{
  "best_metric": 2.7828643321990967,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.010875475802066341,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036251586006887804,
      "eval_loss": 2.916715383529663,
      "eval_runtime": 43.8601,
      "eval_samples_per_second": 26.493,
      "eval_steps_per_second": 13.247,
      "step": 1
    },
    {
      "epoch": 0.001087547580206634,
      "grad_norm": 0.9060821533203125,
      "learning_rate": 0.00012,
      "loss": 2.9159,
      "step": 3
    },
    {
      "epoch": 0.0018125793003443901,
      "eval_loss": 2.8510138988494873,
      "eval_runtime": 43.7838,
      "eval_samples_per_second": 26.539,
      "eval_steps_per_second": 13.27,
      "step": 5
    },
    {
      "epoch": 0.002175095160413268,
      "grad_norm": 0.6758049130439758,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.994,
      "step": 6
    },
    {
      "epoch": 0.0032626427406199023,
      "grad_norm": 0.7025123834609985,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.9295,
      "step": 9
    },
    {
      "epoch": 0.0036251586006887803,
      "eval_loss": 2.819524049758911,
      "eval_runtime": 43.8329,
      "eval_samples_per_second": 26.51,
      "eval_steps_per_second": 13.255,
      "step": 10
    },
    {
      "epoch": 0.004350190320826536,
      "grad_norm": 0.8129050731658936,
      "learning_rate": 0.000163742398974869,
      "loss": 2.828,
      "step": 12
    },
    {
      "epoch": 0.005437737901033171,
      "grad_norm": 0.6539782285690308,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8362,
      "step": 15
    },
    {
      "epoch": 0.005437737901033171,
      "eval_loss": 2.798804998397827,
      "eval_runtime": 44.1608,
      "eval_samples_per_second": 26.313,
      "eval_steps_per_second": 13.156,
      "step": 15
    },
    {
      "epoch": 0.0065252854812398045,
      "grad_norm": 0.6255491971969604,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.8781,
      "step": 18
    },
    {
      "epoch": 0.0072503172013775605,
      "eval_loss": 2.7887346744537354,
      "eval_runtime": 43.8696,
      "eval_samples_per_second": 26.488,
      "eval_steps_per_second": 13.244,
      "step": 20
    },
    {
      "epoch": 0.0076128330614464385,
      "grad_norm": 0.667388916015625,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.8908,
      "step": 21
    },
    {
      "epoch": 0.008700380641653072,
      "grad_norm": 0.6787062287330627,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.8226,
      "step": 24
    },
    {
      "epoch": 0.00906289650172195,
      "eval_loss": 2.783844470977783,
      "eval_runtime": 43.9784,
      "eval_samples_per_second": 26.422,
      "eval_steps_per_second": 13.211,
      "step": 25
    },
    {
      "epoch": 0.009787928221859706,
      "grad_norm": 0.6023674011230469,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.864,
      "step": 27
    },
    {
      "epoch": 0.010875475802066341,
      "grad_norm": 0.6628087162971497,
      "learning_rate": 0.0,
      "loss": 2.8414,
      "step": 30
    },
    {
      "epoch": 0.010875475802066341,
      "eval_loss": 2.7828643321990967,
      "eval_runtime": 43.787,
      "eval_samples_per_second": 26.538,
      "eval_steps_per_second": 13.269,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 743484122726400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}