{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06863417982155114,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009151223976206818,
      "grad_norm": 54.39996337890625,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.9737,
      "step": 1
    },
    {
      "epoch": 0.0009151223976206818,
      "eval_loss": 5.203268051147461,
      "eval_runtime": 118.2109,
      "eval_samples_per_second": 7.791,
      "eval_steps_per_second": 3.9,
      "step": 1
    },
    {
      "epoch": 0.0018302447952413636,
      "grad_norm": 58.29711151123047,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.5667,
      "step": 2
    },
    {
      "epoch": 0.002745367192862045,
      "grad_norm": 34.08722686767578,
      "learning_rate": 0.0001,
      "loss": 1.5324,
      "step": 3
    },
    {
      "epoch": 0.0036604895904827272,
      "grad_norm": 22.385942459106445,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.8586,
      "step": 4
    },
    {
      "epoch": 0.004575611988103409,
      "grad_norm": 11.792092323303223,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.7274,
      "step": 5
    },
    {
      "epoch": 0.00549073438572409,
      "grad_norm": 5.727797985076904,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.4565,
      "step": 6
    },
    {
      "epoch": 0.006405856783344772,
      "grad_norm": 5.8387627601623535,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4339,
      "step": 7
    },
    {
      "epoch": 0.0073209791809654545,
      "grad_norm": 4.341040134429932,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.4869,
      "step": 8
    },
    {
      "epoch": 0.008236101578586136,
      "grad_norm": 4.544722080230713,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.5038,
      "step": 9
    },
    {
      "epoch": 0.009151223976206819,
      "grad_norm": 4.45267391204834,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.564,
      "step": 10
    },
    {
      "epoch": 0.010066346373827499,
      "grad_norm": 4.4613118171691895,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5057,
      "step": 11
    },
    {
      "epoch": 0.01098146877144818,
      "grad_norm": 4.204299449920654,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.4668,
      "step": 12
    },
    {
      "epoch": 0.011896591169068863,
      "grad_norm": 4.608882904052734,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.4163,
      "step": 13
    },
    {
      "epoch": 0.012811713566689545,
      "grad_norm": 5.996987342834473,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.4163,
      "step": 14
    },
    {
      "epoch": 0.013726835964310227,
      "grad_norm": 3.0946178436279297,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2983,
      "step": 15
    },
    {
      "epoch": 0.014641958361930909,
      "grad_norm": 6.740449905395508,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.3792,
      "step": 16
    },
    {
      "epoch": 0.01555708075955159,
      "grad_norm": 5.349632740020752,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.3745,
      "step": 17
    },
    {
      "epoch": 0.016472203157172273,
      "grad_norm": 0.025801466777920723,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0003,
      "step": 18
    },
    {
      "epoch": 0.017387325554792953,
      "grad_norm": 0.5926369428634644,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0204,
      "step": 19
    },
    {
      "epoch": 0.018302447952413637,
      "grad_norm": 0.3014591932296753,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0032,
      "step": 20
    },
    {
      "epoch": 0.019217570350034317,
      "grad_norm": 5.245384216308594,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2281,
      "step": 21
    },
    {
      "epoch": 0.020132692747654998,
      "grad_norm": 3.9620978832244873,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.1387,
      "step": 22
    },
    {
      "epoch": 0.02104781514527568,
      "grad_norm": 2.9123241901397705,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0792,
      "step": 23
    },
    {
      "epoch": 0.02196293754289636,
      "grad_norm": 4.7875590324401855,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0747,
      "step": 24
    },
    {
      "epoch": 0.022878059940517045,
      "grad_norm": 2.0412256717681885,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0176,
      "step": 25
    },
    {
      "epoch": 0.022878059940517045,
      "eval_loss": 0.16302213072776794,
      "eval_runtime": 118.419,
      "eval_samples_per_second": 7.777,
      "eval_steps_per_second": 3.893,
      "step": 25
    },
    {
      "epoch": 0.023793182338137726,
      "grad_norm": 1.1200025081634521,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.0118,
      "step": 26
    },
    {
      "epoch": 0.024708304735758406,
      "grad_norm": 0.16598665714263916,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0009,
      "step": 27
    },
    {
      "epoch": 0.02562342713337909,
      "grad_norm": 0.7957071661949158,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.0073,
      "step": 28
    },
    {
      "epoch": 0.02653854953099977,
      "grad_norm": 3.8172872066497803,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.1607,
      "step": 29
    },
    {
      "epoch": 0.027453671928620454,
      "grad_norm": 1.0546435117721558,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0068,
      "step": 30
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 4.415338039398193,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0483,
      "step": 31
    },
    {
      "epoch": 0.029283916723861818,
      "grad_norm": 0.23499952256679535,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.001,
      "step": 32
    },
    {
      "epoch": 0.030199039121482498,
      "grad_norm": 0.0032876424957066774,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.03111416151910318,
      "grad_norm": 0.0020302478224039078,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.03202928391672386,
      "grad_norm": 0.0020431417506188154,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.032944406314344546,
      "grad_norm": 0.34559494256973267,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0002,
      "step": 36
    },
    {
      "epoch": 0.03385952871196522,
      "grad_norm": 0.14722956717014313,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0004,
      "step": 37
    },
    {
      "epoch": 0.034774651109585906,
      "grad_norm": 0.0014910429017618299,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.03568977350720659,
      "grad_norm": 0.0005584294558502734,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.036604895904827274,
      "grad_norm": 0.0006086250650696456,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.03752001830244795,
      "grad_norm": 0.0006442245212383568,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.038435140700068635,
      "grad_norm": 0.0002517640241421759,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.03935026309768932,
      "grad_norm": 0.00027328028227202594,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.040265385495309995,
      "grad_norm": 0.0007536720368079841,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.04118050789293068,
      "grad_norm": 0.0002211566607002169,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04209563029055136,
      "grad_norm": 0.012777777388691902,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.043010752688172046,
      "grad_norm": 0.0013763984898105264,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.04392587508579272,
      "grad_norm": 0.20022982358932495,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0012,
      "step": 48
    },
    {
      "epoch": 0.04484099748341341,
      "grad_norm": 0.0004175468347966671,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.04575611988103409,
      "grad_norm": 9.72150664892979e-05,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.04575611988103409,
      "eval_loss": 0.28562989830970764,
      "eval_runtime": 118.4097,
      "eval_samples_per_second": 7.778,
      "eval_steps_per_second": 3.893,
      "step": 50
    },
    {
      "epoch": 0.04667124227865477,
      "grad_norm": 15.607521057128906,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9073,
      "step": 51
    },
    {
      "epoch": 0.04758636467627545,
      "grad_norm": 14.263496398925781,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.6026,
      "step": 52
    },
    {
      "epoch": 0.048501487073896135,
      "grad_norm": 7.130948066711426,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.4088,
      "step": 53
    },
    {
      "epoch": 0.04941660947151681,
      "grad_norm": 8.556685447692871,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.6188,
      "step": 54
    },
    {
      "epoch": 0.050331731869137496,
      "grad_norm": 5.391532897949219,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4404,
      "step": 55
    },
    {
      "epoch": 0.05124685426675818,
      "grad_norm": 5.243240833282471,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.3264,
      "step": 56
    },
    {
      "epoch": 0.05216197666437886,
      "grad_norm": 3.5227527618408203,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.3415,
      "step": 57
    },
    {
      "epoch": 0.05307709906199954,
      "grad_norm": 4.664560317993164,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.4925,
      "step": 58
    },
    {
      "epoch": 0.053992221459620224,
      "grad_norm": 5.512412071228027,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.5046,
      "step": 59
    },
    {
      "epoch": 0.05490734385724091,
      "grad_norm": 3.448622703552246,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.35,
      "step": 60
    },
    {
      "epoch": 0.055822466254861584,
      "grad_norm": 2.99069881439209,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.3607,
      "step": 61
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 4.074262619018555,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.4701,
      "step": 62
    },
    {
      "epoch": 0.05765271105010295,
      "grad_norm": 5.847626686096191,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.4466,
      "step": 63
    },
    {
      "epoch": 0.058567833447723636,
      "grad_norm": 3.9188435077667236,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.4807,
      "step": 64
    },
    {
      "epoch": 0.05948295584534431,
      "grad_norm": 4.037470817565918,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.3334,
      "step": 65
    },
    {
      "epoch": 0.060398078242964996,
      "grad_norm": 7.9875712394714355,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.6476,
      "step": 66
    },
    {
      "epoch": 0.06131320064058568,
      "grad_norm": 2.264742612838745,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2031,
      "step": 67
    },
    {
      "epoch": 0.06222832303820636,
      "grad_norm": 0.013100137002766132,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0001,
      "step": 68
    },
    {
      "epoch": 0.06314344543582705,
      "grad_norm": 2.0209121704101562,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0288,
      "step": 69
    },
    {
      "epoch": 0.06405856783344772,
      "grad_norm": 0.24793341755867004,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0045,
      "step": 70
    },
    {
      "epoch": 0.0649736902310684,
      "grad_norm": 0.009124662727117538,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0001,
      "step": 71
    },
    {
      "epoch": 0.06588881262868909,
      "grad_norm": 5.83003568649292,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.1107,
      "step": 72
    },
    {
      "epoch": 0.06680393502630977,
      "grad_norm": 2.5844852924346924,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0796,
      "step": 73
    },
    {
      "epoch": 0.06771905742393045,
      "grad_norm": 1.5514365434646606,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.011,
      "step": 74
    },
    {
      "epoch": 0.06863417982155114,
      "grad_norm": 0.07357123494148254,
      "learning_rate": 0.0,
      "loss": 0.0006,
      "step": 75
    },
    {
      "epoch": 0.06863417982155114,
      "eval_loss": 0.1349995732307434,
      "eval_runtime": 118.4018,
      "eval_samples_per_second": 7.779,
      "eval_steps_per_second": 3.894,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.157714927419392e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}