{
  "best_metric": 2.641629695892334,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.06912044237083118,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002764817694833247,
      "grad_norm": 1.1742911338806152,
      "learning_rate": 5e-05,
      "loss": 2.6986,
      "step": 1
    },
    {
      "epoch": 0.002764817694833247,
      "eval_loss": 2.875308036804199,
      "eval_runtime": 16.7408,
      "eval_samples_per_second": 145.572,
      "eval_steps_per_second": 18.219,
      "step": 1
    },
    {
      "epoch": 0.005529635389666494,
      "grad_norm": 1.2949481010437012,
      "learning_rate": 0.0001,
      "loss": 2.7546,
      "step": 2
    },
    {
      "epoch": 0.00829445308449974,
      "grad_norm": 1.0101735591888428,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.6672,
      "step": 3
    },
    {
      "epoch": 0.011059270779332988,
      "grad_norm": 0.9494262337684631,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.6501,
      "step": 4
    },
    {
      "epoch": 0.013824088474166234,
      "grad_norm": 0.944379985332489,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.6389,
      "step": 5
    },
    {
      "epoch": 0.01658890616899948,
      "grad_norm": 0.9478722810745239,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.6936,
      "step": 6
    },
    {
      "epoch": 0.019353723863832727,
      "grad_norm": 0.9653313755989075,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.6917,
      "step": 7
    },
    {
      "epoch": 0.022118541558665977,
      "grad_norm": 0.9041957855224609,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.6873,
      "step": 8
    },
    {
      "epoch": 0.024883359253499222,
      "grad_norm": 0.8747812509536743,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.7184,
      "step": 9
    },
    {
      "epoch": 0.027648176948332468,
      "grad_norm": 0.9741718173027039,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.6142,
      "step": 10
    },
    {
      "epoch": 0.030412994643165717,
      "grad_norm": 1.4103081226348877,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.6527,
      "step": 11
    },
    {
      "epoch": 0.03317781233799896,
      "grad_norm": 1.8044036626815796,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.685,
      "step": 12
    },
    {
      "epoch": 0.03594263003283221,
      "grad_norm": 1.9407167434692383,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.6937,
      "step": 13
    },
    {
      "epoch": 0.038707447727665455,
      "grad_norm": 2.277519941329956,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7815,
      "step": 14
    },
    {
      "epoch": 0.041472265422498704,
      "grad_norm": 2.2202413082122803,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.7259,
      "step": 15
    },
    {
      "epoch": 0.04423708311733195,
      "grad_norm": 1.8662134408950806,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.7203,
      "step": 16
    },
    {
      "epoch": 0.047001900812165195,
      "grad_norm": 1.5702985525131226,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.6468,
      "step": 17
    },
    {
      "epoch": 0.049766718506998445,
      "grad_norm": 1.2403249740600586,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.6034,
      "step": 18
    },
    {
      "epoch": 0.052531536201831694,
      "grad_norm": 0.9190433621406555,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.5819,
      "step": 19
    },
    {
      "epoch": 0.055296353896664936,
      "grad_norm": 0.7897427082061768,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.6424,
      "step": 20
    },
    {
      "epoch": 0.058061171591498185,
      "grad_norm": 0.911276638507843,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.5984,
      "step": 21
    },
    {
      "epoch": 0.060825989286331435,
      "grad_norm": 1.3512458801269531,
      "learning_rate": 6.294095225512603e-05,
      "loss": 2.6273,
      "step": 22
    },
    {
      "epoch": 0.06359080698116468,
      "grad_norm": 1.441872000694275,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 2.6648,
      "step": 23
    },
    {
      "epoch": 0.06635562467599793,
      "grad_norm": 1.8847798109054565,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.6991,
      "step": 24
    },
    {
      "epoch": 0.06912044237083118,
      "grad_norm": 3.8344838619232178,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.8208,
      "step": 25
    },
    {
      "epoch": 0.06912044237083118,
      "eval_loss": 2.641629695892334,
      "eval_runtime": 16.7537,
      "eval_samples_per_second": 145.46,
      "eval_steps_per_second": 18.205,
      "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": 1.47650456322048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}