{
  "best_metric": 0.014748962596058846,
  "best_model_checkpoint": "./Zephyr/27-03-24-Weni-kto-test_WeniGPT Experiment using KTO trainer with no collator-2_max_steps-786_batch_16_2024-03-27_ppid_1885/checkpoint-300",
  "epoch": 5.333333333333333,
  "eval_steps": 50,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "grad_norm": 2.2224462032318115,
      "kl": 0.054589949548244476,
      "learning_rate": 0.0001666666666666667,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 704.2891,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 2.9781014919281006,
      "kl": 0.014553820714354515,
      "learning_rate": 0.00019580052493438322,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 371.0873,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 40
    },
    {
      "epoch": 0.38,
      "eval_kl": 0.014955863356590271,
      "eval_logps/chosen": -139.6813507080078,
      "eval_logps/rejected": -288.11480712890625,
      "eval_loss": 0.0440419502556324,
      "eval_rewards/chosen": 4.680752754211426,
      "eval_rewards/margins": 14.199661254882812,
      "eval_rewards/rejected": -9.518909454345703,
      "eval_runtime": 437.1874,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 50
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.7002557516098022,
      "kl": 0.36391472816467285,
      "learning_rate": 0.0001905511811023622,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 165.1605,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 60
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.5644651651382446,
      "kl": 0.01063810009509325,
      "learning_rate": 0.00018556430446194227,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 89.197,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 80
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.18941974639892578,
      "kl": 0.0,
      "learning_rate": 0.0001805774278215223,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 57.9834,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 100
    },
    {
      "epoch": 0.76,
      "eval_kl": 0.0,
      "eval_logps/chosen": -135.0946807861328,
      "eval_logps/rejected": -511.870361328125,
      "eval_loss": 0.027495555579662323,
      "eval_rewards/chosen": 5.139419078826904,
      "eval_rewards/margins": 37.033878326416016,
      "eval_rewards/rejected": -31.89446258544922,
      "eval_runtime": 437.2677,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 100
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.2737089395523071,
      "kl": 0.0,
      "learning_rate": 0.00017532808398950132,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 1101.4947,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 120
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.10652273148298264,
      "kl": 0.0,
      "learning_rate": 0.00017007874015748033,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 37.3685,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 140
    },
    {
      "epoch": 1.14,
      "eval_kl": 0.0,
      "eval_logps/chosen": -133.9324951171875,
      "eval_logps/rejected": -464.85992431640625,
      "eval_loss": 0.019584182649850845,
      "eval_rewards/chosen": 5.25563907623291,
      "eval_rewards/margins": 32.449058532714844,
      "eval_rewards/rejected": -27.19342041015625,
      "eval_runtime": 437.0658,
      "eval_samples_per_second": 1.071,
      "eval_steps_per_second": 0.268,
      "step": 150
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.060089632868766785,
      "kl": 0.21830137073993683,
      "learning_rate": 0.00016482939632545934,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 91.1641,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 160
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.08910108357667923,
      "kl": 0.03056584671139717,
      "learning_rate": 0.00015958005249343832,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 8.2078,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 180
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.025327660143375397,
      "kl": 0.0,
      "learning_rate": 0.00015433070866141733,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 3.6561,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 200
    },
    {
      "epoch": 1.52,
      "eval_kl": 0.0,
      "eval_logps/chosen": -132.1833038330078,
      "eval_logps/rejected": -419.2353820800781,
      "eval_loss": 0.016207611188292503,
      "eval_rewards/chosen": 5.430557727813721,
      "eval_rewards/margins": 28.061521530151367,
      "eval_rewards/rejected": -22.630962371826172,
      "eval_runtime": 437.1734,
      "eval_samples_per_second": 1.071,
      "eval_steps_per_second": 0.268,
      "step": 200
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.04120240360498428,
      "kl": 0.04972388595342636,
      "learning_rate": 0.00014908136482939634,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 21.787,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 220
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.043324064463377,
      "kl": 0.09086960554122925,
      "learning_rate": 0.00014383202099737535,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 59.5367,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 240
    },
    {
      "epoch": 1.9,
      "eval_kl": 0.0,
      "eval_logps/chosen": -129.1339111328125,
      "eval_logps/rejected": -504.5447998046875,
      "eval_loss": 0.01432154793292284,
      "eval_rewards/chosen": 5.7354960441589355,
      "eval_rewards/margins": 36.89740753173828,
      "eval_rewards/rejected": -31.161909103393555,
      "eval_runtime": 437.5542,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.267,
      "step": 250
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.028953969478607178,
      "kl": 0.0,
      "learning_rate": 0.00013858267716535433,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 5.7556,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 260
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.022753821685910225,
      "kl": 0.18936340510845184,
      "learning_rate": 0.00013333333333333334,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 4.7774,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 280
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.038736581802368164,
      "kl": 0.0,
      "learning_rate": 0.00012808398950131235,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 13.1891,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 300
    },
    {
      "epoch": 2.29,
      "eval_kl": 0.0,
      "eval_logps/chosen": -130.3461151123047,
      "eval_logps/rejected": -503.4655456542969,
      "eval_loss": 0.014748962596058846,
      "eval_rewards/chosen": 5.614275932312012,
      "eval_rewards/margins": 36.66826248168945,
      "eval_rewards/rejected": -31.05398178100586,
      "eval_runtime": 437.6283,
      "eval_samples_per_second": 1.069,
      "eval_steps_per_second": 0.267,
      "step": 300
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.015456304885447025,
      "kl": 0.016447115689516068,
      "learning_rate": 0.00012283464566929136,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 2.946,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 320
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.03844680264592171,
      "kl": 0.0,
      "learning_rate": 0.00011758530183727034,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 3.8532,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 340
    },
    {
      "epoch": 2.67,
      "eval_kl": 0.0,
      "eval_logps/chosen": -127.6288833618164,
      "eval_logps/rejected": -457.08013916015625,
      "eval_loss": 0.013063323684036732,
      "eval_rewards/chosen": 5.886001110076904,
      "eval_rewards/margins": 32.30144119262695,
      "eval_rewards/rejected": -26.415441513061523,
      "eval_runtime": 437.2,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 350
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.013407759368419647,
      "kl": 0.0,
      "learning_rate": 0.00011233595800524934,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 14.6044,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 360
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.1375456601381302,
      "kl": 0.042511165142059326,
      "learning_rate": 0.00010708661417322836,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 20.8824,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 380
    },
    {
      "epoch": 3.05,
      "grad_norm": 0.012805495411157608,
      "kl": 0.0,
      "learning_rate": 0.00010183727034120735,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 3.7678,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 400
    },
    {
      "epoch": 3.05,
      "eval_kl": 0.0,
      "eval_logps/chosen": -127.17108917236328,
      "eval_logps/rejected": -460.4493408203125,
      "eval_loss": 0.016150476410984993,
      "eval_rewards/chosen": 5.931778430938721,
      "eval_rewards/margins": 32.684139251708984,
      "eval_rewards/rejected": -26.75235939025879,
      "eval_runtime": 437.1823,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 400
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.017726995050907135,
      "kl": 0.2870129942893982,
      "learning_rate": 9.658792650918635e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 1.685,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 420
    },
    {
      "epoch": 3.35,
      "grad_norm": 0.007917443290352821,
      "kl": 0.0,
      "learning_rate": 9.133858267716536e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 49.3456,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 440
    },
    {
      "epoch": 3.43,
      "eval_kl": 0.0,
      "eval_logps/chosen": -127.23651123046875,
      "eval_logps/rejected": -479.95904541015625,
      "eval_loss": 0.016735197976231575,
      "eval_rewards/chosen": 5.925236225128174,
      "eval_rewards/margins": 34.628562927246094,
      "eval_rewards/rejected": -28.703327178955078,
      "eval_runtime": 437.235,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 450
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.016776828095316887,
      "kl": 0.0,
      "learning_rate": 8.608923884514435e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 6.9542,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 460
    },
    {
      "epoch": 3.66,
      "grad_norm": 0.009395829401910305,
      "kl": 0.0,
      "learning_rate": 8.083989501312336e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 25.7168,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 480
    },
    {
      "epoch": 3.81,
      "grad_norm": 0.008246039040386677,
      "kl": 0.028682123869657516,
      "learning_rate": 7.559055118110236e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 12.2886,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 500
    },
    {
      "epoch": 3.81,
      "eval_kl": 0.0,
      "eval_logps/chosen": -126.48030090332031,
      "eval_logps/rejected": -487.4185485839844,
      "eval_loss": 0.01638978347182274,
      "eval_rewards/chosen": 6.000857830047607,
      "eval_rewards/margins": 35.45014190673828,
      "eval_rewards/rejected": -29.44928550720215,
      "eval_runtime": 437.6004,
      "eval_samples_per_second": 1.069,
      "eval_steps_per_second": 0.267,
      "step": 500
    },
    {
      "epoch": 3.96,
      "grad_norm": 0.010333240032196045,
      "kl": 0.0,
      "learning_rate": 7.034120734908137e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 7.7922,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 520
    },
    {
      "epoch": 4.11,
      "grad_norm": 0.00740875443443656,
      "kl": 0.0027637004386633635,
      "learning_rate": 6.509186351706036e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 2.3745,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 540
    },
    {
      "epoch": 4.19,
      "eval_kl": 0.0,
      "eval_logps/chosen": -126.36491394042969,
      "eval_logps/rejected": -492.7337951660156,
      "eval_loss": 0.017263902351260185,
      "eval_rewards/chosen": 6.012395858764648,
      "eval_rewards/margins": 35.993202209472656,
      "eval_rewards/rejected": -29.980806350708008,
      "eval_runtime": 437.4134,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.267,
      "step": 550
    },
    {
      "epoch": 4.27,
      "grad_norm": 0.01026746816933155,
      "kl": 0.2550431191921234,
      "learning_rate": 5.984251968503938e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 3.1176,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 560
    },
    {
      "epoch": 4.42,
      "grad_norm": 0.006209189537912607,
      "kl": 0.0,
      "learning_rate": 5.4593175853018376e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 3.788,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 580
    },
    {
      "epoch": 4.57,
      "grad_norm": 0.007328963838517666,
      "kl": 0.0,
      "learning_rate": 4.934383202099738e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.46,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 600
    },
    {
      "epoch": 4.57,
      "eval_kl": 0.0,
      "eval_logps/chosen": -126.42925262451172,
      "eval_logps/rejected": -497.53179931640625,
      "eval_loss": 0.01734013482928276,
      "eval_rewards/chosen": 6.0059614181518555,
      "eval_rewards/margins": 36.46657180786133,
      "eval_rewards/rejected": -30.460607528686523,
      "eval_runtime": 437.192,
      "eval_samples_per_second": 1.07,
      "eval_steps_per_second": 0.268,
      "step": 600
    },
    {
      "epoch": 4.72,
      "grad_norm": 0.006411154754459858,
      "kl": 0.0,
      "learning_rate": 4.409448818897638e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 5.6447,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 620
    },
    {
      "epoch": 4.88,
      "grad_norm": 0.006403986364603043,
      "kl": 0.0061653731390833855,
      "learning_rate": 3.8845144356955383e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 7.7723,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 640
    },
    {
      "epoch": 4.95,
      "eval_kl": 0.0,
      "eval_logps/chosen": -126.40960693359375,
      "eval_logps/rejected": -499.95538330078125,
      "eval_loss": 0.017983298748731613,
      "eval_rewards/chosen": 6.007925510406494,
      "eval_rewards/margins": 36.71089172363281,
      "eval_rewards/rejected": -30.702964782714844,
      "eval_runtime": 437.1466,
      "eval_samples_per_second": 1.071,
      "eval_steps_per_second": 0.268,
      "step": 650
    },
    {
      "epoch": 5.03,
      "grad_norm": 0.011981657706201077,
      "kl": 0.0,
      "learning_rate": 3.3595800524934386e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 2.9837,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 660
    },
    {
      "epoch": 5.18,
      "grad_norm": 0.003182880114763975,
      "kl": 0.24422872066497803,
      "learning_rate": 2.8346456692913388e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 15.7313,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 680
    },
    {
      "epoch": 5.33,
      "grad_norm": 0.004406992811709642,
      "kl": 0.0,
      "learning_rate": 2.309711286089239e-05,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 4.1333,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 700
    },
    {
      "epoch": 5.33,
      "eval_kl": 0.0,
      "eval_logps/chosen": -126.45208740234375,
      "eval_logps/rejected": -501.8733825683594,
      "eval_loss": 0.018385978415608406,
      "eval_rewards/chosen": 6.003678321838379,
      "eval_rewards/margins": 36.89844512939453,
      "eval_rewards/rejected": -30.89476776123047,
      "eval_runtime": 436.8506,
      "eval_samples_per_second": 1.071,
      "eval_steps_per_second": 0.268,
      "step": 700
    }
  ],
  "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": 2,
  "trial_name": null,
  "trial_params": null
}