{
  "best_metric": 1.550691843032837,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.00207671380807011,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.30685523228044e-05,
      "grad_norm": 0.32762518525123596,
      "learning_rate": 2e-05,
      "loss": 1.3143,
      "step": 1
    },
    {
      "epoch": 8.30685523228044e-05,
      "eval_loss": 2.673133611679077,
      "eval_runtime": 710.3871,
      "eval_samples_per_second": 7.136,
      "eval_steps_per_second": 3.568,
      "step": 1
    },
    {
      "epoch": 0.0001661371046456088,
      "grad_norm": 0.3983103036880493,
      "learning_rate": 4e-05,
      "loss": 0.9697,
      "step": 2
    },
    {
      "epoch": 0.00024920565696841317,
      "grad_norm": 0.48327869176864624,
      "learning_rate": 6e-05,
      "loss": 1.8776,
      "step": 3
    },
    {
      "epoch": 0.0003322742092912176,
      "grad_norm": 0.6413305401802063,
      "learning_rate": 8e-05,
      "loss": 1.7683,
      "step": 4
    },
    {
      "epoch": 0.000415342761614022,
      "grad_norm": 0.8627868890762329,
      "learning_rate": 0.0001,
      "loss": 1.8095,
      "step": 5
    },
    {
      "epoch": 0.000415342761614022,
      "eval_loss": 2.658660411834717,
      "eval_runtime": 710.1991,
      "eval_samples_per_second": 7.137,
      "eval_steps_per_second": 3.569,
      "step": 5
    },
    {
      "epoch": 0.0004984113139368263,
      "grad_norm": 0.4515976905822754,
      "learning_rate": 0.00012,
      "loss": 1.573,
      "step": 6
    },
    {
      "epoch": 0.0005814798662596307,
      "grad_norm": 1.1740977764129639,
      "learning_rate": 0.00014,
      "loss": 2.1893,
      "step": 7
    },
    {
      "epoch": 0.0006645484185824351,
      "grad_norm": 0.3599812984466553,
      "learning_rate": 0.00016,
      "loss": 1.1012,
      "step": 8
    },
    {
      "epoch": 0.0007476169709052396,
      "grad_norm": 0.5296670198440552,
      "learning_rate": 0.00018,
      "loss": 0.839,
      "step": 9
    },
    {
      "epoch": 0.000830685523228044,
      "grad_norm": 1.0727394819259644,
      "learning_rate": 0.0002,
      "loss": 1.8014,
      "step": 10
    },
    {
      "epoch": 0.000830685523228044,
      "eval_loss": 2.3930716514587402,
      "eval_runtime": 710.191,
      "eval_samples_per_second": 7.138,
      "eval_steps_per_second": 3.569,
      "step": 10
    },
    {
      "epoch": 0.0009137540755508484,
      "grad_norm": 0.43717700242996216,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.3097,
      "step": 11
    },
    {
      "epoch": 0.0009968226278736527,
      "grad_norm": 0.30268394947052,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.5942,
      "step": 12
    },
    {
      "epoch": 0.001079891180196457,
      "grad_norm": 0.6315892934799194,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.9464,
      "step": 13
    },
    {
      "epoch": 0.0011629597325192615,
      "grad_norm": 0.6325842142105103,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.3774,
      "step": 14
    },
    {
      "epoch": 0.0012460282848420659,
      "grad_norm": 0.46130749583244324,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2938,
      "step": 15
    },
    {
      "epoch": 0.0012460282848420659,
      "eval_loss": 1.8308182954788208,
      "eval_runtime": 720.8588,
      "eval_samples_per_second": 7.032,
      "eval_steps_per_second": 3.517,
      "step": 15
    },
    {
      "epoch": 0.0013290968371648703,
      "grad_norm": 0.438463419675827,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.114,
      "step": 16
    },
    {
      "epoch": 0.0014121653894876747,
      "grad_norm": 0.6048122048377991,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.6473,
      "step": 17
    },
    {
      "epoch": 0.001495233941810479,
      "grad_norm": 1.1923956871032715,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.4638,
      "step": 18
    },
    {
      "epoch": 0.0015783024941332835,
      "grad_norm": 0.5673062801361084,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6572,
      "step": 19
    },
    {
      "epoch": 0.001661371046456088,
      "grad_norm": 0.7221763730049133,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.3469,
      "step": 20
    },
    {
      "epoch": 0.001661371046456088,
      "eval_loss": 1.5932053327560425,
      "eval_runtime": 718.0656,
      "eval_samples_per_second": 7.059,
      "eval_steps_per_second": 3.53,
      "step": 20
    },
    {
      "epoch": 0.0017444395987788923,
      "grad_norm": 0.8490703701972961,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.8171,
      "step": 21
    },
    {
      "epoch": 0.0018275081511016967,
      "grad_norm": 0.4198557734489441,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.4519,
      "step": 22
    },
    {
      "epoch": 0.0019105767034245011,
      "grad_norm": 0.5982875823974609,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.4833,
      "step": 23
    },
    {
      "epoch": 0.0019936452557473053,
      "grad_norm": 0.6316483020782471,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.8351,
      "step": 24
    },
    {
      "epoch": 0.00207671380807011,
      "grad_norm": 0.4150454103946686,
      "learning_rate": 0.0,
      "loss": 0.5263,
      "step": 25
    },
    {
      "epoch": 0.00207671380807011,
      "eval_loss": 1.550691843032837,
      "eval_runtime": 718.3958,
      "eval_samples_per_second": 7.056,
      "eval_steps_per_second": 3.529,
      "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": 2808666677575680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}