{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22796352583586627,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00303951367781155,
      "grad_norm": 13.49870491027832,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.1121,
      "step": 1
    },
    {
      "epoch": 0.00303951367781155,
      "eval_loss": 4.797636032104492,
      "eval_runtime": 36.7942,
      "eval_samples_per_second": 3.778,
      "eval_steps_per_second": 1.902,
      "step": 1
    },
    {
      "epoch": 0.0060790273556231,
      "grad_norm": 12.006007194519043,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.7642,
      "step": 2
    },
    {
      "epoch": 0.00911854103343465,
      "grad_norm": 11.162591934204102,
      "learning_rate": 5e-05,
      "loss": 3.077,
      "step": 3
    },
    {
      "epoch": 0.0121580547112462,
      "grad_norm": 8.176030158996582,
      "learning_rate": 4.997620553954645e-05,
      "loss": 2.8574,
      "step": 4
    },
    {
      "epoch": 0.015197568389057751,
      "grad_norm": 6.960273265838623,
      "learning_rate": 4.990486745229364e-05,
      "loss": 2.5954,
      "step": 5
    },
    {
      "epoch": 0.0182370820668693,
      "grad_norm": 7.929886817932129,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 2.6525,
      "step": 6
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 6.948627948760986,
      "learning_rate": 4.962019382530521e-05,
      "loss": 2.2277,
      "step": 7
    },
    {
      "epoch": 0.0243161094224924,
      "grad_norm": 6.242570877075195,
      "learning_rate": 4.940740017799833e-05,
      "loss": 1.5744,
      "step": 8
    },
    {
      "epoch": 0.02735562310030395,
      "grad_norm": 7.785113334655762,
      "learning_rate": 4.914814565722671e-05,
      "loss": 2.0428,
      "step": 9
    },
    {
      "epoch": 0.030395136778115502,
      "grad_norm": 7.158974647521973,
      "learning_rate": 4.884292376870567e-05,
      "loss": 1.4865,
      "step": 10
    },
    {
      "epoch": 0.03343465045592705,
      "grad_norm": 7.481812953948975,
      "learning_rate": 4.849231551964771e-05,
      "loss": 1.6615,
      "step": 11
    },
    {
      "epoch": 0.0364741641337386,
      "grad_norm": 13.22747802734375,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 2.5028,
      "step": 12
    },
    {
      "epoch": 0.03951367781155015,
      "grad_norm": 7.720076560974121,
      "learning_rate": 4.765769467591625e-05,
      "loss": 1.1715,
      "step": 13
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 6.172296047210693,
      "learning_rate": 4.717527082945554e-05,
      "loss": 0.7897,
      "step": 14
    },
    {
      "epoch": 0.04559270516717325,
      "grad_norm": 7.666730880737305,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.42,
      "step": 15
    },
    {
      "epoch": 0.0486322188449848,
      "grad_norm": 8.414482116699219,
      "learning_rate": 4.608478614532215e-05,
      "loss": 1.0577,
      "step": 16
    },
    {
      "epoch": 0.05167173252279635,
      "grad_norm": 8.490312576293945,
      "learning_rate": 4.54788011072248e-05,
      "loss": 1.4698,
      "step": 17
    },
    {
      "epoch": 0.0547112462006079,
      "grad_norm": 6.877030372619629,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 1.1734,
      "step": 18
    },
    {
      "epoch": 0.057750759878419454,
      "grad_norm": 7.7711052894592285,
      "learning_rate": 4.415111107797445e-05,
      "loss": 1.1899,
      "step": 19
    },
    {
      "epoch": 0.060790273556231005,
      "grad_norm": 6.355740547180176,
      "learning_rate": 4.34319334202531e-05,
      "loss": 1.0894,
      "step": 20
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 5.492956161499023,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.5664,
      "step": 21
    },
    {
      "epoch": 0.0668693009118541,
      "grad_norm": 5.8868303298950195,
      "learning_rate": 4.188975519039151e-05,
      "loss": 0.7452,
      "step": 22
    },
    {
      "epoch": 0.06990881458966565,
      "grad_norm": 5.961940288543701,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 0.8316,
      "step": 23
    },
    {
      "epoch": 0.0729483282674772,
      "grad_norm": 10.402515411376953,
      "learning_rate": 4.021903572521802e-05,
      "loss": 1.2375,
      "step": 24
    },
    {
      "epoch": 0.07598784194528875,
      "grad_norm": 9.500027656555176,
      "learning_rate": 3.933941090877615e-05,
      "loss": 1.34,
      "step": 25
    },
    {
      "epoch": 0.07598784194528875,
      "eval_loss": 1.3861757516860962,
      "eval_runtime": 37.3804,
      "eval_samples_per_second": 3.719,
      "eval_steps_per_second": 1.873,
      "step": 25
    },
    {
      "epoch": 0.0790273556231003,
      "grad_norm": 10.619952201843262,
      "learning_rate": 3.84324902086706e-05,
      "loss": 0.971,
      "step": 26
    },
    {
      "epoch": 0.08206686930091185,
      "grad_norm": 8.14050579071045,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.4617,
      "step": 27
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 8.265830993652344,
      "learning_rate": 3.654371533087586e-05,
      "loss": 0.9466,
      "step": 28
    },
    {
      "epoch": 0.08814589665653495,
      "grad_norm": 14.07198429107666,
      "learning_rate": 3.556545654351749e-05,
      "loss": 1.1971,
      "step": 29
    },
    {
      "epoch": 0.0911854103343465,
      "grad_norm": 7.206356525421143,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.5795,
      "step": 30
    },
    {
      "epoch": 0.09422492401215805,
      "grad_norm": 6.850846290588379,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.7625,
      "step": 31
    },
    {
      "epoch": 0.0972644376899696,
      "grad_norm": 18.45955467224121,
      "learning_rate": 3.251764498760683e-05,
      "loss": 0.9912,
      "step": 32
    },
    {
      "epoch": 0.10030395136778116,
      "grad_norm": 20.52401351928711,
      "learning_rate": 3.147047612756302e-05,
      "loss": 1.1835,
      "step": 33
    },
    {
      "epoch": 0.1033434650455927,
      "grad_norm": 7.496253490447998,
      "learning_rate": 3.0410990348452573e-05,
      "loss": 0.512,
      "step": 34
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 8.358292579650879,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.7951,
      "step": 35
    },
    {
      "epoch": 0.1094224924012158,
      "grad_norm": 6.15350866317749,
      "learning_rate": 2.8263154805501297e-05,
      "loss": 0.8166,
      "step": 36
    },
    {
      "epoch": 0.11246200607902736,
      "grad_norm": 8.419435501098633,
      "learning_rate": 2.717889356869146e-05,
      "loss": 1.0166,
      "step": 37
    },
    {
      "epoch": 0.11550151975683891,
      "grad_norm": 7.933197975158691,
      "learning_rate": 2.6090484684133404e-05,
      "loss": 1.1009,
      "step": 38
    },
    {
      "epoch": 0.11854103343465046,
      "grad_norm": 8.382092475891113,
      "learning_rate": 2.5e-05,
      "loss": 0.7886,
      "step": 39
    },
    {
      "epoch": 0.12158054711246201,
      "grad_norm": 6.936803817749023,
      "learning_rate": 2.3909515315866605e-05,
      "loss": 0.9169,
      "step": 40
    },
    {
      "epoch": 0.12462006079027356,
      "grad_norm": 8.673044204711914,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 0.8285,
      "step": 41
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 7.593755722045898,
      "learning_rate": 2.173684519449872e-05,
      "loss": 0.9036,
      "step": 42
    },
    {
      "epoch": 0.13069908814589665,
      "grad_norm": 34.3929557800293,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.1941,
      "step": 43
    },
    {
      "epoch": 0.1337386018237082,
      "grad_norm": 16.547935485839844,
      "learning_rate": 1.958900965154743e-05,
      "loss": 1.3811,
      "step": 44
    },
    {
      "epoch": 0.13677811550151975,
      "grad_norm": 32.15914535522461,
      "learning_rate": 1.852952387243698e-05,
      "loss": 1.1523,
      "step": 45
    },
    {
      "epoch": 0.1398176291793313,
      "grad_norm": 12.116189956665039,
      "learning_rate": 1.7482355012393177e-05,
      "loss": 0.9528,
      "step": 46
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 22.938390731811523,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 2.451,
      "step": 47
    },
    {
      "epoch": 0.1458966565349544,
      "grad_norm": 41.893733978271484,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 1.3534,
      "step": 48
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 29.780670166015625,
      "learning_rate": 1.443454345648252e-05,
      "loss": 1.8623,
      "step": 49
    },
    {
      "epoch": 0.1519756838905775,
      "grad_norm": 17.589799880981445,
      "learning_rate": 1.3456284669124158e-05,
      "loss": 1.9448,
      "step": 50
    },
    {
      "epoch": 0.1519756838905775,
      "eval_loss": 1.0934056043624878,
      "eval_runtime": 37.3691,
      "eval_samples_per_second": 3.72,
      "eval_steps_per_second": 1.873,
      "step": 50
    },
    {
      "epoch": 0.15501519756838905,
      "grad_norm": 17.6353759765625,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 1.4377,
      "step": 51
    },
    {
      "epoch": 0.1580547112462006,
      "grad_norm": 15.932900428771973,
      "learning_rate": 1.1567509791329401e-05,
      "loss": 1.1834,
      "step": 52
    },
    {
      "epoch": 0.16109422492401215,
      "grad_norm": 13.163067817687988,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 1.5885,
      "step": 53
    },
    {
      "epoch": 0.1641337386018237,
      "grad_norm": 11.45263385772705,
      "learning_rate": 9.780964274781984e-06,
      "loss": 0.9741,
      "step": 54
    },
    {
      "epoch": 0.16717325227963525,
      "grad_norm": 8.3353910446167,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.6441,
      "step": 55
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 7.865023612976074,
      "learning_rate": 8.110244809608495e-06,
      "loss": 0.658,
      "step": 56
    },
    {
      "epoch": 0.17325227963525835,
      "grad_norm": 6.3831095695495605,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.8165,
      "step": 57
    },
    {
      "epoch": 0.1762917933130699,
      "grad_norm": 5.159278869628906,
      "learning_rate": 6.568066579746901e-06,
      "loss": 0.665,
      "step": 58
    },
    {
      "epoch": 0.17933130699088146,
      "grad_norm": 4.828774452209473,
      "learning_rate": 5.848888922025553e-06,
      "loss": 0.647,
      "step": 59
    },
    {
      "epoch": 0.182370820668693,
      "grad_norm": 5.115424156188965,
      "learning_rate": 5.166166492719124e-06,
      "loss": 0.47,
      "step": 60
    },
    {
      "epoch": 0.18541033434650456,
      "grad_norm": 3.0081770420074463,
      "learning_rate": 4.521198892775203e-06,
      "loss": 0.4042,
      "step": 61
    },
    {
      "epoch": 0.1884498480243161,
      "grad_norm": 3.4292054176330566,
      "learning_rate": 3.9152138546778625e-06,
      "loss": 0.5876,
      "step": 62
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 5.665149211883545,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.6981,
      "step": 63
    },
    {
      "epoch": 0.1945288753799392,
      "grad_norm": 5.063657283782959,
      "learning_rate": 2.8247291705444575e-06,
      "loss": 0.8123,
      "step": 64
    },
    {
      "epoch": 0.19756838905775076,
      "grad_norm": 5.569523334503174,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 0.7608,
      "step": 65
    },
    {
      "epoch": 0.2006079027355623,
      "grad_norm": 5.494087219238281,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.6362,
      "step": 66
    },
    {
      "epoch": 0.20364741641337386,
      "grad_norm": 3.7691006660461426,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.4503,
      "step": 67
    },
    {
      "epoch": 0.2066869300911854,
      "grad_norm": 2.7975122928619385,
      "learning_rate": 1.1570762312943295e-06,
      "loss": 0.5325,
      "step": 68
    },
    {
      "epoch": 0.20972644376899696,
      "grad_norm": 5.918449401855469,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.5773,
      "step": 69
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 5.920218467712402,
      "learning_rate": 5.925998220016659e-07,
      "loss": 0.731,
      "step": 70
    },
    {
      "epoch": 0.21580547112462006,
      "grad_norm": 6.536037445068359,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.6718,
      "step": 71
    },
    {
      "epoch": 0.2188449848024316,
      "grad_norm": 6.299208164215088,
      "learning_rate": 2.1387846565474045e-07,
      "loss": 0.7229,
      "step": 72
    },
    {
      "epoch": 0.22188449848024316,
      "grad_norm": 6.822452545166016,
      "learning_rate": 9.513254770636137e-08,
      "loss": 0.7534,
      "step": 73
    },
    {
      "epoch": 0.22492401215805471,
      "grad_norm": 7.545007705688477,
      "learning_rate": 2.3794460453555047e-08,
      "loss": 0.7793,
      "step": 74
    },
    {
      "epoch": 0.22796352583586627,
      "grad_norm": 8.794013977050781,
      "learning_rate": 0.0,
      "loss": 0.8974,
      "step": 75
    },
    {
      "epoch": 0.22796352583586627,
      "eval_loss": 0.7993611693382263,
      "eval_runtime": 37.3913,
      "eval_samples_per_second": 3.717,
      "eval_steps_per_second": 1.872,
      "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": 2.4882650284032e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}