{
  "best_metric": 0.5944854617118835,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.14414414414414414,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007207207207207207,
      "eval_loss": 2.6794052124023438,
      "eval_runtime": 25.3434,
      "eval_samples_per_second": 4.617,
      "eval_steps_per_second": 1.184,
      "step": 1
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 1.2505189180374146,
      "learning_rate": 0.00012,
      "loss": 10.3543,
      "step": 3
    },
    {
      "epoch": 0.036036036036036036,
      "eval_loss": 2.582805633544922,
      "eval_runtime": 25.5732,
      "eval_samples_per_second": 4.575,
      "eval_steps_per_second": 1.173,
      "step": 5
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 2.4514100551605225,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.3319,
      "step": 6
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 1.915582299232483,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.2138,
      "step": 9
    },
    {
      "epoch": 0.07207207207207207,
      "eval_loss": 1.749941349029541,
      "eval_runtime": 25.627,
      "eval_samples_per_second": 4.566,
      "eval_steps_per_second": 1.171,
      "step": 10
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 3.3332393169403076,
      "learning_rate": 0.000163742398974869,
      "loss": 7.0536,
      "step": 12
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 4.653995037078857,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.5987,
      "step": 15
    },
    {
      "epoch": 0.10810810810810811,
      "eval_loss": 0.8163535594940186,
      "eval_runtime": 25.7616,
      "eval_samples_per_second": 4.542,
      "eval_steps_per_second": 1.165,
      "step": 15
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": 2.8169493675231934,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.9801,
      "step": 18
    },
    {
      "epoch": 0.14414414414414414,
      "eval_loss": 0.5944854617118835,
      "eval_runtime": 25.5671,
      "eval_samples_per_second": 4.576,
      "eval_steps_per_second": 1.173,
      "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": 2.53297944428544e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}