{
  "best_metric": 1.5005075931549072,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.002169197396963,
  "eval_steps": 50,
  "global_step": 231,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004338394793926247,
      "eval_loss": 2.287693500518799,
      "eval_runtime": 2.3715,
      "eval_samples_per_second": 41.323,
      "eval_steps_per_second": 10.542,
      "step": 1
    },
    {
      "epoch": 0.04338394793926247,
      "grad_norm": 0.5313376784324646,
      "learning_rate": 4.12e-05,
      "loss": 1.8587,
      "step": 10
    },
    {
      "epoch": 0.08676789587852494,
      "grad_norm": 0.5186929702758789,
      "learning_rate": 8.24e-05,
      "loss": 2.0639,
      "step": 20
    },
    {
      "epoch": 0.1301518438177874,
      "grad_norm": 0.7352866530418396,
      "learning_rate": 0.0001236,
      "loss": 2.0921,
      "step": 30
    },
    {
      "epoch": 0.1735357917570499,
      "grad_norm": 0.8231748342514038,
      "learning_rate": 0.0001648,
      "loss": 1.8906,
      "step": 40
    },
    {
      "epoch": 0.21691973969631237,
      "grad_norm": 1.9571149349212646,
      "learning_rate": 0.000206,
      "loss": 1.9955,
      "step": 50
    },
    {
      "epoch": 0.21691973969631237,
      "eval_loss": 1.9748687744140625,
      "eval_runtime": 2.3417,
      "eval_samples_per_second": 41.85,
      "eval_steps_per_second": 10.676,
      "step": 50
    },
    {
      "epoch": 0.2603036876355748,
      "grad_norm": 0.42307645082473755,
      "learning_rate": 0.00020445239810895846,
      "loss": 1.7835,
      "step": 60
    },
    {
      "epoch": 0.3036876355748373,
      "grad_norm": 0.465277761220932,
      "learning_rate": 0.00019985609868074957,
      "loss": 1.7309,
      "step": 70
    },
    {
      "epoch": 0.3470715835140998,
      "grad_norm": 0.6410661935806274,
      "learning_rate": 0.0001923492229131769,
      "loss": 1.6651,
      "step": 80
    },
    {
      "epoch": 0.39045553145336226,
      "grad_norm": 0.6676890850067139,
      "learning_rate": 0.0001821573563428174,
      "loss": 1.7176,
      "step": 90
    },
    {
      "epoch": 0.43383947939262474,
      "grad_norm": 2.6857898235321045,
      "learning_rate": 0.00016958676988185618,
      "loss": 1.8401,
      "step": 100
    },
    {
      "epoch": 0.43383947939262474,
      "eval_loss": 1.6733328104019165,
      "eval_runtime": 2.3671,
      "eval_samples_per_second": 41.402,
      "eval_steps_per_second": 10.562,
      "step": 100
    },
    {
      "epoch": 0.4772234273318872,
      "grad_norm": 0.4030924141407013,
      "learning_rate": 0.00015501521621725395,
      "loss": 1.5976,
      "step": 110
    },
    {
      "epoch": 0.5206073752711496,
      "grad_norm": 0.4995245337486267,
      "learning_rate": 0.00013888057814525847,
      "loss": 1.5292,
      "step": 120
    },
    {
      "epoch": 0.5639913232104121,
      "grad_norm": 0.6390402913093567,
      "learning_rate": 0.00012166770996473358,
      "loss": 1.5418,
      "step": 130
    },
    {
      "epoch": 0.6073752711496746,
      "grad_norm": 0.6645438075065613,
      "learning_rate": 0.0001038938673523089,
      "loss": 1.6084,
      "step": 140
    },
    {
      "epoch": 0.6507592190889371,
      "grad_norm": 2.0902185440063477,
      "learning_rate": 8.609316355920905e-05,
      "loss": 1.7155,
      "step": 150
    },
    {
      "epoch": 0.6507592190889371,
      "eval_loss": 1.5498733520507812,
      "eval_runtime": 2.3415,
      "eval_samples_per_second": 41.853,
      "eval_steps_per_second": 10.677,
      "step": 150
    },
    {
      "epoch": 0.6941431670281996,
      "grad_norm": 0.42309829592704773,
      "learning_rate": 6.880051902916351e-05,
      "loss": 1.5078,
      "step": 160
    },
    {
      "epoch": 0.737527114967462,
      "grad_norm": 0.4995267391204834,
      "learning_rate": 5.25355867597608e-05,
      "loss": 1.4928,
      "step": 170
    },
    {
      "epoch": 0.7809110629067245,
      "grad_norm": 0.5781512260437012,
      "learning_rate": 3.778713645853078e-05,
      "loss": 1.4352,
      "step": 180
    },
    {
      "epoch": 0.824295010845987,
      "grad_norm": 0.728786289691925,
      "learning_rate": 2.4998366758019425e-05,
      "loss": 1.4567,
      "step": 190
    },
    {
      "epoch": 0.8676789587852495,
      "grad_norm": 2.4118869304656982,
      "learning_rate": 1.4553586865461783e-05,
      "loss": 1.8346,
      "step": 200
    },
    {
      "epoch": 0.8676789587852495,
      "eval_loss": 1.5005075931549072,
      "eval_runtime": 2.4042,
      "eval_samples_per_second": 40.762,
      "eval_steps_per_second": 10.398,
      "step": 200
    },
    {
      "epoch": 0.911062906724512,
      "grad_norm": 0.4956224858760834,
      "learning_rate": 6.7666678704352e-06,
      "loss": 1.4672,
      "step": 210
    },
    {
      "epoch": 0.9544468546637744,
      "grad_norm": 0.6833217144012451,
      "learning_rate": 1.8716107547278716e-06,
      "loss": 1.419,
      "step": 220
    },
    {
      "epoch": 0.9978308026030369,
      "grad_norm": 1.7939646244049072,
      "learning_rate": 1.5514540650944263e-08,
      "loss": 1.592,
      "step": 230
    }
  ],
  "logging_steps": 10,
  "max_steps": 231,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 2171209892167680.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}