{
  "best_metric": 1.8510099649429321,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.3257328990228013,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013029315960912053,
      "grad_norm": 4.033048629760742,
      "learning_rate": 5e-05,
      "loss": 4.4207,
      "step": 1
    },
    {
      "epoch": 0.013029315960912053,
      "eval_loss": 6.510675430297852,
      "eval_runtime": 15.7339,
      "eval_samples_per_second": 32.859,
      "eval_steps_per_second": 4.131,
      "step": 1
    },
    {
      "epoch": 0.026058631921824105,
      "grad_norm": 4.561133861541748,
      "learning_rate": 0.0001,
      "loss": 4.8966,
      "step": 2
    },
    {
      "epoch": 0.03908794788273615,
      "grad_norm": 5.338207244873047,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.8076,
      "step": 3
    },
    {
      "epoch": 0.05211726384364821,
      "grad_norm": 4.561549186706543,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.1035,
      "step": 4
    },
    {
      "epoch": 0.06514657980456026,
      "grad_norm": 4.916613578796387,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.256,
      "step": 5
    },
    {
      "epoch": 0.0781758957654723,
      "grad_norm": 3.6213910579681396,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.7378,
      "step": 6
    },
    {
      "epoch": 0.09120521172638436,
      "grad_norm": 3.188063859939575,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.7365,
      "step": 7
    },
    {
      "epoch": 0.10423452768729642,
      "grad_norm": 3.4584438800811768,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.453,
      "step": 8
    },
    {
      "epoch": 0.11726384364820847,
      "grad_norm": 3.692514181137085,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.2256,
      "step": 9
    },
    {
      "epoch": 0.13029315960912052,
      "grad_norm": 2.7663116455078125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1805,
      "step": 10
    },
    {
      "epoch": 0.14332247557003258,
      "grad_norm": 3.047680139541626,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8794,
      "step": 11
    },
    {
      "epoch": 0.1563517915309446,
      "grad_norm": 6.86872673034668,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.5884,
      "step": 12
    },
    {
      "epoch": 0.16938110749185667,
      "grad_norm": 9.102276802062988,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.9419,
      "step": 13
    },
    {
      "epoch": 0.18241042345276873,
      "grad_norm": 7.11753511428833,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.6921,
      "step": 14
    },
    {
      "epoch": 0.19543973941368079,
      "grad_norm": 3.8425393104553223,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.3199,
      "step": 15
    },
    {
      "epoch": 0.20846905537459284,
      "grad_norm": 2.036224126815796,
      "learning_rate": 8.043807145043604e-05,
      "loss": 2.3416,
      "step": 16
    },
    {
      "epoch": 0.22149837133550487,
      "grad_norm": 1.965226173400879,
      "learning_rate": 7.777851165098012e-05,
      "loss": 2.149,
      "step": 17
    },
    {
      "epoch": 0.23452768729641693,
      "grad_norm": 2.1932334899902344,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0797,
      "step": 18
    },
    {
      "epoch": 0.247557003257329,
      "grad_norm": 2.3755345344543457,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.1096,
      "step": 19
    },
    {
      "epoch": 0.26058631921824105,
      "grad_norm": 2.250009775161743,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0224,
      "step": 20
    },
    {
      "epoch": 0.2736156351791531,
      "grad_norm": 1.7564245462417603,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.8868,
      "step": 21
    },
    {
      "epoch": 0.28664495114006516,
      "grad_norm": 1.8922572135925293,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.879,
      "step": 22
    },
    {
      "epoch": 0.2996742671009772,
      "grad_norm": 1.9456310272216797,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.4581,
      "step": 23
    },
    {
      "epoch": 0.3127035830618892,
      "grad_norm": 1.9163482189178467,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.2085,
      "step": 24
    },
    {
      "epoch": 0.3257328990228013,
      "grad_norm": 7.9290947914123535,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.5958,
      "step": 25
    },
    {
      "epoch": 0.3257328990228013,
      "eval_loss": 1.8510099649429321,
      "eval_runtime": 15.7107,
      "eval_samples_per_second": 32.907,
      "eval_steps_per_second": 4.137,
      "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": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}