{
  "best_metric": 1.4222428798675537,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.011379800853485065,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "grad_norm": 0.991689145565033,
      "learning_rate": 2e-05,
      "loss": 1.7214,
      "step": 1
    },
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 1.6749292612075806,
      "eval_runtime": 291.9244,
      "eval_samples_per_second": 2.535,
      "eval_steps_per_second": 1.267,
      "step": 1
    },
    {
      "epoch": 0.0011379800853485065,
      "grad_norm": 1.1164624691009521,
      "learning_rate": 4e-05,
      "loss": 1.8154,
      "step": 2
    },
    {
      "epoch": 0.0017069701280227596,
      "grad_norm": 1.037307858467102,
      "learning_rate": 6e-05,
      "loss": 1.6963,
      "step": 3
    },
    {
      "epoch": 0.002275960170697013,
      "grad_norm": 0.9190394878387451,
      "learning_rate": 8e-05,
      "loss": 1.6153,
      "step": 4
    },
    {
      "epoch": 0.002844950213371266,
      "grad_norm": 0.9947201609611511,
      "learning_rate": 0.0001,
      "loss": 1.6797,
      "step": 5
    },
    {
      "epoch": 0.002844950213371266,
      "eval_loss": 1.5971128940582275,
      "eval_runtime": 291.1278,
      "eval_samples_per_second": 2.542,
      "eval_steps_per_second": 1.271,
      "step": 5
    },
    {
      "epoch": 0.0034139402560455193,
      "grad_norm": 0.9191282987594604,
      "learning_rate": 0.00012,
      "loss": 1.5832,
      "step": 6
    },
    {
      "epoch": 0.003982930298719772,
      "grad_norm": 0.8483241200447083,
      "learning_rate": 0.00014,
      "loss": 1.657,
      "step": 7
    },
    {
      "epoch": 0.004551920341394026,
      "grad_norm": 1.2267595529556274,
      "learning_rate": 0.00016,
      "loss": 1.6163,
      "step": 8
    },
    {
      "epoch": 0.005120910384068279,
      "grad_norm": 1.5132993459701538,
      "learning_rate": 0.00018,
      "loss": 1.4569,
      "step": 9
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 1.449670433998108,
      "learning_rate": 0.0002,
      "loss": 1.6523,
      "step": 10
    },
    {
      "epoch": 0.005689900426742532,
      "eval_loss": 1.5192136764526367,
      "eval_runtime": 289.1277,
      "eval_samples_per_second": 2.559,
      "eval_steps_per_second": 1.28,
      "step": 10
    },
    {
      "epoch": 0.006258890469416785,
      "grad_norm": 1.0535948276519775,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.5521,
      "step": 11
    },
    {
      "epoch": 0.0068278805120910386,
      "grad_norm": 0.8515264987945557,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.6025,
      "step": 12
    },
    {
      "epoch": 0.007396870554765292,
      "grad_norm": 0.9776663184165955,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.5925,
      "step": 13
    },
    {
      "epoch": 0.007965860597439544,
      "grad_norm": 0.8630133867263794,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.4374,
      "step": 14
    },
    {
      "epoch": 0.008534850640113799,
      "grad_norm": 0.7540029287338257,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.476,
      "step": 15
    },
    {
      "epoch": 0.008534850640113799,
      "eval_loss": 1.4430253505706787,
      "eval_runtime": 290.3197,
      "eval_samples_per_second": 2.549,
      "eval_steps_per_second": 1.274,
      "step": 15
    },
    {
      "epoch": 0.009103840682788052,
      "grad_norm": 0.7366471290588379,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3592,
      "step": 16
    },
    {
      "epoch": 0.009672830725462305,
      "grad_norm": 0.7789183259010315,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.4968,
      "step": 17
    },
    {
      "epoch": 0.010241820768136558,
      "grad_norm": 0.7127480506896973,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.3537,
      "step": 18
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 0.7237548828125,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.41,
      "step": 19
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 0.840724527835846,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.5217,
      "step": 20
    },
    {
      "epoch": 0.011379800853485065,
      "eval_loss": 1.4222428798675537,
      "eval_runtime": 298.5166,
      "eval_samples_per_second": 2.479,
      "eval_steps_per_second": 1.239,
      "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": 7644365665075200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}