{
  "best_metric": 1.5616466999053955,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.015887726731100223,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005295908910366742,
      "eval_loss": 3.4928104877471924,
      "eval_runtime": 87.0243,
      "eval_samples_per_second": 18.271,
      "eval_steps_per_second": 4.573,
      "step": 1
    },
    {
      "epoch": 0.0015887726731100226,
      "grad_norm": 1.1175850629806519,
      "learning_rate": 0.00012,
      "loss": 2.6221,
      "step": 3
    },
    {
      "epoch": 0.0026479544551833707,
      "eval_loss": 3.100562334060669,
      "eval_runtime": 86.9928,
      "eval_samples_per_second": 18.277,
      "eval_steps_per_second": 4.575,
      "step": 5
    },
    {
      "epoch": 0.003177545346220045,
      "grad_norm": 1.429335117340088,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.4636,
      "step": 6
    },
    {
      "epoch": 0.004766318019330067,
      "grad_norm": 1.6837695837020874,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.8967,
      "step": 9
    },
    {
      "epoch": 0.005295908910366741,
      "eval_loss": 2.1939339637756348,
      "eval_runtime": 87.0,
      "eval_samples_per_second": 18.276,
      "eval_steps_per_second": 4.575,
      "step": 10
    },
    {
      "epoch": 0.00635509069244009,
      "grad_norm": 2.1099212169647217,
      "learning_rate": 0.000163742398974869,
      "loss": 1.6025,
      "step": 12
    },
    {
      "epoch": 0.007943863365550112,
      "grad_norm": 2.824223041534424,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7027,
      "step": 15
    },
    {
      "epoch": 0.007943863365550112,
      "eval_loss": 1.879441499710083,
      "eval_runtime": 86.9668,
      "eval_samples_per_second": 18.283,
      "eval_steps_per_second": 4.576,
      "step": 15
    },
    {
      "epoch": 0.009532636038660135,
      "grad_norm": 1.6235729455947876,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.8063,
      "step": 18
    },
    {
      "epoch": 0.010591817820733483,
      "eval_loss": 1.6363563537597656,
      "eval_runtime": 86.9975,
      "eval_samples_per_second": 18.276,
      "eval_steps_per_second": 4.575,
      "step": 20
    },
    {
      "epoch": 0.011121408711770158,
      "grad_norm": 1.313387155532837,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.4939,
      "step": 21
    },
    {
      "epoch": 0.01271018138488018,
      "grad_norm": 1.5589934587478638,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.6683,
      "step": 24
    },
    {
      "epoch": 0.013239772275916854,
      "eval_loss": 1.5733295679092407,
      "eval_runtime": 86.9917,
      "eval_samples_per_second": 18.278,
      "eval_steps_per_second": 4.575,
      "step": 25
    },
    {
      "epoch": 0.014298954057990202,
      "grad_norm": 1.331397294998169,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.6898,
      "step": 27
    },
    {
      "epoch": 0.015887726731100223,
      "grad_norm": 1.5433915853500366,
      "learning_rate": 0.0,
      "loss": 1.6671,
      "step": 30
    },
    {
      "epoch": 0.015887726731100223,
      "eval_loss": 1.5616466999053955,
      "eval_runtime": 87.023,
      "eval_samples_per_second": 18.271,
      "eval_steps_per_second": 4.574,
      "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": 9878076024422400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}