{
  "best_metric": 0.1660141497850418,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.04215851602023609,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016863406408094434,
      "grad_norm": 3.0104711055755615,
      "learning_rate": 2e-05,
      "loss": 9.4017,
      "step": 1
    },
    {
      "epoch": 0.0016863406408094434,
      "eval_loss": 2.1967105865478516,
      "eval_runtime": 47.4552,
      "eval_samples_per_second": 5.268,
      "eval_steps_per_second": 2.634,
      "step": 1
    },
    {
      "epoch": 0.003372681281618887,
      "grad_norm": 3.4141628742218018,
      "learning_rate": 4e-05,
      "loss": 8.6845,
      "step": 2
    },
    {
      "epoch": 0.00505902192242833,
      "grad_norm": 3.420022487640381,
      "learning_rate": 6e-05,
      "loss": 8.4328,
      "step": 3
    },
    {
      "epoch": 0.006745362563237774,
      "grad_norm": 3.638615846633911,
      "learning_rate": 8e-05,
      "loss": 9.1867,
      "step": 4
    },
    {
      "epoch": 0.008431703204047217,
      "grad_norm": 4.243889331817627,
      "learning_rate": 0.0001,
      "loss": 8.4538,
      "step": 5
    },
    {
      "epoch": 0.008431703204047217,
      "eval_loss": 2.0898311138153076,
      "eval_runtime": 47.5081,
      "eval_samples_per_second": 5.262,
      "eval_steps_per_second": 2.631,
      "step": 5
    },
    {
      "epoch": 0.01011804384485666,
      "grad_norm": 5.26145601272583,
      "learning_rate": 0.00012,
      "loss": 7.6572,
      "step": 6
    },
    {
      "epoch": 0.011804384485666104,
      "grad_norm": 6.131259918212891,
      "learning_rate": 0.00014,
      "loss": 7.1481,
      "step": 7
    },
    {
      "epoch": 0.013490725126475547,
      "grad_norm": 7.825711250305176,
      "learning_rate": 0.00016,
      "loss": 5.9397,
      "step": 8
    },
    {
      "epoch": 0.01517706576728499,
      "grad_norm": 7.180585861206055,
      "learning_rate": 0.00018,
      "loss": 4.6343,
      "step": 9
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 8.550070762634277,
      "learning_rate": 0.0002,
      "loss": 4.0691,
      "step": 10
    },
    {
      "epoch": 0.016863406408094434,
      "eval_loss": 0.5549235939979553,
      "eval_runtime": 47.4748,
      "eval_samples_per_second": 5.266,
      "eval_steps_per_second": 2.633,
      "step": 10
    },
    {
      "epoch": 0.01854974704890388,
      "grad_norm": 6.39945650100708,
      "learning_rate": 0.00019781476007338058,
      "loss": 2.1063,
      "step": 11
    },
    {
      "epoch": 0.02023608768971332,
      "grad_norm": 4.738637447357178,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.0059,
      "step": 12
    },
    {
      "epoch": 0.021922428330522766,
      "grad_norm": 6.6305317878723145,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7437,
      "step": 13
    },
    {
      "epoch": 0.023608768971332208,
      "grad_norm": 9.981011390686035,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.1198,
      "step": 14
    },
    {
      "epoch": 0.025295109612141653,
      "grad_norm": 6.777435302734375,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.6929,
      "step": 15
    },
    {
      "epoch": 0.025295109612141653,
      "eval_loss": 0.26381444931030273,
      "eval_runtime": 47.4625,
      "eval_samples_per_second": 5.267,
      "eval_steps_per_second": 2.634,
      "step": 15
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": 8.257752418518066,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5329,
      "step": 16
    },
    {
      "epoch": 0.02866779089376054,
      "grad_norm": 5.138362407684326,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.3854,
      "step": 17
    },
    {
      "epoch": 0.03035413153456998,
      "grad_norm": 2.0844039916992188,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.1423,
      "step": 18
    },
    {
      "epoch": 0.03204047217537943,
      "grad_norm": 2.545337200164795,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.1563,
      "step": 19
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 3.5031182765960693,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.1879,
      "step": 20
    },
    {
      "epoch": 0.03372681281618887,
      "eval_loss": 0.17875705659389496,
      "eval_runtime": 47.5141,
      "eval_samples_per_second": 5.262,
      "eval_steps_per_second": 2.631,
      "step": 20
    },
    {
      "epoch": 0.03541315345699832,
      "grad_norm": 5.7535295486450195,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.4698,
      "step": 21
    },
    {
      "epoch": 0.03709949409780776,
      "grad_norm": 2.8564772605895996,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.2599,
      "step": 22
    },
    {
      "epoch": 0.0387858347386172,
      "grad_norm": 0.8172993063926697,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0864,
      "step": 23
    },
    {
      "epoch": 0.04047217537942664,
      "grad_norm": 3.7000441551208496,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.2295,
      "step": 24
    },
    {
      "epoch": 0.04215851602023609,
      "grad_norm": 3.757780075073242,
      "learning_rate": 0.0,
      "loss": 0.944,
      "step": 25
    },
    {
      "epoch": 0.04215851602023609,
      "eval_loss": 0.1660141497850418,
      "eval_runtime": 47.4874,
      "eval_samples_per_second": 5.265,
      "eval_steps_per_second": 2.632,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 7915560763392000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}