{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 0,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 1.5525645017623901,
      "learning_rate": 0.0001,
      "loss": 2.999,
      "step": 1
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.48669666051864624,
      "learning_rate": 9.99433669591504e-05,
      "loss": 2.5352,
      "step": 2
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.520565390586853,
      "learning_rate": 9.977359612865423e-05,
      "loss": 2.5459,
      "step": 3
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.4194190502166748,
      "learning_rate": 9.949107209404665e-05,
      "loss": 2.3623,
      "step": 4
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.5773956775665283,
      "learning_rate": 9.909643486313533e-05,
      "loss": 2.3799,
      "step": 5
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.450801283121109,
      "learning_rate": 9.859057841617709e-05,
      "loss": 2.2041,
      "step": 6
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.38954564929008484,
      "learning_rate": 9.797464868072488e-05,
      "loss": 2.0898,
      "step": 7
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.38519182801246643,
      "learning_rate": 9.725004093573342e-05,
      "loss": 2.0986,
      "step": 8
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.4197673499584198,
      "learning_rate": 9.641839665080363e-05,
      "loss": 2.0859,
      "step": 9
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.34918734431266785,
      "learning_rate": 9.548159976772592e-05,
      "loss": 2.0674,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.47316649556159973,
      "learning_rate": 9.444177243274618e-05,
      "loss": 2.1445,
      "step": 11
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.3565642833709717,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.0186,
      "step": 12
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.41718024015426636,
      "learning_rate": 9.206267664155907e-05,
      "loss": 1.9092,
      "step": 13
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.3225971758365631,
      "learning_rate": 9.072879760251679e-05,
      "loss": 1.9336,
      "step": 14
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.4329506754875183,
      "learning_rate": 8.930265473713938e-05,
      "loss": 1.9658,
      "step": 15
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.34980306029319763,
      "learning_rate": 8.778747871771292e-05,
      "loss": 1.9233,
      "step": 16
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.35584837198257446,
      "learning_rate": 8.618670190525352e-05,
      "loss": 1.876,
      "step": 17
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.41015440225601196,
      "learning_rate": 8.450395057410561e-05,
      "loss": 1.8018,
      "step": 18
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.3842436969280243,
      "learning_rate": 8.274303669726426e-05,
      "loss": 1.9844,
      "step": 19
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.36047589778900146,
      "learning_rate": 8.090794931103026e-05,
      "loss": 1.7949,
      "step": 20
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.4712209701538086,
      "learning_rate": 7.900284547855991e-05,
      "loss": 1.9482,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.44793617725372314,
      "learning_rate": 7.703204087277988e-05,
      "loss": 1.959,
      "step": 22
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.4208018183708191,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.54,
      "step": 23
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.3980354368686676,
      "learning_rate": 7.291132608637052e-05,
      "loss": 1.4268,
      "step": 24
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.40800103545188904,
      "learning_rate": 7.077075065009433e-05,
      "loss": 1.5317,
      "step": 25
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.3763895630836487,
      "learning_rate": 6.858312278301637e-05,
      "loss": 1.4351,
      "step": 26
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.43810543417930603,
      "learning_rate": 6.635339816587109e-05,
      "loss": 1.5088,
      "step": 27
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.36717087030410767,
      "learning_rate": 6.408662784207149e-05,
      "loss": 1.2861,
      "step": 28
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.3974374234676361,
      "learning_rate": 6.178794677547137e-05,
      "loss": 1.2939,
      "step": 29
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.4624643623828888,
      "learning_rate": 5.946256221802051e-05,
      "loss": 1.2666,
      "step": 30
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.49110740423202515,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 1.2427,
      "step": 31
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.4905654191970825,
      "learning_rate": 5.475280216520913e-05,
      "loss": 1.375,
      "step": 32
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.5586603283882141,
      "learning_rate": 5.2379095791187124e-05,
      "loss": 1.2378,
      "step": 33
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.4647849500179291,
      "learning_rate": 5e-05,
      "loss": 1.2944,
      "step": 34
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.40533557534217834,
      "learning_rate": 4.762090420881289e-05,
      "loss": 1.2681,
      "step": 35
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.42181581258773804,
      "learning_rate": 4.5247197834790876e-05,
      "loss": 1.2778,
      "step": 36
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.524286150932312,
      "learning_rate": 4.288425808633575e-05,
      "loss": 1.2676,
      "step": 37
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.48165425658226013,
      "learning_rate": 4.0537437781979506e-05,
      "loss": 1.2117,
      "step": 38
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.46707984805107117,
      "learning_rate": 3.821205322452863e-05,
      "loss": 1.2158,
      "step": 39
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.5378795266151428,
      "learning_rate": 3.591337215792852e-05,
      "loss": 1.167,
      "step": 40
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.5202534794807434,
      "learning_rate": 3.364660183412892e-05,
      "loss": 1.2969,
      "step": 41
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.46007615327835083,
      "learning_rate": 3.141687721698363e-05,
      "loss": 1.2017,
      "step": 42
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.5994746088981628,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 1.374,
      "step": 43
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6511712670326233,
      "learning_rate": 2.708867391362948e-05,
      "loss": 1.3047,
      "step": 44
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.5085187554359436,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9595,
      "step": 45
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.4964281916618347,
      "learning_rate": 2.296795912722014e-05,
      "loss": 0.9155,
      "step": 46
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.5115947127342224,
      "learning_rate": 2.09971545214401e-05,
      "loss": 0.9626,
      "step": 47
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.5066834092140198,
      "learning_rate": 1.9092050688969738e-05,
      "loss": 0.9277,
      "step": 48
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.5653634071350098,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.9712,
      "step": 49
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.4669578969478607,
      "learning_rate": 1.549604942589441e-05,
      "loss": 0.7808,
      "step": 50
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 0.4711793065071106,
      "learning_rate": 1.3813298094746491e-05,
      "loss": 0.8389,
      "step": 51
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.5306926369667053,
      "learning_rate": 1.2212521282287092e-05,
      "loss": 0.7915,
      "step": 52
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 0.5232995748519897,
      "learning_rate": 1.0697345262860636e-05,
      "loss": 0.7629,
      "step": 53
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.5442014932632446,
      "learning_rate": 9.271202397483215e-06,
      "loss": 0.9722,
      "step": 54
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.6453394293785095,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.7639,
      "step": 55
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.599093496799469,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.9246,
      "step": 56
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.606338620185852,
      "learning_rate": 5.558227567253832e-06,
      "loss": 0.9175,
      "step": 57
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.6603699326515198,
      "learning_rate": 4.5184002322740785e-06,
      "loss": 0.9619,
      "step": 58
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 0.6807499527931213,
      "learning_rate": 3.581603349196372e-06,
      "loss": 0.9092,
      "step": 59
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.6307097673416138,
      "learning_rate": 2.7499590642665774e-06,
      "loss": 0.8828,
      "step": 60
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 0.6490936875343323,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.9277,
      "step": 61
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.6332418918609619,
      "learning_rate": 1.4094215838229176e-06,
      "loss": 0.8779,
      "step": 62
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 0.7066373229026794,
      "learning_rate": 9.035651368646648e-07,
      "loss": 1.0352,
      "step": 63
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.5728477835655212,
      "learning_rate": 5.089279059533658e-07,
      "loss": 0.9785,
      "step": 64
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.7507941722869873,
      "learning_rate": 2.2640387134577058e-07,
      "loss": 1.145,
      "step": 65
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7610505819320679,
      "learning_rate": 5.663304084960186e-08,
      "loss": 1.0835,
      "step": 66
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6587551221415936e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}