{
  "best_metric": 0.4509950280189514,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.001704049247023239,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.520246235116194e-05,
      "grad_norm": 13.800619125366211,
      "learning_rate": 2e-05,
      "loss": 3.9538,
      "step": 1
    },
    {
      "epoch": 8.520246235116194e-05,
      "eval_loss": 4.14320707321167,
      "eval_runtime": 1069.9506,
      "eval_samples_per_second": 4.619,
      "eval_steps_per_second": 2.309,
      "step": 1
    },
    {
      "epoch": 0.00017040492470232388,
      "grad_norm": 20.46969985961914,
      "learning_rate": 4e-05,
      "loss": 5.339,
      "step": 2
    },
    {
      "epoch": 0.00025560738705348587,
      "grad_norm": 11.057178497314453,
      "learning_rate": 6e-05,
      "loss": 3.1866,
      "step": 3
    },
    {
      "epoch": 0.00034080984940464777,
      "grad_norm": 13.554693222045898,
      "learning_rate": 8e-05,
      "loss": 2.9995,
      "step": 4
    },
    {
      "epoch": 0.0004260123117558097,
      "grad_norm": 13.165817260742188,
      "learning_rate": 0.0001,
      "loss": 3.2751,
      "step": 5
    },
    {
      "epoch": 0.0004260123117558097,
      "eval_loss": 3.6917104721069336,
      "eval_runtime": 1090.227,
      "eval_samples_per_second": 4.533,
      "eval_steps_per_second": 2.267,
      "step": 5
    },
    {
      "epoch": 0.0005112147741069717,
      "grad_norm": 6.886040687561035,
      "learning_rate": 0.00012,
      "loss": 3.3773,
      "step": 6
    },
    {
      "epoch": 0.0005964172364581337,
      "grad_norm": 5.9236226081848145,
      "learning_rate": 0.00014,
      "loss": 2.4765,
      "step": 7
    },
    {
      "epoch": 0.0006816196988092955,
      "grad_norm": 7.4425249099731445,
      "learning_rate": 0.00016,
      "loss": 3.1168,
      "step": 8
    },
    {
      "epoch": 0.0007668221611604575,
      "grad_norm": 5.86643648147583,
      "learning_rate": 0.00018,
      "loss": 2.4278,
      "step": 9
    },
    {
      "epoch": 0.0008520246235116195,
      "grad_norm": 7.741679668426514,
      "learning_rate": 0.0002,
      "loss": 2.5825,
      "step": 10
    },
    {
      "epoch": 0.0008520246235116195,
      "eval_loss": 2.016779899597168,
      "eval_runtime": 1095.0268,
      "eval_samples_per_second": 4.513,
      "eval_steps_per_second": 2.257,
      "step": 10
    },
    {
      "epoch": 0.0009372270858627814,
      "grad_norm": 7.080551624298096,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.8364,
      "step": 11
    },
    {
      "epoch": 0.0010224295482139435,
      "grad_norm": 7.222623348236084,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.5561,
      "step": 12
    },
    {
      "epoch": 0.0011076320105651053,
      "grad_norm": 8.51089096069336,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.6543,
      "step": 13
    },
    {
      "epoch": 0.0011928344729162674,
      "grad_norm": 9.265571594238281,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.7747,
      "step": 14
    },
    {
      "epoch": 0.0012780369352674292,
      "grad_norm": 5.150737285614014,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.9407,
      "step": 15
    },
    {
      "epoch": 0.0012780369352674292,
      "eval_loss": 0.961416482925415,
      "eval_runtime": 1061.4126,
      "eval_samples_per_second": 4.656,
      "eval_steps_per_second": 2.328,
      "step": 15
    },
    {
      "epoch": 0.001363239397618591,
      "grad_norm": 8.208329200744629,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.05,
      "step": 16
    },
    {
      "epoch": 0.0014484418599697531,
      "grad_norm": 6.162915229797363,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.8887,
      "step": 17
    },
    {
      "epoch": 0.001533644322320915,
      "grad_norm": 4.672049522399902,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.6028,
      "step": 18
    },
    {
      "epoch": 0.001618846784672077,
      "grad_norm": 3.763162136077881,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.481,
      "step": 19
    },
    {
      "epoch": 0.001704049247023239,
      "grad_norm": 3.6781723499298096,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.4966,
      "step": 20
    },
    {
      "epoch": 0.001704049247023239,
      "eval_loss": 0.4509950280189514,
      "eval_runtime": 1082.3453,
      "eval_samples_per_second": 4.566,
      "eval_steps_per_second": 2.283,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 153447605207040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}