{
  "best_metric": 0.007178535684943199,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 3.0074074074074075,
  "eval_steps": 50,
  "global_step": 203,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014814814814814815,
      "eval_loss": 0.18927377462387085,
      "eval_runtime": 8.3823,
      "eval_samples_per_second": 13.6,
      "eval_steps_per_second": 3.46,
      "step": 1
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.3402048349380493,
      "learning_rate": 0.0002,
      "loss": 0.1582,
      "step": 10
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.45105603337287903,
      "learning_rate": 0.00019867810796112744,
      "loss": 0.0837,
      "step": 20
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.8855344653129578,
      "learning_rate": 0.00019474737981575832,
      "loss": 0.0677,
      "step": 30
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.7827640175819397,
      "learning_rate": 0.00018831173552873946,
      "loss": 0.0523,
      "step": 40
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.9265003800392151,
      "learning_rate": 0.00017954131963903133,
      "loss": 0.1269,
      "step": 50
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.029032791033387184,
      "eval_runtime": 8.5235,
      "eval_samples_per_second": 13.375,
      "eval_steps_per_second": 3.402,
      "step": 50
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.5671200156211853,
      "learning_rate": 0.00016866800300547813,
      "loss": 0.0523,
      "step": 60
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.22327843308448792,
      "learning_rate": 0.00015597925264196049,
      "loss": 0.0572,
      "step": 70
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.48100635409355164,
      "learning_rate": 0.00014181053171025392,
      "loss": 0.0405,
      "step": 80
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4037186801433563,
      "learning_rate": 0.00012653643059837107,
      "loss": 0.0304,
      "step": 90
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.2432849258184433,
      "learning_rate": 0.0001105607635595266,
      "loss": 0.0456,
      "step": 100
    },
    {
      "epoch": 1.4814814814814814,
      "eval_loss": 0.009937474504113197,
      "eval_runtime": 8.5329,
      "eval_samples_per_second": 13.36,
      "eval_steps_per_second": 3.399,
      "step": 100
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 0.2168407291173935,
      "learning_rate": 9.430589273520703e-05,
      "loss": 0.0303,
      "step": 110
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.15916159749031067,
      "learning_rate": 7.820156181212379e-05,
      "loss": 0.033,
      "step": 120
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 0.15106461942195892,
      "learning_rate": 6.267353452704876e-05,
      "loss": 0.037,
      "step": 130
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.16333474218845367,
      "learning_rate": 4.813233839293265e-05,
      "loss": 0.0245,
      "step": 140
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.19706226885318756,
      "learning_rate": 3.496241123788294e-05,
      "loss": 0.0288,
      "step": 150
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 0.007178535684943199,
      "eval_runtime": 8.5278,
      "eval_samples_per_second": 13.368,
      "eval_steps_per_second": 3.401,
      "step": 150
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.1319075971841812,
      "learning_rate": 2.3511937499075508e-05,
      "loss": 0.0143,
      "step": 160
    },
    {
      "epoch": 2.5185185185185186,
      "grad_norm": 0.2327166497707367,
      "learning_rate": 1.4083642978043277e-05,
      "loss": 0.0191,
      "step": 170
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.19548346102237701,
      "learning_rate": 6.9267914241362585e-06,
      "loss": 0.0226,
      "step": 180
    },
    {
      "epoch": 2.814814814814815,
      "grad_norm": 0.1185711920261383,
      "learning_rate": 2.230594539204489e-06,
      "loss": 0.0134,
      "step": 190
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.09321712702512741,
      "learning_rate": 1.192096287513711e-07,
      "loss": 0.0152,
      "step": 200
    },
    {
      "epoch": 2.962962962962963,
      "eval_loss": 0.006627695634961128,
      "eval_runtime": 8.5391,
      "eval_samples_per_second": 13.35,
      "eval_steps_per_second": 3.396,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 203,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 150,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 2.90017796878762e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}