{
  "best_metric": 2.7208340167999268,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.042105263157894736,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016842105263157896,
      "grad_norm": 26.168102264404297,
      "learning_rate": 2e-05,
      "loss": 11.1581,
      "step": 1
    },
    {
      "epoch": 0.0016842105263157896,
      "eval_loss": 2.928168296813965,
      "eval_runtime": 15.2304,
      "eval_samples_per_second": 16.415,
      "eval_steps_per_second": 8.207,
      "step": 1
    },
    {
      "epoch": 0.003368421052631579,
      "grad_norm": 27.121906280517578,
      "learning_rate": 4e-05,
      "loss": 9.5463,
      "step": 2
    },
    {
      "epoch": 0.0050526315789473685,
      "grad_norm": 30.599964141845703,
      "learning_rate": 6e-05,
      "loss": 11.7554,
      "step": 3
    },
    {
      "epoch": 0.006736842105263158,
      "grad_norm": 26.989221572875977,
      "learning_rate": 8e-05,
      "loss": 9.9618,
      "step": 4
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 35.38678741455078,
      "learning_rate": 0.0001,
      "loss": 10.161,
      "step": 5
    },
    {
      "epoch": 0.008421052631578947,
      "eval_loss": 2.913663625717163,
      "eval_runtime": 14.601,
      "eval_samples_per_second": 17.122,
      "eval_steps_per_second": 8.561,
      "step": 5
    },
    {
      "epoch": 0.010105263157894737,
      "grad_norm": 37.33038330078125,
      "learning_rate": 0.00012,
      "loss": 10.5732,
      "step": 6
    },
    {
      "epoch": 0.011789473684210527,
      "grad_norm": 25.94528579711914,
      "learning_rate": 0.00014,
      "loss": 9.1324,
      "step": 7
    },
    {
      "epoch": 0.013473684210526317,
      "grad_norm": 47.210079193115234,
      "learning_rate": 0.00016,
      "loss": 12.003,
      "step": 8
    },
    {
      "epoch": 0.015157894736842105,
      "grad_norm": 53.6414680480957,
      "learning_rate": 0.00018,
      "loss": 13.2918,
      "step": 9
    },
    {
      "epoch": 0.016842105263157894,
      "grad_norm": 38.67121887207031,
      "learning_rate": 0.0002,
      "loss": 10.7518,
      "step": 10
    },
    {
      "epoch": 0.016842105263157894,
      "eval_loss": 2.852686882019043,
      "eval_runtime": 14.609,
      "eval_samples_per_second": 17.113,
      "eval_steps_per_second": 8.556,
      "step": 10
    },
    {
      "epoch": 0.018526315789473686,
      "grad_norm": 27.88591766357422,
      "learning_rate": 0.00019781476007338058,
      "loss": 10.0682,
      "step": 11
    },
    {
      "epoch": 0.020210526315789474,
      "grad_norm": 43.37436294555664,
      "learning_rate": 0.0001913545457642601,
      "loss": 8.4794,
      "step": 12
    },
    {
      "epoch": 0.021894736842105262,
      "grad_norm": 35.257080078125,
      "learning_rate": 0.00018090169943749476,
      "loss": 8.8119,
      "step": 13
    },
    {
      "epoch": 0.023578947368421053,
      "grad_norm": 45.089637756347656,
      "learning_rate": 0.00016691306063588583,
      "loss": 11.5032,
      "step": 14
    },
    {
      "epoch": 0.02526315789473684,
      "grad_norm": 34.6796989440918,
      "learning_rate": 0.00015000000000000001,
      "loss": 9.2772,
      "step": 15
    },
    {
      "epoch": 0.02526315789473684,
      "eval_loss": 2.7734570503234863,
      "eval_runtime": 14.6233,
      "eval_samples_per_second": 17.096,
      "eval_steps_per_second": 8.548,
      "step": 15
    },
    {
      "epoch": 0.026947368421052633,
      "grad_norm": 33.94763946533203,
      "learning_rate": 0.00013090169943749476,
      "loss": 9.3693,
      "step": 16
    },
    {
      "epoch": 0.02863157894736842,
      "grad_norm": 35.127410888671875,
      "learning_rate": 0.00011045284632676536,
      "loss": 9.8971,
      "step": 17
    },
    {
      "epoch": 0.03031578947368421,
      "grad_norm": 87.55461120605469,
      "learning_rate": 8.954715367323468e-05,
      "loss": 13.3009,
      "step": 18
    },
    {
      "epoch": 0.032,
      "grad_norm": 52.973819732666016,
      "learning_rate": 6.909830056250527e-05,
      "loss": 9.2489,
      "step": 19
    },
    {
      "epoch": 0.03368421052631579,
      "grad_norm": 53.75153732299805,
      "learning_rate": 5.000000000000002e-05,
      "loss": 13.8616,
      "step": 20
    },
    {
      "epoch": 0.03368421052631579,
      "eval_loss": 2.732574224472046,
      "eval_runtime": 14.5453,
      "eval_samples_per_second": 17.188,
      "eval_steps_per_second": 8.594,
      "step": 20
    },
    {
      "epoch": 0.03536842105263158,
      "grad_norm": 40.93978500366211,
      "learning_rate": 3.308693936411421e-05,
      "loss": 9.9624,
      "step": 21
    },
    {
      "epoch": 0.03705263157894737,
      "grad_norm": 41.63092041015625,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 10.9608,
      "step": 22
    },
    {
      "epoch": 0.03873684210526316,
      "grad_norm": 34.82494354248047,
      "learning_rate": 8.645454235739903e-06,
      "loss": 11.4685,
      "step": 23
    },
    {
      "epoch": 0.04042105263157895,
      "grad_norm": 41.74858474731445,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 12.6479,
      "step": 24
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 42.13344192504883,
      "learning_rate": 0.0,
      "loss": 10.1041,
      "step": 25
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 2.7208340167999268,
      "eval_runtime": 14.6308,
      "eval_samples_per_second": 17.087,
      "eval_steps_per_second": 8.544,
      "step": 25
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 219321414451200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}