{
  "best_metric": 1.4047613143920898,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06693440428380187,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013386880856760374,
      "grad_norm": 5.007595062255859,
      "learning_rate": 2e-05,
      "loss": 2.4108,
      "step": 1
    },
    {
      "epoch": 0.0013386880856760374,
      "eval_loss": 2.537308931350708,
      "eval_runtime": 70.4596,
      "eval_samples_per_second": 17.854,
      "eval_steps_per_second": 2.242,
      "step": 1
    },
    {
      "epoch": 0.002677376171352075,
      "grad_norm": 5.144852638244629,
      "learning_rate": 4e-05,
      "loss": 2.2402,
      "step": 2
    },
    {
      "epoch": 0.004016064257028112,
      "grad_norm": 5.203696250915527,
      "learning_rate": 6e-05,
      "loss": 2.1344,
      "step": 3
    },
    {
      "epoch": 0.00535475234270415,
      "grad_norm": 2.281144142150879,
      "learning_rate": 8e-05,
      "loss": 1.1445,
      "step": 4
    },
    {
      "epoch": 0.006693440428380187,
      "grad_norm": 1.4220712184906006,
      "learning_rate": 0.0001,
      "loss": 0.628,
      "step": 5
    },
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 0.9246726632118225,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7653,
      "step": 6
    },
    {
      "epoch": 0.009370816599732263,
      "grad_norm": 1.5859125852584839,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8304,
      "step": 7
    },
    {
      "epoch": 0.0107095046854083,
      "grad_norm": 1.4083868265151978,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9531,
      "step": 8
    },
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 1.2468723058700562,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.2307,
      "step": 9
    },
    {
      "epoch": 0.013386880856760375,
      "grad_norm": 0.8629204630851746,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.2691,
      "step": 10
    },
    {
      "epoch": 0.014725568942436412,
      "grad_norm": 1.033066749572754,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6177,
      "step": 11
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 0.8808890581130981,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.491,
      "step": 12
    },
    {
      "epoch": 0.01740294511378849,
      "grad_norm": 1.1872411966323853,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.7161,
      "step": 13
    },
    {
      "epoch": 0.018741633199464525,
      "grad_norm": 1.1217893362045288,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5348,
      "step": 14
    },
    {
      "epoch": 0.020080321285140562,
      "grad_norm": 0.9734432101249695,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4112,
      "step": 15
    },
    {
      "epoch": 0.0214190093708166,
      "grad_norm": 1.0485011339187622,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1092,
      "step": 16
    },
    {
      "epoch": 0.022757697456492636,
      "grad_norm": 0.9111418128013611,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1245,
      "step": 17
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 0.9790492057800293,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.189,
      "step": 18
    },
    {
      "epoch": 0.025435073627844713,
      "grad_norm": 0.9184658527374268,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2766,
      "step": 19
    },
    {
      "epoch": 0.02677376171352075,
      "grad_norm": 0.8762655854225159,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.172,
      "step": 20
    },
    {
      "epoch": 0.028112449799196786,
      "grad_norm": 0.9275787472724915,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0542,
      "step": 21
    },
    {
      "epoch": 0.029451137884872823,
      "grad_norm": 0.887641191482544,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9658,
      "step": 22
    },
    {
      "epoch": 0.030789825970548863,
      "grad_norm": 1.038800835609436,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1708,
      "step": 23
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 1.0377554893493652,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.1809,
      "step": 24
    },
    {
      "epoch": 0.03346720214190094,
      "grad_norm": 0.9982666373252869,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0061,
      "step": 25
    },
    {
      "epoch": 0.03346720214190094,
      "eval_loss": 1.4723252058029175,
      "eval_runtime": 72.3222,
      "eval_samples_per_second": 17.394,
      "eval_steps_per_second": 2.185,
      "step": 25
    },
    {
      "epoch": 0.03480589022757698,
      "grad_norm": 1.174262523651123,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.065,
      "step": 26
    },
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 1.49019193649292,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1347,
      "step": 27
    },
    {
      "epoch": 0.03748326639892905,
      "grad_norm": 1.8323603868484497,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.2095,
      "step": 28
    },
    {
      "epoch": 0.038821954484605084,
      "grad_norm": 2.324418306350708,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4622,
      "step": 29
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 2.313349962234497,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.663,
      "step": 30
    },
    {
      "epoch": 0.041499330655957165,
      "grad_norm": 2.2213706970214844,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3558,
      "step": 31
    },
    {
      "epoch": 0.0428380187416332,
      "grad_norm": 2.226473093032837,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3718,
      "step": 32
    },
    {
      "epoch": 0.04417670682730924,
      "grad_norm": 2.0623409748077393,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4869,
      "step": 33
    },
    {
      "epoch": 0.04551539491298527,
      "grad_norm": 2.212683916091919,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.5165,
      "step": 34
    },
    {
      "epoch": 0.04685408299866131,
      "grad_norm": 2.247880220413208,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.497,
      "step": 35
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 2.2593677043914795,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.5639,
      "step": 36
    },
    {
      "epoch": 0.049531459170013385,
      "grad_norm": 2.508176803588867,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6135,
      "step": 37
    },
    {
      "epoch": 0.050870147255689425,
      "grad_norm": 2.3610587120056152,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.6932,
      "step": 38
    },
    {
      "epoch": 0.05220883534136546,
      "grad_norm": 2.883047580718994,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5647,
      "step": 39
    },
    {
      "epoch": 0.0535475234270415,
      "grad_norm": 2.6520442962646484,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.711,
      "step": 40
    },
    {
      "epoch": 0.05488621151271754,
      "grad_norm": 2.7636210918426514,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6489,
      "step": 41
    },
    {
      "epoch": 0.05622489959839357,
      "grad_norm": 3.3009133338928223,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.8286,
      "step": 42
    },
    {
      "epoch": 0.05756358768406961,
      "grad_norm": 4.271368503570557,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.0081,
      "step": 43
    },
    {
      "epoch": 0.058902275769745646,
      "grad_norm": 5.240908622741699,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.1059,
      "step": 44
    },
    {
      "epoch": 0.060240963855421686,
      "grad_norm": 8.063950538635254,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.7622,
      "step": 45
    },
    {
      "epoch": 0.06157965194109773,
      "grad_norm": 8.115025520324707,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.3904,
      "step": 46
    },
    {
      "epoch": 0.06291834002677377,
      "grad_norm": 9.404306411743164,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.0908,
      "step": 47
    },
    {
      "epoch": 0.0642570281124498,
      "grad_norm": 9.610150337219238,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.4451,
      "step": 48
    },
    {
      "epoch": 0.06559571619812583,
      "grad_norm": 10.734207153320312,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.7998,
      "step": 49
    },
    {
      "epoch": 0.06693440428380187,
      "grad_norm": 20.90941047668457,
      "learning_rate": 0.0,
      "loss": 3.1422,
      "step": 50
    },
    {
      "epoch": 0.06693440428380187,
      "eval_loss": 1.4047613143920898,
      "eval_runtime": 72.0554,
      "eval_samples_per_second": 17.459,
      "eval_steps_per_second": 2.193,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.022044271516058e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}