{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.03586147725582123,
      "learning_rate": 0.0,
      "loss": 0.9098724722862244,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.03577122464776039,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.9084522724151611,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.031653374433517456,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.8834755420684814,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.025831686332821846,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.871230959892273,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.019876576960086823,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.7917206287384033,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.018677273765206337,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.8436126708984375,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.017528358846902847,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.8075190782546997,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.01399513240903616,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.7754716873168945,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.012644859962165356,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.7459083199501038,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.01209743320941925,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.7365868091583252,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.012133832089602947,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.7119501829147339,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.010017997585237026,
      "learning_rate": 5e-06,
      "loss": 0.6901087760925293,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.009233366698026657,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.6611638069152832,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.00782010331749916,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.6715224981307983,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.007341764867305756,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.6277110576629639,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.00713470159098506,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.6689565181732178,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.0067572277039289474,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.6363875865936279,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.006228511221706867,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.6257224678993225,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.006048806011676788,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.6355900764465332,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.005988306365907192,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.6338369846343994,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.005441761109977961,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.6133573055267334,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.005174445919692516,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.6042410135269165,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.005199746694415808,
      "learning_rate": 1e-05,
      "loss": 0.602219820022583,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.005485028959810734,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.6062123775482178,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.004896003287285566,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.6077945232391357,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.00495151337236166,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.5923135280609131,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.004744194447994232,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.5860621929168701,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.004471767693758011,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.5823097229003906,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.004788320977240801,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.5872600078582764,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.0044632842764258385,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.6070278286933899,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.004317905753850937,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.5780316591262817,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.004291852004826069,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.5697590112686157,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.003922830801457167,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.5747107267379761,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.0041889771819114685,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.6021177172660828,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.004147357773035765,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.5805741548538208,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.0040724254213273525,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.5483200550079346,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.004085644613951445,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.557392954826355,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.004289102274924517,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.590857207775116,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.0040345704182982445,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.5750541090965271,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.004034748766571283,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.5949826240539551,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.003911909181624651,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.5623177289962769,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.0037001846358180046,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.5465081930160522,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.0037095139268785715,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.5752100944519043,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.003655617358162999,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.5452020168304443,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.003784338477998972,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.5616332292556763,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.003718078136444092,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.5558297634124756,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.00395169947296381,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.5600595474243164,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.003555440343916416,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.5372895002365112,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.0037386869080364704,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.5322733521461487,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.003739988896995783,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.5380419492721558,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.5587145090103149,
      "eval_runtime": 8.7676,
      "eval_samples_per_second": 22.811,
      "eval_steps_per_second": 11.406,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.0037539806216955185,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.5472225546836853,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.003411181503906846,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.5134032964706421,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.0037538670003414154,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.5361013412475586,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.0036495670210570097,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.5299779772758484,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.0037342547439038754,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.5607945919036865,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.003572584595531225,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.5528460741043091,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.003770101349800825,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.5440288186073303,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.0036679303739219904,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5564252138137817,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.003834612900391221,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.5473330020904541,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.003683249931782484,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.5463743209838867,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.0036777963396161795,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.524878740310669,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.0038230482023209333,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5563522577285767,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.003645201213657856,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.5059154033660889,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.0035886459518224,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.5312881469726562,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.003721872577443719,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.5358959436416626,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.003683999879285693,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.5442053079605103,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.0036851842887699604,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.5263723731040955,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.003754258854314685,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.5200538039207458,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.0038373274728655815,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.5452108383178711,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.0039480882696807384,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.5066030621528625,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.005897017661482096,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.5380499958992004,
      "step": 71
    }
  ],
  "logging_steps": 1,
  "max_steps": 213,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.242478482194432e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}