{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.909090909090909,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 1.6406759023666382,
      "learning_rate": 1.25e-06,
      "loss": 0.7384,
      "step": 1
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.777174472808838,
      "learning_rate": 2.5e-06,
      "loss": 0.7666,
      "step": 2
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.6539289951324463,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.7385,
      "step": 3
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 1.5728503465652466,
      "learning_rate": 5e-06,
      "loss": 0.7408,
      "step": 4
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.4771438837051392,
      "learning_rate": 6.25e-06,
      "loss": 0.7154,
      "step": 5
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.1310724020004272,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.7054,
      "step": 6
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.9647331833839417,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.6335,
      "step": 7
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.8720846772193909,
      "learning_rate": 1e-05,
      "loss": 0.6252,
      "step": 8
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.9205116033554077,
      "learning_rate": 9.993977281025862e-06,
      "loss": 0.6279,
      "step": 9
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.9854218363761902,
      "learning_rate": 9.975923633360985e-06,
      "loss": 0.6394,
      "step": 10
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.9342491030693054,
      "learning_rate": 9.945882549823906e-06,
      "loss": 0.6368,
      "step": 11
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.7965356111526489,
      "learning_rate": 9.903926402016153e-06,
      "loss": 0.6019,
      "step": 12
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.6925312876701355,
      "learning_rate": 9.850156265972722e-06,
      "loss": 0.6251,
      "step": 13
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.7038740515708923,
      "learning_rate": 9.784701678661045e-06,
      "loss": 0.6023,
      "step": 14
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.5820484161376953,
      "learning_rate": 9.707720325915105e-06,
      "loss": 0.5583,
      "step": 15
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.6657494306564331,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.6093,
      "step": 16
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.5573738813400269,
      "learning_rate": 9.519946465617217e-06,
      "loss": 0.5488,
      "step": 17
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.5118197202682495,
      "learning_rate": 9.409606321741776e-06,
      "loss": 0.5422,
      "step": 18
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 0.53837651014328,
      "learning_rate": 9.288643050001362e-06,
      "loss": 0.5477,
      "step": 19
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.49398595094680786,
      "learning_rate": 9.157348061512728e-06,
      "loss": 0.5245,
      "step": 20
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.48072442412376404,
      "learning_rate": 9.016037657403225e-06,
      "loss": 0.5405,
      "step": 21
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.48007655143737793,
      "learning_rate": 8.865052266813686e-06,
      "loss": 0.5306,
      "step": 22
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 0.45421069860458374,
      "learning_rate": 8.704755626774796e-06,
      "loss": 0.4897,
      "step": 23
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.47499579191207886,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.4854,
      "step": 24
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 0.6332795023918152,
      "learning_rate": 8.357794774235094e-06,
      "loss": 0.675,
      "step": 25
    },
    {
      "epoch": 1.0505050505050506,
      "grad_norm": 0.47866344451904297,
      "learning_rate": 8.171966420818227e-06,
      "loss": 0.4459,
      "step": 26
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.46443578600883484,
      "learning_rate": 7.978496522462167e-06,
      "loss": 0.4561,
      "step": 27
    },
    {
      "epoch": 1.1313131313131313,
      "grad_norm": 0.4448317885398865,
      "learning_rate": 7.777851165098012e-06,
      "loss": 0.4448,
      "step": 28
    },
    {
      "epoch": 1.1717171717171717,
      "grad_norm": 0.44462504982948303,
      "learning_rate": 7.570513720966108e-06,
      "loss": 0.4434,
      "step": 29
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.44808101654052734,
      "learning_rate": 7.3569836841299905e-06,
      "loss": 0.4443,
      "step": 30
    },
    {
      "epoch": 1.2525252525252526,
      "grad_norm": 0.473147988319397,
      "learning_rate": 7.137775467151411e-06,
      "loss": 0.4634,
      "step": 31
    },
    {
      "epoch": 1.2929292929292928,
      "grad_norm": 0.46904295682907104,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.4505,
      "step": 32
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.46802252531051636,
      "learning_rate": 6.684449266961101e-06,
      "loss": 0.4489,
      "step": 33
    },
    {
      "epoch": 1.3737373737373737,
      "grad_norm": 0.43041056394577026,
      "learning_rate": 6.451423386272312e-06,
      "loss": 0.3996,
      "step": 34
    },
    {
      "epoch": 1.4141414141414141,
      "grad_norm": 0.4580051004886627,
      "learning_rate": 6.21490089951632e-06,
      "loss": 0.4013,
      "step": 35
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.48125723004341125,
      "learning_rate": 5.975451610080643e-06,
      "loss": 0.4606,
      "step": 36
    },
    {
      "epoch": 1.494949494949495,
      "grad_norm": 0.4803732633590698,
      "learning_rate": 5.733652372276809e-06,
      "loss": 0.4398,
      "step": 37
    },
    {
      "epoch": 1.5353535353535355,
      "grad_norm": 0.4758044481277466,
      "learning_rate": 5.490085701647805e-06,
      "loss": 0.4314,
      "step": 38
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 0.43107980489730835,
      "learning_rate": 5.245338371637091e-06,
      "loss": 0.4052,
      "step": 39
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.4567951560020447,
      "learning_rate": 5e-06,
      "loss": 0.4341,
      "step": 40
    },
    {
      "epoch": 1.6565656565656566,
      "grad_norm": 0.48505422472953796,
      "learning_rate": 4.75466162836291e-06,
      "loss": 0.4169,
      "step": 41
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 0.490830659866333,
      "learning_rate": 4.509914298352197e-06,
      "loss": 0.4441,
      "step": 42
    },
    {
      "epoch": 1.7373737373737375,
      "grad_norm": 0.4757992923259735,
      "learning_rate": 4.266347627723192e-06,
      "loss": 0.4306,
      "step": 43
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.47538337111473083,
      "learning_rate": 4.02454838991936e-06,
      "loss": 0.4153,
      "step": 44
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.45427966117858887,
      "learning_rate": 3.7850991004836813e-06,
      "loss": 0.4075,
      "step": 45
    },
    {
      "epoch": 1.8585858585858586,
      "grad_norm": 0.4872586131095886,
      "learning_rate": 3.5485766137276894e-06,
      "loss": 0.44,
      "step": 46
    },
    {
      "epoch": 1.898989898989899,
      "grad_norm": 0.4346865117549896,
      "learning_rate": 3.3155507330389004e-06,
      "loss": 0.4338,
      "step": 47
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.44030866026878357,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 0.3924,
      "step": 48
    },
    {
      "epoch": 1.9797979797979797,
      "grad_norm": 0.512447714805603,
      "learning_rate": 2.862224532848591e-06,
      "loss": 0.4813,
      "step": 49
    },
    {
      "epoch": 2.0202020202020203,
      "grad_norm": 0.5484603643417358,
      "learning_rate": 2.6430163158700116e-06,
      "loss": 0.4593,
      "step": 50
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 0.44288182258605957,
      "learning_rate": 2.429486279033892e-06,
      "loss": 0.3801,
      "step": 51
    },
    {
      "epoch": 2.101010101010101,
      "grad_norm": 0.43875348567962646,
      "learning_rate": 2.2221488349019903e-06,
      "loss": 0.3617,
      "step": 52
    },
    {
      "epoch": 2.1414141414141414,
      "grad_norm": 0.4406426250934601,
      "learning_rate": 2.0215034775378336e-06,
      "loss": 0.3975,
      "step": 53
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.4345356822013855,
      "learning_rate": 1.8280335791817733e-06,
      "loss": 0.3506,
      "step": 54
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.45012521743774414,
      "learning_rate": 1.642205225764908e-06,
      "loss": 0.3519,
      "step": 55
    },
    {
      "epoch": 2.2626262626262625,
      "grad_norm": 0.43018749356269836,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.3426,
      "step": 56
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 0.4245786666870117,
      "learning_rate": 1.2952443732252058e-06,
      "loss": 0.3566,
      "step": 57
    },
    {
      "epoch": 2.3434343434343434,
      "grad_norm": 0.44446811079978943,
      "learning_rate": 1.134947733186315e-06,
      "loss": 0.3737,
      "step": 58
    },
    {
      "epoch": 2.3838383838383836,
      "grad_norm": 0.45123612880706787,
      "learning_rate": 9.83962342596776e-07,
      "loss": 0.3814,
      "step": 59
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.4223995506763458,
      "learning_rate": 8.426519384872733e-07,
      "loss": 0.3604,
      "step": 60
    },
    {
      "epoch": 2.4646464646464645,
      "grad_norm": 0.4496898949146271,
      "learning_rate": 7.113569499986401e-07,
      "loss": 0.3379,
      "step": 61
    },
    {
      "epoch": 2.505050505050505,
      "grad_norm": 0.45103389024734497,
      "learning_rate": 5.903936782582253e-07,
      "loss": 0.3728,
      "step": 62
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.46011683344841003,
      "learning_rate": 4.800535343827834e-07,
      "loss": 0.3624,
      "step": 63
    },
    {
      "epoch": 2.5858585858585856,
      "grad_norm": 0.4292215406894684,
      "learning_rate": 3.8060233744356634e-07,
      "loss": 0.3703,
      "step": 64
    },
    {
      "epoch": 2.6262626262626263,
      "grad_norm": 0.4275359809398651,
      "learning_rate": 2.9227967408489653e-07,
      "loss": 0.3596,
      "step": 65
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.41896435618400574,
      "learning_rate": 2.152983213389559e-07,
      "loss": 0.3647,
      "step": 66
    },
    {
      "epoch": 2.707070707070707,
      "grad_norm": 0.4374232292175293,
      "learning_rate": 1.4984373402728014e-07,
      "loss": 0.3672,
      "step": 67
    },
    {
      "epoch": 2.7474747474747474,
      "grad_norm": 0.4519655704498291,
      "learning_rate": 9.607359798384785e-08,
      "loss": 0.3811,
      "step": 68
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 0.4365183711051941,
      "learning_rate": 5.411745017609493e-08,
      "loss": 0.3629,
      "step": 69
    },
    {
      "epoch": 2.8282828282828283,
      "grad_norm": 0.4325156807899475,
      "learning_rate": 2.4076366639015914e-08,
      "loss": 0.3517,
      "step": 70
    },
    {
      "epoch": 2.8686868686868685,
      "grad_norm": 0.4426824748516083,
      "learning_rate": 6.022718974137976e-09,
      "loss": 0.3676,
      "step": 71
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.5022251605987549,
      "learning_rate": 0.0,
      "loss": 0.3794,
      "step": 72
    },
    {
      "epoch": 2.909090909090909,
      "step": 72,
      "total_flos": 3.5981250321711104e+16,
      "train_loss": 0.4774101939466264,
      "train_runtime": 9083.6349,
      "train_samples_per_second": 0.392,
      "train_steps_per_second": 0.008
    }
  ],
  "logging_steps": 1,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5981250321711104e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}