{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 23.386537551879883,
      "learning_rate": 1e-05,
      "loss": 1.9167,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 10.429777145385742,
      "learning_rate": 9.894736842105264e-06,
      "loss": 1.3625,
      "step": 2
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 5.902014255523682,
      "learning_rate": 9.789473684210527e-06,
      "loss": 1.0434,
      "step": 3
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 3.8165690898895264,
      "learning_rate": 9.68421052631579e-06,
      "loss": 0.9712,
      "step": 4
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 2.740595579147339,
      "learning_rate": 9.578947368421054e-06,
      "loss": 0.8903,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 2.1069369316101074,
      "learning_rate": 9.473684210526315e-06,
      "loss": 0.8538,
      "step": 6
    },
    {
      "epoch": 0.07368421052631578,
      "grad_norm": 1.8523842096328735,
      "learning_rate": 9.36842105263158e-06,
      "loss": 0.9114,
      "step": 7
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 2.3119540214538574,
      "learning_rate": 9.263157894736842e-06,
      "loss": 0.8689,
      "step": 8
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 1.5400722026824951,
      "learning_rate": 9.157894736842105e-06,
      "loss": 0.8396,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.361148715019226,
      "learning_rate": 9.05263157894737e-06,
      "loss": 0.8039,
      "step": 10
    },
    {
      "epoch": 0.11578947368421053,
      "grad_norm": 1.372304081916809,
      "learning_rate": 8.947368421052632e-06,
      "loss": 0.7709,
      "step": 11
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.1872608661651611,
      "learning_rate": 8.842105263157895e-06,
      "loss": 0.6855,
      "step": 12
    },
    {
      "epoch": 0.1368421052631579,
      "grad_norm": 1.40359365940094,
      "learning_rate": 8.736842105263158e-06,
      "loss": 0.7116,
      "step": 13
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 1.5963401794433594,
      "learning_rate": 8.631578947368422e-06,
      "loss": 0.7409,
      "step": 14
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.281571388244629,
      "learning_rate": 8.526315789473685e-06,
      "loss": 0.7726,
      "step": 15
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 1.175497055053711,
      "learning_rate": 8.421052631578948e-06,
      "loss": 0.7512,
      "step": 16
    },
    {
      "epoch": 0.17894736842105263,
      "grad_norm": 1.2076319456100464,
      "learning_rate": 8.315789473684212e-06,
      "loss": 0.7557,
      "step": 17
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.5126558542251587,
      "learning_rate": 8.210526315789475e-06,
      "loss": 0.7726,
      "step": 18
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.0856505632400513,
      "learning_rate": 8.105263157894736e-06,
      "loss": 0.7186,
      "step": 19
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.5049703121185303,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7609,
      "step": 20
    },
    {
      "epoch": 0.22105263157894736,
      "grad_norm": 1.3303167819976807,
      "learning_rate": 7.894736842105265e-06,
      "loss": 0.7687,
      "step": 21
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 1.452388048171997,
      "learning_rate": 7.789473684210526e-06,
      "loss": 0.7491,
      "step": 22
    },
    {
      "epoch": 0.24210526315789474,
      "grad_norm": 1.1407661437988281,
      "learning_rate": 7.68421052631579e-06,
      "loss": 0.7664,
      "step": 23
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 1.1311556100845337,
      "learning_rate": 7.578947368421054e-06,
      "loss": 0.7121,
      "step": 24
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.2517611980438232,
      "learning_rate": 7.473684210526316e-06,
      "loss": 0.7488,
      "step": 25
    },
    {
      "epoch": 0.2736842105263158,
      "grad_norm": 1.3132089376449585,
      "learning_rate": 7.368421052631579e-06,
      "loss": 0.7614,
      "step": 26
    },
    {
      "epoch": 0.28421052631578947,
      "grad_norm": 1.1150217056274414,
      "learning_rate": 7.263157894736843e-06,
      "loss": 0.696,
      "step": 27
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 1.4403979778289795,
      "learning_rate": 7.157894736842106e-06,
      "loss": 0.6517,
      "step": 28
    },
    {
      "epoch": 0.30526315789473685,
      "grad_norm": 1.2276042699813843,
      "learning_rate": 7.052631578947369e-06,
      "loss": 0.7429,
      "step": 29
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.221534252166748,
      "learning_rate": 6.947368421052632e-06,
      "loss": 0.7094,
      "step": 30
    },
    {
      "epoch": 0.3263157894736842,
      "grad_norm": 1.1484534740447998,
      "learning_rate": 6.842105263157896e-06,
      "loss": 0.7411,
      "step": 31
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 1.2985154390335083,
      "learning_rate": 6.736842105263158e-06,
      "loss": 0.6867,
      "step": 32
    },
    {
      "epoch": 0.3473684210526316,
      "grad_norm": 1.177146077156067,
      "learning_rate": 6.631578947368421e-06,
      "loss": 0.683,
      "step": 33
    },
    {
      "epoch": 0.35789473684210527,
      "grad_norm": 1.4374433755874634,
      "learning_rate": 6.526315789473685e-06,
      "loss": 0.7092,
      "step": 34
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 1.2070837020874023,
      "learning_rate": 6.421052631578948e-06,
      "loss": 0.7503,
      "step": 35
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 1.227997899055481,
      "learning_rate": 6.31578947368421e-06,
      "loss": 0.7568,
      "step": 36
    },
    {
      "epoch": 0.3894736842105263,
      "grad_norm": 1.0868141651153564,
      "learning_rate": 6.2105263157894745e-06,
      "loss": 0.6607,
      "step": 37
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2848992347717285,
      "learning_rate": 6.105263157894738e-06,
      "loss": 0.7026,
      "step": 38
    },
    {
      "epoch": 0.4105263157894737,
      "grad_norm": 1.3217140436172485,
      "learning_rate": 6e-06,
      "loss": 0.737,
      "step": 39
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.161586046218872,
      "learning_rate": 5.8947368421052634e-06,
      "loss": 0.6788,
      "step": 40
    },
    {
      "epoch": 0.43157894736842106,
      "grad_norm": 1.046071171760559,
      "learning_rate": 5.789473684210527e-06,
      "loss": 0.6617,
      "step": 41
    },
    {
      "epoch": 0.4421052631578947,
      "grad_norm": 1.1674532890319824,
      "learning_rate": 5.68421052631579e-06,
      "loss": 0.7044,
      "step": 42
    },
    {
      "epoch": 0.45263157894736844,
      "grad_norm": 1.3029122352600098,
      "learning_rate": 5.578947368421052e-06,
      "loss": 0.6678,
      "step": 43
    },
    {
      "epoch": 0.4631578947368421,
      "grad_norm": 1.1042920351028442,
      "learning_rate": 5.4736842105263165e-06,
      "loss": 0.6793,
      "step": 44
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 1.1280156373977661,
      "learning_rate": 5.36842105263158e-06,
      "loss": 0.7237,
      "step": 45
    },
    {
      "epoch": 0.4842105263157895,
      "grad_norm": 1.0256831645965576,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.7494,
      "step": 46
    },
    {
      "epoch": 0.49473684210526314,
      "grad_norm": 1.6717668771743774,
      "learning_rate": 5.157894736842106e-06,
      "loss": 0.6832,
      "step": 47
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 1.1831214427947998,
      "learning_rate": 5.052631578947369e-06,
      "loss": 0.6373,
      "step": 48
    },
    {
      "epoch": 0.5157894736842106,
      "grad_norm": 1.233420729637146,
      "learning_rate": 4.947368421052632e-06,
      "loss": 0.5988,
      "step": 49
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.3069719076156616,
      "learning_rate": 4.842105263157895e-06,
      "loss": 0.6621,
      "step": 50
    },
    {
      "epoch": 0.5368421052631579,
      "grad_norm": 1.0840635299682617,
      "learning_rate": 4.736842105263158e-06,
      "loss": 0.6282,
      "step": 51
    },
    {
      "epoch": 0.5473684210526316,
      "grad_norm": 1.312338948249817,
      "learning_rate": 4.631578947368421e-06,
      "loss": 0.6492,
      "step": 52
    },
    {
      "epoch": 0.5578947368421052,
      "grad_norm": 1.155627727508545,
      "learning_rate": 4.526315789473685e-06,
      "loss": 0.6231,
      "step": 53
    },
    {
      "epoch": 0.5684210526315789,
      "grad_norm": 1.1554993391036987,
      "learning_rate": 4.4210526315789476e-06,
      "loss": 0.6046,
      "step": 54
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 1.149007797241211,
      "learning_rate": 4.315789473684211e-06,
      "loss": 0.6111,
      "step": 55
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 1.0409859418869019,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.6147,
      "step": 56
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.1579722166061401,
      "learning_rate": 4.105263157894737e-06,
      "loss": 0.5838,
      "step": 57
    },
    {
      "epoch": 0.6105263157894737,
      "grad_norm": 1.0128191709518433,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6059,
      "step": 58
    },
    {
      "epoch": 0.6210526315789474,
      "grad_norm": 1.2369976043701172,
      "learning_rate": 3.894736842105263e-06,
      "loss": 0.6007,
      "step": 59
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.4128843545913696,
      "learning_rate": 3.789473684210527e-06,
      "loss": 0.6647,
      "step": 60
    },
    {
      "epoch": 0.6421052631578947,
      "grad_norm": 1.320022702217102,
      "learning_rate": 3.6842105263157896e-06,
      "loss": 0.6834,
      "step": 61
    },
    {
      "epoch": 0.6526315789473685,
      "grad_norm": 0.996947169303894,
      "learning_rate": 3.578947368421053e-06,
      "loss": 0.5553,
      "step": 62
    },
    {
      "epoch": 0.6631578947368421,
      "grad_norm": 1.0932636260986328,
      "learning_rate": 3.473684210526316e-06,
      "loss": 0.5997,
      "step": 63
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 1.1183348894119263,
      "learning_rate": 3.368421052631579e-06,
      "loss": 0.58,
      "step": 64
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 1.2177517414093018,
      "learning_rate": 3.2631578947368423e-06,
      "loss": 0.6384,
      "step": 65
    },
    {
      "epoch": 0.6947368421052632,
      "grad_norm": 1.2820733785629272,
      "learning_rate": 3.157894736842105e-06,
      "loss": 0.6548,
      "step": 66
    },
    {
      "epoch": 0.7052631578947368,
      "grad_norm": 1.27961003780365,
      "learning_rate": 3.052631578947369e-06,
      "loss": 0.6085,
      "step": 67
    },
    {
      "epoch": 0.7157894736842105,
      "grad_norm": 1.1323752403259277,
      "learning_rate": 2.9473684210526317e-06,
      "loss": 0.6521,
      "step": 68
    },
    {
      "epoch": 0.7263157894736842,
      "grad_norm": 1.0661325454711914,
      "learning_rate": 2.842105263157895e-06,
      "loss": 0.6587,
      "step": 69
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1.112278699874878,
      "learning_rate": 2.7368421052631583e-06,
      "loss": 0.5834,
      "step": 70
    },
    {
      "epoch": 0.7473684210526316,
      "grad_norm": 1.2987736463546753,
      "learning_rate": 2.631578947368421e-06,
      "loss": 0.6459,
      "step": 71
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 1.196009874343872,
      "learning_rate": 2.5263157894736844e-06,
      "loss": 0.587,
      "step": 72
    },
    {
      "epoch": 0.7684210526315789,
      "grad_norm": 1.2561204433441162,
      "learning_rate": 2.4210526315789477e-06,
      "loss": 0.5874,
      "step": 73
    },
    {
      "epoch": 0.7789473684210526,
      "grad_norm": 1.0731667280197144,
      "learning_rate": 2.3157894736842105e-06,
      "loss": 0.6109,
      "step": 74
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 1.1367136240005493,
      "learning_rate": 2.2105263157894738e-06,
      "loss": 0.6368,
      "step": 75
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1752535104751587,
      "learning_rate": 2.105263157894737e-06,
      "loss": 0.6562,
      "step": 76
    },
    {
      "epoch": 0.8105263157894737,
      "grad_norm": 1.4213778972625732,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6511,
      "step": 77
    },
    {
      "epoch": 0.8210526315789474,
      "grad_norm": 1.342801570892334,
      "learning_rate": 1.8947368421052634e-06,
      "loss": 0.6833,
      "step": 78
    },
    {
      "epoch": 0.8315789473684211,
      "grad_norm": 0.9640871286392212,
      "learning_rate": 1.7894736842105265e-06,
      "loss": 0.5962,
      "step": 79
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.0870826244354248,
      "learning_rate": 1.6842105263157895e-06,
      "loss": 0.6084,
      "step": 80
    },
    {
      "epoch": 0.8526315789473684,
      "grad_norm": 1.0977897644042969,
      "learning_rate": 1.5789473684210526e-06,
      "loss": 0.6475,
      "step": 81
    },
    {
      "epoch": 0.8631578947368421,
      "grad_norm": 1.0268280506134033,
      "learning_rate": 1.4736842105263159e-06,
      "loss": 0.6048,
      "step": 82
    },
    {
      "epoch": 0.8736842105263158,
      "grad_norm": 1.1313055753707886,
      "learning_rate": 1.3684210526315791e-06,
      "loss": 0.6514,
      "step": 83
    },
    {
      "epoch": 0.8842105263157894,
      "grad_norm": 1.0519204139709473,
      "learning_rate": 1.2631578947368422e-06,
      "loss": 0.5872,
      "step": 84
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.9330918788909912,
      "learning_rate": 1.1578947368421053e-06,
      "loss": 0.568,
      "step": 85
    },
    {
      "epoch": 0.9052631578947369,
      "grad_norm": 0.9565713405609131,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 0.5445,
      "step": 86
    },
    {
      "epoch": 0.9157894736842105,
      "grad_norm": 1.0495901107788086,
      "learning_rate": 9.473684210526317e-07,
      "loss": 0.5917,
      "step": 87
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 0.9997472167015076,
      "learning_rate": 8.421052631578948e-07,
      "loss": 0.5896,
      "step": 88
    },
    {
      "epoch": 0.9368421052631579,
      "grad_norm": 1.1609445810317993,
      "learning_rate": 7.368421052631579e-07,
      "loss": 0.5559,
      "step": 89
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 1.0440585613250732,
      "learning_rate": 6.315789473684211e-07,
      "loss": 0.6345,
      "step": 90
    },
    {
      "epoch": 0.9578947368421052,
      "grad_norm": 1.073056697845459,
      "learning_rate": 5.263157894736843e-07,
      "loss": 0.6147,
      "step": 91
    },
    {
      "epoch": 0.968421052631579,
      "grad_norm": 1.022722601890564,
      "learning_rate": 4.210526315789474e-07,
      "loss": 0.6041,
      "step": 92
    },
    {
      "epoch": 0.9789473684210527,
      "grad_norm": 0.9993295073509216,
      "learning_rate": 3.1578947368421055e-07,
      "loss": 0.5827,
      "step": 93
    },
    {
      "epoch": 0.9894736842105263,
      "grad_norm": 1.5678324699401855,
      "learning_rate": 2.105263157894737e-07,
      "loss": 0.5515,
      "step": 94
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1239935159683228,
      "learning_rate": 1.0526315789473685e-07,
      "loss": 0.5996,
      "step": 95
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 9.28204549301207e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}