{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.049714143673875215,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009942828734775043,
      "grad_norm": 1.0510079860687256,
      "learning_rate": 5e-06,
      "loss": 1.4767,
      "step": 1
    },
    {
      "epoch": 0.0009942828734775043,
      "eval_loss": 1.4993078708648682,
      "eval_runtime": 33.8637,
      "eval_samples_per_second": 12.521,
      "eval_steps_per_second": 6.26,
      "step": 1
    },
    {
      "epoch": 0.0019885657469550086,
      "grad_norm": 1.224595069885254,
      "learning_rate": 1e-05,
      "loss": 1.2547,
      "step": 2
    },
    {
      "epoch": 0.002982848620432513,
      "grad_norm": 1.0081843137741089,
      "learning_rate": 1.5e-05,
      "loss": 1.2654,
      "step": 3
    },
    {
      "epoch": 0.003977131493910017,
      "grad_norm": 1.136277675628662,
      "learning_rate": 2e-05,
      "loss": 1.4038,
      "step": 4
    },
    {
      "epoch": 0.004971414367387522,
      "grad_norm": 1.1143028736114502,
      "learning_rate": 2.5e-05,
      "loss": 1.532,
      "step": 5
    },
    {
      "epoch": 0.005965697240865026,
      "grad_norm": 1.0918338298797607,
      "learning_rate": 3e-05,
      "loss": 1.2731,
      "step": 6
    },
    {
      "epoch": 0.00695998011434253,
      "grad_norm": 1.1519715785980225,
      "learning_rate": 3.5e-05,
      "loss": 1.3907,
      "step": 7
    },
    {
      "epoch": 0.007954262987820034,
      "grad_norm": 0.9681263566017151,
      "learning_rate": 4e-05,
      "loss": 1.2741,
      "step": 8
    },
    {
      "epoch": 0.008948545861297539,
      "grad_norm": 1.3093149662017822,
      "learning_rate": 4.5e-05,
      "loss": 1.5193,
      "step": 9
    },
    {
      "epoch": 0.009942828734775044,
      "grad_norm": 1.498204231262207,
      "learning_rate": 5e-05,
      "loss": 1.8308,
      "step": 10
    },
    {
      "epoch": 0.010937111608252548,
      "grad_norm": 1.0419001579284668,
      "learning_rate": 4.99229333433282e-05,
      "loss": 1.3051,
      "step": 11
    },
    {
      "epoch": 0.011931394481730051,
      "grad_norm": 1.1002775430679321,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 1.1676,
      "step": 12
    },
    {
      "epoch": 0.012925677355207556,
      "grad_norm": 1.0704587697982788,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 1.2406,
      "step": 13
    },
    {
      "epoch": 0.012925677355207556,
      "eval_loss": 1.2395694255828857,
      "eval_runtime": 33.9104,
      "eval_samples_per_second": 12.504,
      "eval_steps_per_second": 6.252,
      "step": 13
    },
    {
      "epoch": 0.01391996022868506,
      "grad_norm": 0.9130391478538513,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.7564,
      "step": 14
    },
    {
      "epoch": 0.014914243102162566,
      "grad_norm": 0.6873193979263306,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 1.1892,
      "step": 15
    },
    {
      "epoch": 0.01590852597564007,
      "grad_norm": 0.7080130577087402,
      "learning_rate": 4.72751631047092e-05,
      "loss": 1.2898,
      "step": 16
    },
    {
      "epoch": 0.016902808849117573,
      "grad_norm": 0.6573795676231384,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 1.1486,
      "step": 17
    },
    {
      "epoch": 0.017897091722595078,
      "grad_norm": 0.7076409459114075,
      "learning_rate": 4.522542485937369e-05,
      "loss": 1.3011,
      "step": 18
    },
    {
      "epoch": 0.018891374596072583,
      "grad_norm": 0.8251878619194031,
      "learning_rate": 4.401014914000078e-05,
      "loss": 1.3231,
      "step": 19
    },
    {
      "epoch": 0.019885657469550087,
      "grad_norm": 0.6412386894226074,
      "learning_rate": 4.267766952966369e-05,
      "loss": 1.0668,
      "step": 20
    },
    {
      "epoch": 0.020879940343027592,
      "grad_norm": 0.6613972783088684,
      "learning_rate": 4.123620120825459e-05,
      "loss": 1.11,
      "step": 21
    },
    {
      "epoch": 0.021874223216505097,
      "grad_norm": 0.6054477095603943,
      "learning_rate": 3.969463130731183e-05,
      "loss": 1.1706,
      "step": 22
    },
    {
      "epoch": 0.0228685060899826,
      "grad_norm": 0.6621925234794617,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 1.0535,
      "step": 23
    },
    {
      "epoch": 0.023862788963460103,
      "grad_norm": 0.7019568085670471,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.9425,
      "step": 24
    },
    {
      "epoch": 0.024857071836937607,
      "grad_norm": 0.6158506870269775,
      "learning_rate": 3.456708580912725e-05,
      "loss": 1.0924,
      "step": 25
    },
    {
      "epoch": 0.025851354710415112,
      "grad_norm": 0.6758943200111389,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.9757,
      "step": 26
    },
    {
      "epoch": 0.025851354710415112,
      "eval_loss": 1.1292123794555664,
      "eval_runtime": 33.941,
      "eval_samples_per_second": 12.492,
      "eval_steps_per_second": 6.246,
      "step": 26
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": 0.6172102093696594,
      "learning_rate": 3.083613409639764e-05,
      "loss": 1.3252,
      "step": 27
    },
    {
      "epoch": 0.02783992045737012,
      "grad_norm": 0.5786134600639343,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 1.0781,
      "step": 28
    },
    {
      "epoch": 0.028834203330847626,
      "grad_norm": 0.6131380796432495,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 1.4603,
      "step": 29
    },
    {
      "epoch": 0.02982848620432513,
      "grad_norm": 0.5507011413574219,
      "learning_rate": 2.5e-05,
      "loss": 0.9635,
      "step": 30
    },
    {
      "epoch": 0.030822769077802636,
      "grad_norm": 0.5960745215415955,
      "learning_rate": 2.303852260680388e-05,
      "loss": 1.1379,
      "step": 31
    },
    {
      "epoch": 0.03181705195128014,
      "grad_norm": 0.5253822207450867,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.9897,
      "step": 32
    },
    {
      "epoch": 0.03281133482475764,
      "grad_norm": 0.6236615777015686,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 1.083,
      "step": 33
    },
    {
      "epoch": 0.033805617698235146,
      "grad_norm": 0.5677335858345032,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 1.2313,
      "step": 34
    },
    {
      "epoch": 0.03479990057171265,
      "grad_norm": 0.5143101215362549,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 1.062,
      "step": 35
    },
    {
      "epoch": 0.035794183445190156,
      "grad_norm": 0.48625993728637695,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 1.2285,
      "step": 36
    },
    {
      "epoch": 0.03678846631866766,
      "grad_norm": 0.5220788717269897,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 1.0257,
      "step": 37
    },
    {
      "epoch": 0.037782749192145165,
      "grad_norm": 0.5212054252624512,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.9489,
      "step": 38
    },
    {
      "epoch": 0.03877703206562267,
      "grad_norm": 0.5077629685401917,
      "learning_rate": 8.763798791745411e-06,
      "loss": 1.129,
      "step": 39
    },
    {
      "epoch": 0.03877703206562267,
      "eval_loss": 1.0944116115570068,
      "eval_runtime": 33.9486,
      "eval_samples_per_second": 12.489,
      "eval_steps_per_second": 6.245,
      "step": 39
    },
    {
      "epoch": 0.039771314939100175,
      "grad_norm": 0.5140138268470764,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.8503,
      "step": 40
    },
    {
      "epoch": 0.04076559781257768,
      "grad_norm": 0.48681968450546265,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.8262,
      "step": 41
    },
    {
      "epoch": 0.041759880686055184,
      "grad_norm": 0.4964918792247772,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 1.0563,
      "step": 42
    },
    {
      "epoch": 0.04275416355953269,
      "grad_norm": 0.560379683971405,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 1.0176,
      "step": 43
    },
    {
      "epoch": 0.043748446433010194,
      "grad_norm": 0.48453328013420105,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.9454,
      "step": 44
    },
    {
      "epoch": 0.0447427293064877,
      "grad_norm": 0.45847266912460327,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.9232,
      "step": 45
    },
    {
      "epoch": 0.0457370121799652,
      "grad_norm": 0.5710907578468323,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 1.1137,
      "step": 46
    },
    {
      "epoch": 0.04673129505344271,
      "grad_norm": 0.5743865966796875,
      "learning_rate": 6.907519900580861e-07,
      "loss": 1.1263,
      "step": 47
    },
    {
      "epoch": 0.047725577926920205,
      "grad_norm": 0.9409152269363403,
      "learning_rate": 3.077914851215585e-07,
      "loss": 1.2489,
      "step": 48
    },
    {
      "epoch": 0.04871986080039771,
      "grad_norm": 0.5280179381370544,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.8648,
      "step": 49
    },
    {
      "epoch": 0.049714143673875215,
      "grad_norm": 0.46047770977020264,
      "learning_rate": 0.0,
      "loss": 0.9192,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7547965428137984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}