{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 56,
  "global_step": 56,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 2.694387197494507,
      "learning_rate": 1e-05,
      "loss": 2.857421875,
      "step": 1
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 2.558368682861328,
      "learning_rate": 9.992134075089085e-06,
      "loss": 2.81640625,
      "step": 2
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 2.3488693237304688,
      "learning_rate": 9.968561049466214e-06,
      "loss": 2.681640625,
      "step": 3
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.1087405681610107,
      "learning_rate": 9.92935509259118e-06,
      "loss": 2.544921875,
      "step": 4
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 1.6803760528564453,
      "learning_rate": 9.874639560909118e-06,
      "loss": 2.330078125,
      "step": 5
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.655576229095459,
      "learning_rate": 9.804586609725499e-06,
      "loss": 2.263671875,
      "step": 6
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.5180833339691162,
      "learning_rate": 9.719416651541839e-06,
      "loss": 2.1240234375,
      "step": 7
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.6885188817977905,
      "learning_rate": 9.619397662556434e-06,
      "loss": 2.09814453125,
      "step": 8
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 1.3130377531051636,
      "learning_rate": 9.504844339512096e-06,
      "loss": 1.8671875,
      "step": 9
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.7923501133918762,
      "learning_rate": 9.376117109543769e-06,
      "loss": 1.8203125,
      "step": 10
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.6045828461647034,
      "learning_rate": 9.233620996141421e-06,
      "loss": 1.775390625,
      "step": 11
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.509148895740509,
      "learning_rate": 9.077804344796302e-06,
      "loss": 1.7275390625,
      "step": 12
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.5257807970046997,
      "learning_rate": 8.90915741234015e-06,
      "loss": 1.7373046875,
      "step": 13
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5001201629638672,
      "learning_rate": 8.728210824415829e-06,
      "loss": 1.708984375,
      "step": 14
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.4635830819606781,
      "learning_rate": 8.535533905932739e-06,
      "loss": 1.6552734375,
      "step": 15
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.36223411560058594,
      "learning_rate": 8.331732889760021e-06,
      "loss": 1.666015625,
      "step": 16
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.392349511384964,
      "learning_rate": 8.117449009293668e-06,
      "loss": 1.61328125,
      "step": 17
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.3374916911125183,
      "learning_rate": 7.89335648089903e-06,
      "loss": 1.595703125,
      "step": 18
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.2974811792373657,
      "learning_rate": 7.660160382576683e-06,
      "loss": 1.57421875,
      "step": 19
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.30373185873031616,
      "learning_rate": 7.4185944355261996e-06,
      "loss": 1.546875,
      "step": 20
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3105020821094513,
      "learning_rate": 7.169418695587791e-06,
      "loss": 1.513671875,
      "step": 21
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.33336368203163147,
      "learning_rate": 6.913417161825449e-06,
      "loss": 1.5361328125,
      "step": 22
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.3261295557022095,
      "learning_rate": 6.651395309775837e-06,
      "loss": 1.4931640625,
      "step": 23
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3157199025154114,
      "learning_rate": 6.384177557124247e-06,
      "loss": 1.48779296875,
      "step": 24
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.3149335980415344,
      "learning_rate": 6.112604669781572e-06,
      "loss": 1.46875,
      "step": 25
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.3011397421360016,
      "learning_rate": 5.837531116523683e-06,
      "loss": 1.4775390625,
      "step": 26
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.3071064054965973,
      "learning_rate": 5.559822380516539e-06,
      "loss": 1.44921875,
      "step": 27
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.29467642307281494,
      "learning_rate": 5.2803522361859596e-06,
      "loss": 1.44091796875,
      "step": 28
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 0.3383062481880188,
      "learning_rate": 5e-06,
      "loss": 1.4287109375,
      "step": 29
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.3466164469718933,
      "learning_rate": 4.719647763814041e-06,
      "loss": 1.4345703125,
      "step": 30
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 0.33726248145103455,
      "learning_rate": 4.4401776194834615e-06,
      "loss": 1.4052734375,
      "step": 31
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.36348649859428406,
      "learning_rate": 4.162468883476319e-06,
      "loss": 1.35693359375,
      "step": 32
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 0.31096431612968445,
      "learning_rate": 3.887395330218429e-06,
      "loss": 1.38671875,
      "step": 33
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.3586256802082062,
      "learning_rate": 3.6158224428757538e-06,
      "loss": 1.3544921875,
      "step": 34
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.3652304708957672,
      "learning_rate": 3.3486046902241663e-06,
      "loss": 1.37890625,
      "step": 35
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.4301171600818634,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 1.39013671875,
      "step": 36
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 0.38166680932044983,
      "learning_rate": 2.83058130441221e-06,
      "loss": 1.357421875,
      "step": 37
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.3681507706642151,
      "learning_rate": 2.5814055644738013e-06,
      "loss": 1.3408203125,
      "step": 38
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 0.34061020612716675,
      "learning_rate": 2.339839617423318e-06,
      "loss": 1.341796875,
      "step": 39
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.2774454951286316,
      "learning_rate": 2.1066435191009717e-06,
      "loss": 1.3369140625,
      "step": 40
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 0.2526361346244812,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 1.34423828125,
      "step": 41
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.24453622102737427,
      "learning_rate": 1.6682671102399806e-06,
      "loss": 1.3115234375,
      "step": 42
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 0.2164342850446701,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 1.28076171875,
      "step": 43
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.19291897118091583,
      "learning_rate": 1.2717891755841722e-06,
      "loss": 1.359375,
      "step": 44
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.21438544988632202,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 1.2685546875,
      "step": 45
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.1777007132768631,
      "learning_rate": 9.221956552036992e-07,
      "loss": 1.296875,
      "step": 46
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 0.16975992918014526,
      "learning_rate": 7.663790038585794e-07,
      "loss": 1.3310546875,
      "step": 47
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.15860167145729065,
      "learning_rate": 6.238828904562316e-07,
      "loss": 1.30859375,
      "step": 48
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.1576526165008545,
      "learning_rate": 4.951556604879049e-07,
      "loss": 1.29052734375,
      "step": 49
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.16139984130859375,
      "learning_rate": 3.8060233744356634e-07,
      "loss": 1.3203125,
      "step": 50
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.15369921922683716,
      "learning_rate": 2.8058334845816214e-07,
      "loss": 1.2919921875,
      "step": 51
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.1540217250585556,
      "learning_rate": 1.9541339027450256e-07,
      "loss": 1.3134765625,
      "step": 52
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 0.14983929693698883,
      "learning_rate": 1.253604390908819e-07,
      "loss": 1.310546875,
      "step": 53
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.14664843678474426,
      "learning_rate": 7.064490740882057e-08,
      "loss": 1.33740234375,
      "step": 54
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.1502656489610672,
      "learning_rate": 3.143895053378698e-08,
      "loss": 1.3173828125,
      "step": 55
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.154768168926239,
      "learning_rate": 7.865924910916977e-09,
      "loss": 1.3291015625,
      "step": 56
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.3828125,
      "eval_runtime": 1.0297,
      "eval_samples_per_second": 9.712,
      "eval_steps_per_second": 0.971,
      "step": 56
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 56,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0007198831025848e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}