{
  "best_metric": 1.3429416418075562,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.14727540500736377,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005891016200294551,
      "grad_norm": 5.842298984527588,
      "learning_rate": 5e-05,
      "loss": 9.5356,
      "step": 1
    },
    {
      "epoch": 0.005891016200294551,
      "eval_loss": 9.313302040100098,
      "eval_runtime": 29.0711,
      "eval_samples_per_second": 39.352,
      "eval_steps_per_second": 4.919,
      "step": 1
    },
    {
      "epoch": 0.011782032400589101,
      "grad_norm": 5.442224025726318,
      "learning_rate": 0.0001,
      "loss": 9.6149,
      "step": 2
    },
    {
      "epoch": 0.017673048600883652,
      "grad_norm": 5.885929584503174,
      "learning_rate": 9.989294616193017e-05,
      "loss": 9.0404,
      "step": 3
    },
    {
      "epoch": 0.023564064801178203,
      "grad_norm": 5.703976631164551,
      "learning_rate": 9.957224306869053e-05,
      "loss": 8.5045,
      "step": 4
    },
    {
      "epoch": 0.029455081001472753,
      "grad_norm": 5.090454578399658,
      "learning_rate": 9.903926402016153e-05,
      "loss": 8.0282,
      "step": 5
    },
    {
      "epoch": 0.035346097201767304,
      "grad_norm": 5.094424724578857,
      "learning_rate": 9.829629131445342e-05,
      "loss": 6.7382,
      "step": 6
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 5.329985618591309,
      "learning_rate": 9.73465064747553e-05,
      "loss": 6.2681,
      "step": 7
    },
    {
      "epoch": 0.047128129602356406,
      "grad_norm": 5.399036407470703,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.4843,
      "step": 8
    },
    {
      "epoch": 0.053019145802650956,
      "grad_norm": 6.035473346710205,
      "learning_rate": 9.484363707663442e-05,
      "loss": 4.8206,
      "step": 9
    },
    {
      "epoch": 0.05891016200294551,
      "grad_norm": 4.776269435882568,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.2461,
      "step": 10
    },
    {
      "epoch": 0.06480117820324006,
      "grad_norm": 4.449507713317871,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.6786,
      "step": 11
    },
    {
      "epoch": 0.07069219440353461,
      "grad_norm": 3.3939056396484375,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.3633,
      "step": 12
    },
    {
      "epoch": 0.07658321060382917,
      "grad_norm": 2.991218090057373,
      "learning_rate": 8.759199037394887e-05,
      "loss": 3.5821,
      "step": 13
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 3.1551268100738525,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.58,
      "step": 14
    },
    {
      "epoch": 0.08836524300441827,
      "grad_norm": 2.813246488571167,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.3115,
      "step": 15
    },
    {
      "epoch": 0.09425625920471281,
      "grad_norm": 2.7603561878204346,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.2722,
      "step": 16
    },
    {
      "epoch": 0.10014727540500737,
      "grad_norm": 2.7277021408081055,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.0294,
      "step": 17
    },
    {
      "epoch": 0.10603829160530191,
      "grad_norm": 3.1602253913879395,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.859,
      "step": 18
    },
    {
      "epoch": 0.11192930780559647,
      "grad_norm": 2.9966933727264404,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.4994,
      "step": 19
    },
    {
      "epoch": 0.11782032400589101,
      "grad_norm": 3.4069058895111084,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.37,
      "step": 20
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 3.8147764205932617,
      "learning_rate": 6.607197326515808e-05,
      "loss": 2.1856,
      "step": 21
    },
    {
      "epoch": 0.12960235640648013,
      "grad_norm": 3.6965410709381104,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8319,
      "step": 22
    },
    {
      "epoch": 0.13549337260677466,
      "grad_norm": 3.231584072113037,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.4828,
      "step": 23
    },
    {
      "epoch": 0.14138438880706922,
      "grad_norm": 2.6291158199310303,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.4255,
      "step": 24
    },
    {
      "epoch": 0.14727540500736377,
      "grad_norm": 3.0126707553863525,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5902,
      "step": 25
    },
    {
      "epoch": 0.14727540500736377,
      "eval_loss": 1.3429416418075562,
      "eval_runtime": 28.9981,
      "eval_samples_per_second": 39.451,
      "eval_steps_per_second": 4.931,
      "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": 5.29768176943104e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}