{
  "best_metric": 1.6694777011871338,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.019779133014669523,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006593044338223175,
      "eval_loss": 2.415243625640869,
      "eval_runtime": 92.316,
      "eval_samples_per_second": 6.922,
      "eval_steps_per_second": 3.466,
      "step": 1
    },
    {
      "epoch": 0.0019779133014669525,
      "grad_norm": 21.67613410949707,
      "learning_rate": 3e-05,
      "loss": 9.4106,
      "step": 3
    },
    {
      "epoch": 0.0032965221691115872,
      "eval_loss": 2.2570438385009766,
      "eval_runtime": 93.9378,
      "eval_samples_per_second": 6.802,
      "eval_steps_per_second": 3.407,
      "step": 5
    },
    {
      "epoch": 0.003955826602933905,
      "grad_norm": 16.66733169555664,
      "learning_rate": 6e-05,
      "loss": 8.6288,
      "step": 6
    },
    {
      "epoch": 0.005933739904400857,
      "grad_norm": 13.147473335266113,
      "learning_rate": 9e-05,
      "loss": 8.1932,
      "step": 9
    },
    {
      "epoch": 0.0065930443382231745,
      "eval_loss": 1.9741439819335938,
      "eval_runtime": 94.0939,
      "eval_samples_per_second": 6.791,
      "eval_steps_per_second": 3.401,
      "step": 10
    },
    {
      "epoch": 0.00791165320586781,
      "grad_norm": 12.685226440429688,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.1619,
      "step": 12
    },
    {
      "epoch": 0.009889566507334762,
      "grad_norm": 13.328250885009766,
      "learning_rate": 8.535533905932738e-05,
      "loss": 7.2866,
      "step": 15
    },
    {
      "epoch": 0.009889566507334762,
      "eval_loss": 1.8088501691818237,
      "eval_runtime": 94.236,
      "eval_samples_per_second": 6.781,
      "eval_steps_per_second": 3.396,
      "step": 15
    },
    {
      "epoch": 0.011867479808801713,
      "grad_norm": 12.901671409606934,
      "learning_rate": 6.545084971874738e-05,
      "loss": 7.4435,
      "step": 18
    },
    {
      "epoch": 0.013186088676446349,
      "eval_loss": 1.7110700607299805,
      "eval_runtime": 94.1924,
      "eval_samples_per_second": 6.784,
      "eval_steps_per_second": 3.397,
      "step": 20
    },
    {
      "epoch": 0.013845393110268667,
      "grad_norm": 12.697035789489746,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 6.8798,
      "step": 21
    },
    {
      "epoch": 0.01582330641173562,
      "grad_norm": 10.777671813964844,
      "learning_rate": 2.061073738537635e-05,
      "loss": 6.7368,
      "step": 24
    },
    {
      "epoch": 0.016482610845557938,
      "eval_loss": 1.6773645877838135,
      "eval_runtime": 94.2167,
      "eval_samples_per_second": 6.782,
      "eval_steps_per_second": 3.396,
      "step": 25
    },
    {
      "epoch": 0.01780121971320257,
      "grad_norm": 10.499444961547852,
      "learning_rate": 5.449673790581611e-06,
      "loss": 6.576,
      "step": 27
    },
    {
      "epoch": 0.019779133014669523,
      "grad_norm": 10.993064880371094,
      "learning_rate": 0.0,
      "loss": 6.6867,
      "step": 30
    },
    {
      "epoch": 0.019779133014669523,
      "eval_loss": 1.6694777011871338,
      "eval_runtime": 94.2006,
      "eval_samples_per_second": 6.783,
      "eval_steps_per_second": 3.397,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054694248022016e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}