{
  "best_metric": 0.05446601286530495,
  "best_model_checkpoint": "./mistral/22-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT-1.0.25-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-90",
  "epoch": 2.903225806451613,
  "eval_steps": 30,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 24.6901912689209,
      "learning_rate": 5e-06,
      "logits/chosen": -1.8365566730499268,
      "logits/rejected": -1.8444175720214844,
      "logps/chosen": -195.56666564941406,
      "logps/rejected": -191.41812133789062,
      "loss": 0.653,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": 0.09110366553068161,
      "rewards/margins": 0.10920021682977676,
      "rewards/rejected": -0.018096545711159706,
      "step": 10
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 13.191404342651367,
      "learning_rate": 4.71264367816092e-06,
      "logits/chosen": -1.7314943075180054,
      "logits/rejected": -1.766556978225708,
      "logps/chosen": -137.64279174804688,
      "logps/rejected": -220.5197296142578,
      "loss": 0.3701,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 1.1793702840805054,
      "rewards/margins": 1.4335505962371826,
      "rewards/rejected": -0.2541801631450653,
      "step": 20
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 20.181856155395508,
      "learning_rate": 4.42528735632184e-06,
      "logits/chosen": -1.8526036739349365,
      "logits/rejected": -1.86077880859375,
      "logps/chosen": -121.78877258300781,
      "logps/rejected": -151.2501678466797,
      "loss": 0.225,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.4271174669265747,
      "rewards/margins": 1.875509262084961,
      "rewards/rejected": -0.4483918249607086,
      "step": 30
    },
    {
      "epoch": 0.967741935483871,
      "eval_logits/chosen": -1.9326385259628296,
      "eval_logits/rejected": -1.9565868377685547,
      "eval_logps/chosen": -123.71134185791016,
      "eval_logps/rejected": -215.0025634765625,
      "eval_loss": 0.22270560264587402,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 2.6680667400360107,
      "eval_rewards/margins": 3.676541566848755,
      "eval_rewards/rejected": -1.008474588394165,
      "eval_runtime": 15.7165,
      "eval_samples_per_second": 1.782,
      "eval_steps_per_second": 0.445,
      "step": 30
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 1.0404773950576782,
      "learning_rate": 4.137931034482759e-06,
      "logits/chosen": -1.9101307392120361,
      "logits/rejected": -1.9370834827423096,
      "logps/chosen": -146.01133728027344,
      "logps/rejected": -237.4972686767578,
      "loss": 0.0848,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.0706539154052734,
      "rewards/margins": 5.080114364624023,
      "rewards/rejected": -2.009460926055908,
      "step": 40
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 17.344457626342773,
      "learning_rate": 3.850574712643678e-06,
      "logits/chosen": -1.8972657918930054,
      "logits/rejected": -1.9069604873657227,
      "logps/chosen": -195.85150146484375,
      "logps/rejected": -158.05677795410156,
      "loss": 0.0755,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 3.0010573863983154,
      "rewards/margins": 4.110104560852051,
      "rewards/rejected": -1.1090469360351562,
      "step": 50
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 0.7190752029418945,
      "learning_rate": 3.563218390804598e-06,
      "logits/chosen": -1.8297414779663086,
      "logits/rejected": -1.857456922531128,
      "logps/chosen": -144.957275390625,
      "logps/rejected": -232.25784301757812,
      "loss": 0.0853,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 3.4944889545440674,
      "rewards/margins": 5.610640525817871,
      "rewards/rejected": -2.116152286529541,
      "step": 60
    },
    {
      "epoch": 1.935483870967742,
      "eval_logits/chosen": -1.9170362949371338,
      "eval_logits/rejected": -1.9400348663330078,
      "eval_logps/chosen": -118.40864562988281,
      "eval_logps/rejected": -221.06422424316406,
      "eval_loss": 0.10952840745449066,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 3.7286033630371094,
      "eval_rewards/margins": 5.949405193328857,
      "eval_rewards/rejected": -2.220801830291748,
      "eval_runtime": 15.4022,
      "eval_samples_per_second": 1.818,
      "eval_steps_per_second": 0.454,
      "step": 60
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 6.895229339599609,
      "learning_rate": 3.2758620689655175e-06,
      "logits/chosen": -1.7604904174804688,
      "logits/rejected": -1.7763350009918213,
      "logps/chosen": -94.25442504882812,
      "logps/rejected": -200.06292724609375,
      "loss": 0.0336,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 3.892274856567383,
      "rewards/margins": 7.140706539154053,
      "rewards/rejected": -3.248431444168091,
      "step": 70
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 3.1107871532440186,
      "learning_rate": 2.988505747126437e-06,
      "logits/chosen": -1.773847222328186,
      "logits/rejected": -1.7859563827514648,
      "logps/chosen": -134.7067108154297,
      "logps/rejected": -175.28102111816406,
      "loss": 0.0191,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 3.6734061241149902,
      "rewards/margins": 6.411807060241699,
      "rewards/rejected": -2.738400936126709,
      "step": 80
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 0.4654656946659088,
      "learning_rate": 2.7011494252873567e-06,
      "logits/chosen": -1.8632606267929077,
      "logits/rejected": -1.8870786428451538,
      "logps/chosen": -152.00164794921875,
      "logps/rejected": -194.2272186279297,
      "loss": 0.0285,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": 3.7533652782440186,
      "rewards/margins": 6.942251682281494,
      "rewards/rejected": -3.1888861656188965,
      "step": 90
    },
    {
      "epoch": 2.903225806451613,
      "eval_logits/chosen": -1.9063053131103516,
      "eval_logits/rejected": -1.930100679397583,
      "eval_logps/chosen": -116.32177734375,
      "eval_logps/rejected": -229.86549377441406,
      "eval_loss": 0.05446601286530495,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 4.145977973937988,
      "eval_rewards/margins": 8.12703800201416,
      "eval_rewards/rejected": -3.9810593128204346,
      "eval_runtime": 15.401,
      "eval_samples_per_second": 1.818,
      "eval_steps_per_second": 0.455,
      "step": 90
    }
  ],
  "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
}