{
  "best_metric": 1.6209503412246704,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.16999575010624735,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006799830004249894,
      "grad_norm": 0.6298477649688721,
      "learning_rate": 5e-05,
      "loss": 1.832,
      "step": 1
    },
    {
      "epoch": 0.006799830004249894,
      "eval_loss": 2.225749969482422,
      "eval_runtime": 3.2699,
      "eval_samples_per_second": 15.291,
      "eval_steps_per_second": 3.976,
      "step": 1
    },
    {
      "epoch": 0.013599660008499787,
      "grad_norm": 0.6128033399581909,
      "learning_rate": 0.0001,
      "loss": 1.8995,
      "step": 2
    },
    {
      "epoch": 0.020399490012749683,
      "grad_norm": 0.5658871531486511,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.8713,
      "step": 3
    },
    {
      "epoch": 0.027199320016999574,
      "grad_norm": 0.5368984937667847,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.7962,
      "step": 4
    },
    {
      "epoch": 0.033999150021249466,
      "grad_norm": 0.7190804481506348,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.6879,
      "step": 5
    },
    {
      "epoch": 0.040798980025499365,
      "grad_norm": 0.5174691081047058,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.5877,
      "step": 6
    },
    {
      "epoch": 0.04759881002974926,
      "grad_norm": 0.47408002614974976,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.6172,
      "step": 7
    },
    {
      "epoch": 0.05439864003399915,
      "grad_norm": 0.606837809085846,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.6606,
      "step": 8
    },
    {
      "epoch": 0.06119847003824904,
      "grad_norm": 0.6976940631866455,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.6475,
      "step": 9
    },
    {
      "epoch": 0.06799830004249893,
      "grad_norm": 0.7025362253189087,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.7543,
      "step": 10
    },
    {
      "epoch": 0.07479813004674883,
      "grad_norm": 0.7408571243286133,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.7836,
      "step": 11
    },
    {
      "epoch": 0.08159796005099873,
      "grad_norm": 0.981299638748169,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.7765,
      "step": 12
    },
    {
      "epoch": 0.08839779005524862,
      "grad_norm": 0.6295720934867859,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.6294,
      "step": 13
    },
    {
      "epoch": 0.09519762005949851,
      "grad_norm": 0.4918164014816284,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.6588,
      "step": 14
    },
    {
      "epoch": 0.10199745006374841,
      "grad_norm": 0.4401017129421234,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.6571,
      "step": 15
    },
    {
      "epoch": 0.1087972800679983,
      "grad_norm": 0.4373306334018707,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.4435,
      "step": 16
    },
    {
      "epoch": 0.1155971100722482,
      "grad_norm": 0.39373350143432617,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.4885,
      "step": 17
    },
    {
      "epoch": 0.12239694007649808,
      "grad_norm": 0.3562381863594055,
      "learning_rate": 7.75e-05,
      "loss": 1.4243,
      "step": 18
    },
    {
      "epoch": 0.12919677008074798,
      "grad_norm": 0.3342587351799011,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.4163,
      "step": 19
    },
    {
      "epoch": 0.13599660008499787,
      "grad_norm": 0.3539997339248657,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.3765,
      "step": 20
    },
    {
      "epoch": 0.14279643008924778,
      "grad_norm": 0.37134113907814026,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.4205,
      "step": 21
    },
    {
      "epoch": 0.14959626009349766,
      "grad_norm": 0.4305908977985382,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.4519,
      "step": 22
    },
    {
      "epoch": 0.15639609009774755,
      "grad_norm": 0.4636310636997223,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.5264,
      "step": 23
    },
    {
      "epoch": 0.16319592010199746,
      "grad_norm": 0.6321149468421936,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.6196,
      "step": 24
    },
    {
      "epoch": 0.16999575010624735,
      "grad_norm": 1.0208512544631958,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.8153,
      "step": 25
    },
    {
      "epoch": 0.16999575010624735,
      "eval_loss": 1.6209503412246704,
      "eval_runtime": 3.4198,
      "eval_samples_per_second": 14.621,
      "eval_steps_per_second": 3.801,
      "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": 2.7698250104858214e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}