{
  "best_metric": 3.1905009746551514,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.2674591381872214,
  "eval_steps": 150,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005943536404160475,
      "eval_loss": 6.33011531829834,
      "eval_runtime": 210.4742,
      "eval_samples_per_second": 13.465,
      "eval_steps_per_second": 3.369,
      "step": 1
    },
    {
      "epoch": 0.005943536404160475,
      "grad_norm": 3.636090040206909,
      "learning_rate": 2e-05,
      "loss": 4.2971,
      "step": 10
    },
    {
      "epoch": 0.01188707280832095,
      "grad_norm": 3.378282308578491,
      "learning_rate": 4e-05,
      "loss": 3.9504,
      "step": 20
    },
    {
      "epoch": 0.017830609212481426,
      "grad_norm": 3.461188554763794,
      "learning_rate": 6e-05,
      "loss": 3.3025,
      "step": 30
    },
    {
      "epoch": 0.0237741456166419,
      "grad_norm": 3.8042867183685303,
      "learning_rate": 8e-05,
      "loss": 3.0173,
      "step": 40
    },
    {
      "epoch": 0.029717682020802376,
      "grad_norm": 5.867399215698242,
      "learning_rate": 0.0001,
      "loss": 3.1382,
      "step": 50
    },
    {
      "epoch": 0.03566121842496285,
      "grad_norm": 2.080888271331787,
      "learning_rate": 9.999074760873505e-05,
      "loss": 3.1589,
      "step": 60
    },
    {
      "epoch": 0.041604754829123326,
      "grad_norm": 2.627453088760376,
      "learning_rate": 9.996299385920993e-05,
      "loss": 3.0502,
      "step": 70
    },
    {
      "epoch": 0.0475482912332838,
      "grad_norm": 2.772899627685547,
      "learning_rate": 9.991674902296665e-05,
      "loss": 3.0374,
      "step": 80
    },
    {
      "epoch": 0.05349182763744428,
      "grad_norm": 3.1544461250305176,
      "learning_rate": 9.985203021501797e-05,
      "loss": 2.9162,
      "step": 90
    },
    {
      "epoch": 0.05943536404160475,
      "grad_norm": 6.360644340515137,
      "learning_rate": 9.976886138751321e-05,
      "loss": 2.9194,
      "step": 100
    },
    {
      "epoch": 0.06537890044576523,
      "grad_norm": 2.4774982929229736,
      "learning_rate": 9.96672733208737e-05,
      "loss": 3.2118,
      "step": 110
    },
    {
      "epoch": 0.0713224368499257,
      "grad_norm": 2.2214813232421875,
      "learning_rate": 9.954730361240105e-05,
      "loss": 3.0673,
      "step": 120
    },
    {
      "epoch": 0.07726597325408618,
      "grad_norm": 2.6016104221343994,
      "learning_rate": 9.940899666236258e-05,
      "loss": 2.9907,
      "step": 130
    },
    {
      "epoch": 0.08320950965824665,
      "grad_norm": 3.2741599082946777,
      "learning_rate": 9.925240365755893e-05,
      "loss": 2.9132,
      "step": 140
    },
    {
      "epoch": 0.08915304606240713,
      "grad_norm": 4.4667534828186035,
      "learning_rate": 9.907758255238013e-05,
      "loss": 3.0036,
      "step": 150
    },
    {
      "epoch": 0.08915304606240713,
      "eval_loss": 3.1905009746551514,
      "eval_runtime": 212.6607,
      "eval_samples_per_second": 13.326,
      "eval_steps_per_second": 3.334,
      "step": 150
    },
    {
      "epoch": 0.0950965824665676,
      "grad_norm": 1.8121700286865234,
      "learning_rate": 9.888459804735679e-05,
      "loss": 3.1284,
      "step": 160
    },
    {
      "epoch": 0.10104011887072809,
      "grad_norm": 2.5314412117004395,
      "learning_rate": 9.867352156521488e-05,
      "loss": 3.1552,
      "step": 170
    },
    {
      "epoch": 0.10698365527488855,
      "grad_norm": 2.6681604385375977,
      "learning_rate": 9.844443122444238e-05,
      "loss": 2.9376,
      "step": 180
    },
    {
      "epoch": 0.11292719167904904,
      "grad_norm": 2.87355375289917,
      "learning_rate": 9.819741181037799e-05,
      "loss": 2.8799,
      "step": 190
    },
    {
      "epoch": 0.1188707280832095,
      "grad_norm": 4.919130325317383,
      "learning_rate": 9.793255474383249e-05,
      "loss": 2.8424,
      "step": 200
    },
    {
      "epoch": 0.12481426448736999,
      "grad_norm": 2.0036211013793945,
      "learning_rate": 9.764995804725424e-05,
      "loss": 3.2481,
      "step": 210
    },
    {
      "epoch": 0.13075780089153047,
      "grad_norm": 2.4777944087982178,
      "learning_rate": 9.734972630845151e-05,
      "loss": 3.0006,
      "step": 220
    },
    {
      "epoch": 0.13670133729569092,
      "grad_norm": 2.4493539333343506,
      "learning_rate": 9.703197064188498e-05,
      "loss": 2.9379,
      "step": 230
    },
    {
      "epoch": 0.1426448736998514,
      "grad_norm": 3.2666187286376953,
      "learning_rate": 9.669680864754484e-05,
      "loss": 2.8128,
      "step": 240
    },
    {
      "epoch": 0.1485884101040119,
      "grad_norm": 7.568844795227051,
      "learning_rate": 9.63443643674274e-05,
      "loss": 2.8483,
      "step": 250
    },
    {
      "epoch": 0.15453194650817237,
      "grad_norm": 1.986729383468628,
      "learning_rate": 9.597476823962784e-05,
      "loss": 3.2472,
      "step": 260
    },
    {
      "epoch": 0.16047548291233285,
      "grad_norm": 2.4101827144622803,
      "learning_rate": 9.558815705006555e-05,
      "loss": 3.0007,
      "step": 270
    },
    {
      "epoch": 0.1664190193164933,
      "grad_norm": 2.539492607116699,
      "learning_rate": 9.51846738818602e-05,
      "loss": 2.9353,
      "step": 280
    },
    {
      "epoch": 0.1723625557206538,
      "grad_norm": 2.762788772583008,
      "learning_rate": 9.476446806237749e-05,
      "loss": 2.8221,
      "step": 290
    },
    {
      "epoch": 0.17830609212481427,
      "grad_norm": 7.846682071685791,
      "learning_rate": 9.432769510796353e-05,
      "loss": 2.8917,
      "step": 300
    },
    {
      "epoch": 0.17830609212481427,
      "eval_loss": 3.3436031341552734,
      "eval_runtime": 212.4479,
      "eval_samples_per_second": 13.34,
      "eval_steps_per_second": 3.337,
      "step": 300
    },
    {
      "epoch": 0.18424962852897475,
      "grad_norm": 2.2458980083465576,
      "learning_rate": 9.387451666638906e-05,
      "loss": 3.2819,
      "step": 310
    },
    {
      "epoch": 0.1901931649331352,
      "grad_norm": 2.2853057384490967,
      "learning_rate": 9.340510045702427e-05,
      "loss": 3.0085,
      "step": 320
    },
    {
      "epoch": 0.1961367013372957,
      "grad_norm": 2.456028461456299,
      "learning_rate": 9.291962020876654e-05,
      "loss": 2.8806,
      "step": 330
    },
    {
      "epoch": 0.20208023774145617,
      "grad_norm": 2.9242990016937256,
      "learning_rate": 9.241825559574424e-05,
      "loss": 2.8353,
      "step": 340
    },
    {
      "epoch": 0.20802377414561665,
      "grad_norm": 8.866583824157715,
      "learning_rate": 9.190119217081996e-05,
      "loss": 2.8203,
      "step": 350
    },
    {
      "epoch": 0.2139673105497771,
      "grad_norm": 2.047957420349121,
      "learning_rate": 9.136862129691838e-05,
      "loss": 3.3765,
      "step": 360
    },
    {
      "epoch": 0.2199108469539376,
      "grad_norm": 2.7228925228118896,
      "learning_rate": 9.082074007620356e-05,
      "loss": 3.086,
      "step": 370
    },
    {
      "epoch": 0.22585438335809807,
      "grad_norm": 2.6000123023986816,
      "learning_rate": 9.025775127713232e-05,
      "loss": 2.8523,
      "step": 380
    },
    {
      "epoch": 0.23179791976225855,
      "grad_norm": 2.826296091079712,
      "learning_rate": 8.967986325941056e-05,
      "loss": 2.8088,
      "step": 390
    },
    {
      "epoch": 0.237741456166419,
      "grad_norm": 13.53122329711914,
      "learning_rate": 8.908728989688015e-05,
      "loss": 2.8237,
      "step": 400
    },
    {
      "epoch": 0.2436849925705795,
      "grad_norm": 2.1314334869384766,
      "learning_rate": 8.848025049836522e-05,
      "loss": 3.3274,
      "step": 410
    },
    {
      "epoch": 0.24962852897473997,
      "grad_norm": 2.417358875274658,
      "learning_rate": 8.785896972650694e-05,
      "loss": 3.0393,
      "step": 420
    },
    {
      "epoch": 0.2555720653789004,
      "grad_norm": 2.595625877380371,
      "learning_rate": 8.72236775146167e-05,
      "loss": 2.9731,
      "step": 430
    },
    {
      "epoch": 0.26151560178306094,
      "grad_norm": 2.7309069633483887,
      "learning_rate": 8.657460898157905e-05,
      "loss": 2.7837,
      "step": 440
    },
    {
      "epoch": 0.2674591381872214,
      "grad_norm": 6.042367458343506,
      "learning_rate": 8.5912004344835e-05,
      "loss": 2.7581,
      "step": 450
    },
    {
      "epoch": 0.2674591381872214,
      "eval_loss": 3.2376186847686768,
      "eval_runtime": 212.7494,
      "eval_samples_per_second": 13.321,
      "eval_steps_per_second": 3.333,
      "step": 450
    }
  ],
  "logging_steps": 10,
  "max_steps": 1683,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.658201808189522e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}