{
  "best_metric": 3.0565457344055176,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0019681810726586845,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.560603575528948e-05,
      "eval_loss": 3.727018356323242,
      "eval_runtime": 342.8939,
      "eval_samples_per_second": 37.434,
      "eval_steps_per_second": 9.359,
      "step": 1
    },
    {
      "epoch": 0.00019681810726586847,
      "grad_norm": 5.474586486816406,
      "learning_rate": 0.00012,
      "loss": 13.4442,
      "step": 3
    },
    {
      "epoch": 0.0003280301787764474,
      "eval_loss": 3.4391748905181885,
      "eval_runtime": 342.7425,
      "eval_samples_per_second": 37.451,
      "eval_steps_per_second": 9.363,
      "step": 5
    },
    {
      "epoch": 0.00039363621453173694,
      "grad_norm": 3.978472948074341,
      "learning_rate": 0.0001992114701314478,
      "loss": 13.4982,
      "step": 6
    },
    {
      "epoch": 0.0005904543217976054,
      "grad_norm": 3.9486730098724365,
      "learning_rate": 0.00018763066800438636,
      "loss": 12.3538,
      "step": 9
    },
    {
      "epoch": 0.0006560603575528948,
      "eval_loss": 3.194514513015747,
      "eval_runtime": 343.3566,
      "eval_samples_per_second": 37.384,
      "eval_steps_per_second": 9.346,
      "step": 10
    },
    {
      "epoch": 0.0007872724290634739,
      "grad_norm": 3.388705015182495,
      "learning_rate": 0.000163742398974869,
      "loss": 12.6488,
      "step": 12
    },
    {
      "epoch": 0.0009840905363293422,
      "grad_norm": 2.9014482498168945,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.8357,
      "step": 15
    },
    {
      "epoch": 0.0009840905363293422,
      "eval_loss": 3.1070027351379395,
      "eval_runtime": 344.2293,
      "eval_samples_per_second": 37.289,
      "eval_steps_per_second": 9.322,
      "step": 15
    },
    {
      "epoch": 0.0011809086435952108,
      "grad_norm": 3.955669403076172,
      "learning_rate": 9.372094804706867e-05,
      "loss": 11.9725,
      "step": 18
    },
    {
      "epoch": 0.0013121207151057896,
      "eval_loss": 3.072327136993408,
      "eval_runtime": 344.4953,
      "eval_samples_per_second": 37.26,
      "eval_steps_per_second": 9.315,
      "step": 20
    },
    {
      "epoch": 0.0013777267508610792,
      "grad_norm": 3.1787612438201904,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 11.7956,
      "step": 21
    },
    {
      "epoch": 0.0015745448581269477,
      "grad_norm": 3.7789864540100098,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 12.3078,
      "step": 24
    },
    {
      "epoch": 0.0016401508938822373,
      "eval_loss": 3.060260772705078,
      "eval_runtime": 344.9139,
      "eval_samples_per_second": 37.215,
      "eval_steps_per_second": 9.304,
      "step": 25
    },
    {
      "epoch": 0.001771362965392816,
      "grad_norm": 3.8284847736358643,
      "learning_rate": 7.022351411174866e-06,
      "loss": 12.1145,
      "step": 27
    },
    {
      "epoch": 0.0019681810726586845,
      "grad_norm": 3.6236913204193115,
      "learning_rate": 0.0,
      "loss": 12.0133,
      "step": 30
    },
    {
      "epoch": 0.0019681810726586845,
      "eval_loss": 3.0565457344055176,
      "eval_runtime": 344.3515,
      "eval_samples_per_second": 37.276,
      "eval_steps_per_second": 9.319,
      "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": 7931868280258560.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}