{
  "best_metric": 0.8275464177131653,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.006595000989250148,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002638000395700059,
      "grad_norm": 7.552082538604736,
      "learning_rate": 5e-05,
      "loss": 2.2561,
      "step": 1
    },
    {
      "epoch": 0.0002638000395700059,
      "eval_loss": 4.780569553375244,
      "eval_runtime": 463.0518,
      "eval_samples_per_second": 55.151,
      "eval_steps_per_second": 6.896,
      "step": 1
    },
    {
      "epoch": 0.0005276000791400118,
      "grad_norm": 12.811338424682617,
      "learning_rate": 0.0001,
      "loss": 3.1953,
      "step": 2
    },
    {
      "epoch": 0.0007914001187100178,
      "grad_norm": 18.66082191467285,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.0871,
      "step": 3
    },
    {
      "epoch": 0.0010552001582800237,
      "grad_norm": 9.829119682312012,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.2412,
      "step": 4
    },
    {
      "epoch": 0.0013190001978500296,
      "grad_norm": 16.19348907470703,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.2669,
      "step": 5
    },
    {
      "epoch": 0.0015828002374200355,
      "grad_norm": 9.552570343017578,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.6689,
      "step": 6
    },
    {
      "epoch": 0.0018466002769900415,
      "grad_norm": 8.127283096313477,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.2706,
      "step": 7
    },
    {
      "epoch": 0.0021104003165600474,
      "grad_norm": 3.489779233932495,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9991,
      "step": 8
    },
    {
      "epoch": 0.0023742003561300533,
      "grad_norm": 3.768960475921631,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7926,
      "step": 9
    },
    {
      "epoch": 0.0026380003957000592,
      "grad_norm": 3.6079654693603516,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6851,
      "step": 10
    },
    {
      "epoch": 0.002901800435270065,
      "grad_norm": 4.310703277587891,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.4604,
      "step": 11
    },
    {
      "epoch": 0.003165600474840071,
      "grad_norm": 5.477931499481201,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.2806,
      "step": 12
    },
    {
      "epoch": 0.003429400514410077,
      "grad_norm": 4.753798007965088,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.1273,
      "step": 13
    },
    {
      "epoch": 0.003693200553980083,
      "grad_norm": 5.867488384246826,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1115,
      "step": 14
    },
    {
      "epoch": 0.003957000593550089,
      "grad_norm": 4.033467769622803,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.9478,
      "step": 15
    },
    {
      "epoch": 0.004220800633120095,
      "grad_norm": 1.9320178031921387,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8317,
      "step": 16
    },
    {
      "epoch": 0.004484600672690101,
      "grad_norm": 2.0492303371429443,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.795,
      "step": 17
    },
    {
      "epoch": 0.004748400712260107,
      "grad_norm": 2.7194154262542725,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7997,
      "step": 18
    },
    {
      "epoch": 0.0050122007518301126,
      "grad_norm": 1.8453177213668823,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.7701,
      "step": 19
    },
    {
      "epoch": 0.0052760007914001185,
      "grad_norm": 0.8213685154914856,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7212,
      "step": 20
    },
    {
      "epoch": 0.005539800830970124,
      "grad_norm": 0.5094491839408875,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.6822,
      "step": 21
    },
    {
      "epoch": 0.00580360087054013,
      "grad_norm": 0.6015544533729553,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.6931,
      "step": 22
    },
    {
      "epoch": 0.006067400910110136,
      "grad_norm": 0.5328494906425476,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.6923,
      "step": 23
    },
    {
      "epoch": 0.006331200949680142,
      "grad_norm": 0.3701467216014862,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.6792,
      "step": 24
    },
    {
      "epoch": 0.006595000989250148,
      "grad_norm": 0.3235287070274353,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.6937,
      "step": 25
    },
    {
      "epoch": 0.006595000989250148,
      "eval_loss": 0.8275464177131653,
      "eval_runtime": 462.4413,
      "eval_samples_per_second": 55.224,
      "eval_steps_per_second": 6.905,
      "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": 1.114626154561536e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}