "grad_norm": 1.8219561576843262,
      "learning_rate": 6.896551724137931e-07,
      "logits/chosen": -1.8211644887924194,
      "logits/rejected": -1.8465015888214111,
      "logps/chosen": -104.08028411865234,
      "logps/rejected": -210.0991973876953,
      "loss": 0.0613,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.1849822998046875,
      "rewards/margins": 4.971571922302246,
      "rewards/rejected": -1.7865898609161377,
      "step": 160
    },
    {
      "epoch": 5.483870967741936,
      "grad_norm": 1.121188998222351,
      "learning_rate": 4.0229885057471266e-07,
      "logits/chosen": -1.8207435607910156,
      "logits/rejected": -1.8367401361465454,
      "logps/chosen": -167.99905395507812,
      "logps/rejected": -210.1734161376953,
      "loss": 0.0339,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.480262517929077,
      "rewards/margins": 4.021227836608887,
      "rewards/rejected": -1.5409656763076782,
      "step": 170
    },
    {
      "epoch": 5.806451612903226,
      "grad_norm": 1.1327688694000244,
      "learning_rate": 1.1494252873563219e-07,
      "logits/chosen": -1.875394582748413,
      "logits/rejected": -1.887101411819458,
      "logps/chosen": -181.40708923339844,
      "logps/rejected": -255.3656463623047,
      "loss": 0.0529,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 2.5407514572143555,
      "rewards/margins": 5.552119731903076,
      "rewards/rejected": -3.0113682746887207,
      "step": 180
    },
    {
      "epoch": 5.806451612903226,
      "eval_logits/chosen": -1.7573397159576416,
      "eval_logits/rejected": -1.7717255353927612,
      "eval_logps/chosen": -107.60765075683594,
      "eval_logps/rejected": -167.99813842773438,
      "eval_loss": 0.052017249166965485,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 2.3217406272888184,
      "eval_rewards/margins": 3.8268144130706787,
      "eval_rewards/rejected": -1.5050735473632812,
      "eval_runtime": 10.5205,
      "eval_samples_per_second": 2.661,
      "eval_steps_per_second": 0.665,
      "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
}