{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991111111111111,
  "eval_steps": 500,
  "global_step": 562,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 0.6805279850959778,
      "learning_rate": 0.00019644128113879004,
      "loss": 0.3007,
      "step": 10
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 0.9196615219116211,
      "learning_rate": 0.0001928825622775801,
      "loss": 0.1195,
      "step": 20
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.9212412238121033,
      "learning_rate": 0.0001893238434163701,
      "loss": 0.1172,
      "step": 30
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.4567917585372925,
      "learning_rate": 0.00018576512455516017,
      "loss": 0.097,
      "step": 40
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.4863280653953552,
      "learning_rate": 0.00018220640569395016,
      "loss": 0.0855,
      "step": 50
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.5411233901977539,
      "learning_rate": 0.00017864768683274022,
      "loss": 0.0906,
      "step": 60
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 0.539750337600708,
      "learning_rate": 0.00017508896797153024,
      "loss": 0.0881,
      "step": 70
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.394882470369339,
      "learning_rate": 0.0001715302491103203,
      "loss": 0.0737,
      "step": 80
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.45392346382141113,
      "learning_rate": 0.00016797153024911032,
      "loss": 0.0652,
      "step": 90
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.4979017376899719,
      "learning_rate": 0.00016441281138790037,
      "loss": 0.073,
      "step": 100
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 0.3595920205116272,
      "learning_rate": 0.0001608540925266904,
      "loss": 0.0658,
      "step": 110
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.42612773180007935,
      "learning_rate": 0.00015729537366548045,
      "loss": 0.074,
      "step": 120
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 0.35243910551071167,
      "learning_rate": 0.00015373665480427045,
      "loss": 0.0677,
      "step": 130
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 0.5590384006500244,
      "learning_rate": 0.0001501779359430605,
      "loss": 0.0696,
      "step": 140
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.7073479294776917,
      "learning_rate": 0.00014661921708185053,
      "loss": 0.069,
      "step": 150
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.32941359281539917,
      "learning_rate": 0.00014306049822064058,
      "loss": 0.0677,
      "step": 160
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 0.3985579311847687,
      "learning_rate": 0.0001395017793594306,
      "loss": 0.0546,
      "step": 170
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.3595498502254486,
      "learning_rate": 0.00013594306049822066,
      "loss": 0.0612,
      "step": 180
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 0.7771916389465332,
      "learning_rate": 0.00013238434163701069,
      "loss": 0.0659,
      "step": 190
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.4626810550689697,
      "learning_rate": 0.00012882562277580074,
      "loss": 0.0666,
      "step": 200
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.28734588623046875,
      "learning_rate": 0.00012526690391459074,
      "loss": 0.0471,
      "step": 210
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 0.47027942538261414,
      "learning_rate": 0.0001217081850533808,
      "loss": 0.0603,
      "step": 220
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 0.46543505787849426,
      "learning_rate": 0.00011814946619217081,
      "loss": 0.0465,
      "step": 230
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.378945529460907,
      "learning_rate": 0.00011459074733096087,
      "loss": 0.0585,
      "step": 240
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.4640860855579376,
      "learning_rate": 0.00011103202846975089,
      "loss": 0.0499,
      "step": 250
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 0.30186182260513306,
      "learning_rate": 0.00010747330960854095,
      "loss": 0.0498,
      "step": 260
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.6072084903717041,
      "learning_rate": 0.00010391459074733096,
      "loss": 0.0526,
      "step": 270
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.4315777122974396,
      "learning_rate": 0.00010035587188612101,
      "loss": 0.0412,
      "step": 280
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 0.32349273562431335,
      "learning_rate": 9.679715302491104e-05,
      "loss": 0.0395,
      "step": 290
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.3251255452632904,
      "learning_rate": 9.323843416370108e-05,
      "loss": 0.0449,
      "step": 300
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 0.40258878469467163,
      "learning_rate": 8.96797153024911e-05,
      "loss": 0.0535,
      "step": 310
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.3351120054721832,
      "learning_rate": 8.612099644128114e-05,
      "loss": 0.0449,
      "step": 320
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 0.3918339014053345,
      "learning_rate": 8.256227758007118e-05,
      "loss": 0.0498,
      "step": 330
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 0.26887497305870056,
      "learning_rate": 7.900355871886122e-05,
      "loss": 0.0395,
      "step": 340
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.34482306241989136,
      "learning_rate": 7.544483985765126e-05,
      "loss": 0.0504,
      "step": 350
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.33622053265571594,
      "learning_rate": 7.188612099644128e-05,
      "loss": 0.049,
      "step": 360
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 0.4018609821796417,
      "learning_rate": 6.832740213523132e-05,
      "loss": 0.0456,
      "step": 370
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 0.3232245445251465,
      "learning_rate": 6.476868327402136e-05,
      "loss": 0.0473,
      "step": 380
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 0.2700667679309845,
      "learning_rate": 6.12099644128114e-05,
      "loss": 0.0448,
      "step": 390
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.35857853293418884,
      "learning_rate": 5.765124555160143e-05,
      "loss": 0.0395,
      "step": 400
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 0.3355509638786316,
      "learning_rate": 5.4092526690391465e-05,
      "loss": 0.0381,
      "step": 410
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.36887580156326294,
      "learning_rate": 5.0533807829181504e-05,
      "loss": 0.0393,
      "step": 420
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 0.2498418539762497,
      "learning_rate": 4.697508896797153e-05,
      "loss": 0.0397,
      "step": 430
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.4195568263530731,
      "learning_rate": 4.341637010676157e-05,
      "loss": 0.0399,
      "step": 440
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.2515809237957001,
      "learning_rate": 3.98576512455516e-05,
      "loss": 0.0374,
      "step": 450
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 0.38955771923065186,
      "learning_rate": 3.629893238434164e-05,
      "loss": 0.0404,
      "step": 460
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 0.3211108446121216,
      "learning_rate": 3.274021352313167e-05,
      "loss": 0.0299,
      "step": 470
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.36825743317604065,
      "learning_rate": 2.918149466192171e-05,
      "loss": 0.0365,
      "step": 480
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 0.3567051589488983,
      "learning_rate": 2.5622775800711747e-05,
      "loss": 0.0414,
      "step": 490
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.41268640756607056,
      "learning_rate": 2.2064056939501783e-05,
      "loss": 0.0396,
      "step": 500
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 0.38851094245910645,
      "learning_rate": 1.8505338078291815e-05,
      "loss": 0.0368,
      "step": 510
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.5653034448623657,
      "learning_rate": 1.494661921708185e-05,
      "loss": 0.0339,
      "step": 520
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 0.33567166328430176,
      "learning_rate": 1.1387900355871885e-05,
      "loss": 0.047,
      "step": 530
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.3209730386734009,
      "learning_rate": 7.829181494661921e-06,
      "loss": 0.0411,
      "step": 540
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.2615627348423004,
      "learning_rate": 4.270462633451958e-06,
      "loss": 0.0345,
      "step": 550
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.38623788952827454,
      "learning_rate": 7.117437722419928e-07,
      "loss": 0.0338,
      "step": 560
    }
  ],
  "logging_steps": 10,
  "max_steps": 562,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4307316713467904e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}