{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.9638554216867465,
  "eval_steps": 500,
  "global_step": 515,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 0.9117392307242835,
      "learning_rate": 9.990699835799469e-05,
      "loss": 1.9779,
      "step": 10
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 0.9121432880636753,
      "learning_rate": 9.96283394041954e-05,
      "loss": 1.6698,
      "step": 20
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 0.8113864009102607,
      "learning_rate": 9.916505976821263e-05,
      "loss": 1.5706,
      "step": 30
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.7722456373389991,
      "learning_rate": 9.851888288072053e-05,
      "loss": 1.5093,
      "step": 40
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.840195041159072,
      "learning_rate": 9.769221256218164e-05,
      "loss": 1.463,
      "step": 50
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 0.9154016698600571,
      "learning_rate": 9.668812408047679e-05,
      "loss": 1.4829,
      "step": 60
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 0.890732828345114,
      "learning_rate": 9.551035271070664e-05,
      "loss": 1.4683,
      "step": 70
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 0.9157645257382339,
      "learning_rate": 9.416327983972304e-05,
      "loss": 1.3965,
      "step": 80
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 0.8897525548859271,
      "learning_rate": 9.265191666708209e-05,
      "loss": 1.4475,
      "step": 90
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.861081307668928,
      "learning_rate": 9.098188556305263e-05,
      "loss": 1.4124,
      "step": 100
    },
    {
      "epoch": 1.0602409638554218,
      "grad_norm": 0.85116234930626,
      "learning_rate": 8.915939915302968e-05,
      "loss": 1.3647,
      "step": 110
    },
    {
      "epoch": 1.1566265060240963,
      "grad_norm": 0.9740957258545101,
      "learning_rate": 8.71912372061598e-05,
      "loss": 1.3204,
      "step": 120
    },
    {
      "epoch": 1.2530120481927711,
      "grad_norm": 1.0864987018116612,
      "learning_rate": 8.508472141415467e-05,
      "loss": 1.335,
      "step": 130
    },
    {
      "epoch": 1.3493975903614457,
      "grad_norm": 1.0426867861383922,
      "learning_rate": 8.284768815411692e-05,
      "loss": 1.2918,
      "step": 140
    },
    {
      "epoch": 1.4457831325301205,
      "grad_norm": 1.1563010080529215,
      "learning_rate": 8.048845933670273e-05,
      "loss": 1.3137,
      "step": 150
    },
    {
      "epoch": 1.5421686746987953,
      "grad_norm": 1.1357035664877724,
      "learning_rate": 7.801581144806752e-05,
      "loss": 1.2938,
      "step": 160
    },
    {
      "epoch": 1.6385542168674698,
      "grad_norm": 1.1274251128308745,
      "learning_rate": 7.543894290076103e-05,
      "loss": 1.3013,
      "step": 170
    },
    {
      "epoch": 1.7349397590361446,
      "grad_norm": 1.1376429010873366,
      "learning_rate": 7.276743981502856e-05,
      "loss": 1.3333,
      "step": 180
    },
    {
      "epoch": 1.8313253012048194,
      "grad_norm": 1.1848553562459525,
      "learning_rate": 7.00112403578139e-05,
      "loss": 1.2946,
      "step": 190
    },
    {
      "epoch": 1.927710843373494,
      "grad_norm": 1.1037089869727106,
      "learning_rate": 6.718059777212567e-05,
      "loss": 1.2859,
      "step": 200
    },
    {
      "epoch": 2.0240963855421685,
      "grad_norm": 1.1061364608256432,
      "learning_rate": 6.42860422342998e-05,
      "loss": 1.2725,
      "step": 210
    },
    {
      "epoch": 2.1204819277108435,
      "grad_norm": 1.3057975365378993,
      "learning_rate": 6.133834168105206e-05,
      "loss": 1.1922,
      "step": 220
    },
    {
      "epoch": 2.216867469879518,
      "grad_norm": 1.289860777590967,
      "learning_rate": 5.8348461752046116e-05,
      "loss": 1.1768,
      "step": 230
    },
    {
      "epoch": 2.3132530120481927,
      "grad_norm": 1.393963581012029,
      "learning_rate": 5.532752499699381e-05,
      "loss": 1.1828,
      "step": 240
    },
    {
      "epoch": 2.4096385542168672,
      "grad_norm": 1.4444324116034009,
      "learning_rate": 5.228676949903973e-05,
      "loss": 1.1874,
      "step": 250
    },
    {
      "epoch": 2.5060240963855422,
      "grad_norm": 1.4377450110610097,
      "learning_rate": 4.923750706835371e-05,
      "loss": 1.1709,
      "step": 260
    },
    {
      "epoch": 2.602409638554217,
      "grad_norm": 1.4052399247965977,
      "learning_rate": 4.619108116145411e-05,
      "loss": 1.1545,
      "step": 270
    },
    {
      "epoch": 2.6987951807228914,
      "grad_norm": 1.4874281591631962,
      "learning_rate": 4.31588246828045e-05,
      "loss": 1.1515,
      "step": 280
    },
    {
      "epoch": 2.7951807228915664,
      "grad_norm": 1.510345480121206,
      "learning_rate": 4.015201782566471e-05,
      "loss": 1.1655,
      "step": 290
    },
    {
      "epoch": 2.891566265060241,
      "grad_norm": 1.4989598810015492,
      "learning_rate": 3.7181846109031005e-05,
      "loss": 1.1565,
      "step": 300
    },
    {
      "epoch": 2.9879518072289155,
      "grad_norm": 1.499903571294907,
      "learning_rate": 3.4259358766770766e-05,
      "loss": 1.189,
      "step": 310
    },
    {
      "epoch": 3.0843373493975905,
      "grad_norm": 1.5828347380531096,
      "learning_rate": 3.1395427643746796e-05,
      "loss": 1.0681,
      "step": 320
    },
    {
      "epoch": 3.180722891566265,
      "grad_norm": 1.68873547972742,
      "learning_rate": 2.860070675184036e-05,
      "loss": 1.0827,
      "step": 330
    },
    {
      "epoch": 3.2771084337349397,
      "grad_norm": 1.6928065503330352,
      "learning_rate": 2.588559263632719e-05,
      "loss": 1.055,
      "step": 340
    },
    {
      "epoch": 3.3734939759036147,
      "grad_norm": 1.656803450443418,
      "learning_rate": 2.3260185700046294e-05,
      "loss": 1.0615,
      "step": 350
    },
    {
      "epoch": 3.4698795180722892,
      "grad_norm": 1.7763695778702038,
      "learning_rate": 2.0734252629237894e-05,
      "loss": 1.054,
      "step": 360
    },
    {
      "epoch": 3.566265060240964,
      "grad_norm": 1.7692488057265054,
      "learning_rate": 1.831719006082924e-05,
      "loss": 1.0659,
      "step": 370
    },
    {
      "epoch": 3.662650602409639,
      "grad_norm": 1.7554003807515917,
      "learning_rate": 1.601798962632799e-05,
      "loss": 1.0694,
      "step": 380
    },
    {
      "epoch": 3.7590361445783134,
      "grad_norm": 1.822610764821149,
      "learning_rate": 1.384520450236244e-05,
      "loss": 1.0566,
      "step": 390
    },
    {
      "epoch": 3.855421686746988,
      "grad_norm": 1.8319206289975956,
      "learning_rate": 1.1806917592302762e-05,
      "loss": 1.0494,
      "step": 400
    },
    {
      "epoch": 3.9518072289156625,
      "grad_norm": 1.9096676463205011,
      "learning_rate": 9.91071145732948e-06,
      "loss": 1.0577,
      "step": 410
    },
    {
      "epoch": 4.048192771084337,
      "grad_norm": 1.7249401183320767,
      "learning_rate": 8.163640108807896e-06,
      "loss": 1.0293,
      "step": 420
    },
    {
      "epoch": 4.144578313253012,
      "grad_norm": 1.826717977143128,
      "learning_rate": 6.572202766902569e-06,
      "loss": 1.0078,
      "step": 430
    },
    {
      "epoch": 4.240963855421687,
      "grad_norm": 1.8877052786758952,
      "learning_rate": 5.1423196830513e-06,
      "loss": 0.9904,
      "step": 440
    },
    {
      "epoch": 4.337349397590361,
      "grad_norm": 1.8808793283796603,
      "learning_rate": 3.879310116241042e-06,
      "loss": 0.9815,
      "step": 450
    },
    {
      "epoch": 4.433734939759036,
      "grad_norm": 1.882737371988685,
      "learning_rate": 2.787872545015069e-06,
      "loss": 0.9995,
      "step": 460
    },
    {
      "epoch": 4.530120481927711,
      "grad_norm": 1.9125920590825105,
      "learning_rate": 1.8720671888242059e-06,
      "loss": 1.0179,
      "step": 470
    },
    {
      "epoch": 4.626506024096385,
      "grad_norm": 1.8949023884002059,
      "learning_rate": 1.1353009037437523e-06,
      "loss": 1.002,
      "step": 480
    },
    {
      "epoch": 4.72289156626506,
      "grad_norm": 1.8902529975556408,
      "learning_rate": 5.803145087451945e-07,
      "loss": 0.9862,
      "step": 490
    },
    {
      "epoch": 4.8192771084337345,
      "grad_norm": 1.915141448607233,
      "learning_rate": 2.0917258966953733e-07,
      "loss": 1.0089,
      "step": 500
    },
    {
      "epoch": 4.9156626506024095,
      "grad_norm": 1.8921692295680217,
      "learning_rate": 2.3255818832423894e-08,
      "loss": 0.9775,
      "step": 510
    },
    {
      "epoch": 4.9638554216867465,
      "step": 515,
      "total_flos": 72399436972032.0,
      "train_loss": 1.2166850728896057,
      "train_runtime": 4721.4385,
      "train_samples_per_second": 0.879,
      "train_steps_per_second": 0.109
    }
  ],
  "logging_steps": 10,
  "max_steps": 515,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 72399436972032.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}