{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04976362279173924,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009952724558347848,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0009952724558347848,
      "eval_loss": NaN,
      "eval_runtime": 16.966,
      "eval_samples_per_second": 24.932,
      "eval_steps_per_second": 12.496,
      "step": 1
    },
    {
      "epoch": 0.0019905449116695696,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.002985817367504354,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.003981089823339139,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.004976362279173924,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.005971634735008708,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.006966907190843493,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.007962179646678278,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.008957452102513063,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.009952724558347848,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.010947997014182632,
      "grad_norm": NaN,
      "learning_rate": 4.99229333433282e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.011943269470017417,
      "grad_norm": NaN,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.012938541925852202,
      "grad_norm": NaN,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.012938541925852202,
      "eval_loss": NaN,
      "eval_runtime": 15.2705,
      "eval_samples_per_second": 27.7,
      "eval_steps_per_second": 13.883,
      "step": 13
    },
    {
      "epoch": 0.013933814381686987,
      "grad_norm": NaN,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.014929086837521772,
      "grad_norm": NaN,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.015924359293356557,
      "grad_norm": NaN,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.016919631749191342,
      "grad_norm": NaN,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.017914904205026127,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.018910176660860912,
      "grad_norm": NaN,
      "learning_rate": 4.401014914000078e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.019905449116695697,
      "grad_norm": NaN,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.020900721572530482,
      "grad_norm": NaN,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.021895994028365263,
      "grad_norm": NaN,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.02289126648420005,
      "grad_norm": NaN,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.023886538940034834,
      "grad_norm": NaN,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.02488181139586962,
      "grad_norm": NaN,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.025877083851704404,
      "grad_norm": NaN,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.025877083851704404,
      "eval_loss": NaN,
      "eval_runtime": 15.2969,
      "eval_samples_per_second": 27.653,
      "eval_steps_per_second": 13.859,
      "step": 26
    },
    {
      "epoch": 0.02687235630753919,
      "grad_norm": NaN,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.027867628763373974,
      "grad_norm": NaN,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.02886290121920876,
      "grad_norm": NaN,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.029858173675043544,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03085344613087833,
      "grad_norm": NaN,
      "learning_rate": 2.303852260680388e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.031848718586713114,
      "grad_norm": NaN,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0328439910425479,
      "grad_norm": NaN,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.033839263498382684,
      "grad_norm": NaN,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.03483453595421747,
      "grad_norm": NaN,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.035829808410052254,
      "grad_norm": NaN,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.03682508086588704,
      "grad_norm": NaN,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.037820353321721824,
      "grad_norm": NaN,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.03881562577755661,
      "grad_norm": NaN,
      "learning_rate": 8.763798791745411e-06,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.03881562577755661,
      "eval_loss": NaN,
      "eval_runtime": 15.3128,
      "eval_samples_per_second": 27.624,
      "eval_steps_per_second": 13.845,
      "step": 39
    },
    {
      "epoch": 0.039810898233391394,
      "grad_norm": NaN,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.04080617068922618,
      "grad_norm": NaN,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.041801443145060964,
      "grad_norm": NaN,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.04279671560089574,
      "grad_norm": NaN,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.04379198805673053,
      "grad_norm": NaN,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.04478726051256531,
      "grad_norm": NaN,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0457825329684001,
      "grad_norm": NaN,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.04677780542423488,
      "grad_norm": NaN,
      "learning_rate": 6.907519900580861e-07,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.04777307788006967,
      "grad_norm": NaN,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.04876835033590445,
      "grad_norm": NaN,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.04976362279173924,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1051146382671872e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}