{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07451564828614009,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014903129657228018,
      "grad_norm": 2.0342986583709717,
      "learning_rate": 1e-05,
      "loss": 3.4859,
      "step": 1
    },
    {
      "epoch": 0.0014903129657228018,
      "eval_loss": 3.4842216968536377,
      "eval_runtime": 3.0911,
      "eval_samples_per_second": 182.782,
      "eval_steps_per_second": 22.969,
      "step": 1
    },
    {
      "epoch": 0.0029806259314456036,
      "grad_norm": 1.7465375661849976,
      "learning_rate": 2e-05,
      "loss": 3.4165,
      "step": 2
    },
    {
      "epoch": 0.004470938897168405,
      "grad_norm": 1.9989283084869385,
      "learning_rate": 3e-05,
      "loss": 3.4885,
      "step": 3
    },
    {
      "epoch": 0.005961251862891207,
      "grad_norm": 1.7901273965835571,
      "learning_rate": 4e-05,
      "loss": 3.388,
      "step": 4
    },
    {
      "epoch": 0.007451564828614009,
      "grad_norm": 1.8343313932418823,
      "learning_rate": 5e-05,
      "loss": 3.4413,
      "step": 5
    },
    {
      "epoch": 0.00894187779433681,
      "grad_norm": 1.9110901355743408,
      "learning_rate": 6e-05,
      "loss": 3.4883,
      "step": 6
    },
    {
      "epoch": 0.010432190760059613,
      "grad_norm": 1.8050709962844849,
      "learning_rate": 7e-05,
      "loss": 3.4939,
      "step": 7
    },
    {
      "epoch": 0.011922503725782414,
      "grad_norm": 1.8594285249710083,
      "learning_rate": 8e-05,
      "loss": 3.3683,
      "step": 8
    },
    {
      "epoch": 0.013412816691505217,
      "grad_norm": 2.0457093715667725,
      "learning_rate": 9e-05,
      "loss": 3.4379,
      "step": 9
    },
    {
      "epoch": 0.013412816691505217,
      "eval_loss": 3.1294145584106445,
      "eval_runtime": 2.6674,
      "eval_samples_per_second": 211.814,
      "eval_steps_per_second": 26.617,
      "step": 9
    },
    {
      "epoch": 0.014903129657228018,
      "grad_norm": 1.7745529413223267,
      "learning_rate": 0.0001,
      "loss": 3.1102,
      "step": 10
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 1.6581326723098755,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.9326,
      "step": 11
    },
    {
      "epoch": 0.01788375558867362,
      "grad_norm": 1.645290732383728,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.813,
      "step": 12
    },
    {
      "epoch": 0.019374068554396422,
      "grad_norm": 1.6816961765289307,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.6876,
      "step": 13
    },
    {
      "epoch": 0.020864381520119227,
      "grad_norm": 1.6662911176681519,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6106,
      "step": 14
    },
    {
      "epoch": 0.022354694485842028,
      "grad_norm": 1.542525053024292,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.5321,
      "step": 15
    },
    {
      "epoch": 0.02384500745156483,
      "grad_norm": 1.4631415605545044,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3101,
      "step": 16
    },
    {
      "epoch": 0.02533532041728763,
      "grad_norm": 1.5643318891525269,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2768,
      "step": 17
    },
    {
      "epoch": 0.026825633383010434,
      "grad_norm": 1.6115552186965942,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1149,
      "step": 18
    },
    {
      "epoch": 0.026825633383010434,
      "eval_loss": 2.07175612449646,
      "eval_runtime": 2.6646,
      "eval_samples_per_second": 212.036,
      "eval_steps_per_second": 26.645,
      "step": 18
    },
    {
      "epoch": 0.028315946348733235,
      "grad_norm": 1.5824073553085327,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0145,
      "step": 19
    },
    {
      "epoch": 0.029806259314456036,
      "grad_norm": 1.674318790435791,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.047,
      "step": 20
    },
    {
      "epoch": 0.03129657228017884,
      "grad_norm": 1.6824314594268799,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8464,
      "step": 21
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 1.9013198614120483,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7421,
      "step": 22
    },
    {
      "epoch": 0.03427719821162444,
      "grad_norm": 1.8643028736114502,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7526,
      "step": 23
    },
    {
      "epoch": 0.03576751117734724,
      "grad_norm": 1.9997265338897705,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6996,
      "step": 24
    },
    {
      "epoch": 0.037257824143070044,
      "grad_norm": 2.215336322784424,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6416,
      "step": 25
    },
    {
      "epoch": 0.038748137108792845,
      "grad_norm": 2.1552388668060303,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3777,
      "step": 26
    },
    {
      "epoch": 0.040238450074515646,
      "grad_norm": 2.4514808654785156,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3392,
      "step": 27
    },
    {
      "epoch": 0.040238450074515646,
      "eval_loss": 1.2882710695266724,
      "eval_runtime": 2.7452,
      "eval_samples_per_second": 205.816,
      "eval_steps_per_second": 25.864,
      "step": 27
    },
    {
      "epoch": 0.041728763040238454,
      "grad_norm": 2.4231464862823486,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3952,
      "step": 28
    },
    {
      "epoch": 0.043219076005961254,
      "grad_norm": 2.0393948554992676,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1851,
      "step": 29
    },
    {
      "epoch": 0.044709388971684055,
      "grad_norm": 1.9575780630111694,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1068,
      "step": 30
    },
    {
      "epoch": 0.046199701937406856,
      "grad_norm": 1.8777871131896973,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.0618,
      "step": 31
    },
    {
      "epoch": 0.04769001490312966,
      "grad_norm": 2.131181001663208,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9559,
      "step": 32
    },
    {
      "epoch": 0.04918032786885246,
      "grad_norm": 2.0089690685272217,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.903,
      "step": 33
    },
    {
      "epoch": 0.05067064083457526,
      "grad_norm": 1.756807565689087,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8165,
      "step": 34
    },
    {
      "epoch": 0.05216095380029806,
      "grad_norm": 2.0079643726348877,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.8495,
      "step": 35
    },
    {
      "epoch": 0.05365126676602087,
      "grad_norm": 2.026780366897583,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.8717,
      "step": 36
    },
    {
      "epoch": 0.05365126676602087,
      "eval_loss": 0.7020303606987,
      "eval_runtime": 2.7139,
      "eval_samples_per_second": 208.188,
      "eval_steps_per_second": 26.162,
      "step": 36
    },
    {
      "epoch": 0.05514157973174367,
      "grad_norm": 2.029473304748535,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6712,
      "step": 37
    },
    {
      "epoch": 0.05663189269746647,
      "grad_norm": 1.649437427520752,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.6271,
      "step": 38
    },
    {
      "epoch": 0.05812220566318927,
      "grad_norm": 1.7296348810195923,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.714,
      "step": 39
    },
    {
      "epoch": 0.05961251862891207,
      "grad_norm": 1.313446044921875,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5392,
      "step": 40
    },
    {
      "epoch": 0.06110283159463487,
      "grad_norm": 1.2067147493362427,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.5773,
      "step": 41
    },
    {
      "epoch": 0.06259314456035768,
      "grad_norm": 1.3863986730575562,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5832,
      "step": 42
    },
    {
      "epoch": 0.06408345752608048,
      "grad_norm": 1.4204689264297485,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.4459,
      "step": 43
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 1.5218064785003662,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6278,
      "step": 44
    },
    {
      "epoch": 0.06706408345752608,
      "grad_norm": 1.6203991174697876,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4472,
      "step": 45
    },
    {
      "epoch": 0.06706408345752608,
      "eval_loss": 0.4401513338088989,
      "eval_runtime": 2.6576,
      "eval_samples_per_second": 212.596,
      "eval_steps_per_second": 26.716,
      "step": 45
    },
    {
      "epoch": 0.06855439642324888,
      "grad_norm": 1.0682734251022339,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3199,
      "step": 46
    },
    {
      "epoch": 0.07004470938897168,
      "grad_norm": 1.1575658321380615,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.3394,
      "step": 47
    },
    {
      "epoch": 0.07153502235469449,
      "grad_norm": 1.2181802988052368,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3898,
      "step": 48
    },
    {
      "epoch": 0.07302533532041729,
      "grad_norm": 1.1372705698013306,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.468,
      "step": 49
    },
    {
      "epoch": 0.07451564828614009,
      "grad_norm": 0.888025164604187,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3541,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 694187930419200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}