{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06129704548240775,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001225940909648155,
      "grad_norm": 4.383765697479248,
      "learning_rate": 4e-05,
      "loss": 0.6008,
      "step": 10
    },
    {
      "epoch": 0.00245188181929631,
      "grad_norm": 3.269385576248169,
      "learning_rate": 8e-05,
      "loss": 0.3123,
      "step": 20
    },
    {
      "epoch": 0.003677822728944465,
      "grad_norm": 3.815711259841919,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.3293,
      "step": 30
    },
    {
      "epoch": 0.00490376363859262,
      "grad_norm": 2.635485887527466,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2607,
      "step": 40
    },
    {
      "epoch": 0.0061297045482407745,
      "grad_norm": 2.7631585597991943,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.2159,
      "step": 50
    },
    {
      "epoch": 0.00735564545788893,
      "grad_norm": 3.8087055683135986,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2098,
      "step": 60
    },
    {
      "epoch": 0.008581586367537085,
      "grad_norm": 1.4436062574386597,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.1725,
      "step": 70
    },
    {
      "epoch": 0.00980752727718524,
      "grad_norm": 1.69550621509552,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.1963,
      "step": 80
    },
    {
      "epoch": 0.011033468186833395,
      "grad_norm": 2.8857767581939697,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1729,
      "step": 90
    },
    {
      "epoch": 0.012259409096481549,
      "grad_norm": 1.027714490890503,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.191,
      "step": 100
    },
    {
      "epoch": 0.013485350006129704,
      "grad_norm": 1.3657031059265137,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1567,
      "step": 110
    },
    {
      "epoch": 0.01471129091577786,
      "grad_norm": 3.904578924179077,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1534,
      "step": 120
    },
    {
      "epoch": 0.015937231825426015,
      "grad_norm": 2.95263934135437,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.1863,
      "step": 130
    },
    {
      "epoch": 0.01716317273507417,
      "grad_norm": 2.19970703125,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1809,
      "step": 140
    },
    {
      "epoch": 0.018389113644722323,
      "grad_norm": 1.7940118312835693,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.1367,
      "step": 150
    },
    {
      "epoch": 0.01961505455437048,
      "grad_norm": 1.772947072982788,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1194,
      "step": 160
    },
    {
      "epoch": 0.020840995464018634,
      "grad_norm": 1.1403783559799194,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1509,
      "step": 170
    },
    {
      "epoch": 0.02206693637366679,
      "grad_norm": 2.2660560607910156,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1438,
      "step": 180
    },
    {
      "epoch": 0.023292877283314944,
      "grad_norm": 1.812446117401123,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.1534,
      "step": 190
    },
    {
      "epoch": 0.024518818192963098,
      "grad_norm": 2.2660441398620605,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1517,
      "step": 200
    },
    {
      "epoch": 0.025744759102611255,
      "grad_norm": 1.7808526754379272,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1363,
      "step": 210
    },
    {
      "epoch": 0.02697070001225941,
      "grad_norm": 1.7594811916351318,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1666,
      "step": 220
    },
    {
      "epoch": 0.028196640921907563,
      "grad_norm": 1.3563287258148193,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1141,
      "step": 230
    },
    {
      "epoch": 0.02942258183155572,
      "grad_norm": 1.7707332372665405,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1896,
      "step": 240
    },
    {
      "epoch": 0.030648522741203874,
      "grad_norm": 1.8754723072052002,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0991,
      "step": 250
    },
    {
      "epoch": 0.03187446365085203,
      "grad_norm": 1.3069236278533936,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1073,
      "step": 260
    },
    {
      "epoch": 0.03310040456050018,
      "grad_norm": 1.3609791994094849,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1249,
      "step": 270
    },
    {
      "epoch": 0.03432634547014834,
      "grad_norm": 1.7567753791809082,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0932,
      "step": 280
    },
    {
      "epoch": 0.035552286379796495,
      "grad_norm": 1.649938702583313,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1208,
      "step": 290
    },
    {
      "epoch": 0.036778227289444645,
      "grad_norm": 1.7568031549453735,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1066,
      "step": 300
    },
    {
      "epoch": 0.0380041681990928,
      "grad_norm": 2.218881130218506,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1219,
      "step": 310
    },
    {
      "epoch": 0.03923010910874096,
      "grad_norm": 1.6613621711730957,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1022,
      "step": 320
    },
    {
      "epoch": 0.04045605001838912,
      "grad_norm": 0.924254298210144,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.117,
      "step": 330
    },
    {
      "epoch": 0.04168199092803727,
      "grad_norm": 0.7207609415054321,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0914,
      "step": 340
    },
    {
      "epoch": 0.042907931837685424,
      "grad_norm": 1.2665833234786987,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1334,
      "step": 350
    },
    {
      "epoch": 0.04413387274733358,
      "grad_norm": 1.1735299825668335,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.083,
      "step": 360
    },
    {
      "epoch": 0.04535981365698173,
      "grad_norm": 1.6450732946395874,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1008,
      "step": 370
    },
    {
      "epoch": 0.04658575456662989,
      "grad_norm": 1.1201252937316895,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1057,
      "step": 380
    },
    {
      "epoch": 0.047811695476278046,
      "grad_norm": 0.8063156604766846,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.086,
      "step": 390
    },
    {
      "epoch": 0.049037636385926196,
      "grad_norm": 1.0388742685317993,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1075,
      "step": 400
    },
    {
      "epoch": 0.05026357729557435,
      "grad_norm": 1.5300003290176392,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0809,
      "step": 410
    },
    {
      "epoch": 0.05148951820522251,
      "grad_norm": 1.5584441423416138,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1027,
      "step": 420
    },
    {
      "epoch": 0.05271545911487066,
      "grad_norm": 0.9144107103347778,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0921,
      "step": 430
    },
    {
      "epoch": 0.05394140002451882,
      "grad_norm": 1.0252676010131836,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.103,
      "step": 440
    },
    {
      "epoch": 0.055167340934166975,
      "grad_norm": 1.020387053489685,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0946,
      "step": 450
    },
    {
      "epoch": 0.056393281843815125,
      "grad_norm": 1.2870961427688599,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.1043,
      "step": 460
    },
    {
      "epoch": 0.05761922275346328,
      "grad_norm": 1.3732898235321045,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.096,
      "step": 470
    },
    {
      "epoch": 0.05884516366311144,
      "grad_norm": 1.1968400478363037,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.1426,
      "step": 480
    },
    {
      "epoch": 0.06007110457275959,
      "grad_norm": 1.2050400972366333,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0755,
      "step": 490
    },
    {
      "epoch": 0.06129704548240775,
      "grad_norm": 0.7326511740684509,
      "learning_rate": 0.0,
      "loss": 0.07,
      "step": 500
    },
    {
      "epoch": 0.06129704548240775,
      "step": 500,
      "total_flos": 2454854258304000.0,
      "train_loss": 0.14927043783664704,
      "train_runtime": 139.6822,
      "train_samples_per_second": 14.318,
      "train_steps_per_second": 3.58
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2454854258304000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}