{
  "best_metric": 0.9086689949035645,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.007217610970768676,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036088054853843375,
      "grad_norm": 3.6869497299194336,
      "learning_rate": 2e-05,
      "loss": 8.6382,
      "step": 1
    },
    {
      "epoch": 0.00036088054853843375,
      "eval_loss": 2.059074878692627,
      "eval_runtime": 280.1233,
      "eval_samples_per_second": 4.166,
      "eval_steps_per_second": 2.085,
      "step": 1
    },
    {
      "epoch": 0.0007217610970768675,
      "grad_norm": 3.044846296310425,
      "learning_rate": 4e-05,
      "loss": 7.5329,
      "step": 2
    },
    {
      "epoch": 0.0010826416456153013,
      "grad_norm": 3.2137176990509033,
      "learning_rate": 6e-05,
      "loss": 7.9115,
      "step": 3
    },
    {
      "epoch": 0.001443522194153735,
      "grad_norm": 3.5442140102386475,
      "learning_rate": 8e-05,
      "loss": 7.7322,
      "step": 4
    },
    {
      "epoch": 0.001804402742692169,
      "grad_norm": 3.074554920196533,
      "learning_rate": 0.0001,
      "loss": 7.2018,
      "step": 5
    },
    {
      "epoch": 0.001804402742692169,
      "eval_loss": 1.8853472471237183,
      "eval_runtime": 279.6366,
      "eval_samples_per_second": 4.173,
      "eval_steps_per_second": 2.088,
      "step": 5
    },
    {
      "epoch": 0.0021652832912306026,
      "grad_norm": 3.8418097496032715,
      "learning_rate": 0.00012,
      "loss": 7.5068,
      "step": 6
    },
    {
      "epoch": 0.0025261638397690365,
      "grad_norm": 4.259398460388184,
      "learning_rate": 0.00014,
      "loss": 7.5668,
      "step": 7
    },
    {
      "epoch": 0.00288704438830747,
      "grad_norm": 4.92379093170166,
      "learning_rate": 0.00016,
      "loss": 7.3567,
      "step": 8
    },
    {
      "epoch": 0.003247924936845904,
      "grad_norm": 3.6357803344726562,
      "learning_rate": 0.00018,
      "loss": 6.1502,
      "step": 9
    },
    {
      "epoch": 0.003608805485384338,
      "grad_norm": 4.020624160766602,
      "learning_rate": 0.0002,
      "loss": 5.6372,
      "step": 10
    },
    {
      "epoch": 0.003608805485384338,
      "eval_loss": 1.330490231513977,
      "eval_runtime": 278.9813,
      "eval_samples_per_second": 4.183,
      "eval_steps_per_second": 2.093,
      "step": 10
    },
    {
      "epoch": 0.003969686033922772,
      "grad_norm": 4.434789180755615,
      "learning_rate": 0.00019781476007338058,
      "loss": 4.8738,
      "step": 11
    },
    {
      "epoch": 0.004330566582461205,
      "grad_norm": 8.491475105285645,
      "learning_rate": 0.0001913545457642601,
      "loss": 5.4193,
      "step": 12
    },
    {
      "epoch": 0.004691447130999639,
      "grad_norm": 4.193347930908203,
      "learning_rate": 0.00018090169943749476,
      "loss": 4.4848,
      "step": 13
    },
    {
      "epoch": 0.005052327679538073,
      "grad_norm": 4.052431583404541,
      "learning_rate": 0.00016691306063588583,
      "loss": 4.5256,
      "step": 14
    },
    {
      "epoch": 0.0054132082280765065,
      "grad_norm": 4.638420581817627,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.3011,
      "step": 15
    },
    {
      "epoch": 0.0054132082280765065,
      "eval_loss": 1.0189849138259888,
      "eval_runtime": 277.1724,
      "eval_samples_per_second": 4.21,
      "eval_steps_per_second": 2.107,
      "step": 15
    },
    {
      "epoch": 0.00577408877661494,
      "grad_norm": 3.6194562911987305,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.9049,
      "step": 16
    },
    {
      "epoch": 0.006134969325153374,
      "grad_norm": 4.051806449890137,
      "learning_rate": 0.00011045284632676536,
      "loss": 4.0198,
      "step": 17
    },
    {
      "epoch": 0.006495849873691808,
      "grad_norm": 4.909851551055908,
      "learning_rate": 8.954715367323468e-05,
      "loss": 3.7369,
      "step": 18
    },
    {
      "epoch": 0.006856730422230242,
      "grad_norm": 4.357086181640625,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.7799,
      "step": 19
    },
    {
      "epoch": 0.007217610970768676,
      "grad_norm": 4.044589042663574,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.7341,
      "step": 20
    },
    {
      "epoch": 0.007217610970768676,
      "eval_loss": 0.9086689949035645,
      "eval_runtime": 278.662,
      "eval_samples_per_second": 4.188,
      "eval_steps_per_second": 2.096,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 1.14112214335488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}