{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07272727272727272,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014545454545454545,
      "grad_norm": 0.5051049590110779,
      "learning_rate": 2e-05,
      "loss": 0.3615,
      "step": 1
    },
    {
      "epoch": 0.0014545454545454545,
      "eval_loss": 0.4058317542076111,
      "eval_runtime": 24.9192,
      "eval_samples_per_second": 11.638,
      "eval_steps_per_second": 5.819,
      "step": 1
    },
    {
      "epoch": 0.002909090909090909,
      "grad_norm": 0.7143672704696655,
      "learning_rate": 4e-05,
      "loss": 0.4981,
      "step": 2
    },
    {
      "epoch": 0.004363636363636364,
      "grad_norm": 0.3360948860645294,
      "learning_rate": 6e-05,
      "loss": 0.2856,
      "step": 3
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 0.44477200508117676,
      "learning_rate": 8e-05,
      "loss": 0.2617,
      "step": 4
    },
    {
      "epoch": 0.007272727272727273,
      "grad_norm": 0.4044454097747803,
      "learning_rate": 0.0001,
      "loss": 0.2466,
      "step": 5
    },
    {
      "epoch": 0.007272727272727273,
      "eval_loss": 0.3780933916568756,
      "eval_runtime": 24.6289,
      "eval_samples_per_second": 11.775,
      "eval_steps_per_second": 5.887,
      "step": 5
    },
    {
      "epoch": 0.008727272727272728,
      "grad_norm": 0.43507444858551025,
      "learning_rate": 0.00012,
      "loss": 0.2384,
      "step": 6
    },
    {
      "epoch": 0.010181818181818183,
      "grad_norm": 0.541296124458313,
      "learning_rate": 0.00014,
      "loss": 0.2606,
      "step": 7
    },
    {
      "epoch": 0.011636363636363636,
      "grad_norm": 0.4881332814693451,
      "learning_rate": 0.00016,
      "loss": 0.2463,
      "step": 8
    },
    {
      "epoch": 0.01309090909090909,
      "grad_norm": 0.7712896466255188,
      "learning_rate": 0.00018,
      "loss": 0.3117,
      "step": 9
    },
    {
      "epoch": 0.014545454545454545,
      "grad_norm": 0.48558855056762695,
      "learning_rate": 0.0002,
      "loss": 0.1169,
      "step": 10
    },
    {
      "epoch": 0.014545454545454545,
      "eval_loss": 0.12428049743175507,
      "eval_runtime": 24.7343,
      "eval_samples_per_second": 11.725,
      "eval_steps_per_second": 5.862,
      "step": 10
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.4993226230144501,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.1023,
      "step": 11
    },
    {
      "epoch": 0.017454545454545455,
      "grad_norm": 0.8036471009254456,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0975,
      "step": 12
    },
    {
      "epoch": 0.01890909090909091,
      "grad_norm": 0.8658446073532104,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.1072,
      "step": 13
    },
    {
      "epoch": 0.020363636363636365,
      "grad_norm": 0.5599696040153503,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0612,
      "step": 14
    },
    {
      "epoch": 0.02181818181818182,
      "grad_norm": 0.5136664509773254,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0837,
      "step": 15
    },
    {
      "epoch": 0.02181818181818182,
      "eval_loss": 0.07245617359876633,
      "eval_runtime": 24.6969,
      "eval_samples_per_second": 11.742,
      "eval_steps_per_second": 5.871,
      "step": 15
    },
    {
      "epoch": 0.02327272727272727,
      "grad_norm": 0.6104558706283569,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.0643,
      "step": 16
    },
    {
      "epoch": 0.024727272727272726,
      "grad_norm": 0.5080060958862305,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.0751,
      "step": 17
    },
    {
      "epoch": 0.02618181818181818,
      "grad_norm": 0.3353659212589264,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0363,
      "step": 18
    },
    {
      "epoch": 0.027636363636363636,
      "grad_norm": 0.5001118779182434,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.0556,
      "step": 19
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 0.6435399055480957,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0711,
      "step": 20
    },
    {
      "epoch": 0.02909090909090909,
      "eval_loss": 0.06782884895801544,
      "eval_runtime": 24.764,
      "eval_samples_per_second": 11.711,
      "eval_steps_per_second": 5.855,
      "step": 20
    },
    {
      "epoch": 0.030545454545454546,
      "grad_norm": 0.561763346195221,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.095,
      "step": 21
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.8185080885887146,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.1344,
      "step": 22
    },
    {
      "epoch": 0.03345454545454545,
      "grad_norm": 0.3717232942581177,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.0271,
      "step": 23
    },
    {
      "epoch": 0.03490909090909091,
      "grad_norm": 0.31359872221946716,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0392,
      "step": 24
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.5982680916786194,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0611,
      "step": 25
    },
    {
      "epoch": 0.03636363636363636,
      "eval_loss": 0.05668775737285614,
      "eval_runtime": 24.7809,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 5.851,
      "step": 25
    },
    {
      "epoch": 0.03781818181818182,
      "grad_norm": 0.22259199619293213,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0199,
      "step": 26
    },
    {
      "epoch": 0.03927272727272727,
      "grad_norm": 0.7268075942993164,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.177,
      "step": 27
    },
    {
      "epoch": 0.04072727272727273,
      "grad_norm": 0.22450760006904602,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0249,
      "step": 28
    },
    {
      "epoch": 0.04218181818181818,
      "grad_norm": 0.4080381691455841,
      "learning_rate": 0.0001078459095727845,
      "loss": 0.0378,
      "step": 29
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": 0.47309610247612,
      "learning_rate": 0.0001,
      "loss": 0.0387,
      "step": 30
    },
    {
      "epoch": 0.04363636363636364,
      "eval_loss": 0.0551588237285614,
      "eval_runtime": 24.7856,
      "eval_samples_per_second": 11.7,
      "eval_steps_per_second": 5.85,
      "step": 30
    },
    {
      "epoch": 0.04509090909090909,
      "grad_norm": 0.565868079662323,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.1016,
      "step": 31
    },
    {
      "epoch": 0.04654545454545454,
      "grad_norm": 0.5154087543487549,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0434,
      "step": 32
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.7290896773338318,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.1061,
      "step": 33
    },
    {
      "epoch": 0.04945454545454545,
      "grad_norm": 0.7846975326538086,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.1535,
      "step": 34
    },
    {
      "epoch": 0.05090909090909091,
      "grad_norm": 0.3980070650577545,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0709,
      "step": 35
    },
    {
      "epoch": 0.05090909090909091,
      "eval_loss": 0.05250132083892822,
      "eval_runtime": 24.7914,
      "eval_samples_per_second": 11.698,
      "eval_steps_per_second": 5.849,
      "step": 35
    },
    {
      "epoch": 0.05236363636363636,
      "grad_norm": 0.49924206733703613,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0803,
      "step": 36
    },
    {
      "epoch": 0.05381818181818182,
      "grad_norm": 0.42729631066322327,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.0447,
      "step": 37
    },
    {
      "epoch": 0.05527272727272727,
      "grad_norm": 0.20265118777751923,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0277,
      "step": 38
    },
    {
      "epoch": 0.05672727272727273,
      "grad_norm": 0.5974223613739014,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.1184,
      "step": 39
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 0.6130847334861755,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.1079,
      "step": 40
    },
    {
      "epoch": 0.05818181818181818,
      "eval_loss": 0.05132311210036278,
      "eval_runtime": 24.7921,
      "eval_samples_per_second": 11.697,
      "eval_steps_per_second": 5.849,
      "step": 40
    },
    {
      "epoch": 0.05963636363636363,
      "grad_norm": 0.5219517946243286,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.0571,
      "step": 41
    },
    {
      "epoch": 0.06109090909090909,
      "grad_norm": 0.20746634900569916,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0254,
      "step": 42
    },
    {
      "epoch": 0.06254545454545454,
      "grad_norm": 1.359476089477539,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.04,
      "step": 43
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.55459064245224,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0772,
      "step": 44
    },
    {
      "epoch": 0.06545454545454546,
      "grad_norm": 0.19099941849708557,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0142,
      "step": 45
    },
    {
      "epoch": 0.06545454545454546,
      "eval_loss": 0.051045071333646774,
      "eval_runtime": 24.8018,
      "eval_samples_per_second": 11.693,
      "eval_steps_per_second": 5.846,
      "step": 45
    },
    {
      "epoch": 0.0669090909090909,
      "grad_norm": 0.20805087685585022,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0106,
      "step": 46
    },
    {
      "epoch": 0.06836363636363636,
      "grad_norm": 0.36373722553253174,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.0605,
      "step": 47
    },
    {
      "epoch": 0.06981818181818182,
      "grad_norm": 0.2527661621570587,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0241,
      "step": 48
    },
    {
      "epoch": 0.07127272727272728,
      "grad_norm": 2.111194372177124,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.1286,
      "step": 49
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.45172688364982605,
      "learning_rate": 0.0,
      "loss": 0.0227,
      "step": 50
    },
    {
      "epoch": 0.07272727272727272,
      "eval_loss": 0.05098990350961685,
      "eval_runtime": 24.8142,
      "eval_samples_per_second": 11.687,
      "eval_steps_per_second": 5.843,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8588120693866496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}