{
  "best_metric": 2.6063930988311768,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.00975371860521824,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003251239535072746,
      "eval_loss": 3.9193971157073975,
      "eval_runtime": 228.562,
      "eval_samples_per_second": 11.336,
      "eval_steps_per_second": 2.835,
      "step": 1
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 1.5996079444885254,
      "learning_rate": 0.00012,
      "loss": 2.557,
      "step": 3
    },
    {
      "epoch": 0.0016256197675363732,
      "eval_loss": 3.553191900253296,
      "eval_runtime": 228.5198,
      "eval_samples_per_second": 11.338,
      "eval_steps_per_second": 2.836,
      "step": 5
    },
    {
      "epoch": 0.001950743721043648,
      "grad_norm": 2.073932647705078,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.4685,
      "step": 6
    },
    {
      "epoch": 0.002926115581565472,
      "grad_norm": 1.3495839834213257,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.2953,
      "step": 9
    },
    {
      "epoch": 0.0032512395350727465,
      "eval_loss": 3.028703212738037,
      "eval_runtime": 228.8022,
      "eval_samples_per_second": 11.324,
      "eval_steps_per_second": 2.832,
      "step": 10
    },
    {
      "epoch": 0.003901487442087296,
      "grad_norm": 1.0149577856063843,
      "learning_rate": 0.000163742398974869,
      "loss": 2.2831,
      "step": 12
    },
    {
      "epoch": 0.00487685930260912,
      "grad_norm": 1.0780360698699951,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2027,
      "step": 15
    },
    {
      "epoch": 0.00487685930260912,
      "eval_loss": 2.7850940227508545,
      "eval_runtime": 228.566,
      "eval_samples_per_second": 11.336,
      "eval_steps_per_second": 2.835,
      "step": 15
    },
    {
      "epoch": 0.005852231163130944,
      "grad_norm": 1.1503500938415527,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.3607,
      "step": 18
    },
    {
      "epoch": 0.006502479070145493,
      "eval_loss": 2.664445400238037,
      "eval_runtime": 229.157,
      "eval_samples_per_second": 11.307,
      "eval_steps_per_second": 2.828,
      "step": 20
    },
    {
      "epoch": 0.006827603023652768,
      "grad_norm": 1.208409309387207,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.3119,
      "step": 21
    },
    {
      "epoch": 0.007802974884174592,
      "grad_norm": 1.367969274520874,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.3106,
      "step": 24
    },
    {
      "epoch": 0.008128098837681867,
      "eval_loss": 2.616642951965332,
      "eval_runtime": 228.6629,
      "eval_samples_per_second": 11.331,
      "eval_steps_per_second": 2.834,
      "step": 25
    },
    {
      "epoch": 0.008778346744696415,
      "grad_norm": 1.717703104019165,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.3972,
      "step": 27
    },
    {
      "epoch": 0.00975371860521824,
      "grad_norm": 1.9316027164459229,
      "learning_rate": 0.0,
      "loss": 2.2749,
      "step": 30
    },
    {
      "epoch": 0.00975371860521824,
      "eval_loss": 2.6063930988311768,
      "eval_runtime": 228.8831,
      "eval_samples_per_second": 11.32,
      "eval_steps_per_second": 2.831,
      "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": 2.470837626077184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}