{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4990642545227698,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009981285090455396,
      "grad_norm": 3.6207456588745117,
      "learning_rate": 0.0,
      "loss": 2.1368,
      "memory/device_mem_reserved(gib)": 22.54,
      "memory/max_mem_active(gib)": 21.64,
      "memory/max_mem_allocated(gib)": 21.64,
      "step": 1
    },
    {
      "epoch": 0.019962570180910792,
      "grad_norm": 3.4113731384277344,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.1863,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 2
    },
    {
      "epoch": 0.02994385527136619,
      "grad_norm": 2.7534945011138916,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0607,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 3
    },
    {
      "epoch": 0.039925140361821584,
      "grad_norm": 1.3044390678405762,
      "learning_rate": 1.2e-05,
      "loss": 2.0696,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 4
    },
    {
      "epoch": 0.049906425452276984,
      "grad_norm": 1.0728504657745361,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.0523,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 5
    },
    {
      "epoch": 0.05988771054273238,
      "grad_norm": 1.2591698169708252,
      "learning_rate": 2e-05,
      "loss": 2.0477,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 6
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 0.8697449564933777,
      "learning_rate": 2.4e-05,
      "loss": 2.0703,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 7
    },
    {
      "epoch": 0.07985028072364317,
      "grad_norm": 0.7723014950752258,
      "learning_rate": 2.8e-05,
      "loss": 2.0812,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 8
    },
    {
      "epoch": 0.08983156581409857,
      "grad_norm": 0.7950255274772644,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.0739,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 9
    },
    {
      "epoch": 0.09981285090455397,
      "grad_norm": 0.7113617062568665,
      "learning_rate": 3.6e-05,
      "loss": 2.0721,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 10
    },
    {
      "epoch": 0.10979413599500935,
      "grad_norm": 0.5955151915550232,
      "learning_rate": 4e-05,
      "loss": 2.0413,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 11
    },
    {
      "epoch": 0.11977542108546475,
      "grad_norm": 0.7105816602706909,
      "learning_rate": 3.998781654038192e-05,
      "loss": 2.0175,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 12
    },
    {
      "epoch": 0.12975670617592014,
      "grad_norm": 0.6847625374794006,
      "learning_rate": 3.9951281005196486e-05,
      "loss": 2.0421,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 13
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 0.6292261481285095,
      "learning_rate": 3.989043790736547e-05,
      "loss": 1.9706,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 14
    },
    {
      "epoch": 0.14971927635683094,
      "grad_norm": 0.709656298160553,
      "learning_rate": 3.980536137483141e-05,
      "loss": 1.9926,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 15
    },
    {
      "epoch": 0.15970056144728634,
      "grad_norm": 0.7978456020355225,
      "learning_rate": 3.9696155060244166e-05,
      "loss": 2.0237,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 16
    },
    {
      "epoch": 0.16968184653774174,
      "grad_norm": 0.5705327987670898,
      "learning_rate": 3.9562952014676116e-05,
      "loss": 1.9824,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 17
    },
    {
      "epoch": 0.17966313162819714,
      "grad_norm": 0.5546987652778625,
      "learning_rate": 3.940591452551993e-05,
      "loss": 2.0687,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 18
    },
    {
      "epoch": 0.18964441671865254,
      "grad_norm": 0.5450860857963562,
      "learning_rate": 3.922523391876638e-05,
      "loss": 2.0185,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 19
    },
    {
      "epoch": 0.19962570180910794,
      "grad_norm": 0.5838854908943176,
      "learning_rate": 3.9021130325903076e-05,
      "loss": 2.0635,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 20
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 0.4847394824028015,
      "learning_rate": 3.879385241571817e-05,
      "loss": 2.0144,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 21
    },
    {
      "epoch": 0.2195882719900187,
      "grad_norm": 0.47744879126548767,
      "learning_rate": 3.854367709133575e-05,
      "loss": 1.9929,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 22
    },
    {
      "epoch": 0.2295695570804741,
      "grad_norm": 0.4802912771701813,
      "learning_rate": 3.827090915285202e-05,
      "loss": 2.1544,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 23
    },
    {
      "epoch": 0.2395508421709295,
      "grad_norm": 0.6012081503868103,
      "learning_rate": 3.7975880925983345e-05,
      "loss": 1.9946,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 24
    },
    {
      "epoch": 0.2495321272613849,
      "grad_norm": 0.5076060891151428,
      "learning_rate": 3.7658951857178544e-05,
      "loss": 2.035,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 25
    },
    {
      "epoch": 0.2595134123518403,
      "grad_norm": 0.48807328939437866,
      "learning_rate": 3.732050807568878e-05,
      "loss": 2.0136,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 26
    },
    {
      "epoch": 0.2694946974422957,
      "grad_norm": 0.5449339151382446,
      "learning_rate": 3.696096192312852e-05,
      "loss": 2.0416,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 27
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 0.4534550607204437,
      "learning_rate": 3.658075145110083e-05,
      "loss": 1.9851,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 28
    },
    {
      "epoch": 0.2894572676232065,
      "grad_norm": 0.4585009813308716,
      "learning_rate": 3.6180339887498953e-05,
      "loss": 2.0535,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 29
    },
    {
      "epoch": 0.2994385527136619,
      "grad_norm": 0.4384298026561737,
      "learning_rate": 3.576021507213444e-05,
      "loss": 1.9707,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 30
    },
    {
      "epoch": 0.3094198378041173,
      "grad_norm": 0.45061880350112915,
      "learning_rate": 3.532088886237956e-05,
      "loss": 1.9852,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 31
    },
    {
      "epoch": 0.3194011228945727,
      "grad_norm": 0.440997451543808,
      "learning_rate": 3.4862896509547886e-05,
      "loss": 2.035,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 32
    },
    {
      "epoch": 0.32938240798502805,
      "grad_norm": 0.48148396611213684,
      "learning_rate": 3.438679600677303e-05,
      "loss": 1.9924,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 33
    },
    {
      "epoch": 0.3393636930754835,
      "grad_norm": 0.4378114938735962,
      "learning_rate": 3.3893167409179945e-05,
      "loss": 2.0534,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 34
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 0.46853017807006836,
      "learning_rate": 3.3382612127177166e-05,
      "loss": 1.9461,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 35
    },
    {
      "epoch": 0.3593262632563943,
      "grad_norm": 0.5121273994445801,
      "learning_rate": 3.285575219373079e-05,
      "loss": 2.0041,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 36
    },
    {
      "epoch": 0.36930754834684965,
      "grad_norm": 0.4384448230266571,
      "learning_rate": 3.2313229506513167e-05,
      "loss": 1.9977,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 37
    },
    {
      "epoch": 0.3792888334373051,
      "grad_norm": 0.44052553176879883,
      "learning_rate": 3.1755705045849465e-05,
      "loss": 2.089,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 38
    },
    {
      "epoch": 0.38927011852776044,
      "grad_norm": 0.4314590394496918,
      "learning_rate": 3.1183858069414936e-05,
      "loss": 2.0599,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 39
    },
    {
      "epoch": 0.39925140361821587,
      "grad_norm": 0.48110687732696533,
      "learning_rate": 3.05983852846641e-05,
      "loss": 1.9633,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 40
    },
    {
      "epoch": 0.40923268870867124,
      "grad_norm": 0.45507025718688965,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 2.0115,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 41
    },
    {
      "epoch": 0.4192139737991266,
      "grad_norm": 0.4412468671798706,
      "learning_rate": 2.938943125571782e-05,
      "loss": 2.0052,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 42
    },
    {
      "epoch": 0.42919525888958204,
      "grad_norm": 0.417965829372406,
      "learning_rate": 2.876742293578155e-05,
      "loss": 1.9892,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 43
    },
    {
      "epoch": 0.4391765439800374,
      "grad_norm": 0.442302405834198,
      "learning_rate": 2.813473286151601e-05,
      "loss": 1.9746,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 44
    },
    {
      "epoch": 0.44915782907049284,
      "grad_norm": 0.44751137495040894,
      "learning_rate": 2.7492131868318247e-05,
      "loss": 2.0332,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 45
    },
    {
      "epoch": 0.4591391141609482,
      "grad_norm": 0.48814818263053894,
      "learning_rate": 2.684040286651338e-05,
      "loss": 1.9955,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 46
    },
    {
      "epoch": 0.46912039925140364,
      "grad_norm": 0.5113667845726013,
      "learning_rate": 2.618033988749895e-05,
      "loss": 2.0105,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 47
    },
    {
      "epoch": 0.479101684341859,
      "grad_norm": 0.4296576678752899,
      "learning_rate": 2.5512747116339985e-05,
      "loss": 1.9865,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 48
    },
    {
      "epoch": 0.4890829694323144,
      "grad_norm": 0.43028151988983154,
      "learning_rate": 2.4838437911993355e-05,
      "loss": 1.9667,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 49
    },
    {
      "epoch": 0.4990642545227698,
      "grad_norm": 0.7580711245536804,
      "learning_rate": 2.4158233816355185e-05,
      "loss": 1.9566,
      "memory/device_mem_reserved(gib)": 22.88,
      "memory/max_mem_active(gib)": 22.34,
      "memory/max_mem_allocated(gib)": 22.34,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.83010099986432e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}