{
  "best_metric": 0.43841221928596497,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.0023310023310024,
  "eval_steps": 50,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004662004662004662,
      "eval_loss": 0.7121074199676514,
      "eval_runtime": 7.0933,
      "eval_samples_per_second": 12.829,
      "eval_steps_per_second": 3.242,
      "step": 1
    },
    {
      "epoch": 0.046620046620046623,
      "grad_norm": 0.5039583444595337,
      "learning_rate": 4.22e-05,
      "loss": 0.6299,
      "step": 10
    },
    {
      "epoch": 0.09324009324009325,
      "grad_norm": 0.983407199382782,
      "learning_rate": 8.44e-05,
      "loss": 0.6324,
      "step": 20
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 0.9202139377593994,
      "learning_rate": 0.0001266,
      "loss": 0.5562,
      "step": 30
    },
    {
      "epoch": 0.1864801864801865,
      "grad_norm": 1.4665826559066772,
      "learning_rate": 0.0001688,
      "loss": 0.5768,
      "step": 40
    },
    {
      "epoch": 0.2331002331002331,
      "grad_norm": 2.6910219192504883,
      "learning_rate": 0.000211,
      "loss": 0.5501,
      "step": 50
    },
    {
      "epoch": 0.2331002331002331,
      "eval_loss": 0.5634785890579224,
      "eval_runtime": 7.092,
      "eval_samples_per_second": 12.831,
      "eval_steps_per_second": 3.243,
      "step": 50
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 0.5147734880447388,
      "learning_rate": 0.00020909347756121555,
      "loss": 0.6062,
      "step": 60
    },
    {
      "epoch": 0.32634032634032634,
      "grad_norm": 0.5392813682556152,
      "learning_rate": 0.00020344281693319567,
      "loss": 0.5125,
      "step": 70
    },
    {
      "epoch": 0.372960372960373,
      "grad_norm": 0.8237327337265015,
      "learning_rate": 0.00019425224771368963,
      "loss": 0.4912,
      "step": 80
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 0.8676568269729614,
      "learning_rate": 0.0001818539410200849,
      "loss": 0.4504,
      "step": 90
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 2.122711181640625,
      "learning_rate": 0.00016669600395976142,
      "loss": 0.4019,
      "step": 100
    },
    {
      "epoch": 0.4662004662004662,
      "eval_loss": 0.5337139368057251,
      "eval_runtime": 7.0219,
      "eval_samples_per_second": 12.959,
      "eval_steps_per_second": 3.275,
      "step": 100
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.6717955470085144,
      "learning_rate": 0.00014932628387169904,
      "loss": 0.473,
      "step": 110
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.6870163083076477,
      "learning_rate": 0.0001303725676962446,
      "loss": 0.482,
      "step": 120
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.6760181784629822,
      "learning_rate": 0.00011051989211940484,
      "loss": 0.4559,
      "step": 130
    },
    {
      "epoch": 0.6526806526806527,
      "grad_norm": 0.966548502445221,
      "learning_rate": 9.048578456216843e-05,
      "loss": 0.4025,
      "step": 140
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 3.640005588531494,
      "learning_rate": 7.099432987001202e-05,
      "loss": 0.4958,
      "step": 150
    },
    {
      "epoch": 0.6993006993006993,
      "eval_loss": 0.4841608703136444,
      "eval_runtime": 7.1179,
      "eval_samples_per_second": 12.785,
      "eval_steps_per_second": 3.231,
      "step": 150
    },
    {
      "epoch": 0.745920745920746,
      "grad_norm": 0.4770185649394989,
      "learning_rate": 5.275000000000002e-05,
      "loss": 0.4045,
      "step": 160
    },
    {
      "epoch": 0.7925407925407926,
      "grad_norm": 0.7207168340682983,
      "learning_rate": 3.6412192568772434e-05,
      "loss": 0.4739,
      "step": 170
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 0.7188816666603088,
      "learning_rate": 2.257139850463594e-05,
      "loss": 0.4556,
      "step": 180
    },
    {
      "epoch": 0.8857808857808858,
      "grad_norm": 0.9799768328666687,
      "learning_rate": 1.1727860166905585e-05,
      "loss": 0.5001,
      "step": 190
    },
    {
      "epoch": 0.9324009324009324,
      "grad_norm": 2.884735584259033,
      "learning_rate": 4.27349128367054e-06,
      "loss": 0.5498,
      "step": 200
    },
    {
      "epoch": 0.9324009324009324,
      "eval_loss": 0.43841221928596497,
      "eval_runtime": 6.931,
      "eval_samples_per_second": 13.129,
      "eval_steps_per_second": 3.318,
      "step": 200
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 0.7910031676292419,
      "learning_rate": 4.777121685395759e-07,
      "loss": 0.4308,
      "step": 210
    }
  ],
  "logging_steps": 10,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4.789784787340493e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}