{
  "best_metric": 1.8255712985992432,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.2345679012345678,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.25252068042755127,
      "learning_rate": 1e-05,
      "loss": 2.0604,
      "step": 1
    },
    {
      "epoch": 0.024691358024691357,
      "eval_loss": 2.237061023712158,
      "eval_runtime": 1.21,
      "eval_samples_per_second": 57.023,
      "eval_steps_per_second": 14.876,
      "step": 1
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.31075847148895264,
      "learning_rate": 2e-05,
      "loss": 2.2158,
      "step": 2
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.38259977102279663,
      "learning_rate": 3e-05,
      "loss": 2.1454,
      "step": 3
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.35990017652511597,
      "learning_rate": 4e-05,
      "loss": 2.0522,
      "step": 4
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.4168837070465088,
      "learning_rate": 5e-05,
      "loss": 2.3263,
      "step": 5
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.469605028629303,
      "learning_rate": 6e-05,
      "loss": 2.2257,
      "step": 6
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 0.5073450207710266,
      "learning_rate": 7e-05,
      "loss": 2.3573,
      "step": 7
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.7278738021850586,
      "learning_rate": 8e-05,
      "loss": 2.4981,
      "step": 8
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.8480843305587769,
      "learning_rate": 9e-05,
      "loss": 2.4136,
      "step": 9
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.1377860307693481,
      "learning_rate": 0.0001,
      "loss": 2.6231,
      "step": 10
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 0.1992480605840683,
      "learning_rate": 9.998033131915266e-05,
      "loss": 2.125,
      "step": 11
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.21675321459770203,
      "learning_rate": 9.992134075089084e-05,
      "loss": 2.1632,
      "step": 12
    },
    {
      "epoch": 0.32098765432098764,
      "grad_norm": 0.2902778387069702,
      "learning_rate": 9.982307470588098e-05,
      "loss": 2.079,
      "step": 13
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.2948603630065918,
      "learning_rate": 9.968561049466214e-05,
      "loss": 2.031,
      "step": 14
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.347444623708725,
      "learning_rate": 9.950905626682228e-05,
      "loss": 2.0397,
      "step": 15
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.4035986363887787,
      "learning_rate": 9.92935509259118e-05,
      "loss": 2.1259,
      "step": 16
    },
    {
      "epoch": 0.41975308641975306,
      "grad_norm": 0.4339040517807007,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.1056,
      "step": 17
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5206056833267212,
      "learning_rate": 9.874639560909117e-05,
      "loss": 2.0121,
      "step": 18
    },
    {
      "epoch": 0.4691358024691358,
      "grad_norm": 0.719115674495697,
      "learning_rate": 9.841517610611309e-05,
      "loss": 2.1641,
      "step": 19
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.9554781317710876,
      "learning_rate": 9.804586609725499e-05,
      "loss": 2.112,
      "step": 20
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.2317459136247635,
      "learning_rate": 9.763875613614482e-05,
      "loss": 2.0239,
      "step": 21
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.3069552481174469,
      "learning_rate": 9.719416651541839e-05,
      "loss": 2.0365,
      "step": 22
    },
    {
      "epoch": 0.5679012345679012,
      "grad_norm": 0.34765249490737915,
      "learning_rate": 9.671244701472999e-05,
      "loss": 2.1446,
      "step": 23
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.37877699732780457,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0267,
      "step": 24
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 0.4079001843929291,
      "learning_rate": 9.563916325306594e-05,
      "loss": 2.0075,
      "step": 25
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.3358095586299896,
      "learning_rate": 9.504844339512095e-05,
      "loss": 1.8691,
      "step": 26
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.4075435400009155,
      "learning_rate": 9.442228179894362e-05,
      "loss": 2.0415,
      "step": 27
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.4543934762477875,
      "learning_rate": 9.376117109543769e-05,
      "loss": 1.9039,
      "step": 28
    },
    {
      "epoch": 0.7160493827160493,
      "grad_norm": 0.5283561944961548,
      "learning_rate": 9.306563141162046e-05,
      "loss": 1.8946,
      "step": 29
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.7076103687286377,
      "learning_rate": 9.233620996141421e-05,
      "loss": 1.5743,
      "step": 30
    },
    {
      "epoch": 0.7654320987654321,
      "grad_norm": 0.19869261980056763,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.9074,
      "step": 31
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.2551741302013397,
      "learning_rate": 9.077804344796302e-05,
      "loss": 1.9752,
      "step": 32
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.29231002926826477,
      "learning_rate": 8.995052426791247e-05,
      "loss": 2.0127,
      "step": 33
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.2705162465572357,
      "learning_rate": 8.90915741234015e-05,
      "loss": 1.8734,
      "step": 34
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 0.30582037568092346,
      "learning_rate": 8.820186879108038e-05,
      "loss": 1.7893,
      "step": 35
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.2692418694496155,
      "learning_rate": 8.728210824415827e-05,
      "loss": 1.897,
      "step": 36
    },
    {
      "epoch": 0.9135802469135802,
      "grad_norm": 0.3430037498474121,
      "learning_rate": 8.633301610170135e-05,
      "loss": 1.8172,
      "step": 37
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.3440125286579132,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9525,
      "step": 38
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.46276724338531494,
      "learning_rate": 8.434984630174509e-05,
      "loss": 1.8196,
      "step": 39
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.7176722288131714,
      "learning_rate": 8.33173288976002e-05,
      "loss": 1.837,
      "step": 40
    },
    {
      "epoch": 1.0123456790123457,
      "grad_norm": 0.38161012530326843,
      "learning_rate": 8.225859917710439e-05,
      "loss": 3.0373,
      "step": 41
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.16387499868869781,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.6453,
      "step": 42
    },
    {
      "epoch": 1.0617283950617284,
      "grad_norm": 0.24855704605579376,
      "learning_rate": 8.006585456492029e-05,
      "loss": 2.0729,
      "step": 43
    },
    {
      "epoch": 1.0864197530864197,
      "grad_norm": 0.2932082712650299,
      "learning_rate": 7.89335648089903e-05,
      "loss": 1.991,
      "step": 44
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2368183583021164,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6878,
      "step": 45
    },
    {
      "epoch": 1.1358024691358024,
      "grad_norm": 0.3216198682785034,
      "learning_rate": 7.660160382576683e-05,
      "loss": 2.1539,
      "step": 46
    },
    {
      "epoch": 1.1604938271604939,
      "grad_norm": 0.31032422184944153,
      "learning_rate": 7.540376726232648e-05,
      "loss": 1.784,
      "step": 47
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.3157343566417694,
      "learning_rate": 7.4185944355262e-05,
      "loss": 1.6648,
      "step": 48
    },
    {
      "epoch": 1.2098765432098766,
      "grad_norm": 0.4062681794166565,
      "learning_rate": 7.294909322337689e-05,
      "loss": 1.8114,
      "step": 49
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 0.5582627654075623,
      "learning_rate": 7.169418695587791e-05,
      "loss": 1.6857,
      "step": 50
    },
    {
      "epoch": 1.2345679012345678,
      "eval_loss": 1.8255712985992432,
      "eval_runtime": 1.2107,
      "eval_samples_per_second": 56.991,
      "eval_steps_per_second": 14.867,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 122,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3432293245255680.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}