{
  "best_metric": 1.9494298696517944,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.16161616161616163,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006464646464646465,
      "grad_norm": 0.13794121146202087,
      "learning_rate": 5e-05,
      "loss": 2.1076,
      "step": 1
    },
    {
      "epoch": 0.006464646464646465,
      "eval_loss": 2.1259307861328125,
      "eval_runtime": 18.9274,
      "eval_samples_per_second": 55.105,
      "eval_steps_per_second": 6.921,
      "step": 1
    },
    {
      "epoch": 0.01292929292929293,
      "grad_norm": 0.19002071022987366,
      "learning_rate": 0.0001,
      "loss": 2.1139,
      "step": 2
    },
    {
      "epoch": 0.019393939393939394,
      "grad_norm": 0.20002254843711853,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.1161,
      "step": 3
    },
    {
      "epoch": 0.02585858585858586,
      "grad_norm": 0.23847076296806335,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.0648,
      "step": 4
    },
    {
      "epoch": 0.03232323232323232,
      "grad_norm": 0.18669605255126953,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.0676,
      "step": 5
    },
    {
      "epoch": 0.03878787878787879,
      "grad_norm": 0.16979680955410004,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.0377,
      "step": 6
    },
    {
      "epoch": 0.04525252525252525,
      "grad_norm": 0.1790999323129654,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.0074,
      "step": 7
    },
    {
      "epoch": 0.05171717171717172,
      "grad_norm": 0.1701156347990036,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9835,
      "step": 8
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 0.21324147284030914,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9334,
      "step": 9
    },
    {
      "epoch": 0.06464646464646465,
      "grad_norm": 0.3143400251865387,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8562,
      "step": 10
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.3273347318172455,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8348,
      "step": 11
    },
    {
      "epoch": 0.07757575757575758,
      "grad_norm": 0.348003089427948,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.7444,
      "step": 12
    },
    {
      "epoch": 0.08404040404040404,
      "grad_norm": 0.34863314032554626,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.1291,
      "step": 13
    },
    {
      "epoch": 0.0905050505050505,
      "grad_norm": 0.3459385633468628,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1046,
      "step": 14
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 0.2635910212993622,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.1029,
      "step": 15
    },
    {
      "epoch": 0.10343434343434343,
      "grad_norm": 0.2018289715051651,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.0579,
      "step": 16
    },
    {
      "epoch": 0.1098989898989899,
      "grad_norm": 0.15820299088954926,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.0294,
      "step": 17
    },
    {
      "epoch": 0.11636363636363636,
      "grad_norm": 0.17375575006008148,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0248,
      "step": 18
    },
    {
      "epoch": 0.12282828282828283,
      "grad_norm": 0.16773708164691925,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.0072,
      "step": 19
    },
    {
      "epoch": 0.1292929292929293,
      "grad_norm": 0.15941676497459412,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.9344,
      "step": 20
    },
    {
      "epoch": 0.13575757575757577,
      "grad_norm": 0.16956786811351776,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.9306,
      "step": 21
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.21462693810462952,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8964,
      "step": 22
    },
    {
      "epoch": 0.1486868686868687,
      "grad_norm": 0.3244251012802124,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8402,
      "step": 23
    },
    {
      "epoch": 0.15515151515151515,
      "grad_norm": 0.39707544445991516,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.8173,
      "step": 24
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.5086701512336731,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7137,
      "step": 25
    },
    {
      "epoch": 0.16161616161616163,
      "eval_loss": 1.9494298696517944,
      "eval_runtime": 18.9074,
      "eval_samples_per_second": 55.164,
      "eval_steps_per_second": 6.929,
      "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": 1.127497768894464e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}