{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 4.817715644836426,
      "learning_rate": 0.0,
      "loss": 2.4596,
      "step": 1
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.894565105438232,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.468,
      "step": 2
    },
    {
      "epoch": 0.3,
      "grad_norm": 4.599151134490967,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.4369,
      "step": 3
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.634383678436279,
      "learning_rate": 0.0001,
      "loss": 2.4219,
      "step": 4
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.405484676361084,
      "learning_rate": 9.997377845227576e-05,
      "loss": 2.3884,
      "step": 5
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.227508068084717,
      "learning_rate": 9.989514131188559e-05,
      "loss": 2.3539,
      "step": 6
    },
    {
      "epoch": 0.7,
      "grad_norm": 3.989192247390747,
      "learning_rate": 9.97641710583307e-05,
      "loss": 2.3132,
      "step": 7
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.904679775238037,
      "learning_rate": 9.958100506132127e-05,
      "loss": 2.2919,
      "step": 8
    },
    {
      "epoch": 0.9,
      "grad_norm": 3.8267431259155273,
      "learning_rate": 9.934583543669453e-05,
      "loss": 2.2709,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.6127519607543945,
      "learning_rate": 9.905890884491195e-05,
      "loss": 2.2313,
      "step": 10
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1856,
      "eval_loss": 2.2107839584350586,
      "eval_runtime": 18.3869,
      "eval_samples_per_second": 543.864,
      "eval_steps_per_second": 0.109,
      "step": 10
    },
    {
      "epoch": 1.1,
      "grad_norm": 3.6324033737182617,
      "learning_rate": 9.872052623234632e-05,
      "loss": 2.2162,
      "step": 11
    },
    {
      "epoch": 1.2,
      "grad_norm": 3.4379923343658447,
      "learning_rate": 9.833104251563056e-05,
      "loss": 2.1835,
      "step": 12
    },
    {
      "epoch": 1.3,
      "grad_norm": 3.394665479660034,
      "learning_rate": 9.789086620939936e-05,
      "loss": 2.1677,
      "step": 13
    },
    {
      "epoch": 1.4,
      "grad_norm": 3.3317911624908447,
      "learning_rate": 9.740045899781352e-05,
      "loss": 2.1358,
      "step": 14
    },
    {
      "epoch": 1.5,
      "grad_norm": 3.2182583808898926,
      "learning_rate": 9.686033525031719e-05,
      "loss": 2.1124,
      "step": 15
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.1929690837860107,
      "learning_rate": 9.627106148213522e-05,
      "loss": 2.0794,
      "step": 16
    },
    {
      "epoch": 1.7,
      "grad_norm": 3.1744496822357178,
      "learning_rate": 9.563325576007701e-05,
      "loss": 2.0664,
      "step": 17
    },
    {
      "epoch": 1.8,
      "grad_norm": 3.2177734375,
      "learning_rate": 9.494758705426978e-05,
      "loss": 2.0374,
      "step": 18
    },
    {
      "epoch": 1.9,
      "grad_norm": 3.143730640411377,
      "learning_rate": 9.421477453650118e-05,
      "loss": 2.0087,
      "step": 19
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.086007595062256,
      "learning_rate": 9.343558682590756e-05,
      "loss": 1.9995,
      "step": 20
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3659,
      "eval_loss": 1.9728946685791016,
      "eval_runtime": 18.2892,
      "eval_samples_per_second": 546.77,
      "eval_steps_per_second": 0.109,
      "step": 20
    },
    {
      "epoch": 2.1,
      "grad_norm": 3.093388795852661,
      "learning_rate": 9.261084118279847e-05,
      "loss": 1.9768,
      "step": 21
    },
    {
      "epoch": 2.2,
      "grad_norm": 3.0235588550567627,
      "learning_rate": 9.174140265146356e-05,
      "loss": 1.9573,
      "step": 22
    },
    {
      "epoch": 2.3,
      "grad_norm": 3.054340362548828,
      "learning_rate": 9.082818315286055e-05,
      "loss": 1.9279,
      "step": 23
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.977816104888916,
      "learning_rate": 8.987214052813604e-05,
      "loss": 1.9009,
      "step": 24
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.974107027053833,
      "learning_rate": 8.887427753398248e-05,
      "loss": 1.8879,
      "step": 25
    },
    {
      "epoch": 2.6,
      "grad_norm": 2.926490545272827,
      "learning_rate": 8.783564079088477e-05,
      "loss": 1.8672,
      "step": 26
    },
    {
      "epoch": 2.7,
      "grad_norm": 2.8999850749969482,
      "learning_rate": 8.675731968536002e-05,
      "loss": 1.8563,
      "step": 27
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.8928842544555664,
      "learning_rate": 8.564044522734147e-05,
      "loss": 1.832,
      "step": 28
    },
    {
      "epoch": 2.9,
      "grad_norm": 2.8881161212921143,
      "learning_rate": 8.448618886390522e-05,
      "loss": 1.8051,
      "step": 29
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.852555274963379,
      "learning_rate": 8.329576125058406e-05,
      "loss": 1.7828,
      "step": 30
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5687,
      "eval_loss": 1.7709296941757202,
      "eval_runtime": 18.5173,
      "eval_samples_per_second": 540.036,
      "eval_steps_per_second": 0.108,
      "step": 30
    },
    {
      "epoch": 3.1,
      "grad_norm": 2.829819679260254,
      "learning_rate": 8.2070410981557e-05,
      "loss": 1.7684,
      "step": 31
    },
    {
      "epoch": 3.2,
      "grad_norm": 2.830519437789917,
      "learning_rate": 8.081142328004637e-05,
      "loss": 1.7467,
      "step": 32
    },
    {
      "epoch": 3.3,
      "grad_norm": 2.827852964401245,
      "learning_rate": 7.952011865029614e-05,
      "loss": 1.7348,
      "step": 33
    },
    {
      "epoch": 3.4,
      "grad_norm": 2.8194892406463623,
      "learning_rate": 7.819785149254532e-05,
      "loss": 1.7118,
      "step": 34
    },
    {
      "epoch": 3.5,
      "grad_norm": 2.788273334503174,
      "learning_rate": 7.68460086824492e-05,
      "loss": 1.6999,
      "step": 35
    },
    {
      "epoch": 3.6,
      "grad_norm": 2.770765542984009,
      "learning_rate": 7.546600811643816e-05,
      "loss": 1.6856,
      "step": 36
    },
    {
      "epoch": 3.7,
      "grad_norm": 2.784775972366333,
      "learning_rate": 7.405929722454026e-05,
      "loss": 1.6736,
      "step": 37
    },
    {
      "epoch": 3.8,
      "grad_norm": 2.7415084838867188,
      "learning_rate": 7.262735145222696e-05,
      "loss": 1.6511,
      "step": 38
    },
    {
      "epoch": 3.9,
      "grad_norm": 2.702268123626709,
      "learning_rate": 7.117167271287453e-05,
      "loss": 1.6376,
      "step": 39
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.713175058364868,
      "learning_rate": 6.969378781246436e-05,
      "loss": 1.6164,
      "step": 40
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7026,
      "eval_loss": 1.6059929132461548,
      "eval_runtime": 19.2121,
      "eval_samples_per_second": 520.506,
      "eval_steps_per_second": 0.104,
      "step": 40
    },
    {
      "epoch": 4.1,
      "grad_norm": 2.7123563289642334,
      "learning_rate": 6.819524684817438e-05,
      "loss": 1.6115,
      "step": 41
    },
    {
      "epoch": 4.2,
      "grad_norm": 2.6732938289642334,
      "learning_rate": 6.667762158254104e-05,
      "loss": 1.5974,
      "step": 42
    },
    {
      "epoch": 4.3,
      "grad_norm": 2.6421256065368652,
      "learning_rate": 6.514250379489753e-05,
      "loss": 1.5815,
      "step": 43
    },
    {
      "epoch": 4.4,
      "grad_norm": 2.6315958499908447,
      "learning_rate": 6.359150361181715e-05,
      "loss": 1.5605,
      "step": 44
    },
    {
      "epoch": 4.5,
      "grad_norm": 2.6411125659942627,
      "learning_rate": 6.202624781831268e-05,
      "loss": 1.547,
      "step": 45
    },
    {
      "epoch": 4.6,
      "grad_norm": 2.5971579551696777,
      "learning_rate": 6.044837815156377e-05,
      "loss": 1.5264,
      "step": 46
    },
    {
      "epoch": 4.7,
      "grad_norm": 2.60679030418396,
      "learning_rate": 5.885954957896115e-05,
      "loss": 1.5204,
      "step": 47
    },
    {
      "epoch": 4.8,
      "grad_norm": 2.6132194995880127,
      "learning_rate": 5.726142856227452e-05,
      "loss": 1.5138,
      "step": 48
    },
    {
      "epoch": 4.9,
      "grad_norm": 2.5883078575134277,
      "learning_rate": 5.565569130976422e-05,
      "loss": 1.5027,
      "step": 49
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.5475687980651855,
      "learning_rate": 5.4044022018070214e-05,
      "loss": 1.4917,
      "step": 50
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7804,
      "eval_loss": 1.4809952974319458,
      "eval_runtime": 19.4674,
      "eval_samples_per_second": 513.679,
      "eval_steps_per_second": 0.103,
      "step": 50
    },
    {
      "epoch": 5.1,
      "grad_norm": 2.5411295890808105,
      "learning_rate": 5.242811110572242e-05,
      "loss": 1.4768,
      "step": 51
    },
    {
      "epoch": 5.2,
      "grad_norm": 2.529762029647827,
      "learning_rate": 5.080965344012508e-05,
      "loss": 1.4711,
      "step": 52
    },
    {
      "epoch": 5.3,
      "grad_norm": 2.547415256500244,
      "learning_rate": 4.919034655987493e-05,
      "loss": 1.4621,
      "step": 53
    },
    {
      "epoch": 5.4,
      "grad_norm": 2.500286817550659,
      "learning_rate": 4.7571888894277604e-05,
      "loss": 1.4553,
      "step": 54
    },
    {
      "epoch": 5.5,
      "grad_norm": 2.536651611328125,
      "learning_rate": 4.59559779819298e-05,
      "loss": 1.4408,
      "step": 55
    },
    {
      "epoch": 5.6,
      "grad_norm": 2.4803407192230225,
      "learning_rate": 4.434430869023579e-05,
      "loss": 1.4245,
      "step": 56
    },
    {
      "epoch": 5.7,
      "grad_norm": 2.4855239391326904,
      "learning_rate": 4.27385714377255e-05,
      "loss": 1.4253,
      "step": 57
    },
    {
      "epoch": 5.8,
      "grad_norm": 2.4846363067626953,
      "learning_rate": 4.114045042103887e-05,
      "loss": 1.4154,
      "step": 58
    },
    {
      "epoch": 5.9,
      "grad_norm": 2.5024306774139404,
      "learning_rate": 3.955162184843625e-05,
      "loss": 1.4044,
      "step": 59
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.460845470428467,
      "learning_rate": 3.7973752181687335e-05,
      "loss": 1.3896,
      "step": 60
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8226,
      "eval_loss": 1.393266201019287,
      "eval_runtime": 19.4581,
      "eval_samples_per_second": 513.924,
      "eval_steps_per_second": 0.103,
      "step": 60
    },
    {
      "epoch": 6.1,
      "grad_norm": 2.4671754837036133,
      "learning_rate": 3.640849638818286e-05,
      "loss": 1.3983,
      "step": 61
    },
    {
      "epoch": 6.2,
      "grad_norm": 2.4589459896087646,
      "learning_rate": 3.4857496205102474e-05,
      "loss": 1.3897,
      "step": 62
    },
    {
      "epoch": 6.3,
      "grad_norm": 2.431168794631958,
      "learning_rate": 3.332237841745898e-05,
      "loss": 1.3805,
      "step": 63
    },
    {
      "epoch": 6.4,
      "grad_norm": 2.405449390411377,
      "learning_rate": 3.180475315182563e-05,
      "loss": 1.3686,
      "step": 64
    },
    {
      "epoch": 6.5,
      "grad_norm": 2.4028396606445312,
      "learning_rate": 3.0306212187535653e-05,
      "loss": 1.3594,
      "step": 65
    },
    {
      "epoch": 6.6,
      "grad_norm": 2.452636480331421,
      "learning_rate": 2.882832728712551e-05,
      "loss": 1.3544,
      "step": 66
    },
    {
      "epoch": 6.7,
      "grad_norm": 2.3963868618011475,
      "learning_rate": 2.737264854777306e-05,
      "loss": 1.3554,
      "step": 67
    },
    {
      "epoch": 6.8,
      "grad_norm": 2.3924241065979004,
      "learning_rate": 2.5940702775459747e-05,
      "loss": 1.3509,
      "step": 68
    },
    {
      "epoch": 6.9,
      "grad_norm": 2.4093081951141357,
      "learning_rate": 2.4533991883561868e-05,
      "loss": 1.3379,
      "step": 69
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.374818801879883,
      "learning_rate": 2.315399131755081e-05,
      "loss": 1.3421,
      "step": 70
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8459,
      "eval_loss": 1.337928295135498,
      "eval_runtime": 19.5166,
      "eval_samples_per_second": 512.386,
      "eval_steps_per_second": 0.102,
      "step": 70
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}