{
  "best_metric": 0.32884421944618225,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.12330456226880394,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004932182490752158,
      "grad_norm": 1.8650400638580322,
      "learning_rate": 5e-05,
      "loss": 1.1438,
      "step": 1
    },
    {
      "epoch": 0.004932182490752158,
      "eval_loss": 1.414349913597107,
      "eval_runtime": 20.2671,
      "eval_samples_per_second": 67.4,
      "eval_steps_per_second": 8.437,
      "step": 1
    },
    {
      "epoch": 0.009864364981504316,
      "grad_norm": 1.849665880203247,
      "learning_rate": 0.0001,
      "loss": 1.1763,
      "step": 2
    },
    {
      "epoch": 0.014796547472256474,
      "grad_norm": 1.5722370147705078,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.1466,
      "step": 3
    },
    {
      "epoch": 0.01972872996300863,
      "grad_norm": 1.2196251153945923,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9743,
      "step": 4
    },
    {
      "epoch": 0.02466091245376079,
      "grad_norm": 1.2063157558441162,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.8742,
      "step": 5
    },
    {
      "epoch": 0.029593094944512947,
      "grad_norm": 1.196218729019165,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7981,
      "step": 6
    },
    {
      "epoch": 0.0345252774352651,
      "grad_norm": 1.059170126914978,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7206,
      "step": 7
    },
    {
      "epoch": 0.03945745992601726,
      "grad_norm": 1.107353925704956,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6495,
      "step": 8
    },
    {
      "epoch": 0.04438964241676942,
      "grad_norm": 1.1146334409713745,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6043,
      "step": 9
    },
    {
      "epoch": 0.04932182490752158,
      "grad_norm": 1.1989785432815552,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5555,
      "step": 10
    },
    {
      "epoch": 0.05425400739827373,
      "grad_norm": 1.366790533065796,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.5734,
      "step": 11
    },
    {
      "epoch": 0.059186189889025895,
      "grad_norm": 1.1458686590194702,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5739,
      "step": 12
    },
    {
      "epoch": 0.06411837237977805,
      "grad_norm": 1.9404748678207397,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3946,
      "step": 13
    },
    {
      "epoch": 0.0690505548705302,
      "grad_norm": 1.2511030435562134,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3832,
      "step": 14
    },
    {
      "epoch": 0.07398273736128237,
      "grad_norm": 0.8801244497299194,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.3734,
      "step": 15
    },
    {
      "epoch": 0.07891491985203453,
      "grad_norm": 0.7699196934700012,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.381,
      "step": 16
    },
    {
      "epoch": 0.08384710234278668,
      "grad_norm": 0.6188871264457703,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.3598,
      "step": 17
    },
    {
      "epoch": 0.08877928483353884,
      "grad_norm": 0.5674222707748413,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3389,
      "step": 18
    },
    {
      "epoch": 0.093711467324291,
      "grad_norm": 0.6306641101837158,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.3669,
      "step": 19
    },
    {
      "epoch": 0.09864364981504316,
      "grad_norm": 0.4506845474243164,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3072,
      "step": 20
    },
    {
      "epoch": 0.10357583230579531,
      "grad_norm": 0.4561832547187805,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.3402,
      "step": 21
    },
    {
      "epoch": 0.10850801479654747,
      "grad_norm": 0.5709429979324341,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3453,
      "step": 22
    },
    {
      "epoch": 0.11344019728729964,
      "grad_norm": 0.5596646666526794,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.3298,
      "step": 23
    },
    {
      "epoch": 0.11837237977805179,
      "grad_norm": 0.6210820078849792,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.4192,
      "step": 24
    },
    {
      "epoch": 0.12330456226880394,
      "grad_norm": 1.0289266109466553,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3351,
      "step": 25
    },
    {
      "epoch": 0.12330456226880394,
      "eval_loss": 0.32884421944618225,
      "eval_runtime": 20.2458,
      "eval_samples_per_second": 67.471,
      "eval_steps_per_second": 8.446,
      "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": 2.898563020567347e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}