{
  "best_metric": 1.254755973815918,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0266844563042028,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001067378252168112,
      "grad_norm": 0.3036106824874878,
      "learning_rate": 2e-05,
      "loss": 1.1428,
      "step": 1
    },
    {
      "epoch": 0.001067378252168112,
      "eval_loss": 1.3529059886932373,
      "eval_runtime": 96.8916,
      "eval_samples_per_second": 16.286,
      "eval_steps_per_second": 4.077,
      "step": 1
    },
    {
      "epoch": 0.002134756504336224,
      "grad_norm": 0.275738924741745,
      "learning_rate": 4e-05,
      "loss": 1.3115,
      "step": 2
    },
    {
      "epoch": 0.0032021347565043363,
      "grad_norm": 0.3127615451812744,
      "learning_rate": 6e-05,
      "loss": 1.3912,
      "step": 3
    },
    {
      "epoch": 0.004269513008672448,
      "grad_norm": 0.34139585494995117,
      "learning_rate": 8e-05,
      "loss": 1.3878,
      "step": 4
    },
    {
      "epoch": 0.00533689126084056,
      "grad_norm": 0.4060903489589691,
      "learning_rate": 0.0001,
      "loss": 1.3911,
      "step": 5
    },
    {
      "epoch": 0.00533689126084056,
      "eval_loss": 1.3339942693710327,
      "eval_runtime": 95.0814,
      "eval_samples_per_second": 16.596,
      "eval_steps_per_second": 4.154,
      "step": 5
    },
    {
      "epoch": 0.006404269513008673,
      "grad_norm": 0.33436480164527893,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.3435,
      "step": 6
    },
    {
      "epoch": 0.0074716477651767844,
      "grad_norm": 0.2888622581958771,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2677,
      "step": 7
    },
    {
      "epoch": 0.008539026017344896,
      "grad_norm": 0.21092571318149567,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.3051,
      "step": 8
    },
    {
      "epoch": 0.009606404269513008,
      "grad_norm": 0.1956106722354889,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2975,
      "step": 9
    },
    {
      "epoch": 0.01067378252168112,
      "grad_norm": 0.1843109130859375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2726,
      "step": 10
    },
    {
      "epoch": 0.01067378252168112,
      "eval_loss": 1.275883436203003,
      "eval_runtime": 94.838,
      "eval_samples_per_second": 16.639,
      "eval_steps_per_second": 4.165,
      "step": 10
    },
    {
      "epoch": 0.011741160773849233,
      "grad_norm": 0.2093294858932495,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2068,
      "step": 11
    },
    {
      "epoch": 0.012808539026017345,
      "grad_norm": 0.19510294497013092,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.3839,
      "step": 12
    },
    {
      "epoch": 0.013875917278185457,
      "grad_norm": 0.22046039998531342,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2001,
      "step": 13
    },
    {
      "epoch": 0.014943295530353569,
      "grad_norm": 0.1908130645751953,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.3136,
      "step": 14
    },
    {
      "epoch": 0.016010673782521682,
      "grad_norm": 0.24008464813232422,
      "learning_rate": 5e-05,
      "loss": 1.5086,
      "step": 15
    },
    {
      "epoch": 0.016010673782521682,
      "eval_loss": 1.2642096281051636,
      "eval_runtime": 95.1551,
      "eval_samples_per_second": 16.583,
      "eval_steps_per_second": 4.151,
      "step": 15
    },
    {
      "epoch": 0.017078052034689793,
      "grad_norm": 0.24746070802211761,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.4205,
      "step": 16
    },
    {
      "epoch": 0.018145430286857906,
      "grad_norm": 0.21102803945541382,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.3235,
      "step": 17
    },
    {
      "epoch": 0.019212808539026016,
      "grad_norm": 0.2305644154548645,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 1.3631,
      "step": 18
    },
    {
      "epoch": 0.02028018679119413,
      "grad_norm": 0.2286321073770523,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1059,
      "step": 19
    },
    {
      "epoch": 0.02134756504336224,
      "grad_norm": 0.18094190955162048,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.242,
      "step": 20
    },
    {
      "epoch": 0.02134756504336224,
      "eval_loss": 1.2566584348678589,
      "eval_runtime": 101.1211,
      "eval_samples_per_second": 15.605,
      "eval_steps_per_second": 3.906,
      "step": 20
    },
    {
      "epoch": 0.022414943295530353,
      "grad_norm": 0.2256290465593338,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2848,
      "step": 21
    },
    {
      "epoch": 0.023482321547698467,
      "grad_norm": 0.20047390460968018,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.184,
      "step": 22
    },
    {
      "epoch": 0.024549699799866577,
      "grad_norm": 0.20741315186023712,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2936,
      "step": 23
    },
    {
      "epoch": 0.02561707805203469,
      "grad_norm": 0.19564567506313324,
      "learning_rate": 6.15582970243117e-07,
      "loss": 1.3172,
      "step": 24
    },
    {
      "epoch": 0.0266844563042028,
      "grad_norm": 0.23147764801979065,
      "learning_rate": 0.0,
      "loss": 1.2654,
      "step": 25
    },
    {
      "epoch": 0.0266844563042028,
      "eval_loss": 1.254755973815918,
      "eval_runtime": 95.6601,
      "eval_samples_per_second": 16.496,
      "eval_steps_per_second": 4.129,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5635794026889216.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}