{
  "best_metric": 6.001819610595703,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0654205607476634,
  "eval_steps": 25,
  "global_step": 41,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 2.4745001792907715,
      "learning_rate": 5e-05,
      "loss": 7.2318,
      "step": 1
    },
    {
      "epoch": 0.07476635514018691,
      "eval_loss": 7.067153453826904,
      "eval_runtime": 1.6261,
      "eval_samples_per_second": 55.346,
      "eval_steps_per_second": 7.379,
      "step": 1
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 2.630521774291992,
      "learning_rate": 0.0001,
      "loss": 7.2158,
      "step": 2
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 2.3736913204193115,
      "learning_rate": 9.983786540671051e-05,
      "loss": 7.2184,
      "step": 3
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 1.5834097862243652,
      "learning_rate": 9.935251313189564e-05,
      "loss": 7.067,
      "step": 4
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 1.0912190675735474,
      "learning_rate": 9.85470908713026e-05,
      "loss": 7.0553,
      "step": 5
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 1.0540122985839844,
      "learning_rate": 9.742682209735727e-05,
      "loss": 6.8939,
      "step": 6
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 0.9415560364723206,
      "learning_rate": 9.599897218294122e-05,
      "loss": 6.6911,
      "step": 7
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 0.900778591632843,
      "learning_rate": 9.42728012826605e-05,
      "loss": 6.8455,
      "step": 8
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 0.9453460574150085,
      "learning_rate": 9.225950427718975e-05,
      "loss": 6.8096,
      "step": 9
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.8959687948226929,
      "learning_rate": 8.997213817017507e-05,
      "loss": 6.8073,
      "step": 10
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 0.8399636745452881,
      "learning_rate": 8.742553740855506e-05,
      "loss": 6.7164,
      "step": 11
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.9570170044898987,
      "learning_rate": 8.463621767547998e-05,
      "loss": 6.6769,
      "step": 12
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": 1.0214438438415527,
      "learning_rate": 8.162226877976887e-05,
      "loss": 6.5346,
      "step": 13
    },
    {
      "epoch": 1.0467289719626167,
      "grad_norm": 1.5697999000549316,
      "learning_rate": 7.840323733655778e-05,
      "loss": 10.4881,
      "step": 14
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 1.2612519264221191,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.0914,
      "step": 15
    },
    {
      "epoch": 1.1962616822429906,
      "grad_norm": 1.2088847160339355,
      "learning_rate": 7.143462807015271e-05,
      "loss": 6.6426,
      "step": 16
    },
    {
      "epoch": 1.2710280373831775,
      "grad_norm": 0.7120554447174072,
      "learning_rate": 6.773024435212678e-05,
      "loss": 4.6183,
      "step": 17
    },
    {
      "epoch": 1.3457943925233644,
      "grad_norm": 1.0831141471862793,
      "learning_rate": 6.391087319582264e-05,
      "loss": 7.882,
      "step": 18
    },
    {
      "epoch": 1.4205607476635513,
      "grad_norm": 1.1047991514205933,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 6.4772,
      "step": 19
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 0.9030379056930542,
      "learning_rate": 5.602683401276615e-05,
      "loss": 4.2253,
      "step": 20
    },
    {
      "epoch": 1.5700934579439252,
      "grad_norm": 0.999780535697937,
      "learning_rate": 5.201329700547076e-05,
      "loss": 7.8832,
      "step": 21
    },
    {
      "epoch": 1.644859813084112,
      "grad_norm": 0.9681606292724609,
      "learning_rate": 4.798670299452926e-05,
      "loss": 6.4247,
      "step": 22
    },
    {
      "epoch": 1.719626168224299,
      "grad_norm": 0.74932861328125,
      "learning_rate": 4.397316598723385e-05,
      "loss": 4.33,
      "step": 23
    },
    {
      "epoch": 1.794392523364486,
      "grad_norm": 1.0142208337783813,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 7.3124,
      "step": 24
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 1.1012533903121948,
      "learning_rate": 3.608912680417737e-05,
      "loss": 6.6556,
      "step": 25
    },
    {
      "epoch": 1.8691588785046729,
      "eval_loss": 6.001819610595703,
      "eval_runtime": 1.627,
      "eval_samples_per_second": 55.318,
      "eval_steps_per_second": 7.376,
      "step": 25
    },
    {
      "epoch": 1.9439252336448598,
      "grad_norm": 1.1970505714416504,
      "learning_rate": 3.226975564787322e-05,
      "loss": 6.4239,
      "step": 26
    },
    {
      "epoch": 2.0186915887850465,
      "grad_norm": 1.1707515716552734,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 8.9556,
      "step": 27
    },
    {
      "epoch": 2.0934579439252334,
      "grad_norm": 0.7799269556999207,
      "learning_rate": 2.500000000000001e-05,
      "loss": 6.6629,
      "step": 28
    },
    {
      "epoch": 2.1682242990654204,
      "grad_norm": 0.8445941209793091,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 5.9799,
      "step": 29
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 0.649803102016449,
      "learning_rate": 1.837773122023114e-05,
      "loss": 4.6584,
      "step": 30
    },
    {
      "epoch": 2.317757009345794,
      "grad_norm": 0.8148556351661682,
      "learning_rate": 1.536378232452003e-05,
      "loss": 7.5261,
      "step": 31
    },
    {
      "epoch": 2.392523364485981,
      "grad_norm": 0.844731867313385,
      "learning_rate": 1.257446259144494e-05,
      "loss": 5.9557,
      "step": 32
    },
    {
      "epoch": 2.467289719626168,
      "grad_norm": 0.6243622899055481,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 4.8558,
      "step": 33
    },
    {
      "epoch": 2.542056074766355,
      "grad_norm": 0.8896576762199402,
      "learning_rate": 7.740495722810271e-06,
      "loss": 7.3544,
      "step": 34
    },
    {
      "epoch": 2.616822429906542,
      "grad_norm": 0.7065213918685913,
      "learning_rate": 5.727198717339511e-06,
      "loss": 5.966,
      "step": 35
    },
    {
      "epoch": 2.691588785046729,
      "grad_norm": 0.7317398190498352,
      "learning_rate": 4.001027817058789e-06,
      "loss": 5.3642,
      "step": 36
    },
    {
      "epoch": 2.7663551401869158,
      "grad_norm": 0.757183849811554,
      "learning_rate": 2.573177902642726e-06,
      "loss": 6.2839,
      "step": 37
    },
    {
      "epoch": 2.8411214953271027,
      "grad_norm": 0.7204071879386902,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 6.29,
      "step": 38
    },
    {
      "epoch": 2.9158878504672896,
      "grad_norm": 1.0202537775039673,
      "learning_rate": 6.474868681043578e-07,
      "loss": 6.5971,
      "step": 39
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 1.3982231616973877,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 8.418,
      "step": 40
    },
    {
      "epoch": 3.0654205607476634,
      "grad_norm": 0.9841596484184265,
      "learning_rate": 0.0,
      "loss": 6.5826,
      "step": 41
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 9.264320894468096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}