{
  "best_metric": 1.4082918167114258,
  "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": 5.025701999664307,
      "learning_rate": 2e-05,
      "loss": 2.4108,
      "step": 1
    },
    {
      "epoch": 0.0013386880856760374,
      "eval_loss": 2.537308931350708,
      "eval_runtime": 70.7541,
      "eval_samples_per_second": 17.78,
      "eval_steps_per_second": 2.233,
      "step": 1
    },
    {
      "epoch": 0.002677376171352075,
      "grad_norm": 5.110573768615723,
      "learning_rate": 4e-05,
      "loss": 2.2402,
      "step": 2
    },
    {
      "epoch": 0.004016064257028112,
      "grad_norm": 5.169720649719238,
      "learning_rate": 6e-05,
      "loss": 2.1319,
      "step": 3
    },
    {
      "epoch": 0.00535475234270415,
      "grad_norm": 2.304621458053589,
      "learning_rate": 8e-05,
      "loss": 1.1494,
      "step": 4
    },
    {
      "epoch": 0.006693440428380187,
      "grad_norm": 1.453190565109253,
      "learning_rate": 0.0001,
      "loss": 0.6319,
      "step": 5
    },
    {
      "epoch": 0.008032128514056224,
      "grad_norm": 0.9239307641983032,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7635,
      "step": 6
    },
    {
      "epoch": 0.009370816599732263,
      "grad_norm": 1.6850275993347168,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8355,
      "step": 7
    },
    {
      "epoch": 0.0107095046854083,
      "grad_norm": 1.4980453252792358,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9613,
      "step": 8
    },
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 1.374350905418396,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.2347,
      "step": 9
    },
    {
      "epoch": 0.013386880856760375,
      "grad_norm": 0.8881041407585144,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.2745,
      "step": 10
    },
    {
      "epoch": 0.014725568942436412,
      "grad_norm": 1.0661808252334595,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6181,
      "step": 11
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 0.8983698487281799,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4951,
      "step": 12
    },
    {
      "epoch": 0.01740294511378849,
      "grad_norm": 1.2034538984298706,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.713,
      "step": 13
    },
    {
      "epoch": 0.018741633199464525,
      "grad_norm": 1.136259913444519,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5381,
      "step": 14
    },
    {
      "epoch": 0.020080321285140562,
      "grad_norm": 0.9251773357391357,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4089,
      "step": 15
    },
    {
      "epoch": 0.0214190093708166,
      "grad_norm": 1.101027250289917,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1084,
      "step": 16
    },
    {
      "epoch": 0.022757697456492636,
      "grad_norm": 0.8664842844009399,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1297,
      "step": 17
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 1.0595276355743408,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1792,
      "step": 18
    },
    {
      "epoch": 0.025435073627844713,
      "grad_norm": 0.9103767275810242,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.2791,
      "step": 19
    },
    {
      "epoch": 0.02677376171352075,
      "grad_norm": 0.895751416683197,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1642,
      "step": 20
    },
    {
      "epoch": 0.028112449799196786,
      "grad_norm": 0.8980446457862854,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0529,
      "step": 21
    },
    {
      "epoch": 0.029451137884872823,
      "grad_norm": 0.9152507185935974,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9741,
      "step": 22
    },
    {
      "epoch": 0.030789825970548863,
      "grad_norm": 1.0312362909317017,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1645,
      "step": 23
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 1.0697182416915894,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.1863,
      "step": 24
    },
    {
      "epoch": 0.03346720214190094,
      "grad_norm": 1.0174766778945923,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0057,
      "step": 25
    },
    {
      "epoch": 0.03346720214190094,
      "eval_loss": 1.471519947052002,
      "eval_runtime": 72.2713,
      "eval_samples_per_second": 17.407,
      "eval_steps_per_second": 2.186,
      "step": 25
    },
    {
      "epoch": 0.03480589022757698,
      "grad_norm": 1.196843147277832,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.0659,
      "step": 26
    },
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 1.452512264251709,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1401,
      "step": 27
    },
    {
      "epoch": 0.03748326639892905,
      "grad_norm": 1.8693279027938843,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.1954,
      "step": 28
    },
    {
      "epoch": 0.038821954484605084,
      "grad_norm": 2.132535934448242,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.4661,
      "step": 29
    },
    {
      "epoch": 0.040160642570281124,
      "grad_norm": 2.3404362201690674,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6736,
      "step": 30
    },
    {
      "epoch": 0.041499330655957165,
      "grad_norm": 2.2586476802825928,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.3548,
      "step": 31
    },
    {
      "epoch": 0.0428380187416332,
      "grad_norm": 2.1530497074127197,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3779,
      "step": 32
    },
    {
      "epoch": 0.04417670682730924,
      "grad_norm": 2.098426342010498,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.4974,
      "step": 33
    },
    {
      "epoch": 0.04551539491298527,
      "grad_norm": 2.2894680500030518,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.5319,
      "step": 34
    },
    {
      "epoch": 0.04685408299866131,
      "grad_norm": 2.207040309906006,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5025,
      "step": 35
    },
    {
      "epoch": 0.04819277108433735,
      "grad_norm": 2.2640841007232666,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.5726,
      "step": 36
    },
    {
      "epoch": 0.049531459170013385,
      "grad_norm": 2.5610170364379883,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6428,
      "step": 37
    },
    {
      "epoch": 0.050870147255689425,
      "grad_norm": 2.411795139312744,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.6973,
      "step": 38
    },
    {
      "epoch": 0.05220883534136546,
      "grad_norm": 2.789268732070923,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5699,
      "step": 39
    },
    {
      "epoch": 0.0535475234270415,
      "grad_norm": 2.6263678073883057,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7022,
      "step": 40
    },
    {
      "epoch": 0.05488621151271754,
      "grad_norm": 2.829754590988159,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6516,
      "step": 41
    },
    {
      "epoch": 0.05622489959839357,
      "grad_norm": 3.3074681758880615,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.8118,
      "step": 42
    },
    {
      "epoch": 0.05756358768406961,
      "grad_norm": 4.270014762878418,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.9913,
      "step": 43
    },
    {
      "epoch": 0.058902275769745646,
      "grad_norm": 5.280431747436523,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.0868,
      "step": 44
    },
    {
      "epoch": 0.060240963855421686,
      "grad_norm": 8.311389923095703,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.7795,
      "step": 45
    },
    {
      "epoch": 0.06157965194109773,
      "grad_norm": 8.135458946228027,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.3549,
      "step": 46
    },
    {
      "epoch": 0.06291834002677377,
      "grad_norm": 9.432684898376465,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.1519,
      "step": 47
    },
    {
      "epoch": 0.0642570281124498,
      "grad_norm": 9.505349159240723,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.4938,
      "step": 48
    },
    {
      "epoch": 0.06559571619812583,
      "grad_norm": 10.815413475036621,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.7774,
      "step": 49
    },
    {
      "epoch": 0.06693440428380187,
      "grad_norm": 21.284269332885742,
      "learning_rate": 0.0,
      "loss": 3.1468,
      "step": 50
    },
    {
      "epoch": 0.06693440428380187,
      "eval_loss": 1.4082918167114258,
      "eval_runtime": 72.0522,
      "eval_samples_per_second": 17.46,
      "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
}