{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06201550387596899,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00124031007751938,
      "grad_norm": 10.036916732788086,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 8.1095,
      "step": 1
    },
    {
      "epoch": 0.00124031007751938,
      "eval_loss": 9.117852210998535,
      "eval_runtime": 76.3739,
      "eval_samples_per_second": 8.89,
      "eval_steps_per_second": 4.452,
      "step": 1
    },
    {
      "epoch": 0.00248062015503876,
      "grad_norm": 11.031106948852539,
      "learning_rate": 6.666666666666667e-05,
      "loss": 8.5269,
      "step": 2
    },
    {
      "epoch": 0.0037209302325581397,
      "grad_norm": 11.883184432983398,
      "learning_rate": 0.0001,
      "loss": 10.0789,
      "step": 3
    },
    {
      "epoch": 0.00496124031007752,
      "grad_norm": 11.162190437316895,
      "learning_rate": 9.99524110790929e-05,
      "loss": 6.9676,
      "step": 4
    },
    {
      "epoch": 0.006201550387596899,
      "grad_norm": 17.476125717163086,
      "learning_rate": 9.980973490458728e-05,
      "loss": 6.3001,
      "step": 5
    },
    {
      "epoch": 0.0074418604651162795,
      "grad_norm": 17.252897262573242,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.9376,
      "step": 6
    },
    {
      "epoch": 0.008682170542635658,
      "grad_norm": 13.084904670715332,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.2759,
      "step": 7
    },
    {
      "epoch": 0.00992248062015504,
      "grad_norm": 16.068397521972656,
      "learning_rate": 9.881480035599667e-05,
      "loss": 2.304,
      "step": 8
    },
    {
      "epoch": 0.011162790697674419,
      "grad_norm": 18.40654945373535,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.2888,
      "step": 9
    },
    {
      "epoch": 0.012403100775193798,
      "grad_norm": 9.211000442504883,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.7295,
      "step": 10
    },
    {
      "epoch": 0.013643410852713178,
      "grad_norm": 7.752258777618408,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4072,
      "step": 11
    },
    {
      "epoch": 0.014883720930232559,
      "grad_norm": 4.2014055252075195,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2088,
      "step": 12
    },
    {
      "epoch": 0.01612403100775194,
      "grad_norm": 12.749472618103027,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.3866,
      "step": 13
    },
    {
      "epoch": 0.017364341085271316,
      "grad_norm": 8.866931915283203,
      "learning_rate": 9.435054165891109e-05,
      "loss": 1.2496,
      "step": 14
    },
    {
      "epoch": 0.018604651162790697,
      "grad_norm": 9.160735130310059,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5326,
      "step": 15
    },
    {
      "epoch": 0.01984496124031008,
      "grad_norm": 4.777466297149658,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.1491,
      "step": 16
    },
    {
      "epoch": 0.021085271317829456,
      "grad_norm": 9.52919864654541,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.6692,
      "step": 17
    },
    {
      "epoch": 0.022325581395348838,
      "grad_norm": 6.059999942779541,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.4079,
      "step": 18
    },
    {
      "epoch": 0.023565891472868215,
      "grad_norm": 4.906097412109375,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4181,
      "step": 19
    },
    {
      "epoch": 0.024806201550387597,
      "grad_norm": 4.529596328735352,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.3098,
      "step": 20
    },
    {
      "epoch": 0.026046511627906978,
      "grad_norm": 2.2114293575286865,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1024,
      "step": 21
    },
    {
      "epoch": 0.027286821705426356,
      "grad_norm": 3.5464649200439453,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.2618,
      "step": 22
    },
    {
      "epoch": 0.028527131782945737,
      "grad_norm": 2.7277891635894775,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.122,
      "step": 23
    },
    {
      "epoch": 0.029767441860465118,
      "grad_norm": 6.989150047302246,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4793,
      "step": 24
    },
    {
      "epoch": 0.031007751937984496,
      "grad_norm": 2.827395439147949,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0882,
      "step": 25
    },
    {
      "epoch": 0.031007751937984496,
      "eval_loss": 0.4584539830684662,
      "eval_runtime": 75.8039,
      "eval_samples_per_second": 8.957,
      "eval_steps_per_second": 4.485,
      "step": 25
    },
    {
      "epoch": 0.03224806201550388,
      "grad_norm": 3.6787235736846924,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.5067,
      "step": 26
    },
    {
      "epoch": 0.03348837209302326,
      "grad_norm": 3.147265672683716,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1425,
      "step": 27
    },
    {
      "epoch": 0.03472868217054263,
      "grad_norm": 8.905163764953613,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.3812,
      "step": 28
    },
    {
      "epoch": 0.035968992248062014,
      "grad_norm": 3.192728042602539,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.185,
      "step": 29
    },
    {
      "epoch": 0.037209302325581395,
      "grad_norm": 4.592311859130859,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5299,
      "step": 30
    },
    {
      "epoch": 0.038449612403100776,
      "grad_norm": 4.895242691040039,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.438,
      "step": 31
    },
    {
      "epoch": 0.03968992248062016,
      "grad_norm": 5.272075653076172,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.4829,
      "step": 32
    },
    {
      "epoch": 0.04093023255813953,
      "grad_norm": 4.914361953735352,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.2553,
      "step": 33
    },
    {
      "epoch": 0.04217054263565891,
      "grad_norm": 1.8775806427001953,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0675,
      "step": 34
    },
    {
      "epoch": 0.043410852713178294,
      "grad_norm": 4.3540730476379395,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3092,
      "step": 35
    },
    {
      "epoch": 0.044651162790697675,
      "grad_norm": 2.111719846725464,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1889,
      "step": 36
    },
    {
      "epoch": 0.045891472868217056,
      "grad_norm": 2.258272647857666,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.145,
      "step": 37
    },
    {
      "epoch": 0.04713178294573643,
      "grad_norm": 2.4425384998321533,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.1353,
      "step": 38
    },
    {
      "epoch": 0.04837209302325581,
      "grad_norm": 4.513883590698242,
      "learning_rate": 5e-05,
      "loss": 0.512,
      "step": 39
    },
    {
      "epoch": 0.04961240310077519,
      "grad_norm": 3.031637668609619,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.1914,
      "step": 40
    },
    {
      "epoch": 0.050852713178294574,
      "grad_norm": 1.72134268283844,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.1026,
      "step": 41
    },
    {
      "epoch": 0.052093023255813956,
      "grad_norm": 3.1912903785705566,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.2749,
      "step": 42
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 4.633580207824707,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3602,
      "step": 43
    },
    {
      "epoch": 0.05457364341085271,
      "grad_norm": 3.736760377883911,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.275,
      "step": 44
    },
    {
      "epoch": 0.05581395348837209,
      "grad_norm": 6.0138325691223145,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7282,
      "step": 45
    },
    {
      "epoch": 0.05705426356589147,
      "grad_norm": 5.953103542327881,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.5171,
      "step": 46
    },
    {
      "epoch": 0.058294573643410855,
      "grad_norm": 5.933166980743408,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8627,
      "step": 47
    },
    {
      "epoch": 0.059534883720930236,
      "grad_norm": 5.244954586029053,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0686,
      "step": 48
    },
    {
      "epoch": 0.06077519379844961,
      "grad_norm": 5.3813581466674805,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.2411,
      "step": 49
    },
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 5.831821918487549,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 1.2176,
      "step": 50
    },
    {
      "epoch": 0.06201550387596899,
      "eval_loss": 0.42768043279647827,
      "eval_runtime": 75.9401,
      "eval_samples_per_second": 8.941,
      "eval_steps_per_second": 4.477,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.46010452164608e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}