{
  "best_metric": 0.6009775400161743,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.10875475802066341,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001087547580206634,
      "eval_loss": 2.6140365600585938,
      "eval_runtime": 22.8682,
      "eval_samples_per_second": 16.967,
      "eval_steps_per_second": 4.242,
      "step": 1
    },
    {
      "epoch": 0.010875475802066341,
      "grad_norm": 1.15413498878479,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 0.6819,
      "step": 10
    },
    {
      "epoch": 0.021750951604132682,
      "grad_norm": 1.6452891826629639,
      "learning_rate": 8.400000000000001e-05,
      "loss": 0.6379,
      "step": 20
    },
    {
      "epoch": 0.03262642740619902,
      "grad_norm": 2.625800848007202,
      "learning_rate": 0.000126,
      "loss": 0.4516,
      "step": 30
    },
    {
      "epoch": 0.043501903208265365,
      "grad_norm": 6.286452770233154,
      "learning_rate": 0.00016800000000000002,
      "loss": 0.5501,
      "step": 40
    },
    {
      "epoch": 0.054377379010331704,
      "grad_norm": 4.992573261260986,
      "learning_rate": 0.00021,
      "loss": 0.4475,
      "step": 50
    },
    {
      "epoch": 0.054377379010331704,
      "eval_loss": 0.6009775400161743,
      "eval_runtime": 22.7637,
      "eval_samples_per_second": 17.045,
      "eval_steps_per_second": 4.261,
      "step": 50
    },
    {
      "epoch": 0.06525285481239804,
      "grad_norm": 1.2332814931869507,
      "learning_rate": 0.00020974422527728155,
      "loss": 0.2856,
      "step": 60
    },
    {
      "epoch": 0.07612833061446438,
      "grad_norm": 0.9268720149993896,
      "learning_rate": 0.0002089781472178649,
      "loss": 0.2699,
      "step": 70
    },
    {
      "epoch": 0.08700380641653073,
      "grad_norm": 1.5051002502441406,
      "learning_rate": 0.0002077054980770496,
      "loss": 0.2242,
      "step": 80
    },
    {
      "epoch": 0.09787928221859707,
      "grad_norm": 4.559469223022461,
      "learning_rate": 0.00020593247807352348,
      "loss": 0.2854,
      "step": 90
    },
    {
      "epoch": 0.10875475802066341,
      "grad_norm": 2.309359073638916,
      "learning_rate": 0.00020366772518252038,
      "loss": 0.4822,
      "step": 100
    },
    {
      "epoch": 0.10875475802066341,
      "eval_loss": 0.6521262526512146,
      "eval_runtime": 22.8192,
      "eval_samples_per_second": 17.003,
      "eval_steps_per_second": 4.251,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.804021269528576e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}