{
  "best_metric": 2.5573222637176514,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03305238803503553,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016526194017517766,
      "eval_loss": 3.1149251461029053,
      "eval_runtime": 43.6347,
      "eval_samples_per_second": 58.394,
      "eval_steps_per_second": 14.598,
      "step": 1
    },
    {
      "epoch": 0.0016526194017517765,
      "grad_norm": 2.4044153690338135,
      "learning_rate": 4.36e-05,
      "loss": 2.4216,
      "step": 10
    },
    {
      "epoch": 0.003305238803503553,
      "grad_norm": 3.2215139865875244,
      "learning_rate": 8.72e-05,
      "loss": 2.2895,
      "step": 20
    },
    {
      "epoch": 0.00495785820525533,
      "grad_norm": 4.437511444091797,
      "learning_rate": 0.0001308,
      "loss": 2.2952,
      "step": 30
    },
    {
      "epoch": 0.006610477607007106,
      "grad_norm": 6.676159381866455,
      "learning_rate": 0.0001744,
      "loss": 2.2616,
      "step": 40
    },
    {
      "epoch": 0.008263097008758883,
      "grad_norm": 22.480907440185547,
      "learning_rate": 0.000218,
      "loss": 2.7042,
      "step": 50
    },
    {
      "epoch": 0.008263097008758883,
      "eval_loss": 2.7512803077697754,
      "eval_runtime": 43.5634,
      "eval_samples_per_second": 58.489,
      "eval_steps_per_second": 14.622,
      "step": 50
    },
    {
      "epoch": 0.00991571641051066,
      "grad_norm": 2.332223415374756,
      "learning_rate": 0.00021773448147832086,
      "loss": 2.3331,
      "step": 60
    },
    {
      "epoch": 0.011568335812262435,
      "grad_norm": 2.4621620178222656,
      "learning_rate": 0.0002169392194928312,
      "loss": 2.3293,
      "step": 70
    },
    {
      "epoch": 0.013220955214014212,
      "grad_norm": 3.450859546661377,
      "learning_rate": 0.00021561808847998484,
      "loss": 2.1836,
      "step": 80
    },
    {
      "epoch": 0.014873574615765989,
      "grad_norm": 7.603415489196777,
      "learning_rate": 0.00021377752485727676,
      "loss": 2.2165,
      "step": 90
    },
    {
      "epoch": 0.016526194017517766,
      "grad_norm": 19.09664535522461,
      "learning_rate": 0.00021142649566566402,
      "loss": 3.0109,
      "step": 100
    },
    {
      "epoch": 0.016526194017517766,
      "eval_loss": 2.7991316318511963,
      "eval_runtime": 43.5731,
      "eval_samples_per_second": 58.476,
      "eval_steps_per_second": 14.619,
      "step": 100
    },
    {
      "epoch": 0.01817881341926954,
      "grad_norm": 2.182637929916382,
      "learning_rate": 0.0002085764548830435,
      "loss": 2.4546,
      "step": 110
    },
    {
      "epoch": 0.01983143282102132,
      "grad_norm": 2.9767863750457764,
      "learning_rate": 0.00020524128762162305,
      "loss": 2.252,
      "step": 120
    },
    {
      "epoch": 0.021484052222773095,
      "grad_norm": 4.451344966888428,
      "learning_rate": 0.00020143724248105043,
      "loss": 2.1921,
      "step": 130
    },
    {
      "epoch": 0.02313667162452487,
      "grad_norm": 5.990928649902344,
      "learning_rate": 0.0001971828523868693,
      "loss": 2.0887,
      "step": 140
    },
    {
      "epoch": 0.02478929102627665,
      "grad_norm": 19.66733741760254,
      "learning_rate": 0.0001924988442999686,
      "loss": 2.5636,
      "step": 150
    },
    {
      "epoch": 0.02478929102627665,
      "eval_loss": 2.7373805046081543,
      "eval_runtime": 43.5877,
      "eval_samples_per_second": 58.457,
      "eval_steps_per_second": 14.614,
      "step": 150
    },
    {
      "epoch": 0.026441910428028424,
      "grad_norm": 2.0548884868621826,
      "learning_rate": 0.00018740803823691298,
      "loss": 2.4033,
      "step": 160
    },
    {
      "epoch": 0.028094529829780203,
      "grad_norm": 2.9234230518341064,
      "learning_rate": 0.00018193523609311556,
      "loss": 2.2948,
      "step": 170
    },
    {
      "epoch": 0.029747149231531978,
      "grad_norm": 3.7016618251800537,
      "learning_rate": 0.00017610710081049675,
      "loss": 2.3234,
      "step": 180
    },
    {
      "epoch": 0.03139976863328375,
      "grad_norm": 5.965432643890381,
      "learning_rate": 0.00016995202647831142,
      "loss": 2.2832,
      "step": 190
    },
    {
      "epoch": 0.03305238803503553,
      "grad_norm": 17.460437774658203,
      "learning_rate": 0.00016350000000000002,
      "loss": 3.0321,
      "step": 200
    },
    {
      "epoch": 0.03305238803503553,
      "eval_loss": 2.5573222637176514,
      "eval_runtime": 43.5955,
      "eval_samples_per_second": 58.446,
      "eval_steps_per_second": 14.612,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 5042364292792320.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}