{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 11,
  "global_step": 101,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 1.9865820407867432,
      "learning_rate": 5e-06,
      "loss": 0.8807,
      "step": 1
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 1.6995460987091064,
      "learning_rate": 1e-05,
      "loss": 0.7298,
      "step": 2
    },
    {
      "epoch": 0.0297029702970297,
      "grad_norm": 1.870273232460022,
      "learning_rate": 9.997482711915926e-06,
      "loss": 0.8256,
      "step": 3
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 2.035698175430298,
      "learning_rate": 9.989933382359423e-06,
      "loss": 0.8423,
      "step": 4
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 1.5802401304244995,
      "learning_rate": 9.977359612865424e-06,
      "loss": 1.0321,
      "step": 5
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 1.3238128423690796,
      "learning_rate": 9.959774064153977e-06,
      "loss": 0.7894,
      "step": 6
    },
    {
      "epoch": 0.06930693069306931,
      "grad_norm": 1.3449586629867554,
      "learning_rate": 9.937194443381972e-06,
      "loss": 0.69,
      "step": 7
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 1.215697169303894,
      "learning_rate": 9.909643486313533e-06,
      "loss": 0.8263,
      "step": 8
    },
    {
      "epoch": 0.0891089108910891,
      "grad_norm": 1.4947011470794678,
      "learning_rate": 9.877148934427037e-06,
      "loss": 0.7706,
      "step": 9
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 0.9939355850219727,
      "learning_rate": 9.839743506981783e-06,
      "loss": 0.6854,
      "step": 10
    },
    {
      "epoch": 0.10891089108910891,
      "grad_norm": 1.3050940036773682,
      "learning_rate": 9.797464868072489e-06,
      "loss": 0.9061,
      "step": 11
    },
    {
      "epoch": 0.10891089108910891,
      "eval_loss": 0.7099791765213013,
      "eval_runtime": 1.6876,
      "eval_samples_per_second": 5.333,
      "eval_steps_per_second": 1.185,
      "step": 11
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 1.0027287006378174,
      "learning_rate": 9.750355588704728e-06,
      "loss": 0.7043,
      "step": 12
    },
    {
      "epoch": 0.12871287128712872,
      "grad_norm": 0.9371753334999084,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.6727,
      "step": 13
    },
    {
      "epoch": 0.13861386138613863,
      "grad_norm": 0.9471062421798706,
      "learning_rate": 9.641839665080363e-06,
      "loss": 0.6772,
      "step": 14
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 1.1542134284973145,
      "learning_rate": 9.580542287160348e-06,
      "loss": 0.7956,
      "step": 15
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 1.1275238990783691,
      "learning_rate": 9.514632691433108e-06,
      "loss": 0.7486,
      "step": 16
    },
    {
      "epoch": 0.16831683168316833,
      "grad_norm": 1.0453617572784424,
      "learning_rate": 9.444177243274619e-06,
      "loss": 0.659,
      "step": 17
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 1.0331149101257324,
      "learning_rate": 9.369246885348926e-06,
      "loss": 0.7471,
      "step": 18
    },
    {
      "epoch": 0.18811881188118812,
      "grad_norm": 0.8706634044647217,
      "learning_rate": 9.289917066174887e-06,
      "loss": 0.5547,
      "step": 19
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 1.1781532764434814,
      "learning_rate": 9.206267664155906e-06,
      "loss": 0.6239,
      "step": 20
    },
    {
      "epoch": 0.2079207920792079,
      "grad_norm": 1.2011443376541138,
      "learning_rate": 9.118382907149164e-06,
      "loss": 0.7847,
      "step": 21
    },
    {
      "epoch": 0.21782178217821782,
      "grad_norm": 1.028536319732666,
      "learning_rate": 9.026351287655294e-06,
      "loss": 0.6565,
      "step": 22
    },
    {
      "epoch": 0.21782178217821782,
      "eval_loss": 0.6684643030166626,
      "eval_runtime": 1.6848,
      "eval_samples_per_second": 5.342,
      "eval_steps_per_second": 1.187,
      "step": 22
    },
    {
      "epoch": 0.22772277227722773,
      "grad_norm": 0.9103761315345764,
      "learning_rate": 8.930265473713939e-06,
      "loss": 0.6495,
      "step": 23
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 1.0075730085372925,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.7109,
      "step": 24
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 0.9617104530334473,
      "learning_rate": 8.726322248378775e-06,
      "loss": 0.6993,
      "step": 25
    },
    {
      "epoch": 0.25742574257425743,
      "grad_norm": 1.072245717048645,
      "learning_rate": 8.61867019052535e-06,
      "loss": 0.8897,
      "step": 26
    },
    {
      "epoch": 0.26732673267326734,
      "grad_norm": 1.0244859457015991,
      "learning_rate": 8.507374438531606e-06,
      "loss": 0.8158,
      "step": 27
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 1.0862797498703003,
      "learning_rate": 8.392547057785662e-06,
      "loss": 0.7539,
      "step": 28
    },
    {
      "epoch": 0.2871287128712871,
      "grad_norm": 0.9954370260238647,
      "learning_rate": 8.274303669726427e-06,
      "loss": 0.718,
      "step": 29
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 1.0018794536590576,
      "learning_rate": 8.152763335422612e-06,
      "loss": 0.7518,
      "step": 30
    },
    {
      "epoch": 0.3069306930693069,
      "grad_norm": 0.9397566318511963,
      "learning_rate": 8.028048435688333e-06,
      "loss": 0.663,
      "step": 31
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 0.8733705878257751,
      "learning_rate": 7.900284547855992e-06,
      "loss": 0.6565,
      "step": 32
    },
    {
      "epoch": 0.32673267326732675,
      "grad_norm": 0.938222348690033,
      "learning_rate": 7.769600319330553e-06,
      "loss": 0.601,
      "step": 33
    },
    {
      "epoch": 0.32673267326732675,
      "eval_loss": 0.648015022277832,
      "eval_runtime": 1.6839,
      "eval_samples_per_second": 5.345,
      "eval_steps_per_second": 1.188,
      "step": 33
    },
    {
      "epoch": 0.33663366336633666,
      "grad_norm": 0.9610555768013,
      "learning_rate": 7.636127338052513e-06,
      "loss": 0.7488,
      "step": 34
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 1.0051265954971313,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.7929,
      "step": 35
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 0.8689800500869751,
      "learning_rate": 7.361355373863415e-06,
      "loss": 0.57,
      "step": 36
    },
    {
      "epoch": 0.36633663366336633,
      "grad_norm": 1.0085370540618896,
      "learning_rate": 7.2203330630288714e-06,
      "loss": 0.672,
      "step": 37
    },
    {
      "epoch": 0.37623762376237624,
      "grad_norm": 0.8325203061103821,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 0.6143,
      "step": 38
    },
    {
      "epoch": 0.38613861386138615,
      "grad_norm": 0.9245986342430115,
      "learning_rate": 6.931725628465643e-06,
      "loss": 0.7288,
      "step": 39
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.1846799850463867,
      "learning_rate": 6.78443110795936e-06,
      "loss": 0.8207,
      "step": 40
    },
    {
      "epoch": 0.40594059405940597,
      "grad_norm": 0.8949479460716248,
      "learning_rate": 6.635339816587109e-06,
      "loss": 0.6476,
      "step": 41
    },
    {
      "epoch": 0.4158415841584158,
      "grad_norm": 0.9853402376174927,
      "learning_rate": 6.484601876641375e-06,
      "loss": 0.7146,
      "step": 42
    },
    {
      "epoch": 0.42574257425742573,
      "grad_norm": 0.9564022421836853,
      "learning_rate": 6.332369068450175e-06,
      "loss": 0.7382,
      "step": 43
    },
    {
      "epoch": 0.43564356435643564,
      "grad_norm": 1.0044441223144531,
      "learning_rate": 6.178794677547138e-06,
      "loss": 0.7668,
      "step": 44
    },
    {
      "epoch": 0.43564356435643564,
      "eval_loss": 0.6342881917953491,
      "eval_runtime": 1.6847,
      "eval_samples_per_second": 5.342,
      "eval_steps_per_second": 1.187,
      "step": 44
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 0.8848042488098145,
      "learning_rate": 6.024033340325954e-06,
      "loss": 0.6532,
      "step": 45
    },
    {
      "epoch": 0.45544554455445546,
      "grad_norm": 0.8762900233268738,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.674,
      "step": 46
    },
    {
      "epoch": 0.46534653465346537,
      "grad_norm": 0.8674903512001038,
      "learning_rate": 5.711574191366427e-06,
      "loss": 0.6138,
      "step": 47
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.9267687201499939,
      "learning_rate": 5.5541909995050554e-06,
      "loss": 0.6838,
      "step": 48
    },
    {
      "epoch": 0.48514851485148514,
      "grad_norm": 0.8423399329185486,
      "learning_rate": 5.396249784283943e-06,
      "loss": 0.6081,
      "step": 49
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 0.9809019565582275,
      "learning_rate": 5.237909579118713e-06,
      "loss": 0.7202,
      "step": 50
    },
    {
      "epoch": 0.504950495049505,
      "grad_norm": 0.8688491582870483,
      "learning_rate": 5.07932981917404e-06,
      "loss": 0.6236,
      "step": 51
    },
    {
      "epoch": 0.5148514851485149,
      "grad_norm": 0.9908064007759094,
      "learning_rate": 4.9206701808259605e-06,
      "loss": 0.7449,
      "step": 52
    },
    {
      "epoch": 0.5247524752475248,
      "grad_norm": 0.935342013835907,
      "learning_rate": 4.762090420881289e-06,
      "loss": 0.6582,
      "step": 53
    },
    {
      "epoch": 0.5346534653465347,
      "grad_norm": 1.0338435173034668,
      "learning_rate": 4.603750215716057e-06,
      "loss": 0.7808,
      "step": 54
    },
    {
      "epoch": 0.5445544554455446,
      "grad_norm": 1.0253307819366455,
      "learning_rate": 4.445809000494945e-06,
      "loss": 0.8058,
      "step": 55
    },
    {
      "epoch": 0.5445544554455446,
      "eval_loss": 0.6248189210891724,
      "eval_runtime": 1.6835,
      "eval_samples_per_second": 5.346,
      "eval_steps_per_second": 1.188,
      "step": 55
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 0.9448875188827515,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 0.7117,
      "step": 56
    },
    {
      "epoch": 0.5643564356435643,
      "grad_norm": 0.8737557530403137,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.5988,
      "step": 57
    },
    {
      "epoch": 0.5742574257425742,
      "grad_norm": 0.764798104763031,
      "learning_rate": 3.975966659674048e-06,
      "loss": 0.501,
      "step": 58
    },
    {
      "epoch": 0.5841584158415841,
      "grad_norm": 0.9195338487625122,
      "learning_rate": 3.821205322452863e-06,
      "loss": 0.677,
      "step": 59
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.9102662801742554,
      "learning_rate": 3.667630931549826e-06,
      "loss": 0.6363,
      "step": 60
    },
    {
      "epoch": 0.6039603960396039,
      "grad_norm": 1.1512144804000854,
      "learning_rate": 3.5153981233586277e-06,
      "loss": 0.7082,
      "step": 61
    },
    {
      "epoch": 0.6138613861386139,
      "grad_norm": 1.0006070137023926,
      "learning_rate": 3.3646601834128924e-06,
      "loss": 0.6685,
      "step": 62
    },
    {
      "epoch": 0.6237623762376238,
      "grad_norm": 0.9273307919502258,
      "learning_rate": 3.2155688920406415e-06,
      "loss": 0.6652,
      "step": 63
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 0.9092214703559875,
      "learning_rate": 3.0682743715343565e-06,
      "loss": 0.6497,
      "step": 64
    },
    {
      "epoch": 0.6435643564356436,
      "grad_norm": 0.8190207481384277,
      "learning_rate": 2.9229249349905686e-06,
      "loss": 0.5194,
      "step": 65
    },
    {
      "epoch": 0.6534653465346535,
      "grad_norm": 0.9039291739463806,
      "learning_rate": 2.7796669369711294e-06,
      "loss": 0.675,
      "step": 66
    },
    {
      "epoch": 0.6534653465346535,
      "eval_loss": 0.6190232038497925,
      "eval_runtime": 1.6846,
      "eval_samples_per_second": 5.342,
      "eval_steps_per_second": 1.187,
      "step": 66
    },
    {
      "epoch": 0.6633663366336634,
      "grad_norm": 1.0311757326126099,
      "learning_rate": 2.6386446261365874e-06,
      "loss": 0.8244,
      "step": 67
    },
    {
      "epoch": 0.6732673267326733,
      "grad_norm": 0.8113132119178772,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.5488,
      "step": 68
    },
    {
      "epoch": 0.6831683168316832,
      "grad_norm": 0.9003159403800964,
      "learning_rate": 2.363872661947488e-06,
      "loss": 0.7291,
      "step": 69
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 1.057133674621582,
      "learning_rate": 2.230399680669449e-06,
      "loss": 0.8625,
      "step": 70
    },
    {
      "epoch": 0.7029702970297029,
      "grad_norm": 0.9384030699729919,
      "learning_rate": 2.09971545214401e-06,
      "loss": 0.6813,
      "step": 71
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.8832238912582397,
      "learning_rate": 1.971951564311668e-06,
      "loss": 0.6099,
      "step": 72
    },
    {
      "epoch": 0.7227722772277227,
      "grad_norm": 0.8297242522239685,
      "learning_rate": 1.8472366645773892e-06,
      "loss": 0.5465,
      "step": 73
    },
    {
      "epoch": 0.7326732673267327,
      "grad_norm": 0.9183589816093445,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 0.6971,
      "step": 74
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 0.8353100419044495,
      "learning_rate": 1.6074529422143398e-06,
      "loss": 0.5426,
      "step": 75
    },
    {
      "epoch": 0.7524752475247525,
      "grad_norm": 1.051756739616394,
      "learning_rate": 1.4926255614683931e-06,
      "loss": 0.7567,
      "step": 76
    },
    {
      "epoch": 0.7623762376237624,
      "grad_norm": 0.8063908815383911,
      "learning_rate": 1.3813298094746491e-06,
      "loss": 0.5383,
      "step": 77
    },
    {
      "epoch": 0.7623762376237624,
      "eval_loss": 0.6155756711959839,
      "eval_runtime": 1.6854,
      "eval_samples_per_second": 5.34,
      "eval_steps_per_second": 1.187,
      "step": 77
    },
    {
      "epoch": 0.7722772277227723,
      "grad_norm": 0.8472511768341064,
      "learning_rate": 1.2736777516212267e-06,
      "loss": 0.5792,
      "step": 78
    },
    {
      "epoch": 0.7821782178217822,
      "grad_norm": 0.8465410470962524,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.6283,
      "step": 79
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.7360741496086121,
      "learning_rate": 1.0697345262860638e-06,
      "loss": 0.4699,
      "step": 80
    },
    {
      "epoch": 0.801980198019802,
      "grad_norm": 0.9224135875701904,
      "learning_rate": 9.73648712344707e-07,
      "loss": 0.6806,
      "step": 81
    },
    {
      "epoch": 0.8118811881188119,
      "grad_norm": 0.871505081653595,
      "learning_rate": 8.816170928508367e-07,
      "loss": 0.6824,
      "step": 82
    },
    {
      "epoch": 0.8217821782178217,
      "grad_norm": 0.8890396952629089,
      "learning_rate": 7.937323358440935e-07,
      "loss": 0.6427,
      "step": 83
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 1.091757893562317,
      "learning_rate": 7.100829338251147e-07,
      "loss": 0.7535,
      "step": 84
    },
    {
      "epoch": 0.8415841584158416,
      "grad_norm": 0.809833824634552,
      "learning_rate": 6.307531146510754e-07,
      "loss": 0.5965,
      "step": 85
    },
    {
      "epoch": 0.8514851485148515,
      "grad_norm": 0.861588716506958,
      "learning_rate": 5.558227567253832e-07,
      "loss": 0.6629,
      "step": 86
    },
    {
      "epoch": 0.8613861386138614,
      "grad_norm": 0.7921182513237,
      "learning_rate": 4.853673085668947e-07,
      "loss": 0.482,
      "step": 87
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 0.7692471742630005,
      "learning_rate": 4.194577128396521e-07,
      "loss": 0.5044,
      "step": 88
    },
    {
      "epoch": 0.8712871287128713,
      "eval_loss": 0.6139124035835266,
      "eval_runtime": 1.684,
      "eval_samples_per_second": 5.344,
      "eval_steps_per_second": 1.188,
      "step": 88
    },
    {
      "epoch": 0.8811881188118812,
      "grad_norm": 0.8603846430778503,
      "learning_rate": 3.581603349196372e-07,
      "loss": 0.6439,
      "step": 89
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 0.8953405022621155,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.6881,
      "step": 90
    },
    {
      "epoch": 0.900990099009901,
      "grad_norm": 0.9108988046646118,
      "learning_rate": 2.4964441129527337e-07,
      "loss": 0.7118,
      "step": 91
    },
    {
      "epoch": 0.9108910891089109,
      "grad_norm": 0.886647641658783,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 0.7544,
      "step": 92
    },
    {
      "epoch": 0.9207920792079208,
      "grad_norm": 0.943878173828125,
      "learning_rate": 1.6025649301821877e-07,
      "loss": 0.7527,
      "step": 93
    },
    {
      "epoch": 0.9306930693069307,
      "grad_norm": 0.8354966044425964,
      "learning_rate": 1.2285106557296479e-07,
      "loss": 0.6079,
      "step": 94
    },
    {
      "epoch": 0.9405940594059405,
      "grad_norm": 0.8121664524078369,
      "learning_rate": 9.035651368646647e-08,
      "loss": 0.5891,
      "step": 95
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.9194057583808899,
      "learning_rate": 6.280555661802857e-08,
      "loss": 0.6953,
      "step": 96
    },
    {
      "epoch": 0.9603960396039604,
      "grad_norm": 0.9447068572044373,
      "learning_rate": 4.02259358460233e-08,
      "loss": 0.7401,
      "step": 97
    },
    {
      "epoch": 0.9702970297029703,
      "grad_norm": 0.8672422766685486,
      "learning_rate": 2.264038713457706e-08,
      "loss": 0.6349,
      "step": 98
    },
    {
      "epoch": 0.9801980198019802,
      "grad_norm": 0.904771625995636,
      "learning_rate": 1.006661764057837e-08,
      "loss": 0.6322,
      "step": 99
    },
    {
      "epoch": 0.9801980198019802,
      "eval_loss": 0.6136024594306946,
      "eval_runtime": 1.6864,
      "eval_samples_per_second": 5.337,
      "eval_steps_per_second": 1.186,
      "step": 99
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 0.8689496517181396,
      "learning_rate": 2.5172880840745873e-09,
      "loss": 0.6191,
      "step": 100
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8673611283302307,
      "learning_rate": 0.0,
      "loss": 0.5897,
      "step": 101
    },
    {
      "epoch": 1.0,
      "step": 101,
      "total_flos": 1.5438974547499418e+17,
      "train_loss": 0.6889385657735391,
      "train_runtime": 730.4137,
      "train_samples_per_second": 1.101,
      "train_steps_per_second": 0.138
    }
  ],
  "logging_steps": 1,
  "max_steps": 101,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 101,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5438974547499418e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}