{
  "best_metric": 1.1611876487731934,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.684931506849315,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0136986301369863,
      "grad_norm": 2.3104567527770996,
      "learning_rate": 1e-05,
      "loss": 2.6772,
      "step": 1
    },
    {
      "epoch": 0.0136986301369863,
      "eval_loss": 2.6535723209381104,
      "eval_runtime": 17.3303,
      "eval_samples_per_second": 7.097,
      "eval_steps_per_second": 1.789,
      "step": 1
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 2.2860801219940186,
      "learning_rate": 2e-05,
      "loss": 2.5427,
      "step": 2
    },
    {
      "epoch": 0.0410958904109589,
      "grad_norm": 2.4849393367767334,
      "learning_rate": 3e-05,
      "loss": 2.6223,
      "step": 3
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 1.9940364360809326,
      "learning_rate": 4e-05,
      "loss": 2.4287,
      "step": 4
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 1.7210477590560913,
      "learning_rate": 5e-05,
      "loss": 2.3605,
      "step": 5
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 1.2044246196746826,
      "learning_rate": 6e-05,
      "loss": 2.2256,
      "step": 6
    },
    {
      "epoch": 0.0958904109589041,
      "grad_norm": 0.7198757529258728,
      "learning_rate": 7e-05,
      "loss": 2.0664,
      "step": 7
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.5114027261734009,
      "learning_rate": 8e-05,
      "loss": 2.2381,
      "step": 8
    },
    {
      "epoch": 0.1232876712328767,
      "grad_norm": 0.6468356251716614,
      "learning_rate": 9e-05,
      "loss": 2.0742,
      "step": 9
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.6318015456199646,
      "learning_rate": 0.0001,
      "loss": 1.9805,
      "step": 10
    },
    {
      "epoch": 0.1506849315068493,
      "grad_norm": 0.7080933451652527,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.9232,
      "step": 11
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.6762998104095459,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.9994,
      "step": 12
    },
    {
      "epoch": 0.1780821917808219,
      "grad_norm": 0.6594786047935486,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.9786,
      "step": 13
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.5222786664962769,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6868,
      "step": 14
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.58636075258255,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8013,
      "step": 15
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.6786454916000366,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.9422,
      "step": 16
    },
    {
      "epoch": 0.2328767123287671,
      "grad_norm": 0.698627769947052,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.8039,
      "step": 17
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.8333738446235657,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7332,
      "step": 18
    },
    {
      "epoch": 0.2602739726027397,
      "grad_norm": 0.5399659276008606,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6334,
      "step": 19
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.5942010879516602,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5734,
      "step": 20
    },
    {
      "epoch": 0.2876712328767123,
      "grad_norm": 0.5469406843185425,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4613,
      "step": 21
    },
    {
      "epoch": 0.3013698630136986,
      "grad_norm": 0.461607426404953,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.5705,
      "step": 22
    },
    {
      "epoch": 0.3150684931506849,
      "grad_norm": 0.48899999260902405,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4752,
      "step": 23
    },
    {
      "epoch": 0.3287671232876712,
      "grad_norm": 0.4735804796218872,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5224,
      "step": 24
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.46453773975372314,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.4607,
      "step": 25
    },
    {
      "epoch": 0.3561643835616438,
      "grad_norm": 0.5345879197120667,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2636,
      "step": 26
    },
    {
      "epoch": 0.3698630136986301,
      "grad_norm": 0.47283685207366943,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4447,
      "step": 27
    },
    {
      "epoch": 0.3835616438356164,
      "grad_norm": 0.46636468172073364,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.4252,
      "step": 28
    },
    {
      "epoch": 0.3972602739726027,
      "grad_norm": 0.5225064158439636,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3312,
      "step": 29
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.5501663684844971,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.2208,
      "step": 30
    },
    {
      "epoch": 0.4246575342465753,
      "grad_norm": 0.566003680229187,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.369,
      "step": 31
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.5202441215515137,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2976,
      "step": 32
    },
    {
      "epoch": 0.4520547945205479,
      "grad_norm": 0.518156886100769,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2891,
      "step": 33
    },
    {
      "epoch": 0.4657534246575342,
      "grad_norm": 0.6312072277069092,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2836,
      "step": 34
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.6018211841583252,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3762,
      "step": 35
    },
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.7894740104675293,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3325,
      "step": 36
    },
    {
      "epoch": 0.5068493150684932,
      "grad_norm": 0.5007014870643616,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.3137,
      "step": 37
    },
    {
      "epoch": 0.5205479452054794,
      "grad_norm": 0.4664342403411865,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2576,
      "step": 38
    },
    {
      "epoch": 0.5342465753424658,
      "grad_norm": 0.5222160816192627,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.2053,
      "step": 39
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.45446133613586426,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1862,
      "step": 40
    },
    {
      "epoch": 0.5616438356164384,
      "grad_norm": 0.5213246941566467,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1884,
      "step": 41
    },
    {
      "epoch": 0.5753424657534246,
      "grad_norm": 0.4332996904850006,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2503,
      "step": 42
    },
    {
      "epoch": 0.589041095890411,
      "grad_norm": 0.45690229535102844,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.2862,
      "step": 43
    },
    {
      "epoch": 0.6027397260273972,
      "grad_norm": 0.4400925040245056,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1974,
      "step": 44
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.39044520258903503,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0507,
      "step": 45
    },
    {
      "epoch": 0.6301369863013698,
      "grad_norm": 0.4855286180973053,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.0906,
      "step": 46
    },
    {
      "epoch": 0.6438356164383562,
      "grad_norm": 0.4984034597873688,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2483,
      "step": 47
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.44656309485435486,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1795,
      "step": 48
    },
    {
      "epoch": 0.6712328767123288,
      "grad_norm": 0.4836941659450531,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1595,
      "step": 49
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.4639911949634552,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0114,
      "step": 50
    },
    {
      "epoch": 0.684931506849315,
      "eval_loss": 1.1611876487731934,
      "eval_runtime": 17.7314,
      "eval_samples_per_second": 6.937,
      "eval_steps_per_second": 1.748,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3898961899225088e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}