{
  "best_metric": 0.7502281069755554,
  "best_model_checkpoint": "./checkpoints/llava-v1.6-34b-chatml_direct-anyres/checkpoint-115",
  "epoch": 3.75,
  "eval_steps": 1.0,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03125,
      "grad_norm": 0.3345325833952841,
      "learning_rate": 0.0,
      "loss": 1.2677,
      "step": 1
    },
    {
      "epoch": 0.03125,
      "eval_loss": 1.3042412996292114,
      "eval_runtime": 195.8656,
      "eval_samples_per_second": 1.021,
      "eval_steps_per_second": 0.128,
      "step": 1
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.35890614982474045,
      "learning_rate": 8.613531161467863e-06,
      "loss": 1.3505,
      "step": 2
    },
    {
      "epoch": 0.0625,
      "eval_loss": 1.3042412996292114,
      "eval_runtime": 190.4145,
      "eval_samples_per_second": 1.05,
      "eval_steps_per_second": 0.131,
      "step": 2
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.3316701046946783,
      "learning_rate": 1.3652123889719709e-05,
      "loss": 1.2569,
      "step": 3
    },
    {
      "epoch": 0.09375,
      "eval_loss": 1.2942205667495728,
      "eval_runtime": 190.6475,
      "eval_samples_per_second": 1.049,
      "eval_steps_per_second": 0.131,
      "step": 3
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.32188096642751235,
      "learning_rate": 1.7227062322935725e-05,
      "loss": 1.2323,
      "step": 4
    },
    {
      "epoch": 0.125,
      "eval_loss": 1.2789555788040161,
      "eval_runtime": 189.7666,
      "eval_samples_per_second": 1.054,
      "eval_steps_per_second": 0.132,
      "step": 4
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.3767527705004001,
      "learning_rate": 2e-05,
      "loss": 1.2785,
      "step": 5
    },
    {
      "epoch": 0.15625,
      "eval_loss": 1.258152723312378,
      "eval_runtime": 189.5935,
      "eval_samples_per_second": 1.055,
      "eval_steps_per_second": 0.132,
      "step": 5
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.3287126070774628,
      "learning_rate": 2e-05,
      "loss": 1.2151,
      "step": 6
    },
    {
      "epoch": 0.1875,
      "eval_loss": 1.2347216606140137,
      "eval_runtime": 190.4111,
      "eval_samples_per_second": 1.05,
      "eval_steps_per_second": 0.131,
      "step": 6
    },
    {
      "epoch": 0.21875,
      "grad_norm": 0.34451127286331007,
      "learning_rate": 2e-05,
      "loss": 1.2968,
      "step": 7
    },
    {
      "epoch": 0.21875,
      "eval_loss": 1.210167646408081,
      "eval_runtime": 190.9799,
      "eval_samples_per_second": 1.047,
      "eval_steps_per_second": 0.131,
      "step": 7
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.36105870692958336,
      "learning_rate": 2e-05,
      "loss": 1.2277,
      "step": 8
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.1862907409667969,
      "eval_runtime": 190.685,
      "eval_samples_per_second": 1.049,
      "eval_steps_per_second": 0.131,
      "step": 8
    },
    {
      "epoch": 0.28125,
      "grad_norm": 0.35460549637546845,
      "learning_rate": 2e-05,
      "loss": 1.2101,
      "step": 9
    },
    {
      "epoch": 0.28125,
      "eval_loss": 1.1649302244186401,
      "eval_runtime": 190.1569,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 0.131,
      "step": 9
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.3134923556618721,
      "learning_rate": 2e-05,
      "loss": 1.1163,
      "step": 10
    },
    {
      "epoch": 0.3125,
      "eval_loss": 1.144965410232544,
      "eval_runtime": 190.0982,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 0.132,
      "step": 10
    },
    {
      "epoch": 0.34375,
      "grad_norm": 0.3069481492118633,
      "learning_rate": 2e-05,
      "loss": 1.1483,
      "step": 11
    },
    {
      "epoch": 0.34375,
      "eval_loss": 1.124668002128601,
      "eval_runtime": 192.0572,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.13,
      "step": 11
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.2801324709168811,
      "learning_rate": 2e-05,
      "loss": 1.1172,
      "step": 12
    },
    {
      "epoch": 0.375,
      "eval_loss": 1.1061824560165405,
      "eval_runtime": 192.6406,
      "eval_samples_per_second": 1.038,
      "eval_steps_per_second": 0.13,
      "step": 12
    },
    {
      "epoch": 0.40625,
      "grad_norm": 0.33156251919932406,
      "learning_rate": 2e-05,
      "loss": 1.1902,
      "step": 13
    },
    {
      "epoch": 0.40625,
      "eval_loss": 1.0897018909454346,
      "eval_runtime": 192.8064,
      "eval_samples_per_second": 1.037,
      "eval_steps_per_second": 0.13,
      "step": 13
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.3307149375898363,
      "learning_rate": 2e-05,
      "loss": 1.1014,
      "step": 14
    },
    {
      "epoch": 0.4375,
      "eval_loss": 1.075058937072754,
      "eval_runtime": 192.1353,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.13,
      "step": 14
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.31999611930431227,
      "learning_rate": 2e-05,
      "loss": 1.0847,
      "step": 15
    },
    {
      "epoch": 0.46875,
      "eval_loss": 1.0613062381744385,
      "eval_runtime": 192.0586,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.13,
      "step": 15
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.2494159223446848,
      "learning_rate": 2e-05,
      "loss": 1.0428,
      "step": 16
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.0484405755996704,
      "eval_runtime": 192.52,
      "eval_samples_per_second": 1.039,
      "eval_steps_per_second": 0.13,
      "step": 16
    },
    {
      "epoch": 0.53125,
      "grad_norm": 0.2899303168196212,
      "learning_rate": 2e-05,
      "loss": 1.122,
      "step": 17
    },
    {
      "epoch": 0.53125,
      "eval_loss": 1.036120891571045,
      "eval_runtime": 192.5716,
      "eval_samples_per_second": 1.039,
      "eval_steps_per_second": 0.13,
      "step": 17
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.2995776829874209,
      "learning_rate": 2e-05,
      "loss": 1.0425,
      "step": 18
    },
    {
      "epoch": 0.5625,
      "eval_loss": 1.0226774215698242,
      "eval_runtime": 192.5256,
      "eval_samples_per_second": 1.039,
      "eval_steps_per_second": 0.13,
      "step": 18
    },
    {
      "epoch": 0.59375,
      "grad_norm": 0.28709859243892955,
      "learning_rate": 2e-05,
      "loss": 1.0098,
      "step": 19
    },
    {
      "epoch": 0.59375,
      "eval_loss": 1.0081837177276611,
      "eval_runtime": 192.3486,
      "eval_samples_per_second": 1.04,
      "eval_steps_per_second": 0.13,
      "step": 19
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.27612474678791227,
      "learning_rate": 2e-05,
      "loss": 1.0563,
      "step": 20
    },
    {
      "epoch": 0.625,
      "eval_loss": 0.994163990020752,
      "eval_runtime": 191.9782,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.13,
      "step": 20
    },
    {
      "epoch": 0.65625,
      "grad_norm": 0.24260720679126926,
      "learning_rate": 2e-05,
      "loss": 1.0355,
      "step": 21
    },
    {
      "epoch": 0.65625,
      "eval_loss": 0.9819543361663818,
      "eval_runtime": 191.9306,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.13,
      "step": 21
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.25336536603884946,
      "learning_rate": 2e-05,
      "loss": 1.0525,
      "step": 22
    },
    {
      "epoch": 0.6875,
      "eval_loss": 0.9709838032722473,
      "eval_runtime": 192.9913,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.13,
      "step": 22
    },
    {
      "epoch": 0.71875,
      "grad_norm": 0.24820839136364292,
      "learning_rate": 2e-05,
      "loss": 1.1392,
      "step": 23
    },
    {
      "epoch": 0.71875,
      "eval_loss": 0.9616628885269165,
      "eval_runtime": 192.6673,
      "eval_samples_per_second": 1.038,
      "eval_steps_per_second": 0.13,
      "step": 23
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.24589291203527217,
      "learning_rate": 2e-05,
      "loss": 1.058,
      "step": 24
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.9531083703041077,
      "eval_runtime": 193.0994,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.129,
      "step": 24
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.249532642718915,
      "learning_rate": 2e-05,
      "loss": 0.938,
      "step": 25
    },
    {
      "epoch": 0.78125,
      "eval_loss": 0.9455437660217285,
      "eval_runtime": 191.9941,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.13,
      "step": 25
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.28034242585086017,
      "learning_rate": 2e-05,
      "loss": 0.9387,
      "step": 26
    },
    {
      "epoch": 0.8125,
      "eval_loss": 0.93752121925354,
      "eval_runtime": 195.4083,
      "eval_samples_per_second": 1.023,
      "eval_steps_per_second": 0.128,
      "step": 26
    },
    {
      "epoch": 0.84375,
      "grad_norm": 0.2692565070546352,
      "learning_rate": 2e-05,
      "loss": 1.0474,
      "step": 27
    },
    {
      "epoch": 0.84375,
      "eval_loss": 0.9300512075424194,
      "eval_runtime": 195.3651,
      "eval_samples_per_second": 1.024,
      "eval_steps_per_second": 0.128,
      "step": 27
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.24705041646949316,
      "learning_rate": 2e-05,
      "loss": 0.9596,
      "step": 28
    },
    {
      "epoch": 0.875,
      "eval_loss": 0.9226720929145813,
      "eval_runtime": 195.4848,
      "eval_samples_per_second": 1.023,
      "eval_steps_per_second": 0.128,
      "step": 28
    },
    {
      "epoch": 0.90625,
      "grad_norm": 0.24799871352606165,
      "learning_rate": 2e-05,
      "loss": 1.0172,
      "step": 29
    },
    {
      "epoch": 0.90625,
      "eval_loss": 0.9159422516822815,
      "eval_runtime": 196.157,
      "eval_samples_per_second": 1.02,
      "eval_steps_per_second": 0.127,
      "step": 29
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.29755264040904106,
      "learning_rate": 2e-05,
      "loss": 0.9324,
      "step": 30
    },
    {
      "epoch": 0.9375,
      "eval_loss": 0.9090733528137207,
      "eval_runtime": 196.5295,
      "eval_samples_per_second": 1.018,
      "eval_steps_per_second": 0.127,
      "step": 30
    },
    {
      "epoch": 0.96875,
      "grad_norm": 0.2629221961008751,
      "learning_rate": 2e-05,
      "loss": 0.9265,
      "step": 31
    },
    {
      "epoch": 0.96875,
      "eval_loss": 0.9027940630912781,
      "eval_runtime": 196.281,
      "eval_samples_per_second": 1.019,
      "eval_steps_per_second": 0.127,
      "step": 31
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2901110704218056,
      "learning_rate": 2e-05,
      "loss": 0.9933,
      "step": 32
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8970211148262024,
      "eval_runtime": 190.2702,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 32
    },
    {
      "epoch": 1.03125,
      "grad_norm": 0.27746608883483487,
      "learning_rate": 2e-05,
      "loss": 0.9339,
      "step": 33
    },
    {
      "epoch": 1.03125,
      "eval_loss": 0.8916085958480835,
      "eval_runtime": 189.4543,
      "eval_samples_per_second": 1.056,
      "eval_steps_per_second": 0.132,
      "step": 33
    },
    {
      "epoch": 1.0625,
      "grad_norm": 0.26134437145600353,
      "learning_rate": 2e-05,
      "loss": 0.9438,
      "step": 34
    },
    {
      "epoch": 1.0625,
      "eval_loss": 0.8867039680480957,
      "eval_runtime": 189.6926,
      "eval_samples_per_second": 1.054,
      "eval_steps_per_second": 0.132,
      "step": 34
    },
    {
      "epoch": 1.09375,
      "grad_norm": 0.252882507519195,
      "learning_rate": 2e-05,
      "loss": 0.8979,
      "step": 35
    },
    {
      "epoch": 1.09375,
      "eval_loss": 0.8824067711830139,
      "eval_runtime": 189.9217,
      "eval_samples_per_second": 1.053,
      "eval_steps_per_second": 0.132,
      "step": 35
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.25443025949474585,
      "learning_rate": 2e-05,
      "loss": 0.9411,
      "step": 36
    },
    {
      "epoch": 1.125,
      "eval_loss": 0.8788293600082397,
      "eval_runtime": 191.4083,
      "eval_samples_per_second": 1.045,
      "eval_steps_per_second": 0.131,
      "step": 36
    },
    {
      "epoch": 1.15625,
      "grad_norm": 0.2559343621244427,
      "learning_rate": 2e-05,
      "loss": 0.9827,
      "step": 37
    },
    {
      "epoch": 1.15625,
      "eval_loss": 0.8760793805122375,
      "eval_runtime": 191.2732,
      "eval_samples_per_second": 1.046,
      "eval_steps_per_second": 0.131,
      "step": 37
    },
    {
      "epoch": 1.1875,
      "grad_norm": 0.25403189851366254,
      "learning_rate": 2e-05,
      "loss": 0.8658,
      "step": 38
    },
    {
      "epoch": 1.1875,
      "eval_loss": 0.8727380633354187,
      "eval_runtime": 190.4281,
      "eval_samples_per_second": 1.05,
      "eval_steps_per_second": 0.131,
      "step": 38
    },
    {
      "epoch": 1.21875,
      "grad_norm": 0.2493777578005398,
      "learning_rate": 2e-05,
      "loss": 1.0053,
      "step": 39
    },
    {
      "epoch": 1.21875,
      "eval_loss": 0.869698703289032,
      "eval_runtime": 190.3431,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 39
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.24823573574563138,
      "learning_rate": 2e-05,
      "loss": 0.8967,
      "step": 40
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.8664910793304443,
      "eval_runtime": 189.9802,
      "eval_samples_per_second": 1.053,
      "eval_steps_per_second": 0.132,
      "step": 40
    },
    {
      "epoch": 1.28125,
      "grad_norm": 0.25462243237743476,
      "learning_rate": 2e-05,
      "loss": 1.0064,
      "step": 41
    },
    {
      "epoch": 1.28125,
      "eval_loss": 0.8638657927513123,
      "eval_runtime": 195.3373,
      "eval_samples_per_second": 1.024,
      "eval_steps_per_second": 0.128,
      "step": 41
    },
    {
      "epoch": 1.3125,
      "grad_norm": 0.2604089386111215,
      "learning_rate": 2e-05,
      "loss": 0.9898,
      "step": 42
    },
    {
      "epoch": 1.3125,
      "eval_loss": 0.8607734441757202,
      "eval_runtime": 195.219,
      "eval_samples_per_second": 1.024,
      "eval_steps_per_second": 0.128,
      "step": 42
    },
    {
      "epoch": 1.34375,
      "grad_norm": 0.27139202440805793,
      "learning_rate": 2e-05,
      "loss": 1.0539,
      "step": 43
    },
    {
      "epoch": 1.34375,
      "eval_loss": 0.8573687672615051,
      "eval_runtime": 195.8828,
      "eval_samples_per_second": 1.021,
      "eval_steps_per_second": 0.128,
      "step": 43
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.27474433057157854,
      "learning_rate": 2e-05,
      "loss": 0.86,
      "step": 44
    },
    {
      "epoch": 1.375,
      "eval_loss": 0.8537396192550659,
      "eval_runtime": 194.9741,
      "eval_samples_per_second": 1.026,
      "eval_steps_per_second": 0.128,
      "step": 44
    },
    {
      "epoch": 1.40625,
      "grad_norm": 0.2537208760747199,
      "learning_rate": 2e-05,
      "loss": 0.9562,
      "step": 45
    },
    {
      "epoch": 1.40625,
      "eval_loss": 0.8497809767723083,
      "eval_runtime": 194.9162,
      "eval_samples_per_second": 1.026,
      "eval_steps_per_second": 0.128,
      "step": 45
    },
    {
      "epoch": 1.4375,
      "grad_norm": 0.27560461131090846,
      "learning_rate": 2e-05,
      "loss": 0.8767,
      "step": 46
    },
    {
      "epoch": 1.4375,
      "eval_loss": 0.8458660244941711,
      "eval_runtime": 195.1157,
      "eval_samples_per_second": 1.025,
      "eval_steps_per_second": 0.128,
      "step": 46
    },
    {
      "epoch": 1.46875,
      "grad_norm": 0.2594536794112662,
      "learning_rate": 2e-05,
      "loss": 0.9256,
      "step": 47
    },
    {
      "epoch": 1.46875,
      "eval_loss": 0.8429936766624451,
      "eval_runtime": 195.048,
      "eval_samples_per_second": 1.025,
      "eval_steps_per_second": 0.128,
      "step": 47
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.28583207453838866,
      "learning_rate": 2e-05,
      "loss": 0.9858,
      "step": 48
    },
    {
      "epoch": 1.5,
      "eval_loss": 0.84013831615448,
      "eval_runtime": 194.3046,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 48
    },
    {
      "epoch": 1.53125,
      "grad_norm": 0.28118976636788506,
      "learning_rate": 2e-05,
      "loss": 0.9158,
      "step": 49
    },
    {
      "epoch": 1.53125,
      "eval_loss": 0.8369531035423279,
      "eval_runtime": 194.521,
      "eval_samples_per_second": 1.028,
      "eval_steps_per_second": 0.129,
      "step": 49
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.29276573776696546,
      "learning_rate": 2e-05,
      "loss": 0.8745,
      "step": 50
    },
    {
      "epoch": 1.5625,
      "eval_loss": 0.8341982960700989,
      "eval_runtime": 194.1114,
      "eval_samples_per_second": 1.03,
      "eval_steps_per_second": 0.129,
      "step": 50
    },
    {
      "epoch": 1.59375,
      "grad_norm": 0.2860638141439372,
      "learning_rate": 2e-05,
      "loss": 0.854,
      "step": 51
    },
    {
      "epoch": 1.59375,
      "eval_loss": 0.8317239284515381,
      "eval_runtime": 198.1029,
      "eval_samples_per_second": 1.01,
      "eval_steps_per_second": 0.126,
      "step": 51
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.29960349722496704,
      "learning_rate": 2e-05,
      "loss": 0.8399,
      "step": 52
    },
    {
      "epoch": 1.625,
      "eval_loss": 0.8290513753890991,
      "eval_runtime": 198.0764,
      "eval_samples_per_second": 1.01,
      "eval_steps_per_second": 0.126,
      "step": 52
    },
    {
      "epoch": 1.65625,
      "grad_norm": 0.2964234305808419,
      "learning_rate": 2e-05,
      "loss": 0.9694,
      "step": 53
    },
    {
      "epoch": 1.65625,
      "eval_loss": 0.8267760276794434,
      "eval_runtime": 197.8284,
      "eval_samples_per_second": 1.011,
      "eval_steps_per_second": 0.126,
      "step": 53
    },
    {
      "epoch": 1.6875,
      "grad_norm": 0.26183932644077784,
      "learning_rate": 2e-05,
      "loss": 0.8153,
      "step": 54
    },
    {
      "epoch": 1.6875,
      "eval_loss": 0.824044942855835,
      "eval_runtime": 198.1694,
      "eval_samples_per_second": 1.009,
      "eval_steps_per_second": 0.126,
      "step": 54
    },
    {
      "epoch": 1.71875,
      "grad_norm": 0.3067024314453144,
      "learning_rate": 2e-05,
      "loss": 0.883,
      "step": 55
    },
    {
      "epoch": 1.71875,
      "eval_loss": 0.8216392397880554,
      "eval_runtime": 198.0249,
      "eval_samples_per_second": 1.01,
      "eval_steps_per_second": 0.126,
      "step": 55
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.27888658705355013,
      "learning_rate": 2e-05,
      "loss": 0.8771,
      "step": 56
    },
    {
      "epoch": 1.75,
      "eval_loss": 0.8194215297698975,
      "eval_runtime": 195.4688,
      "eval_samples_per_second": 1.023,
      "eval_steps_per_second": 0.128,
      "step": 56
    },
    {
      "epoch": 1.78125,
      "grad_norm": 0.32571765544245934,
      "learning_rate": 2e-05,
      "loss": 0.897,
      "step": 57
    },
    {
      "epoch": 1.78125,
      "eval_loss": 0.8167170882225037,
      "eval_runtime": 189.6243,
      "eval_samples_per_second": 1.055,
      "eval_steps_per_second": 0.132,
      "step": 57
    },
    {
      "epoch": 1.8125,
      "grad_norm": 0.292216058855145,
      "learning_rate": 2e-05,
      "loss": 0.9277,
      "step": 58
    },
    {
      "epoch": 1.8125,
      "eval_loss": 0.8145509958267212,
      "eval_runtime": 190.2429,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 58
    },
    {
      "epoch": 1.84375,
      "grad_norm": 0.29002612820437024,
      "learning_rate": 2e-05,
      "loss": 0.8971,
      "step": 59
    },
    {
      "epoch": 1.84375,
      "eval_loss": 0.8122230768203735,
      "eval_runtime": 189.9403,
      "eval_samples_per_second": 1.053,
      "eval_steps_per_second": 0.132,
      "step": 59
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.2926088029288858,
      "learning_rate": 2e-05,
      "loss": 0.9225,
      "step": 60
    },
    {
      "epoch": 1.875,
      "eval_loss": 0.8100479245185852,
      "eval_runtime": 190.2569,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 60
    },
    {
      "epoch": 1.90625,
      "grad_norm": 0.30068993111077397,
      "learning_rate": 2e-05,
      "loss": 0.9134,
      "step": 61
    },
    {
      "epoch": 1.90625,
      "eval_loss": 0.808087944984436,
      "eval_runtime": 192.4896,
      "eval_samples_per_second": 1.039,
      "eval_steps_per_second": 0.13,
      "step": 61
    },
    {
      "epoch": 1.9375,
      "grad_norm": 0.3157573686768343,
      "learning_rate": 2e-05,
      "loss": 0.8965,
      "step": 62
    },
    {
      "epoch": 1.9375,
      "eval_loss": 0.8057371377944946,
      "eval_runtime": 190.0158,
      "eval_samples_per_second": 1.053,
      "eval_steps_per_second": 0.132,
      "step": 62
    },
    {
      "epoch": 1.96875,
      "grad_norm": 0.31215592754506605,
      "learning_rate": 2e-05,
      "loss": 0.7828,
      "step": 63
    },
    {
      "epoch": 1.96875,
      "eval_loss": 0.8031384944915771,
      "eval_runtime": 189.5204,
      "eval_samples_per_second": 1.055,
      "eval_steps_per_second": 0.132,
      "step": 63
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.29422828766227993,
      "learning_rate": 2e-05,
      "loss": 0.8196,
      "step": 64
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8012601733207703,
      "eval_runtime": 189.7041,
      "eval_samples_per_second": 1.054,
      "eval_steps_per_second": 0.132,
      "step": 64
    },
    {
      "epoch": 2.03125,
      "grad_norm": 0.2885449518895793,
      "learning_rate": 2e-05,
      "loss": 0.9715,
      "step": 65
    },
    {
      "epoch": 2.03125,
      "eval_loss": 0.8001161813735962,
      "eval_runtime": 189.57,
      "eval_samples_per_second": 1.055,
      "eval_steps_per_second": 0.132,
      "step": 65
    },
    {
      "epoch": 2.0625,
      "grad_norm": 0.30260184063348483,
      "learning_rate": 2e-05,
      "loss": 0.7912,
      "step": 66
    },
    {
      "epoch": 2.0625,
      "eval_loss": 0.7989436388015747,
      "eval_runtime": 193.0193,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.13,
      "step": 66
    },
    {
      "epoch": 2.09375,
      "grad_norm": 0.32650294605024255,
      "learning_rate": 2e-05,
      "loss": 0.8176,
      "step": 67
    },
    {
      "epoch": 2.09375,
      "eval_loss": 0.7972333431243896,
      "eval_runtime": 193.2225,
      "eval_samples_per_second": 1.035,
      "eval_steps_per_second": 0.129,
      "step": 67
    },
    {
      "epoch": 2.125,
      "grad_norm": 0.3382679480741134,
      "learning_rate": 2e-05,
      "loss": 0.8141,
      "step": 68
    },
    {
      "epoch": 2.125,
      "eval_loss": 0.7950598001480103,
      "eval_runtime": 193.2781,
      "eval_samples_per_second": 1.035,
      "eval_steps_per_second": 0.129,
      "step": 68
    },
    {
      "epoch": 2.15625,
      "grad_norm": 0.3094090784935889,
      "learning_rate": 2e-05,
      "loss": 0.796,
      "step": 69
    },
    {
      "epoch": 2.15625,
      "eval_loss": 0.7932476997375488,
      "eval_runtime": 193.0282,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.13,
      "step": 69
    },
    {
      "epoch": 2.1875,
      "grad_norm": 0.30209558834780514,
      "learning_rate": 2e-05,
      "loss": 0.927,
      "step": 70
    },
    {
      "epoch": 2.1875,
      "eval_loss": 0.7922118902206421,
      "eval_runtime": 192.8284,
      "eval_samples_per_second": 1.037,
      "eval_steps_per_second": 0.13,
      "step": 70
    },
    {
      "epoch": 2.21875,
      "grad_norm": 0.35958652905266686,
      "learning_rate": 2e-05,
      "loss": 0.8224,
      "step": 71
    },
    {
      "epoch": 2.21875,
      "eval_loss": 0.7909810543060303,
      "eval_runtime": 202.3128,
      "eval_samples_per_second": 0.989,
      "eval_steps_per_second": 0.124,
      "step": 71
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.356338004067507,
      "learning_rate": 2e-05,
      "loss": 0.8376,
      "step": 72
    },
    {
      "epoch": 2.25,
      "eval_loss": 0.7894656658172607,
      "eval_runtime": 195.1481,
      "eval_samples_per_second": 1.025,
      "eval_steps_per_second": 0.128,
      "step": 72
    },
    {
      "epoch": 2.28125,
      "grad_norm": 0.31886905989727465,
      "learning_rate": 2e-05,
      "loss": 0.8688,
      "step": 73
    },
    {
      "epoch": 2.28125,
      "eval_loss": 0.7889463901519775,
      "eval_runtime": 194.8418,
      "eval_samples_per_second": 1.026,
      "eval_steps_per_second": 0.128,
      "step": 73
    },
    {
      "epoch": 2.3125,
      "grad_norm": 0.35606342918056466,
      "learning_rate": 2e-05,
      "loss": 0.835,
      "step": 74
    },
    {
      "epoch": 2.3125,
      "eval_loss": 0.7875587344169617,
      "eval_runtime": 194.7701,
      "eval_samples_per_second": 1.027,
      "eval_steps_per_second": 0.128,
      "step": 74
    },
    {
      "epoch": 2.34375,
      "grad_norm": 0.3161858862696026,
      "learning_rate": 2e-05,
      "loss": 0.873,
      "step": 75
    },
    {
      "epoch": 2.34375,
      "eval_loss": 0.7863460779190063,
      "eval_runtime": 195.4811,
      "eval_samples_per_second": 1.023,
      "eval_steps_per_second": 0.128,
      "step": 75
    },
    {
      "epoch": 2.375,
      "grad_norm": 0.35771781884741477,
      "learning_rate": 2e-05,
      "loss": 0.9021,
      "step": 76
    },
    {
      "epoch": 2.375,
      "eval_loss": 0.7847577929496765,
      "eval_runtime": 195.3724,
      "eval_samples_per_second": 1.024,
      "eval_steps_per_second": 0.128,
      "step": 76
    },
    {
      "epoch": 2.40625,
      "grad_norm": 0.3549789155823785,
      "learning_rate": 2e-05,
      "loss": 0.9195,
      "step": 77
    },
    {
      "epoch": 2.40625,
      "eval_loss": 0.783415675163269,
      "eval_runtime": 190.226,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 77
    },
    {
      "epoch": 2.4375,
      "grad_norm": 0.34734314309709374,
      "learning_rate": 2e-05,
      "loss": 0.8386,
      "step": 78
    },
    {
      "epoch": 2.4375,
      "eval_loss": 0.7814657688140869,
      "eval_runtime": 190.3177,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 78
    },
    {
      "epoch": 2.46875,
      "grad_norm": 0.35540762574897183,
      "learning_rate": 2e-05,
      "loss": 0.851,
      "step": 79
    },
    {
      "epoch": 2.46875,
      "eval_loss": 0.7798058390617371,
      "eval_runtime": 190.7447,
      "eval_samples_per_second": 1.049,
      "eval_steps_per_second": 0.131,
      "step": 79
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.3844458514717174,
      "learning_rate": 2e-05,
      "loss": 0.767,
      "step": 80
    },
    {
      "epoch": 2.5,
      "eval_loss": 0.7777827978134155,
      "eval_runtime": 190.8548,
      "eval_samples_per_second": 1.048,
      "eval_steps_per_second": 0.131,
      "step": 80
    },
    {
      "epoch": 2.53125,
      "grad_norm": 0.36232344175264375,
      "learning_rate": 2e-05,
      "loss": 0.8508,
      "step": 81
    },
    {
      "epoch": 2.53125,
      "eval_loss": 0.7763205170631409,
      "eval_runtime": 190.335,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 81
    },
    {
      "epoch": 2.5625,
      "grad_norm": 0.36279843147857743,
      "learning_rate": 2e-05,
      "loss": 0.8331,
      "step": 82
    },
    {
      "epoch": 2.5625,
      "eval_loss": 0.7757676839828491,
      "eval_runtime": 190.9559,
      "eval_samples_per_second": 1.047,
      "eval_steps_per_second": 0.131,
      "step": 82
    },
    {
      "epoch": 2.59375,
      "grad_norm": 0.395360566032837,
      "learning_rate": 2e-05,
      "loss": 0.847,
      "step": 83
    },
    {
      "epoch": 2.59375,
      "eval_loss": 0.7743326425552368,
      "eval_runtime": 190.6372,
      "eval_samples_per_second": 1.049,
      "eval_steps_per_second": 0.131,
      "step": 83
    },
    {
      "epoch": 2.625,
      "grad_norm": 0.4268568783791123,
      "learning_rate": 2e-05,
      "loss": 0.869,
      "step": 84
    },
    {
      "epoch": 2.625,
      "eval_loss": 0.772053062915802,
      "eval_runtime": 190.2072,
      "eval_samples_per_second": 1.051,
      "eval_steps_per_second": 0.131,
      "step": 84
    },
    {
      "epoch": 2.65625,
      "grad_norm": 0.3581495538253167,
      "learning_rate": 2e-05,
      "loss": 0.8591,
      "step": 85
    },
    {
      "epoch": 2.65625,
      "eval_loss": 0.7711917757987976,
      "eval_runtime": 190.4392,
      "eval_samples_per_second": 1.05,
      "eval_steps_per_second": 0.131,
      "step": 85
    },
    {
      "epoch": 2.6875,
      "grad_norm": 0.3952841797586726,
      "learning_rate": 2e-05,
      "loss": 0.8167,
      "step": 86
    },
    {
      "epoch": 2.6875,
      "eval_loss": 0.7714033722877502,
      "eval_runtime": 193.8038,
      "eval_samples_per_second": 1.032,
      "eval_steps_per_second": 0.129,
      "step": 86
    },
    {
      "epoch": 2.71875,
      "grad_norm": 0.41820009905687616,
      "learning_rate": 2e-05,
      "loss": 0.8165,
      "step": 87
    },
    {
      "epoch": 2.71875,
      "eval_loss": 0.771486759185791,
      "eval_runtime": 194.4791,
      "eval_samples_per_second": 1.028,
      "eval_steps_per_second": 0.129,
      "step": 87
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.3852566717747202,
      "learning_rate": 2e-05,
      "loss": 0.8459,
      "step": 88
    },
    {
      "epoch": 2.75,
      "eval_loss": 0.7710732817649841,
      "eval_runtime": 194.3404,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 88
    },
    {
      "epoch": 2.78125,
      "grad_norm": 0.39909292055831935,
      "learning_rate": 2e-05,
      "loss": 0.8945,
      "step": 89
    },
    {
      "epoch": 2.78125,
      "eval_loss": 0.7708308696746826,
      "eval_runtime": 194.4483,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 89
    },
    {
      "epoch": 2.8125,
      "grad_norm": 0.3916487629667217,
      "learning_rate": 2e-05,
      "loss": 0.8029,
      "step": 90
    },
    {
      "epoch": 2.8125,
      "eval_loss": 0.7713395953178406,
      "eval_runtime": 194.6045,
      "eval_samples_per_second": 1.028,
      "eval_steps_per_second": 0.128,
      "step": 90
    },
    {
      "epoch": 2.84375,
      "grad_norm": 0.36969072235715195,
      "learning_rate": 2e-05,
      "loss": 0.7704,
      "step": 91
    },
    {
      "epoch": 2.84375,
      "eval_loss": 0.7713618278503418,
      "eval_runtime": 194.3895,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 91
    },
    {
      "epoch": 2.875,
      "grad_norm": 0.3853248559868725,
      "learning_rate": 2e-05,
      "loss": 0.8247,
      "step": 92
    },
    {
      "epoch": 2.875,
      "eval_loss": 0.7703633308410645,
      "eval_runtime": 194.0457,
      "eval_samples_per_second": 1.031,
      "eval_steps_per_second": 0.129,
      "step": 92
    },
    {
      "epoch": 2.90625,
      "grad_norm": 0.38111471762069055,
      "learning_rate": 2e-05,
      "loss": 0.855,
      "step": 93
    },
    {
      "epoch": 2.90625,
      "eval_loss": 0.7690189480781555,
      "eval_runtime": 194.3506,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 93
    },
    {
      "epoch": 2.9375,
      "grad_norm": 0.3701270310997752,
      "learning_rate": 2e-05,
      "loss": 0.7518,
      "step": 94
    },
    {
      "epoch": 2.9375,
      "eval_loss": 0.7675644159317017,
      "eval_runtime": 194.3756,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 94
    },
    {
      "epoch": 2.96875,
      "grad_norm": 0.40489524752286055,
      "learning_rate": 2e-05,
      "loss": 0.8559,
      "step": 95
    },
    {
      "epoch": 2.96875,
      "eval_loss": 0.766002357006073,
      "eval_runtime": 193.9472,
      "eval_samples_per_second": 1.031,
      "eval_steps_per_second": 0.129,
      "step": 95
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.39220887464051457,
      "learning_rate": 2e-05,
      "loss": 0.8629,
      "step": 96
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7644355893135071,
      "eval_runtime": 196.1686,
      "eval_samples_per_second": 1.02,
      "eval_steps_per_second": 0.127,
      "step": 96
    },
    {
      "epoch": 3.03125,
      "grad_norm": 0.3644925708419195,
      "learning_rate": 2e-05,
      "loss": 0.7434,
      "step": 97
    },
    {
      "epoch": 3.03125,
      "eval_loss": 0.7628399133682251,
      "eval_runtime": 196.1515,
      "eval_samples_per_second": 1.02,
      "eval_steps_per_second": 0.127,
      "step": 97
    },
    {
      "epoch": 3.0625,
      "grad_norm": 0.407089942317534,
      "learning_rate": 2e-05,
      "loss": 0.8038,
      "step": 98
    },
    {
      "epoch": 3.0625,
      "eval_loss": 0.7609645128250122,
      "eval_runtime": 196.8662,
      "eval_samples_per_second": 1.016,
      "eval_steps_per_second": 0.127,
      "step": 98
    },
    {
      "epoch": 3.09375,
      "grad_norm": 0.38849177572880716,
      "learning_rate": 2e-05,
      "loss": 0.8106,
      "step": 99
    },
    {
      "epoch": 3.09375,
      "eval_loss": 0.7598288059234619,
      "eval_runtime": 196.1846,
      "eval_samples_per_second": 1.019,
      "eval_steps_per_second": 0.127,
      "step": 99
    },
    {
      "epoch": 3.125,
      "grad_norm": 0.41885563528617265,
      "learning_rate": 2e-05,
      "loss": 0.808,
      "step": 100
    },
    {
      "epoch": 3.125,
      "eval_loss": 0.7587143778800964,
      "eval_runtime": 195.7296,
      "eval_samples_per_second": 1.022,
      "eval_steps_per_second": 0.128,
      "step": 100
    },
    {
      "epoch": 3.15625,
      "grad_norm": 0.4003909227323588,
      "learning_rate": 2e-05,
      "loss": 0.791,
      "step": 101
    },
    {
      "epoch": 3.15625,
      "eval_loss": 0.7578326463699341,
      "eval_runtime": 195.2831,
      "eval_samples_per_second": 1.024,
      "eval_steps_per_second": 0.128,
      "step": 101
    },
    {
      "epoch": 3.1875,
      "grad_norm": 0.4014550365826672,
      "learning_rate": 2e-05,
      "loss": 0.7402,
      "step": 102
    },
    {
      "epoch": 3.1875,
      "eval_loss": 0.7573958039283752,
      "eval_runtime": 189.5234,
      "eval_samples_per_second": 1.055,
      "eval_steps_per_second": 0.132,
      "step": 102
    },
    {
      "epoch": 3.21875,
      "grad_norm": 0.4018554316691014,
      "learning_rate": 2e-05,
      "loss": 0.8165,
      "step": 103
    },
    {
      "epoch": 3.21875,
      "eval_loss": 0.7571737766265869,
      "eval_runtime": 190.0146,
      "eval_samples_per_second": 1.053,
      "eval_steps_per_second": 0.132,
      "step": 103
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.39691385018938347,
      "learning_rate": 2e-05,
      "loss": 0.7806,
      "step": 104
    },
    {
      "epoch": 3.25,
      "eval_loss": 0.7581367492675781,
      "eval_runtime": 190.1851,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 0.131,
      "step": 104
    },
    {
      "epoch": 3.28125,
      "grad_norm": 0.390373263306042,
      "learning_rate": 2e-05,
      "loss": 0.7454,
      "step": 105
    },
    {
      "epoch": 3.28125,
      "eval_loss": 0.7590533494949341,
      "eval_runtime": 190.1255,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 0.131,
      "step": 105
    },
    {
      "epoch": 3.3125,
      "grad_norm": 0.45093404603350434,
      "learning_rate": 2e-05,
      "loss": 0.8598,
      "step": 106
    },
    {
      "epoch": 3.3125,
      "eval_loss": 0.7584137916564941,
      "eval_runtime": 193.5956,
      "eval_samples_per_second": 1.033,
      "eval_steps_per_second": 0.129,
      "step": 106
    },
    {
      "epoch": 3.34375,
      "grad_norm": 0.4112664411035318,
      "learning_rate": 2e-05,
      "loss": 0.8612,
      "step": 107
    },
    {
      "epoch": 3.34375,
      "eval_loss": 0.757759690284729,
      "eval_runtime": 191.7864,
      "eval_samples_per_second": 1.043,
      "eval_steps_per_second": 0.13,
      "step": 107
    },
    {
      "epoch": 3.375,
      "grad_norm": 0.4158875890717671,
      "learning_rate": 2e-05,
      "loss": 0.7916,
      "step": 108
    },
    {
      "epoch": 3.375,
      "eval_loss": 0.756908655166626,
      "eval_runtime": 190.1833,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 0.131,
      "step": 108
    },
    {
      "epoch": 3.40625,
      "grad_norm": 0.4234644828447959,
      "learning_rate": 2e-05,
      "loss": 0.798,
      "step": 109
    },
    {
      "epoch": 3.40625,
      "eval_loss": 0.7559736371040344,
      "eval_runtime": 190.0515,
      "eval_samples_per_second": 1.052,
      "eval_steps_per_second": 0.132,
      "step": 109
    },
    {
      "epoch": 3.4375,
      "grad_norm": 0.480506693884699,
      "learning_rate": 2e-05,
      "loss": 0.7964,
      "step": 110
    },
    {
      "epoch": 3.4375,
      "eval_loss": 0.7547717094421387,
      "eval_runtime": 189.9579,
      "eval_samples_per_second": 1.053,
      "eval_steps_per_second": 0.132,
      "step": 110
    },
    {
      "epoch": 3.46875,
      "grad_norm": 0.4540166631930203,
      "learning_rate": 2e-05,
      "loss": 0.8172,
      "step": 111
    },
    {
      "epoch": 3.46875,
      "eval_loss": 0.7538467645645142,
      "eval_runtime": 194.2136,
      "eval_samples_per_second": 1.03,
      "eval_steps_per_second": 0.129,
      "step": 111
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.46782505650509537,
      "learning_rate": 2e-05,
      "loss": 0.7826,
      "step": 112
    },
    {
      "epoch": 3.5,
      "eval_loss": 0.7537503838539124,
      "eval_runtime": 194.396,
      "eval_samples_per_second": 1.029,
      "eval_steps_per_second": 0.129,
      "step": 112
    },
    {
      "epoch": 3.53125,
      "grad_norm": 0.5212465522615498,
      "learning_rate": 2e-05,
      "loss": 0.7715,
      "step": 113
    },
    {
      "epoch": 3.53125,
      "eval_loss": 0.7527998089790344,
      "eval_runtime": 193.1123,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.129,
      "step": 113
    },
    {
      "epoch": 3.5625,
      "grad_norm": 0.4869709286188453,
      "learning_rate": 2e-05,
      "loss": 0.8007,
      "step": 114
    },
    {
      "epoch": 3.5625,
      "eval_loss": 0.7510444521903992,
      "eval_runtime": 193.3613,
      "eval_samples_per_second": 1.034,
      "eval_steps_per_second": 0.129,
      "step": 114
    },
    {
      "epoch": 3.59375,
      "grad_norm": 0.45218808224844204,
      "learning_rate": 2e-05,
      "loss": 0.7183,
      "step": 115
    },
    {
      "epoch": 3.59375,
      "eval_loss": 0.7502281069755554,
      "eval_runtime": 192.9756,
      "eval_samples_per_second": 1.036,
      "eval_steps_per_second": 0.13,
      "step": 115
    },
    {
      "epoch": 3.625,
      "grad_norm": 0.4563394511077237,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 116
    },
    {
      "epoch": 3.625,
      "eval_loss": 0.75026535987854,
      "eval_runtime": 196.5666,
      "eval_samples_per_second": 1.017,
      "eval_steps_per_second": 0.127,
      "step": 116
    },
    {
      "epoch": 3.65625,
      "grad_norm": 0.4439962576867383,
      "learning_rate": 2e-05,
      "loss": 0.8091,
      "step": 117
    },
    {
      "epoch": 3.65625,
      "eval_loss": 0.7515027523040771,
      "eval_runtime": 196.6311,
      "eval_samples_per_second": 1.017,
      "eval_steps_per_second": 0.127,
      "step": 117
    },
    {
      "epoch": 3.6875,
      "grad_norm": 0.44782841352683267,
      "learning_rate": 2e-05,
      "loss": 0.7636,
      "step": 118
    },
    {
      "epoch": 3.6875,
      "eval_loss": 0.7535241842269897,
      "eval_runtime": 196.4625,
      "eval_samples_per_second": 1.018,
      "eval_steps_per_second": 0.127,
      "step": 118
    },
    {
      "epoch": 3.71875,
      "grad_norm": 0.5651906616770451,
      "learning_rate": 2e-05,
      "loss": 0.8106,
      "step": 119
    },
    {
      "epoch": 3.71875,
      "eval_loss": 0.7535383701324463,
      "eval_runtime": 196.0073,
      "eval_samples_per_second": 1.02,
      "eval_steps_per_second": 0.128,
      "step": 119
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.44715700121507296,
      "learning_rate": 2e-05,
      "loss": 0.7991,
      "step": 120
    },
    {
      "epoch": 3.75,
      "eval_loss": 0.75335294008255,
      "eval_runtime": 195.9837,
      "eval_samples_per_second": 1.02,
      "eval_steps_per_second": 0.128,
      "step": 120
    },
    {
      "epoch": 3.75,
      "step": 120,
      "total_flos": 266165567225856.0,
      "train_loss": 0.0,
      "train_runtime": 1.4333,
      "train_samples_per_second": 2790.753,
      "train_steps_per_second": 44.652
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 64,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 266165567225856.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}