{
  "best_metric": 0.9773313403129578,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.28653295128939826,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0057306590257879654,
      "grad_norm": 1.0035889148712158,
      "learning_rate": 1e-05,
      "loss": 1.1815,
      "step": 1
    },
    {
      "epoch": 0.0057306590257879654,
      "eval_loss": 4.764197826385498,
      "eval_runtime": 31.1782,
      "eval_samples_per_second": 9.43,
      "eval_steps_per_second": 2.373,
      "step": 1
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 1.284098744392395,
      "learning_rate": 2e-05,
      "loss": 1.4512,
      "step": 2
    },
    {
      "epoch": 0.017191977077363897,
      "grad_norm": 1.4318172931671143,
      "learning_rate": 3e-05,
      "loss": 1.5606,
      "step": 3
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 1.313220500946045,
      "learning_rate": 4e-05,
      "loss": 1.3823,
      "step": 4
    },
    {
      "epoch": 0.02865329512893983,
      "grad_norm": 1.4467310905456543,
      "learning_rate": 5e-05,
      "loss": 1.4146,
      "step": 5
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 1.2124062776565552,
      "learning_rate": 6e-05,
      "loss": 0.9605,
      "step": 6
    },
    {
      "epoch": 0.04011461318051576,
      "grad_norm": 1.8278082609176636,
      "learning_rate": 7e-05,
      "loss": 1.0288,
      "step": 7
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 2.009721279144287,
      "learning_rate": 8e-05,
      "loss": 1.1359,
      "step": 8
    },
    {
      "epoch": 0.05157593123209169,
      "grad_norm": 2.1793124675750732,
      "learning_rate": 9e-05,
      "loss": 0.9358,
      "step": 9
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 19.282501220703125,
      "learning_rate": 0.0001,
      "loss": 2.2681,
      "step": 10
    },
    {
      "epoch": 0.06303724928366762,
      "grad_norm": 33.58476257324219,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.5587,
      "step": 11
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 15.062165260314941,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.4257,
      "step": 12
    },
    {
      "epoch": 0.07449856733524356,
      "grad_norm": 12.21485710144043,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6596,
      "step": 13
    },
    {
      "epoch": 0.08022922636103152,
      "grad_norm": 6.862950325012207,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4768,
      "step": 14
    },
    {
      "epoch": 0.08595988538681948,
      "grad_norm": 39.041934967041016,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4254,
      "step": 15
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 14.904204368591309,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5324,
      "step": 16
    },
    {
      "epoch": 0.09742120343839542,
      "grad_norm": 64.56082916259766,
      "learning_rate": 9.966546331768191e-05,
      "loss": 13.9855,
      "step": 17
    },
    {
      "epoch": 0.10315186246418338,
      "grad_norm": 65.52576446533203,
      "learning_rate": 9.956320346634876e-05,
      "loss": 11.8833,
      "step": 18
    },
    {
      "epoch": 0.10888252148997135,
      "grad_norm": 61.4244384765625,
      "learning_rate": 9.944739353007344e-05,
      "loss": 6.7465,
      "step": 19
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 27.389549255371094,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5388,
      "step": 20
    },
    {
      "epoch": 0.12034383954154727,
      "grad_norm": 2.302321434020996,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.92,
      "step": 21
    },
    {
      "epoch": 0.12607449856733524,
      "grad_norm": 2.0892953872680664,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7421,
      "step": 22
    },
    {
      "epoch": 0.1318051575931232,
      "grad_norm": 1.3867814540863037,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6724,
      "step": 23
    },
    {
      "epoch": 0.13753581661891118,
      "grad_norm": 1.2110521793365479,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5989,
      "step": 24
    },
    {
      "epoch": 0.14326647564469913,
      "grad_norm": 0.9389761686325073,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6053,
      "step": 25
    },
    {
      "epoch": 0.1489971346704871,
      "grad_norm": 1.0855313539505005,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5802,
      "step": 26
    },
    {
      "epoch": 0.15472779369627507,
      "grad_norm": 1.1220835447311401,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8231,
      "step": 27
    },
    {
      "epoch": 0.16045845272206305,
      "grad_norm": 1.0798989534378052,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6332,
      "step": 28
    },
    {
      "epoch": 0.166189111747851,
      "grad_norm": 0.836507260799408,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.493,
      "step": 29
    },
    {
      "epoch": 0.17191977077363896,
      "grad_norm": 0.9351760149002075,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4356,
      "step": 30
    },
    {
      "epoch": 0.17765042979942694,
      "grad_norm": 0.9819492101669312,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4732,
      "step": 31
    },
    {
      "epoch": 0.1833810888252149,
      "grad_norm": 0.9373030662536621,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.534,
      "step": 32
    },
    {
      "epoch": 0.18911174785100288,
      "grad_norm": 1.21796452999115,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5958,
      "step": 33
    },
    {
      "epoch": 0.19484240687679083,
      "grad_norm": 0.9990187883377075,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5209,
      "step": 34
    },
    {
      "epoch": 0.20057306590257878,
      "grad_norm": 1.1247957944869995,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6153,
      "step": 35
    },
    {
      "epoch": 0.20630372492836677,
      "grad_norm": 1.2250124216079712,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.624,
      "step": 36
    },
    {
      "epoch": 0.21203438395415472,
      "grad_norm": 1.1935553550720215,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4949,
      "step": 37
    },
    {
      "epoch": 0.2177650429799427,
      "grad_norm": 0.9890780448913574,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.5411,
      "step": 38
    },
    {
      "epoch": 0.22349570200573066,
      "grad_norm": 1.2203408479690552,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6145,
      "step": 39
    },
    {
      "epoch": 0.22922636103151864,
      "grad_norm": 0.9592453837394714,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5206,
      "step": 40
    },
    {
      "epoch": 0.2349570200573066,
      "grad_norm": 1.0418148040771484,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5794,
      "step": 41
    },
    {
      "epoch": 0.24068767908309455,
      "grad_norm": 1.1782774925231934,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.5522,
      "step": 42
    },
    {
      "epoch": 0.24641833810888253,
      "grad_norm": 1.3091051578521729,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4101,
      "step": 43
    },
    {
      "epoch": 0.2521489971346705,
      "grad_norm": 1.1064131259918213,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9251,
      "step": 44
    },
    {
      "epoch": 0.25787965616045844,
      "grad_norm": 0.7374259829521179,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9514,
      "step": 45
    },
    {
      "epoch": 0.2636103151862464,
      "grad_norm": 0.6981614232063293,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9857,
      "step": 46
    },
    {
      "epoch": 0.2693409742120344,
      "grad_norm": 0.7841881513595581,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9988,
      "step": 47
    },
    {
      "epoch": 0.27507163323782235,
      "grad_norm": 0.7463127970695496,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.9756,
      "step": 48
    },
    {
      "epoch": 0.2808022922636103,
      "grad_norm": 0.7383707165718079,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.8701,
      "step": 49
    },
    {
      "epoch": 0.28653295128939826,
      "grad_norm": 0.8134977221488953,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7029,
      "step": 50
    },
    {
      "epoch": 0.28653295128939826,
      "eval_loss": 0.9773313403129578,
      "eval_runtime": 32.0113,
      "eval_samples_per_second": 9.184,
      "eval_steps_per_second": 2.312,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.1125287643250688e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}