{
  "best_metric": 4.673962593078613,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.043544524276072284,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017417809710428913,
      "grad_norm": 1042.4998779296875,
      "learning_rate": 5e-05,
      "loss": 52.678,
      "step": 1
    },
    {
      "epoch": 0.0017417809710428913,
      "eval_loss": 95.80888366699219,
      "eval_runtime": 128.0354,
      "eval_samples_per_second": 30.21,
      "eval_steps_per_second": 3.78,
      "step": 1
    },
    {
      "epoch": 0.0034835619420857827,
      "grad_norm": 1335.59716796875,
      "learning_rate": 0.0001,
      "loss": 66.1445,
      "step": 2
    },
    {
      "epoch": 0.005225342913128674,
      "grad_norm": 244.45648193359375,
      "learning_rate": 9.989294616193017e-05,
      "loss": 54.2622,
      "step": 3
    },
    {
      "epoch": 0.006967123884171565,
      "grad_norm": 182.58251953125,
      "learning_rate": 9.957224306869053e-05,
      "loss": 44.3626,
      "step": 4
    },
    {
      "epoch": 0.008708904855214456,
      "grad_norm": 222.32257080078125,
      "learning_rate": 9.903926402016153e-05,
      "loss": 37.7121,
      "step": 5
    },
    {
      "epoch": 0.010450685826257348,
      "grad_norm": 240.82568359375,
      "learning_rate": 9.829629131445342e-05,
      "loss": 22.2959,
      "step": 6
    },
    {
      "epoch": 0.012192466797300239,
      "grad_norm": 252.58872985839844,
      "learning_rate": 9.73465064747553e-05,
      "loss": 7.2634,
      "step": 7
    },
    {
      "epoch": 0.01393424776834313,
      "grad_norm": 8.834219932556152,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.4485,
      "step": 8
    },
    {
      "epoch": 0.015676028739386023,
      "grad_norm": 7.470920085906982,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.4602,
      "step": 9
    },
    {
      "epoch": 0.017417809710428913,
      "grad_norm": 48.436824798583984,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.6101,
      "step": 10
    },
    {
      "epoch": 0.019159590681471803,
      "grad_norm": 39.14765167236328,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.5374,
      "step": 11
    },
    {
      "epoch": 0.020901371652514697,
      "grad_norm": 11.199342727661133,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.44,
      "step": 12
    },
    {
      "epoch": 0.022643152623557587,
      "grad_norm": 13.544066429138184,
      "learning_rate": 8.759199037394887e-05,
      "loss": 5.8266,
      "step": 13
    },
    {
      "epoch": 0.024384933594600477,
      "grad_norm": 9.120245933532715,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.4304,
      "step": 14
    },
    {
      "epoch": 0.02612671456564337,
      "grad_norm": 7.594675540924072,
      "learning_rate": 8.296729075500344e-05,
      "loss": 4.802,
      "step": 15
    },
    {
      "epoch": 0.02786849553668626,
      "grad_norm": 6.660674571990967,
      "learning_rate": 8.043807145043604e-05,
      "loss": 4.5614,
      "step": 16
    },
    {
      "epoch": 0.029610276507729152,
      "grad_norm": 7.0615925788879395,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.4997,
      "step": 17
    },
    {
      "epoch": 0.031352057478772045,
      "grad_norm": 6.209261417388916,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.6316,
      "step": 18
    },
    {
      "epoch": 0.033093838449814936,
      "grad_norm": 7.270112991333008,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.6835,
      "step": 19
    },
    {
      "epoch": 0.034835619420857826,
      "grad_norm": 15.498638153076172,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.5747,
      "step": 20
    },
    {
      "epoch": 0.036577400391900716,
      "grad_norm": 8.84870719909668,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.4316,
      "step": 21
    },
    {
      "epoch": 0.038319181362943606,
      "grad_norm": 6.131610870361328,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.4651,
      "step": 22
    },
    {
      "epoch": 0.040060962333986504,
      "grad_norm": 8.077975273132324,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.8909,
      "step": 23
    },
    {
      "epoch": 0.041802743305029394,
      "grad_norm": 4.703813076019287,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.6565,
      "step": 24
    },
    {
      "epoch": 0.043544524276072284,
      "grad_norm": 8.461095809936523,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.8622,
      "step": 25
    },
    {
      "epoch": 0.043544524276072284,
      "eval_loss": 4.673962593078613,
      "eval_runtime": 128.7456,
      "eval_samples_per_second": 30.044,
      "eval_steps_per_second": 3.759,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 3.087239672233984e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}