{
  "best_metric": 1.3513970375061035,
  "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": 0.18750134110450745,
      "learning_rate": 2e-05,
      "loss": 1.1205,
      "step": 1
    },
    {
      "epoch": 0.0024848578971890046,
      "eval_loss": 1.5502378940582275,
      "eval_runtime": 1.16,
      "eval_samples_per_second": 43.105,
      "eval_steps_per_second": 11.207,
      "step": 1
    },
    {
      "epoch": 0.004969715794378009,
      "grad_norm": 0.2050493061542511,
      "learning_rate": 4e-05,
      "loss": 1.1432,
      "step": 2
    },
    {
      "epoch": 0.007454573691567014,
      "grad_norm": 0.23336094617843628,
      "learning_rate": 6e-05,
      "loss": 1.1906,
      "step": 3
    },
    {
      "epoch": 0.009939431588756018,
      "grad_norm": 0.2642175257205963,
      "learning_rate": 8e-05,
      "loss": 1.2138,
      "step": 4
    },
    {
      "epoch": 0.012424289485945022,
      "grad_norm": 0.2873069941997528,
      "learning_rate": 0.0001,
      "loss": 1.2386,
      "step": 5
    },
    {
      "epoch": 0.014909147383134027,
      "grad_norm": 0.3289160430431366,
      "learning_rate": 9.997539658034168e-05,
      "loss": 1.3354,
      "step": 6
    },
    {
      "epoch": 0.017394005280323033,
      "grad_norm": 0.3904762864112854,
      "learning_rate": 9.990161322484486e-05,
      "loss": 1.3982,
      "step": 7
    },
    {
      "epoch": 0.019878863177512036,
      "grad_norm": 0.5013667941093445,
      "learning_rate": 9.977873061452552e-05,
      "loss": 1.4638,
      "step": 8
    },
    {
      "epoch": 0.02236372107470104,
      "grad_norm": 0.7098448872566223,
      "learning_rate": 9.96068831197139e-05,
      "loss": 1.6263,
      "step": 9
    },
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 0.9447751641273499,
      "learning_rate": 9.938625865312251e-05,
      "loss": 1.6602,
      "step": 10
    },
    {
      "epoch": 0.02733343686907905,
      "grad_norm": 1.1918106079101562,
      "learning_rate": 9.911709846436641e-05,
      "loss": 1.7242,
      "step": 11
    },
    {
      "epoch": 0.029818294766268055,
      "grad_norm": 1.6665799617767334,
      "learning_rate": 9.879969687616027e-05,
      "loss": 1.9561,
      "step": 12
    },
    {
      "epoch": 0.03230315266345706,
      "grad_norm": 0.5675529837608337,
      "learning_rate": 9.84344009624807e-05,
      "loss": 1.0769,
      "step": 13
    },
    {
      "epoch": 0.034788010560646065,
      "grad_norm": 0.7401061058044434,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.1726,
      "step": 14
    },
    {
      "epoch": 0.03727286845783507,
      "grad_norm": 0.6895852088928223,
      "learning_rate": 9.756177587652856e-05,
      "loss": 1.1816,
      "step": 15
    },
    {
      "epoch": 0.03975772635502407,
      "grad_norm": 0.6290579438209534,
      "learning_rate": 9.705540090697575e-05,
      "loss": 1.2386,
      "step": 16
    },
    {
      "epoch": 0.042242584252213077,
      "grad_norm": 0.550385057926178,
      "learning_rate": 9.650303897398232e-05,
      "loss": 1.2365,
      "step": 17
    },
    {
      "epoch": 0.04472744214940208,
      "grad_norm": 0.4426826238632202,
      "learning_rate": 9.590529407721231e-05,
      "loss": 1.2245,
      "step": 18
    },
    {
      "epoch": 0.047212300046591084,
      "grad_norm": 0.3795057535171509,
      "learning_rate": 9.526281984193436e-05,
      "loss": 1.2883,
      "step": 19
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 1.7804195880889893,
      "learning_rate": 9.4576318804292e-05,
      "loss": 1.3227,
      "step": 20
    },
    {
      "epoch": 0.05218201584096909,
      "grad_norm": 0.46404874324798584,
      "learning_rate": 9.384654164309083e-05,
      "loss": 1.5023,
      "step": 21
    },
    {
      "epoch": 0.0546668737381581,
      "grad_norm": 0.63600754737854,
      "learning_rate": 9.30742863589421e-05,
      "loss": 1.5474,
      "step": 22
    },
    {
      "epoch": 0.057151731635347106,
      "grad_norm": 0.8300634622573853,
      "learning_rate": 9.226039740166091e-05,
      "loss": 1.5191,
      "step": 23
    },
    {
      "epoch": 0.05963658953253611,
      "grad_norm": 1.0977858304977417,
      "learning_rate": 9.140576474687264e-05,
      "loss": 1.877,
      "step": 24
    },
    {
      "epoch": 0.06212144742972511,
      "grad_norm": 1.9869602918624878,
      "learning_rate": 9.051132292283771e-05,
      "loss": 2.3241,
      "step": 25
    },
    {
      "epoch": 0.06212144742972511,
      "eval_loss": 1.3513970375061035,
      "eval_runtime": 1.193,
      "eval_samples_per_second": 41.912,
      "eval_steps_per_second": 10.897,
      "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
}