{
  "best_metric": 1.5912128686904907,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06212144742972511,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024848578971890046,
      "grad_norm": 2.2064015865325928,
      "learning_rate": 2e-05,
      "loss": 1.3872,
      "step": 1
    },
    {
      "epoch": 0.0024848578971890046,
      "eval_loss": 2.3529415130615234,
      "eval_runtime": 0.5026,
      "eval_samples_per_second": 99.477,
      "eval_steps_per_second": 25.864,
      "step": 1
    },
    {
      "epoch": 0.004969715794378009,
      "grad_norm": 2.8333449363708496,
      "learning_rate": 4e-05,
      "loss": 1.4444,
      "step": 2
    },
    {
      "epoch": 0.007454573691567014,
      "grad_norm": 1.8522814512252808,
      "learning_rate": 6e-05,
      "loss": 1.5417,
      "step": 3
    },
    {
      "epoch": 0.009939431588756018,
      "grad_norm": 0.7707993388175964,
      "learning_rate": 8e-05,
      "loss": 1.5648,
      "step": 4
    },
    {
      "epoch": 0.012424289485945022,
      "grad_norm": 0.8538352251052856,
      "learning_rate": 0.0001,
      "loss": 1.6446,
      "step": 5
    },
    {
      "epoch": 0.014909147383134027,
      "grad_norm": 1.292691946029663,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.8205,
      "step": 6
    },
    {
      "epoch": 0.017394005280323033,
      "grad_norm": 1.3566771745681763,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.888,
      "step": 7
    },
    {
      "epoch": 0.019878863177512036,
      "grad_norm": 1.3478772640228271,
      "learning_rate": 9.977873061452552e-05,
      "loss": 2.0025,
      "step": 8
    },
    {
      "epoch": 0.02236372107470104,
      "grad_norm": 2.3724148273468018,
      "learning_rate": 9.96068831197139e-05,
      "loss": 2.3861,
      "step": 9
    },
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 2.5542187690734863,
      "learning_rate": 9.938625865312251e-05,
      "loss": 2.4441,
      "step": 10
    },
    {
      "epoch": 0.02733343686907905,
      "grad_norm": 2.9612715244293213,
      "learning_rate": 9.911709846436641e-05,
      "loss": 2.4473,
      "step": 11
    },
    {
      "epoch": 0.029818294766268055,
      "grad_norm": 3.946715831756592,
      "learning_rate": 9.879969687616027e-05,
      "loss": 2.796,
      "step": 12
    },
    {
      "epoch": 0.03230315266345706,
      "grad_norm": 0.6914235949516296,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.2153,
      "step": 13
    },
    {
      "epoch": 0.034788010560646065,
      "grad_norm": 0.5879468321800232,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.3014,
      "step": 14
    },
    {
      "epoch": 0.03727286845783507,
      "grad_norm": 0.4194982051849365,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.3002,
      "step": 15
    },
    {
      "epoch": 0.03975772635502407,
      "grad_norm": 0.43755513429641724,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.3616,
      "step": 16
    },
    {
      "epoch": 0.042242584252213077,
      "grad_norm": 0.35957348346710205,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.3768,
      "step": 17
    },
    {
      "epoch": 0.04472744214940208,
      "grad_norm": 0.4144904911518097,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.4022,
      "step": 18
    },
    {
      "epoch": 0.047212300046591084,
      "grad_norm": 0.46732762455940247,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.4593,
      "step": 19
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 0.5609594583511353,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.5165,
      "step": 20
    },
    {
      "epoch": 0.05218201584096909,
      "grad_norm": 0.7970541715621948,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.7275,
      "step": 21
    },
    {
      "epoch": 0.0546668737381581,
      "grad_norm": 1.0460487604141235,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.8141,
      "step": 22
    },
    {
      "epoch": 0.057151731635347106,
      "grad_norm": 1.3908549547195435,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.8613,
      "step": 23
    },
    {
      "epoch": 0.05963658953253611,
      "grad_norm": 1.8160243034362793,
      "learning_rate": 9.140576474687264e-05,
      "loss": 2.2734,
      "step": 24
    },
    {
      "epoch": 0.06212144742972511,
      "grad_norm": 2.9735653400421143,
      "learning_rate": 9.051132292283771e-05,
      "loss": 2.7456,
      "step": 25
    },
    {
      "epoch": 0.06212144742972511,
      "eval_loss": 1.5912128686904907,
      "eval_runtime": 0.502,
      "eval_samples_per_second": 99.599,
      "eval_steps_per_second": 25.896,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 4.16708196040704e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}