{
  "best_metric": 1.4155030250549316,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.00252881798832529,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.429393294417634e-05,
      "eval_loss": 1.7336317300796509,
      "eval_runtime": 1317.8086,
      "eval_samples_per_second": 7.581,
      "eval_steps_per_second": 1.896,
      "step": 1
    },
    {
      "epoch": 0.00025288179883252904,
      "grad_norm": 0.49506431818008423,
      "learning_rate": 0.00012,
      "loss": 1.4334,
      "step": 3
    },
    {
      "epoch": 0.0004214696647208817,
      "eval_loss": 1.5950169563293457,
      "eval_runtime": 1324.1752,
      "eval_samples_per_second": 7.544,
      "eval_steps_per_second": 1.886,
      "step": 5
    },
    {
      "epoch": 0.0005057635976650581,
      "grad_norm": 0.45649203658103943,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.5217,
      "step": 6
    },
    {
      "epoch": 0.0007586453964975871,
      "grad_norm": 0.5874845385551453,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.5183,
      "step": 9
    },
    {
      "epoch": 0.0008429393294417634,
      "eval_loss": 1.5017088651657104,
      "eval_runtime": 1322.8406,
      "eval_samples_per_second": 7.552,
      "eval_steps_per_second": 1.888,
      "step": 10
    },
    {
      "epoch": 0.0010115271953301161,
      "grad_norm": 0.37414276599884033,
      "learning_rate": 0.000163742398974869,
      "loss": 1.4129,
      "step": 12
    },
    {
      "epoch": 0.001264408994162645,
      "grad_norm": 0.39338499307632446,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4379,
      "step": 15
    },
    {
      "epoch": 0.001264408994162645,
      "eval_loss": 1.4593209028244019,
      "eval_runtime": 1323.5477,
      "eval_samples_per_second": 7.548,
      "eval_steps_per_second": 1.887,
      "step": 15
    },
    {
      "epoch": 0.0015172907929951742,
      "grad_norm": 0.3726945221424103,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.4376,
      "step": 18
    },
    {
      "epoch": 0.0016858786588835268,
      "eval_loss": 1.431047797203064,
      "eval_runtime": 1323.2684,
      "eval_samples_per_second": 7.549,
      "eval_steps_per_second": 1.888,
      "step": 20
    },
    {
      "epoch": 0.0017701725918277031,
      "grad_norm": 0.3949830234050751,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.3766,
      "step": 21
    },
    {
      "epoch": 0.0020230543906602323,
      "grad_norm": 0.47331270575523376,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.4327,
      "step": 24
    },
    {
      "epoch": 0.0021073483236044087,
      "eval_loss": 1.418473720550537,
      "eval_runtime": 1321.3789,
      "eval_samples_per_second": 7.56,
      "eval_steps_per_second": 1.89,
      "step": 25
    },
    {
      "epoch": 0.0022759361894927614,
      "grad_norm": 0.40120798349380493,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.3449,
      "step": 27
    },
    {
      "epoch": 0.00252881798832529,
      "grad_norm": 0.4255647659301758,
      "learning_rate": 0.0,
      "loss": 1.3517,
      "step": 30
    },
    {
      "epoch": 0.00252881798832529,
      "eval_loss": 1.4155030250549316,
      "eval_runtime": 1321.4996,
      "eval_samples_per_second": 7.56,
      "eval_steps_per_second": 1.89,
      "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": 2.4667752178384896e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}