{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 12,
  "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": 0.504075825214386,
      "learning_rate": 0.0,
      "loss": 0.952880859375,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.84909588098526,
      "learning_rate": 1.25e-05,
      "loss": 1.4071044921875,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.9116283059120178,
      "learning_rate": 2.5e-05,
      "loss": 1.8212890625,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.6357577443122864,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.494140625,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.4251970052719116,
      "learning_rate": 5e-05,
      "loss": 1.55810546875,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.38511571288108826,
      "learning_rate": 4.996811065272715e-05,
      "loss": 1.4208984375,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.39757227897644043,
      "learning_rate": 4.987253300472809e-05,
      "loss": 1.34619140625,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.41428616642951965,
      "learning_rate": 4.971353798123026e-05,
      "loss": 1.256103515625,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.44648289680480957,
      "learning_rate": 4.9491576270902e-05,
      "loss": 1.384765625,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.14706675708293915,
      "learning_rate": 4.9207277048326614e-05,
      "loss": 0.57861328125,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.3266434669494629,
      "learning_rate": 4.8861446190538576e-05,
      "loss": 1.1953125,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.41698017716407776,
      "learning_rate": 4.845506399267762e-05,
      "loss": 1.15576171875,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.4158884882926941,
      "learning_rate": 4.798928238923555e-05,
      "loss": 1.13134765625,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.23661643266677856,
      "learning_rate": 4.746542168877286e-05,
      "loss": 0.61376953125,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.14239594340324402,
      "learning_rate": 4.688496683136064e-05,
      "loss": 0.4979248046875,
      "step": 15
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.76904296875,
      "eval_runtime": 6.9552,
      "eval_samples_per_second": 0.431,
      "eval_steps_per_second": 0.144,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.4148307144641876,
      "learning_rate": 4.624956317935659e-05,
      "loss": 1.2275390625,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.36151090264320374,
      "learning_rate": 4.5561011853446684e-05,
      "loss": 1.1533203125,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2754807472229004,
      "learning_rate": 4.482126462717289e-05,
      "loss": 0.9306640625,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.19679869711399078,
      "learning_rate": 4.403241839441901e-05,
      "loss": 0.627197265625,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.31440937519073486,
      "learning_rate": 4.319670922553716e-05,
      "loss": 1.02197265625,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.21160554885864258,
      "learning_rate": 4.2316506028963374e-05,
      "loss": 0.625,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.18778546154499054,
      "learning_rate": 4.139430383628932e-05,
      "loss": 0.626220703125,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.2859490215778351,
      "learning_rate": 4.043271672982416e-05,
      "loss": 0.911865234375,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.32474955916404724,
      "learning_rate": 3.9434470432694206e-05,
      "loss": 1.1572265625,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.29572197794914246,
      "learning_rate": 3.840239458248463e-05,
      "loss": 0.9375,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.337645560503006,
      "learning_rate": 3.733941471032425e-05,
      "loss": 1.09228515625,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.3162105083465576,
      "learning_rate": 3.624854394814972e-05,
      "loss": 0.98486328125,
      "step": 27
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 0.68505859375,
      "eval_runtime": 6.934,
      "eval_samples_per_second": 0.433,
      "eval_steps_per_second": 0.144,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.32920169830322266,
      "learning_rate": 3.5132874487655685e-05,
      "loss": 0.9638671875,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.31738510727882385,
      "learning_rate": 3.3995568815141475e-05,
      "loss": 0.897216796875,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.3534000515937805,
      "learning_rate": 3.283985074710009e-05,
      "loss": 1.0439453125,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.1297687441110611,
      "learning_rate": 3.1668996291960073e-05,
      "loss": 0.46630859375,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.3024066686630249,
      "learning_rate": 3.0486324363883744e-05,
      "loss": 0.9208984375,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.3092036843299866,
      "learning_rate": 2.929518737494437e-05,
      "loss": 0.880615234375,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.26634103059768677,
      "learning_rate": 2.8098961732349938e-05,
      "loss": 0.8994140625,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.1544313281774521,
      "learning_rate": 2.6901038267650068e-05,
      "loss": 0.507080078125,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.12492088973522186,
      "learning_rate": 2.570481262505563e-05,
      "loss": 0.4268798828125,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.3151899576187134,
      "learning_rate": 2.451367563611626e-05,
      "loss": 0.99658203125,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.3599281907081604,
      "learning_rate": 2.3331003708039932e-05,
      "loss": 0.9140625,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.2778172492980957,
      "learning_rate": 2.2160149252899913e-05,
      "loss": 0.77880859375,
      "step": 39
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 0.650146484375,
      "eval_runtime": 6.9614,
      "eval_samples_per_second": 0.431,
      "eval_steps_per_second": 0.144,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.1729755997657776,
      "learning_rate": 2.1004431184858537e-05,
      "loss": 0.55126953125,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.271622896194458,
      "learning_rate": 1.986712551234432e-05,
      "loss": 0.870361328125,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2445545345544815,
      "learning_rate": 1.8751456051850286e-05,
      "loss": 0.51806640625,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.19641229510307312,
      "learning_rate": 1.7660585289675758e-05,
      "loss": 0.525634765625,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.296785444021225,
      "learning_rate": 1.6597605417515376e-05,
      "loss": 0.773681640625,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.3932756781578064,
      "learning_rate": 1.5565529567305796e-05,
      "loss": 0.98486328125,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.3204335570335388,
      "learning_rate": 1.4567283270175847e-05,
      "loss": 0.796630859375,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.3055640757083893,
      "learning_rate": 1.3605696163710686e-05,
      "loss": 0.944091796875,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.3195129930973053,
      "learning_rate": 1.2683493971036633e-05,
      "loss": 0.847412109375,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.3543568551540375,
      "learning_rate": 1.1803290774462848e-05,
      "loss": 0.82666015625,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.3553006649017334,
      "learning_rate": 1.0967581605580993e-05,
      "loss": 0.76568603515625,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 1.970801591873169,
      "learning_rate": 1.0178735372827107e-05,
      "loss": 0.90185546875,
      "step": 51
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 0.634033203125,
      "eval_runtime": 6.9461,
      "eval_samples_per_second": 0.432,
      "eval_steps_per_second": 0.144,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.1519669145345688,
      "learning_rate": 9.438988146553323e-06,
      "loss": 0.433349609375,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.3140393793582916,
      "learning_rate": 8.750436820643412e-06,
      "loss": 0.8173828125,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.3270789086818695,
      "learning_rate": 8.115033168639362e-06,
      "loss": 0.7716064453125,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.30802422761917114,
      "learning_rate": 7.534578311227143e-06,
      "loss": 0.81005859375,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.17056985199451447,
      "learning_rate": 7.010717610764453e-06,
      "loss": 0.470703125,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.1402541548013687,
      "learning_rate": 6.5449360073223855e-06,
      "loss": 0.40234375,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.3359140157699585,
      "learning_rate": 6.138553809461422e-06,
      "loss": 0.9013671875,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.3612743318080902,
      "learning_rate": 5.792722951673392e-06,
      "loss": 0.8173828125,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.2949378788471222,
      "learning_rate": 5.5084237290980005e-06,
      "loss": 0.70947265625,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.1847359985113144,
      "learning_rate": 5.286462018769748e-06,
      "loss": 0.524169921875,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.29889002442359924,
      "learning_rate": 5.127466995271916e-06,
      "loss": 0.808837890625,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.1996440291404724,
      "learning_rate": 5.031889347272857e-06,
      "loss": 0.47119140625,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.62548828125,
      "eval_runtime": 6.9491,
      "eval_samples_per_second": 0.432,
      "eval_steps_per_second": 0.144,
      "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": 6.233815874587853e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}