checkpoint-200/trainer_state.json

{
  "best_metric": 0.0047710007056593895,
  "best_model_checkpoint": "./Zephyr/28-03-24-Weni-WeniGPT-QA-Zephyr-7B-4.0.1-KTO_WeniGPT Experiment using KTO trainer with no collator, Zephyr model and no system prompt.-2_max_steps-786_batch_32_2024-03-28_ppid_9/checkpoint-200",
  "epoch": 1.5122873345935728,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "grad_norm": 1.94673752784729,
      "kl": 0.3060356676578522,
      "learning_rate": 0.0001666666666666667,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 1.0194,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.799897313117981,
      "kl": 0.08012839406728745,
      "learning_rate": 0.00019580052493438322,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.204,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 40
    },
    {
      "epoch": 0.38,
      "eval_kl": 0.0,
      "eval_logps/chosen": -120.33751678466797,
      "eval_logps/rejected": -405.6329345703125,
      "eval_loss": 0.02746938355267048,
      "eval_rewards/chosen": 5.632839202880859,
      "eval_rewards/margins": 25.979337692260742,
      "eval_rewards/rejected": -20.346500396728516,
      "eval_runtime": 215.3361,
      "eval_samples_per_second": 2.322,
      "eval_steps_per_second": 0.58,
      "step": 50
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1745920479297638,
      "kl": 0.20441873371601105,
      "learning_rate": 0.0001905511811023622,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0962,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 60
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.8645330667495728,
      "kl": 0.0,
      "learning_rate": 0.00018556430446194227,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0881,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 80
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.13575485348701477,
      "kl": 0.0,
      "learning_rate": 0.00018031496062992125,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.073,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 100
    },
    {
      "epoch": 0.76,
      "eval_kl": 0.0,
      "eval_logps/chosen": -118.76765441894531,
      "eval_logps/rejected": -394.83203125,
      "eval_loss": 0.014343788847327232,
      "eval_rewards/chosen": 5.789826393127441,
      "eval_rewards/margins": 25.05623435974121,
      "eval_rewards/rejected": -19.266408920288086,
      "eval_runtime": 215.2593,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 100
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.04445016011595726,
      "kl": 0.25088077783584595,
      "learning_rate": 0.0001750656167979003,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0312,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 120
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.08600552380084991,
      "kl": 0.0,
      "learning_rate": 0.00016981627296587927,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0553,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 140
    },
    {
      "epoch": 1.13,
      "eval_kl": 0.0,
      "eval_logps/chosen": -118.54534149169922,
      "eval_logps/rejected": -501.9826354980469,
      "eval_loss": 0.022491294890642166,
      "eval_rewards/chosen": 5.812057018280029,
      "eval_rewards/margins": 35.79352569580078,
      "eval_rewards/rejected": -29.981468200683594,
      "eval_runtime": 215.2877,
      "eval_samples_per_second": 2.322,
      "eval_steps_per_second": 0.581,
      "step": 150
    },
    {
      "epoch": 1.21,
      "grad_norm": 1.7538838386535645,
      "kl": 0.08890169113874435,
      "learning_rate": 0.00016456692913385828,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0322,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 160
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.1595699042081833,
      "kl": 0.0,
      "learning_rate": 0.00015931758530183726,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0108,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 180
    },
    {
      "epoch": 1.51,
      "grad_norm": 1.2758983373641968,
      "kl": 0.011286890134215355,
      "learning_rate": 0.0001540682414698163,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0232,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 200
    },
    {
      "epoch": 1.51,
      "eval_kl": 0.0,
      "eval_logps/chosen": -112.15116882324219,
      "eval_logps/rejected": -478.0784912109375,
      "eval_loss": 0.0047710007056593895,
      "eval_rewards/chosen": 6.451474189758301,
      "eval_rewards/margins": 34.04253005981445,
      "eval_rewards/rejected": -27.591054916381836,
      "eval_runtime": 215.2869,
      "eval_samples_per_second": 2.322,
      "eval_steps_per_second": 0.581,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 786,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}