{
  "best_metric": 3.2418150901794434,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06056935190793458,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024227740763173833,
      "grad_norm": 6.354554653167725,
      "learning_rate": 0.0001,
      "loss": 5.003,
      "step": 1
    },
    {
      "epoch": 0.0024227740763173833,
      "eval_loss": 4.445741176605225,
      "eval_runtime": 48.9332,
      "eval_samples_per_second": 3.556,
      "eval_steps_per_second": 1.778,
      "step": 1
    },
    {
      "epoch": 0.004845548152634767,
      "grad_norm": 7.047632217407227,
      "learning_rate": 0.0002,
      "loss": 5.4559,
      "step": 2
    },
    {
      "epoch": 0.0072683222289521504,
      "grad_norm": 7.0595598220825195,
      "learning_rate": 0.00019978589232386035,
      "loss": 4.8398,
      "step": 3
    },
    {
      "epoch": 0.009691096305269533,
      "grad_norm": 9.777852058410645,
      "learning_rate": 0.00019914448613738106,
      "loss": 4.7029,
      "step": 4
    },
    {
      "epoch": 0.012113870381586917,
      "grad_norm": 3.7091481685638428,
      "learning_rate": 0.00019807852804032305,
      "loss": 3.8521,
      "step": 5
    },
    {
      "epoch": 0.014536644457904301,
      "grad_norm": 3.647103786468506,
      "learning_rate": 0.00019659258262890683,
      "loss": 4.2682,
      "step": 6
    },
    {
      "epoch": 0.016959418534221685,
      "grad_norm": 4.299393653869629,
      "learning_rate": 0.0001946930129495106,
      "loss": 3.9939,
      "step": 7
    },
    {
      "epoch": 0.019382192610539067,
      "grad_norm": 3.0232176780700684,
      "learning_rate": 0.0001923879532511287,
      "loss": 3.8496,
      "step": 8
    },
    {
      "epoch": 0.021804966686856452,
      "grad_norm": 3.2615227699279785,
      "learning_rate": 0.00018968727415326884,
      "loss": 3.6195,
      "step": 9
    },
    {
      "epoch": 0.024227740763173834,
      "grad_norm": 2.2656781673431396,
      "learning_rate": 0.00018660254037844388,
      "loss": 3.746,
      "step": 10
    },
    {
      "epoch": 0.026650514839491216,
      "grad_norm": 3.4833717346191406,
      "learning_rate": 0.00018314696123025454,
      "loss": 3.1256,
      "step": 11
    },
    {
      "epoch": 0.029073288915808602,
      "grad_norm": 5.78814172744751,
      "learning_rate": 0.00017933533402912354,
      "loss": 2.9103,
      "step": 12
    },
    {
      "epoch": 0.031496062992125984,
      "grad_norm": 3.293673038482666,
      "learning_rate": 0.00017518398074789775,
      "loss": 3.0973,
      "step": 13
    },
    {
      "epoch": 0.03391883706844337,
      "grad_norm": 4.502946376800537,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.2474,
      "step": 14
    },
    {
      "epoch": 0.03634161114476075,
      "grad_norm": 2.1124539375305176,
      "learning_rate": 0.00016593458151000688,
      "loss": 2.8826,
      "step": 15
    },
    {
      "epoch": 0.03876438522107813,
      "grad_norm": 3.9200596809387207,
      "learning_rate": 0.00016087614290087208,
      "loss": 3.1527,
      "step": 16
    },
    {
      "epoch": 0.04118715929739552,
      "grad_norm": 1.7969374656677246,
      "learning_rate": 0.00015555702330196023,
      "loss": 2.9535,
      "step": 17
    },
    {
      "epoch": 0.043609933373712904,
      "grad_norm": 3.1285815238952637,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.2713,
      "step": 18
    },
    {
      "epoch": 0.04603270745003028,
      "grad_norm": 8.577775955200195,
      "learning_rate": 0.00014422886902190014,
      "loss": 3.3961,
      "step": 19
    },
    {
      "epoch": 0.04845548152634767,
      "grad_norm": 2.5606937408447266,
      "learning_rate": 0.000138268343236509,
      "loss": 3.1592,
      "step": 20
    },
    {
      "epoch": 0.050878255602665054,
      "grad_norm": 3.973900318145752,
      "learning_rate": 0.00013214394653031616,
      "loss": 2.9197,
      "step": 21
    },
    {
      "epoch": 0.05330102967898243,
      "grad_norm": 1.974953532218933,
      "learning_rate": 0.00012588190451025207,
      "loss": 3.3658,
      "step": 22
    },
    {
      "epoch": 0.05572380375529982,
      "grad_norm": 3.7481021881103516,
      "learning_rate": 0.00011950903220161285,
      "loss": 2.8164,
      "step": 23
    },
    {
      "epoch": 0.058146577831617204,
      "grad_norm": 1.198407769203186,
      "learning_rate": 0.00011305261922200519,
      "loss": 3.1784,
      "step": 24
    },
    {
      "epoch": 0.06056935190793458,
      "grad_norm": 2.7096714973449707,
      "learning_rate": 0.00010654031292301432,
      "loss": 2.9163,
      "step": 25
    },
    {
      "epoch": 0.06056935190793458,
      "eval_loss": 3.2418150901794434,
      "eval_runtime": 49.5368,
      "eval_samples_per_second": 3.513,
      "eval_steps_per_second": 1.756,
      "step": 25
    }
  ],
  "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": 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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.70943641780224e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}