{
  "best_metric": 1.4106637239456177,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.22805017103762829,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009122006841505131,
      "grad_norm": 8.655662536621094,
      "learning_rate": 5e-05,
      "loss": 1.871,
      "step": 1
    },
    {
      "epoch": 0.009122006841505131,
      "eval_loss": 3.7504098415374756,
      "eval_runtime": 1.5013,
      "eval_samples_per_second": 33.304,
      "eval_steps_per_second": 8.659,
      "step": 1
    },
    {
      "epoch": 0.018244013683010263,
      "grad_norm": 18.90291404724121,
      "learning_rate": 0.0001,
      "loss": 2.5266,
      "step": 2
    },
    {
      "epoch": 0.027366020524515394,
      "grad_norm": 11.101104736328125,
      "learning_rate": 9.990365154573717e-05,
      "loss": 2.2531,
      "step": 3
    },
    {
      "epoch": 0.036488027366020526,
      "grad_norm": 3.917557954788208,
      "learning_rate": 9.961501876182148e-05,
      "loss": 2.1085,
      "step": 4
    },
    {
      "epoch": 0.04561003420752566,
      "grad_norm": 2.785952091217041,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.1402,
      "step": 5
    },
    {
      "epoch": 0.05473204104903079,
      "grad_norm": 2.5528736114501953,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.0671,
      "step": 6
    },
    {
      "epoch": 0.06385404789053592,
      "grad_norm": 3.1096019744873047,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.022,
      "step": 7
    },
    {
      "epoch": 0.07297605473204105,
      "grad_norm": 4.098336696624756,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.9843,
      "step": 8
    },
    {
      "epoch": 0.08209806157354618,
      "grad_norm": 4.202548027038574,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.0921,
      "step": 9
    },
    {
      "epoch": 0.09122006841505131,
      "grad_norm": 3.1605403423309326,
      "learning_rate": 9.397114317029975e-05,
      "loss": 2.0352,
      "step": 10
    },
    {
      "epoch": 0.10034207525655645,
      "grad_norm": 2.562784194946289,
      "learning_rate": 9.241613255361455e-05,
      "loss": 2.0455,
      "step": 11
    },
    {
      "epoch": 0.10946408209806158,
      "grad_norm": 2.120959520339966,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.0248,
      "step": 12
    },
    {
      "epoch": 0.11858608893956671,
      "grad_norm": 1.7797281742095947,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.3069,
      "step": 13
    },
    {
      "epoch": 0.12770809578107184,
      "grad_norm": 1.5691810846328735,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.4204,
      "step": 14
    },
    {
      "epoch": 0.13683010262257697,
      "grad_norm": 1.2062739133834839,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.5388,
      "step": 15
    },
    {
      "epoch": 0.1459521094640821,
      "grad_norm": 0.7961310744285583,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.4491,
      "step": 16
    },
    {
      "epoch": 0.15507411630558723,
      "grad_norm": 0.7442319393157959,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.5383,
      "step": 17
    },
    {
      "epoch": 0.16419612314709237,
      "grad_norm": 0.6347817778587341,
      "learning_rate": 7.75e-05,
      "loss": 1.5935,
      "step": 18
    },
    {
      "epoch": 0.1733181299885975,
      "grad_norm": 0.6833974719047546,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.5712,
      "step": 19
    },
    {
      "epoch": 0.18244013683010263,
      "grad_norm": 0.9213839173316956,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.5696,
      "step": 20
    },
    {
      "epoch": 0.19156214367160776,
      "grad_norm": 1.3780533075332642,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.6993,
      "step": 21
    },
    {
      "epoch": 0.2006841505131129,
      "grad_norm": 1.2376089096069336,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.6858,
      "step": 22
    },
    {
      "epoch": 0.20980615735461802,
      "grad_norm": 1.1128700971603394,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.6236,
      "step": 23
    },
    {
      "epoch": 0.21892816419612315,
      "grad_norm": 1.1550122499465942,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.6805,
      "step": 24
    },
    {
      "epoch": 0.22805017103762829,
      "grad_norm": 1.4760537147521973,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.7456,
      "step": 25
    },
    {
      "epoch": 0.22805017103762829,
      "eval_loss": 1.4106637239456177,
      "eval_runtime": 1.0204,
      "eval_samples_per_second": 49.001,
      "eval_steps_per_second": 12.74,
      "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": 4.182708527824896e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}