{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06615776081424936,
  "eval_steps": 13,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002544529262086514,
      "grad_norm": 3.013115882873535,
      "learning_rate": 5e-06,
      "loss": 1.1819,
      "step": 1
    },
    {
      "epoch": 0.002544529262086514,
      "eval_loss": 1.6131161451339722,
      "eval_runtime": 4.1535,
      "eval_samples_per_second": 39.966,
      "eval_steps_per_second": 19.983,
      "step": 1
    },
    {
      "epoch": 0.005089058524173028,
      "grad_norm": 3.4997785091400146,
      "learning_rate": 1e-05,
      "loss": 1.447,
      "step": 2
    },
    {
      "epoch": 0.007633587786259542,
      "grad_norm": 2.859135627746582,
      "learning_rate": 1.5e-05,
      "loss": 1.1831,
      "step": 3
    },
    {
      "epoch": 0.010178117048346057,
      "grad_norm": 2.542371988296509,
      "learning_rate": 2e-05,
      "loss": 0.8844,
      "step": 4
    },
    {
      "epoch": 0.01272264631043257,
      "grad_norm": 2.9563982486724854,
      "learning_rate": 2.5e-05,
      "loss": 1.2164,
      "step": 5
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": 3.415498733520508,
      "learning_rate": 3e-05,
      "loss": 1.3261,
      "step": 6
    },
    {
      "epoch": 0.017811704834605598,
      "grad_norm": 3.1173617839813232,
      "learning_rate": 3.5e-05,
      "loss": 1.2456,
      "step": 7
    },
    {
      "epoch": 0.020356234096692113,
      "grad_norm": 2.952441453933716,
      "learning_rate": 4e-05,
      "loss": 1.0949,
      "step": 8
    },
    {
      "epoch": 0.022900763358778626,
      "grad_norm": 3.2792415618896484,
      "learning_rate": 4.5e-05,
      "loss": 1.1191,
      "step": 9
    },
    {
      "epoch": 0.02544529262086514,
      "grad_norm": 2.428950786590576,
      "learning_rate": 5e-05,
      "loss": 0.9415,
      "step": 10
    },
    {
      "epoch": 0.027989821882951654,
      "grad_norm": 3.6672072410583496,
      "learning_rate": 4.99229333433282e-05,
      "loss": 1.1482,
      "step": 11
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": 2.3909623622894287,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.7157,
      "step": 12
    },
    {
      "epoch": 0.03307888040712468,
      "grad_norm": 2.3522462844848633,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 0.5238,
      "step": 13
    },
    {
      "epoch": 0.03307888040712468,
      "eval_loss": 0.7261966466903687,
      "eval_runtime": 4.1767,
      "eval_samples_per_second": 39.744,
      "eval_steps_per_second": 19.872,
      "step": 13
    },
    {
      "epoch": 0.035623409669211195,
      "grad_norm": 3.122359275817871,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.7318,
      "step": 14
    },
    {
      "epoch": 0.03816793893129771,
      "grad_norm": 5.089092254638672,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.8987,
      "step": 15
    },
    {
      "epoch": 0.04071246819338423,
      "grad_norm": 2.803917407989502,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.5268,
      "step": 16
    },
    {
      "epoch": 0.043256997455470736,
      "grad_norm": 2.718916654586792,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.6317,
      "step": 17
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": 2.230231285095215,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.2857,
      "step": 18
    },
    {
      "epoch": 0.04834605597964377,
      "grad_norm": 1.5982710123062134,
      "learning_rate": 4.401014914000078e-05,
      "loss": 0.1697,
      "step": 19
    },
    {
      "epoch": 0.05089058524173028,
      "grad_norm": 1.402782917022705,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.2827,
      "step": 20
    },
    {
      "epoch": 0.05343511450381679,
      "grad_norm": 1.7604286670684814,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.1834,
      "step": 21
    },
    {
      "epoch": 0.05597964376590331,
      "grad_norm": 4.199867248535156,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.4652,
      "step": 22
    },
    {
      "epoch": 0.058524173027989825,
      "grad_norm": 1.1508660316467285,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.1081,
      "step": 23
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": 1.6623399257659912,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.1578,
      "step": 24
    },
    {
      "epoch": 0.06361323155216285,
      "grad_norm": 1.1933339834213257,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.1515,
      "step": 25
    },
    {
      "epoch": 0.06615776081424936,
      "grad_norm": 1.6038551330566406,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.2152,
      "step": 26
    },
    {
      "epoch": 0.06615776081424936,
      "eval_loss": 0.18286243081092834,
      "eval_runtime": 4.0988,
      "eval_samples_per_second": 40.499,
      "eval_steps_per_second": 20.25,
      "step": 26
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1300253059842048.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}