{
  "best_metric": 1.8561629056930542,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.01737619461337967,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017376194613379669,
      "grad_norm": 0.9666237235069275,
      "learning_rate": 2e-05,
      "loss": 2.4111,
      "step": 1
    },
    {
      "epoch": 0.0017376194613379669,
      "eval_loss": 2.35498046875,
      "eval_runtime": 48.5637,
      "eval_samples_per_second": 5.004,
      "eval_steps_per_second": 2.512,
      "step": 1
    },
    {
      "epoch": 0.0034752389226759338,
      "grad_norm": 0.8123922348022461,
      "learning_rate": 4e-05,
      "loss": 2.3583,
      "step": 2
    },
    {
      "epoch": 0.005212858384013901,
      "grad_norm": 0.7388425469398499,
      "learning_rate": 6e-05,
      "loss": 2.2589,
      "step": 3
    },
    {
      "epoch": 0.0069504778453518675,
      "grad_norm": 0.688607931137085,
      "learning_rate": 8e-05,
      "loss": 1.9124,
      "step": 4
    },
    {
      "epoch": 0.008688097306689836,
      "grad_norm": 0.9173185229301453,
      "learning_rate": 0.0001,
      "loss": 2.3572,
      "step": 5
    },
    {
      "epoch": 0.008688097306689836,
      "eval_loss": 2.288583278656006,
      "eval_runtime": 46.5472,
      "eval_samples_per_second": 5.221,
      "eval_steps_per_second": 2.621,
      "step": 5
    },
    {
      "epoch": 0.010425716768027803,
      "grad_norm": 1.004861831665039,
      "learning_rate": 0.00012,
      "loss": 2.2209,
      "step": 6
    },
    {
      "epoch": 0.01216333622936577,
      "grad_norm": 1.193684697151184,
      "learning_rate": 0.00014,
      "loss": 2.1625,
      "step": 7
    },
    {
      "epoch": 0.013900955690703735,
      "grad_norm": 1.0951910018920898,
      "learning_rate": 0.00016,
      "loss": 2.144,
      "step": 8
    },
    {
      "epoch": 0.015638575152041704,
      "grad_norm": 0.7744985818862915,
      "learning_rate": 0.00018,
      "loss": 1.9588,
      "step": 9
    },
    {
      "epoch": 0.01737619461337967,
      "grad_norm": 0.5166142582893372,
      "learning_rate": 0.0002,
      "loss": 1.9411,
      "step": 10
    },
    {
      "epoch": 0.01737619461337967,
      "eval_loss": 1.8561629056930542,
      "eval_runtime": 46.4923,
      "eval_samples_per_second": 5.227,
      "eval_steps_per_second": 2.624,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 2100974227292160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}