{
  "best_metric": 0.6244143843650818,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0021422450728363325,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010711225364181663,
      "eval_loss": 0.9622905850410461,
      "eval_runtime": 1228.0338,
      "eval_samples_per_second": 3.201,
      "eval_steps_per_second": 1.601,
      "step": 1
    },
    {
      "epoch": 0.00032133676092544985,
      "grad_norm": 0.8823647499084473,
      "learning_rate": 0.00012,
      "loss": 0.8727,
      "step": 3
    },
    {
      "epoch": 0.0005355612682090831,
      "eval_loss": 0.8281564116477966,
      "eval_runtime": 1249.1258,
      "eval_samples_per_second": 3.147,
      "eval_steps_per_second": 1.574,
      "step": 5
    },
    {
      "epoch": 0.0006426735218508997,
      "grad_norm": 0.42191818356513977,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.8907,
      "step": 6
    },
    {
      "epoch": 0.0009640102827763496,
      "grad_norm": 0.5159677267074585,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.7614,
      "step": 9
    },
    {
      "epoch": 0.0010711225364181663,
      "eval_loss": 0.7212615013122559,
      "eval_runtime": 1244.9616,
      "eval_samples_per_second": 3.158,
      "eval_steps_per_second": 1.579,
      "step": 10
    },
    {
      "epoch": 0.0012853470437017994,
      "grad_norm": 0.34578871726989746,
      "learning_rate": 0.000163742398974869,
      "loss": 0.6988,
      "step": 12
    },
    {
      "epoch": 0.0016066838046272494,
      "grad_norm": 0.3703376054763794,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6307,
      "step": 15
    },
    {
      "epoch": 0.0016066838046272494,
      "eval_loss": 0.6502181887626648,
      "eval_runtime": 1246.9455,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 1.577,
      "step": 15
    },
    {
      "epoch": 0.0019280205655526992,
      "grad_norm": 0.458924800157547,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.6273,
      "step": 18
    },
    {
      "epoch": 0.0021422450728363325,
      "eval_loss": 0.6244143843650818,
      "eval_runtime": 1247.5698,
      "eval_samples_per_second": 3.151,
      "eval_steps_per_second": 1.576,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.430240492519424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}