{
  "best_metric": 10.674420356750488,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.018867924528302,
  "eval_steps": 25,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 20.191490173339844,
      "learning_rate": 5e-05,
      "loss": 177.1814,
      "step": 1
    },
    {
      "epoch": 0.07547169811320754,
      "eval_loss": 11.088399887084961,
      "eval_runtime": 1.5249,
      "eval_samples_per_second": 32.788,
      "eval_steps_per_second": 8.525,
      "step": 1
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 24.14354705810547,
      "learning_rate": 0.0001,
      "loss": 177.3503,
      "step": 2
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 32.585731506347656,
      "learning_rate": 9.984630218530014e-05,
      "loss": 177.6295,
      "step": 3
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 22.008026123046875,
      "learning_rate": 9.938625865312251e-05,
      "loss": 176.9826,
      "step": 4
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 23.932588577270508,
      "learning_rate": 9.862301196726987e-05,
      "loss": 176.1517,
      "step": 5
    },
    {
      "epoch": 0.4528301886792453,
      "grad_norm": 32.37459945678711,
      "learning_rate": 9.756177587652856e-05,
      "loss": 176.2939,
      "step": 6
    },
    {
      "epoch": 0.5283018867924528,
      "grad_norm": 25.027816772460938,
      "learning_rate": 9.620979969947759e-05,
      "loss": 175.8869,
      "step": 7
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 21.235912322998047,
      "learning_rate": 9.4576318804292e-05,
      "loss": 175.4052,
      "step": 8
    },
    {
      "epoch": 0.6792452830188679,
      "grad_norm": 33.418392181396484,
      "learning_rate": 9.267249152181379e-05,
      "loss": 175.2009,
      "step": 9
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 28.781606674194336,
      "learning_rate": 9.051132292283771e-05,
      "loss": 174.6055,
      "step": 10
    },
    {
      "epoch": 0.8301886792452831,
      "grad_norm": 20.592010498046875,
      "learning_rate": 8.810757598029093e-05,
      "loss": 174.605,
      "step": 11
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 26.657976150512695,
      "learning_rate": 8.547767072315835e-05,
      "loss": 174.001,
      "step": 12
    },
    {
      "epoch": 0.9811320754716981,
      "grad_norm": 33.04609680175781,
      "learning_rate": 8.263957207103507e-05,
      "loss": 173.1651,
      "step": 13
    },
    {
      "epoch": 1.0566037735849056,
      "grad_norm": 20.265743255615234,
      "learning_rate": 7.961266711550922e-05,
      "loss": 174.0557,
      "step": 14
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 23.273855209350586,
      "learning_rate": 7.641763268666831e-05,
      "loss": 173.1172,
      "step": 15
    },
    {
      "epoch": 1.2075471698113207,
      "grad_norm": 30.730178833007812,
      "learning_rate": 7.307629410938363e-05,
      "loss": 172.1886,
      "step": 16
    },
    {
      "epoch": 1.2830188679245282,
      "grad_norm": 23.721712112426758,
      "learning_rate": 6.961147611421075e-05,
      "loss": 172.679,
      "step": 17
    },
    {
      "epoch": 1.3584905660377358,
      "grad_norm": 20.491455078125,
      "learning_rate": 6.604684692133597e-05,
      "loss": 172.8896,
      "step": 18
    },
    {
      "epoch": 1.4339622641509435,
      "grad_norm": 29.927913665771484,
      "learning_rate": 6.240675656263303e-05,
      "loss": 171.3634,
      "step": 19
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 26.627092361450195,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 171.2386,
      "step": 20
    },
    {
      "epoch": 1.5849056603773586,
      "grad_norm": 19.200040817260742,
      "learning_rate": 5.500000000000001e-05,
      "loss": 172.4474,
      "step": 21
    },
    {
      "epoch": 1.6603773584905661,
      "grad_norm": 23.857038497924805,
      "learning_rate": 5.128392945374505e-05,
      "loss": 171.151,
      "step": 22
    },
    {
      "epoch": 1.7358490566037736,
      "grad_norm": 30.006938934326172,
      "learning_rate": 4.7593243437366975e-05,
      "loss": 169.8178,
      "step": 23
    },
    {
      "epoch": 1.8113207547169812,
      "grad_norm": 18.68699073791504,
      "learning_rate": 4.395315307866405e-05,
      "loss": 172.3379,
      "step": 24
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 22.799198150634766,
      "learning_rate": 4.0388523885789256e-05,
      "loss": 170.6125,
      "step": 25
    },
    {
      "epoch": 1.8867924528301887,
      "eval_loss": 10.674420356750488,
      "eval_runtime": 0.1132,
      "eval_samples_per_second": 441.851,
      "eval_steps_per_second": 114.881,
      "step": 25
    },
    {
      "epoch": 1.9622641509433962,
      "grad_norm": 27.86113929748535,
      "learning_rate": 3.692370589061639e-05,
      "loss": 169.3305,
      "step": 26
    },
    {
      "epoch": 2.0377358490566038,
      "grad_norm": 19.5020809173584,
      "learning_rate": 3.358236731333169e-05,
      "loss": 171.0887,
      "step": 27
    },
    {
      "epoch": 2.1132075471698113,
      "grad_norm": 20.567012786865234,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 171.2371,
      "step": 28
    },
    {
      "epoch": 2.188679245283019,
      "grad_norm": 26.858049392700195,
      "learning_rate": 2.736042792896495e-05,
      "loss": 169.3462,
      "step": 29
    },
    {
      "epoch": 2.2641509433962264,
      "grad_norm": 24.104114532470703,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 169.4767,
      "step": 30
    },
    {
      "epoch": 2.339622641509434,
      "grad_norm": 18.2357234954834,
      "learning_rate": 2.189242401970908e-05,
      "loss": 171.2782,
      "step": 31
    },
    {
      "epoch": 2.4150943396226414,
      "grad_norm": 24.269392013549805,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 169.5011,
      "step": 32
    },
    {
      "epoch": 2.490566037735849,
      "grad_norm": 27.363483428955078,
      "learning_rate": 1.7327508478186218e-05,
      "loss": 168.39,
      "step": 33
    },
    {
      "epoch": 2.5660377358490565,
      "grad_norm": 17.812620162963867,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 171.4145,
      "step": 34
    },
    {
      "epoch": 2.641509433962264,
      "grad_norm": 20.519203186035156,
      "learning_rate": 1.3790200300522413e-05,
      "loss": 169.7659,
      "step": 35
    },
    {
      "epoch": 2.7169811320754715,
      "grad_norm": 26.273950576782227,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 168.288,
      "step": 36
    },
    {
      "epoch": 2.7924528301886795,
      "grad_norm": 18.332481384277344,
      "learning_rate": 1.1376988032730134e-05,
      "loss": 170.6672,
      "step": 37
    },
    {
      "epoch": 2.867924528301887,
      "grad_norm": 20.2203311920166,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 169.821,
      "step": 38
    },
    {
      "epoch": 2.9433962264150946,
      "grad_norm": 26.442291259765625,
      "learning_rate": 1.0153697814699859e-05,
      "loss": 168.0069,
      "step": 39
    },
    {
      "epoch": 3.018867924528302,
      "grad_norm": 21.066753387451172,
      "learning_rate": 1e-05,
      "loss": 169.3049,
      "step": 40
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 34883588063232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}