{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 63,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 1.0377577543258667,
      "learning_rate": 0.0,
      "loss": 2.2598,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.950491726398468,
      "learning_rate": 5e-05,
      "loss": 2.1162,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.8062677383422852,
      "learning_rate": 0.0001,
      "loss": 1.8789,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.2896675169467926,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.415,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.18858225643634796,
      "learning_rate": 0.0002,
      "loss": 1.2537,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.3589648902416229,
      "learning_rate": 0.0001998724426109086,
      "loss": 1.157,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.2034045308828354,
      "learning_rate": 0.00019949013201891235,
      "loss": 1.256,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.20806469023227692,
      "learning_rate": 0.00019885415192492104,
      "loss": 0.9347,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.1329486072063446,
      "learning_rate": 0.000197966305083608,
      "loss": 1.0225,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.10501191765069962,
      "learning_rate": 0.00019682910819330646,
      "loss": 1.0608,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.08167339116334915,
      "learning_rate": 0.0001954457847621543,
      "loss": 1.0442,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.07467832416296005,
      "learning_rate": 0.00019382025597071049,
      "loss": 0.9116,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.10425141453742981,
      "learning_rate": 0.0001919571295569422,
      "loss": 1.0774,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.08753609657287598,
      "learning_rate": 0.00018986168675509145,
      "loss": 0.9084,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.09329564869403839,
      "learning_rate": 0.00018753986732544255,
      "loss": 1.0326,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.06999287754297256,
      "learning_rate": 0.00018499825271742635,
      "loss": 1.066,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.07671773433685303,
      "learning_rate": 0.00018224404741378674,
      "loss": 0.9196,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.07140030711889267,
      "learning_rate": 0.00017928505850869157,
      "loss": 1.0462,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.10820895433425903,
      "learning_rate": 0.00017612967357767605,
      "loss": 0.7579,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.11008598655462265,
      "learning_rate": 0.00017278683690214865,
      "loss": 0.5615,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.07539282739162445,
      "learning_rate": 0.0001692660241158535,
      "loss": 0.8203,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.10306309908628464,
      "learning_rate": 0.0001655772153451573,
      "loss": 0.885,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.09677709639072418,
      "learning_rate": 0.00016173086691929664,
      "loss": 0.8434,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.07850930839776993,
      "learning_rate": 0.00015773788173077682,
      "loss": 0.9404,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.0830693244934082,
      "learning_rate": 0.00015360957832993852,
      "loss": 0.9149,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.0840546041727066,
      "learning_rate": 0.000149357658841297,
      "loss": 0.827,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.07045507431030273,
      "learning_rate": 0.0001449941757925989,
      "loss": 0.7903,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.07093216478824615,
      "learning_rate": 0.00014053149795062274,
      "loss": 0.962,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.07280776649713516,
      "learning_rate": 0.0001359822752605659,
      "loss": 0.6519,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.0633326843380928,
      "learning_rate": 0.00013135940298840035,
      "loss": 0.7894,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.06777395308017731,
      "learning_rate": 0.0001266759851678403,
      "loss": 0.8445,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.06890520453453064,
      "learning_rate": 0.00012194529745553497,
      "loss": 0.8394,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.07028112560510635,
      "learning_rate": 0.00011718074949977748,
      "loss": 0.7128,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.0746479257941246,
      "learning_rate": 0.00011239584692939975,
      "loss": 0.8896,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.08016974478960037,
      "learning_rate": 0.00010760415307060027,
      "loss": 0.7318,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.06959321349859238,
      "learning_rate": 0.00010281925050022251,
      "loss": 0.8489,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.06887049973011017,
      "learning_rate": 9.805470254446503e-05,
      "loss": 0.9084,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.0744592696428299,
      "learning_rate": 9.332401483215973e-05,
      "loss": 0.7318,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.0794808566570282,
      "learning_rate": 8.864059701159965e-05,
      "loss": 0.9065,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.07422224432229996,
      "learning_rate": 8.401772473943415e-05,
      "loss": 0.5881,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.07543457299470901,
      "learning_rate": 7.946850204937728e-05,
      "loss": 0.4109,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07449755817651749,
      "learning_rate": 7.500582420740115e-05,
      "loss": 0.6763,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.0908975750207901,
      "learning_rate": 7.064234115870303e-05,
      "loss": 0.7145,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.09462336450815201,
      "learning_rate": 6.63904216700615e-05,
      "loss": 0.6831,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.07695115357637405,
      "learning_rate": 6.226211826922319e-05,
      "loss": 0.8054,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.07964155077934265,
      "learning_rate": 5.8269133080703386e-05,
      "loss": 0.8001,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.08799073100090027,
      "learning_rate": 5.442278465484274e-05,
      "loss": 0.6975,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.07706860452890396,
      "learning_rate": 5.0733975884146533e-05,
      "loss": 0.6651,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.07903925329446793,
      "learning_rate": 4.721316309785139e-05,
      "loss": 0.8473,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.094353087246418,
      "learning_rate": 4.387032642232397e-05,
      "loss": 0.5177,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.09457288682460785,
      "learning_rate": 4.071494149130843e-05,
      "loss": 0.6799,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.08974256366491318,
      "learning_rate": 3.775595258621329e-05,
      "loss": 0.7302,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.08180077373981476,
      "learning_rate": 3.500174728257365e-05,
      "loss": 0.7274,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.07987571507692337,
      "learning_rate": 3.246013267455745e-05,
      "loss": 0.6073,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.08051332831382751,
      "learning_rate": 3.0138313244908573e-05,
      "loss": 0.7881,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.08457138389348984,
      "learning_rate": 2.8042870443057812e-05,
      "loss": 0.636,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.0923929363489151,
      "learning_rate": 2.6179744029289542e-05,
      "loss": 0.7524,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.08431456238031387,
      "learning_rate": 2.4554215237845687e-05,
      "loss": 0.8206,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.09262314438819885,
      "learning_rate": 2.3170891806693566e-05,
      "loss": 0.6298,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.08955827355384827,
      "learning_rate": 2.2033694916392002e-05,
      "loss": 0.8282,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.0884852334856987,
      "learning_rate": 2.1145848075078993e-05,
      "loss": 0.5063,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.07892720401287079,
      "learning_rate": 2.0509867981087663e-05,
      "loss": 0.3413,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0838647335767746,
      "learning_rate": 2.0127557389091428e-05,
      "loss": 0.5994,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6357218623161316,
      "eval_runtime": 3.9804,
      "eval_samples_per_second": 5.778,
      "eval_steps_per_second": 0.754,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.2942816179965133e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}