{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024752475247524754,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004950495049504951,
      "grad_norm": 0.5099626779556274,
      "learning_rate": 5e-06,
      "loss": 2.5697,
      "step": 1
    },
    {
      "epoch": 0.0004950495049504951,
      "eval_loss": 2.622131824493408,
      "eval_runtime": 15.9426,
      "eval_samples_per_second": 53.379,
      "eval_steps_per_second": 26.721,
      "step": 1
    },
    {
      "epoch": 0.0009900990099009901,
      "grad_norm": 0.539216935634613,
      "learning_rate": 1e-05,
      "loss": 2.6019,
      "step": 2
    },
    {
      "epoch": 0.0014851485148514852,
      "grad_norm": 1.0987958908081055,
      "learning_rate": 1.5e-05,
      "loss": 2.5236,
      "step": 3
    },
    {
      "epoch": 0.0019801980198019802,
      "grad_norm": 0.9217115640640259,
      "learning_rate": 2e-05,
      "loss": 2.682,
      "step": 4
    },
    {
      "epoch": 0.0024752475247524753,
      "grad_norm": 0.7861433625221252,
      "learning_rate": 2.5e-05,
      "loss": 2.3686,
      "step": 5
    },
    {
      "epoch": 0.0029702970297029703,
      "grad_norm": 0.9432778358459473,
      "learning_rate": 3e-05,
      "loss": 2.3954,
      "step": 6
    },
    {
      "epoch": 0.0034653465346534654,
      "grad_norm": 0.6162946820259094,
      "learning_rate": 3.5e-05,
      "loss": 2.8127,
      "step": 7
    },
    {
      "epoch": 0.0039603960396039604,
      "grad_norm": 0.671248197555542,
      "learning_rate": 4e-05,
      "loss": 2.5454,
      "step": 8
    },
    {
      "epoch": 0.004455445544554455,
      "grad_norm": 0.7792280912399292,
      "learning_rate": 4.5e-05,
      "loss": 2.5155,
      "step": 9
    },
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": 0.5344467163085938,
      "learning_rate": 5e-05,
      "loss": 2.6138,
      "step": 10
    },
    {
      "epoch": 0.005445544554455445,
      "grad_norm": 0.8850129246711731,
      "learning_rate": 4.99229333433282e-05,
      "loss": 2.5492,
      "step": 11
    },
    {
      "epoch": 0.005940594059405941,
      "grad_norm": 0.8699153065681458,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 2.7188,
      "step": 12
    },
    {
      "epoch": 0.006435643564356435,
      "grad_norm": 0.7159351110458374,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 2.7603,
      "step": 13
    },
    {
      "epoch": 0.006435643564356435,
      "eval_loss": 2.6000754833221436,
      "eval_runtime": 14.7393,
      "eval_samples_per_second": 57.737,
      "eval_steps_per_second": 28.902,
      "step": 13
    },
    {
      "epoch": 0.006930693069306931,
      "grad_norm": 0.7229506969451904,
      "learning_rate": 4.877641290737884e-05,
      "loss": 2.5148,
      "step": 14
    },
    {
      "epoch": 0.007425742574257425,
      "grad_norm": 0.7777081727981567,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 2.716,
      "step": 15
    },
    {
      "epoch": 0.007920792079207921,
      "grad_norm": 0.709530770778656,
      "learning_rate": 4.72751631047092e-05,
      "loss": 2.6661,
      "step": 16
    },
    {
      "epoch": 0.008415841584158416,
      "grad_norm": 0.6867318749427795,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 2.6155,
      "step": 17
    },
    {
      "epoch": 0.00891089108910891,
      "grad_norm": 0.8236218690872192,
      "learning_rate": 4.522542485937369e-05,
      "loss": 2.5981,
      "step": 18
    },
    {
      "epoch": 0.009405940594059406,
      "grad_norm": 0.6285402774810791,
      "learning_rate": 4.401014914000078e-05,
      "loss": 2.6279,
      "step": 19
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 0.6804826259613037,
      "learning_rate": 4.267766952966369e-05,
      "loss": 2.5699,
      "step": 20
    },
    {
      "epoch": 0.010396039603960397,
      "grad_norm": 0.8533461093902588,
      "learning_rate": 4.123620120825459e-05,
      "loss": 2.5804,
      "step": 21
    },
    {
      "epoch": 0.01089108910891089,
      "grad_norm": 1.2304980754852295,
      "learning_rate": 3.969463130731183e-05,
      "loss": 2.7291,
      "step": 22
    },
    {
      "epoch": 0.011386138613861386,
      "grad_norm": 0.7633657455444336,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 2.4248,
      "step": 23
    },
    {
      "epoch": 0.011881188118811881,
      "grad_norm": 0.8680675029754639,
      "learning_rate": 3.634976249348867e-05,
      "loss": 2.5192,
      "step": 24
    },
    {
      "epoch": 0.012376237623762377,
      "grad_norm": 0.703606903553009,
      "learning_rate": 3.456708580912725e-05,
      "loss": 2.2694,
      "step": 25
    },
    {
      "epoch": 0.01287128712871287,
      "grad_norm": 0.9794207215309143,
      "learning_rate": 3.272542485937369e-05,
      "loss": 2.5514,
      "step": 26
    },
    {
      "epoch": 0.01287128712871287,
      "eval_loss": 2.531092882156372,
      "eval_runtime": 14.5972,
      "eval_samples_per_second": 58.299,
      "eval_steps_per_second": 29.184,
      "step": 26
    },
    {
      "epoch": 0.013366336633663366,
      "grad_norm": 0.712409257888794,
      "learning_rate": 3.083613409639764e-05,
      "loss": 2.7024,
      "step": 27
    },
    {
      "epoch": 0.013861386138613862,
      "grad_norm": 0.7140835523605347,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 2.3597,
      "step": 28
    },
    {
      "epoch": 0.014356435643564357,
      "grad_norm": 0.7529740929603577,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 2.4987,
      "step": 29
    },
    {
      "epoch": 0.01485148514851485,
      "grad_norm": 0.7249071002006531,
      "learning_rate": 2.5e-05,
      "loss": 2.5261,
      "step": 30
    },
    {
      "epoch": 0.015346534653465346,
      "grad_norm": 0.6572368144989014,
      "learning_rate": 2.303852260680388e-05,
      "loss": 2.5675,
      "step": 31
    },
    {
      "epoch": 0.015841584158415842,
      "grad_norm": 0.8049694895744324,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 2.4052,
      "step": 32
    },
    {
      "epoch": 0.016336633663366337,
      "grad_norm": 1.333217740058899,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 3.0249,
      "step": 33
    },
    {
      "epoch": 0.016831683168316833,
      "grad_norm": 0.6144301891326904,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 2.6427,
      "step": 34
    },
    {
      "epoch": 0.017326732673267328,
      "grad_norm": 0.5658847093582153,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 2.3681,
      "step": 35
    },
    {
      "epoch": 0.01782178217821782,
      "grad_norm": 0.5838199257850647,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 2.2482,
      "step": 36
    },
    {
      "epoch": 0.018316831683168316,
      "grad_norm": 0.6288196444511414,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 2.495,
      "step": 37
    },
    {
      "epoch": 0.01881188118811881,
      "grad_norm": 0.7089413404464722,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 2.4151,
      "step": 38
    },
    {
      "epoch": 0.019306930693069307,
      "grad_norm": 0.46954041719436646,
      "learning_rate": 8.763798791745411e-06,
      "loss": 2.3573,
      "step": 39
    },
    {
      "epoch": 0.019306930693069307,
      "eval_loss": 2.504016399383545,
      "eval_runtime": 14.7245,
      "eval_samples_per_second": 57.795,
      "eval_steps_per_second": 28.931,
      "step": 39
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 0.5877854824066162,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 2.3505,
      "step": 40
    },
    {
      "epoch": 0.020297029702970298,
      "grad_norm": 0.7243385910987854,
      "learning_rate": 5.989850859999227e-06,
      "loss": 2.5964,
      "step": 41
    },
    {
      "epoch": 0.020792079207920793,
      "grad_norm": 0.5486332774162292,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 2.5455,
      "step": 42
    },
    {
      "epoch": 0.02128712871287129,
      "grad_norm": 0.5547685623168945,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 2.5585,
      "step": 43
    },
    {
      "epoch": 0.02178217821782178,
      "grad_norm": 0.5885905027389526,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 2.3613,
      "step": 44
    },
    {
      "epoch": 0.022277227722772276,
      "grad_norm": 0.47415289282798767,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 2.4039,
      "step": 45
    },
    {
      "epoch": 0.02277227722772277,
      "grad_norm": 0.6020286083221436,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 2.5496,
      "step": 46
    },
    {
      "epoch": 0.023267326732673267,
      "grad_norm": 0.8112446069717407,
      "learning_rate": 6.907519900580861e-07,
      "loss": 2.6563,
      "step": 47
    },
    {
      "epoch": 0.023762376237623763,
      "grad_norm": 0.6824198365211487,
      "learning_rate": 3.077914851215585e-07,
      "loss": 2.5111,
      "step": 48
    },
    {
      "epoch": 0.024257425742574258,
      "grad_norm": 0.5109888315200806,
      "learning_rate": 7.706665667180091e-08,
      "loss": 2.4153,
      "step": 49
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 0.6785337328910828,
      "learning_rate": 0.0,
      "loss": 2.5139,
      "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": 1624279061889024.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}