{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.18562874251497,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11976047904191617,
      "grad_norm": 2.8749659061431885,
      "learning_rate": 0.0002,
      "loss": 1.4673,
      "step": 10
    },
    {
      "epoch": 0.23952095808383234,
      "grad_norm": 3.4398715496063232,
      "learning_rate": 0.0002,
      "loss": 1.0019,
      "step": 20
    },
    {
      "epoch": 0.3592814371257485,
      "grad_norm": 1.9059951305389404,
      "learning_rate": 0.0002,
      "loss": 1.0575,
      "step": 30
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 4.149394989013672,
      "learning_rate": 0.0002,
      "loss": 0.8164,
      "step": 40
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 1.4866076707839966,
      "learning_rate": 0.0002,
      "loss": 0.8684,
      "step": 50
    },
    {
      "epoch": 0.718562874251497,
      "grad_norm": 3.1927452087402344,
      "learning_rate": 0.0002,
      "loss": 0.8016,
      "step": 60
    },
    {
      "epoch": 0.8383233532934131,
      "grad_norm": 1.1162314414978027,
      "learning_rate": 0.0002,
      "loss": 0.6809,
      "step": 70
    },
    {
      "epoch": 0.9580838323353293,
      "grad_norm": 2.829102039337158,
      "learning_rate": 0.0002,
      "loss": 0.6962,
      "step": 80
    },
    {
      "epoch": 1.0778443113772456,
      "grad_norm": 1.2642532587051392,
      "learning_rate": 0.0002,
      "loss": 0.5769,
      "step": 90
    },
    {
      "epoch": 1.1976047904191618,
      "grad_norm": 1.3799452781677246,
      "learning_rate": 0.0002,
      "loss": 0.4128,
      "step": 100
    },
    {
      "epoch": 1.3173652694610778,
      "grad_norm": 2.3143367767333984,
      "learning_rate": 0.0002,
      "loss": 0.6441,
      "step": 110
    },
    {
      "epoch": 1.437125748502994,
      "grad_norm": 1.085919976234436,
      "learning_rate": 0.0002,
      "loss": 0.393,
      "step": 120
    },
    {
      "epoch": 1.55688622754491,
      "grad_norm": 1.2423957586288452,
      "learning_rate": 0.0002,
      "loss": 0.5582,
      "step": 130
    },
    {
      "epoch": 1.6766467065868262,
      "grad_norm": 1.2964059114456177,
      "learning_rate": 0.0002,
      "loss": 0.4276,
      "step": 140
    },
    {
      "epoch": 1.7964071856287425,
      "grad_norm": 1.8397400379180908,
      "learning_rate": 0.0002,
      "loss": 0.6162,
      "step": 150
    },
    {
      "epoch": 1.9161676646706587,
      "grad_norm": 1.0209627151489258,
      "learning_rate": 0.0002,
      "loss": 0.4565,
      "step": 160
    },
    {
      "epoch": 2.035928143712575,
      "grad_norm": 0.8725757598876953,
      "learning_rate": 0.0002,
      "loss": 0.4807,
      "step": 170
    },
    {
      "epoch": 2.155688622754491,
      "grad_norm": 1.1269447803497314,
      "learning_rate": 0.0002,
      "loss": 0.3895,
      "step": 180
    },
    {
      "epoch": 2.2754491017964074,
      "grad_norm": 1.528011679649353,
      "learning_rate": 0.0002,
      "loss": 0.3553,
      "step": 190
    },
    {
      "epoch": 2.3952095808383236,
      "grad_norm": 0.8296527862548828,
      "learning_rate": 0.0002,
      "loss": 0.3516,
      "step": 200
    },
    {
      "epoch": 2.5149700598802394,
      "grad_norm": 1.301917552947998,
      "learning_rate": 0.0002,
      "loss": 0.3918,
      "step": 210
    },
    {
      "epoch": 2.6347305389221556,
      "grad_norm": 0.8420801758766174,
      "learning_rate": 0.0002,
      "loss": 0.3497,
      "step": 220
    },
    {
      "epoch": 2.754491017964072,
      "grad_norm": 1.1430580615997314,
      "learning_rate": 0.0002,
      "loss": 0.4311,
      "step": 230
    },
    {
      "epoch": 2.874251497005988,
      "grad_norm": 0.9065356850624084,
      "learning_rate": 0.0002,
      "loss": 0.3551,
      "step": 240
    },
    {
      "epoch": 2.9940119760479043,
      "grad_norm": 1.1302285194396973,
      "learning_rate": 0.0002,
      "loss": 0.3513,
      "step": 250
    },
    {
      "epoch": 3.1137724550898205,
      "grad_norm": 0.9960314631462097,
      "learning_rate": 0.0002,
      "loss": 0.3124,
      "step": 260
    },
    {
      "epoch": 3.2335329341317367,
      "grad_norm": 1.680296778678894,
      "learning_rate": 0.0002,
      "loss": 0.3065,
      "step": 270
    },
    {
      "epoch": 3.3532934131736525,
      "grad_norm": 1.1697853803634644,
      "learning_rate": 0.0002,
      "loss": 0.3009,
      "step": 280
    },
    {
      "epoch": 3.4730538922155687,
      "grad_norm": 1.9219907522201538,
      "learning_rate": 0.0002,
      "loss": 0.2802,
      "step": 290
    },
    {
      "epoch": 3.592814371257485,
      "grad_norm": 1.384773850440979,
      "learning_rate": 0.0002,
      "loss": 0.3419,
      "step": 300
    },
    {
      "epoch": 3.712574850299401,
      "grad_norm": 1.3956997394561768,
      "learning_rate": 0.0002,
      "loss": 0.3172,
      "step": 310
    },
    {
      "epoch": 3.8323353293413174,
      "grad_norm": 1.058669924736023,
      "learning_rate": 0.0002,
      "loss": 0.3723,
      "step": 320
    },
    {
      "epoch": 3.9520958083832336,
      "grad_norm": 1.5626955032348633,
      "learning_rate": 0.0002,
      "loss": 0.325,
      "step": 330
    },
    {
      "epoch": 4.07185628742515,
      "grad_norm": 1.2782564163208008,
      "learning_rate": 0.0002,
      "loss": 0.2912,
      "step": 340
    },
    {
      "epoch": 4.191616766467066,
      "grad_norm": 1.0916423797607422,
      "learning_rate": 0.0002,
      "loss": 0.233,
      "step": 350
    },
    {
      "epoch": 4.311377245508982,
      "grad_norm": 0.8613762855529785,
      "learning_rate": 0.0002,
      "loss": 0.3058,
      "step": 360
    },
    {
      "epoch": 4.431137724550898,
      "grad_norm": 0.6293674111366272,
      "learning_rate": 0.0002,
      "loss": 0.2334,
      "step": 370
    },
    {
      "epoch": 4.550898203592815,
      "grad_norm": 1.6042566299438477,
      "learning_rate": 0.0002,
      "loss": 0.3287,
      "step": 380
    },
    {
      "epoch": 4.6706586826347305,
      "grad_norm": 0.8140411376953125,
      "learning_rate": 0.0002,
      "loss": 0.2372,
      "step": 390
    },
    {
      "epoch": 4.790419161676647,
      "grad_norm": 1.5365833044052124,
      "learning_rate": 0.0002,
      "loss": 0.3266,
      "step": 400
    },
    {
      "epoch": 4.910179640718563,
      "grad_norm": 0.9418448805809021,
      "learning_rate": 0.0002,
      "loss": 0.2513,
      "step": 410
    },
    {
      "epoch": 5.029940119760479,
      "grad_norm": 0.6695829033851624,
      "learning_rate": 0.0002,
      "loss": 0.2688,
      "step": 420
    },
    {
      "epoch": 5.149700598802395,
      "grad_norm": 0.628887414932251,
      "learning_rate": 0.0002,
      "loss": 0.2149,
      "step": 430
    },
    {
      "epoch": 5.269461077844311,
      "grad_norm": 0.964766263961792,
      "learning_rate": 0.0002,
      "loss": 0.2606,
      "step": 440
    },
    {
      "epoch": 5.389221556886228,
      "grad_norm": 0.5990360975265503,
      "learning_rate": 0.0002,
      "loss": 0.2364,
      "step": 450
    },
    {
      "epoch": 5.508982035928144,
      "grad_norm": 0.8189520835876465,
      "learning_rate": 0.0002,
      "loss": 0.2857,
      "step": 460
    },
    {
      "epoch": 5.62874251497006,
      "grad_norm": 0.5583224296569824,
      "learning_rate": 0.0002,
      "loss": 0.2414,
      "step": 470
    },
    {
      "epoch": 5.748502994011976,
      "grad_norm": 0.7695009708404541,
      "learning_rate": 0.0002,
      "loss": 0.2434,
      "step": 480
    },
    {
      "epoch": 5.868263473053892,
      "grad_norm": 0.3456665575504303,
      "learning_rate": 0.0002,
      "loss": 0.2597,
      "step": 490
    },
    {
      "epoch": 5.9880239520958085,
      "grad_norm": 0.7596808671951294,
      "learning_rate": 0.0002,
      "loss": 0.2983,
      "step": 500
    },
    {
      "epoch": 6.107784431137724,
      "grad_norm": 0.9513673782348633,
      "learning_rate": 0.0002,
      "loss": 0.2139,
      "step": 510
    },
    {
      "epoch": 6.227544910179641,
      "grad_norm": 1.0958881378173828,
      "learning_rate": 0.0002,
      "loss": 0.2211,
      "step": 520
    },
    {
      "epoch": 6.347305389221557,
      "grad_norm": 0.6882690787315369,
      "learning_rate": 0.0002,
      "loss": 0.2347,
      "step": 530
    },
    {
      "epoch": 6.467065868263473,
      "grad_norm": 1.0562934875488281,
      "learning_rate": 0.0002,
      "loss": 0.2276,
      "step": 540
    },
    {
      "epoch": 6.586826347305389,
      "grad_norm": 1.1535356044769287,
      "learning_rate": 0.0002,
      "loss": 0.2469,
      "step": 550
    },
    {
      "epoch": 6.706586826347305,
      "grad_norm": 0.9436424970626831,
      "learning_rate": 0.0002,
      "loss": 0.2713,
      "step": 560
    },
    {
      "epoch": 6.826347305389222,
      "grad_norm": 1.0283164978027344,
      "learning_rate": 0.0002,
      "loss": 0.2449,
      "step": 570
    },
    {
      "epoch": 6.946107784431137,
      "grad_norm": 1.3945902585983276,
      "learning_rate": 0.0002,
      "loss": 0.2193,
      "step": 580
    },
    {
      "epoch": 7.065868263473054,
      "grad_norm": 0.5662649869918823,
      "learning_rate": 0.0002,
      "loss": 0.2415,
      "step": 590
    },
    {
      "epoch": 7.18562874251497,
      "grad_norm": 0.4687662720680237,
      "learning_rate": 0.0002,
      "loss": 0.1792,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 100,
  "total_flos": 1753733775298560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}