{
  "best_metric": 0.35316547751426697,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.087527352297593,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00087527352297593,
      "eval_loss": 0.5409302115440369,
      "eval_runtime": 48.1638,
      "eval_samples_per_second": 9.987,
      "eval_steps_per_second": 2.512,
      "step": 1
    },
    {
      "epoch": 0.0087527352297593,
      "grad_norm": 0.6199236512184143,
      "learning_rate": 4.22e-05,
      "loss": 1.1012,
      "step": 10
    },
    {
      "epoch": 0.0175054704595186,
      "grad_norm": 0.603871762752533,
      "learning_rate": 8.44e-05,
      "loss": 0.7497,
      "step": 20
    },
    {
      "epoch": 0.0262582056892779,
      "grad_norm": 0.17278185486793518,
      "learning_rate": 0.0001266,
      "loss": 0.2424,
      "step": 30
    },
    {
      "epoch": 0.0350109409190372,
      "grad_norm": 0.2742425203323364,
      "learning_rate": 0.0001688,
      "loss": 0.0084,
      "step": 40
    },
    {
      "epoch": 0.0437636761487965,
      "grad_norm": 0.21153666079044342,
      "learning_rate": 0.000211,
      "loss": 0.0076,
      "step": 50
    },
    {
      "epoch": 0.0437636761487965,
      "eval_loss": 0.4160047173500061,
      "eval_runtime": 48.0642,
      "eval_samples_per_second": 10.007,
      "eval_steps_per_second": 2.517,
      "step": 50
    },
    {
      "epoch": 0.0525164113785558,
      "grad_norm": 0.5463985204696655,
      "learning_rate": 0.00021074300730241147,
      "loss": 0.6921,
      "step": 60
    },
    {
      "epoch": 0.061269146608315096,
      "grad_norm": 0.8098825812339783,
      "learning_rate": 0.00020997328125223568,
      "loss": 0.5244,
      "step": 70
    },
    {
      "epoch": 0.0700218818380744,
      "grad_norm": 0.38064104318618774,
      "learning_rate": 0.0002086945718774165,
      "loss": 0.2607,
      "step": 80
    },
    {
      "epoch": 0.0787746170678337,
      "grad_norm": 0.050267886370420456,
      "learning_rate": 0.00020691310892149265,
      "loss": 0.0061,
      "step": 90
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 0.3279358148574829,
      "learning_rate": 0.00020463757149291335,
      "loss": 0.0024,
      "step": 100
    },
    {
      "epoch": 0.087527352297593,
      "eval_loss": 0.35316547751426697,
      "eval_runtime": 48.4486,
      "eval_samples_per_second": 9.928,
      "eval_steps_per_second": 2.497,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.252570367721472e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}