{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 565,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 5.764378547668457,
      "learning_rate": 1.8e-05,
      "loss": 3.9245,
      "step": 10
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 4.340976715087891,
      "learning_rate": 3.8e-05,
      "loss": 3.4043,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 4.136200904846191,
      "learning_rate": 5.8e-05,
      "loss": 2.2864,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.0005297660827637,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.1498,
      "step": 40
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.5809401273727417,
      "learning_rate": 9.8e-05,
      "loss": 0.8409,
      "step": 50
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.0459725856781006,
      "learning_rate": 9.99246642311259e-05,
      "loss": 0.8145,
      "step": 60
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.44736912846565247,
      "learning_rate": 9.966453573423791e-05,
      "loss": 0.7908,
      "step": 70
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.8621402978897095,
      "learning_rate": 9.921965190244129e-05,
      "loss": 0.7472,
      "step": 80
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8157559037208557,
      "learning_rate": 9.85916677328104e-05,
      "loss": 0.6703,
      "step": 90
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.6298869848251343,
      "learning_rate": 9.77829193677024e-05,
      "loss": 0.546,
      "step": 100
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.996382713317871,
      "learning_rate": 9.679641540415427e-05,
      "loss": 0.341,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.32163509726524353,
      "eval_runtime": 42.6613,
      "eval_samples_per_second": 2.344,
      "eval_steps_per_second": 0.305,
      "step": 113
    },
    {
      "epoch": 1.0622222222222222,
      "grad_norm": 0.3126855194568634,
      "learning_rate": 9.563582570170417e-05,
      "loss": 0.3204,
      "step": 120
    },
    {
      "epoch": 1.1511111111111112,
      "grad_norm": 0.3520595133304596,
      "learning_rate": 9.430546773027302e-05,
      "loss": 0.3214,
      "step": 130
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.3733944594860077,
      "learning_rate": 9.281029050889274e-05,
      "loss": 0.3201,
      "step": 140
    },
    {
      "epoch": 1.3288888888888888,
      "grad_norm": 0.2799483835697174,
      "learning_rate": 9.115585619503039e-05,
      "loss": 0.321,
      "step": 150
    },
    {
      "epoch": 1.4177777777777778,
      "grad_norm": 0.21395893394947052,
      "learning_rate": 8.934831939299714e-05,
      "loss": 0.3214,
      "step": 160
    },
    {
      "epoch": 1.5066666666666668,
      "grad_norm": 0.24816612899303436,
      "learning_rate": 8.739440425841599e-05,
      "loss": 0.3192,
      "step": 170
    },
    {
      "epoch": 1.5955555555555554,
      "grad_norm": 0.11175958812236786,
      "learning_rate": 8.530137948392112e-05,
      "loss": 0.318,
      "step": 180
    },
    {
      "epoch": 1.6844444444444444,
      "grad_norm": 0.16557013988494873,
      "learning_rate": 8.307703125914397e-05,
      "loss": 0.3198,
      "step": 190
    },
    {
      "epoch": 1.7733333333333334,
      "grad_norm": 0.32549384236335754,
      "learning_rate": 8.072963430557636e-05,
      "loss": 0.3225,
      "step": 200
    },
    {
      "epoch": 1.8622222222222222,
      "grad_norm": 0.21063511073589325,
      "learning_rate": 7.826792109406308e-05,
      "loss": 0.3181,
      "step": 210
    },
    {
      "epoch": 1.951111111111111,
      "grad_norm": 0.22092826664447784,
      "learning_rate": 7.570104935943685e-05,
      "loss": 0.3187,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.32037025690078735,
      "eval_runtime": 40.3313,
      "eval_samples_per_second": 2.479,
      "eval_steps_per_second": 0.322,
      "step": 226
    },
    {
      "epoch": 2.0355555555555553,
      "grad_norm": 0.22031903266906738,
      "learning_rate": 7.303856803314313e-05,
      "loss": 0.3273,
      "step": 230
    },
    {
      "epoch": 2.1244444444444444,
      "grad_norm": 0.16489087045192719,
      "learning_rate": 7.029038172058809e-05,
      "loss": 0.3184,
      "step": 240
    },
    {
      "epoch": 2.2133333333333334,
      "grad_norm": 0.1534615159034729,
      "learning_rate": 6.746671385535586e-05,
      "loss": 0.3185,
      "step": 250
    },
    {
      "epoch": 2.3022222222222224,
      "grad_norm": 0.13345931470394135,
      "learning_rate": 6.457806866736424e-05,
      "loss": 0.3209,
      "step": 260
    },
    {
      "epoch": 2.391111111111111,
      "grad_norm": 0.18040268123149872,
      "learning_rate": 6.163519210643939e-05,
      "loss": 0.3199,
      "step": 270
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.2649783790111542,
      "learning_rate": 5.864903186667668e-05,
      "loss": 0.3207,
      "step": 280
    },
    {
      "epoch": 2.568888888888889,
      "grad_norm": 0.18706634640693665,
      "learning_rate": 5.5630696660299694e-05,
      "loss": 0.3195,
      "step": 290
    },
    {
      "epoch": 2.6577777777777776,
      "grad_norm": 0.24964497983455658,
      "learning_rate": 5.259141489252104e-05,
      "loss": 0.3216,
      "step": 300
    },
    {
      "epoch": 2.7466666666666666,
      "grad_norm": 0.13545331358909607,
      "learning_rate": 4.9542492891137526e-05,
      "loss": 0.3178,
      "step": 310
    },
    {
      "epoch": 2.8355555555555556,
      "grad_norm": 0.2153831124305725,
      "learning_rate": 4.6495272846248146e-05,
      "loss": 0.3182,
      "step": 320
    },
    {
      "epoch": 2.924444444444444,
      "grad_norm": 0.15629053115844727,
      "learning_rate": 4.346109061656195e-05,
      "loss": 0.3185,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.32035037875175476,
      "eval_runtime": 40.3621,
      "eval_samples_per_second": 2.478,
      "eval_steps_per_second": 0.322,
      "step": 339
    },
    {
      "epoch": 3.008888888888889,
      "grad_norm": 0.13374465703964233,
      "learning_rate": 4.04512335592591e-05,
      "loss": 0.3199,
      "step": 340
    },
    {
      "epoch": 3.097777777777778,
      "grad_norm": 0.19588690996170044,
      "learning_rate": 3.747689854028081e-05,
      "loss": 0.319,
      "step": 350
    },
    {
      "epoch": 3.1866666666666665,
      "grad_norm": 0.17849618196487427,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3198,
      "step": 360
    },
    {
      "epoch": 3.2755555555555556,
      "grad_norm": 0.11948955059051514,
      "learning_rate": 3.16788801979933e-05,
      "loss": 0.3182,
      "step": 370
    },
    {
      "epoch": 3.3644444444444446,
      "grad_norm": 0.13129116594791412,
      "learning_rate": 2.8876765883732447e-05,
      "loss": 0.3176,
      "step": 380
    },
    {
      "epoch": 3.453333333333333,
      "grad_norm": 0.20687370002269745,
      "learning_rate": 2.6153231387762637e-05,
      "loss": 0.3197,
      "step": 390
    },
    {
      "epoch": 3.542222222222222,
      "grad_norm": 0.22439858317375183,
      "learning_rate": 2.3518408437291157e-05,
      "loss": 0.321,
      "step": 400
    },
    {
      "epoch": 3.631111111111111,
      "grad_norm": 0.16592849791049957,
      "learning_rate": 2.0982098746749523e-05,
      "loss": 0.3196,
      "step": 410
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 0.09099625796079636,
      "learning_rate": 1.8553737554771882e-05,
      "loss": 0.318,
      "step": 420
    },
    {
      "epoch": 3.8088888888888888,
      "grad_norm": 0.13774339854717255,
      "learning_rate": 1.62423585244877e-05,
      "loss": 0.319,
      "step": 430
    },
    {
      "epoch": 3.897777777777778,
      "grad_norm": 0.13488805294036865,
      "learning_rate": 1.405656013770147e-05,
      "loss": 0.3181,
      "step": 440
    },
    {
      "epoch": 3.986666666666667,
      "grad_norm": 0.15799656510353088,
      "learning_rate": 1.2004473707975761e-05,
      "loss": 0.3201,
      "step": 450
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.31841641664505005,
      "eval_runtime": 40.3686,
      "eval_samples_per_second": 2.477,
      "eval_steps_per_second": 0.322,
      "step": 452
    },
    {
      "epoch": 4.071111111111111,
      "grad_norm": 0.10995037853717804,
      "learning_rate": 1.0093733131610622e-05,
      "loss": 0.3184,
      "step": 460
    },
    {
      "epoch": 4.16,
      "grad_norm": 0.15549620985984802,
      "learning_rate": 8.331446489047956e-06,
      "loss": 0.3173,
      "step": 470
    },
    {
      "epoch": 4.248888888888889,
      "grad_norm": 0.17202192544937134,
      "learning_rate": 6.724169602345487e-06,
      "loss": 0.3203,
      "step": 480
    },
    {
      "epoch": 4.337777777777778,
      "grad_norm": 0.11324512213468552,
      "learning_rate": 5.277881647088024e-06,
      "loss": 0.316,
      "step": 490
    },
    {
      "epoch": 4.426666666666667,
      "grad_norm": 0.11072061955928802,
      "learning_rate": 3.9979629094616115e-06,
      "loss": 0.3186,
      "step": 500
    },
    {
      "epoch": 4.515555555555555,
      "grad_norm": 0.13301220536231995,
      "learning_rate": 2.88917477123557e-06,
      "loss": 0.3187,
      "step": 510
    },
    {
      "epoch": 4.604444444444445,
      "grad_norm": 0.09929703176021576,
      "learning_rate": 1.9556419971095363e-06,
      "loss": 0.3195,
      "step": 520
    },
    {
      "epoch": 4.693333333333333,
      "grad_norm": 0.1245638057589531,
      "learning_rate": 1.2008373903178827e-06,
      "loss": 0.3185,
      "step": 530
    },
    {
      "epoch": 4.782222222222222,
      "grad_norm": 0.10131300240755081,
      "learning_rate": 6.275688735736141e-07,
      "loss": 0.3186,
      "step": 540
    },
    {
      "epoch": 4.871111111111111,
      "grad_norm": 0.25302281975746155,
      "learning_rate": 2.3796904341141235e-07,
      "loss": 0.3203,
      "step": 550
    },
    {
      "epoch": 4.96,
      "grad_norm": 0.12090457230806351,
      "learning_rate": 3.348723678847643e-08,
      "loss": 0.3183,
      "step": 560
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.3198339641094208,
      "eval_runtime": 40.339,
      "eval_samples_per_second": 2.479,
      "eval_steps_per_second": 0.322,
      "step": 565
    }
  ],
  "logging_steps": 10,
  "max_steps": 565,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.3759216984064e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}