{
  "best_metric": 1.608966588973999,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.006165703275529865,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.165703275529865e-05,
      "eval_loss": 2.288787603378296,
      "eval_runtime": 1041.9153,
      "eval_samples_per_second": 13.109,
      "eval_steps_per_second": 6.554,
      "step": 1
    },
    {
      "epoch": 0.0024662813102119463,
      "grad_norm": 1.1392245292663574,
      "learning_rate": 5e-05,
      "loss": 1.8648,
      "step": 40
    },
    {
      "epoch": 0.0030828516377649326,
      "eval_loss": 1.6245982646942139,
      "eval_runtime": 1041.7956,
      "eval_samples_per_second": 13.11,
      "eval_steps_per_second": 6.555,
      "step": 50
    },
    {
      "epoch": 0.0049325626204238925,
      "grad_norm": 1.1976816654205322,
      "learning_rate": 0.0001,
      "loss": 1.6089,
      "step": 80
    },
    {
      "epoch": 0.006165703275529865,
      "eval_loss": 1.608966588973999,
      "eval_runtime": 1041.4182,
      "eval_samples_per_second": 13.115,
      "eval_steps_per_second": 6.557,
      "step": 100
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "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": 4.098397133655245e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}