{
  "best_metric": 0.003762652399018407,
  "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-400",
  "epoch": 4.536862003780718,
  "eval_steps": 50,
  "global_step": 600,
  "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
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.04578682407736778,
      "kl": 0.08650239557027817,
      "learning_rate": 0.00014881889763779528,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0095,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 220
    },
    {
      "epoch": 1.81,
      "grad_norm": 4.036252498626709,
      "kl": 0.0,
      "learning_rate": 0.0001435695538057743,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0519,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 240
    },
    {
      "epoch": 1.89,
      "eval_kl": 0.0,
      "eval_logps/chosen": -111.8521728515625,
      "eval_logps/rejected": -507.0782470703125,
      "eval_loss": 0.008064903318881989,
      "eval_rewards/chosen": 6.481375217437744,
      "eval_rewards/margins": 36.97240447998047,
      "eval_rewards/rejected": -30.491031646728516,
      "eval_runtime": 215.2836,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 250
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.027836302295327187,
      "kl": 0.10306696593761444,
      "learning_rate": 0.00013832020997375327,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0103,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 260
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.5005787014961243,
      "kl": 0.0,
      "learning_rate": 0.0001330708661417323,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0185,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 280
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.010965784080326557,
      "kl": 0.008135443553328514,
      "learning_rate": 0.0001278215223097113,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0095,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 300
    },
    {
      "epoch": 2.27,
      "eval_kl": 0.0,
      "eval_logps/chosen": -112.58515930175781,
      "eval_logps/rejected": -541.0062866210938,
      "eval_loss": 0.0153852179646492,
      "eval_rewards/chosen": 6.408076286315918,
      "eval_rewards/margins": 40.29190444946289,
      "eval_rewards/rejected": -33.88383102416992,
      "eval_runtime": 215.4103,
      "eval_samples_per_second": 2.321,
      "eval_steps_per_second": 0.58,
      "step": 300
    },
    {
      "epoch": 2.42,
      "grad_norm": 0.03853553906083107,
      "kl": 0.09816194325685501,
      "learning_rate": 0.0001225721784776903,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0074,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 320
    },
    {
      "epoch": 2.57,
      "grad_norm": 0.019064167514443398,
      "kl": 0.0,
      "learning_rate": 0.00011732283464566928,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0098,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 340
    },
    {
      "epoch": 2.65,
      "eval_kl": 0.0,
      "eval_logps/chosen": -110.7034683227539,
      "eval_logps/rejected": -614.9013671875,
      "eval_loss": 0.005230295471847057,
      "eval_rewards/chosen": 6.596245288848877,
      "eval_rewards/margins": 47.869590759277344,
      "eval_rewards/rejected": -41.27334213256836,
      "eval_runtime": 215.26,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 350
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.011980261653661728,
      "kl": 0.0,
      "learning_rate": 0.0001120734908136483,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0147,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 360
    },
    {
      "epoch": 2.87,
      "grad_norm": 0.02171475999057293,
      "kl": 0.0,
      "learning_rate": 0.0001068241469816273,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0066,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 380
    },
    {
      "epoch": 3.02,
      "grad_norm": 0.013751395046710968,
      "kl": 0.0,
      "learning_rate": 0.0001015748031496063,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0038,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 400
    },
    {
      "epoch": 3.02,
      "eval_kl": 0.0,
      "eval_logps/chosen": -111.44074249267578,
      "eval_logps/rejected": -539.215576171875,
      "eval_loss": 0.003762652399018407,
      "eval_rewards/chosen": 6.522518157958984,
      "eval_rewards/margins": 40.22727966308594,
      "eval_rewards/rejected": -33.70476531982422,
      "eval_runtime": 215.2203,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 400
    },
    {
      "epoch": 3.18,
      "grad_norm": 0.01895367167890072,
      "kl": 0.11727146804332733,
      "learning_rate": 9.63254593175853e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.003,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 420
    },
    {
      "epoch": 3.33,
      "grad_norm": 0.024156125262379646,
      "kl": 0.0,
      "learning_rate": 9.10761154855643e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0068,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 440
    },
    {
      "epoch": 3.4,
      "eval_kl": 0.0,
      "eval_logps/chosen": -113.2169418334961,
      "eval_logps/rejected": -635.6953735351562,
      "eval_loss": 0.007997407577931881,
      "eval_rewards/chosen": 6.34489631652832,
      "eval_rewards/margins": 49.6976432800293,
      "eval_rewards/rejected": -43.35274887084961,
      "eval_runtime": 215.2157,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 450
    },
    {
      "epoch": 3.48,
      "grad_norm": 0.011542567051947117,
      "kl": 0.0,
      "learning_rate": 8.582677165354331e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0049,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 460
    },
    {
      "epoch": 3.63,
      "grad_norm": 0.004607899580150843,
      "kl": 0.0,
      "learning_rate": 8.05774278215223e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0044,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 480
    },
    {
      "epoch": 3.78,
      "grad_norm": 0.01574736088514328,
      "kl": 0.0,
      "learning_rate": 7.532808398950132e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0037,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 500
    },
    {
      "epoch": 3.78,
      "eval_kl": 0.0,
      "eval_logps/chosen": -111.0267562866211,
      "eval_logps/rejected": -647.2003784179688,
      "eval_loss": 0.007149172946810722,
      "eval_rewards/chosen": 6.56391716003418,
      "eval_rewards/margins": 51.067161560058594,
      "eval_rewards/rejected": -44.50325012207031,
      "eval_runtime": 215.232,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 500
    },
    {
      "epoch": 3.93,
      "grad_norm": 0.006896671839058399,
      "kl": 0.0,
      "learning_rate": 7.007874015748031e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0128,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 520
    },
    {
      "epoch": 4.08,
      "grad_norm": 0.011443168856203556,
      "kl": 0.0,
      "learning_rate": 6.482939632545932e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0032,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 540
    },
    {
      "epoch": 4.16,
      "eval_kl": 0.0,
      "eval_logps/chosen": -110.33329010009766,
      "eval_logps/rejected": -497.2630615234375,
      "eval_loss": 0.008454231545329094,
      "eval_rewards/chosen": 6.633263111114502,
      "eval_rewards/margins": 36.14277648925781,
      "eval_rewards/rejected": -29.50951385498047,
      "eval_runtime": 215.2369,
      "eval_samples_per_second": 2.323,
      "eval_steps_per_second": 0.581,
      "step": 550
    },
    {
      "epoch": 4.23,
      "grad_norm": 0.010104779154062271,
      "kl": 0.17969775199890137,
      "learning_rate": 5.958005249343832e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0361,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 560
    },
    {
      "epoch": 4.39,
      "grad_norm": 0.006650259718298912,
      "kl": 0.0,
      "learning_rate": 5.433070866141733e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.005,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 580
    },
    {
      "epoch": 4.54,
      "grad_norm": 0.007144566159695387,
      "kl": 0.0,
      "learning_rate": 4.908136482939633e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0029,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 600
    },
    {
      "epoch": 4.54,
      "eval_kl": 0.0,
      "eval_logps/chosen": -111.09209442138672,
      "eval_logps/rejected": -623.0257568359375,
      "eval_loss": 0.0048020947724580765,
      "eval_rewards/chosen": 6.557381629943848,
      "eval_rewards/margins": 48.643157958984375,
      "eval_rewards/rejected": -42.08577346801758,
      "eval_runtime": 215.4697,
      "eval_samples_per_second": 2.321,
      "eval_steps_per_second": 0.58,
      "step": 600
    }
  ],
  "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
}