{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9904153354632586,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038338658146964855,
      "grad_norm": 6.566943168640137,
      "learning_rate": 1.25e-06,
      "loss": 0.9912,
      "step": 1
    },
    {
      "epoch": 0.07667731629392971,
      "grad_norm": 6.667538642883301,
      "learning_rate": 2.5e-06,
      "loss": 1.0339,
      "step": 2
    },
    {
      "epoch": 0.11501597444089456,
      "grad_norm": 6.683051586151123,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.0161,
      "step": 3
    },
    {
      "epoch": 0.15335463258785942,
      "grad_norm": 5.961772918701172,
      "learning_rate": 5e-06,
      "loss": 0.9784,
      "step": 4
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 4.3473219871521,
      "learning_rate": 6.25e-06,
      "loss": 0.9369,
      "step": 5
    },
    {
      "epoch": 0.23003194888178913,
      "grad_norm": 2.654831886291504,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.9299,
      "step": 6
    },
    {
      "epoch": 0.268370607028754,
      "grad_norm": 4.331104278564453,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.9099,
      "step": 7
    },
    {
      "epoch": 0.30670926517571884,
      "grad_norm": 4.492929458618164,
      "learning_rate": 1e-05,
      "loss": 0.8921,
      "step": 8
    },
    {
      "epoch": 0.3450479233226837,
      "grad_norm": 4.256988048553467,
      "learning_rate": 9.994965332706574e-06,
      "loss": 0.8642,
      "step": 9
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 4.097072601318359,
      "learning_rate": 9.979871469976197e-06,
      "loss": 0.8734,
      "step": 10
    },
    {
      "epoch": 0.4217252396166134,
      "grad_norm": 2.9042553901672363,
      "learning_rate": 9.954748808839675e-06,
      "loss": 0.799,
      "step": 11
    },
    {
      "epoch": 0.46006389776357826,
      "grad_norm": 2.2866175174713135,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.7953,
      "step": 12
    },
    {
      "epoch": 0.4984025559105431,
      "grad_norm": 1.9496941566467285,
      "learning_rate": 9.874639560909118e-06,
      "loss": 0.8545,
      "step": 13
    },
    {
      "epoch": 0.536741214057508,
      "grad_norm": 1.6259281635284424,
      "learning_rate": 9.819814303479268e-06,
      "loss": 0.8282,
      "step": 14
    },
    {
      "epoch": 0.5750798722044729,
      "grad_norm": 1.4897539615631104,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.8204,
      "step": 15
    },
    {
      "epoch": 0.6134185303514377,
      "grad_norm": 1.2102625370025635,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.7118,
      "step": 16
    },
    {
      "epoch": 0.6517571884984026,
      "grad_norm": 1.174496054649353,
      "learning_rate": 9.597638862757255e-06,
      "loss": 0.7225,
      "step": 17
    },
    {
      "epoch": 0.6900958466453674,
      "grad_norm": 0.9705604910850525,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.7826,
      "step": 18
    },
    {
      "epoch": 0.7284345047923323,
      "grad_norm": 0.8558895587921143,
      "learning_rate": 9.40297765928369e-06,
      "loss": 0.6528,
      "step": 19
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 1.1361898183822632,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.7468,
      "step": 20
    },
    {
      "epoch": 0.805111821086262,
      "grad_norm": 0.9566231966018677,
      "learning_rate": 9.172866268606514e-06,
      "loss": 0.7835,
      "step": 21
    },
    {
      "epoch": 0.8434504792332268,
      "grad_norm": 0.799024224281311,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.7201,
      "step": 22
    },
    {
      "epoch": 0.8817891373801917,
      "grad_norm": 0.9119431376457214,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.7316,
      "step": 23
    },
    {
      "epoch": 0.9201277955271565,
      "grad_norm": 0.9676729440689087,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.7309,
      "step": 24
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 0.8352231979370117,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.7387,
      "step": 25
    },
    {
      "epoch": 0.9968051118210862,
      "grad_norm": 0.7437606453895569,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.6776,
      "step": 26
    },
    {
      "epoch": 1.035143769968051,
      "grad_norm": 1.8444374799728394,
      "learning_rate": 8.289693629698564e-06,
      "loss": 1.3068,
      "step": 27
    },
    {
      "epoch": 1.073482428115016,
      "grad_norm": 0.7973372936248779,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.7039,
      "step": 28
    },
    {
      "epoch": 1.1118210862619808,
      "grad_norm": 0.6874552369117737,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.6564,
      "step": 29
    },
    {
      "epoch": 1.1501597444089458,
      "grad_norm": 0.791155219078064,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.7544,
      "step": 30
    },
    {
      "epoch": 1.1884984025559104,
      "grad_norm": 0.650628387928009,
      "learning_rate": 7.564496387029532e-06,
      "loss": 0.6084,
      "step": 31
    },
    {
      "epoch": 1.2268370607028753,
      "grad_norm": 0.7958367466926575,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.7656,
      "step": 32
    },
    {
      "epoch": 1.2651757188498403,
      "grad_norm": 0.5882742404937744,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.6485,
      "step": 33
    },
    {
      "epoch": 1.3035143769968052,
      "grad_norm": 0.6747470498085022,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.6833,
      "step": 34
    },
    {
      "epoch": 1.34185303514377,
      "grad_norm": 0.7728204727172852,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.7012,
      "step": 35
    },
    {
      "epoch": 1.3801916932907348,
      "grad_norm": 0.7125829458236694,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.7188,
      "step": 36
    },
    {
      "epoch": 1.4185303514376997,
      "grad_norm": 0.5703654885292053,
      "learning_rate": 6.330184227833376e-06,
      "loss": 0.6263,
      "step": 37
    },
    {
      "epoch": 1.4568690095846646,
      "grad_norm": 0.6992270946502686,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.7023,
      "step": 38
    },
    {
      "epoch": 1.4952076677316293,
      "grad_norm": 0.6634102463722229,
      "learning_rate": 5.892784473993184e-06,
      "loss": 0.7389,
      "step": 39
    },
    {
      "epoch": 1.5335463258785942,
      "grad_norm": 0.5911535024642944,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.5946,
      "step": 40
    },
    {
      "epoch": 1.571884984025559,
      "grad_norm": 0.5847533941268921,
      "learning_rate": 5.448196544517168e-06,
      "loss": 0.6093,
      "step": 41
    },
    {
      "epoch": 1.610223642172524,
      "grad_norm": 0.6068536043167114,
      "learning_rate": 5.224324151752575e-06,
      "loss": 0.7004,
      "step": 42
    },
    {
      "epoch": 1.648562300319489,
      "grad_norm": 0.6313533782958984,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 43
    },
    {
      "epoch": 1.6869009584664538,
      "grad_norm": 0.5607591271400452,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.6507,
      "step": 44
    },
    {
      "epoch": 1.7252396166134185,
      "grad_norm": 0.5534031987190247,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.6537,
      "step": 45
    },
    {
      "epoch": 1.7635782747603834,
      "grad_norm": 0.7338098287582397,
      "learning_rate": 4.3288336709117246e-06,
      "loss": 0.6759,
      "step": 46
    },
    {
      "epoch": 1.8019169329073481,
      "grad_norm": 0.5336121916770935,
      "learning_rate": 4.107215526006818e-06,
      "loss": 0.6291,
      "step": 47
    },
    {
      "epoch": 1.840255591054313,
      "grad_norm": 0.5626507997512817,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.7169,
      "step": 48
    },
    {
      "epoch": 1.878594249201278,
      "grad_norm": 0.5214377641677856,
      "learning_rate": 3.669815772166625e-06,
      "loss": 0.6841,
      "step": 49
    },
    {
      "epoch": 1.9169329073482428,
      "grad_norm": 0.5888833999633789,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.6188,
      "step": 50
    },
    {
      "epoch": 1.9552715654952078,
      "grad_norm": 0.6187015175819397,
      "learning_rate": 3.2431258795932863e-06,
      "loss": 0.6847,
      "step": 51
    },
    {
      "epoch": 1.9936102236421727,
      "grad_norm": 0.5085355043411255,
      "learning_rate": 3.0348748417303826e-06,
      "loss": 0.6988,
      "step": 52
    },
    {
      "epoch": 2.0319488817891376,
      "grad_norm": 1.593553066253662,
      "learning_rate": 2.83058130441221e-06,
      "loss": 0.9038,
      "step": 53
    },
    {
      "epoch": 2.070287539936102,
      "grad_norm": 0.6568206548690796,
      "learning_rate": 2.6306566876350072e-06,
      "loss": 0.813,
      "step": 54
    },
    {
      "epoch": 2.108626198083067,
      "grad_norm": 0.5504679083824158,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.6436,
      "step": 55
    },
    {
      "epoch": 2.146964856230032,
      "grad_norm": 0.5460967421531677,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.6551,
      "step": 56
    },
    {
      "epoch": 2.1853035143769968,
      "grad_norm": 0.4491327404975891,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.5822,
      "step": 57
    },
    {
      "epoch": 2.2236421725239617,
      "grad_norm": 0.5268153548240662,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.5855,
      "step": 58
    },
    {
      "epoch": 2.2619808306709266,
      "grad_norm": 0.5288434028625488,
      "learning_rate": 1.7103063703014372e-06,
      "loss": 0.601,
      "step": 59
    },
    {
      "epoch": 2.3003194888178915,
      "grad_norm": 0.5175487995147705,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.6244,
      "step": 60
    },
    {
      "epoch": 2.3386581469648564,
      "grad_norm": 0.5145055651664734,
      "learning_rate": 1.3860256808630429e-06,
      "loss": 0.6623,
      "step": 61
    },
    {
      "epoch": 2.376996805111821,
      "grad_norm": 0.48586106300354004,
      "learning_rate": 1.234642669981946e-06,
      "loss": 0.6316,
      "step": 62
    },
    {
      "epoch": 2.415335463258786,
      "grad_norm": 0.47657573223114014,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.6679,
      "step": 63
    },
    {
      "epoch": 2.4536741214057507,
      "grad_norm": 0.579838216304779,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.6767,
      "step": 64
    },
    {
      "epoch": 2.4920127795527156,
      "grad_norm": 0.4816247820854187,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.584,
      "step": 65
    },
    {
      "epoch": 2.5303514376996805,
      "grad_norm": 0.3775748312473297,
      "learning_rate": 7.077560319906696e-07,
      "loss": 0.544,
      "step": 66
    },
    {
      "epoch": 2.5686900958466454,
      "grad_norm": 0.5384094715118408,
      "learning_rate": 5.9702234071631e-07,
      "loss": 0.6657,
      "step": 67
    },
    {
      "epoch": 2.6070287539936103,
      "grad_norm": 0.4351522624492645,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.6259,
      "step": 68
    },
    {
      "epoch": 2.6453674121405752,
      "grad_norm": 0.47292372584342957,
      "learning_rate": 4.0236113724274716e-07,
      "loss": 0.5954,
      "step": 69
    },
    {
      "epoch": 2.68370607028754,
      "grad_norm": 0.4936652183532715,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.6747,
      "step": 70
    },
    {
      "epoch": 2.722044728434505,
      "grad_norm": 0.4379514753818512,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.5837,
      "step": 71
    },
    {
      "epoch": 2.7603833865814695,
      "grad_norm": 0.4948698580265045,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.6162,
      "step": 72
    },
    {
      "epoch": 2.7987220447284344,
      "grad_norm": 0.46995505690574646,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.6017,
      "step": 73
    },
    {
      "epoch": 2.8370607028753994,
      "grad_norm": 0.5322490334510803,
      "learning_rate": 8.035205700685167e-08,
      "loss": 0.6607,
      "step": 74
    },
    {
      "epoch": 2.8753993610223643,
      "grad_norm": 0.4294443428516388,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.636,
      "step": 75
    },
    {
      "epoch": 2.913738019169329,
      "grad_norm": 0.4481096863746643,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.6001,
      "step": 76
    },
    {
      "epoch": 2.952076677316294,
      "grad_norm": 0.4829566478729248,
      "learning_rate": 5.034667293427053e-09,
      "loss": 0.6874,
      "step": 77
    },
    {
      "epoch": 2.9904153354632586,
      "grad_norm": 0.42941945791244507,
      "learning_rate": 0.0,
      "loss": 0.5749,
      "step": 78
    },
    {
      "epoch": 2.9904153354632586,
      "step": 78,
      "total_flos": 50642230919168.0,
      "train_loss": 0.7231000386751615,
      "train_runtime": 6151.5481,
      "train_samples_per_second": 1.219,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 78,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 50642230919168.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}