{
  "best_metric": 1.1732544898986816,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2035623409669211,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008142493638676845,
      "grad_norm": 0.7831802368164062,
      "learning_rate": 5e-05,
      "loss": 2.1777,
      "step": 1
    },
    {
      "epoch": 0.008142493638676845,
      "eval_loss": 2.6585562229156494,
      "eval_runtime": 3.179,
      "eval_samples_per_second": 15.728,
      "eval_steps_per_second": 4.089,
      "step": 1
    },
    {
      "epoch": 0.01628498727735369,
      "grad_norm": 0.9065176248550415,
      "learning_rate": 0.0001,
      "loss": 2.1561,
      "step": 2
    },
    {
      "epoch": 0.024427480916030534,
      "grad_norm": 0.9400052428245544,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.1895,
      "step": 3
    },
    {
      "epoch": 0.03256997455470738,
      "grad_norm": 1.0230543613433838,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.0533,
      "step": 4
    },
    {
      "epoch": 0.04071246819338423,
      "grad_norm": 0.9375590085983276,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.7889,
      "step": 5
    },
    {
      "epoch": 0.04885496183206107,
      "grad_norm": 0.684062659740448,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.5627,
      "step": 6
    },
    {
      "epoch": 0.056997455470737916,
      "grad_norm": 0.6688232421875,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.324,
      "step": 7
    },
    {
      "epoch": 0.06513994910941476,
      "grad_norm": 0.7182115912437439,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.2985,
      "step": 8
    },
    {
      "epoch": 0.0732824427480916,
      "grad_norm": 0.5141118764877319,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.1464,
      "step": 9
    },
    {
      "epoch": 0.08142493638676845,
      "grad_norm": 0.495283305644989,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.158,
      "step": 10
    },
    {
      "epoch": 0.08956743002544529,
      "grad_norm": 0.5461936593055725,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.0639,
      "step": 11
    },
    {
      "epoch": 0.09770992366412214,
      "grad_norm": 0.6632602214813232,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.9866,
      "step": 12
    },
    {
      "epoch": 0.10585241730279898,
      "grad_norm": 0.5742640495300293,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.4373,
      "step": 13
    },
    {
      "epoch": 0.11399491094147583,
      "grad_norm": 0.6885349750518799,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.4673,
      "step": 14
    },
    {
      "epoch": 0.12213740458015267,
      "grad_norm": 0.5408735871315002,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.366,
      "step": 15
    },
    {
      "epoch": 0.13027989821882952,
      "grad_norm": 0.4258224070072174,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.3541,
      "step": 16
    },
    {
      "epoch": 0.13842239185750635,
      "grad_norm": 0.47161340713500977,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.3002,
      "step": 17
    },
    {
      "epoch": 0.1465648854961832,
      "grad_norm": 0.4001603126525879,
      "learning_rate": 7.75e-05,
      "loss": 1.2064,
      "step": 18
    },
    {
      "epoch": 0.15470737913486005,
      "grad_norm": 0.5180523991584778,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.2031,
      "step": 19
    },
    {
      "epoch": 0.1628498727735369,
      "grad_norm": 0.4585513472557068,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.1297,
      "step": 20
    },
    {
      "epoch": 0.17099236641221374,
      "grad_norm": 0.42557641863822937,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.1331,
      "step": 21
    },
    {
      "epoch": 0.17913486005089058,
      "grad_norm": 0.36922454833984375,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.1081,
      "step": 22
    },
    {
      "epoch": 0.18727735368956744,
      "grad_norm": 0.3761698007583618,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.0548,
      "step": 23
    },
    {
      "epoch": 0.19541984732824427,
      "grad_norm": 0.4325619637966156,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.99,
      "step": 24
    },
    {
      "epoch": 0.2035623409669211,
      "grad_norm": 0.4425663352012634,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.7986,
      "step": 25
    },
    {
      "epoch": 0.2035623409669211,
      "eval_loss": 1.1732544898986816,
      "eval_runtime": 3.2358,
      "eval_samples_per_second": 15.452,
      "eval_steps_per_second": 4.018,
      "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": 2.812028905324544e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}