{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 2000,
  "global_step": 21994,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_HasAns_exact": 0.06747638326585695,
      "eval_HasAns_f1": 7.18502154989456,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 0.0336417157275021,
      "eval_NoAns_f1": 0.0336417157275021,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 50.07159100480081,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 50.075846569172874,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 0.050534826918217805,
      "eval_f1": 3.6042118881306284,
      "eval_runtime": -14.2699,
      "eval_samples_per_second": -852.912,
      "eval_steps_per_second": -13.385,
      "eval_total": 11873,
      "step": 0
    },
    {
      "epoch": 0.18186778212239701,
      "grad_norm": 40.6475715637207,
      "learning_rate": 2.7271983268164044e-05,
      "loss": 1.4132,
      "step": 2000
    },
    {
      "epoch": 0.18186778212239701,
      "eval_HasAns_exact": 67.25708502024291,
      "eval_HasAns_f1": 74.98296116605809,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 70.81581160639193,
      "eval_NoAns_f1": 70.81581160639193,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 69.03899604143855,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 72.89640308198375,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 69.03899604143855,
      "eval_f1": 72.89640308198369,
      "eval_runtime": 136.0827,
      "eval_samples_per_second": 89.438,
      "eval_steps_per_second": 1.404,
      "eval_total": 11873,
      "step": 2000
    },
    {
      "epoch": 0.36373556424479403,
      "grad_norm": 41.061927795410156,
      "learning_rate": 2.4543966536328087e-05,
      "loss": 1.2638,
      "step": 4000
    },
    {
      "epoch": 0.36373556424479403,
      "eval_HasAns_exact": 73.59986504723346,
      "eval_HasAns_f1": 81.00757791997825,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 65.78637510513036,
      "eval_NoAns_f1": 65.78637510513036,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 69.68752632022235,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 73.38607950051664,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 69.68752632022235,
      "eval_f1": 73.38607950051639,
      "eval_runtime": 136.2286,
      "eval_samples_per_second": 89.342,
      "eval_steps_per_second": 1.402,
      "eval_total": 11873,
      "step": 4000
    },
    {
      "epoch": 0.5456033463671911,
      "grad_norm": 52.56464767456055,
      "learning_rate": 2.1815949804492137e-05,
      "loss": 1.3977,
      "step": 6000
    },
    {
      "epoch": 0.5456033463671911,
      "eval_HasAns_exact": 71.94669365721997,
      "eval_HasAns_f1": 79.2064004599959,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 72.17830109335576,
      "eval_NoAns_f1": 72.17830109335576,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 72.07108565653162,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 75.69574176087386,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 72.0626631853786,
      "eval_f1": 75.68731928972085,
      "eval_runtime": 136.1854,
      "eval_samples_per_second": 89.371,
      "eval_steps_per_second": 1.403,
      "eval_total": 11873,
      "step": 6000
    },
    {
      "epoch": 0.7274711284895881,
      "grad_norm": 49.72623825073242,
      "learning_rate": 1.908793307265618e-05,
      "loss": 1.3384,
      "step": 8000
    },
    {
      "epoch": 0.7274711284895881,
      "eval_HasAns_exact": 72.0310391363023,
      "eval_HasAns_f1": 78.95689148837117,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 75.00420521446594,
      "eval_NoAns_f1": 75.00420521446594,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 73.51975069485387,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 76.9777185835984,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 73.51975069485387,
      "eval_f1": 76.97771858359845,
      "eval_runtime": 135.7796,
      "eval_samples_per_second": 89.638,
      "eval_steps_per_second": 1.407,
      "eval_total": 11873,
      "step": 8000
    },
    {
      "epoch": 0.9093389106119851,
      "grad_norm": 39.458927154541016,
      "learning_rate": 1.6359916340820223e-05,
      "loss": 1.2258,
      "step": 10000
    },
    {
      "epoch": 0.9093389106119851,
      "eval_HasAns_exact": 73.54925775978407,
      "eval_HasAns_f1": 80.29283351227244,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 76.23212783851976,
      "eval_NoAns_f1": 76.23212783851976,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 74.88419102164575,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 78.25115110424915,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 74.89261349279879,
      "eval_f1": 78.25957357540227,
      "eval_runtime": 136.1576,
      "eval_samples_per_second": 89.389,
      "eval_steps_per_second": 1.403,
      "eval_total": 11873,
      "step": 10000
    },
    {
      "epoch": 1.0912066927343822,
      "grad_norm": 41.23106002807617,
      "learning_rate": 1.363189960898427e-05,
      "loss": 0.7822,
      "step": 12000
    },
    {
      "epoch": 1.0912066927343822,
      "eval_HasAns_exact": 77.26045883940621,
      "eval_HasAns_f1": 84.1124672080756,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 69.97476871320437,
      "eval_NoAns_f1": 69.97476871320437,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 73.6208203486903,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 77.04191911138483,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 73.61239787753728,
      "eval_f1": 77.0334966402318,
      "eval_runtime": 135.9367,
      "eval_samples_per_second": 89.534,
      "eval_steps_per_second": 1.405,
      "eval_total": 11873,
      "step": 12000
    },
    {
      "epoch": 1.273074474856779,
      "grad_norm": 21.682905197143555,
      "learning_rate": 1.0903882877148312e-05,
      "loss": 0.6771,
      "step": 14000
    },
    {
      "epoch": 1.273074474856779,
      "eval_HasAns_exact": 73.78542510121457,
      "eval_HasAns_f1": 80.35769680092089,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 80.7569386038688,
      "eval_NoAns_f1": 80.7569386038688,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 77.27617282910806,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 80.55760352361308,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.27617282910806,
      "eval_f1": 80.55760352361317,
      "eval_runtime": 136.5688,
      "eval_samples_per_second": 89.12,
      "eval_steps_per_second": 1.399,
      "eval_total": 11873,
      "step": 14000
    },
    {
      "epoch": 1.4549422569791761,
      "grad_norm": 56.2855339050293,
      "learning_rate": 8.175866145312359e-06,
      "loss": 0.6521,
      "step": 16000
    },
    {
      "epoch": 1.4549422569791761,
      "eval_HasAns_exact": 71.82860998650472,
      "eval_HasAns_f1": 77.91336965584932,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 85.18082422203533,
      "eval_NoAns_f1": 85.18082422203533,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 78.52269855975743,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.56072225384261,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 78.51427608860439,
      "eval_f1": 81.55229978268969,
      "eval_runtime": 136.3366,
      "eval_samples_per_second": 89.272,
      "eval_steps_per_second": 1.401,
      "eval_total": 11873,
      "step": 16000
    },
    {
      "epoch": 1.6368100391015732,
      "grad_norm": 24.467727661132812,
      "learning_rate": 5.447849413476403e-06,
      "loss": 0.6455,
      "step": 18000
    },
    {
      "epoch": 1.6368100391015732,
      "eval_HasAns_exact": 75.57354925775978,
      "eval_HasAns_f1": 82.12994203860852,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 79.0412111017662,
      "eval_NoAns_f1": 79.0412111017662,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 77.31828518487325,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 80.59178778782702,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.30986271372021,
      "eval_f1": 80.58336531667406,
      "eval_runtime": 136.1893,
      "eval_samples_per_second": 89.368,
      "eval_steps_per_second": 1.402,
      "eval_total": 11873,
      "step": 18000
    },
    {
      "epoch": 1.8186778212239703,
      "grad_norm": 36.233985900878906,
      "learning_rate": 2.7198326816404476e-06,
      "loss": 0.6175,
      "step": 20000
    },
    {
      "epoch": 1.8186778212239703,
      "eval_HasAns_exact": 74.19028340080972,
      "eval_HasAns_f1": 80.57880057678263,
      "eval_HasAns_total": 5928,
      "eval_NoAns_exact": 83.46509671993272,
      "eval_NoAns_f1": 83.46509671993272,
      "eval_NoAns_total": 5945,
      "eval_best_exact": 78.83432999241978,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.02401497676792,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 78.83432999241978,
      "eval_f1": 82.02401497676809,
      "eval_runtime": 136.3043,
      "eval_samples_per_second": 89.293,
      "eval_steps_per_second": 1.401,
      "eval_total": 11873,
      "step": 20000
    },
    {
      "epoch": 2.0,
      "step": 21994,
      "total_flos": 4371201741330432.0,
      "train_loss": 0.9652459149015072,
      "train_runtime": 5408.776,
      "train_samples_per_second": 48.794,
      "train_steps_per_second": 4.066
    }
  ],
  "logging_steps": 2000,
  "max_steps": 21994,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4371201741330432.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}