{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5886812785036658,
  "eval_steps": 500,
  "global_step": 478,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.999992497128677e-05,
      "loss": 2.0742,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9998124338461647e-05,
      "loss": 1.2327,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9992498057467824e-05,
      "loss": 1.159,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.9983123267618306e-05,
      "loss": 1.1495,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.997000348569964e-05,
      "loss": 1.1277,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.99531436333659e-05,
      "loss": 1.1321,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9932550035292393e-05,
      "loss": 1.1259,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9908230416803093e-05,
      "loss": 1.1427,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.98801939009726e-05,
      "loss": 1.1101,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9848451005203795e-05,
      "loss": 1.1267,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9813013637282426e-05,
      "loss": 1.1185,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9773895090910098e-05,
      "loss": 1.1049,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9731110040717384e-05,
      "loss": 1.1232,
      "step": 60
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9684674536758894e-05,
      "loss": 1.1158,
      "step": 65
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9634605998492386e-05,
      "loss": 1.0992,
      "step": 70
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.958092320824417e-05,
      "loss": 1.118,
      "step": 75
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.952364630416322e-05,
      "loss": 1.1062,
      "step": 80
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9462796772666746e-05,
      "loss": 1.1213,
      "step": 85
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9398397440379923e-05,
      "loss": 1.0936,
      "step": 90
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9330472465572883e-05,
      "loss": 1.1248,
      "step": 95
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9259047329098173e-05,
      "loss": 1.1104,
      "step": 100
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.918414882483206e-05,
      "loss": 1.1026,
      "step": 105
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.91058050496233e-05,
      "loss": 1.1049,
      "step": 110
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.902404539275307e-05,
      "loss": 1.0877,
      "step": 115
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.8938900524910128e-05,
      "loss": 1.1035,
      "step": 120
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.8850402386685235e-05,
      "loss": 1.0895,
      "step": 125
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.875858417658921e-05,
      "loss": 1.0995,
      "step": 130
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.866348033859909e-05,
      "loss": 1.1066,
      "step": 135
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8565126549237092e-05,
      "loss": 1.1129,
      "step": 140
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.846355970418718e-05,
      "loss": 1.0883,
      "step": 145
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8358817904454328e-05,
      "loss": 1.1067,
      "step": 150
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.825094044207158e-05,
      "loss": 1.0965,
      "step": 155
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8139967785360338e-05,
      "loss": 1.0957,
      "step": 160
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8025941563749407e-05,
      "loss": 1.0956,
      "step": 165
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.7908904552158435e-05,
      "loss": 1.0859,
      "step": 170
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7788900654951664e-05,
      "loss": 1.1044,
      "step": 175
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.766597488946798e-05,
      "loss": 1.1113,
      "step": 180
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7540173369133463e-05,
      "loss": 1.1069,
      "step": 185
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.741154328616274e-05,
      "loss": 1.1087,
      "step": 190
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.728013289385568e-05,
      "loss": 1.0956,
      "step": 195
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7145991488495997e-05,
      "loss": 1.0832,
      "step": 200
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7009169390858635e-05,
      "loss": 1.1101,
      "step": 205
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.6869717927332825e-05,
      "loss": 1.0885,
      "step": 210
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.6727689410667887e-05,
      "loss": 1.0907,
      "step": 215
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.6583137120349028e-05,
      "loss": 1.1001,
      "step": 220
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.64361152826105e-05,
      "loss": 1.1047,
      "step": 225
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.6286679050093573e-05,
      "loss": 1.0976,
      "step": 230
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6134884481156994e-05,
      "loss": 1.1082,
      "step": 235
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.5980788518847706e-05,
      "loss": 1.0839,
      "step": 240
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.5824448969539653e-05,
      "loss": 1.0892,
      "step": 245
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.566592448124874e-05,
      "loss": 1.1104,
      "step": 250
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.550527452163209e-05,
      "loss": 1.0929,
      "step": 255
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.5342559355679776e-05,
      "loss": 1.0888,
      "step": 260
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5177840023107498e-05,
      "loss": 1.0824,
      "step": 265
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5011178315458601e-05,
      "loss": 1.0953,
      "step": 270
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.4842636752924073e-05,
      "loss": 1.079,
      "step": 275
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.467227856088921e-05,
      "loss": 1.0762,
      "step": 280
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.4500167646215722e-05,
      "loss": 1.0995,
      "step": 285
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4326368573268199e-05,
      "loss": 1.0934,
      "step": 290
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.415094653969395e-05,
      "loss": 1.0889,
      "step": 295
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.397396735196525e-05,
      "loss": 1.0913,
      "step": 300
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.3795497400693198e-05,
      "loss": 1.0786,
      "step": 305
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.3615603635722463e-05,
      "loss": 1.0863,
      "step": 310
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3434353541016238e-05,
      "loss": 1.0904,
      "step": 315
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3251815109340813e-05,
      "loss": 1.0932,
      "step": 320
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3068056816759303e-05,
      "loss": 1.1046,
      "step": 325
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.2883147596944054e-05,
      "loss": 1.0881,
      "step": 330
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.2697156815317409e-05,
      "loss": 1.0994,
      "step": 335
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.2510154243030482e-05,
      "loss": 1.0975,
      "step": 340
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.2322210030789759e-05,
      "loss": 1.0813,
      "step": 345
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.2133394682541287e-05,
      "loss": 1.091,
      "step": 350
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.194377902902238e-05,
      "loss": 1.0777,
      "step": 355
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.1753434201190716e-05,
      "loss": 1.0904,
      "step": 360
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.1562431603540807e-05,
      "loss": 1.0827,
      "step": 365
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1370842887317888e-05,
      "loss": 1.0922,
      "step": 370
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.117873992363919e-05,
      "loss": 1.1067,
      "step": 375
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.09861947765328e-05,
      "loss": 1.1017,
      "step": 380
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.0793279675904072e-05,
      "loss": 1.0762,
      "step": 385
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.0600066990439895e-05,
      "loss": 1.0908,
      "step": 390
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0406629200460836e-05,
      "loss": 1.0848,
      "step": 395
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0213038870731443e-05,
      "loss": 1.088,
      "step": 400
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.0019368623238845e-05,
      "loss": 1.088,
      "step": 405
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.82569110994992e-06,
      "loss": 1.0889,
      "step": 410
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.632078985557163e-06,
      "loss": 1.0811,
      "step": 415
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.438604880223595e-06,
      "loss": 1.1001,
      "step": 420
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.245341372336829e-06,
      "loss": 1.092,
      "step": 425
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.052360961282558e-06,
      "loss": 1.1029,
      "step": 430
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.859736040247719e-06,
      "loss": 1.0768,
      "step": 435
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.667538869063456e-06,
      "loss": 1.0811,
      "step": 440
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.475841547098128e-06,
      "loss": 1.0795,
      "step": 445
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.28471598621049e-06,
      "loss": 1.0765,
      "step": 450
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.094233883773255e-06,
      "loss": 1.0957,
      "step": 455
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.904466695777082e-06,
      "loss": 1.0678,
      "step": 460
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.715485610025124e-06,
      "loss": 1.1001,
      "step": 465
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.5273615194281845e-06,
      "loss": 1.0732,
      "step": 470
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.340164995410497e-06,
      "loss": 1.0835,
      "step": 475
    },
    {
      "epoch": 0.59,
      "eval_loss": 1.0884634256362915,
      "eval_runtime": 268.6576,
      "eval_samples_per_second": 86.02,
      "eval_steps_per_second": 10.753,
      "step": 478
    },
    {
      "epoch": 0.59,
      "step": 478,
      "total_flos": 1.0640133502713987e+19,
      "train_loss": 1.1024827179050845,
      "train_runtime": 38937.2818,
      "train_samples_per_second": 5.338,
      "train_steps_per_second": 0.021
    }
  ],
  "logging_steps": 5,
  "max_steps": 811,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.0640133502713987e+19,
  "train_batch_size": null,
  "trial_name": null,
  "trial_params": null
}