{
  "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": 7.037278175354004,
      "learning_rate": 1.25e-06,
      "loss": 1.2319,
      "step": 1
    },
    {
      "epoch": 0.07667731629392971,
      "grad_norm": 6.708124160766602,
      "learning_rate": 2.5e-06,
      "loss": 1.2411,
      "step": 2
    },
    {
      "epoch": 0.11501597444089456,
      "grad_norm": 6.743295192718506,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.2482,
      "step": 3
    },
    {
      "epoch": 0.15335463258785942,
      "grad_norm": 5.96616792678833,
      "learning_rate": 5e-06,
      "loss": 1.1939,
      "step": 4
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 4.493274688720703,
      "learning_rate": 6.25e-06,
      "loss": 1.1718,
      "step": 5
    },
    {
      "epoch": 0.23003194888178913,
      "grad_norm": 2.7944629192352295,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1475,
      "step": 6
    },
    {
      "epoch": 0.268370607028754,
      "grad_norm": 5.779400825500488,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.1467,
      "step": 7
    },
    {
      "epoch": 0.30670926517571884,
      "grad_norm": 5.755585670471191,
      "learning_rate": 1e-05,
      "loss": 1.1438,
      "step": 8
    },
    {
      "epoch": 0.3450479233226837,
      "grad_norm": 5.320728302001953,
      "learning_rate": 9.994965332706574e-06,
      "loss": 1.0984,
      "step": 9
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 5.437542915344238,
      "learning_rate": 9.979871469976197e-06,
      "loss": 1.1075,
      "step": 10
    },
    {
      "epoch": 0.4217252396166134,
      "grad_norm": 3.694889783859253,
      "learning_rate": 9.954748808839675e-06,
      "loss": 1.091,
      "step": 11
    },
    {
      "epoch": 0.46006389776357826,
      "grad_norm": 2.2280046939849854,
      "learning_rate": 9.91964794299315e-06,
      "loss": 1.0743,
      "step": 12
    },
    {
      "epoch": 0.4984025559105431,
      "grad_norm": 2.301802635192871,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.0347,
      "step": 13
    },
    {
      "epoch": 0.536741214057508,
      "grad_norm": 1.8430911302566528,
      "learning_rate": 9.819814303479268e-06,
      "loss": 0.9834,
      "step": 14
    },
    {
      "epoch": 0.5750798722044729,
      "grad_norm": 1.2682379484176636,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.962,
      "step": 15
    },
    {
      "epoch": 0.6134185303514377,
      "grad_norm": 1.1230387687683105,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.9627,
      "step": 16
    },
    {
      "epoch": 0.6517571884984026,
      "grad_norm": 1.1826258897781372,
      "learning_rate": 9.597638862757255e-06,
      "loss": 0.9564,
      "step": 17
    },
    {
      "epoch": 0.6900958466453674,
      "grad_norm": 1.229060411453247,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.9779,
      "step": 18
    },
    {
      "epoch": 0.7284345047923323,
      "grad_norm": 0.948596179485321,
      "learning_rate": 9.40297765928369e-06,
      "loss": 0.9654,
      "step": 19
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 1.1174476146697998,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.9196,
      "step": 20
    },
    {
      "epoch": 0.805111821086262,
      "grad_norm": 1.1104681491851807,
      "learning_rate": 9.172866268606514e-06,
      "loss": 0.9197,
      "step": 21
    },
    {
      "epoch": 0.8434504792332268,
      "grad_norm": 1.2027409076690674,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.9444,
      "step": 22
    },
    {
      "epoch": 0.8817891373801917,
      "grad_norm": 1.2598828077316284,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.98,
      "step": 23
    },
    {
      "epoch": 0.9201277955271565,
      "grad_norm": 0.8814008831977844,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.928,
      "step": 24
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 0.9681753516197205,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.9868,
      "step": 25
    },
    {
      "epoch": 0.9968051118210862,
      "grad_norm": 1.181720495223999,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.9477,
      "step": 26
    },
    {
      "epoch": 1.035143769968051,
      "grad_norm": 2.375579357147217,
      "learning_rate": 8.289693629698564e-06,
      "loss": 1.5598,
      "step": 27
    },
    {
      "epoch": 1.073482428115016,
      "grad_norm": 0.8964683413505554,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.8733,
      "step": 28
    },
    {
      "epoch": 1.1118210862619808,
      "grad_norm": 0.9166988730430603,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.9163,
      "step": 29
    },
    {
      "epoch": 1.1501597444089458,
      "grad_norm": 1.0348312854766846,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.9485,
      "step": 30
    },
    {
      "epoch": 1.1884984025559104,
      "grad_norm": 0.8942492008209229,
      "learning_rate": 7.564496387029532e-06,
      "loss": 0.8937,
      "step": 31
    },
    {
      "epoch": 1.2268370607028753,
      "grad_norm": 0.8508261442184448,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.894,
      "step": 32
    },
    {
      "epoch": 1.2651757188498403,
      "grad_norm": 0.7349827885627747,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.924,
      "step": 33
    },
    {
      "epoch": 1.3035143769968052,
      "grad_norm": 0.797027051448822,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.8593,
      "step": 34
    },
    {
      "epoch": 1.34185303514377,
      "grad_norm": 0.8137903809547424,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.8627,
      "step": 35
    },
    {
      "epoch": 1.3801916932907348,
      "grad_norm": 0.7105099558830261,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.8712,
      "step": 36
    },
    {
      "epoch": 1.4185303514376997,
      "grad_norm": 0.6708528995513916,
      "learning_rate": 6.330184227833376e-06,
      "loss": 0.8984,
      "step": 37
    },
    {
      "epoch": 1.4568690095846646,
      "grad_norm": 0.6093773245811462,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.8588,
      "step": 38
    },
    {
      "epoch": 1.4952076677316293,
      "grad_norm": 0.6303824186325073,
      "learning_rate": 5.892784473993184e-06,
      "loss": 0.9026,
      "step": 39
    },
    {
      "epoch": 1.5335463258785942,
      "grad_norm": 0.6594157218933105,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.8586,
      "step": 40
    },
    {
      "epoch": 1.571884984025559,
      "grad_norm": 0.6607796549797058,
      "learning_rate": 5.448196544517168e-06,
      "loss": 0.8117,
      "step": 41
    },
    {
      "epoch": 1.610223642172524,
      "grad_norm": 0.590767502784729,
      "learning_rate": 5.224324151752575e-06,
      "loss": 0.8858,
      "step": 42
    },
    {
      "epoch": 1.648562300319489,
      "grad_norm": 0.5660220384597778,
      "learning_rate": 5e-06,
      "loss": 0.8353,
      "step": 43
    },
    {
      "epoch": 1.6869009584664538,
      "grad_norm": 0.5475494861602783,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.8308,
      "step": 44
    },
    {
      "epoch": 1.7252396166134185,
      "grad_norm": 0.5573390126228333,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.8464,
      "step": 45
    },
    {
      "epoch": 1.7635782747603834,
      "grad_norm": 0.5183398723602295,
      "learning_rate": 4.3288336709117246e-06,
      "loss": 0.8905,
      "step": 46
    },
    {
      "epoch": 1.8019169329073481,
      "grad_norm": 0.6313608288764954,
      "learning_rate": 4.107215526006818e-06,
      "loss": 0.9465,
      "step": 47
    },
    {
      "epoch": 1.840255591054313,
      "grad_norm": 0.576272189617157,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.7775,
      "step": 48
    },
    {
      "epoch": 1.878594249201278,
      "grad_norm": 0.651371419429779,
      "learning_rate": 3.669815772166625e-06,
      "loss": 0.8888,
      "step": 49
    },
    {
      "epoch": 1.9169329073482428,
      "grad_norm": 0.5718173384666443,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.8844,
      "step": 50
    },
    {
      "epoch": 1.9552715654952078,
      "grad_norm": 0.4762439727783203,
      "learning_rate": 3.2431258795932863e-06,
      "loss": 0.8484,
      "step": 51
    },
    {
      "epoch": 1.9936102236421727,
      "grad_norm": 0.5076062679290771,
      "learning_rate": 3.0348748417303826e-06,
      "loss": 0.8936,
      "step": 52
    },
    {
      "epoch": 2.0319488817891376,
      "grad_norm": 1.8401753902435303,
      "learning_rate": 2.83058130441221e-06,
      "loss": 1.5562,
      "step": 53
    },
    {
      "epoch": 2.070287539936102,
      "grad_norm": 0.4500599205493927,
      "learning_rate": 2.6306566876350072e-06,
      "loss": 0.7651,
      "step": 54
    },
    {
      "epoch": 2.108626198083067,
      "grad_norm": 0.4810475707054138,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.8988,
      "step": 55
    },
    {
      "epoch": 2.146964856230032,
      "grad_norm": 0.5080612301826477,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.8234,
      "step": 56
    },
    {
      "epoch": 2.1853035143769968,
      "grad_norm": 0.6019585132598877,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.8461,
      "step": 57
    },
    {
      "epoch": 2.2236421725239617,
      "grad_norm": 0.4502711296081543,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.7693,
      "step": 58
    },
    {
      "epoch": 2.2619808306709266,
      "grad_norm": 0.5242336392402649,
      "learning_rate": 1.7103063703014372e-06,
      "loss": 0.9397,
      "step": 59
    },
    {
      "epoch": 2.3003194888178915,
      "grad_norm": 0.4489525258541107,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.8213,
      "step": 60
    },
    {
      "epoch": 2.3386581469648564,
      "grad_norm": 0.43693825602531433,
      "learning_rate": 1.3860256808630429e-06,
      "loss": 0.8128,
      "step": 61
    },
    {
      "epoch": 2.376996805111821,
      "grad_norm": 0.4453686773777008,
      "learning_rate": 1.234642669981946e-06,
      "loss": 0.844,
      "step": 62
    },
    {
      "epoch": 2.415335463258786,
      "grad_norm": 0.44349491596221924,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.8105,
      "step": 63
    },
    {
      "epoch": 2.4536741214057507,
      "grad_norm": 0.4361194372177124,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.7351,
      "step": 64
    },
    {
      "epoch": 2.4920127795527156,
      "grad_norm": 0.5383359789848328,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.8991,
      "step": 65
    },
    {
      "epoch": 2.5303514376996805,
      "grad_norm": 0.4292016923427582,
      "learning_rate": 7.077560319906696e-07,
      "loss": 0.7968,
      "step": 66
    },
    {
      "epoch": 2.5686900958466454,
      "grad_norm": 0.44161736965179443,
      "learning_rate": 5.9702234071631e-07,
      "loss": 0.8126,
      "step": 67
    },
    {
      "epoch": 2.6070287539936103,
      "grad_norm": 0.45729973912239075,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.7749,
      "step": 68
    },
    {
      "epoch": 2.6453674121405752,
      "grad_norm": 0.4838651120662689,
      "learning_rate": 4.0236113724274716e-07,
      "loss": 0.8785,
      "step": 69
    },
    {
      "epoch": 2.68370607028754,
      "grad_norm": 0.41112348437309265,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.8036,
      "step": 70
    },
    {
      "epoch": 2.722044728434505,
      "grad_norm": 0.43668246269226074,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.877,
      "step": 71
    },
    {
      "epoch": 2.7603833865814695,
      "grad_norm": 0.40545573830604553,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.8163,
      "step": 72
    },
    {
      "epoch": 2.7987220447284344,
      "grad_norm": 0.44029009342193604,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.8399,
      "step": 73
    },
    {
      "epoch": 2.8370607028753994,
      "grad_norm": 0.3983535170555115,
      "learning_rate": 8.035205700685167e-08,
      "loss": 0.7787,
      "step": 74
    },
    {
      "epoch": 2.8753993610223643,
      "grad_norm": 0.45925256609916687,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.8863,
      "step": 75
    },
    {
      "epoch": 2.913738019169329,
      "grad_norm": 0.3907840847969055,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.8601,
      "step": 76
    },
    {
      "epoch": 2.952076677316294,
      "grad_norm": 0.4407999813556671,
      "learning_rate": 5.034667293427053e-09,
      "loss": 0.7761,
      "step": 77
    },
    {
      "epoch": 2.9904153354632586,
      "grad_norm": 0.3897060751914978,
      "learning_rate": 0.0,
      "loss": 0.8033,
      "step": 78
    },
    {
      "epoch": 2.9904153354632586,
      "step": 78,
      "total_flos": 81292061122560.0,
      "train_loss": 0.936553975710502,
      "train_runtime": 7850.0328,
      "train_samples_per_second": 0.955,
      "train_steps_per_second": 0.01
    }
  ],
  "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": 81292061122560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}