{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 22,
  "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": 13.541594505310059,
      "learning_rate": 1e-05,
      "loss": 1.687255859375,
      "step": 1
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 270.9620056152344,
      "learning_rate": 9.994336695915041e-06,
      "loss": 4.320972442626953,
      "step": 2
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 8.045546531677246,
      "learning_rate": 9.977359612865424e-06,
      "loss": 0.990966796875,
      "step": 3
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 4.051703453063965,
      "learning_rate": 9.949107209404664e-06,
      "loss": 1.09613037109375,
      "step": 4
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 2.503697633743286,
      "learning_rate": 9.909643486313533e-06,
      "loss": 1.016815185546875,
      "step": 5
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 3.1819581985473633,
      "learning_rate": 9.859057841617709e-06,
      "loss": 0.91766357421875,
      "step": 6
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.810927391052246,
      "learning_rate": 9.797464868072489e-06,
      "loss": 0.9587249755859375,
      "step": 7
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.6619356870651245,
      "learning_rate": 9.725004093573343e-06,
      "loss": 0.80902099609375,
      "step": 8
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 2.2837491035461426,
      "learning_rate": 9.641839665080363e-06,
      "loss": 0.8079757690429688,
      "step": 9
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 3.019440174102783,
      "learning_rate": 9.548159976772593e-06,
      "loss": 0.8288116455078125,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.1921716928482056,
      "learning_rate": 9.444177243274619e-06,
      "loss": 0.6759376525878906,
      "step": 11
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 2.224130153656006,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.54034423828125,
      "step": 12
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 1.386547327041626,
      "learning_rate": 9.206267664155906e-06,
      "loss": 0.49675750732421875,
      "step": 13
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.4452524185180664,
      "learning_rate": 9.07287976025168e-06,
      "loss": 0.4326019287109375,
      "step": 14
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 2.8639578819274902,
      "learning_rate": 8.930265473713939e-06,
      "loss": 0.587005615234375,
      "step": 15
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.1509618759155273,
      "learning_rate": 8.778747871771293e-06,
      "loss": 0.49512481689453125,
      "step": 16
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 1.06486177444458,
      "learning_rate": 8.61867019052535e-06,
      "loss": 0.6640739440917969,
      "step": 17
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.9991989731788635,
      "learning_rate": 8.450395057410561e-06,
      "loss": 0.437957763671875,
      "step": 18
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.7819029092788696,
      "learning_rate": 8.274303669726427e-06,
      "loss": 0.5671710968017578,
      "step": 19
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.8972281813621521,
      "learning_rate": 8.090794931103026e-06,
      "loss": 0.3094291687011719,
      "step": 20
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.8230551481246948,
      "learning_rate": 7.900284547855992e-06,
      "loss": 0.42014312744140625,
      "step": 21
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9112458229064941,
      "learning_rate": 7.703204087277989e-06,
      "loss": 0.3252525329589844,
      "step": 22
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.59442138671875,
      "eval_runtime": 13.685,
      "eval_samples_per_second": 0.365,
      "eval_steps_per_second": 0.073,
      "step": 22
    },
    {
      "checkpoint_runtime": 130.4115
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 1.6123707294464111,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.5166397094726562,
      "step": 23
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.3553637266159058,
      "learning_rate": 7.291132608637053e-06,
      "loss": 0.3297233581542969,
      "step": 24
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 1.3093994855880737,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 0.49069786071777344,
      "step": 25
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.996208667755127,
      "learning_rate": 6.858312278301638e-06,
      "loss": 0.2602996826171875,
      "step": 26
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.8691992163658142,
      "learning_rate": 6.635339816587109e-06,
      "loss": 0.09621810913085938,
      "step": 27
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.73832106590271,
      "learning_rate": 6.408662784207149e-06,
      "loss": 0.2693767547607422,
      "step": 28
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.9352995753288269,
      "learning_rate": 6.178794677547138e-06,
      "loss": 0.2981605529785156,
      "step": 29
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.6079849004745483,
      "learning_rate": 5.946256221802052e-06,
      "loss": 0.26114463806152344,
      "step": 30
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 1.1613916158676147,
      "learning_rate": 5.711574191366427e-06,
      "loss": 0.3663311004638672,
      "step": 31
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.0265836715698242,
      "learning_rate": 5.475280216520913e-06,
      "loss": 0.13217544555664062,
      "step": 32
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.9267441630363464,
      "learning_rate": 5.237909579118713e-06,
      "loss": 0.3060760498046875,
      "step": 33
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.6758596301078796,
      "learning_rate": 5e-06,
      "loss": 0.053920745849609375,
      "step": 34
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.6371091604232788,
      "learning_rate": 4.762090420881289e-06,
      "loss": 0.11317062377929688,
      "step": 35
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.6892620325088501,
      "learning_rate": 4.524719783479088e-06,
      "loss": 0.1634387969970703,
      "step": 36
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 1.267598032951355,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 0.1157989501953125,
      "step": 37
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.618965208530426,
      "learning_rate": 4.053743778197951e-06,
      "loss": 0.2590446472167969,
      "step": 38
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.8626583814620972,
      "learning_rate": 3.821205322452863e-06,
      "loss": 0.4122934341430664,
      "step": 39
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.5675498843193054,
      "learning_rate": 3.5913372157928515e-06,
      "loss": 0.18222999572753906,
      "step": 40
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 1.346577525138855,
      "learning_rate": 3.3646601834128924e-06,
      "loss": 0.36645030975341797,
      "step": 41
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.5783951282501221,
      "learning_rate": 3.141687721698363e-06,
      "loss": 0.19093704223632812,
      "step": 42
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.7677918672561646,
      "learning_rate": 2.9229249349905686e-06,
      "loss": 0.24652671813964844,
      "step": 43
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6522639393806458,
      "learning_rate": 2.708867391362948e-06,
      "loss": 0.13533401489257812,
      "step": 44
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.59344482421875,
      "eval_runtime": 4.3126,
      "eval_samples_per_second": 1.159,
      "eval_steps_per_second": 0.232,
      "step": 44
    },
    {
      "checkpoint_runtime": 134.2782
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 1.315116286277771,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.2724342346191406,
      "step": 45
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 0.5187699198722839,
      "learning_rate": 2.296795912722014e-06,
      "loss": 0.18209326267242432,
      "step": 46
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": 0.9916004538536072,
      "learning_rate": 2.09971545214401e-06,
      "loss": 0.2614755630493164,
      "step": 47
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.5112076997756958,
      "learning_rate": 1.9092050688969736e-06,
      "loss": 0.1507863998413086,
      "step": 48
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 0.3336804211139679,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 0.024288177490234375,
      "step": 49
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.40631377696990967,
      "learning_rate": 1.549604942589441e-06,
      "loss": 0.19109153747558594,
      "step": 50
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 0.8899633288383484,
      "learning_rate": 1.3813298094746491e-06,
      "loss": 0.17161941528320312,
      "step": 51
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.5578643679618835,
      "learning_rate": 1.2212521282287093e-06,
      "loss": 0.17924213409423828,
      "step": 52
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 1.057443618774414,
      "learning_rate": 1.0697345262860638e-06,
      "loss": 0.21059799194335938,
      "step": 53
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.6124624609947205,
      "learning_rate": 9.271202397483214e-07,
      "loss": 0.050838470458984375,
      "step": 54
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.5138548016548157,
      "learning_rate": 7.937323358440935e-07,
      "loss": 0.22317028045654297,
      "step": 55
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.5870931148529053,
      "learning_rate": 6.698729810778065e-07,
      "loss": 0.02097320556640625,
      "step": 56
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 0.47857600450515747,
      "learning_rate": 5.558227567253832e-07,
      "loss": 0.056339263916015625,
      "step": 57
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.4128285050392151,
      "learning_rate": 4.5184002322740784e-07,
      "loss": 0.10932445526123047,
      "step": 58
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 0.9088109135627747,
      "learning_rate": 3.581603349196372e-07,
      "loss": 0.04517364501953125,
      "step": 59
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5057564973831177,
      "learning_rate": 2.7499590642665773e-07,
      "loss": 0.19766902923583984,
      "step": 60
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 0.792408287525177,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 0.33954524993896484,
      "step": 61
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.47474050521850586,
      "learning_rate": 1.4094215838229176e-07,
      "loss": 0.12943077087402344,
      "step": 62
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 0.9088992476463318,
      "learning_rate": 9.035651368646647e-08,
      "loss": 0.3276538848876953,
      "step": 63
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.4451668858528137,
      "learning_rate": 5.089279059533658e-08,
      "loss": 0.1589193344116211,
      "step": 64
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.6257097721099854,
      "learning_rate": 2.264038713457706e-08,
      "loss": 0.2027444839477539,
      "step": 65
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4987045228481293,
      "learning_rate": 5.6633040849601865e-09,
      "loss": 0.09051704406738281,
      "step": 66
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.61431884765625,
      "eval_runtime": 4.3337,
      "eval_samples_per_second": 1.154,
      "eval_steps_per_second": 0.231,
      "step": 66
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 22,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.409622391826678e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}