{
  "best_metric": 0.005947421304881573,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 3.0074074074074075,
  "eval_steps": 100,
  "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": 8.2776,
      "eval_samples_per_second": 13.772,
      "eval_steps_per_second": 3.503,
      "step": 1
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.1394836902618408,
      "learning_rate": 0.0002,
      "loss": 0.217,
      "step": 10
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.5900225639343262,
      "learning_rate": 0.00019867810796112744,
      "loss": 0.0815,
      "step": 20
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.951280415058136,
      "learning_rate": 0.00019474737981575832,
      "loss": 0.0673,
      "step": 30
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.5382400155067444,
      "learning_rate": 0.00018831173552873946,
      "loss": 0.0433,
      "step": 40
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.19571830332279205,
      "learning_rate": 0.00017954131963903133,
      "loss": 0.0388,
      "step": 50
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.31481191515922546,
      "learning_rate": 0.00016866800300547813,
      "loss": 0.0407,
      "step": 60
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.14493128657341003,
      "learning_rate": 0.00015597925264196049,
      "loss": 0.0374,
      "step": 70
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.297669917345047,
      "learning_rate": 0.00014181053171025392,
      "loss": 0.0287,
      "step": 80
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4568837285041809,
      "learning_rate": 0.00012653643059837107,
      "loss": 0.0319,
      "step": 90
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.18460723757743835,
      "learning_rate": 0.0001105607635595266,
      "loss": 0.0342,
      "step": 100
    },
    {
      "epoch": 1.4814814814814814,
      "eval_loss": 0.009630908258259296,
      "eval_runtime": 8.488,
      "eval_samples_per_second": 13.431,
      "eval_steps_per_second": 3.417,
      "step": 100
    },
    {
      "epoch": 1.6296296296296298,
      "grad_norm": 0.28684261441230774,
      "learning_rate": 9.430589273520703e-05,
      "loss": 0.0289,
      "step": 110
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.17550404369831085,
      "learning_rate": 7.820156181212379e-05,
      "loss": 0.0305,
      "step": 120
    },
    {
      "epoch": 1.925925925925926,
      "grad_norm": 0.2396201491355896,
      "learning_rate": 6.267353452704876e-05,
      "loss": 0.0425,
      "step": 130
    },
    {
      "epoch": 2.074074074074074,
      "grad_norm": 0.11954505741596222,
      "learning_rate": 4.813233839293265e-05,
      "loss": 0.0194,
      "step": 140
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.20377297699451447,
      "learning_rate": 3.496241123788294e-05,
      "loss": 0.0259,
      "step": 150
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.1429290771484375,
      "learning_rate": 2.3511937499075508e-05,
      "loss": 0.0165,
      "step": 160
    },
    {
      "epoch": 2.5185185185185186,
      "grad_norm": 0.07042884826660156,
      "learning_rate": 1.4083642978043277e-05,
      "loss": 0.0214,
      "step": 170
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.24834026396274567,
      "learning_rate": 6.9267914241362585e-06,
      "loss": 0.0231,
      "step": 180
    },
    {
      "epoch": 2.814814814814815,
      "grad_norm": 0.1596260964870453,
      "learning_rate": 2.230594539204489e-06,
      "loss": 0.0126,
      "step": 190
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.10979495942592621,
      "learning_rate": 1.192096287513711e-07,
      "loss": 0.0212,
      "step": 200
    },
    {
      "epoch": 2.962962962962963,
      "eval_loss": 0.005947421304881573,
      "eval_runtime": 8.491,
      "eval_samples_per_second": 13.426,
      "eval_steps_per_second": 3.415,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 203,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "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": 2.8748166164014694e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}