{
  "best_metric": 0.1095743179321289,
  "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-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": 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
    }
  ],
  "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
}