{
  "best_metric": 1.4608114957809448,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.011878600700837441,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.939300350418721e-05,
      "eval_loss": 1.8331416845321655,
      "eval_runtime": 430.6344,
      "eval_samples_per_second": 12.347,
      "eval_steps_per_second": 3.088,
      "step": 1
    },
    {
      "epoch": 0.0005939300350418721,
      "grad_norm": 2.968214273452759,
      "learning_rate": 5.095e-06,
      "loss": 1.5987,
      "step": 10
    },
    {
      "epoch": 0.0011878600700837441,
      "grad_norm": 2.5024313926696777,
      "learning_rate": 1.019e-05,
      "loss": 1.5744,
      "step": 20
    },
    {
      "epoch": 0.0017817901051256162,
      "grad_norm": 2.9678239822387695,
      "learning_rate": 9.623888888888889e-06,
      "loss": 1.572,
      "step": 30
    },
    {
      "epoch": 0.0023757201401674883,
      "grad_norm": 4.353546142578125,
      "learning_rate": 9.057777777777777e-06,
      "loss": 1.5805,
      "step": 40
    },
    {
      "epoch": 0.0029696501752093604,
      "grad_norm": 10.799284934997559,
      "learning_rate": 8.491666666666667e-06,
      "loss": 1.7313,
      "step": 50
    },
    {
      "epoch": 0.0029696501752093604,
      "eval_loss": 1.5447496175765991,
      "eval_runtime": 433.6896,
      "eval_samples_per_second": 12.26,
      "eval_steps_per_second": 3.067,
      "step": 50
    },
    {
      "epoch": 0.0035635802102512324,
      "grad_norm": 1.9188200235366821,
      "learning_rate": 7.925555555555557e-06,
      "loss": 1.4851,
      "step": 60
    },
    {
      "epoch": 0.004157510245293104,
      "grad_norm": 2.6333954334259033,
      "learning_rate": 7.359444444444445e-06,
      "loss": 1.4511,
      "step": 70
    },
    {
      "epoch": 0.004751440280334977,
      "grad_norm": 3.505038261413574,
      "learning_rate": 6.793333333333333e-06,
      "loss": 1.467,
      "step": 80
    },
    {
      "epoch": 0.005345370315376848,
      "grad_norm": 4.344202995300293,
      "learning_rate": 6.227222222222223e-06,
      "loss": 1.502,
      "step": 90
    },
    {
      "epoch": 0.005939300350418721,
      "grad_norm": 11.995814323425293,
      "learning_rate": 5.661111111111112e-06,
      "loss": 1.6424,
      "step": 100
    },
    {
      "epoch": 0.005939300350418721,
      "eval_loss": 1.4858251810073853,
      "eval_runtime": 434.3077,
      "eval_samples_per_second": 12.242,
      "eval_steps_per_second": 3.062,
      "step": 100
    },
    {
      "epoch": 0.006533230385460592,
      "grad_norm": 2.0615479946136475,
      "learning_rate": 5.095e-06,
      "loss": 1.4343,
      "step": 110
    },
    {
      "epoch": 0.007127160420502465,
      "grad_norm": 2.4463698863983154,
      "learning_rate": 4.5288888888888885e-06,
      "loss": 1.4471,
      "step": 120
    },
    {
      "epoch": 0.0077210904555443365,
      "grad_norm": 3.745335578918457,
      "learning_rate": 3.9627777777777784e-06,
      "loss": 1.4454,
      "step": 130
    },
    {
      "epoch": 0.008315020490586208,
      "grad_norm": 4.0279221534729,
      "learning_rate": 3.3966666666666666e-06,
      "loss": 1.4979,
      "step": 140
    },
    {
      "epoch": 0.008908950525628082,
      "grad_norm": 6.417429447174072,
      "learning_rate": 2.830555555555556e-06,
      "loss": 1.4139,
      "step": 150
    },
    {
      "epoch": 0.008908950525628082,
      "eval_loss": 1.4660513401031494,
      "eval_runtime": 433.0753,
      "eval_samples_per_second": 12.277,
      "eval_steps_per_second": 3.071,
      "step": 150
    },
    {
      "epoch": 0.009502880560669953,
      "grad_norm": 2.0533039569854736,
      "learning_rate": 2.2644444444444443e-06,
      "loss": 1.4115,
      "step": 160
    },
    {
      "epoch": 0.010096810595711825,
      "grad_norm": 2.7204930782318115,
      "learning_rate": 1.6983333333333333e-06,
      "loss": 1.4418,
      "step": 170
    },
    {
      "epoch": 0.010690740630753696,
      "grad_norm": 3.4697649478912354,
      "learning_rate": 1.1322222222222221e-06,
      "loss": 1.4363,
      "step": 180
    },
    {
      "epoch": 0.01128467066579557,
      "grad_norm": 4.115236282348633,
      "learning_rate": 5.661111111111111e-07,
      "loss": 1.4766,
      "step": 190
    },
    {
      "epoch": 0.011878600700837441,
      "grad_norm": 8.668231010437012,
      "learning_rate": 0.0,
      "loss": 1.6002,
      "step": 200
    },
    {
      "epoch": 0.011878600700837441,
      "eval_loss": 1.4608114957809448,
      "eval_runtime": 433.8437,
      "eval_samples_per_second": 12.256,
      "eval_steps_per_second": 3.066,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.834834505105408e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}