{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.5444015444015444,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03088803088803089,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 19398584.0,
      "step": 1
    },
    {
      "epoch": 0.03088803088803089,
      "eval_loss": NaN,
      "eval_runtime": 1.4046,
      "eval_samples_per_second": 35.598,
      "eval_steps_per_second": 9.255,
      "step": 1
    },
    {
      "epoch": 0.06177606177606178,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.09266409266409266,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.12355212355212356,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": NaN,
      "learning_rate": 9.997487036786146e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.18532818532818532,
      "grad_norm": NaN,
      "learning_rate": 9.98995095380419e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": NaN,
      "learning_rate": 9.977400167898269e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.2471042471042471,
      "grad_norm": NaN,
      "learning_rate": 9.959848696696512e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.277992277992278,
      "grad_norm": NaN,
      "learning_rate": 9.937316142955128e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": NaN,
      "learning_rate": 9.90982767266464e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.33976833976833976,
      "grad_norm": NaN,
      "learning_rate": 9.877413986942667e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.37065637065637064,
      "grad_norm": NaN,
      "learning_rate": 9.840111287744695e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.4015444015444015,
      "grad_norm": NaN,
      "learning_rate": 9.797961237431105e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": NaN,
      "learning_rate": 9.751010912235635e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.46332046332046334,
      "grad_norm": NaN,
      "learning_rate": 9.699312749687212e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.4942084942084942,
      "grad_norm": NaN,
      "learning_rate": 9.642924490043929e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.525096525096525,
      "grad_norm": NaN,
      "learning_rate": 9.581909111804534e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.555984555984556,
      "grad_norm": NaN,
      "learning_rate": 9.516334761369466e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.5868725868725869,
      "grad_norm": NaN,
      "learning_rate": 9.446274676930022e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": NaN,
      "learning_rate": 9.371807106670628e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": NaN,
      "learning_rate": 9.293015221375587e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.6795366795366795,
      "grad_norm": NaN,
      "learning_rate": 9.209987021537921e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.7104247104247104,
      "grad_norm": NaN,
      "learning_rate": 9.122815239074034e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.7413127413127413,
      "grad_norm": NaN,
      "learning_rate": 9.031597233753974e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.7722007722007722,
      "grad_norm": NaN,
      "learning_rate": 8.936434884462995e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.7722007722007722,
      "eval_loss": NaN,
      "eval_runtime": 1.4052,
      "eval_samples_per_second": 35.581,
      "eval_steps_per_second": 9.251,
      "step": 25
    },
    {
      "epoch": 0.803088803088803,
      "grad_norm": NaN,
      "learning_rate": 8.83743447541581e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.833976833976834,
      "grad_norm": NaN,
      "learning_rate": 8.734706577450683e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": NaN,
      "learning_rate": 8.628365924535892e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.8957528957528957,
      "grad_norm": NaN,
      "learning_rate": 8.518531285626507e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": NaN,
      "learning_rate": 8.405325332014611e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.9575289575289575,
      "grad_norm": NaN,
      "learning_rate": 8.288874500321102e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.9884169884169884,
      "grad_norm": NaN,
      "learning_rate": 8.169308851282099e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 1.0193050193050193,
      "grad_norm": NaN,
      "learning_rate": 8.046761924487679e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 1.05019305019305,
      "grad_norm": NaN,
      "learning_rate": 7.921370589235178e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": NaN,
      "learning_rate": 7.793274891663629e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 1.111969111969112,
      "grad_norm": NaN,
      "learning_rate": 7.662617898340078e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": NaN,
      "learning_rate": 7.529545536472458e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 1.1737451737451738,
      "grad_norm": NaN,
      "learning_rate": 7.394206430927509e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 1.2046332046332047,
      "grad_norm": NaN,
      "learning_rate": 7.256751738235726e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 1.2355212355212355,
      "grad_norm": NaN,
      "learning_rate": 7.117334977768807e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 1.2664092664092665,
      "grad_norm": NaN,
      "learning_rate": 6.97611186027806e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": NaN,
      "learning_rate": 6.833240113985353e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 1.3281853281853282,
      "grad_norm": NaN,
      "learning_rate": 6.688879308420789e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 1.359073359073359,
      "grad_norm": NaN,
      "learning_rate": 6.543190676203878e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 1.3899613899613898,
      "grad_norm": NaN,
      "learning_rate": 6.396336932967262e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 1.420849420849421,
      "grad_norm": NaN,
      "learning_rate": 6.248482095624086e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 1.4517374517374517,
      "grad_norm": NaN,
      "learning_rate": 6.0997912991820064e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 1.4826254826254825,
      "grad_norm": NaN,
      "learning_rate": 5.950430612308444e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": NaN,
      "learning_rate": 5.8005668518530475e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 1.5444015444015444,
      "grad_norm": NaN,
      "learning_rate": 5.650367396534536e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 1.5444015444015444,
      "eval_loss": NaN,
      "eval_runtime": 1.405,
      "eval_samples_per_second": 35.587,
      "eval_steps_per_second": 9.253,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 98,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.624057810649088e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}