{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.724309642372114,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014486192847442281,
      "grad_norm": 1142.723876953125,
      "learning_rate": 5e-05,
      "loss": 366.0216,
      "step": 1
    },
    {
      "epoch": 0.014486192847442281,
      "eval_loss": 11.197284698486328,
      "eval_runtime": 41.2659,
      "eval_samples_per_second": 11.268,
      "eval_steps_per_second": 2.835,
      "step": 1
    },
    {
      "epoch": 0.028972385694884563,
      "grad_norm": 1126.6475830078125,
      "learning_rate": 0.0001,
      "loss": 347.0512,
      "step": 2
    },
    {
      "epoch": 0.04345857854232685,
      "grad_norm": 1244.7637939453125,
      "learning_rate": 9.989294616193017e-05,
      "loss": 333.4102,
      "step": 3
    },
    {
      "epoch": 0.057944771389769126,
      "grad_norm": 860.9097290039062,
      "learning_rate": 9.957224306869053e-05,
      "loss": 176.127,
      "step": 4
    },
    {
      "epoch": 0.0724309642372114,
      "grad_norm": 2220.339599609375,
      "learning_rate": 9.903926402016153e-05,
      "loss": 224.2955,
      "step": 5
    },
    {
      "epoch": 0.0869171570846537,
      "grad_norm": 2301.009033203125,
      "learning_rate": 9.829629131445342e-05,
      "loss": 208.5273,
      "step": 6
    },
    {
      "epoch": 0.10140334993209597,
      "grad_norm": 852.5401611328125,
      "learning_rate": 9.73465064747553e-05,
      "loss": 146.1845,
      "step": 7
    },
    {
      "epoch": 0.11588954277953825,
      "grad_norm": 379.1105651855469,
      "learning_rate": 9.619397662556435e-05,
      "loss": 109.2204,
      "step": 8
    },
    {
      "epoch": 0.13037573562698054,
      "grad_norm": 428.03802490234375,
      "learning_rate": 9.484363707663442e-05,
      "loss": 90.4438,
      "step": 9
    },
    {
      "epoch": 0.1448619284744228,
      "grad_norm": 516.3211669921875,
      "learning_rate": 9.330127018922194e-05,
      "loss": 93.6263,
      "step": 10
    },
    {
      "epoch": 0.1593481213218651,
      "grad_norm": 312.0606689453125,
      "learning_rate": 9.157348061512727e-05,
      "loss": 73.8311,
      "step": 11
    },
    {
      "epoch": 0.1738343141693074,
      "grad_norm": 232.24649047851562,
      "learning_rate": 8.966766701456177e-05,
      "loss": 62.2049,
      "step": 12
    },
    {
      "epoch": 0.18832050701674966,
      "grad_norm": 209.9749298095703,
      "learning_rate": 8.759199037394887e-05,
      "loss": 53.5616,
      "step": 13
    },
    {
      "epoch": 0.18832050701674966,
      "eval_loss": 1.432969570159912,
      "eval_runtime": 41.3466,
      "eval_samples_per_second": 11.246,
      "eval_steps_per_second": 2.83,
      "step": 13
    },
    {
      "epoch": 0.20280669986419195,
      "grad_norm": 227.82803344726562,
      "learning_rate": 8.535533905932738e-05,
      "loss": 45.4463,
      "step": 14
    },
    {
      "epoch": 0.2172928927116342,
      "grad_norm": 233.84213256835938,
      "learning_rate": 8.296729075500344e-05,
      "loss": 40.7913,
      "step": 15
    },
    {
      "epoch": 0.2317790855590765,
      "grad_norm": 241.74923706054688,
      "learning_rate": 8.043807145043604e-05,
      "loss": 36.8332,
      "step": 16
    },
    {
      "epoch": 0.2462652784065188,
      "grad_norm": 273.61724853515625,
      "learning_rate": 7.777851165098012e-05,
      "loss": 33.5054,
      "step": 17
    },
    {
      "epoch": 0.2607514712539611,
      "grad_norm": 336.7424011230469,
      "learning_rate": 7.500000000000001e-05,
      "loss": 26.3073,
      "step": 18
    },
    {
      "epoch": 0.2752376641014033,
      "grad_norm": 398.2518005371094,
      "learning_rate": 7.211443451095007e-05,
      "loss": 29.1703,
      "step": 19
    },
    {
      "epoch": 0.2897238569488456,
      "grad_norm": 263.69000244140625,
      "learning_rate": 6.91341716182545e-05,
      "loss": 25.753,
      "step": 20
    },
    {
      "epoch": 0.3042100497962879,
      "grad_norm": 140.5085906982422,
      "learning_rate": 6.607197326515808e-05,
      "loss": 24.2245,
      "step": 21
    },
    {
      "epoch": 0.3186962426437302,
      "grad_norm": 126.79087829589844,
      "learning_rate": 6.294095225512603e-05,
      "loss": 20.9214,
      "step": 22
    },
    {
      "epoch": 0.3331824354911725,
      "grad_norm": 126.19627380371094,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 19.3473,
      "step": 23
    },
    {
      "epoch": 0.3476686283386148,
      "grad_norm": 218.7227325439453,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 23.4087,
      "step": 24
    },
    {
      "epoch": 0.362154821186057,
      "grad_norm": 117.1246566772461,
      "learning_rate": 5.327015646150716e-05,
      "loss": 18.8893,
      "step": 25
    },
    {
      "epoch": 0.3766410140334993,
      "grad_norm": 319.6368103027344,
      "learning_rate": 5e-05,
      "loss": 21.5772,
      "step": 26
    },
    {
      "epoch": 0.3766410140334993,
      "eval_loss": 0.5946769714355469,
      "eval_runtime": 41.3369,
      "eval_samples_per_second": 11.249,
      "eval_steps_per_second": 2.83,
      "step": 26
    },
    {
      "epoch": 0.3911272068809416,
      "grad_norm": 149.88087463378906,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 21.5878,
      "step": 27
    },
    {
      "epoch": 0.4056133997283839,
      "grad_norm": 119.75304412841797,
      "learning_rate": 4.347369038899744e-05,
      "loss": 21.2073,
      "step": 28
    },
    {
      "epoch": 0.4200995925758262,
      "grad_norm": 320.1707763671875,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 17.1099,
      "step": 29
    },
    {
      "epoch": 0.4345857854232684,
      "grad_norm": 128.20896911621094,
      "learning_rate": 3.705904774487396e-05,
      "loss": 16.6537,
      "step": 30
    },
    {
      "epoch": 0.4490719782707107,
      "grad_norm": 181.88687133789062,
      "learning_rate": 3.392802673484193e-05,
      "loss": 19.7434,
      "step": 31
    },
    {
      "epoch": 0.463558171118153,
      "grad_norm": 182.82069396972656,
      "learning_rate": 3.086582838174551e-05,
      "loss": 20.6309,
      "step": 32
    },
    {
      "epoch": 0.4780443639655953,
      "grad_norm": 173.1058807373047,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 18.576,
      "step": 33
    },
    {
      "epoch": 0.4925305568130376,
      "grad_norm": 266.4740295410156,
      "learning_rate": 2.500000000000001e-05,
      "loss": 17.5184,
      "step": 34
    },
    {
      "epoch": 0.5070167496604798,
      "grad_norm": 405.75341796875,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 15.6519,
      "step": 35
    },
    {
      "epoch": 0.5215029425079222,
      "grad_norm": 356.82489013671875,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 17.717,
      "step": 36
    },
    {
      "epoch": 0.5359891353553644,
      "grad_norm": 91.6025619506836,
      "learning_rate": 1.703270924499656e-05,
      "loss": 17.8593,
      "step": 37
    },
    {
      "epoch": 0.5504753282028066,
      "grad_norm": 138.64764404296875,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 15.968,
      "step": 38
    },
    {
      "epoch": 0.564961521050249,
      "grad_norm": 87.49166107177734,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 15.2474,
      "step": 39
    },
    {
      "epoch": 0.564961521050249,
      "eval_loss": 0.500713586807251,
      "eval_runtime": 41.3261,
      "eval_samples_per_second": 11.252,
      "eval_steps_per_second": 2.831,
      "step": 39
    },
    {
      "epoch": 0.5794477138976912,
      "grad_norm": 100.62445068359375,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 17.5808,
      "step": 40
    },
    {
      "epoch": 0.5939339067451336,
      "grad_norm": 108.46626281738281,
      "learning_rate": 8.426519384872733e-06,
      "loss": 13.7374,
      "step": 41
    },
    {
      "epoch": 0.6084200995925758,
      "grad_norm": 85.36103820800781,
      "learning_rate": 6.698729810778065e-06,
      "loss": 17.013,
      "step": 42
    },
    {
      "epoch": 0.6229062924400182,
      "grad_norm": 83.11396789550781,
      "learning_rate": 5.156362923365588e-06,
      "loss": 13.9914,
      "step": 43
    },
    {
      "epoch": 0.6373924852874604,
      "grad_norm": 93.9541015625,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 16.1954,
      "step": 44
    },
    {
      "epoch": 0.6518786781349026,
      "grad_norm": 102.81454467773438,
      "learning_rate": 2.653493525244721e-06,
      "loss": 14.4745,
      "step": 45
    },
    {
      "epoch": 0.666364870982345,
      "grad_norm": 111.78718566894531,
      "learning_rate": 1.70370868554659e-06,
      "loss": 15.9655,
      "step": 46
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 186.56785583496094,
      "learning_rate": 9.607359798384785e-07,
      "loss": 14.6932,
      "step": 47
    },
    {
      "epoch": 0.6953372566772296,
      "grad_norm": 69.18374633789062,
      "learning_rate": 4.277569313094809e-07,
      "loss": 13.9869,
      "step": 48
    },
    {
      "epoch": 0.7098234495246718,
      "grad_norm": 95.9025650024414,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 16.5867,
      "step": 49
    },
    {
      "epoch": 0.724309642372114,
      "grad_norm": 103.1650390625,
      "learning_rate": 0.0,
      "loss": 13.8776,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1250278137331712e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}