{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.052369730295888976,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010473946059177796,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0010473946059177796,
      "eval_loss": NaN,
      "eval_runtime": 139.0077,
      "eval_samples_per_second": 2.892,
      "eval_steps_per_second": 1.446,
      "step": 1
    },
    {
      "epoch": 0.002094789211835559,
      "grad_norm": 0.0,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.003142183817753339,
      "grad_norm": 0.0,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.004189578423671118,
      "grad_norm": 0.0,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.005236973029588898,
      "grad_norm": 0.0,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.006284367635506678,
      "grad_norm": 0.0,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.007331762241424456,
      "grad_norm": 0.0,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.008379156847342237,
      "grad_norm": 0.0,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.009426551453260016,
      "grad_norm": 0.0,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.010473946059177796,
      "grad_norm": 0.0,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.011521340665095576,
      "grad_norm": 0.0,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.012568735271013355,
      "grad_norm": 0.0,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.013616129876931133,
      "grad_norm": 0.0,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.014663524482848913,
      "grad_norm": 0.0,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.015710919088766692,
      "grad_norm": 0.0,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.016758313694684474,
      "grad_norm": 0.0,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.01780570830060225,
      "grad_norm": 0.0,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.018853102906520033,
      "grad_norm": 0.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.01990049751243781,
      "grad_norm": 0.0,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.020947892118355592,
      "grad_norm": 0.0,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.02199528672427337,
      "grad_norm": 0.0,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.02304268133019115,
      "grad_norm": 0.0,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.02409007593610893,
      "grad_norm": 0.0,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.02513747054202671,
      "grad_norm": 0.0,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.026184865147944488,
      "grad_norm": 0.0,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.026184865147944488,
      "eval_loss": NaN,
      "eval_runtime": 140.6308,
      "eval_samples_per_second": 2.859,
      "eval_steps_per_second": 1.429,
      "step": 25
    },
    {
      "epoch": 0.027232259753862266,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.028279654359780047,
      "grad_norm": 0.0,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.029327048965697825,
      "grad_norm": 0.0,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.030374443571615607,
      "grad_norm": 0.0,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.031421838177533384,
      "grad_norm": 0.0,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.032469232783451166,
      "grad_norm": 0.0,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.03351662738936895,
      "grad_norm": 0.0,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.03456402199528672,
      "grad_norm": 0.0,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0356114166012045,
      "grad_norm": 0.0,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.036658811207122284,
      "grad_norm": 0.0,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.037706205813040065,
      "grad_norm": 0.0,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.03875360041895784,
      "grad_norm": 0.0,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 0.0,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0408483896307934,
      "grad_norm": 0.0,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.041895784236711184,
      "grad_norm": 0.0,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.04294317884262896,
      "grad_norm": 0.0,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.04399057344854674,
      "grad_norm": 0.0,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.04503796805446452,
      "grad_norm": 0.0,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0460853626603823,
      "grad_norm": 0.0,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.04713275726630008,
      "grad_norm": 0.0,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04818015187221786,
      "grad_norm": 0.0,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.04922754647813564,
      "grad_norm": 0.0,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.05027494108405342,
      "grad_norm": 0.0,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.051322335689971195,
      "grad_norm": 0.0,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.052369730295888976,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.052369730295888976,
      "eval_loss": NaN,
      "eval_runtime": 140.6403,
      "eval_samples_per_second": 2.858,
      "eval_steps_per_second": 1.429,
      "step": 50
    }
  ],
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.41887283560448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}