{
  "best_metric": 1.2058666944503784,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0013823610727121925,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.607870242373975e-05,
      "eval_loss": 1.6098943948745728,
      "eval_runtime": 1879.8428,
      "eval_samples_per_second": 4.861,
      "eval_steps_per_second": 2.431,
      "step": 1
    },
    {
      "epoch": 0.00013823610727121925,
      "grad_norm": 0.8221157193183899,
      "learning_rate": 6e-05,
      "loss": 5.9377,
      "step": 3
    },
    {
      "epoch": 0.00023039351211869873,
      "eval_loss": 1.5648736953735352,
      "eval_runtime": 1888.9741,
      "eval_samples_per_second": 4.838,
      "eval_steps_per_second": 2.419,
      "step": 5
    },
    {
      "epoch": 0.0002764722145424385,
      "grad_norm": 1.3728289604187012,
      "learning_rate": 0.00012,
      "loss": 5.2212,
      "step": 6
    },
    {
      "epoch": 0.0004147083218136577,
      "grad_norm": 0.9891195297241211,
      "learning_rate": 0.00018,
      "loss": 5.832,
      "step": 9
    },
    {
      "epoch": 0.00046078702423739745,
      "eval_loss": 1.348448395729065,
      "eval_runtime": 1889.9919,
      "eval_samples_per_second": 4.835,
      "eval_steps_per_second": 2.417,
      "step": 10
    },
    {
      "epoch": 0.000552944429084877,
      "grad_norm": 0.7286670804023743,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.7504,
      "step": 12
    },
    {
      "epoch": 0.0006911805363560963,
      "grad_norm": 0.8415332436561584,
      "learning_rate": 0.00017071067811865476,
      "loss": 5.1408,
      "step": 15
    },
    {
      "epoch": 0.0006911805363560963,
      "eval_loss": 1.2483679056167603,
      "eval_runtime": 1884.6621,
      "eval_samples_per_second": 4.849,
      "eval_steps_per_second": 2.424,
      "step": 15
    },
    {
      "epoch": 0.0008294166436273154,
      "grad_norm": 1.1995240449905396,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.1321,
      "step": 18
    },
    {
      "epoch": 0.0009215740484747949,
      "eval_loss": 1.2183318138122559,
      "eval_runtime": 1883.2865,
      "eval_samples_per_second": 4.852,
      "eval_steps_per_second": 2.426,
      "step": 20
    },
    {
      "epoch": 0.0009676527508985347,
      "grad_norm": 0.8395941853523254,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.7077,
      "step": 21
    },
    {
      "epoch": 0.001105888858169754,
      "grad_norm": 0.8471205234527588,
      "learning_rate": 4.12214747707527e-05,
      "loss": 4.414,
      "step": 24
    },
    {
      "epoch": 0.0011519675605934938,
      "eval_loss": 1.2079477310180664,
      "eval_runtime": 1882.5808,
      "eval_samples_per_second": 4.854,
      "eval_steps_per_second": 2.427,
      "step": 25
    },
    {
      "epoch": 0.0012441249654409731,
      "grad_norm": 0.9873213768005371,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 4.72,
      "step": 27
    },
    {
      "epoch": 0.0013823610727121925,
      "grad_norm": 0.850914716720581,
      "learning_rate": 0.0,
      "loss": 5.203,
      "step": 30
    },
    {
      "epoch": 0.0013823610727121925,
      "eval_loss": 1.2058666944503784,
      "eval_runtime": 1888.528,
      "eval_samples_per_second": 4.839,
      "eval_steps_per_second": 2.419,
      "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": 2.094783887572992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}