{
  "best_metric": 1.0726149082183838,
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
  "epoch": 3.0027322404371586,
  "eval_steps": 50,
  "global_step": 274,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01092896174863388,
      "eval_loss": 1.3896751403808594,
      "eval_runtime": 4.4477,
      "eval_samples_per_second": 138.274,
      "eval_steps_per_second": 4.497,
      "step": 1
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.07987593859434128,
      "learning_rate": 0.000217,
      "loss": 1.2139,
      "step": 50
    },
    {
      "epoch": 0.546448087431694,
      "eval_loss": 1.1595056056976318,
      "eval_runtime": 4.5031,
      "eval_samples_per_second": 136.573,
      "eval_steps_per_second": 4.441,
      "step": 50
    },
    {
      "epoch": 1.0956284153005464,
      "grad_norm": 0.07953406125307083,
      "learning_rate": 0.000217,
      "loss": 1.1682,
      "step": 100
    },
    {
      "epoch": 1.0956284153005464,
      "eval_loss": 1.1244853734970093,
      "eval_runtime": 4.3309,
      "eval_samples_per_second": 142.001,
      "eval_steps_per_second": 4.618,
      "step": 100
    },
    {
      "epoch": 1.6420765027322406,
      "grad_norm": 0.10945800691843033,
      "learning_rate": 0.000217,
      "loss": 1.1145,
      "step": 150
    },
    {
      "epoch": 1.6420765027322406,
      "eval_loss": 1.0944714546203613,
      "eval_runtime": 4.5606,
      "eval_samples_per_second": 134.851,
      "eval_steps_per_second": 4.385,
      "step": 150
    },
    {
      "epoch": 2.191256830601093,
      "grad_norm": 0.10548992455005646,
      "learning_rate": 0.000217,
      "loss": 1.0988,
      "step": 200
    },
    {
      "epoch": 2.191256830601093,
      "eval_loss": 1.0749144554138184,
      "eval_runtime": 4.6732,
      "eval_samples_per_second": 131.601,
      "eval_steps_per_second": 4.28,
      "step": 200
    },
    {
      "epoch": 2.737704918032787,
      "grad_norm": 0.12534111738204956,
      "learning_rate": 0.000217,
      "loss": 1.0443,
      "step": 250
    },
    {
      "epoch": 2.737704918032787,
      "eval_loss": 1.0726149082183838,
      "eval_runtime": 4.5687,
      "eval_samples_per_second": 134.612,
      "eval_steps_per_second": 4.378,
      "step": 250
    }
  ],
  "logging_steps": 50,
  "max_steps": 274,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5797204929216512e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}