{
  "best_metric": 0.7244487404823303,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4048582995951417,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008097165991902834,
      "grad_norm": 160.5043182373047,
      "learning_rate": 1e-06,
      "loss": 11.5445,
      "step": 1
    },
    {
      "epoch": 0.008097165991902834,
      "eval_loss": 11.895453453063965,
      "eval_runtime": 1.2561,
      "eval_samples_per_second": 41.398,
      "eval_steps_per_second": 10.349,
      "step": 1
    },
    {
      "epoch": 0.016194331983805668,
      "grad_norm": 113.18714904785156,
      "learning_rate": 2e-06,
      "loss": 12.2262,
      "step": 2
    },
    {
      "epoch": 0.024291497975708502,
      "grad_norm": 134.26119995117188,
      "learning_rate": 3e-06,
      "loss": 12.1703,
      "step": 3
    },
    {
      "epoch": 0.032388663967611336,
      "grad_norm": 151.49256896972656,
      "learning_rate": 4e-06,
      "loss": 11.2431,
      "step": 4
    },
    {
      "epoch": 0.04048582995951417,
      "grad_norm": 128.835205078125,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 12.309,
      "step": 5
    },
    {
      "epoch": 0.048582995951417005,
      "grad_norm": 126.78450012207031,
      "learning_rate": 6e-06,
      "loss": 12.4684,
      "step": 6
    },
    {
      "epoch": 0.05668016194331984,
      "grad_norm": 128.61981201171875,
      "learning_rate": 7e-06,
      "loss": 11.275,
      "step": 7
    },
    {
      "epoch": 0.06477732793522267,
      "grad_norm": 132.9573516845703,
      "learning_rate": 8e-06,
      "loss": 9.7015,
      "step": 8
    },
    {
      "epoch": 0.0728744939271255,
      "grad_norm": 114.10719299316406,
      "learning_rate": 9e-06,
      "loss": 8.4523,
      "step": 9
    },
    {
      "epoch": 0.08097165991902834,
      "grad_norm": 102.33385467529297,
      "learning_rate": 9.999999999999999e-06,
      "loss": 7.9721,
      "step": 10
    },
    {
      "epoch": 0.08906882591093117,
      "grad_norm": 85.0543212890625,
      "learning_rate": 1.1e-05,
      "loss": 6.5994,
      "step": 11
    },
    {
      "epoch": 0.09716599190283401,
      "grad_norm": 114.57733917236328,
      "learning_rate": 1.2e-05,
      "loss": 5.7194,
      "step": 12
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 84.9945297241211,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 4.7599,
      "step": 13
    },
    {
      "epoch": 0.11336032388663968,
      "grad_norm": 82.66494750976562,
      "learning_rate": 1.4e-05,
      "loss": 6.2553,
      "step": 14
    },
    {
      "epoch": 0.1214574898785425,
      "grad_norm": 66.0272445678711,
      "learning_rate": 1.5e-05,
      "loss": 3.5185,
      "step": 15
    },
    {
      "epoch": 0.12955465587044535,
      "grad_norm": 59.03416061401367,
      "learning_rate": 1.6e-05,
      "loss": 2.4052,
      "step": 16
    },
    {
      "epoch": 0.13765182186234817,
      "grad_norm": 60.23641586303711,
      "learning_rate": 1.7e-05,
      "loss": 2.7286,
      "step": 17
    },
    {
      "epoch": 0.145748987854251,
      "grad_norm": 37.41645431518555,
      "learning_rate": 1.8e-05,
      "loss": 2.7418,
      "step": 18
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 31.624427795410156,
      "learning_rate": 1.9e-05,
      "loss": 1.5455,
      "step": 19
    },
    {
      "epoch": 0.16194331983805668,
      "grad_norm": 33.63788986206055,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 2.2783,
      "step": 20
    },
    {
      "epoch": 0.1700404858299595,
      "grad_norm": 35.38190841674805,
      "learning_rate": 2.1e-05,
      "loss": 1.6235,
      "step": 21
    },
    {
      "epoch": 0.17813765182186234,
      "grad_norm": 46.83808135986328,
      "learning_rate": 2.2e-05,
      "loss": 1.8509,
      "step": 22
    },
    {
      "epoch": 0.1862348178137652,
      "grad_norm": 21.023977279663086,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.9755,
      "step": 23
    },
    {
      "epoch": 0.19433198380566802,
      "grad_norm": 34.79740905761719,
      "learning_rate": 2.4e-05,
      "loss": 0.9948,
      "step": 24
    },
    {
      "epoch": 0.20242914979757085,
      "grad_norm": 26.90549659729004,
      "learning_rate": 2.5e-05,
      "loss": 0.7971,
      "step": 25
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 30.40579605102539,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.1038,
      "step": 26
    },
    {
      "epoch": 0.21862348178137653,
      "grad_norm": 36.04926681518555,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.7739,
      "step": 27
    },
    {
      "epoch": 0.22672064777327935,
      "grad_norm": 35.41645050048828,
      "learning_rate": 2.8e-05,
      "loss": 1.3239,
      "step": 28
    },
    {
      "epoch": 0.23481781376518218,
      "grad_norm": 26.374845504760742,
      "learning_rate": 2.9e-05,
      "loss": 1.2692,
      "step": 29
    },
    {
      "epoch": 0.242914979757085,
      "grad_norm": 24.77640151977539,
      "learning_rate": 3e-05,
      "loss": 0.8267,
      "step": 30
    },
    {
      "epoch": 0.25101214574898784,
      "grad_norm": 27.26534652709961,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 0.8929,
      "step": 31
    },
    {
      "epoch": 0.2591093117408907,
      "grad_norm": 16.130844116210938,
      "learning_rate": 2.993961440992859e-05,
      "loss": 0.8517,
      "step": 32
    },
    {
      "epoch": 0.26720647773279355,
      "grad_norm": 18.54865074157715,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.7742,
      "step": 33
    },
    {
      "epoch": 0.27530364372469635,
      "grad_norm": 12.706560134887695,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.6831,
      "step": 34
    },
    {
      "epoch": 0.2834008097165992,
      "grad_norm": 12.227797508239746,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.749,
      "step": 35
    },
    {
      "epoch": 0.291497975708502,
      "grad_norm": 17.94428062438965,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 0.7489,
      "step": 36
    },
    {
      "epoch": 0.29959514170040485,
      "grad_norm": 12.291033744812012,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.6317,
      "step": 37
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 23.2242431640625,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.9003,
      "step": 38
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 15.302254676818848,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.6306,
      "step": 39
    },
    {
      "epoch": 0.32388663967611336,
      "grad_norm": 17.329072952270508,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 0.8858,
      "step": 40
    },
    {
      "epoch": 0.3319838056680162,
      "grad_norm": 11.782532691955566,
      "learning_rate": 2.820893297785107e-05,
      "loss": 0.7977,
      "step": 41
    },
    {
      "epoch": 0.340080971659919,
      "grad_norm": 10.306597709655762,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 0.6432,
      "step": 42
    },
    {
      "epoch": 0.3481781376518219,
      "grad_norm": 15.597854614257812,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.6245,
      "step": 43
    },
    {
      "epoch": 0.3562753036437247,
      "grad_norm": 13.594710350036621,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.7767,
      "step": 44
    },
    {
      "epoch": 0.3643724696356275,
      "grad_norm": 9.834576606750488,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.768,
      "step": 45
    },
    {
      "epoch": 0.3724696356275304,
      "grad_norm": 4.552821159362793,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.6271,
      "step": 46
    },
    {
      "epoch": 0.3805668016194332,
      "grad_norm": 9.330282211303711,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.7619,
      "step": 47
    },
    {
      "epoch": 0.38866396761133604,
      "grad_norm": 10.170756340026855,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 0.7114,
      "step": 48
    },
    {
      "epoch": 0.3967611336032389,
      "grad_norm": 7.350127696990967,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 0.7545,
      "step": 49
    },
    {
      "epoch": 0.4048582995951417,
      "grad_norm": 11.022176742553711,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 0.7612,
      "step": 50
    },
    {
      "epoch": 0.4048582995951417,
      "eval_loss": 0.7244487404823303,
      "eval_runtime": 1.2651,
      "eval_samples_per_second": 41.102,
      "eval_steps_per_second": 10.275,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 966060303974400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}