{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007187350263536177,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011978917105893628,
      "grad_norm": 0.953666090965271,
      "learning_rate": 4e-05,
      "loss": 2.065,
      "step": 1
    },
    {
      "epoch": 0.00023957834211787255,
      "grad_norm": 0.8322485685348511,
      "learning_rate": 8e-05,
      "loss": 2.0129,
      "step": 2
    },
    {
      "epoch": 0.0003593675131768088,
      "grad_norm": 0.9846245646476746,
      "learning_rate": 0.00012,
      "loss": 2.0287,
      "step": 3
    },
    {
      "epoch": 0.0004791566842357451,
      "grad_norm": 0.8462266325950623,
      "learning_rate": 0.00016,
      "loss": 2.0177,
      "step": 4
    },
    {
      "epoch": 0.0005989458552946814,
      "grad_norm": 0.8897871375083923,
      "learning_rate": 0.0002,
      "loss": 1.888,
      "step": 5
    },
    {
      "epoch": 0.0007187350263536176,
      "grad_norm": 0.7725397348403931,
      "learning_rate": 0.00019636363636363636,
      "loss": 2.0803,
      "step": 6
    },
    {
      "epoch": 0.0008385241974125539,
      "grad_norm": 0.674379825592041,
      "learning_rate": 0.00019272727272727274,
      "loss": 1.8878,
      "step": 7
    },
    {
      "epoch": 0.0009583133684714902,
      "grad_norm": 0.7274234294891357,
      "learning_rate": 0.0001890909090909091,
      "loss": 2.0603,
      "step": 8
    },
    {
      "epoch": 0.0010781025395304265,
      "grad_norm": 0.5945920944213867,
      "learning_rate": 0.00018545454545454545,
      "loss": 1.8161,
      "step": 9
    },
    {
      "epoch": 0.0011978917105893627,
      "grad_norm": 0.6586880087852478,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.9888,
      "step": 10
    },
    {
      "epoch": 0.001317680881648299,
      "grad_norm": 0.7260717153549194,
      "learning_rate": 0.0001781818181818182,
      "loss": 1.8034,
      "step": 11
    },
    {
      "epoch": 0.0014374700527072352,
      "grad_norm": 0.7235636711120605,
      "learning_rate": 0.00017454545454545454,
      "loss": 1.7587,
      "step": 12
    },
    {
      "epoch": 0.0015572592237661715,
      "grad_norm": 0.6093252897262573,
      "learning_rate": 0.0001709090909090909,
      "loss": 1.8527,
      "step": 13
    },
    {
      "epoch": 0.0016770483948251077,
      "grad_norm": 0.6886703968048096,
      "learning_rate": 0.00016727272727272728,
      "loss": 1.9906,
      "step": 14
    },
    {
      "epoch": 0.0017968375658840442,
      "grad_norm": 0.613222062587738,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.7073,
      "step": 15
    },
    {
      "epoch": 0.0019166267369429804,
      "grad_norm": 0.5307195782661438,
      "learning_rate": 0.00016,
      "loss": 1.7741,
      "step": 16
    },
    {
      "epoch": 0.0020364159080019165,
      "grad_norm": 0.6123448610305786,
      "learning_rate": 0.00015636363636363637,
      "loss": 1.7753,
      "step": 17
    },
    {
      "epoch": 0.002156205079060853,
      "grad_norm": 0.5280768275260925,
      "learning_rate": 0.00015272727272727275,
      "loss": 1.7654,
      "step": 18
    },
    {
      "epoch": 0.002275994250119789,
      "grad_norm": 0.5204810500144958,
      "learning_rate": 0.0001490909090909091,
      "loss": 1.7462,
      "step": 19
    },
    {
      "epoch": 0.0023957834211787254,
      "grad_norm": 0.5603053569793701,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.7481,
      "step": 20
    },
    {
      "epoch": 0.002515572592237662,
      "grad_norm": 0.46755069494247437,
      "learning_rate": 0.00014181818181818184,
      "loss": 1.6687,
      "step": 21
    },
    {
      "epoch": 0.002635361763296598,
      "grad_norm": 0.6600363254547119,
      "learning_rate": 0.0001381818181818182,
      "loss": 1.7004,
      "step": 22
    },
    {
      "epoch": 0.0027551509343555344,
      "grad_norm": 0.7076529264450073,
      "learning_rate": 0.00013454545454545455,
      "loss": 1.8755,
      "step": 23
    },
    {
      "epoch": 0.0028749401054144704,
      "grad_norm": 0.6433557271957397,
      "learning_rate": 0.00013090909090909093,
      "loss": 1.8093,
      "step": 24
    },
    {
      "epoch": 0.002994729276473407,
      "grad_norm": 0.416513592004776,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.7596,
      "step": 25
    },
    {
      "epoch": 0.003114518447532343,
      "grad_norm": 0.571668803691864,
      "learning_rate": 0.00012363636363636364,
      "loss": 1.7043,
      "step": 26
    },
    {
      "epoch": 0.0032343076185912794,
      "grad_norm": 0.5698043704032898,
      "learning_rate": 0.00012,
      "loss": 1.6695,
      "step": 27
    },
    {
      "epoch": 0.0033540967896502154,
      "grad_norm": 0.5556852221488953,
      "learning_rate": 0.00011636363636363636,
      "loss": 1.8473,
      "step": 28
    },
    {
      "epoch": 0.003473885960709152,
      "grad_norm": 0.544235110282898,
      "learning_rate": 0.00011272727272727272,
      "loss": 1.7663,
      "step": 29
    },
    {
      "epoch": 0.0035936751317680884,
      "grad_norm": 0.486969918012619,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.7088,
      "step": 30
    },
    {
      "epoch": 0.0037134643028270244,
      "grad_norm": 0.5989601016044617,
      "learning_rate": 0.00010545454545454545,
      "loss": 1.8058,
      "step": 31
    },
    {
      "epoch": 0.003833253473885961,
      "grad_norm": 0.6275827884674072,
      "learning_rate": 0.00010181818181818181,
      "loss": 1.715,
      "step": 32
    },
    {
      "epoch": 0.003953042644944897,
      "grad_norm": 0.46334367990493774,
      "learning_rate": 9.818181818181818e-05,
      "loss": 1.6563,
      "step": 33
    },
    {
      "epoch": 0.004072831816003833,
      "grad_norm": 0.6081639528274536,
      "learning_rate": 9.454545454545455e-05,
      "loss": 1.9894,
      "step": 34
    },
    {
      "epoch": 0.004192620987062769,
      "grad_norm": 0.4673190414905548,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.5616,
      "step": 35
    },
    {
      "epoch": 0.004312410158121706,
      "grad_norm": 0.5921393036842346,
      "learning_rate": 8.727272727272727e-05,
      "loss": 1.8312,
      "step": 36
    },
    {
      "epoch": 0.004432199329180642,
      "grad_norm": 0.5008795261383057,
      "learning_rate": 8.363636363636364e-05,
      "loss": 1.793,
      "step": 37
    },
    {
      "epoch": 0.004551988500239578,
      "grad_norm": 0.49707821011543274,
      "learning_rate": 8e-05,
      "loss": 1.7043,
      "step": 38
    },
    {
      "epoch": 0.004671777671298514,
      "grad_norm": 0.6233934164047241,
      "learning_rate": 7.636363636363637e-05,
      "loss": 1.7512,
      "step": 39
    },
    {
      "epoch": 0.004791566842357451,
      "grad_norm": 0.5607012510299683,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.6754,
      "step": 40
    },
    {
      "epoch": 0.004911356013416387,
      "grad_norm": 0.6054458618164062,
      "learning_rate": 6.90909090909091e-05,
      "loss": 1.7594,
      "step": 41
    },
    {
      "epoch": 0.005031145184475324,
      "grad_norm": 0.5356596112251282,
      "learning_rate": 6.545454545454546e-05,
      "loss": 1.7597,
      "step": 42
    },
    {
      "epoch": 0.005150934355534259,
      "grad_norm": 0.4934113919734955,
      "learning_rate": 6.181818181818182e-05,
      "loss": 1.6513,
      "step": 43
    },
    {
      "epoch": 0.005270723526593196,
      "grad_norm": 0.5411939024925232,
      "learning_rate": 5.818181818181818e-05,
      "loss": 1.617,
      "step": 44
    },
    {
      "epoch": 0.005390512697652132,
      "grad_norm": 0.46617865562438965,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.6456,
      "step": 45
    },
    {
      "epoch": 0.005510301868711069,
      "grad_norm": 0.605570375919342,
      "learning_rate": 5.090909090909091e-05,
      "loss": 1.7424,
      "step": 46
    },
    {
      "epoch": 0.005630091039770004,
      "grad_norm": 0.527157187461853,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 1.6622,
      "step": 47
    },
    {
      "epoch": 0.005749880210828941,
      "grad_norm": 0.5319560170173645,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 1.6626,
      "step": 48
    },
    {
      "epoch": 0.005869669381887877,
      "grad_norm": 0.5411937236785889,
      "learning_rate": 4e-05,
      "loss": 1.5206,
      "step": 49
    },
    {
      "epoch": 0.005989458552946814,
      "grad_norm": 0.519945502281189,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.6893,
      "step": 50
    },
    {
      "epoch": 0.00610924772400575,
      "grad_norm": 0.594184398651123,
      "learning_rate": 3.272727272727273e-05,
      "loss": 1.9877,
      "step": 51
    },
    {
      "epoch": 0.006229036895064686,
      "grad_norm": 0.63973468542099,
      "learning_rate": 2.909090909090909e-05,
      "loss": 1.9143,
      "step": 52
    },
    {
      "epoch": 0.006348826066123622,
      "grad_norm": 0.5652793049812317,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 1.6949,
      "step": 53
    },
    {
      "epoch": 0.006468615237182559,
      "grad_norm": 0.5221755504608154,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 1.8363,
      "step": 54
    },
    {
      "epoch": 0.006588404408241495,
      "grad_norm": 0.5718774795532227,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.7272,
      "step": 55
    },
    {
      "epoch": 0.006708193579300431,
      "grad_norm": 0.4630696177482605,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 1.5824,
      "step": 56
    },
    {
      "epoch": 0.006827982750359367,
      "grad_norm": 0.5809832811355591,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.7316,
      "step": 57
    },
    {
      "epoch": 0.006947771921418304,
      "grad_norm": 0.4795840382575989,
      "learning_rate": 7.272727272727272e-06,
      "loss": 1.5127,
      "step": 58
    },
    {
      "epoch": 0.00706756109247724,
      "grad_norm": 0.4962644875049591,
      "learning_rate": 3.636363636363636e-06,
      "loss": 1.633,
      "step": 59
    },
    {
      "epoch": 0.007187350263536177,
      "grad_norm": 0.47581109404563904,
      "learning_rate": 0.0,
      "loss": 1.5483,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3581339433615360.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}