{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.008437394532568343,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016874789065136686,
      "grad_norm": 1.204833279189188e-05,
      "learning_rate": 1.007e-05,
      "loss": 23.0,
      "step": 1
    },
    {
      "epoch": 0.00016874789065136686,
      "eval_loss": 11.5,
      "eval_runtime": 31.0185,
      "eval_samples_per_second": 80.436,
      "eval_steps_per_second": 20.117,
      "step": 1
    },
    {
      "epoch": 0.0003374957813027337,
      "grad_norm": 1.1431009625084698e-05,
      "learning_rate": 2.014e-05,
      "loss": 23.0,
      "step": 2
    },
    {
      "epoch": 0.0005062436719541006,
      "grad_norm": 1.5091093700903002e-05,
      "learning_rate": 3.0209999999999997e-05,
      "loss": 23.0,
      "step": 3
    },
    {
      "epoch": 0.0006749915626054674,
      "grad_norm": 1.993294426938519e-05,
      "learning_rate": 4.028e-05,
      "loss": 23.0,
      "step": 4
    },
    {
      "epoch": 0.0008437394532568343,
      "grad_norm": 1.4757441022084095e-05,
      "learning_rate": 5.035e-05,
      "loss": 23.0,
      "step": 5
    },
    {
      "epoch": 0.0010124873439082012,
      "grad_norm": 1.3547244634537492e-05,
      "learning_rate": 6.0419999999999994e-05,
      "loss": 23.0,
      "step": 6
    },
    {
      "epoch": 0.001181235234559568,
      "grad_norm": 1.6674213838996366e-05,
      "learning_rate": 7.049e-05,
      "loss": 23.0,
      "step": 7
    },
    {
      "epoch": 0.0013499831252109348,
      "grad_norm": 1.7742673662723973e-05,
      "learning_rate": 8.056e-05,
      "loss": 23.0,
      "step": 8
    },
    {
      "epoch": 0.0015187310158623017,
      "grad_norm": 1.2505891390901525e-05,
      "learning_rate": 9.062999999999999e-05,
      "loss": 23.0,
      "step": 9
    },
    {
      "epoch": 0.0016874789065136687,
      "grad_norm": 1.3835131539963186e-05,
      "learning_rate": 0.0001007,
      "loss": 23.0,
      "step": 10
    },
    {
      "epoch": 0.0018562267971650355,
      "grad_norm": 2.4900897187762894e-05,
      "learning_rate": 0.00010017,
      "loss": 23.0,
      "step": 11
    },
    {
      "epoch": 0.0020249746878164025,
      "grad_norm": 1.7070025933207944e-05,
      "learning_rate": 9.963999999999999e-05,
      "loss": 23.0,
      "step": 12
    },
    {
      "epoch": 0.0021937225784677693,
      "grad_norm": 2.7361658794688992e-05,
      "learning_rate": 9.910999999999999e-05,
      "loss": 23.0,
      "step": 13
    },
    {
      "epoch": 0.002362470469119136,
      "grad_norm": 1.2697471902356483e-05,
      "learning_rate": 9.858e-05,
      "loss": 23.0,
      "step": 14
    },
    {
      "epoch": 0.002531218359770503,
      "grad_norm": 1.9702922145370394e-05,
      "learning_rate": 9.805e-05,
      "loss": 23.0,
      "step": 15
    },
    {
      "epoch": 0.0026999662504218697,
      "grad_norm": 2.4902374207158573e-05,
      "learning_rate": 9.752e-05,
      "loss": 23.0,
      "step": 16
    },
    {
      "epoch": 0.0028687141410732365,
      "grad_norm": 2.721859527810011e-05,
      "learning_rate": 9.698999999999999e-05,
      "loss": 23.0,
      "step": 17
    },
    {
      "epoch": 0.0030374620317246033,
      "grad_norm": 1.8586168152978644e-05,
      "learning_rate": 9.646e-05,
      "loss": 23.0,
      "step": 18
    },
    {
      "epoch": 0.00320620992237597,
      "grad_norm": 1.872859866125509e-05,
      "learning_rate": 9.593e-05,
      "loss": 23.0,
      "step": 19
    },
    {
      "epoch": 0.0033749578130273373,
      "grad_norm": 3.305126665509306e-05,
      "learning_rate": 9.539999999999999e-05,
      "loss": 23.0,
      "step": 20
    },
    {
      "epoch": 0.003543705703678704,
      "grad_norm": 2.0460800442378968e-05,
      "learning_rate": 9.487e-05,
      "loss": 23.0,
      "step": 21
    },
    {
      "epoch": 0.003712453594330071,
      "grad_norm": 2.6154682927881368e-05,
      "learning_rate": 9.434e-05,
      "loss": 23.0,
      "step": 22
    },
    {
      "epoch": 0.0038812014849814377,
      "grad_norm": 2.1470910724019632e-05,
      "learning_rate": 9.381e-05,
      "loss": 23.0,
      "step": 23
    },
    {
      "epoch": 0.004049949375632805,
      "grad_norm": 2.203008989454247e-05,
      "learning_rate": 9.327999999999999e-05,
      "loss": 23.0,
      "step": 24
    },
    {
      "epoch": 0.004218697266284171,
      "grad_norm": 2.6265855922247283e-05,
      "learning_rate": 9.274999999999999e-05,
      "loss": 23.0,
      "step": 25
    },
    {
      "epoch": 0.004387445156935539,
      "grad_norm": 3.531806214596145e-05,
      "learning_rate": 9.222e-05,
      "loss": 23.0,
      "step": 26
    },
    {
      "epoch": 0.004556193047586905,
      "grad_norm": 3.6674504372058436e-05,
      "learning_rate": 9.169e-05,
      "loss": 23.0,
      "step": 27
    },
    {
      "epoch": 0.004724940938238272,
      "grad_norm": 3.1309191399486735e-05,
      "learning_rate": 9.116e-05,
      "loss": 23.0,
      "step": 28
    },
    {
      "epoch": 0.0048936888288896386,
      "grad_norm": 2.5531946448609233e-05,
      "learning_rate": 9.062999999999999e-05,
      "loss": 23.0,
      "step": 29
    },
    {
      "epoch": 0.005062436719541006,
      "grad_norm": 3.693735197884962e-05,
      "learning_rate": 9.01e-05,
      "loss": 23.0,
      "step": 30
    },
    {
      "epoch": 0.005231184610192373,
      "grad_norm": 3.671792001114227e-05,
      "learning_rate": 8.957e-05,
      "loss": 23.0,
      "step": 31
    },
    {
      "epoch": 0.005399932500843739,
      "grad_norm": 2.8840735467383638e-05,
      "learning_rate": 8.903999999999999e-05,
      "loss": 23.0,
      "step": 32
    },
    {
      "epoch": 0.005568680391495107,
      "grad_norm": 4.73731524834875e-05,
      "learning_rate": 8.850999999999999e-05,
      "loss": 23.0,
      "step": 33
    },
    {
      "epoch": 0.005737428282146473,
      "grad_norm": 4.9730784667190164e-05,
      "learning_rate": 8.798e-05,
      "loss": 23.0,
      "step": 34
    },
    {
      "epoch": 0.00590617617279784,
      "grad_norm": 4.867700408794917e-05,
      "learning_rate": 8.745e-05,
      "loss": 23.0,
      "step": 35
    },
    {
      "epoch": 0.006074924063449207,
      "grad_norm": 4.8206897190539166e-05,
      "learning_rate": 8.692e-05,
      "loss": 23.0,
      "step": 36
    },
    {
      "epoch": 0.006243671954100574,
      "grad_norm": 5.011281609768048e-05,
      "learning_rate": 8.638999999999999e-05,
      "loss": 23.0,
      "step": 37
    },
    {
      "epoch": 0.00641241984475194,
      "grad_norm": 8.074403740465641e-05,
      "learning_rate": 8.586e-05,
      "loss": 23.0,
      "step": 38
    },
    {
      "epoch": 0.0065811677354033074,
      "grad_norm": 6.544839561684057e-05,
      "learning_rate": 8.533e-05,
      "loss": 23.0,
      "step": 39
    },
    {
      "epoch": 0.006749915626054675,
      "grad_norm": 7.167661533458158e-05,
      "learning_rate": 8.479999999999999e-05,
      "loss": 23.0,
      "step": 40
    },
    {
      "epoch": 0.006918663516706041,
      "grad_norm": 6.072892210795544e-05,
      "learning_rate": 8.427e-05,
      "loss": 23.0,
      "step": 41
    },
    {
      "epoch": 0.007087411407357408,
      "grad_norm": 4.846288720727898e-05,
      "learning_rate": 8.374e-05,
      "loss": 23.0,
      "step": 42
    },
    {
      "epoch": 0.007256159298008775,
      "grad_norm": 7.074383756844327e-05,
      "learning_rate": 8.321e-05,
      "loss": 23.0,
      "step": 43
    },
    {
      "epoch": 0.007424907188660142,
      "grad_norm": 4.74240405310411e-05,
      "learning_rate": 8.268e-05,
      "loss": 23.0,
      "step": 44
    },
    {
      "epoch": 0.007593655079311508,
      "grad_norm": 0.00011488777818158269,
      "learning_rate": 8.214999999999999e-05,
      "loss": 23.0,
      "step": 45
    },
    {
      "epoch": 0.0077624029699628755,
      "grad_norm": 9.618495823815465e-05,
      "learning_rate": 8.162e-05,
      "loss": 23.0,
      "step": 46
    },
    {
      "epoch": 0.007931150860614243,
      "grad_norm": 7.153845945140347e-05,
      "learning_rate": 8.108999999999998e-05,
      "loss": 23.0,
      "step": 47
    },
    {
      "epoch": 0.00809989875126561,
      "grad_norm": 0.00012329178571235389,
      "learning_rate": 8.056e-05,
      "loss": 23.0,
      "step": 48
    },
    {
      "epoch": 0.008268646641916975,
      "grad_norm": 9.25509084481746e-05,
      "learning_rate": 8.003e-05,
      "loss": 23.0,
      "step": 49
    },
    {
      "epoch": 0.008437394532568343,
      "grad_norm": 0.00014846926205791533,
      "learning_rate": 7.95e-05,
      "loss": 23.0,
      "step": 50
    },
    {
      "epoch": 0.008437394532568343,
      "eval_loss": 11.5,
      "eval_runtime": 31.0281,
      "eval_samples_per_second": 80.411,
      "eval_steps_per_second": 20.111,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2009903923200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}