{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13614703880190607,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005104645227156713,
      "grad_norm": 24.05441665649414,
      "learning_rate": 0.0,
      "loss": 2.0061,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 139.53,
      "memory/max_allocated (GiB)": 139.53,
      "step": 1
    },
    {
      "epoch": 0.0010209290454313426,
      "grad_norm": 7.6078009605407715,
      "learning_rate": 1.0309278350515465e-07,
      "loss": 1.8967,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 2
    },
    {
      "epoch": 0.0015313935681470138,
      "grad_norm": 8.540678977966309,
      "learning_rate": 2.061855670103093e-07,
      "loss": 1.7939,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 3
    },
    {
      "epoch": 0.002041858090862685,
      "grad_norm": 16.590530395507812,
      "learning_rate": 3.0927835051546394e-07,
      "loss": 1.9599,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 4
    },
    {
      "epoch": 0.002552322613578356,
      "grad_norm": 7.192079544067383,
      "learning_rate": 4.123711340206186e-07,
      "loss": 1.8068,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 5
    },
    {
      "epoch": 0.0030627871362940277,
      "grad_norm": 8.165936470031738,
      "learning_rate": 5.154639175257732e-07,
      "loss": 1.8497,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 6
    },
    {
      "epoch": 0.0035732516590096988,
      "grad_norm": 8.299514770507812,
      "learning_rate": 6.185567010309279e-07,
      "loss": 1.7926,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 7
    },
    {
      "epoch": 0.00408371618172537,
      "grad_norm": 6.091303825378418,
      "learning_rate": 7.216494845360824e-07,
      "loss": 1.8695,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 8
    },
    {
      "epoch": 0.004594180704441042,
      "grad_norm": 16.246517181396484,
      "learning_rate": 8.247422680412372e-07,
      "loss": 1.9153,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 9
    },
    {
      "epoch": 0.005104645227156712,
      "grad_norm": 7.1781325340271,
      "learning_rate": 9.278350515463919e-07,
      "loss": 1.7798,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 10
    },
    {
      "epoch": 0.005615109749872384,
      "grad_norm": 2.5561985969543457,
      "learning_rate": 1.0309278350515464e-06,
      "loss": 1.8484,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 11
    },
    {
      "epoch": 0.006125574272588055,
      "grad_norm": 2.5366039276123047,
      "learning_rate": 1.134020618556701e-06,
      "loss": 1.8163,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 12
    },
    {
      "epoch": 0.006636038795303726,
      "grad_norm": 2.0043585300445557,
      "learning_rate": 1.2371134020618557e-06,
      "loss": 1.8295,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 13
    },
    {
      "epoch": 0.0071465033180193975,
      "grad_norm": 1.26850426197052,
      "learning_rate": 1.3402061855670104e-06,
      "loss": 1.8045,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 14
    },
    {
      "epoch": 0.007656967840735069,
      "grad_norm": 1.0957386493682861,
      "learning_rate": 1.4432989690721649e-06,
      "loss": 1.7863,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 15
    },
    {
      "epoch": 0.00816743236345074,
      "grad_norm": 1.302420735359192,
      "learning_rate": 1.5463917525773197e-06,
      "loss": 1.7876,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 16
    },
    {
      "epoch": 0.008677896886166412,
      "grad_norm": 0.9507644176483154,
      "learning_rate": 1.6494845360824744e-06,
      "loss": 1.7966,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 17
    },
    {
      "epoch": 0.009188361408882083,
      "grad_norm": 1.1378878355026245,
      "learning_rate": 1.7525773195876288e-06,
      "loss": 1.8161,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 18
    },
    {
      "epoch": 0.009698825931597753,
      "grad_norm": 1.7316354513168335,
      "learning_rate": 1.8556701030927837e-06,
      "loss": 1.7439,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 19
    },
    {
      "epoch": 0.010209290454313425,
      "grad_norm": 1.0558087825775146,
      "learning_rate": 1.9587628865979384e-06,
      "loss": 1.7623,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 20
    },
    {
      "epoch": 0.010719754977029096,
      "grad_norm": 0.9555009603500366,
      "learning_rate": 2.061855670103093e-06,
      "loss": 1.6405,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 21
    },
    {
      "epoch": 0.011230219499744768,
      "grad_norm": 1.0347907543182373,
      "learning_rate": 2.1649484536082477e-06,
      "loss": 1.7348,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 22
    },
    {
      "epoch": 0.01174068402246044,
      "grad_norm": 1.1328850984573364,
      "learning_rate": 2.268041237113402e-06,
      "loss": 1.847,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 23
    },
    {
      "epoch": 0.01225114854517611,
      "grad_norm": 1.0314826965332031,
      "learning_rate": 2.3711340206185566e-06,
      "loss": 1.7493,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 24
    },
    {
      "epoch": 0.012761613067891782,
      "grad_norm": 1.158893346786499,
      "learning_rate": 2.4742268041237115e-06,
      "loss": 1.7491,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 25
    },
    {
      "epoch": 0.013272077590607452,
      "grad_norm": 1.144657015800476,
      "learning_rate": 2.577319587628866e-06,
      "loss": 1.8281,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 26
    },
    {
      "epoch": 0.013782542113323124,
      "grad_norm": 0.9864128828048706,
      "learning_rate": 2.680412371134021e-06,
      "loss": 1.7979,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 27
    },
    {
      "epoch": 0.014293006636038795,
      "grad_norm": 0.9023644328117371,
      "learning_rate": 2.7835051546391757e-06,
      "loss": 1.7567,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 28
    },
    {
      "epoch": 0.014803471158754467,
      "grad_norm": 1.0202115774154663,
      "learning_rate": 2.8865979381443297e-06,
      "loss": 1.7217,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 29
    },
    {
      "epoch": 0.015313935681470138,
      "grad_norm": 1.4286682605743408,
      "learning_rate": 2.9896907216494846e-06,
      "loss": 1.7248,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 30
    },
    {
      "epoch": 0.01582440020418581,
      "grad_norm": 0.8136070966720581,
      "learning_rate": 3.0927835051546395e-06,
      "loss": 1.6771,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 31
    },
    {
      "epoch": 0.01633486472690148,
      "grad_norm": 0.9729646444320679,
      "learning_rate": 3.195876288659794e-06,
      "loss": 1.7832,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 32
    },
    {
      "epoch": 0.016845329249617153,
      "grad_norm": 1.1746621131896973,
      "learning_rate": 3.298969072164949e-06,
      "loss": 1.7123,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 33
    },
    {
      "epoch": 0.017355793772332824,
      "grad_norm": 0.813364565372467,
      "learning_rate": 3.4020618556701037e-06,
      "loss": 1.7838,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 34
    },
    {
      "epoch": 0.017866258295048495,
      "grad_norm": 0.9410524368286133,
      "learning_rate": 3.5051546391752577e-06,
      "loss": 1.7666,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 35
    },
    {
      "epoch": 0.018376722817764167,
      "grad_norm": 0.7961885929107666,
      "learning_rate": 3.6082474226804126e-06,
      "loss": 1.7823,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 36
    },
    {
      "epoch": 0.018887187340479835,
      "grad_norm": 0.8009322881698608,
      "learning_rate": 3.7113402061855674e-06,
      "loss": 1.7066,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 37
    },
    {
      "epoch": 0.019397651863195507,
      "grad_norm": 0.9726182222366333,
      "learning_rate": 3.814432989690722e-06,
      "loss": 1.7448,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 38
    },
    {
      "epoch": 0.019908116385911178,
      "grad_norm": 0.9403437972068787,
      "learning_rate": 3.917525773195877e-06,
      "loss": 1.8017,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 39
    },
    {
      "epoch": 0.02041858090862685,
      "grad_norm": 0.9949467182159424,
      "learning_rate": 4.020618556701032e-06,
      "loss": 1.6682,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 40
    },
    {
      "epoch": 0.02092904543134252,
      "grad_norm": 0.8237268328666687,
      "learning_rate": 4.123711340206186e-06,
      "loss": 1.7786,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 41
    },
    {
      "epoch": 0.021439509954058193,
      "grad_norm": 0.774246871471405,
      "learning_rate": 4.2268041237113405e-06,
      "loss": 1.7255,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 42
    },
    {
      "epoch": 0.021949974476773864,
      "grad_norm": 1.031959891319275,
      "learning_rate": 4.329896907216495e-06,
      "loss": 1.7181,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 43
    },
    {
      "epoch": 0.022460438999489536,
      "grad_norm": 1.1743037700653076,
      "learning_rate": 4.4329896907216494e-06,
      "loss": 1.7398,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 44
    },
    {
      "epoch": 0.022970903522205207,
      "grad_norm": 0.8437848091125488,
      "learning_rate": 4.536082474226804e-06,
      "loss": 1.8505,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 45
    },
    {
      "epoch": 0.02348136804492088,
      "grad_norm": 0.971718430519104,
      "learning_rate": 4.639175257731959e-06,
      "loss": 1.7237,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 46
    },
    {
      "epoch": 0.02399183256763655,
      "grad_norm": 0.9551330208778381,
      "learning_rate": 4.742268041237113e-06,
      "loss": 1.6944,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 47
    },
    {
      "epoch": 0.02450229709035222,
      "grad_norm": 1.007398009300232,
      "learning_rate": 4.845360824742268e-06,
      "loss": 1.744,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 48
    },
    {
      "epoch": 0.025012761613067893,
      "grad_norm": 0.7662305235862732,
      "learning_rate": 4.948453608247423e-06,
      "loss": 1.684,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 49
    },
    {
      "epoch": 0.025523226135783564,
      "grad_norm": 0.8253554105758667,
      "learning_rate": 5.051546391752578e-06,
      "loss": 1.7711,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 50
    },
    {
      "epoch": 0.026033690658499236,
      "grad_norm": 0.8845403790473938,
      "learning_rate": 5.154639175257732e-06,
      "loss": 1.8203,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 51
    },
    {
      "epoch": 0.026544155181214904,
      "grad_norm": 0.8738449215888977,
      "learning_rate": 5.257731958762888e-06,
      "loss": 1.6307,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 52
    },
    {
      "epoch": 0.027054619703930576,
      "grad_norm": 0.711958646774292,
      "learning_rate": 5.360824742268042e-06,
      "loss": 1.7172,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 53
    },
    {
      "epoch": 0.027565084226646247,
      "grad_norm": 0.7549559473991394,
      "learning_rate": 5.463917525773196e-06,
      "loss": 1.755,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 54
    },
    {
      "epoch": 0.02807554874936192,
      "grad_norm": 0.7762870192527771,
      "learning_rate": 5.567010309278351e-06,
      "loss": 1.6802,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 55
    },
    {
      "epoch": 0.02858601327207759,
      "grad_norm": 0.8023381233215332,
      "learning_rate": 5.670103092783505e-06,
      "loss": 1.698,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 56
    },
    {
      "epoch": 0.02909647779479326,
      "grad_norm": 0.865761399269104,
      "learning_rate": 5.7731958762886594e-06,
      "loss": 1.6885,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 57
    },
    {
      "epoch": 0.029606942317508933,
      "grad_norm": 1.0811809301376343,
      "learning_rate": 5.876288659793815e-06,
      "loss": 1.6592,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 58
    },
    {
      "epoch": 0.030117406840224605,
      "grad_norm": 0.9070002436637878,
      "learning_rate": 5.979381443298969e-06,
      "loss": 1.7564,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 59
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": 1.04336416721344,
      "learning_rate": 6.082474226804124e-06,
      "loss": 1.7126,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 60
    },
    {
      "epoch": 0.031138335885655948,
      "grad_norm": 1.3839117288589478,
      "learning_rate": 6.185567010309279e-06,
      "loss": 1.6491,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 61
    },
    {
      "epoch": 0.03164880040837162,
      "grad_norm": 0.7790964841842651,
      "learning_rate": 6.288659793814433e-06,
      "loss": 1.7819,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 62
    },
    {
      "epoch": 0.03215926493108729,
      "grad_norm": 1.3247586488723755,
      "learning_rate": 6.391752577319588e-06,
      "loss": 1.7544,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 63
    },
    {
      "epoch": 0.03266972945380296,
      "grad_norm": 1.272275686264038,
      "learning_rate": 6.494845360824743e-06,
      "loss": 1.7166,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 64
    },
    {
      "epoch": 0.033180193976518634,
      "grad_norm": 1.0625935792922974,
      "learning_rate": 6.597938144329898e-06,
      "loss": 1.8027,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 65
    },
    {
      "epoch": 0.033690658499234305,
      "grad_norm": 1.3712449073791504,
      "learning_rate": 6.701030927835052e-06,
      "loss": 1.6856,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 66
    },
    {
      "epoch": 0.034201123021949976,
      "grad_norm": 13.220693588256836,
      "learning_rate": 6.804123711340207e-06,
      "loss": 1.8061,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 67
    },
    {
      "epoch": 0.03471158754466565,
      "grad_norm": 1.3873469829559326,
      "learning_rate": 6.907216494845361e-06,
      "loss": 1.6946,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 68
    },
    {
      "epoch": 0.03522205206738132,
      "grad_norm": 0.8954477310180664,
      "learning_rate": 7.010309278350515e-06,
      "loss": 1.5911,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 69
    },
    {
      "epoch": 0.03573251659009699,
      "grad_norm": 1.6247202157974243,
      "learning_rate": 7.113402061855671e-06,
      "loss": 1.6588,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 70
    },
    {
      "epoch": 0.03624298111281266,
      "grad_norm": 1.2285557985305786,
      "learning_rate": 7.216494845360825e-06,
      "loss": 1.7729,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 71
    },
    {
      "epoch": 0.036753445635528334,
      "grad_norm": 1.0797786712646484,
      "learning_rate": 7.319587628865979e-06,
      "loss": 1.6978,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 72
    },
    {
      "epoch": 0.037263910158244005,
      "grad_norm": 1.8204232454299927,
      "learning_rate": 7.422680412371135e-06,
      "loss": 1.6912,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 73
    },
    {
      "epoch": 0.03777437468095967,
      "grad_norm": 3.366705894470215,
      "learning_rate": 7.525773195876289e-06,
      "loss": 1.7523,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 74
    },
    {
      "epoch": 0.03828483920367534,
      "grad_norm": 1.5358184576034546,
      "learning_rate": 7.628865979381444e-06,
      "loss": 1.7172,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 75
    },
    {
      "epoch": 0.03879530372639101,
      "grad_norm": 0.8976320028305054,
      "learning_rate": 7.731958762886599e-06,
      "loss": 1.7073,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 76
    },
    {
      "epoch": 0.039305768249106685,
      "grad_norm": 0.8933356404304504,
      "learning_rate": 7.835051546391754e-06,
      "loss": 1.6702,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 77
    },
    {
      "epoch": 0.039816232771822356,
      "grad_norm": 1.2677210569381714,
      "learning_rate": 7.938144329896907e-06,
      "loss": 1.7786,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 78
    },
    {
      "epoch": 0.04032669729453803,
      "grad_norm": 0.8787310719490051,
      "learning_rate": 8.041237113402063e-06,
      "loss": 1.6648,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 79
    },
    {
      "epoch": 0.0408371618172537,
      "grad_norm": 1.032422661781311,
      "learning_rate": 8.144329896907216e-06,
      "loss": 1.7612,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 80
    },
    {
      "epoch": 0.04134762633996937,
      "grad_norm": 0.8892786502838135,
      "learning_rate": 8.247422680412371e-06,
      "loss": 1.7551,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 81
    },
    {
      "epoch": 0.04185809086268504,
      "grad_norm": 1.0008693933486938,
      "learning_rate": 8.350515463917526e-06,
      "loss": 1.7573,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 82
    },
    {
      "epoch": 0.042368555385400714,
      "grad_norm": 0.9513587951660156,
      "learning_rate": 8.453608247422681e-06,
      "loss": 1.7052,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 83
    },
    {
      "epoch": 0.042879019908116385,
      "grad_norm": 0.8307821154594421,
      "learning_rate": 8.556701030927836e-06,
      "loss": 1.7634,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 84
    },
    {
      "epoch": 0.043389484430832057,
      "grad_norm": 0.8338541388511658,
      "learning_rate": 8.65979381443299e-06,
      "loss": 1.699,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 85
    },
    {
      "epoch": 0.04389994895354773,
      "grad_norm": 0.9660134315490723,
      "learning_rate": 8.762886597938146e-06,
      "loss": 1.6446,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 86
    },
    {
      "epoch": 0.0444104134762634,
      "grad_norm": 1.0152493715286255,
      "learning_rate": 8.865979381443299e-06,
      "loss": 1.7269,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 87
    },
    {
      "epoch": 0.04492087799897907,
      "grad_norm": 1.0614452362060547,
      "learning_rate": 8.969072164948455e-06,
      "loss": 1.6373,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 88
    },
    {
      "epoch": 0.04543134252169474,
      "grad_norm": 4.689784526824951,
      "learning_rate": 9.072164948453609e-06,
      "loss": 1.8024,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 89
    },
    {
      "epoch": 0.045941807044410414,
      "grad_norm": 2.7629218101501465,
      "learning_rate": 9.175257731958764e-06,
      "loss": 1.7774,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 90
    },
    {
      "epoch": 0.046452271567126086,
      "grad_norm": 1.2467944622039795,
      "learning_rate": 9.278350515463918e-06,
      "loss": 1.7005,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 91
    },
    {
      "epoch": 0.04696273608984176,
      "grad_norm": 1.175451636314392,
      "learning_rate": 9.381443298969073e-06,
      "loss": 1.708,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 92
    },
    {
      "epoch": 0.04747320061255743,
      "grad_norm": 36.13218307495117,
      "learning_rate": 9.484536082474226e-06,
      "loss": 1.9211,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 93
    },
    {
      "epoch": 0.0479836651352731,
      "grad_norm": 1.6346375942230225,
      "learning_rate": 9.587628865979383e-06,
      "loss": 1.6819,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 94
    },
    {
      "epoch": 0.04849412965798877,
      "grad_norm": 1.2270629405975342,
      "learning_rate": 9.690721649484536e-06,
      "loss": 1.5809,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 95
    },
    {
      "epoch": 0.04900459418070444,
      "grad_norm": 1.4751657247543335,
      "learning_rate": 9.793814432989691e-06,
      "loss": 1.7517,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 96
    },
    {
      "epoch": 0.049515058703420115,
      "grad_norm": 1.174103856086731,
      "learning_rate": 9.896907216494846e-06,
      "loss": 1.6645,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 97
    },
    {
      "epoch": 0.050025523226135786,
      "grad_norm": 1.0809050798416138,
      "learning_rate": 1e-05,
      "loss": 1.7526,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 98
    },
    {
      "epoch": 0.05053598774885146,
      "grad_norm": 0.9332408308982849,
      "learning_rate": 9.999992883273144e-06,
      "loss": 1.717,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 99
    },
    {
      "epoch": 0.05104645227156713,
      "grad_norm": 0.9629523754119873,
      "learning_rate": 9.999971533112832e-06,
      "loss": 1.6674,
      "memory/device_reserved (GiB)": 192.97,
      "memory/max_active (GiB)": 151.03,
      "memory/max_allocated (GiB)": 151.03,
      "step": 100
    },
    {
      "epoch": 0.06875425459496257,
      "grad_norm": 0.9861069321632385,
      "learning_rate": 9.999935949579843e-06,
      "loss": 1.7583,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 101
    },
    {
      "epoch": 0.06943498978897208,
      "grad_norm": 1.425486445426941,
      "learning_rate": 9.898346201737316e-06,
      "loss": 1.7852,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 102
    },
    {
      "epoch": 0.07011572498298162,
      "grad_norm": 1.648892879486084,
      "learning_rate": 9.896179406315343e-06,
      "loss": 1.6976,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 103
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 1.883970022201538,
      "learning_rate": 9.893990002892777e-06,
      "loss": 1.7738,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 104
    },
    {
      "epoch": 0.07147719537100068,
      "grad_norm": 1.1324390172958374,
      "learning_rate": 9.891778001579136e-06,
      "loss": 1.7525,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 105
    },
    {
      "epoch": 0.07215793056501021,
      "grad_norm": 1.5833842754364014,
      "learning_rate": 9.88954341258829e-06,
      "loss": 1.7709,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 106
    },
    {
      "epoch": 0.07283866575901975,
      "grad_norm": 1.1700878143310547,
      "learning_rate": 9.887286246238406e-06,
      "loss": 1.7962,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 107
    },
    {
      "epoch": 0.07351940095302927,
      "grad_norm": 1.573387861251831,
      "learning_rate": 9.885006512951898e-06,
      "loss": 1.7308,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 108
    },
    {
      "epoch": 0.0742001361470388,
      "grad_norm": 2.2107796669006348,
      "learning_rate": 9.882704223255383e-06,
      "loss": 1.7296,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 109
    },
    {
      "epoch": 0.07488087134104833,
      "grad_norm": 0.7726507186889648,
      "learning_rate": 9.880379387779637e-06,
      "loss": 1.7369,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 110
    },
    {
      "epoch": 0.07556160653505786,
      "grad_norm": 1.3989717960357666,
      "learning_rate": 9.878032017259533e-06,
      "loss": 1.7628,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 111
    },
    {
      "epoch": 0.0762423417290674,
      "grad_norm": 0.7562165260314941,
      "learning_rate": 9.875662122534004e-06,
      "loss": 1.6657,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 112
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.1455652713775635,
      "learning_rate": 9.873269714545986e-06,
      "loss": 1.7242,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 113
    },
    {
      "epoch": 0.07760381211708646,
      "grad_norm": 0.7659608721733093,
      "learning_rate": 9.87085480434237e-06,
      "loss": 1.6782,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 114
    },
    {
      "epoch": 0.07828454731109598,
      "grad_norm": 1.2639816999435425,
      "learning_rate": 9.868417403073954e-06,
      "loss": 1.7197,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 115
    },
    {
      "epoch": 0.07896528250510551,
      "grad_norm": 0.8840866088867188,
      "learning_rate": 9.86595752199538e-06,
      "loss": 1.7588,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 116
    },
    {
      "epoch": 0.07964601769911504,
      "grad_norm": 0.9605395793914795,
      "learning_rate": 9.863475172465096e-06,
      "loss": 1.746,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 117
    },
    {
      "epoch": 0.08032675289312458,
      "grad_norm": 1.208536148071289,
      "learning_rate": 9.8609703659453e-06,
      "loss": 1.8172,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 118
    },
    {
      "epoch": 0.08100748808713411,
      "grad_norm": 0.9458699226379395,
      "learning_rate": 9.858443114001876e-06,
      "loss": 1.6307,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 119
    },
    {
      "epoch": 0.08168822328114364,
      "grad_norm": 6.640661239624023,
      "learning_rate": 9.855893428304357e-06,
      "loss": 1.7085,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 120
    },
    {
      "epoch": 0.08236895847515316,
      "grad_norm": 4.13405704498291,
      "learning_rate": 9.853321320625859e-06,
      "loss": 1.7143,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 121
    },
    {
      "epoch": 0.08304969366916269,
      "grad_norm": 1.9490628242492676,
      "learning_rate": 9.850726802843035e-06,
      "loss": 1.7832,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 122
    },
    {
      "epoch": 0.08373042886317222,
      "grad_norm": 0.9990502595901489,
      "learning_rate": 9.848109886936011e-06,
      "loss": 1.6934,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 123
    },
    {
      "epoch": 0.08441116405718176,
      "grad_norm": 1.1732097864151,
      "learning_rate": 9.84547058498834e-06,
      "loss": 1.7131,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 124
    },
    {
      "epoch": 0.08509189925119129,
      "grad_norm": 0.9427511692047119,
      "learning_rate": 9.842808909186941e-06,
      "loss": 1.73,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 125
    },
    {
      "epoch": 0.08577263444520082,
      "grad_norm": 1.0290261507034302,
      "learning_rate": 9.84012487182204e-06,
      "loss": 1.7099,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 126
    },
    {
      "epoch": 0.08645336963921035,
      "grad_norm": 0.9603204727172852,
      "learning_rate": 9.837418485287126e-06,
      "loss": 1.7028,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 127
    },
    {
      "epoch": 0.08713410483321987,
      "grad_norm": 1.0807061195373535,
      "learning_rate": 9.834689762078877e-06,
      "loss": 1.6857,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 128
    },
    {
      "epoch": 0.0878148400272294,
      "grad_norm": 1.2012745141983032,
      "learning_rate": 9.83193871479711e-06,
      "loss": 1.7612,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 129
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 1.2601819038391113,
      "learning_rate": 9.829165356144728e-06,
      "loss": 1.7485,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 130
    },
    {
      "epoch": 0.08917631041524847,
      "grad_norm": 0.7284013628959656,
      "learning_rate": 9.82636969892765e-06,
      "loss": 1.7126,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 131
    },
    {
      "epoch": 0.089857045609258,
      "grad_norm": 1.1513925790786743,
      "learning_rate": 9.823551756054768e-06,
      "loss": 1.7005,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 132
    },
    {
      "epoch": 0.09053778080326753,
      "grad_norm": 0.660559356212616,
      "learning_rate": 9.820711540537866e-06,
      "loss": 1.6811,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 133
    },
    {
      "epoch": 0.09121851599727705,
      "grad_norm": 1.0490988492965698,
      "learning_rate": 9.817849065491576e-06,
      "loss": 1.7433,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 134
    },
    {
      "epoch": 0.09189925119128659,
      "grad_norm": 0.8521629571914673,
      "learning_rate": 9.814964344133318e-06,
      "loss": 1.7245,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 135
    },
    {
      "epoch": 0.09257998638529612,
      "grad_norm": 0.8048623204231262,
      "learning_rate": 9.812057389783225e-06,
      "loss": 1.7915,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 136
    },
    {
      "epoch": 0.09326072157930565,
      "grad_norm": 0.8406012654304504,
      "learning_rate": 9.809128215864096e-06,
      "loss": 1.7127,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 137
    },
    {
      "epoch": 0.09394145677331518,
      "grad_norm": 1.0638079643249512,
      "learning_rate": 9.806176835901329e-06,
      "loss": 1.6889,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 138
    },
    {
      "epoch": 0.09462219196732471,
      "grad_norm": 0.8079673647880554,
      "learning_rate": 9.803203263522854e-06,
      "loss": 1.7144,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 139
    },
    {
      "epoch": 0.09530292716133425,
      "grad_norm": 0.6343026161193848,
      "learning_rate": 9.800207512459076e-06,
      "loss": 1.6674,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 140
    },
    {
      "epoch": 0.09598366235534377,
      "grad_norm": 0.8282296657562256,
      "learning_rate": 9.797189596542809e-06,
      "loss": 1.6704,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 141
    },
    {
      "epoch": 0.0966643975493533,
      "grad_norm": 0.7079451084136963,
      "learning_rate": 9.794149529709217e-06,
      "loss": 1.7305,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 142
    },
    {
      "epoch": 0.09734513274336283,
      "grad_norm": 0.6755410432815552,
      "learning_rate": 9.791087325995737e-06,
      "loss": 1.6668,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 143
    },
    {
      "epoch": 0.09802586793737236,
      "grad_norm": 1.338319182395935,
      "learning_rate": 9.78800299954203e-06,
      "loss": 1.674,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 144
    },
    {
      "epoch": 0.0987066031313819,
      "grad_norm": 0.8062757253646851,
      "learning_rate": 9.784896564589905e-06,
      "loss": 1.6971,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 145
    },
    {
      "epoch": 0.09938733832539143,
      "grad_norm": 0.7266926169395447,
      "learning_rate": 9.781768035483256e-06,
      "loss": 1.7531,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 146
    },
    {
      "epoch": 0.10006807351940095,
      "grad_norm": 0.946113109588623,
      "learning_rate": 9.778617426667998e-06,
      "loss": 1.7512,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 147
    },
    {
      "epoch": 0.10074880871341048,
      "grad_norm": 0.7514466643333435,
      "learning_rate": 9.775444752691998e-06,
      "loss": 1.6771,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 148
    },
    {
      "epoch": 0.10142954390742001,
      "grad_norm": 1.0235679149627686,
      "learning_rate": 9.772250028205009e-06,
      "loss": 1.6477,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 149
    },
    {
      "epoch": 0.10211027910142954,
      "grad_norm": 0.7400968074798584,
      "learning_rate": 9.769033267958598e-06,
      "loss": 1.7386,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 150
    },
    {
      "epoch": 0.10279101429543908,
      "grad_norm": 0.8439730405807495,
      "learning_rate": 9.765794486806089e-06,
      "loss": 1.6702,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 151
    },
    {
      "epoch": 0.10347174948944861,
      "grad_norm": 0.9278808236122131,
      "learning_rate": 9.76253369970248e-06,
      "loss": 1.756,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 152
    },
    {
      "epoch": 0.10415248468345814,
      "grad_norm": 0.7247333526611328,
      "learning_rate": 9.759250921704382e-06,
      "loss": 1.7133,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 153
    },
    {
      "epoch": 0.10483321987746766,
      "grad_norm": 0.7844570279121399,
      "learning_rate": 9.755946167969952e-06,
      "loss": 1.6426,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 154
    },
    {
      "epoch": 0.10551395507147719,
      "grad_norm": 0.878671407699585,
      "learning_rate": 9.752619453758818e-06,
      "loss": 1.7451,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 155
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 0.8259819149971008,
      "learning_rate": 9.749270794432011e-06,
      "loss": 1.7338,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 156
    },
    {
      "epoch": 0.10687542545949626,
      "grad_norm": 1.142391324043274,
      "learning_rate": 9.745900205451888e-06,
      "loss": 1.6637,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 157
    },
    {
      "epoch": 0.10755616065350579,
      "grad_norm": 0.8899725079536438,
      "learning_rate": 9.74250770238207e-06,
      "loss": 1.6494,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 158
    },
    {
      "epoch": 0.10823689584751532,
      "grad_norm": 0.7415008544921875,
      "learning_rate": 9.73909330088737e-06,
      "loss": 1.6499,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 159
    },
    {
      "epoch": 0.10891763104152484,
      "grad_norm": 0.7182707786560059,
      "learning_rate": 9.735657016733706e-06,
      "loss": 1.7394,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 160
    },
    {
      "epoch": 0.10959836623553437,
      "grad_norm": 0.9890943169593811,
      "learning_rate": 9.732198865788047e-06,
      "loss": 1.7266,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 161
    },
    {
      "epoch": 0.1102791014295439,
      "grad_norm": 0.9935751557350159,
      "learning_rate": 9.72871886401833e-06,
      "loss": 1.6527,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 162
    },
    {
      "epoch": 0.11095983662355344,
      "grad_norm": 0.7096329927444458,
      "learning_rate": 9.725217027493383e-06,
      "loss": 1.667,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 163
    },
    {
      "epoch": 0.11164057181756297,
      "grad_norm": 0.8332772850990295,
      "learning_rate": 9.721693372382863e-06,
      "loss": 1.7337,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 164
    },
    {
      "epoch": 0.1123213070115725,
      "grad_norm": 0.7919803857803345,
      "learning_rate": 9.718147914957166e-06,
      "loss": 1.576,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 165
    },
    {
      "epoch": 0.11300204220558203,
      "grad_norm": 0.8618379235267639,
      "learning_rate": 9.714580671587366e-06,
      "loss": 1.6249,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 166
    },
    {
      "epoch": 0.11368277739959155,
      "grad_norm": 0.7667165994644165,
      "learning_rate": 9.71099165874513e-06,
      "loss": 1.6761,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 167
    },
    {
      "epoch": 0.11436351259360109,
      "grad_norm": 0.6841418147087097,
      "learning_rate": 9.707380893002647e-06,
      "loss": 1.6868,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 168
    },
    {
      "epoch": 0.11504424778761062,
      "grad_norm": 0.6731845140457153,
      "learning_rate": 9.703748391032548e-06,
      "loss": 1.7487,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 169
    },
    {
      "epoch": 0.11572498298162015,
      "grad_norm": 0.7406771779060364,
      "learning_rate": 9.700094169607828e-06,
      "loss": 1.7071,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 170
    },
    {
      "epoch": 0.11640571817562968,
      "grad_norm": 0.7292412519454956,
      "learning_rate": 9.696418245601779e-06,
      "loss": 1.706,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 171
    },
    {
      "epoch": 0.11708645336963922,
      "grad_norm": 0.8011760711669922,
      "learning_rate": 9.692720635987893e-06,
      "loss": 1.7142,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 172
    },
    {
      "epoch": 0.11776718856364875,
      "grad_norm": 0.9184378385543823,
      "learning_rate": 9.689001357839807e-06,
      "loss": 1.7051,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 173
    },
    {
      "epoch": 0.11844792375765827,
      "grad_norm": 0.6435485482215881,
      "learning_rate": 9.685260428331203e-06,
      "loss": 1.736,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 174
    },
    {
      "epoch": 0.1191286589516678,
      "grad_norm": 0.8926677107810974,
      "learning_rate": 9.68149786473574e-06,
      "loss": 1.6661,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 175
    },
    {
      "epoch": 0.11980939414567733,
      "grad_norm": 0.6705238819122314,
      "learning_rate": 9.677713684426973e-06,
      "loss": 1.6917,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 176
    },
    {
      "epoch": 0.12049012933968686,
      "grad_norm": 0.6798558831214905,
      "learning_rate": 9.673907904878272e-06,
      "loss": 1.6402,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 177
    },
    {
      "epoch": 0.1211708645336964,
      "grad_norm": 0.6277421712875366,
      "learning_rate": 9.670080543662742e-06,
      "loss": 1.6738,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 178
    },
    {
      "epoch": 0.12185159972770593,
      "grad_norm": 0.6391667723655701,
      "learning_rate": 9.666231618453135e-06,
      "loss": 1.6823,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 179
    },
    {
      "epoch": 0.12253233492171545,
      "grad_norm": 0.6664396524429321,
      "learning_rate": 9.66236114702178e-06,
      "loss": 1.7058,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 180
    },
    {
      "epoch": 0.12321307011572498,
      "grad_norm": 1.5816713571548462,
      "learning_rate": 9.658469147240494e-06,
      "loss": 1.7435,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 181
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 8.72884750366211,
      "learning_rate": 9.654555637080503e-06,
      "loss": 1.6991,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 182
    },
    {
      "epoch": 0.12457454050374404,
      "grad_norm": 1.1152446269989014,
      "learning_rate": 9.65062063461235e-06,
      "loss": 1.7147,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 183
    },
    {
      "epoch": 0.12525527569775358,
      "grad_norm": 0.953542172908783,
      "learning_rate": 9.646664158005823e-06,
      "loss": 1.7064,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 184
    },
    {
      "epoch": 0.1259360108917631,
      "grad_norm": 0.8553478717803955,
      "learning_rate": 9.642686225529864e-06,
      "loss": 1.683,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 185
    },
    {
      "epoch": 0.12661674608577264,
      "grad_norm": 1.008264422416687,
      "learning_rate": 9.638686855552494e-06,
      "loss": 1.6093,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 186
    },
    {
      "epoch": 0.12729748127978216,
      "grad_norm": 0.8719388246536255,
      "learning_rate": 9.634666066540713e-06,
      "loss": 1.7384,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 187
    },
    {
      "epoch": 0.1279782164737917,
      "grad_norm": 1.1259270906448364,
      "learning_rate": 9.630623877060423e-06,
      "loss": 1.7397,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 188
    },
    {
      "epoch": 0.12865895166780122,
      "grad_norm": 1.1336485147476196,
      "learning_rate": 9.626560305776349e-06,
      "loss": 1.6912,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 189
    },
    {
      "epoch": 0.12933968686181074,
      "grad_norm": 1.1066447496414185,
      "learning_rate": 9.62247537145194e-06,
      "loss": 1.667,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 190
    },
    {
      "epoch": 0.1300204220558203,
      "grad_norm": 0.8986105918884277,
      "learning_rate": 9.618369092949289e-06,
      "loss": 1.7657,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 191
    },
    {
      "epoch": 0.1307011572498298,
      "grad_norm": 0.7317138314247131,
      "learning_rate": 9.61424148922905e-06,
      "loss": 1.6715,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 192
    },
    {
      "epoch": 0.13138189244383935,
      "grad_norm": 0.6420246362686157,
      "learning_rate": 9.610092579350339e-06,
      "loss": 1.6346,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 193
    },
    {
      "epoch": 0.13206262763784887,
      "grad_norm": 0.7444735765457153,
      "learning_rate": 9.605922382470659e-06,
      "loss": 1.6846,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 194
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": 0.9247352480888367,
      "learning_rate": 9.601730917845798e-06,
      "loss": 1.6513,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 195
    },
    {
      "epoch": 0.13342409802586794,
      "grad_norm": 0.7954132556915283,
      "learning_rate": 9.597518204829755e-06,
      "loss": 1.7392,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 196
    },
    {
      "epoch": 0.13410483321987746,
      "grad_norm": 0.7020078301429749,
      "learning_rate": 9.59328426287464e-06,
      "loss": 1.6942,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 197
    },
    {
      "epoch": 0.134785568413887,
      "grad_norm": 0.7420036792755127,
      "learning_rate": 9.589029111530585e-06,
      "loss": 1.7682,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 198
    },
    {
      "epoch": 0.13546630360789652,
      "grad_norm": 0.7332531213760376,
      "learning_rate": 9.584752770445658e-06,
      "loss": 1.7433,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 199
    },
    {
      "epoch": 0.13614703880190607,
      "grad_norm": 0.6352435946464539,
      "learning_rate": 9.58045525936577e-06,
      "loss": 1.706,
      "memory/device_reserved (GiB)": 234.63,
      "memory/max_active (GiB)": 186.82,
      "memory/max_allocated (GiB)": 186.82,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 1469,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5488598918372524e+19,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}