{
  "best_metric": 1.6801203489303589,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.006881838827334664,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013763677654669328,
      "grad_norm": 1.681911587715149,
      "learning_rate": 2e-05,
      "loss": 1.7218,
      "step": 1
    },
    {
      "epoch": 0.00013763677654669328,
      "eval_loss": 2.2520158290863037,
      "eval_runtime": 106.8393,
      "eval_samples_per_second": 114.536,
      "eval_steps_per_second": 14.321,
      "step": 1
    },
    {
      "epoch": 0.00027527355309338655,
      "grad_norm": 1.9964476823806763,
      "learning_rate": 4e-05,
      "loss": 1.878,
      "step": 2
    },
    {
      "epoch": 0.00041291032964007983,
      "grad_norm": 2.218065023422241,
      "learning_rate": 6e-05,
      "loss": 1.9068,
      "step": 3
    },
    {
      "epoch": 0.0005505471061867731,
      "grad_norm": 2.161393404006958,
      "learning_rate": 8e-05,
      "loss": 1.7922,
      "step": 4
    },
    {
      "epoch": 0.0006881838827334664,
      "grad_norm": 1.9325798749923706,
      "learning_rate": 0.0001,
      "loss": 1.7442,
      "step": 5
    },
    {
      "epoch": 0.0008258206592801597,
      "grad_norm": 3.0492777824401855,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.7041,
      "step": 6
    },
    {
      "epoch": 0.0009634574358268529,
      "grad_norm": 2.1566667556762695,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.7044,
      "step": 7
    },
    {
      "epoch": 0.0011010942123735462,
      "grad_norm": 2.4497389793395996,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7599,
      "step": 8
    },
    {
      "epoch": 0.0012387309889202395,
      "grad_norm": 2.009220600128174,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.6069,
      "step": 9
    },
    {
      "epoch": 0.0013763677654669328,
      "grad_norm": 1.8601412773132324,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.6321,
      "step": 10
    },
    {
      "epoch": 0.001514004542013626,
      "grad_norm": 2.1711673736572266,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6355,
      "step": 11
    },
    {
      "epoch": 0.0016516413185603193,
      "grad_norm": 1.869681715965271,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6564,
      "step": 12
    },
    {
      "epoch": 0.0017892780951070126,
      "grad_norm": 1.8459086418151855,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.6571,
      "step": 13
    },
    {
      "epoch": 0.0019269148716537059,
      "grad_norm": 1.9504926204681396,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5846,
      "step": 14
    },
    {
      "epoch": 0.002064551648200399,
      "grad_norm": 1.7249507904052734,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4764,
      "step": 15
    },
    {
      "epoch": 0.0022021884247470924,
      "grad_norm": 1.8206087350845337,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.7208,
      "step": 16
    },
    {
      "epoch": 0.0023398252012937857,
      "grad_norm": 1.8255046606063843,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.6589,
      "step": 17
    },
    {
      "epoch": 0.002477461977840479,
      "grad_norm": 1.8157140016555786,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5725,
      "step": 18
    },
    {
      "epoch": 0.0026150987543871723,
      "grad_norm": 1.8305015563964844,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.6672,
      "step": 19
    },
    {
      "epoch": 0.0027527355309338655,
      "grad_norm": 1.768606185913086,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6213,
      "step": 20
    },
    {
      "epoch": 0.002890372307480559,
      "grad_norm": 1.811745285987854,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.6071,
      "step": 21
    },
    {
      "epoch": 0.003028009084027252,
      "grad_norm": 1.7457269430160522,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.5049,
      "step": 22
    },
    {
      "epoch": 0.0031656458605739454,
      "grad_norm": 1.6813018321990967,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.55,
      "step": 23
    },
    {
      "epoch": 0.0033032826371206386,
      "grad_norm": 1.7682090997695923,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6086,
      "step": 24
    },
    {
      "epoch": 0.003440919413667332,
      "grad_norm": 1.8451300859451294,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5775,
      "step": 25
    },
    {
      "epoch": 0.003440919413667332,
      "eval_loss": 1.70032799243927,
      "eval_runtime": 106.8297,
      "eval_samples_per_second": 114.547,
      "eval_steps_per_second": 14.322,
      "step": 25
    },
    {
      "epoch": 0.003578556190214025,
      "grad_norm": 1.8355437517166138,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.579,
      "step": 26
    },
    {
      "epoch": 0.0037161929667607185,
      "grad_norm": 1.7906683683395386,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.4476,
      "step": 27
    },
    {
      "epoch": 0.0038538297433074117,
      "grad_norm": 1.82988703250885,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.5864,
      "step": 28
    },
    {
      "epoch": 0.003991466519854105,
      "grad_norm": 1.955890417098999,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.5891,
      "step": 29
    },
    {
      "epoch": 0.004129103296400798,
      "grad_norm": 2.021894931793213,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.8077,
      "step": 30
    },
    {
      "epoch": 0.0042667400729474916,
      "grad_norm": 2.075988531112671,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.7214,
      "step": 31
    },
    {
      "epoch": 0.004404376849494185,
      "grad_norm": 1.942689061164856,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7103,
      "step": 32
    },
    {
      "epoch": 0.004542013626040878,
      "grad_norm": 2.155029058456421,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.7459,
      "step": 33
    },
    {
      "epoch": 0.004679650402587571,
      "grad_norm": 1.9637714624404907,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.6637,
      "step": 34
    },
    {
      "epoch": 0.004817287179134265,
      "grad_norm": 1.9927000999450684,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6629,
      "step": 35
    },
    {
      "epoch": 0.004954923955680958,
      "grad_norm": 2.146827459335327,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.6425,
      "step": 36
    },
    {
      "epoch": 0.005092560732227651,
      "grad_norm": 2.037449836730957,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.8133,
      "step": 37
    },
    {
      "epoch": 0.0052301975087743445,
      "grad_norm": 2.0150561332702637,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.636,
      "step": 38
    },
    {
      "epoch": 0.005367834285321038,
      "grad_norm": 2.134779691696167,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.8358,
      "step": 39
    },
    {
      "epoch": 0.005505471061867731,
      "grad_norm": 2.3213002681732178,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.8923,
      "step": 40
    },
    {
      "epoch": 0.005643107838414424,
      "grad_norm": 2.3136813640594482,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6691,
      "step": 41
    },
    {
      "epoch": 0.005780744614961118,
      "grad_norm": 2.2391891479492188,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7149,
      "step": 42
    },
    {
      "epoch": 0.005918381391507811,
      "grad_norm": 2.2326366901397705,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.7424,
      "step": 43
    },
    {
      "epoch": 0.006056018168054504,
      "grad_norm": 2.3350918292999268,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.9315,
      "step": 44
    },
    {
      "epoch": 0.0061936549446011974,
      "grad_norm": 2.414999485015869,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.8257,
      "step": 45
    },
    {
      "epoch": 0.006331291721147891,
      "grad_norm": 2.6851768493652344,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.0204,
      "step": 46
    },
    {
      "epoch": 0.006468928497694584,
      "grad_norm": 3.064577579498291,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.0167,
      "step": 47
    },
    {
      "epoch": 0.006606565274241277,
      "grad_norm": 3.4269301891326904,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.2436,
      "step": 48
    },
    {
      "epoch": 0.0067442020507879705,
      "grad_norm": 3.9567739963531494,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.3654,
      "step": 49
    },
    {
      "epoch": 0.006881838827334664,
      "grad_norm": 7.154803276062012,
      "learning_rate": 0.0,
      "loss": 3.1455,
      "step": 50
    },
    {
      "epoch": 0.006881838827334664,
      "eval_loss": 1.6801203489303589,
      "eval_runtime": 106.7627,
      "eval_samples_per_second": 114.619,
      "eval_steps_per_second": 14.331,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1941781210988544.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}