{
  "best_metric": 1.6071616411209106,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.9607843137254903,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 0.24988579750061035,
      "learning_rate": 5e-05,
      "loss": 1.8407,
      "step": 1
    },
    {
      "epoch": 0.0392156862745098,
      "eval_loss": 1.9764854907989502,
      "eval_runtime": 4.5291,
      "eval_samples_per_second": 37.976,
      "eval_steps_per_second": 4.857,
      "step": 1
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.25837182998657227,
      "learning_rate": 0.0001,
      "loss": 1.883,
      "step": 2
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.2485896646976471,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.8896,
      "step": 3
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 0.25695013999938965,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.9502,
      "step": 4
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 0.2187684327363968,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.9433,
      "step": 5
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.21632742881774902,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9729,
      "step": 6
    },
    {
      "epoch": 0.27450980392156865,
      "grad_norm": 0.16930197179317474,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.6653,
      "step": 7
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 0.22359579801559448,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7018,
      "step": 8
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.2660350203514099,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7458,
      "step": 9
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.2784881293773651,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7523,
      "step": 10
    },
    {
      "epoch": 0.43137254901960786,
      "grad_norm": 0.23793818056583405,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8239,
      "step": 11
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.22583788633346558,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9176,
      "step": 12
    },
    {
      "epoch": 0.5098039215686274,
      "grad_norm": 0.14187447726726532,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.6413,
      "step": 13
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 0.1522621512413025,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6188,
      "step": 14
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.16769146919250488,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.6939,
      "step": 15
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 0.18174070119857788,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6399,
      "step": 16
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.19126224517822266,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.7498,
      "step": 17
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.19128768146038055,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7815,
      "step": 18
    },
    {
      "epoch": 0.7450980392156863,
      "grad_norm": 0.17445573210716248,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.6568,
      "step": 19
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.16562898457050323,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5288,
      "step": 20
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.16586856544017792,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6014,
      "step": 21
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.16047951579093933,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6202,
      "step": 22
    },
    {
      "epoch": 0.9019607843137255,
      "grad_norm": 0.17289896309375763,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.7032,
      "step": 23
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.19855345785617828,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.771,
      "step": 24
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 0.25787705183029175,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7947,
      "step": 25
    },
    {
      "epoch": 0.9803921568627451,
      "eval_loss": 1.648253321647644,
      "eval_runtime": 4.5219,
      "eval_samples_per_second": 38.037,
      "eval_steps_per_second": 4.865,
      "step": 25
    },
    {
      "epoch": 1.0196078431372548,
      "grad_norm": 0.2848551869392395,
      "learning_rate": 5e-05,
      "loss": 2.3663,
      "step": 26
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.15716268122196198,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.4474,
      "step": 27
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 0.1628309041261673,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.5175,
      "step": 28
    },
    {
      "epoch": 1.1372549019607843,
      "grad_norm": 0.1741650551557541,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.5354,
      "step": 29
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.17867332696914673,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.6915,
      "step": 30
    },
    {
      "epoch": 1.215686274509804,
      "grad_norm": 0.22520938515663147,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.7774,
      "step": 31
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 0.16765983402729034,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4057,
      "step": 32
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.16934159398078918,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.6124,
      "step": 33
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.1716342717409134,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5156,
      "step": 34
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 0.1707359254360199,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.5827,
      "step": 35
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.19614113867282867,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.6265,
      "step": 36
    },
    {
      "epoch": 1.4509803921568627,
      "grad_norm": 0.2117149829864502,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.7197,
      "step": 37
    },
    {
      "epoch": 1.4901960784313726,
      "grad_norm": 0.15891553461551666,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.0998,
      "step": 38
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.20347225666046143,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.017,
      "step": 39
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.16208526492118835,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.5114,
      "step": 40
    },
    {
      "epoch": 1.607843137254902,
      "grad_norm": 0.1645675152540207,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.5453,
      "step": 41
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.17670050263404846,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.6267,
      "step": 42
    },
    {
      "epoch": 1.6862745098039216,
      "grad_norm": 0.19448737800121307,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.6249,
      "step": 43
    },
    {
      "epoch": 1.7254901960784315,
      "grad_norm": 0.19081003963947296,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.339,
      "step": 44
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.20244494080543518,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.7738,
      "step": 45
    },
    {
      "epoch": 1.803921568627451,
      "grad_norm": 0.1626470386981964,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.4865,
      "step": 46
    },
    {
      "epoch": 1.843137254901961,
      "grad_norm": 0.1605791300535202,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.5688,
      "step": 47
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.17136767506599426,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.5956,
      "step": 48
    },
    {
      "epoch": 1.9215686274509802,
      "grad_norm": 0.1877204030752182,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.6583,
      "step": 49
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 0.251743882894516,
      "learning_rate": 0.0,
      "loss": 1.8541,
      "step": 50
    },
    {
      "epoch": 1.9607843137254903,
      "eval_loss": 1.6071616411209106,
      "eval_runtime": 4.5217,
      "eval_samples_per_second": 38.038,
      "eval_steps_per_second": 4.865,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "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": 5.639875509480325e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}