{
  "best_metric": 2.766298294067383,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.08064516129032258,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002688172043010753,
      "eval_loss": 3.4243428707122803,
      "eval_runtime": 19.3608,
      "eval_samples_per_second": 16.218,
      "eval_steps_per_second": 4.08,
      "step": 1
    },
    {
      "epoch": 0.008064516129032258,
      "grad_norm": 0.7152450680732727,
      "learning_rate": 0.00012,
      "loss": 3.1647,
      "step": 3
    },
    {
      "epoch": 0.013440860215053764,
      "eval_loss": 3.157710075378418,
      "eval_runtime": 18.5749,
      "eval_samples_per_second": 16.905,
      "eval_steps_per_second": 4.253,
      "step": 5
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 0.4566909968852997,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.262,
      "step": 6
    },
    {
      "epoch": 0.024193548387096774,
      "grad_norm": 0.7445195317268372,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.0191,
      "step": 9
    },
    {
      "epoch": 0.026881720430107527,
      "eval_loss": 2.905691385269165,
      "eval_runtime": 18.5532,
      "eval_samples_per_second": 16.924,
      "eval_steps_per_second": 4.258,
      "step": 10
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.38733378052711487,
      "learning_rate": 0.000163742398974869,
      "loss": 2.9041,
      "step": 12
    },
    {
      "epoch": 0.04032258064516129,
      "grad_norm": 0.37677866220474243,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8743,
      "step": 15
    },
    {
      "epoch": 0.04032258064516129,
      "eval_loss": 2.8276760578155518,
      "eval_runtime": 18.5601,
      "eval_samples_per_second": 16.918,
      "eval_steps_per_second": 4.256,
      "step": 15
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 0.3784741163253784,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.7693,
      "step": 18
    },
    {
      "epoch": 0.053763440860215055,
      "eval_loss": 2.7892918586730957,
      "eval_runtime": 19.0013,
      "eval_samples_per_second": 16.525,
      "eval_steps_per_second": 4.158,
      "step": 20
    },
    {
      "epoch": 0.056451612903225805,
      "grad_norm": 0.425810307264328,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.751,
      "step": 21
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 0.4043796956539154,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.8102,
      "step": 24
    },
    {
      "epoch": 0.06720430107526881,
      "eval_loss": 2.7712013721466064,
      "eval_runtime": 18.5863,
      "eval_samples_per_second": 16.894,
      "eval_steps_per_second": 4.25,
      "step": 25
    },
    {
      "epoch": 0.07258064516129033,
      "grad_norm": 0.47676122188568115,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.6888,
      "step": 27
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 0.8812837600708008,
      "learning_rate": 0.0,
      "loss": 2.6662,
      "step": 30
    },
    {
      "epoch": 0.08064516129032258,
      "eval_loss": 2.766298294067383,
      "eval_runtime": 18.9878,
      "eval_samples_per_second": 16.537,
      "eval_steps_per_second": 4.161,
      "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": 1.012502792503296e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}