{
  "best_metric": 1.4965966939926147,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.07356998344675372,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003678499172337686,
      "eval_loss": 4.303531169891357,
      "eval_runtime": 107.0593,
      "eval_samples_per_second": 10.695,
      "eval_steps_per_second": 2.681,
      "step": 1
    },
    {
      "epoch": 0.0036784991723376862,
      "grad_norm": 1.8631224632263184,
      "learning_rate": 4.36e-05,
      "loss": 3.7124,
      "step": 10
    },
    {
      "epoch": 0.0073569983446753725,
      "grad_norm": 1.0357885360717773,
      "learning_rate": 8.72e-05,
      "loss": 2.3794,
      "step": 20
    },
    {
      "epoch": 0.011035497517013059,
      "grad_norm": 0.8365756273269653,
      "learning_rate": 0.0001308,
      "loss": 1.7752,
      "step": 30
    },
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 0.9363265037536621,
      "learning_rate": 0.0001744,
      "loss": 1.62,
      "step": 40
    },
    {
      "epoch": 0.01839249586168843,
      "grad_norm": 0.9486646056175232,
      "learning_rate": 0.000218,
      "loss": 1.4426,
      "step": 50
    },
    {
      "epoch": 0.01839249586168843,
      "eval_loss": 1.658852458000183,
      "eval_runtime": 107.1756,
      "eval_samples_per_second": 10.683,
      "eval_steps_per_second": 2.678,
      "step": 50
    },
    {
      "epoch": 0.022070995034026118,
      "grad_norm": 0.6641014814376831,
      "learning_rate": 0.00021773448147832086,
      "loss": 1.6935,
      "step": 60
    },
    {
      "epoch": 0.025749494206363802,
      "grad_norm": 0.6979497671127319,
      "learning_rate": 0.0002169392194928312,
      "loss": 1.5954,
      "step": 70
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 0.8027070760726929,
      "learning_rate": 0.00021561808847998484,
      "loss": 1.5455,
      "step": 80
    },
    {
      "epoch": 0.033106492551039174,
      "grad_norm": 0.6991447806358337,
      "learning_rate": 0.00021377752485727676,
      "loss": 1.4689,
      "step": 90
    },
    {
      "epoch": 0.03678499172337686,
      "grad_norm": 0.9628053903579712,
      "learning_rate": 0.00021142649566566402,
      "loss": 1.4403,
      "step": 100
    },
    {
      "epoch": 0.03678499172337686,
      "eval_loss": 1.5630460977554321,
      "eval_runtime": 107.2017,
      "eval_samples_per_second": 10.681,
      "eval_steps_per_second": 2.677,
      "step": 100
    },
    {
      "epoch": 0.04046349089571455,
      "grad_norm": 0.6026347875595093,
      "learning_rate": 0.0002085764548830435,
      "loss": 1.6232,
      "step": 110
    },
    {
      "epoch": 0.044141990068052236,
      "grad_norm": 0.7379695773124695,
      "learning_rate": 0.00020524128762162305,
      "loss": 1.4991,
      "step": 120
    },
    {
      "epoch": 0.047820489240389924,
      "grad_norm": 0.6722536683082581,
      "learning_rate": 0.00020143724248105043,
      "loss": 1.5017,
      "step": 130
    },
    {
      "epoch": 0.051498988412727605,
      "grad_norm": 0.6395397186279297,
      "learning_rate": 0.0001971828523868693,
      "loss": 1.4441,
      "step": 140
    },
    {
      "epoch": 0.05517748758506529,
      "grad_norm": 0.8695403933525085,
      "learning_rate": 0.0001924988442999686,
      "loss": 1.3411,
      "step": 150
    },
    {
      "epoch": 0.05517748758506529,
      "eval_loss": 1.5262999534606934,
      "eval_runtime": 107.2361,
      "eval_samples_per_second": 10.677,
      "eval_steps_per_second": 2.676,
      "step": 150
    },
    {
      "epoch": 0.05885598675740298,
      "grad_norm": 0.6810901165008545,
      "learning_rate": 0.00018740803823691298,
      "loss": 1.5936,
      "step": 160
    },
    {
      "epoch": 0.06253448592974066,
      "grad_norm": 0.657184362411499,
      "learning_rate": 0.00018193523609311556,
      "loss": 1.5681,
      "step": 170
    },
    {
      "epoch": 0.06621298510207835,
      "grad_norm": 0.6586466431617737,
      "learning_rate": 0.00017610710081049675,
      "loss": 1.4321,
      "step": 180
    },
    {
      "epoch": 0.06989148427441604,
      "grad_norm": 0.7010196447372437,
      "learning_rate": 0.00016995202647831142,
      "loss": 1.3784,
      "step": 190
    },
    {
      "epoch": 0.07356998344675372,
      "grad_norm": 0.8979406356811523,
      "learning_rate": 0.00016350000000000002,
      "loss": 1.341,
      "step": 200
    },
    {
      "epoch": 0.07356998344675372,
      "eval_loss": 1.4965966939926147,
      "eval_runtime": 107.3593,
      "eval_samples_per_second": 10.665,
      "eval_steps_per_second": 2.673,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 6.7033928564736e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}