{
  "best_metric": 0.7651157379150391,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.016849199663016005,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008424599831508003,
      "grad_norm": 5.564464092254639,
      "learning_rate": 2e-05,
      "loss": 4.1662,
      "step": 1
    },
    {
      "epoch": 0.0008424599831508003,
      "eval_loss": 1.0932800769805908,
      "eval_runtime": 157.0296,
      "eval_samples_per_second": 3.184,
      "eval_steps_per_second": 1.592,
      "step": 1
    },
    {
      "epoch": 0.0016849199663016006,
      "grad_norm": 6.621733665466309,
      "learning_rate": 4e-05,
      "loss": 4.7167,
      "step": 2
    },
    {
      "epoch": 0.002527379949452401,
      "grad_norm": 5.463293075561523,
      "learning_rate": 6e-05,
      "loss": 4.5737,
      "step": 3
    },
    {
      "epoch": 0.003369839932603201,
      "grad_norm": 5.316159248352051,
      "learning_rate": 8e-05,
      "loss": 4.1971,
      "step": 4
    },
    {
      "epoch": 0.004212299915754001,
      "grad_norm": 4.543119430541992,
      "learning_rate": 0.0001,
      "loss": 3.5679,
      "step": 5
    },
    {
      "epoch": 0.004212299915754001,
      "eval_loss": 0.9457617402076721,
      "eval_runtime": 157.6073,
      "eval_samples_per_second": 3.172,
      "eval_steps_per_second": 1.586,
      "step": 5
    },
    {
      "epoch": 0.005054759898904802,
      "grad_norm": 3.820000171661377,
      "learning_rate": 0.00012,
      "loss": 3.5363,
      "step": 6
    },
    {
      "epoch": 0.005897219882055603,
      "grad_norm": 4.322159290313721,
      "learning_rate": 0.00014,
      "loss": 3.6507,
      "step": 7
    },
    {
      "epoch": 0.006739679865206402,
      "grad_norm": 4.500161170959473,
      "learning_rate": 0.00016,
      "loss": 3.5666,
      "step": 8
    },
    {
      "epoch": 0.007582139848357203,
      "grad_norm": 3.7983176708221436,
      "learning_rate": 0.00018,
      "loss": 3.7759,
      "step": 9
    },
    {
      "epoch": 0.008424599831508003,
      "grad_norm": 3.879716396331787,
      "learning_rate": 0.0002,
      "loss": 3.3886,
      "step": 10
    },
    {
      "epoch": 0.008424599831508003,
      "eval_loss": 0.8209472894668579,
      "eval_runtime": 159.3798,
      "eval_samples_per_second": 3.137,
      "eval_steps_per_second": 1.569,
      "step": 10
    },
    {
      "epoch": 0.009267059814658803,
      "grad_norm": 4.509300708770752,
      "learning_rate": 0.00019781476007338058,
      "loss": 3.1134,
      "step": 11
    },
    {
      "epoch": 0.010109519797809604,
      "grad_norm": 4.930267333984375,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.8386,
      "step": 12
    },
    {
      "epoch": 0.010951979780960405,
      "grad_norm": 3.4825778007507324,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.8907,
      "step": 13
    },
    {
      "epoch": 0.011794439764111205,
      "grad_norm": 3.1873111724853516,
      "learning_rate": 0.00016691306063588583,
      "loss": 3.047,
      "step": 14
    },
    {
      "epoch": 0.012636899747262006,
      "grad_norm": 7.248643398284912,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.4106,
      "step": 15
    },
    {
      "epoch": 0.012636899747262006,
      "eval_loss": 0.7930175065994263,
      "eval_runtime": 159.3164,
      "eval_samples_per_second": 3.138,
      "eval_steps_per_second": 1.569,
      "step": 15
    },
    {
      "epoch": 0.013479359730412805,
      "grad_norm": 3.6828701496124268,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.1635,
      "step": 16
    },
    {
      "epoch": 0.014321819713563605,
      "grad_norm": 2.783341407775879,
      "learning_rate": 0.00011045284632676536,
      "loss": 2.9676,
      "step": 17
    },
    {
      "epoch": 0.015164279696714406,
      "grad_norm": 3.4732234477996826,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.5988,
      "step": 18
    },
    {
      "epoch": 0.016006739679865205,
      "grad_norm": 5.506781578063965,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.662,
      "step": 19
    },
    {
      "epoch": 0.016849199663016005,
      "grad_norm": 3.5755441188812256,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.5257,
      "step": 20
    },
    {
      "epoch": 0.016849199663016005,
      "eval_loss": 0.7651157379150391,
      "eval_runtime": 159.3684,
      "eval_samples_per_second": 3.137,
      "eval_steps_per_second": 1.569,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7010679143792640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}