{
  "best_metric": 2.246959686279297,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0013698817792024548,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7397635584049098e-05,
      "grad_norm": 17.083011627197266,
      "learning_rate": 1.0110000000000001e-05,
      "loss": 3.6833,
      "step": 1
    },
    {
      "epoch": 2.7397635584049098e-05,
      "eval_loss": 5.066332817077637,
      "eval_runtime": 907.7509,
      "eval_samples_per_second": 16.931,
      "eval_steps_per_second": 4.234,
      "step": 1
    },
    {
      "epoch": 5.4795271168098196e-05,
      "grad_norm": 30.948528289794922,
      "learning_rate": 2.0220000000000003e-05,
      "loss": 5.5955,
      "step": 2
    },
    {
      "epoch": 8.219290675214729e-05,
      "grad_norm": 24.4798641204834,
      "learning_rate": 3.033e-05,
      "loss": 5.2317,
      "step": 3
    },
    {
      "epoch": 0.00010959054233619639,
      "grad_norm": 26.41942596435547,
      "learning_rate": 4.0440000000000006e-05,
      "loss": 6.3092,
      "step": 4
    },
    {
      "epoch": 0.00013698817792024548,
      "grad_norm": 31.87883949279785,
      "learning_rate": 5.055e-05,
      "loss": 5.9147,
      "step": 5
    },
    {
      "epoch": 0.00016438581350429457,
      "grad_norm": 33.11574172973633,
      "learning_rate": 6.066e-05,
      "loss": 6.6052,
      "step": 6
    },
    {
      "epoch": 0.00019178344908834366,
      "grad_norm": 21.89510726928711,
      "learning_rate": 7.077e-05,
      "loss": 4.7486,
      "step": 7
    },
    {
      "epoch": 0.00021918108467239278,
      "grad_norm": 20.02174949645996,
      "learning_rate": 8.088000000000001e-05,
      "loss": 3.4227,
      "step": 8
    },
    {
      "epoch": 0.00024657872025644185,
      "grad_norm": 19.635520935058594,
      "learning_rate": 9.099000000000001e-05,
      "loss": 3.8081,
      "step": 9
    },
    {
      "epoch": 0.00027397635584049096,
      "grad_norm": 23.233644485473633,
      "learning_rate": 0.0001011,
      "loss": 3.0193,
      "step": 10
    },
    {
      "epoch": 0.0003013739914245401,
      "grad_norm": 22.40667724609375,
      "learning_rate": 0.00010056789473684211,
      "loss": 2.9783,
      "step": 11
    },
    {
      "epoch": 0.00032877162700858915,
      "grad_norm": 15.5116548538208,
      "learning_rate": 0.00010003578947368421,
      "loss": 2.7802,
      "step": 12
    },
    {
      "epoch": 0.00035616926259263826,
      "grad_norm": 12.772533416748047,
      "learning_rate": 9.950368421052632e-05,
      "loss": 2.3746,
      "step": 13
    },
    {
      "epoch": 0.00038356689817668733,
      "grad_norm": 12.892407417297363,
      "learning_rate": 9.897157894736842e-05,
      "loss": 1.5691,
      "step": 14
    },
    {
      "epoch": 0.00041096453376073645,
      "grad_norm": 12.087071418762207,
      "learning_rate": 9.843947368421053e-05,
      "loss": 1.8777,
      "step": 15
    },
    {
      "epoch": 0.00043836216934478556,
      "grad_norm": 19.26116943359375,
      "learning_rate": 9.790736842105264e-05,
      "loss": 2.8353,
      "step": 16
    },
    {
      "epoch": 0.00046575980492883463,
      "grad_norm": 11.111328125,
      "learning_rate": 9.737526315789474e-05,
      "loss": 1.8071,
      "step": 17
    },
    {
      "epoch": 0.0004931574405128837,
      "grad_norm": 12.628350257873535,
      "learning_rate": 9.684315789473684e-05,
      "loss": 2.1004,
      "step": 18
    },
    {
      "epoch": 0.0005205550760969328,
      "grad_norm": 14.211240768432617,
      "learning_rate": 9.631105263157895e-05,
      "loss": 2.2592,
      "step": 19
    },
    {
      "epoch": 0.0005479527116809819,
      "grad_norm": 15.376936912536621,
      "learning_rate": 9.577894736842105e-05,
      "loss": 1.8852,
      "step": 20
    },
    {
      "epoch": 0.000575350347265031,
      "grad_norm": 12.521246910095215,
      "learning_rate": 9.524684210526317e-05,
      "loss": 2.0885,
      "step": 21
    },
    {
      "epoch": 0.0006027479828490802,
      "grad_norm": 13.282447814941406,
      "learning_rate": 9.471473684210526e-05,
      "loss": 2.1103,
      "step": 22
    },
    {
      "epoch": 0.0006301456184331292,
      "grad_norm": 11.5529203414917,
      "learning_rate": 9.418263157894737e-05,
      "loss": 1.9263,
      "step": 23
    },
    {
      "epoch": 0.0006575432540171783,
      "grad_norm": 11.215520858764648,
      "learning_rate": 9.365052631578948e-05,
      "loss": 1.9848,
      "step": 24
    },
    {
      "epoch": 0.0006849408896012274,
      "grad_norm": 14.77686882019043,
      "learning_rate": 9.311842105263157e-05,
      "loss": 2.4333,
      "step": 25
    },
    {
      "epoch": 0.0007123385251852765,
      "grad_norm": 12.779730796813965,
      "learning_rate": 9.258631578947368e-05,
      "loss": 2.5709,
      "step": 26
    },
    {
      "epoch": 0.0007397361607693256,
      "grad_norm": 11.351499557495117,
      "learning_rate": 9.20542105263158e-05,
      "loss": 2.2625,
      "step": 27
    },
    {
      "epoch": 0.0007671337963533747,
      "grad_norm": 13.397592544555664,
      "learning_rate": 9.15221052631579e-05,
      "loss": 2.7227,
      "step": 28
    },
    {
      "epoch": 0.0007945314319374238,
      "grad_norm": 10.616507530212402,
      "learning_rate": 9.099000000000001e-05,
      "loss": 1.8181,
      "step": 29
    },
    {
      "epoch": 0.0008219290675214729,
      "grad_norm": 11.262557983398438,
      "learning_rate": 9.045789473684212e-05,
      "loss": 1.7244,
      "step": 30
    },
    {
      "epoch": 0.000849326703105522,
      "grad_norm": 11.611719131469727,
      "learning_rate": 8.992578947368421e-05,
      "loss": 1.7876,
      "step": 31
    },
    {
      "epoch": 0.0008767243386895711,
      "grad_norm": 12.462687492370605,
      "learning_rate": 8.939368421052632e-05,
      "loss": 2.3846,
      "step": 32
    },
    {
      "epoch": 0.0009041219742736201,
      "grad_norm": 11.689743995666504,
      "learning_rate": 8.886157894736841e-05,
      "loss": 1.893,
      "step": 33
    },
    {
      "epoch": 0.0009315196098576693,
      "grad_norm": 15.821490287780762,
      "learning_rate": 8.832947368421054e-05,
      "loss": 2.277,
      "step": 34
    },
    {
      "epoch": 0.0009589172454417184,
      "grad_norm": 11.826910018920898,
      "learning_rate": 8.779736842105264e-05,
      "loss": 1.8275,
      "step": 35
    },
    {
      "epoch": 0.0009863148810257674,
      "grad_norm": 10.841914176940918,
      "learning_rate": 8.726526315789474e-05,
      "loss": 1.553,
      "step": 36
    },
    {
      "epoch": 0.0010137125166098165,
      "grad_norm": 11.523122787475586,
      "learning_rate": 8.673315789473685e-05,
      "loss": 1.9103,
      "step": 37
    },
    {
      "epoch": 0.0010411101521938656,
      "grad_norm": 11.838396072387695,
      "learning_rate": 8.620105263157896e-05,
      "loss": 1.5697,
      "step": 38
    },
    {
      "epoch": 0.0010685077877779147,
      "grad_norm": 11.571324348449707,
      "learning_rate": 8.566894736842105e-05,
      "loss": 2.0003,
      "step": 39
    },
    {
      "epoch": 0.0010959054233619639,
      "grad_norm": 10.516695022583008,
      "learning_rate": 8.513684210526316e-05,
      "loss": 1.5583,
      "step": 40
    },
    {
      "epoch": 0.001123303058946013,
      "grad_norm": 9.6254301071167,
      "learning_rate": 8.460473684210527e-05,
      "loss": 1.3097,
      "step": 41
    },
    {
      "epoch": 0.001150700694530062,
      "grad_norm": 9.205260276794434,
      "learning_rate": 8.407263157894738e-05,
      "loss": 1.32,
      "step": 42
    },
    {
      "epoch": 0.0011780983301141112,
      "grad_norm": 12.572107315063477,
      "learning_rate": 8.354052631578948e-05,
      "loss": 2.1812,
      "step": 43
    },
    {
      "epoch": 0.0012054959656981603,
      "grad_norm": 12.90071964263916,
      "learning_rate": 8.300842105263158e-05,
      "loss": 1.3577,
      "step": 44
    },
    {
      "epoch": 0.0012328936012822094,
      "grad_norm": 13.483455657958984,
      "learning_rate": 8.247631578947369e-05,
      "loss": 2.3667,
      "step": 45
    },
    {
      "epoch": 0.0012602912368662584,
      "grad_norm": 15.868042945861816,
      "learning_rate": 8.19442105263158e-05,
      "loss": 2.6061,
      "step": 46
    },
    {
      "epoch": 0.0012876888724503075,
      "grad_norm": 13.639692306518555,
      "learning_rate": 8.141210526315789e-05,
      "loss": 2.9595,
      "step": 47
    },
    {
      "epoch": 0.0013150865080343566,
      "grad_norm": 11.425675392150879,
      "learning_rate": 8.088000000000001e-05,
      "loss": 1.7875,
      "step": 48
    },
    {
      "epoch": 0.0013424841436184057,
      "grad_norm": 11.319607734680176,
      "learning_rate": 8.03478947368421e-05,
      "loss": 2.12,
      "step": 49
    },
    {
      "epoch": 0.0013698817792024548,
      "grad_norm": 13.456693649291992,
      "learning_rate": 7.981578947368421e-05,
      "loss": 1.9008,
      "step": 50
    },
    {
      "epoch": 0.0013698817792024548,
      "eval_loss": 2.246959686279297,
      "eval_runtime": 901.5117,
      "eval_samples_per_second": 17.048,
      "eval_steps_per_second": 4.263,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5721720518344704.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}