{
  "best_metric": 1.2019925117492676,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.17046665246111228,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003409333049222246,
      "eval_loss": 1.5774061679840088,
      "eval_runtime": 861.8671,
      "eval_samples_per_second": 5.732,
      "eval_steps_per_second": 1.433,
      "step": 1
    },
    {
      "epoch": 0.01704666524611123,
      "grad_norm": 0.3103428781032562,
      "learning_rate": 0.0001075,
      "loss": 1.4204,
      "step": 50
    },
    {
      "epoch": 0.03409333049222246,
      "grad_norm": 0.26232999563217163,
      "learning_rate": 0.000215,
      "loss": 1.29,
      "step": 100
    },
    {
      "epoch": 0.051139995738333686,
      "grad_norm": 0.25642865896224976,
      "learning_rate": 0.0002068170497449633,
      "loss": 1.2655,
      "step": 150
    },
    {
      "epoch": 0.06818666098444492,
      "grad_norm": 0.25544941425323486,
      "learning_rate": 0.00018351397897755384,
      "loss": 1.2377,
      "step": 200
    },
    {
      "epoch": 0.08523332623055614,
      "grad_norm": 0.24827460944652557,
      "learning_rate": 0.00014863846897924716,
      "loss": 1.2247,
      "step": 250
    },
    {
      "epoch": 0.10227999147666737,
      "grad_norm": 0.29134467244148254,
      "learning_rate": 0.0001075,
      "loss": 1.2223,
      "step": 300
    },
    {
      "epoch": 0.1193266567227786,
      "grad_norm": 0.25550398230552673,
      "learning_rate": 6.636153102075285e-05,
      "loss": 1.2133,
      "step": 350
    },
    {
      "epoch": 0.13637332196888985,
      "grad_norm": 0.2586924135684967,
      "learning_rate": 3.148602102244615e-05,
      "loss": 1.2099,
      "step": 400
    },
    {
      "epoch": 0.15341998721500105,
      "grad_norm": 0.23815681040287018,
      "learning_rate": 8.182950255036675e-06,
      "loss": 1.1922,
      "step": 450
    },
    {
      "epoch": 0.17046665246111228,
      "grad_norm": 0.2304764986038208,
      "learning_rate": 0.0,
      "loss": 1.2125,
      "step": 500
    },
    {
      "epoch": 0.17046665246111228,
      "eval_loss": 1.2019925117492676,
      "eval_runtime": 862.7591,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 1.431,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 1.1656918990093025e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}