{
  "best_metric": 0.006774452514946461,
  "best_model_checkpoint": "/home/paperspace/Data/models/akash_unifo_757/llm3br256/checkpoint-1500",
  "epoch": 3.8434197886647454,
  "eval_steps": 25,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002561639449247518,
      "grad_norm": 0.23406565189361572,
      "learning_rate": 5.128205128205128e-07,
      "loss": 0.066,
      "step": 1
    },
    {
      "epoch": 0.005123278898495036,
      "grad_norm": 0.27100902795791626,
      "learning_rate": 1.0256410256410257e-06,
      "loss": 0.0991,
      "step": 2
    },
    {
      "epoch": 0.007684918347742555,
      "grad_norm": 0.3291971683502197,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.0805,
      "step": 3
    },
    {
      "epoch": 0.010246557796990073,
      "grad_norm": 0.17330855131149292,
      "learning_rate": 2.0512820512820513e-06,
      "loss": 0.0754,
      "step": 4
    },
    {
      "epoch": 0.012808197246237591,
      "grad_norm": 0.2650797665119171,
      "learning_rate": 2.564102564102564e-06,
      "loss": 0.0837,
      "step": 5
    },
    {
      "epoch": 0.01536983669548511,
      "grad_norm": 0.3484267294406891,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.0938,
      "step": 6
    },
    {
      "epoch": 0.01793147614473263,
      "grad_norm": 0.3011722266674042,
      "learning_rate": 3.5897435897435896e-06,
      "loss": 0.0777,
      "step": 7
    },
    {
      "epoch": 0.020493115593980146,
      "grad_norm": 0.184189110994339,
      "learning_rate": 4.102564102564103e-06,
      "loss": 0.0612,
      "step": 8
    },
    {
      "epoch": 0.023054755043227664,
      "grad_norm": 0.18665608763694763,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.0629,
      "step": 9
    },
    {
      "epoch": 0.025616394492475183,
      "grad_norm": 0.20304617285728455,
      "learning_rate": 5.128205128205128e-06,
      "loss": 0.0628,
      "step": 10
    },
    {
      "epoch": 0.0281780339417227,
      "grad_norm": 0.2860122323036194,
      "learning_rate": 5.641025641025641e-06,
      "loss": 0.0792,
      "step": 11
    },
    {
      "epoch": 0.03073967339097022,
      "grad_norm": 0.21296048164367676,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.0575,
      "step": 12
    },
    {
      "epoch": 0.03330131284021774,
      "grad_norm": 0.17642973363399506,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.0563,
      "step": 13
    },
    {
      "epoch": 0.03586295228946526,
      "grad_norm": 0.17329099774360657,
      "learning_rate": 7.179487179487179e-06,
      "loss": 0.0592,
      "step": 14
    },
    {
      "epoch": 0.03842459173871278,
      "grad_norm": 0.11658388376235962,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0448,
      "step": 15
    },
    {
      "epoch": 0.04098623118796029,
      "grad_norm": 0.11522124707698822,
      "learning_rate": 8.205128205128205e-06,
      "loss": 0.0469,
      "step": 16
    },
    {
      "epoch": 0.04354787063720781,
      "grad_norm": 0.15479238331317902,
      "learning_rate": 8.717948717948717e-06,
      "loss": 0.0648,
      "step": 17
    },
    {
      "epoch": 0.04610951008645533,
      "grad_norm": 0.11629645526409149,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.061,
      "step": 18
    },
    {
      "epoch": 0.04867114953570285,
      "grad_norm": 0.09216923266649246,
      "learning_rate": 9.743589743589744e-06,
      "loss": 0.033,
      "step": 19
    },
    {
      "epoch": 0.051232788984950366,
      "grad_norm": 0.10224215686321259,
      "learning_rate": 1.0256410256410256e-05,
      "loss": 0.0329,
      "step": 20
    },
    {
      "epoch": 0.053794428434197884,
      "grad_norm": 0.06882911175489426,
      "learning_rate": 1.0769230769230771e-05,
      "loss": 0.0377,
      "step": 21
    },
    {
      "epoch": 0.0563560678834454,
      "grad_norm": 0.08286888152360916,
      "learning_rate": 1.1282051282051283e-05,
      "loss": 0.0454,
      "step": 22
    },
    {
      "epoch": 0.05891770733269292,
      "grad_norm": 0.08083554357290268,
      "learning_rate": 1.1794871794871795e-05,
      "loss": 0.032,
      "step": 23
    },
    {
      "epoch": 0.06147934678194044,
      "grad_norm": 0.08587988466024399,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.0455,
      "step": 24
    },
    {
      "epoch": 0.06404098623118797,
      "grad_norm": 0.08212395757436752,
      "learning_rate": 1.282051282051282e-05,
      "loss": 0.0269,
      "step": 25
    },
    {
      "epoch": 0.06404098623118797,
      "eval_loss": 0.03533320128917694,
      "eval_runtime": 19.4814,
      "eval_samples_per_second": 5.133,
      "eval_steps_per_second": 1.283,
      "step": 25
    },
    {
      "epoch": 0.06660262568043548,
      "grad_norm": 0.07568451762199402,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.0326,
      "step": 26
    },
    {
      "epoch": 0.069164265129683,
      "grad_norm": 0.0810084268450737,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.0367,
      "step": 27
    },
    {
      "epoch": 0.07172590457893052,
      "grad_norm": 0.06835253536701202,
      "learning_rate": 1.4358974358974359e-05,
      "loss": 0.0344,
      "step": 28
    },
    {
      "epoch": 0.07428754402817804,
      "grad_norm": 0.06612852215766907,
      "learning_rate": 1.4871794871794872e-05,
      "loss": 0.0267,
      "step": 29
    },
    {
      "epoch": 0.07684918347742556,
      "grad_norm": 0.07679713517427444,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0293,
      "step": 30
    },
    {
      "epoch": 0.07941082292667308,
      "grad_norm": 0.06691370159387589,
      "learning_rate": 1.5897435897435897e-05,
      "loss": 0.0349,
      "step": 31
    },
    {
      "epoch": 0.08197246237592058,
      "grad_norm": 0.06954924762248993,
      "learning_rate": 1.641025641025641e-05,
      "loss": 0.0285,
      "step": 32
    },
    {
      "epoch": 0.0845341018251681,
      "grad_norm": 0.06169690564274788,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.0289,
      "step": 33
    },
    {
      "epoch": 0.08709574127441562,
      "grad_norm": 0.05233864113688469,
      "learning_rate": 1.7435897435897434e-05,
      "loss": 0.0259,
      "step": 34
    },
    {
      "epoch": 0.08965738072366314,
      "grad_norm": 0.06114787235856056,
      "learning_rate": 1.794871794871795e-05,
      "loss": 0.0313,
      "step": 35
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": 0.06372269988059998,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.0246,
      "step": 36
    },
    {
      "epoch": 0.09478065962215818,
      "grad_norm": 0.061186905950307846,
      "learning_rate": 1.8974358974358975e-05,
      "loss": 0.0264,
      "step": 37
    },
    {
      "epoch": 0.0973422990714057,
      "grad_norm": 0.06332549452781677,
      "learning_rate": 1.9487179487179488e-05,
      "loss": 0.0396,
      "step": 38
    },
    {
      "epoch": 0.09990393852065321,
      "grad_norm": 0.0470692403614521,
      "learning_rate": 2e-05,
      "loss": 0.0274,
      "step": 39
    },
    {
      "epoch": 0.10246557796990073,
      "grad_norm": 0.0600397065281868,
      "learning_rate": 2.0512820512820512e-05,
      "loss": 0.0373,
      "step": 40
    },
    {
      "epoch": 0.10502721741914825,
      "grad_norm": 0.05703675001859665,
      "learning_rate": 2.102564102564103e-05,
      "loss": 0.0223,
      "step": 41
    },
    {
      "epoch": 0.10758885686839577,
      "grad_norm": 0.07255468517541885,
      "learning_rate": 2.1538461538461542e-05,
      "loss": 0.0424,
      "step": 42
    },
    {
      "epoch": 0.11015049631764329,
      "grad_norm": 0.06241394206881523,
      "learning_rate": 2.2051282051282052e-05,
      "loss": 0.0313,
      "step": 43
    },
    {
      "epoch": 0.1127121357668908,
      "grad_norm": 0.056400399655103683,
      "learning_rate": 2.2564102564102566e-05,
      "loss": 0.0196,
      "step": 44
    },
    {
      "epoch": 0.11527377521613832,
      "grad_norm": 0.04130598530173302,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0243,
      "step": 45
    },
    {
      "epoch": 0.11783541466538584,
      "grad_norm": 0.05306409299373627,
      "learning_rate": 2.358974358974359e-05,
      "loss": 0.0274,
      "step": 46
    },
    {
      "epoch": 0.12039705411463336,
      "grad_norm": 0.04285677894949913,
      "learning_rate": 2.4102564102564103e-05,
      "loss": 0.0161,
      "step": 47
    },
    {
      "epoch": 0.12295869356388088,
      "grad_norm": 0.05328772962093353,
      "learning_rate": 2.461538461538462e-05,
      "loss": 0.0243,
      "step": 48
    },
    {
      "epoch": 0.1255203330131284,
      "grad_norm": 0.05073712766170502,
      "learning_rate": 2.512820512820513e-05,
      "loss": 0.0206,
      "step": 49
    },
    {
      "epoch": 0.12808197246237593,
      "grad_norm": 0.05035106837749481,
      "learning_rate": 2.564102564102564e-05,
      "loss": 0.0361,
      "step": 50
    },
    {
      "epoch": 0.12808197246237593,
      "eval_loss": 0.02137046866118908,
      "eval_runtime": 15.8283,
      "eval_samples_per_second": 6.318,
      "eval_steps_per_second": 1.579,
      "step": 50
    },
    {
      "epoch": 0.13064361191162344,
      "grad_norm": 0.0659724548459053,
      "learning_rate": 2.6153846153846157e-05,
      "loss": 0.031,
      "step": 51
    },
    {
      "epoch": 0.13320525136087097,
      "grad_norm": 0.04782676696777344,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0238,
      "step": 52
    },
    {
      "epoch": 0.13576689081011847,
      "grad_norm": 0.05571295693516731,
      "learning_rate": 2.717948717948718e-05,
      "loss": 0.0258,
      "step": 53
    },
    {
      "epoch": 0.138328530259366,
      "grad_norm": 0.05261208489537239,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 0.0221,
      "step": 54
    },
    {
      "epoch": 0.1408901697086135,
      "grad_norm": 0.053560130298137665,
      "learning_rate": 2.8205128205128207e-05,
      "loss": 0.032,
      "step": 55
    },
    {
      "epoch": 0.14345180915786104,
      "grad_norm": 0.0561230406165123,
      "learning_rate": 2.8717948717948717e-05,
      "loss": 0.0165,
      "step": 56
    },
    {
      "epoch": 0.14601344860710855,
      "grad_norm": 0.05372655764222145,
      "learning_rate": 2.9230769230769234e-05,
      "loss": 0.0295,
      "step": 57
    },
    {
      "epoch": 0.14857508805635608,
      "grad_norm": 0.05659542977809906,
      "learning_rate": 2.9743589743589744e-05,
      "loss": 0.0229,
      "step": 58
    },
    {
      "epoch": 0.15113672750560359,
      "grad_norm": 0.051467038691043854,
      "learning_rate": 3.0256410256410257e-05,
      "loss": 0.0192,
      "step": 59
    },
    {
      "epoch": 0.15369836695485112,
      "grad_norm": 0.0462658628821373,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0236,
      "step": 60
    },
    {
      "epoch": 0.15626000640409862,
      "grad_norm": 0.0534682422876358,
      "learning_rate": 3.128205128205128e-05,
      "loss": 0.027,
      "step": 61
    },
    {
      "epoch": 0.15882164585334616,
      "grad_norm": 0.045332759618759155,
      "learning_rate": 3.1794871794871795e-05,
      "loss": 0.0291,
      "step": 62
    },
    {
      "epoch": 0.16138328530259366,
      "grad_norm": 0.04076462239027023,
      "learning_rate": 3.230769230769231e-05,
      "loss": 0.0245,
      "step": 63
    },
    {
      "epoch": 0.16394492475184116,
      "grad_norm": 0.036102596670389175,
      "learning_rate": 3.282051282051282e-05,
      "loss": 0.0153,
      "step": 64
    },
    {
      "epoch": 0.1665065642010887,
      "grad_norm": 0.06842701137065887,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0506,
      "step": 65
    },
    {
      "epoch": 0.1690682036503362,
      "grad_norm": 0.04626695066690445,
      "learning_rate": 3.384615384615385e-05,
      "loss": 0.0331,
      "step": 66
    },
    {
      "epoch": 0.17162984309958373,
      "grad_norm": 0.058188967406749725,
      "learning_rate": 3.435897435897436e-05,
      "loss": 0.0171,
      "step": 67
    },
    {
      "epoch": 0.17419148254883124,
      "grad_norm": 0.03610702231526375,
      "learning_rate": 3.487179487179487e-05,
      "loss": 0.0246,
      "step": 68
    },
    {
      "epoch": 0.17675312199807877,
      "grad_norm": 0.043155767023563385,
      "learning_rate": 3.538461538461539e-05,
      "loss": 0.0157,
      "step": 69
    },
    {
      "epoch": 0.17931476144732628,
      "grad_norm": 0.04548976942896843,
      "learning_rate": 3.58974358974359e-05,
      "loss": 0.0298,
      "step": 70
    },
    {
      "epoch": 0.1818764008965738,
      "grad_norm": 0.04875415563583374,
      "learning_rate": 3.641025641025641e-05,
      "loss": 0.0217,
      "step": 71
    },
    {
      "epoch": 0.1844380403458213,
      "grad_norm": 0.053107842803001404,
      "learning_rate": 3.692307692307693e-05,
      "loss": 0.0184,
      "step": 72
    },
    {
      "epoch": 0.18699967979506885,
      "grad_norm": 0.04690933972597122,
      "learning_rate": 3.7435897435897436e-05,
      "loss": 0.0162,
      "step": 73
    },
    {
      "epoch": 0.18956131924431635,
      "grad_norm": 0.04177139699459076,
      "learning_rate": 3.794871794871795e-05,
      "loss": 0.0201,
      "step": 74
    },
    {
      "epoch": 0.19212295869356388,
      "grad_norm": 0.07623627781867981,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0301,
      "step": 75
    },
    {
      "epoch": 0.19212295869356388,
      "eval_loss": 0.01890488900244236,
      "eval_runtime": 15.7788,
      "eval_samples_per_second": 6.338,
      "eval_steps_per_second": 1.584,
      "step": 75
    },
    {
      "epoch": 0.1946845981428114,
      "grad_norm": 0.05075330659747124,
      "learning_rate": 3.8974358974358976e-05,
      "loss": 0.0267,
      "step": 76
    },
    {
      "epoch": 0.19724623759205892,
      "grad_norm": 0.06402429938316345,
      "learning_rate": 3.948717948717949e-05,
      "loss": 0.0324,
      "step": 77
    },
    {
      "epoch": 0.19980787704130643,
      "grad_norm": 0.041263386607170105,
      "learning_rate": 4e-05,
      "loss": 0.0187,
      "step": 78
    },
    {
      "epoch": 0.20236951649055396,
      "grad_norm": 0.051044903695583344,
      "learning_rate": 4.051282051282052e-05,
      "loss": 0.0289,
      "step": 79
    },
    {
      "epoch": 0.20493115593980146,
      "grad_norm": 0.06309404224157333,
      "learning_rate": 4.1025641025641023e-05,
      "loss": 0.0323,
      "step": 80
    },
    {
      "epoch": 0.207492795389049,
      "grad_norm": 0.04254679009318352,
      "learning_rate": 4.1538461538461544e-05,
      "loss": 0.0212,
      "step": 81
    },
    {
      "epoch": 0.2100544348382965,
      "grad_norm": 0.03591303154826164,
      "learning_rate": 4.205128205128206e-05,
      "loss": 0.0204,
      "step": 82
    },
    {
      "epoch": 0.21261607428754403,
      "grad_norm": 0.047834377735853195,
      "learning_rate": 4.2564102564102564e-05,
      "loss": 0.0201,
      "step": 83
    },
    {
      "epoch": 0.21517771373679154,
      "grad_norm": 0.04303661361336708,
      "learning_rate": 4.3076923076923084e-05,
      "loss": 0.0207,
      "step": 84
    },
    {
      "epoch": 0.21773935318603907,
      "grad_norm": 0.03778654336929321,
      "learning_rate": 4.358974358974359e-05,
      "loss": 0.0138,
      "step": 85
    },
    {
      "epoch": 0.22030099263528657,
      "grad_norm": 0.059220101684331894,
      "learning_rate": 4.4102564102564104e-05,
      "loss": 0.0294,
      "step": 86
    },
    {
      "epoch": 0.2228626320845341,
      "grad_norm": 0.06273186206817627,
      "learning_rate": 4.461538461538462e-05,
      "loss": 0.0194,
      "step": 87
    },
    {
      "epoch": 0.2254242715337816,
      "grad_norm": 0.05138327553868294,
      "learning_rate": 4.512820512820513e-05,
      "loss": 0.0257,
      "step": 88
    },
    {
      "epoch": 0.22798591098302914,
      "grad_norm": 0.05410440266132355,
      "learning_rate": 4.5641025641025645e-05,
      "loss": 0.0203,
      "step": 89
    },
    {
      "epoch": 0.23054755043227665,
      "grad_norm": 0.04224589839577675,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0181,
      "step": 90
    },
    {
      "epoch": 0.23310918988152418,
      "grad_norm": 0.060652345418930054,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.0252,
      "step": 91
    },
    {
      "epoch": 0.2356708293307717,
      "grad_norm": 0.06052101030945778,
      "learning_rate": 4.717948717948718e-05,
      "loss": 0.0326,
      "step": 92
    },
    {
      "epoch": 0.23823246878001922,
      "grad_norm": 0.050801996141672134,
      "learning_rate": 4.76923076923077e-05,
      "loss": 0.0282,
      "step": 93
    },
    {
      "epoch": 0.24079410822926672,
      "grad_norm": 0.042453132569789886,
      "learning_rate": 4.8205128205128205e-05,
      "loss": 0.0166,
      "step": 94
    },
    {
      "epoch": 0.24335574767851426,
      "grad_norm": 0.037676140666007996,
      "learning_rate": 4.871794871794872e-05,
      "loss": 0.0188,
      "step": 95
    },
    {
      "epoch": 0.24591738712776176,
      "grad_norm": 0.037714943289756775,
      "learning_rate": 4.923076923076924e-05,
      "loss": 0.0141,
      "step": 96
    },
    {
      "epoch": 0.2484790265770093,
      "grad_norm": 0.04738244786858559,
      "learning_rate": 4.9743589743589746e-05,
      "loss": 0.0348,
      "step": 97
    },
    {
      "epoch": 0.2510406660262568,
      "grad_norm": 0.039117615669965744,
      "learning_rate": 5.025641025641026e-05,
      "loss": 0.0184,
      "step": 98
    },
    {
      "epoch": 0.25360230547550433,
      "grad_norm": 0.03788371384143829,
      "learning_rate": 5.0769230769230766e-05,
      "loss": 0.0192,
      "step": 99
    },
    {
      "epoch": 0.25616394492475186,
      "grad_norm": 0.07863015681505203,
      "learning_rate": 5.128205128205128e-05,
      "loss": 0.0217,
      "step": 100
    },
    {
      "epoch": 0.25616394492475186,
      "eval_loss": 0.017253482714295387,
      "eval_runtime": 15.7742,
      "eval_samples_per_second": 6.339,
      "eval_steps_per_second": 1.585,
      "step": 100
    },
    {
      "epoch": 0.25872558437399934,
      "grad_norm": 0.04783935844898224,
      "learning_rate": 5.17948717948718e-05,
      "loss": 0.0193,
      "step": 101
    },
    {
      "epoch": 0.2612872238232469,
      "grad_norm": 0.04175376892089844,
      "learning_rate": 5.230769230769231e-05,
      "loss": 0.0155,
      "step": 102
    },
    {
      "epoch": 0.2638488632724944,
      "grad_norm": 0.05416353419423103,
      "learning_rate": 5.2820512820512826e-05,
      "loss": 0.0317,
      "step": 103
    },
    {
      "epoch": 0.26641050272174194,
      "grad_norm": 0.028790106996893883,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.0131,
      "step": 104
    },
    {
      "epoch": 0.2689721421709894,
      "grad_norm": 0.057330165058374405,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0176,
      "step": 105
    },
    {
      "epoch": 0.27153378162023695,
      "grad_norm": 0.07159876078367233,
      "learning_rate": 5.435897435897436e-05,
      "loss": 0.0228,
      "step": 106
    },
    {
      "epoch": 0.2740954210694845,
      "grad_norm": 0.04449112340807915,
      "learning_rate": 5.487179487179488e-05,
      "loss": 0.0202,
      "step": 107
    },
    {
      "epoch": 0.276657060518732,
      "grad_norm": 0.06222032755613327,
      "learning_rate": 5.538461538461539e-05,
      "loss": 0.0298,
      "step": 108
    },
    {
      "epoch": 0.2792186999679795,
      "grad_norm": 0.04552404209971428,
      "learning_rate": 5.58974358974359e-05,
      "loss": 0.0149,
      "step": 109
    },
    {
      "epoch": 0.281780339417227,
      "grad_norm": 0.03565036877989769,
      "learning_rate": 5.6410256410256414e-05,
      "loss": 0.0162,
      "step": 110
    },
    {
      "epoch": 0.28434197886647455,
      "grad_norm": 0.04282074794173241,
      "learning_rate": 5.692307692307692e-05,
      "loss": 0.0191,
      "step": 111
    },
    {
      "epoch": 0.2869036183157221,
      "grad_norm": 0.0391264371573925,
      "learning_rate": 5.7435897435897434e-05,
      "loss": 0.0144,
      "step": 112
    },
    {
      "epoch": 0.28946525776496956,
      "grad_norm": 0.048470303416252136,
      "learning_rate": 5.7948717948717954e-05,
      "loss": 0.0305,
      "step": 113
    },
    {
      "epoch": 0.2920268972142171,
      "grad_norm": 0.04939977452158928,
      "learning_rate": 5.846153846153847e-05,
      "loss": 0.0239,
      "step": 114
    },
    {
      "epoch": 0.29458853666346463,
      "grad_norm": 0.0445936843752861,
      "learning_rate": 5.897435897435898e-05,
      "loss": 0.0155,
      "step": 115
    },
    {
      "epoch": 0.29715017611271216,
      "grad_norm": 0.05109110474586487,
      "learning_rate": 5.948717948717949e-05,
      "loss": 0.0251,
      "step": 116
    },
    {
      "epoch": 0.29971181556195964,
      "grad_norm": 0.044525668025016785,
      "learning_rate": 6e-05,
      "loss": 0.0274,
      "step": 117
    },
    {
      "epoch": 0.30227345501120717,
      "grad_norm": 0.051556315273046494,
      "learning_rate": 6.0512820512820515e-05,
      "loss": 0.0171,
      "step": 118
    },
    {
      "epoch": 0.3048350944604547,
      "grad_norm": 0.06288602948188782,
      "learning_rate": 6.1025641025641035e-05,
      "loss": 0.0277,
      "step": 119
    },
    {
      "epoch": 0.30739673390970224,
      "grad_norm": 0.03961167111992836,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0166,
      "step": 120
    },
    {
      "epoch": 0.3099583733589497,
      "grad_norm": 0.05251983925700188,
      "learning_rate": 6.205128205128206e-05,
      "loss": 0.0294,
      "step": 121
    },
    {
      "epoch": 0.31252001280819725,
      "grad_norm": 0.03636966273188591,
      "learning_rate": 6.256410256410256e-05,
      "loss": 0.0126,
      "step": 122
    },
    {
      "epoch": 0.3150816522574448,
      "grad_norm": 0.047448430210351944,
      "learning_rate": 6.307692307692308e-05,
      "loss": 0.0201,
      "step": 123
    },
    {
      "epoch": 0.3176432917066923,
      "grad_norm": 0.05578154698014259,
      "learning_rate": 6.358974358974359e-05,
      "loss": 0.0227,
      "step": 124
    },
    {
      "epoch": 0.3202049311559398,
      "grad_norm": 0.08173694461584091,
      "learning_rate": 6.410256410256412e-05,
      "loss": 0.0186,
      "step": 125
    },
    {
      "epoch": 0.3202049311559398,
      "eval_loss": 0.016197798773646355,
      "eval_runtime": 15.7682,
      "eval_samples_per_second": 6.342,
      "eval_steps_per_second": 1.585,
      "step": 125
    },
    {
      "epoch": 0.3227665706051873,
      "grad_norm": 0.048432037234306335,
      "learning_rate": 6.461538461538462e-05,
      "loss": 0.0143,
      "step": 126
    },
    {
      "epoch": 0.32532821005443485,
      "grad_norm": 0.03601989895105362,
      "learning_rate": 6.512820512820513e-05,
      "loss": 0.0183,
      "step": 127
    },
    {
      "epoch": 0.32788984950368233,
      "grad_norm": 0.045704398304224014,
      "learning_rate": 6.564102564102564e-05,
      "loss": 0.0204,
      "step": 128
    },
    {
      "epoch": 0.33045148895292986,
      "grad_norm": 0.04779214784502983,
      "learning_rate": 6.615384615384616e-05,
      "loss": 0.0157,
      "step": 129
    },
    {
      "epoch": 0.3330131284021774,
      "grad_norm": 0.03140333667397499,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0149,
      "step": 130
    },
    {
      "epoch": 0.3355747678514249,
      "grad_norm": 0.03896024823188782,
      "learning_rate": 6.717948717948718e-05,
      "loss": 0.0251,
      "step": 131
    },
    {
      "epoch": 0.3381364073006724,
      "grad_norm": 0.03296570107340813,
      "learning_rate": 6.76923076923077e-05,
      "loss": 0.0193,
      "step": 132
    },
    {
      "epoch": 0.34069804674991994,
      "grad_norm": 0.04064328223466873,
      "learning_rate": 6.820512820512821e-05,
      "loss": 0.0269,
      "step": 133
    },
    {
      "epoch": 0.34325968619916747,
      "grad_norm": 0.04517941549420357,
      "learning_rate": 6.871794871794872e-05,
      "loss": 0.0152,
      "step": 134
    },
    {
      "epoch": 0.345821325648415,
      "grad_norm": 0.037514880299568176,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.029,
      "step": 135
    },
    {
      "epoch": 0.3483829650976625,
      "grad_norm": 0.04924914240837097,
      "learning_rate": 6.974358974358974e-05,
      "loss": 0.0156,
      "step": 136
    },
    {
      "epoch": 0.35094460454691,
      "grad_norm": 0.0434134341776371,
      "learning_rate": 7.025641025641025e-05,
      "loss": 0.0118,
      "step": 137
    },
    {
      "epoch": 0.35350624399615754,
      "grad_norm": 0.046721406280994415,
      "learning_rate": 7.076923076923078e-05,
      "loss": 0.0238,
      "step": 138
    },
    {
      "epoch": 0.3560678834454051,
      "grad_norm": 0.04098832234740257,
      "learning_rate": 7.128205128205129e-05,
      "loss": 0.0188,
      "step": 139
    },
    {
      "epoch": 0.35862952289465255,
      "grad_norm": 0.03906092047691345,
      "learning_rate": 7.17948717948718e-05,
      "loss": 0.016,
      "step": 140
    },
    {
      "epoch": 0.3611911623439001,
      "grad_norm": 0.046422287821769714,
      "learning_rate": 7.23076923076923e-05,
      "loss": 0.0296,
      "step": 141
    },
    {
      "epoch": 0.3637528017931476,
      "grad_norm": 0.05698518827557564,
      "learning_rate": 7.282051282051282e-05,
      "loss": 0.0191,
      "step": 142
    },
    {
      "epoch": 0.36631444124239515,
      "grad_norm": 0.04666212946176529,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.0234,
      "step": 143
    },
    {
      "epoch": 0.3688760806916426,
      "grad_norm": 0.03416457027196884,
      "learning_rate": 7.384615384615386e-05,
      "loss": 0.0197,
      "step": 144
    },
    {
      "epoch": 0.37143772014089016,
      "grad_norm": 0.04253166541457176,
      "learning_rate": 7.435897435897436e-05,
      "loss": 0.0189,
      "step": 145
    },
    {
      "epoch": 0.3739993595901377,
      "grad_norm": 0.03973923251032829,
      "learning_rate": 7.487179487179487e-05,
      "loss": 0.0182,
      "step": 146
    },
    {
      "epoch": 0.3765609990393852,
      "grad_norm": 0.03506443649530411,
      "learning_rate": 7.538461538461539e-05,
      "loss": 0.0138,
      "step": 147
    },
    {
      "epoch": 0.3791226384886327,
      "grad_norm": 0.054082706570625305,
      "learning_rate": 7.58974358974359e-05,
      "loss": 0.0284,
      "step": 148
    },
    {
      "epoch": 0.38168427793788023,
      "grad_norm": 0.057566624134778976,
      "learning_rate": 7.641025641025641e-05,
      "loss": 0.0162,
      "step": 149
    },
    {
      "epoch": 0.38424591738712777,
      "grad_norm": 0.04910784214735031,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0216,
      "step": 150
    },
    {
      "epoch": 0.38424591738712777,
      "eval_loss": 0.015280881896615028,
      "eval_runtime": 15.7668,
      "eval_samples_per_second": 6.342,
      "eval_steps_per_second": 1.586,
      "step": 150
    },
    {
      "epoch": 0.3868075568363753,
      "grad_norm": 0.034558191895484924,
      "learning_rate": 7.743589743589744e-05,
      "loss": 0.0145,
      "step": 151
    },
    {
      "epoch": 0.3893691962856228,
      "grad_norm": 0.03240443766117096,
      "learning_rate": 7.794871794871795e-05,
      "loss": 0.0167,
      "step": 152
    },
    {
      "epoch": 0.3919308357348703,
      "grad_norm": 0.03908954933285713,
      "learning_rate": 7.846153846153847e-05,
      "loss": 0.0254,
      "step": 153
    },
    {
      "epoch": 0.39449247518411784,
      "grad_norm": 0.04887024685740471,
      "learning_rate": 7.897435897435898e-05,
      "loss": 0.0174,
      "step": 154
    },
    {
      "epoch": 0.3970541146333654,
      "grad_norm": 0.035764534026384354,
      "learning_rate": 7.948717948717948e-05,
      "loss": 0.0193,
      "step": 155
    },
    {
      "epoch": 0.39961575408261285,
      "grad_norm": 0.02639930136501789,
      "learning_rate": 8e-05,
      "loss": 0.0122,
      "step": 156
    },
    {
      "epoch": 0.4021773935318604,
      "grad_norm": 0.029830757528543472,
      "learning_rate": 8.051282051282052e-05,
      "loss": 0.0121,
      "step": 157
    },
    {
      "epoch": 0.4047390329811079,
      "grad_norm": 0.054097048938274384,
      "learning_rate": 8.102564102564103e-05,
      "loss": 0.0357,
      "step": 158
    },
    {
      "epoch": 0.40730067243035545,
      "grad_norm": 0.03186127543449402,
      "learning_rate": 8.153846153846155e-05,
      "loss": 0.0133,
      "step": 159
    },
    {
      "epoch": 0.4098623118796029,
      "grad_norm": 0.03369072452187538,
      "learning_rate": 8.205128205128205e-05,
      "loss": 0.0125,
      "step": 160
    },
    {
      "epoch": 0.41242395132885046,
      "grad_norm": 0.03541966527700424,
      "learning_rate": 8.256410256410256e-05,
      "loss": 0.0138,
      "step": 161
    },
    {
      "epoch": 0.414985590778098,
      "grad_norm": 0.02782193198800087,
      "learning_rate": 8.307692307692309e-05,
      "loss": 0.0118,
      "step": 162
    },
    {
      "epoch": 0.4175472302273455,
      "grad_norm": 0.06363299489021301,
      "learning_rate": 8.35897435897436e-05,
      "loss": 0.0339,
      "step": 163
    },
    {
      "epoch": 0.420108869676593,
      "grad_norm": 0.03677621856331825,
      "learning_rate": 8.410256410256411e-05,
      "loss": 0.0148,
      "step": 164
    },
    {
      "epoch": 0.42267050912584053,
      "grad_norm": 0.039866507053375244,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0122,
      "step": 165
    },
    {
      "epoch": 0.42523214857508806,
      "grad_norm": 0.04610941559076309,
      "learning_rate": 8.512820512820513e-05,
      "loss": 0.0307,
      "step": 166
    },
    {
      "epoch": 0.4277937880243356,
      "grad_norm": 0.04283754900097847,
      "learning_rate": 8.564102564102564e-05,
      "loss": 0.0176,
      "step": 167
    },
    {
      "epoch": 0.4303554274735831,
      "grad_norm": 0.040971748530864716,
      "learning_rate": 8.615384615384617e-05,
      "loss": 0.0164,
      "step": 168
    },
    {
      "epoch": 0.4329170669228306,
      "grad_norm": 0.03258652612566948,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.0152,
      "step": 169
    },
    {
      "epoch": 0.43547870637207814,
      "grad_norm": 0.03341250121593475,
      "learning_rate": 8.717948717948718e-05,
      "loss": 0.0128,
      "step": 170
    },
    {
      "epoch": 0.43804034582132567,
      "grad_norm": 0.030181603506207466,
      "learning_rate": 8.76923076923077e-05,
      "loss": 0.0138,
      "step": 171
    },
    {
      "epoch": 0.44060198527057315,
      "grad_norm": 0.0757037103176117,
      "learning_rate": 8.820512820512821e-05,
      "loss": 0.018,
      "step": 172
    },
    {
      "epoch": 0.4431636247198207,
      "grad_norm": 0.035500697791576385,
      "learning_rate": 8.871794871794872e-05,
      "loss": 0.0206,
      "step": 173
    },
    {
      "epoch": 0.4457252641690682,
      "grad_norm": 0.02978915348649025,
      "learning_rate": 8.923076923076924e-05,
      "loss": 0.0141,
      "step": 174
    },
    {
      "epoch": 0.44828690361831575,
      "grad_norm": 0.04094715043902397,
      "learning_rate": 8.974358974358975e-05,
      "loss": 0.0138,
      "step": 175
    },
    {
      "epoch": 0.44828690361831575,
      "eval_loss": 0.015311915427446365,
      "eval_runtime": 15.7999,
      "eval_samples_per_second": 6.329,
      "eval_steps_per_second": 1.582,
      "step": 175
    },
    {
      "epoch": 0.4508485430675632,
      "grad_norm": 0.03736531361937523,
      "learning_rate": 9.025641025641026e-05,
      "loss": 0.0133,
      "step": 176
    },
    {
      "epoch": 0.45341018251681076,
      "grad_norm": 0.026462465524673462,
      "learning_rate": 9.076923076923078e-05,
      "loss": 0.0087,
      "step": 177
    },
    {
      "epoch": 0.4559718219660583,
      "grad_norm": 0.044491320848464966,
      "learning_rate": 9.128205128205129e-05,
      "loss": 0.0168,
      "step": 178
    },
    {
      "epoch": 0.4585334614153058,
      "grad_norm": 0.040210917592048645,
      "learning_rate": 9.179487179487179e-05,
      "loss": 0.0217,
      "step": 179
    },
    {
      "epoch": 0.4610951008645533,
      "grad_norm": 0.067959725856781,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0192,
      "step": 180
    },
    {
      "epoch": 0.46365674031380083,
      "grad_norm": 0.03490135073661804,
      "learning_rate": 9.282051282051283e-05,
      "loss": 0.0118,
      "step": 181
    },
    {
      "epoch": 0.46621837976304836,
      "grad_norm": 0.04227762669324875,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.0146,
      "step": 182
    },
    {
      "epoch": 0.4687800192122959,
      "grad_norm": 0.07856088131666183,
      "learning_rate": 9.384615384615386e-05,
      "loss": 0.0187,
      "step": 183
    },
    {
      "epoch": 0.4713416586615434,
      "grad_norm": 0.039737801998853683,
      "learning_rate": 9.435897435897436e-05,
      "loss": 0.0187,
      "step": 184
    },
    {
      "epoch": 0.4739032981107909,
      "grad_norm": 0.04330054298043251,
      "learning_rate": 9.487179487179487e-05,
      "loss": 0.0188,
      "step": 185
    },
    {
      "epoch": 0.47646493756003844,
      "grad_norm": 0.045348942279815674,
      "learning_rate": 9.53846153846154e-05,
      "loss": 0.0216,
      "step": 186
    },
    {
      "epoch": 0.47902657700928597,
      "grad_norm": 0.03437650576233864,
      "learning_rate": 9.589743589743591e-05,
      "loss": 0.0184,
      "step": 187
    },
    {
      "epoch": 0.48158821645853345,
      "grad_norm": 0.03575362637639046,
      "learning_rate": 9.641025641025641e-05,
      "loss": 0.0223,
      "step": 188
    },
    {
      "epoch": 0.484149855907781,
      "grad_norm": 0.022593902423977852,
      "learning_rate": 9.692307692307692e-05,
      "loss": 0.0128,
      "step": 189
    },
    {
      "epoch": 0.4867114953570285,
      "grad_norm": 0.04331602156162262,
      "learning_rate": 9.743589743589744e-05,
      "loss": 0.0254,
      "step": 190
    },
    {
      "epoch": 0.48927313480627604,
      "grad_norm": 0.02803720161318779,
      "learning_rate": 9.794871794871795e-05,
      "loss": 0.0132,
      "step": 191
    },
    {
      "epoch": 0.4918347742555235,
      "grad_norm": 0.036241576075553894,
      "learning_rate": 9.846153846153848e-05,
      "loss": 0.012,
      "step": 192
    },
    {
      "epoch": 0.49439641370477105,
      "grad_norm": 0.03179619088768959,
      "learning_rate": 9.897435897435898e-05,
      "loss": 0.0126,
      "step": 193
    },
    {
      "epoch": 0.4969580531540186,
      "grad_norm": 0.03643405809998512,
      "learning_rate": 9.948717948717949e-05,
      "loss": 0.0184,
      "step": 194
    },
    {
      "epoch": 0.49951969260326606,
      "grad_norm": 0.03236660733819008,
      "learning_rate": 0.0001,
      "loss": 0.0174,
      "step": 195
    },
    {
      "epoch": 0.5020813320525136,
      "grad_norm": 0.025117913261055946,
      "learning_rate": 9.999991989024631e-05,
      "loss": 0.0125,
      "step": 196
    },
    {
      "epoch": 0.5046429715017611,
      "grad_norm": 0.026827501133084297,
      "learning_rate": 9.999967956124192e-05,
      "loss": 0.0125,
      "step": 197
    },
    {
      "epoch": 0.5072046109510087,
      "grad_norm": 0.02300351858139038,
      "learning_rate": 9.999927901375693e-05,
      "loss": 0.0098,
      "step": 198
    },
    {
      "epoch": 0.5097662504002561,
      "grad_norm": 0.03161875531077385,
      "learning_rate": 9.999871824907485e-05,
      "loss": 0.02,
      "step": 199
    },
    {
      "epoch": 0.5123278898495037,
      "grad_norm": 0.040188804268836975,
      "learning_rate": 9.999799726899262e-05,
      "loss": 0.021,
      "step": 200
    },
    {
      "epoch": 0.5123278898495037,
      "eval_loss": 0.014618256129324436,
      "eval_runtime": 15.7792,
      "eval_samples_per_second": 6.337,
      "eval_steps_per_second": 1.584,
      "step": 200
    },
    {
      "epoch": 0.5148895292987512,
      "grad_norm": 0.027994215488433838,
      "learning_rate": 9.999711607582052e-05,
      "loss": 0.0157,
      "step": 201
    },
    {
      "epoch": 0.5174511687479987,
      "grad_norm": 0.03944910690188408,
      "learning_rate": 9.999607467238223e-05,
      "loss": 0.0199,
      "step": 202
    },
    {
      "epoch": 0.5200128081972463,
      "grad_norm": 0.03262855485081673,
      "learning_rate": 9.999487306201483e-05,
      "loss": 0.0162,
      "step": 203
    },
    {
      "epoch": 0.5225744476464937,
      "grad_norm": 0.020725559443235397,
      "learning_rate": 9.999351124856874e-05,
      "loss": 0.0089,
      "step": 204
    },
    {
      "epoch": 0.5251360870957412,
      "grad_norm": 0.03486771881580353,
      "learning_rate": 9.999198923640774e-05,
      "loss": 0.0133,
      "step": 205
    },
    {
      "epoch": 0.5276977265449888,
      "grad_norm": 0.03679514676332474,
      "learning_rate": 9.999030703040895e-05,
      "loss": 0.0231,
      "step": 206
    },
    {
      "epoch": 0.5302593659942363,
      "grad_norm": 0.029446182772517204,
      "learning_rate": 9.998846463596281e-05,
      "loss": 0.013,
      "step": 207
    },
    {
      "epoch": 0.5328210054434839,
      "grad_norm": 0.03434671834111214,
      "learning_rate": 9.998646205897309e-05,
      "loss": 0.0187,
      "step": 208
    },
    {
      "epoch": 0.5353826448927314,
      "grad_norm": 0.03190897777676582,
      "learning_rate": 9.998429930585682e-05,
      "loss": 0.0141,
      "step": 209
    },
    {
      "epoch": 0.5379442843419788,
      "grad_norm": 0.03730105608701706,
      "learning_rate": 9.998197638354428e-05,
      "loss": 0.0217,
      "step": 210
    },
    {
      "epoch": 0.5405059237912264,
      "grad_norm": 0.03427678719162941,
      "learning_rate": 9.997949329947904e-05,
      "loss": 0.0207,
      "step": 211
    },
    {
      "epoch": 0.5430675632404739,
      "grad_norm": 0.03182192146778107,
      "learning_rate": 9.997685006161788e-05,
      "loss": 0.0272,
      "step": 212
    },
    {
      "epoch": 0.5456292026897214,
      "grad_norm": 0.02717447653412819,
      "learning_rate": 9.997404667843075e-05,
      "loss": 0.0135,
      "step": 213
    },
    {
      "epoch": 0.548190842138969,
      "grad_norm": 0.04445464909076691,
      "learning_rate": 9.99710831589008e-05,
      "loss": 0.0265,
      "step": 214
    },
    {
      "epoch": 0.5507524815882164,
      "grad_norm": 0.03553137183189392,
      "learning_rate": 9.996795951252427e-05,
      "loss": 0.0174,
      "step": 215
    },
    {
      "epoch": 0.553314121037464,
      "grad_norm": 0.034598637372255325,
      "learning_rate": 9.996467574931057e-05,
      "loss": 0.0178,
      "step": 216
    },
    {
      "epoch": 0.5558757604867115,
      "grad_norm": 0.030017906799912453,
      "learning_rate": 9.996123187978215e-05,
      "loss": 0.0128,
      "step": 217
    },
    {
      "epoch": 0.558437399935959,
      "grad_norm": 0.033853303641080856,
      "learning_rate": 9.995762791497452e-05,
      "loss": 0.0173,
      "step": 218
    },
    {
      "epoch": 0.5609990393852066,
      "grad_norm": 0.030432872474193573,
      "learning_rate": 9.99538638664362e-05,
      "loss": 0.0138,
      "step": 219
    },
    {
      "epoch": 0.563560678834454,
      "grad_norm": 0.03020687773823738,
      "learning_rate": 9.994993974622862e-05,
      "loss": 0.0143,
      "step": 220
    },
    {
      "epoch": 0.5661223182837015,
      "grad_norm": 0.035555846989154816,
      "learning_rate": 9.994585556692624e-05,
      "loss": 0.0228,
      "step": 221
    },
    {
      "epoch": 0.5686839577329491,
      "grad_norm": 0.036969736218452454,
      "learning_rate": 9.994161134161634e-05,
      "loss": 0.0241,
      "step": 222
    },
    {
      "epoch": 0.5712455971821966,
      "grad_norm": 0.0440659373998642,
      "learning_rate": 9.993720708389909e-05,
      "loss": 0.0241,
      "step": 223
    },
    {
      "epoch": 0.5738072366314442,
      "grad_norm": 0.03319979086518288,
      "learning_rate": 9.993264280788744e-05,
      "loss": 0.0253,
      "step": 224
    },
    {
      "epoch": 0.5763688760806917,
      "grad_norm": 0.026040690019726753,
      "learning_rate": 9.992791852820709e-05,
      "loss": 0.0166,
      "step": 225
    },
    {
      "epoch": 0.5763688760806917,
      "eval_loss": 0.013338856399059296,
      "eval_runtime": 15.7439,
      "eval_samples_per_second": 6.352,
      "eval_steps_per_second": 1.588,
      "step": 225
    },
    {
      "epoch": 0.5789305155299391,
      "grad_norm": 0.02438931353390217,
      "learning_rate": 9.992303425999652e-05,
      "loss": 0.0108,
      "step": 226
    },
    {
      "epoch": 0.5814921549791867,
      "grad_norm": 0.023932714015245438,
      "learning_rate": 9.99179900189068e-05,
      "loss": 0.011,
      "step": 227
    },
    {
      "epoch": 0.5840537944284342,
      "grad_norm": 0.0349879153072834,
      "learning_rate": 9.991278582110167e-05,
      "loss": 0.0279,
      "step": 228
    },
    {
      "epoch": 0.5866154338776817,
      "grad_norm": 0.037302933633327484,
      "learning_rate": 9.99074216832574e-05,
      "loss": 0.0177,
      "step": 229
    },
    {
      "epoch": 0.5891770733269293,
      "grad_norm": 0.033939432352781296,
      "learning_rate": 9.990189762256276e-05,
      "loss": 0.018,
      "step": 230
    },
    {
      "epoch": 0.5917387127761767,
      "grad_norm": 0.025025606155395508,
      "learning_rate": 9.989621365671902e-05,
      "loss": 0.0151,
      "step": 231
    },
    {
      "epoch": 0.5943003522254243,
      "grad_norm": 0.031279440969228745,
      "learning_rate": 9.98903698039398e-05,
      "loss": 0.0119,
      "step": 232
    },
    {
      "epoch": 0.5968619916746718,
      "grad_norm": 0.03417769819498062,
      "learning_rate": 9.988436608295112e-05,
      "loss": 0.0202,
      "step": 233
    },
    {
      "epoch": 0.5994236311239193,
      "grad_norm": 0.048715490847826004,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0227,
      "step": 234
    },
    {
      "epoch": 0.6019852705731669,
      "grad_norm": 0.03958699479699135,
      "learning_rate": 9.987187911381059e-05,
      "loss": 0.0211,
      "step": 235
    },
    {
      "epoch": 0.6045469100224143,
      "grad_norm": 0.034175582230091095,
      "learning_rate": 9.986539590567186e-05,
      "loss": 0.0116,
      "step": 236
    },
    {
      "epoch": 0.6071085494716618,
      "grad_norm": 0.035210780799388885,
      "learning_rate": 9.985875290934977e-05,
      "loss": 0.0225,
      "step": 237
    },
    {
      "epoch": 0.6096701889209094,
      "grad_norm": 0.033485546708106995,
      "learning_rate": 9.985195014613105e-05,
      "loss": 0.0167,
      "step": 238
    },
    {
      "epoch": 0.6122318283701569,
      "grad_norm": 0.03267650306224823,
      "learning_rate": 9.984498763781444e-05,
      "loss": 0.0135,
      "step": 239
    },
    {
      "epoch": 0.6147934678194045,
      "grad_norm": 0.028668779879808426,
      "learning_rate": 9.983786540671051e-05,
      "loss": 0.0119,
      "step": 240
    },
    {
      "epoch": 0.617355107268652,
      "grad_norm": 0.028682347387075424,
      "learning_rate": 9.983058347564167e-05,
      "loss": 0.0104,
      "step": 241
    },
    {
      "epoch": 0.6199167467178994,
      "grad_norm": 0.02997414395213127,
      "learning_rate": 9.982314186794207e-05,
      "loss": 0.0143,
      "step": 242
    },
    {
      "epoch": 0.622478386167147,
      "grad_norm": 0.028074778616428375,
      "learning_rate": 9.981554060745754e-05,
      "loss": 0.0103,
      "step": 243
    },
    {
      "epoch": 0.6250400256163945,
      "grad_norm": 0.035082463175058365,
      "learning_rate": 9.980777971854545e-05,
      "loss": 0.0208,
      "step": 244
    },
    {
      "epoch": 0.627601665065642,
      "grad_norm": 0.03993948549032211,
      "learning_rate": 9.979985922607475e-05,
      "loss": 0.0201,
      "step": 245
    },
    {
      "epoch": 0.6301633045148896,
      "grad_norm": 0.027228379622101784,
      "learning_rate": 9.979177915542577e-05,
      "loss": 0.0145,
      "step": 246
    },
    {
      "epoch": 0.632724943964137,
      "grad_norm": 0.02641998790204525,
      "learning_rate": 9.978353953249022e-05,
      "loss": 0.0116,
      "step": 247
    },
    {
      "epoch": 0.6352865834133846,
      "grad_norm": 0.04445129632949829,
      "learning_rate": 9.977514038367106e-05,
      "loss": 0.0161,
      "step": 248
    },
    {
      "epoch": 0.6378482228626321,
      "grad_norm": 0.041566576808691025,
      "learning_rate": 9.976658173588244e-05,
      "loss": 0.0344,
      "step": 249
    },
    {
      "epoch": 0.6404098623118796,
      "grad_norm": 0.031222566962242126,
      "learning_rate": 9.97578636165496e-05,
      "loss": 0.0109,
      "step": 250
    },
    {
      "epoch": 0.6404098623118796,
      "eval_loss": 0.011403795331716537,
      "eval_runtime": 15.8176,
      "eval_samples_per_second": 6.322,
      "eval_steps_per_second": 1.581,
      "step": 250
    },
    {
      "epoch": 0.6429715017611272,
      "grad_norm": 0.03305068984627724,
      "learning_rate": 9.974898605360881e-05,
      "loss": 0.0161,
      "step": 251
    },
    {
      "epoch": 0.6455331412103746,
      "grad_norm": 0.032358262687921524,
      "learning_rate": 9.973994907550722e-05,
      "loss": 0.0151,
      "step": 252
    },
    {
      "epoch": 0.6480947806596221,
      "grad_norm": 0.022366944700479507,
      "learning_rate": 9.973075271120287e-05,
      "loss": 0.0133,
      "step": 253
    },
    {
      "epoch": 0.6506564201088697,
      "grad_norm": 0.034839093685150146,
      "learning_rate": 9.972139699016446e-05,
      "loss": 0.0114,
      "step": 254
    },
    {
      "epoch": 0.6532180595581172,
      "grad_norm": 0.03348885849118233,
      "learning_rate": 9.97118819423714e-05,
      "loss": 0.02,
      "step": 255
    },
    {
      "epoch": 0.6557796990073647,
      "grad_norm": 0.024363042786717415,
      "learning_rate": 9.970220759831361e-05,
      "loss": 0.0108,
      "step": 256
    },
    {
      "epoch": 0.6583413384566122,
      "grad_norm": 0.027448901906609535,
      "learning_rate": 9.969237398899145e-05,
      "loss": 0.0122,
      "step": 257
    },
    {
      "epoch": 0.6609029779058597,
      "grad_norm": 0.04620316997170448,
      "learning_rate": 9.968238114591566e-05,
      "loss": 0.0232,
      "step": 258
    },
    {
      "epoch": 0.6634646173551073,
      "grad_norm": 0.033076781779527664,
      "learning_rate": 9.967222910110719e-05,
      "loss": 0.0196,
      "step": 259
    },
    {
      "epoch": 0.6660262568043548,
      "grad_norm": 0.021274225786328316,
      "learning_rate": 9.966191788709716e-05,
      "loss": 0.0097,
      "step": 260
    },
    {
      "epoch": 0.6685878962536023,
      "grad_norm": 0.046971239149570465,
      "learning_rate": 9.965144753692672e-05,
      "loss": 0.0232,
      "step": 261
    },
    {
      "epoch": 0.6711495357028499,
      "grad_norm": 0.029293019324541092,
      "learning_rate": 9.964081808414696e-05,
      "loss": 0.0194,
      "step": 262
    },
    {
      "epoch": 0.6737111751520973,
      "grad_norm": 0.027929246425628662,
      "learning_rate": 9.963002956281879e-05,
      "loss": 0.01,
      "step": 263
    },
    {
      "epoch": 0.6762728146013448,
      "grad_norm": 0.0408920980989933,
      "learning_rate": 9.961908200751284e-05,
      "loss": 0.0207,
      "step": 264
    },
    {
      "epoch": 0.6788344540505924,
      "grad_norm": 0.02565447986125946,
      "learning_rate": 9.960797545330936e-05,
      "loss": 0.0189,
      "step": 265
    },
    {
      "epoch": 0.6813960934998399,
      "grad_norm": 0.037796501070261,
      "learning_rate": 9.959670993579808e-05,
      "loss": 0.0164,
      "step": 266
    },
    {
      "epoch": 0.6839577329490875,
      "grad_norm": 0.025817422196269035,
      "learning_rate": 9.95852854910781e-05,
      "loss": 0.0095,
      "step": 267
    },
    {
      "epoch": 0.6865193723983349,
      "grad_norm": 0.027300599962472916,
      "learning_rate": 9.95737021557578e-05,
      "loss": 0.0124,
      "step": 268
    },
    {
      "epoch": 0.6890810118475824,
      "grad_norm": 0.03461704030632973,
      "learning_rate": 9.956195996695474e-05,
      "loss": 0.0263,
      "step": 269
    },
    {
      "epoch": 0.69164265129683,
      "grad_norm": 0.03362032026052475,
      "learning_rate": 9.955005896229543e-05,
      "loss": 0.0176,
      "step": 270
    },
    {
      "epoch": 0.6942042907460775,
      "grad_norm": 0.027980942279100418,
      "learning_rate": 9.953799917991535e-05,
      "loss": 0.0148,
      "step": 271
    },
    {
      "epoch": 0.696765930195325,
      "grad_norm": 0.030006052926182747,
      "learning_rate": 9.952578065845874e-05,
      "loss": 0.0158,
      "step": 272
    },
    {
      "epoch": 0.6993275696445725,
      "grad_norm": 0.03503892198204994,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0247,
      "step": 273
    },
    {
      "epoch": 0.70188920909382,
      "grad_norm": 0.025154704228043556,
      "learning_rate": 9.950086755543613e-05,
      "loss": 0.0125,
      "step": 274
    },
    {
      "epoch": 0.7044508485430676,
      "grad_norm": 0.024434421211481094,
      "learning_rate": 9.948817305370143e-05,
      "loss": 0.0127,
      "step": 275
    },
    {
      "epoch": 0.7044508485430676,
      "eval_loss": 0.011695047840476036,
      "eval_runtime": 15.7735,
      "eval_samples_per_second": 6.34,
      "eval_steps_per_second": 1.585,
      "step": 275
    },
    {
      "epoch": 0.7070124879923151,
      "grad_norm": 0.02198687754571438,
      "learning_rate": 9.947531997255256e-05,
      "loss": 0.0111,
      "step": 276
    },
    {
      "epoch": 0.7095741274415626,
      "grad_norm": 0.0338519886136055,
      "learning_rate": 9.94623083531758e-05,
      "loss": 0.0289,
      "step": 277
    },
    {
      "epoch": 0.7121357668908102,
      "grad_norm": 0.02596919983625412,
      "learning_rate": 9.944913823726546e-05,
      "loss": 0.0113,
      "step": 278
    },
    {
      "epoch": 0.7146974063400576,
      "grad_norm": 0.03738397732377052,
      "learning_rate": 9.94358096670237e-05,
      "loss": 0.0193,
      "step": 279
    },
    {
      "epoch": 0.7172590457893051,
      "grad_norm": 0.020664948970079422,
      "learning_rate": 9.94223226851605e-05,
      "loss": 0.0136,
      "step": 280
    },
    {
      "epoch": 0.7198206852385527,
      "grad_norm": 0.021599043160676956,
      "learning_rate": 9.940867733489341e-05,
      "loss": 0.0107,
      "step": 281
    },
    {
      "epoch": 0.7223823246878002,
      "grad_norm": 0.024695029482245445,
      "learning_rate": 9.939487365994742e-05,
      "loss": 0.0154,
      "step": 282
    },
    {
      "epoch": 0.7249439641370478,
      "grad_norm": 0.028182033449411392,
      "learning_rate": 9.938091170455494e-05,
      "loss": 0.0141,
      "step": 283
    },
    {
      "epoch": 0.7275056035862952,
      "grad_norm": 0.02947639487683773,
      "learning_rate": 9.936679151345547e-05,
      "loss": 0.021,
      "step": 284
    },
    {
      "epoch": 0.7300672430355427,
      "grad_norm": 0.025371797382831573,
      "learning_rate": 9.935251313189564e-05,
      "loss": 0.0152,
      "step": 285
    },
    {
      "epoch": 0.7326288824847903,
      "grad_norm": 0.024596597999334335,
      "learning_rate": 9.933807660562898e-05,
      "loss": 0.0145,
      "step": 286
    },
    {
      "epoch": 0.7351905219340378,
      "grad_norm": 0.026564741507172585,
      "learning_rate": 9.932348198091568e-05,
      "loss": 0.0174,
      "step": 287
    },
    {
      "epoch": 0.7377521613832853,
      "grad_norm": 0.021402254700660706,
      "learning_rate": 9.930872930452269e-05,
      "loss": 0.0119,
      "step": 288
    },
    {
      "epoch": 0.7403138008325328,
      "grad_norm": 0.0332682728767395,
      "learning_rate": 9.929381862372329e-05,
      "loss": 0.0174,
      "step": 289
    },
    {
      "epoch": 0.7428754402817803,
      "grad_norm": 0.027293076738715172,
      "learning_rate": 9.927874998629714e-05,
      "loss": 0.017,
      "step": 290
    },
    {
      "epoch": 0.7454370797310279,
      "grad_norm": 0.023125778883695602,
      "learning_rate": 9.926352344053002e-05,
      "loss": 0.014,
      "step": 291
    },
    {
      "epoch": 0.7479987191802754,
      "grad_norm": 0.028066707774996758,
      "learning_rate": 9.924813903521373e-05,
      "loss": 0.0199,
      "step": 292
    },
    {
      "epoch": 0.7505603586295229,
      "grad_norm": 0.025812916457653046,
      "learning_rate": 9.923259681964592e-05,
      "loss": 0.0143,
      "step": 293
    },
    {
      "epoch": 0.7531219980787704,
      "grad_norm": 0.020010055974125862,
      "learning_rate": 9.921689684362989e-05,
      "loss": 0.0108,
      "step": 294
    },
    {
      "epoch": 0.7556836375280179,
      "grad_norm": 0.027351340278983116,
      "learning_rate": 9.92010391574745e-05,
      "loss": 0.0142,
      "step": 295
    },
    {
      "epoch": 0.7582452769772654,
      "grad_norm": 0.02779037319123745,
      "learning_rate": 9.918502381199397e-05,
      "loss": 0.0126,
      "step": 296
    },
    {
      "epoch": 0.760806916426513,
      "grad_norm": 0.019299093633890152,
      "learning_rate": 9.916885085850771e-05,
      "loss": 0.0095,
      "step": 297
    },
    {
      "epoch": 0.7633685558757605,
      "grad_norm": 0.02957143820822239,
      "learning_rate": 9.915252034884018e-05,
      "loss": 0.0244,
      "step": 298
    },
    {
      "epoch": 0.7659301953250081,
      "grad_norm": 0.02845151349902153,
      "learning_rate": 9.913603233532067e-05,
      "loss": 0.0134,
      "step": 299
    },
    {
      "epoch": 0.7684918347742555,
      "grad_norm": 0.019368290901184082,
      "learning_rate": 9.911938687078324e-05,
      "loss": 0.0095,
      "step": 300
    },
    {
      "epoch": 0.7684918347742555,
      "eval_loss": 0.011247427202761173,
      "eval_runtime": 15.7866,
      "eval_samples_per_second": 6.334,
      "eval_steps_per_second": 1.584,
      "step": 300
    },
    {
      "epoch": 0.771053474223503,
      "grad_norm": 0.027626069262623787,
      "learning_rate": 9.910258400856646e-05,
      "loss": 0.0131,
      "step": 301
    },
    {
      "epoch": 0.7736151136727506,
      "grad_norm": 0.018759949132800102,
      "learning_rate": 9.908562380251323e-05,
      "loss": 0.01,
      "step": 302
    },
    {
      "epoch": 0.7761767531219981,
      "grad_norm": 0.0227984506636858,
      "learning_rate": 9.906850630697068e-05,
      "loss": 0.0103,
      "step": 303
    },
    {
      "epoch": 0.7787383925712456,
      "grad_norm": 0.022225648164749146,
      "learning_rate": 9.905123157678995e-05,
      "loss": 0.013,
      "step": 304
    },
    {
      "epoch": 0.7813000320204931,
      "grad_norm": 0.02687612920999527,
      "learning_rate": 9.9033799667326e-05,
      "loss": 0.0144,
      "step": 305
    },
    {
      "epoch": 0.7838616714697406,
      "grad_norm": 0.027007579803466797,
      "learning_rate": 9.901621063443747e-05,
      "loss": 0.0244,
      "step": 306
    },
    {
      "epoch": 0.7864233109189882,
      "grad_norm": 0.030599134042859077,
      "learning_rate": 9.89984645344865e-05,
      "loss": 0.0198,
      "step": 307
    },
    {
      "epoch": 0.7889849503682357,
      "grad_norm": 0.025911178439855576,
      "learning_rate": 9.898056142433851e-05,
      "loss": 0.0113,
      "step": 308
    },
    {
      "epoch": 0.7915465898174832,
      "grad_norm": 0.028860868886113167,
      "learning_rate": 9.896250136136205e-05,
      "loss": 0.0146,
      "step": 309
    },
    {
      "epoch": 0.7941082292667307,
      "grad_norm": 0.02513432502746582,
      "learning_rate": 9.89442844034286e-05,
      "loss": 0.0176,
      "step": 310
    },
    {
      "epoch": 0.7966698687159782,
      "grad_norm": 0.0275620985776186,
      "learning_rate": 9.89259106089124e-05,
      "loss": 0.0114,
      "step": 311
    },
    {
      "epoch": 0.7992315081652257,
      "grad_norm": 0.01991882734000683,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0108,
      "step": 312
    },
    {
      "epoch": 0.8017931476144733,
      "grad_norm": 0.027305619791150093,
      "learning_rate": 9.888869274614141e-05,
      "loss": 0.0226,
      "step": 313
    },
    {
      "epoch": 0.8043547870637208,
      "grad_norm": 0.025072338059544563,
      "learning_rate": 9.886984879714713e-05,
      "loss": 0.0122,
      "step": 314
    },
    {
      "epoch": 0.8069164265129684,
      "grad_norm": 0.022108634933829308,
      "learning_rate": 9.885084825009086e-05,
      "loss": 0.0129,
      "step": 315
    },
    {
      "epoch": 0.8094780659622158,
      "grad_norm": 0.030420850962400436,
      "learning_rate": 9.883169116585772e-05,
      "loss": 0.0175,
      "step": 316
    },
    {
      "epoch": 0.8120397054114633,
      "grad_norm": 0.03353031352162361,
      "learning_rate": 9.88123776058345e-05,
      "loss": 0.0144,
      "step": 317
    },
    {
      "epoch": 0.8146013448607109,
      "grad_norm": 0.0281111728399992,
      "learning_rate": 9.879290763190938e-05,
      "loss": 0.0118,
      "step": 318
    },
    {
      "epoch": 0.8171629843099584,
      "grad_norm": 0.02738821692764759,
      "learning_rate": 9.877328130647175e-05,
      "loss": 0.0114,
      "step": 319
    },
    {
      "epoch": 0.8197246237592059,
      "grad_norm": 0.026797035709023476,
      "learning_rate": 9.875349869241201e-05,
      "loss": 0.011,
      "step": 320
    },
    {
      "epoch": 0.8222862632084534,
      "grad_norm": 0.0358194038271904,
      "learning_rate": 9.87335598531214e-05,
      "loss": 0.0123,
      "step": 321
    },
    {
      "epoch": 0.8248479026577009,
      "grad_norm": 0.022085469216108322,
      "learning_rate": 9.87134648524917e-05,
      "loss": 0.012,
      "step": 322
    },
    {
      "epoch": 0.8274095421069484,
      "grad_norm": 0.02928551472723484,
      "learning_rate": 9.869321375491516e-05,
      "loss": 0.0203,
      "step": 323
    },
    {
      "epoch": 0.829971181556196,
      "grad_norm": 0.025247866287827492,
      "learning_rate": 9.867280662528419e-05,
      "loss": 0.0123,
      "step": 324
    },
    {
      "epoch": 0.8325328210054435,
      "grad_norm": 0.026824558153748512,
      "learning_rate": 9.865224352899119e-05,
      "loss": 0.0142,
      "step": 325
    },
    {
      "epoch": 0.8325328210054435,
      "eval_loss": 0.011021601967513561,
      "eval_runtime": 15.7711,
      "eval_samples_per_second": 6.341,
      "eval_steps_per_second": 1.585,
      "step": 325
    },
    {
      "epoch": 0.835094460454691,
      "grad_norm": 0.028063297271728516,
      "learning_rate": 9.863152453192836e-05,
      "loss": 0.0123,
      "step": 326
    },
    {
      "epoch": 0.8376560999039385,
      "grad_norm": 0.026745524257421494,
      "learning_rate": 9.861064970048744e-05,
      "loss": 0.0121,
      "step": 327
    },
    {
      "epoch": 0.840217739353186,
      "grad_norm": 0.0259662177413702,
      "learning_rate": 9.85896191015595e-05,
      "loss": 0.0111,
      "step": 328
    },
    {
      "epoch": 0.8427793788024336,
      "grad_norm": 0.03781949728727341,
      "learning_rate": 9.856843280253485e-05,
      "loss": 0.0228,
      "step": 329
    },
    {
      "epoch": 0.8453410182516811,
      "grad_norm": 0.019805191084742546,
      "learning_rate": 9.85470908713026e-05,
      "loss": 0.0099,
      "step": 330
    },
    {
      "epoch": 0.8479026577009285,
      "grad_norm": 0.03662043437361717,
      "learning_rate": 9.852559337625066e-05,
      "loss": 0.021,
      "step": 331
    },
    {
      "epoch": 0.8504642971501761,
      "grad_norm": 0.021586574614048004,
      "learning_rate": 9.850394038626539e-05,
      "loss": 0.0111,
      "step": 332
    },
    {
      "epoch": 0.8530259365994236,
      "grad_norm": 0.024759409949183464,
      "learning_rate": 9.848213197073139e-05,
      "loss": 0.0109,
      "step": 333
    },
    {
      "epoch": 0.8555875760486712,
      "grad_norm": 0.027631640434265137,
      "learning_rate": 9.846016819953136e-05,
      "loss": 0.0106,
      "step": 334
    },
    {
      "epoch": 0.8581492154979187,
      "grad_norm": 0.029770981520414352,
      "learning_rate": 9.843804914304577e-05,
      "loss": 0.0151,
      "step": 335
    },
    {
      "epoch": 0.8607108549471661,
      "grad_norm": 0.02814965881407261,
      "learning_rate": 9.841577487215271e-05,
      "loss": 0.0158,
      "step": 336
    },
    {
      "epoch": 0.8632724943964137,
      "grad_norm": 0.026514781638979912,
      "learning_rate": 9.839334545822768e-05,
      "loss": 0.013,
      "step": 337
    },
    {
      "epoch": 0.8658341338456612,
      "grad_norm": 0.022735703736543655,
      "learning_rate": 9.837076097314319e-05,
      "loss": 0.0157,
      "step": 338
    },
    {
      "epoch": 0.8683957732949087,
      "grad_norm": 0.026729697361588478,
      "learning_rate": 9.834802148926882e-05,
      "loss": 0.0189,
      "step": 339
    },
    {
      "epoch": 0.8709574127441563,
      "grad_norm": 0.025248195976018906,
      "learning_rate": 9.83251270794707e-05,
      "loss": 0.0121,
      "step": 340
    },
    {
      "epoch": 0.8735190521934038,
      "grad_norm": 0.025944946333765984,
      "learning_rate": 9.830207781711147e-05,
      "loss": 0.0135,
      "step": 341
    },
    {
      "epoch": 0.8760806916426513,
      "grad_norm": 0.025446701794862747,
      "learning_rate": 9.827887377604995e-05,
      "loss": 0.0189,
      "step": 342
    },
    {
      "epoch": 0.8786423310918988,
      "grad_norm": 0.0214429572224617,
      "learning_rate": 9.825551503064094e-05,
      "loss": 0.0118,
      "step": 343
    },
    {
      "epoch": 0.8812039705411463,
      "grad_norm": 0.025962600484490395,
      "learning_rate": 9.8232001655735e-05,
      "loss": 0.0107,
      "step": 344
    },
    {
      "epoch": 0.8837656099903939,
      "grad_norm": 0.026138875633478165,
      "learning_rate": 9.820833372667812e-05,
      "loss": 0.0107,
      "step": 345
    },
    {
      "epoch": 0.8863272494396414,
      "grad_norm": 0.0326177254319191,
      "learning_rate": 9.81845113193116e-05,
      "loss": 0.0136,
      "step": 346
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.03477172553539276,
      "learning_rate": 9.816053450997172e-05,
      "loss": 0.0127,
      "step": 347
    },
    {
      "epoch": 0.8914505283381364,
      "grad_norm": 0.03032323718070984,
      "learning_rate": 9.813640337548954e-05,
      "loss": 0.025,
      "step": 348
    },
    {
      "epoch": 0.8940121677873839,
      "grad_norm": 0.02440054714679718,
      "learning_rate": 9.811211799319062e-05,
      "loss": 0.0143,
      "step": 349
    },
    {
      "epoch": 0.8965738072366315,
      "grad_norm": 0.02038225159049034,
      "learning_rate": 9.80876784408948e-05,
      "loss": 0.0134,
      "step": 350
    },
    {
      "epoch": 0.8965738072366315,
      "eval_loss": 0.010415345430374146,
      "eval_runtime": 15.6951,
      "eval_samples_per_second": 6.371,
      "eval_steps_per_second": 1.593,
      "step": 350
    },
    {
      "epoch": 0.899135446685879,
      "grad_norm": 0.04363004118204117,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0335,
      "step": 351
    },
    {
      "epoch": 0.9016970861351264,
      "grad_norm": 0.029303282499313354,
      "learning_rate": 9.803833714006169e-05,
      "loss": 0.0184,
      "step": 352
    },
    {
      "epoch": 0.904258725584374,
      "grad_norm": 0.02172860875725746,
      "learning_rate": 9.801343554963317e-05,
      "loss": 0.0105,
      "step": 353
    },
    {
      "epoch": 0.9068203650336215,
      "grad_norm": 0.023900095373392105,
      "learning_rate": 9.798838010542482e-05,
      "loss": 0.0104,
      "step": 354
    },
    {
      "epoch": 0.909382004482869,
      "grad_norm": 0.02863960526883602,
      "learning_rate": 9.796317088772403e-05,
      "loss": 0.0191,
      "step": 355
    },
    {
      "epoch": 0.9119436439321166,
      "grad_norm": 0.03499027341604233,
      "learning_rate": 9.793780797731096e-05,
      "loss": 0.0133,
      "step": 356
    },
    {
      "epoch": 0.914505283381364,
      "grad_norm": 0.025026291608810425,
      "learning_rate": 9.791229145545831e-05,
      "loss": 0.0105,
      "step": 357
    },
    {
      "epoch": 0.9170669228306116,
      "grad_norm": 0.019676843658089638,
      "learning_rate": 9.788662140393096e-05,
      "loss": 0.01,
      "step": 358
    },
    {
      "epoch": 0.9196285622798591,
      "grad_norm": 0.029065057635307312,
      "learning_rate": 9.786079790498575e-05,
      "loss": 0.0164,
      "step": 359
    },
    {
      "epoch": 0.9221902017291066,
      "grad_norm": 0.028103569522500038,
      "learning_rate": 9.783482104137127e-05,
      "loss": 0.0104,
      "step": 360
    },
    {
      "epoch": 0.9247518411783542,
      "grad_norm": 0.02853201888501644,
      "learning_rate": 9.780869089632749e-05,
      "loss": 0.021,
      "step": 361
    },
    {
      "epoch": 0.9273134806276017,
      "grad_norm": 0.022803885862231255,
      "learning_rate": 9.778240755358564e-05,
      "loss": 0.011,
      "step": 362
    },
    {
      "epoch": 0.9298751200768491,
      "grad_norm": 0.024698354303836823,
      "learning_rate": 9.775597109736776e-05,
      "loss": 0.0126,
      "step": 363
    },
    {
      "epoch": 0.9324367595260967,
      "grad_norm": 0.027431121096014977,
      "learning_rate": 9.77293816123866e-05,
      "loss": 0.0199,
      "step": 364
    },
    {
      "epoch": 0.9349983989753442,
      "grad_norm": 0.02329852059483528,
      "learning_rate": 9.770263918384524e-05,
      "loss": 0.012,
      "step": 365
    },
    {
      "epoch": 0.9375600384245918,
      "grad_norm": 0.019519859924912453,
      "learning_rate": 9.767574389743682e-05,
      "loss": 0.0083,
      "step": 366
    },
    {
      "epoch": 0.9401216778738393,
      "grad_norm": 0.02185627445578575,
      "learning_rate": 9.764869583934437e-05,
      "loss": 0.0078,
      "step": 367
    },
    {
      "epoch": 0.9426833173230867,
      "grad_norm": 0.03656851127743721,
      "learning_rate": 9.76214950962404e-05,
      "loss": 0.017,
      "step": 368
    },
    {
      "epoch": 0.9452449567723343,
      "grad_norm": 0.025890717282891273,
      "learning_rate": 9.759414175528672e-05,
      "loss": 0.0171,
      "step": 369
    },
    {
      "epoch": 0.9478065962215818,
      "grad_norm": 0.02669275552034378,
      "learning_rate": 9.75666359041341e-05,
      "loss": 0.0129,
      "step": 370
    },
    {
      "epoch": 0.9503682356708293,
      "grad_norm": 0.0161345936357975,
      "learning_rate": 9.753897763092202e-05,
      "loss": 0.01,
      "step": 371
    },
    {
      "epoch": 0.9529298751200769,
      "grad_norm": 0.023527219891548157,
      "learning_rate": 9.751116702427836e-05,
      "loss": 0.0107,
      "step": 372
    },
    {
      "epoch": 0.9554915145693244,
      "grad_norm": 0.0295490100979805,
      "learning_rate": 9.748320417331915e-05,
      "loss": 0.0151,
      "step": 373
    },
    {
      "epoch": 0.9580531540185719,
      "grad_norm": 0.027163468301296234,
      "learning_rate": 9.745508916764832e-05,
      "loss": 0.0147,
      "step": 374
    },
    {
      "epoch": 0.9606147934678194,
      "grad_norm": 0.025246214121580124,
      "learning_rate": 9.742682209735727e-05,
      "loss": 0.0124,
      "step": 375
    },
    {
      "epoch": 0.9606147934678194,
      "eval_loss": 0.009683902375400066,
      "eval_runtime": 15.6724,
      "eval_samples_per_second": 6.381,
      "eval_steps_per_second": 1.595,
      "step": 375
    },
    {
      "epoch": 0.9631764329170669,
      "grad_norm": 0.02218458242714405,
      "learning_rate": 9.739840305302477e-05,
      "loss": 0.0111,
      "step": 376
    },
    {
      "epoch": 0.9657380723663145,
      "grad_norm": 0.03978296369314194,
      "learning_rate": 9.736983212571646e-05,
      "loss": 0.0208,
      "step": 377
    },
    {
      "epoch": 0.968299711815562,
      "grad_norm": 0.031306296586990356,
      "learning_rate": 9.73411094069848e-05,
      "loss": 0.0159,
      "step": 378
    },
    {
      "epoch": 0.9708613512648094,
      "grad_norm": 0.020451745018363,
      "learning_rate": 9.731223498886855e-05,
      "loss": 0.0095,
      "step": 379
    },
    {
      "epoch": 0.973422990714057,
      "grad_norm": 0.030514508485794067,
      "learning_rate": 9.728320896389263e-05,
      "loss": 0.016,
      "step": 380
    },
    {
      "epoch": 0.9759846301633045,
      "grad_norm": 0.023473547771573067,
      "learning_rate": 9.725403142506774e-05,
      "loss": 0.0117,
      "step": 381
    },
    {
      "epoch": 0.9785462696125521,
      "grad_norm": 0.025907503440976143,
      "learning_rate": 9.722470246589008e-05,
      "loss": 0.0116,
      "step": 382
    },
    {
      "epoch": 0.9811079090617996,
      "grad_norm": 0.02568023093044758,
      "learning_rate": 9.719522218034112e-05,
      "loss": 0.0122,
      "step": 383
    },
    {
      "epoch": 0.983669548511047,
      "grad_norm": 0.03493017703294754,
      "learning_rate": 9.716559066288715e-05,
      "loss": 0.0165,
      "step": 384
    },
    {
      "epoch": 0.9862311879602946,
      "grad_norm": 0.02209441363811493,
      "learning_rate": 9.713580800847916e-05,
      "loss": 0.0154,
      "step": 385
    },
    {
      "epoch": 0.9887928274095421,
      "grad_norm": 0.03291688114404678,
      "learning_rate": 9.710587431255236e-05,
      "loss": 0.0087,
      "step": 386
    },
    {
      "epoch": 0.9913544668587896,
      "grad_norm": 0.025987064465880394,
      "learning_rate": 9.7075789671026e-05,
      "loss": 0.0113,
      "step": 387
    },
    {
      "epoch": 0.9939161063080372,
      "grad_norm": 0.03901522606611252,
      "learning_rate": 9.7045554180303e-05,
      "loss": 0.013,
      "step": 388
    },
    {
      "epoch": 0.9964777457572846,
      "grad_norm": 0.020256483927369118,
      "learning_rate": 9.701516793726967e-05,
      "loss": 0.0105,
      "step": 389
    },
    {
      "epoch": 0.9990393852065321,
      "grad_norm": 0.03212558478116989,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0211,
      "step": 390
    },
    {
      "epoch": 1.0019212295869357,
      "grad_norm": 0.04988866299390793,
      "learning_rate": 9.695394358423236e-05,
      "loss": 0.0198,
      "step": 391
    },
    {
      "epoch": 1.0044828690361831,
      "grad_norm": 0.025478005409240723,
      "learning_rate": 9.692310567041505e-05,
      "loss": 0.0124,
      "step": 392
    },
    {
      "epoch": 1.0070445084854307,
      "grad_norm": 0.01753000169992447,
      "learning_rate": 9.689211739666023e-05,
      "loss": 0.009,
      "step": 393
    },
    {
      "epoch": 1.0096061479346783,
      "grad_norm": 0.02424152009189129,
      "learning_rate": 9.68609788622664e-05,
      "loss": 0.0094,
      "step": 394
    },
    {
      "epoch": 1.0121677873839257,
      "grad_norm": 0.02567497454583645,
      "learning_rate": 9.682969016701358e-05,
      "loss": 0.0162,
      "step": 395
    },
    {
      "epoch": 1.0147294268331732,
      "grad_norm": 0.02308768406510353,
      "learning_rate": 9.679825141116296e-05,
      "loss": 0.0094,
      "step": 396
    },
    {
      "epoch": 1.0172910662824208,
      "grad_norm": 0.02406313829123974,
      "learning_rate": 9.676666269545655e-05,
      "loss": 0.0107,
      "step": 397
    },
    {
      "epoch": 1.0198527057316682,
      "grad_norm": 0.026956558227539062,
      "learning_rate": 9.673492412111698e-05,
      "loss": 0.0142,
      "step": 398
    },
    {
      "epoch": 1.0224143451809158,
      "grad_norm": 0.0189517792314291,
      "learning_rate": 9.670303578984697e-05,
      "loss": 0.0093,
      "step": 399
    },
    {
      "epoch": 1.0249759846301634,
      "grad_norm": 0.025387246161699295,
      "learning_rate": 9.66709978038292e-05,
      "loss": 0.0122,
      "step": 400
    },
    {
      "epoch": 1.0249759846301634,
      "eval_loss": 0.009496361948549747,
      "eval_runtime": 15.6763,
      "eval_samples_per_second": 6.379,
      "eval_steps_per_second": 1.595,
      "step": 400
    },
    {
      "epoch": 1.0275376240794107,
      "grad_norm": 0.020283183082938194,
      "learning_rate": 9.663881026572586e-05,
      "loss": 0.0109,
      "step": 401
    },
    {
      "epoch": 1.0300992635286583,
      "grad_norm": 0.02017321065068245,
      "learning_rate": 9.66064732786784e-05,
      "loss": 0.0142,
      "step": 402
    },
    {
      "epoch": 1.032660902977906,
      "grad_norm": 0.02185225673019886,
      "learning_rate": 9.657398694630712e-05,
      "loss": 0.0069,
      "step": 403
    },
    {
      "epoch": 1.0352225424271533,
      "grad_norm": 0.02693125233054161,
      "learning_rate": 9.654135137271093e-05,
      "loss": 0.0121,
      "step": 404
    },
    {
      "epoch": 1.0377841818764009,
      "grad_norm": 0.026309996843338013,
      "learning_rate": 9.650856666246693e-05,
      "loss": 0.0144,
      "step": 405
    },
    {
      "epoch": 1.0403458213256485,
      "grad_norm": 0.022313056513667107,
      "learning_rate": 9.64756329206301e-05,
      "loss": 0.0086,
      "step": 406
    },
    {
      "epoch": 1.042907460774896,
      "grad_norm": 0.033154942095279694,
      "learning_rate": 9.644255025273304e-05,
      "loss": 0.0173,
      "step": 407
    },
    {
      "epoch": 1.0454691002241434,
      "grad_norm": 0.021595394238829613,
      "learning_rate": 9.640931876478547e-05,
      "loss": 0.0108,
      "step": 408
    },
    {
      "epoch": 1.048030739673391,
      "grad_norm": 0.02003701590001583,
      "learning_rate": 9.637593856327411e-05,
      "loss": 0.0098,
      "step": 409
    },
    {
      "epoch": 1.0505923791226386,
      "grad_norm": 0.022105243057012558,
      "learning_rate": 9.634240975516209e-05,
      "loss": 0.0088,
      "step": 410
    },
    {
      "epoch": 1.053154018571886,
      "grad_norm": 0.01878410391509533,
      "learning_rate": 9.630873244788883e-05,
      "loss": 0.0081,
      "step": 411
    },
    {
      "epoch": 1.0557156580211335,
      "grad_norm": 0.02455531433224678,
      "learning_rate": 9.627490674936954e-05,
      "loss": 0.0132,
      "step": 412
    },
    {
      "epoch": 1.0582772974703811,
      "grad_norm": 0.02545606903731823,
      "learning_rate": 9.624093276799498e-05,
      "loss": 0.0106,
      "step": 413
    },
    {
      "epoch": 1.0608389369196285,
      "grad_norm": 0.019652288407087326,
      "learning_rate": 9.6206810612631e-05,
      "loss": 0.0105,
      "step": 414
    },
    {
      "epoch": 1.063400576368876,
      "grad_norm": 0.022004250437021255,
      "learning_rate": 9.617254039261834e-05,
      "loss": 0.0136,
      "step": 415
    },
    {
      "epoch": 1.0659622158181237,
      "grad_norm": 0.02517751231789589,
      "learning_rate": 9.613812221777212e-05,
      "loss": 0.0133,
      "step": 416
    },
    {
      "epoch": 1.068523855267371,
      "grad_norm": 0.021614955738186836,
      "learning_rate": 9.610355619838163e-05,
      "loss": 0.0094,
      "step": 417
    },
    {
      "epoch": 1.0710854947166186,
      "grad_norm": 0.038878973573446274,
      "learning_rate": 9.606884244520987e-05,
      "loss": 0.0084,
      "step": 418
    },
    {
      "epoch": 1.0736471341658662,
      "grad_norm": 0.020645610988140106,
      "learning_rate": 9.603398106949326e-05,
      "loss": 0.0109,
      "step": 419
    },
    {
      "epoch": 1.0762087736151136,
      "grad_norm": 0.018204625695943832,
      "learning_rate": 9.599897218294122e-05,
      "loss": 0.0082,
      "step": 420
    },
    {
      "epoch": 1.0787704130643612,
      "grad_norm": 0.02104598470032215,
      "learning_rate": 9.59638158977359e-05,
      "loss": 0.009,
      "step": 421
    },
    {
      "epoch": 1.0813320525136088,
      "grad_norm": 0.03736334294080734,
      "learning_rate": 9.592851232653175e-05,
      "loss": 0.0177,
      "step": 422
    },
    {
      "epoch": 1.0838936919628561,
      "grad_norm": 0.026802612468600273,
      "learning_rate": 9.58930615824552e-05,
      "loss": 0.0111,
      "step": 423
    },
    {
      "epoch": 1.0864553314121037,
      "grad_norm": 0.01986725442111492,
      "learning_rate": 9.585746377910425e-05,
      "loss": 0.0081,
      "step": 424
    },
    {
      "epoch": 1.0890169708613513,
      "grad_norm": 0.03875807672739029,
      "learning_rate": 9.582171903054816e-05,
      "loss": 0.0211,
      "step": 425
    },
    {
      "epoch": 1.0890169708613513,
      "eval_loss": 0.009211279451847076,
      "eval_runtime": 15.6813,
      "eval_samples_per_second": 6.377,
      "eval_steps_per_second": 1.594,
      "step": 425
    },
    {
      "epoch": 1.0915786103105989,
      "grad_norm": 0.019004806876182556,
      "learning_rate": 9.578582745132704e-05,
      "loss": 0.0069,
      "step": 426
    },
    {
      "epoch": 1.0941402497598463,
      "grad_norm": 0.024430232122540474,
      "learning_rate": 9.574978915645152e-05,
      "loss": 0.0088,
      "step": 427
    },
    {
      "epoch": 1.0967018892090938,
      "grad_norm": 0.02753954567015171,
      "learning_rate": 9.571360426140235e-05,
      "loss": 0.015,
      "step": 428
    },
    {
      "epoch": 1.0992635286583414,
      "grad_norm": 0.0206803847104311,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0093,
      "step": 429
    },
    {
      "epoch": 1.1018251681075888,
      "grad_norm": 0.02357391081750393,
      "learning_rate": 9.564079513505455e-05,
      "loss": 0.0142,
      "step": 430
    },
    {
      "epoch": 1.1043868075568364,
      "grad_norm": 0.0350952111184597,
      "learning_rate": 9.560417113706477e-05,
      "loss": 0.0139,
      "step": 431
    },
    {
      "epoch": 1.106948447006084,
      "grad_norm": 0.023076610639691353,
      "learning_rate": 9.556740100551829e-05,
      "loss": 0.0101,
      "step": 432
    },
    {
      "epoch": 1.1095100864553313,
      "grad_norm": 0.023970071226358414,
      "learning_rate": 9.553048485824095e-05,
      "loss": 0.0104,
      "step": 433
    },
    {
      "epoch": 1.112071725904579,
      "grad_norm": 0.02964206598699093,
      "learning_rate": 9.549342281352649e-05,
      "loss": 0.0231,
      "step": 434
    },
    {
      "epoch": 1.1146333653538265,
      "grad_norm": 0.020167216658592224,
      "learning_rate": 9.54562149901362e-05,
      "loss": 0.0098,
      "step": 435
    },
    {
      "epoch": 1.1171950048030739,
      "grad_norm": 0.021479401737451553,
      "learning_rate": 9.54188615072984e-05,
      "loss": 0.0159,
      "step": 436
    },
    {
      "epoch": 1.1197566442523215,
      "grad_norm": 0.015459496527910233,
      "learning_rate": 9.538136248470827e-05,
      "loss": 0.0062,
      "step": 437
    },
    {
      "epoch": 1.122318283701569,
      "grad_norm": 0.02548816241323948,
      "learning_rate": 9.534371804252728e-05,
      "loss": 0.0133,
      "step": 438
    },
    {
      "epoch": 1.1248799231508164,
      "grad_norm": 0.018775109201669693,
      "learning_rate": 9.530592830138292e-05,
      "loss": 0.0088,
      "step": 439
    },
    {
      "epoch": 1.127441562600064,
      "grad_norm": 0.031876884400844574,
      "learning_rate": 9.526799338236827e-05,
      "loss": 0.0124,
      "step": 440
    },
    {
      "epoch": 1.1300032020493116,
      "grad_norm": 0.03683663532137871,
      "learning_rate": 9.522991340704162e-05,
      "loss": 0.0174,
      "step": 441
    },
    {
      "epoch": 1.1325648414985592,
      "grad_norm": 0.02702777087688446,
      "learning_rate": 9.519168849742604e-05,
      "loss": 0.0102,
      "step": 442
    },
    {
      "epoch": 1.1351264809478065,
      "grad_norm": 0.028959324583411217,
      "learning_rate": 9.515331877600906e-05,
      "loss": 0.0106,
      "step": 443
    },
    {
      "epoch": 1.1376881203970541,
      "grad_norm": 0.029596347361803055,
      "learning_rate": 9.511480436574225e-05,
      "loss": 0.0096,
      "step": 444
    },
    {
      "epoch": 1.1402497598463017,
      "grad_norm": 0.025607751682400703,
      "learning_rate": 9.507614539004082e-05,
      "loss": 0.0131,
      "step": 445
    },
    {
      "epoch": 1.142811399295549,
      "grad_norm": 0.023415246978402138,
      "learning_rate": 9.503734197278316e-05,
      "loss": 0.0107,
      "step": 446
    },
    {
      "epoch": 1.1453730387447967,
      "grad_norm": 0.029267001897096634,
      "learning_rate": 9.49983942383106e-05,
      "loss": 0.0116,
      "step": 447
    },
    {
      "epoch": 1.1479346781940443,
      "grad_norm": 0.021906791254878044,
      "learning_rate": 9.495930231142689e-05,
      "loss": 0.0113,
      "step": 448
    },
    {
      "epoch": 1.1504963176432916,
      "grad_norm": 0.0230691060423851,
      "learning_rate": 9.492006631739777e-05,
      "loss": 0.0123,
      "step": 449
    },
    {
      "epoch": 1.1530579570925392,
      "grad_norm": 0.023082030937075615,
      "learning_rate": 9.48806863819507e-05,
      "loss": 0.01,
      "step": 450
    },
    {
      "epoch": 1.1530579570925392,
      "eval_loss": 0.009998048655688763,
      "eval_runtime": 15.7731,
      "eval_samples_per_second": 6.34,
      "eval_steps_per_second": 1.585,
      "step": 450
    },
    {
      "epoch": 1.1556195965417868,
      "grad_norm": 0.026397304609417915,
      "learning_rate": 9.484116263127436e-05,
      "loss": 0.0123,
      "step": 451
    },
    {
      "epoch": 1.1581812359910342,
      "grad_norm": 0.02318529225885868,
      "learning_rate": 9.480149519201825e-05,
      "loss": 0.0107,
      "step": 452
    },
    {
      "epoch": 1.1607428754402818,
      "grad_norm": 0.021503478288650513,
      "learning_rate": 9.476168419129235e-05,
      "loss": 0.0124,
      "step": 453
    },
    {
      "epoch": 1.1633045148895294,
      "grad_norm": 0.03301948681473732,
      "learning_rate": 9.47217297566666e-05,
      "loss": 0.0136,
      "step": 454
    },
    {
      "epoch": 1.1658661543387767,
      "grad_norm": 0.021176926791667938,
      "learning_rate": 9.468163201617062e-05,
      "loss": 0.0084,
      "step": 455
    },
    {
      "epoch": 1.1684277937880243,
      "grad_norm": 0.021742813289165497,
      "learning_rate": 9.464139109829321e-05,
      "loss": 0.0112,
      "step": 456
    },
    {
      "epoch": 1.170989433237272,
      "grad_norm": 0.01652652770280838,
      "learning_rate": 9.460100713198196e-05,
      "loss": 0.0063,
      "step": 457
    },
    {
      "epoch": 1.1735510726865193,
      "grad_norm": 0.02279038541018963,
      "learning_rate": 9.456048024664288e-05,
      "loss": 0.0097,
      "step": 458
    },
    {
      "epoch": 1.1761127121357668,
      "grad_norm": 0.019902581349015236,
      "learning_rate": 9.451981057213992e-05,
      "loss": 0.0091,
      "step": 459
    },
    {
      "epoch": 1.1786743515850144,
      "grad_norm": 0.03399882838129997,
      "learning_rate": 9.447899823879456e-05,
      "loss": 0.018,
      "step": 460
    },
    {
      "epoch": 1.181235991034262,
      "grad_norm": 0.022234100848436356,
      "learning_rate": 9.443804337738544e-05,
      "loss": 0.0068,
      "step": 461
    },
    {
      "epoch": 1.1837976304835094,
      "grad_norm": 0.019693007692694664,
      "learning_rate": 9.439694611914796e-05,
      "loss": 0.0054,
      "step": 462
    },
    {
      "epoch": 1.186359269932757,
      "grad_norm": 0.02781878225505352,
      "learning_rate": 9.43557065957737e-05,
      "loss": 0.0166,
      "step": 463
    },
    {
      "epoch": 1.1889209093820046,
      "grad_norm": 0.018343890085816383,
      "learning_rate": 9.431432493941022e-05,
      "loss": 0.0085,
      "step": 464
    },
    {
      "epoch": 1.191482548831252,
      "grad_norm": 0.03791218250989914,
      "learning_rate": 9.42728012826605e-05,
      "loss": 0.014,
      "step": 465
    },
    {
      "epoch": 1.1940441882804995,
      "grad_norm": 0.025248322635889053,
      "learning_rate": 9.423113575858252e-05,
      "loss": 0.01,
      "step": 466
    },
    {
      "epoch": 1.196605827729747,
      "grad_norm": 0.020284641534090042,
      "learning_rate": 9.418932850068889e-05,
      "loss": 0.0082,
      "step": 467
    },
    {
      "epoch": 1.1991674671789945,
      "grad_norm": 0.02318977750837803,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0104,
      "step": 468
    },
    {
      "epoch": 1.201729106628242,
      "grad_norm": 0.020158514380455017,
      "learning_rate": 9.410528931977542e-05,
      "loss": 0.0087,
      "step": 469
    },
    {
      "epoch": 1.2042907460774896,
      "grad_norm": 0.028263043612241745,
      "learning_rate": 9.406305766604995e-05,
      "loss": 0.0124,
      "step": 470
    },
    {
      "epoch": 1.206852385526737,
      "grad_norm": 0.03137621656060219,
      "learning_rate": 9.402068481709658e-05,
      "loss": 0.0206,
      "step": 471
    },
    {
      "epoch": 1.2094140249759846,
      "grad_norm": 0.02518923208117485,
      "learning_rate": 9.397817090869448e-05,
      "loss": 0.0162,
      "step": 472
    },
    {
      "epoch": 1.2119756644252322,
      "grad_norm": 0.021693777292966843,
      "learning_rate": 9.393551607707478e-05,
      "loss": 0.0111,
      "step": 473
    },
    {
      "epoch": 1.2145373038744798,
      "grad_norm": 0.023595202714204788,
      "learning_rate": 9.389272045892024e-05,
      "loss": 0.0086,
      "step": 474
    },
    {
      "epoch": 1.2170989433237271,
      "grad_norm": 0.025104286149144173,
      "learning_rate": 9.384978419136468e-05,
      "loss": 0.0158,
      "step": 475
    },
    {
      "epoch": 1.2170989433237271,
      "eval_loss": 0.008896440267562866,
      "eval_runtime": 15.7543,
      "eval_samples_per_second": 6.347,
      "eval_steps_per_second": 1.587,
      "step": 475
    },
    {
      "epoch": 1.2196605827729747,
      "grad_norm": 0.016638245433568954,
      "learning_rate": 9.380670741199266e-05,
      "loss": 0.0079,
      "step": 476
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.015983251854777336,
      "learning_rate": 9.3763490258839e-05,
      "loss": 0.0067,
      "step": 477
    },
    {
      "epoch": 1.2247838616714697,
      "grad_norm": 0.020340844988822937,
      "learning_rate": 9.37201328703883e-05,
      "loss": 0.0102,
      "step": 478
    },
    {
      "epoch": 1.2273455011207173,
      "grad_norm": 0.019760936498641968,
      "learning_rate": 9.367663538557457e-05,
      "loss": 0.0099,
      "step": 479
    },
    {
      "epoch": 1.2299071405699649,
      "grad_norm": 0.027867259457707405,
      "learning_rate": 9.363299794378073e-05,
      "loss": 0.0183,
      "step": 480
    },
    {
      "epoch": 1.2324687800192122,
      "grad_norm": 0.025274328887462616,
      "learning_rate": 9.358922068483812e-05,
      "loss": 0.0144,
      "step": 481
    },
    {
      "epoch": 1.2350304194684598,
      "grad_norm": 0.025409767404198647,
      "learning_rate": 9.354530374902622e-05,
      "loss": 0.0127,
      "step": 482
    },
    {
      "epoch": 1.2375920589177074,
      "grad_norm": 0.0174652561545372,
      "learning_rate": 9.350124727707197e-05,
      "loss": 0.0081,
      "step": 483
    },
    {
      "epoch": 1.2401536983669548,
      "grad_norm": 0.020473089069128036,
      "learning_rate": 9.345705141014953e-05,
      "loss": 0.0107,
      "step": 484
    },
    {
      "epoch": 1.2427153378162024,
      "grad_norm": 0.02481193281710148,
      "learning_rate": 9.341271628987968e-05,
      "loss": 0.0162,
      "step": 485
    },
    {
      "epoch": 1.24527697726545,
      "grad_norm": 0.018237514421343803,
      "learning_rate": 9.336824205832947e-05,
      "loss": 0.0094,
      "step": 486
    },
    {
      "epoch": 1.2478386167146973,
      "grad_norm": 0.016897965222597122,
      "learning_rate": 9.332362885801167e-05,
      "loss": 0.0064,
      "step": 487
    },
    {
      "epoch": 1.250400256163945,
      "grad_norm": 0.01858009584248066,
      "learning_rate": 9.327887683188436e-05,
      "loss": 0.0065,
      "step": 488
    },
    {
      "epoch": 1.2529618956131925,
      "grad_norm": 0.02213798649609089,
      "learning_rate": 9.323398612335055e-05,
      "loss": 0.009,
      "step": 489
    },
    {
      "epoch": 1.2555235350624399,
      "grad_norm": 0.03265499696135521,
      "learning_rate": 9.318895687625751e-05,
      "loss": 0.0128,
      "step": 490
    },
    {
      "epoch": 1.2580851745116874,
      "grad_norm": 0.01880866289138794,
      "learning_rate": 9.314378923489658e-05,
      "loss": 0.0092,
      "step": 491
    },
    {
      "epoch": 1.260646813960935,
      "grad_norm": 0.03112734854221344,
      "learning_rate": 9.309848334400246e-05,
      "loss": 0.011,
      "step": 492
    },
    {
      "epoch": 1.2632084534101824,
      "grad_norm": 0.028772294521331787,
      "learning_rate": 9.305303934875294e-05,
      "loss": 0.0149,
      "step": 493
    },
    {
      "epoch": 1.26577009285943,
      "grad_norm": 0.015158562920987606,
      "learning_rate": 9.300745739476829e-05,
      "loss": 0.0071,
      "step": 494
    },
    {
      "epoch": 1.2683317323086776,
      "grad_norm": 0.02867531031370163,
      "learning_rate": 9.296173762811085e-05,
      "loss": 0.0203,
      "step": 495
    },
    {
      "epoch": 1.270893371757925,
      "grad_norm": 0.03381772339344025,
      "learning_rate": 9.291588019528462e-05,
      "loss": 0.021,
      "step": 496
    },
    {
      "epoch": 1.2734550112071725,
      "grad_norm": 0.019410375505685806,
      "learning_rate": 9.28698852432347e-05,
      "loss": 0.0088,
      "step": 497
    },
    {
      "epoch": 1.2760166506564201,
      "grad_norm": 0.025806061923503876,
      "learning_rate": 9.282375291934687e-05,
      "loss": 0.0097,
      "step": 498
    },
    {
      "epoch": 1.2785782901056677,
      "grad_norm": 0.02822774648666382,
      "learning_rate": 9.277748337144709e-05,
      "loss": 0.016,
      "step": 499
    },
    {
      "epoch": 1.281139929554915,
      "grad_norm": 0.025421006605029106,
      "learning_rate": 9.273107674780102e-05,
      "loss": 0.0176,
      "step": 500
    },
    {
      "epoch": 1.281139929554915,
      "eval_loss": 0.008733320981264114,
      "eval_runtime": 15.7696,
      "eval_samples_per_second": 6.341,
      "eval_steps_per_second": 1.585,
      "step": 500
    },
    {
      "epoch": 1.2837015690041627,
      "grad_norm": 0.022834056988358498,
      "learning_rate": 9.268453319711363e-05,
      "loss": 0.0102,
      "step": 501
    },
    {
      "epoch": 1.2862632084534102,
      "grad_norm": 0.02453305944800377,
      "learning_rate": 9.263785286852857e-05,
      "loss": 0.0128,
      "step": 502
    },
    {
      "epoch": 1.2888248479026578,
      "grad_norm": 0.020842405036091805,
      "learning_rate": 9.259103591162785e-05,
      "loss": 0.0061,
      "step": 503
    },
    {
      "epoch": 1.2913864873519052,
      "grad_norm": 0.033657580614089966,
      "learning_rate": 9.254408247643126e-05,
      "loss": 0.0231,
      "step": 504
    },
    {
      "epoch": 1.2939481268011528,
      "grad_norm": 0.020036958158016205,
      "learning_rate": 9.249699271339593e-05,
      "loss": 0.0092,
      "step": 505
    },
    {
      "epoch": 1.2965097662504004,
      "grad_norm": 0.02098897099494934,
      "learning_rate": 9.244976677341583e-05,
      "loss": 0.0092,
      "step": 506
    },
    {
      "epoch": 1.2990714056996477,
      "grad_norm": 0.017251061275601387,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0093,
      "step": 507
    },
    {
      "epoch": 1.3016330451488953,
      "grad_norm": 0.02004789188504219,
      "learning_rate": 9.235490696837855e-05,
      "loss": 0.0117,
      "step": 508
    },
    {
      "epoch": 1.304194684598143,
      "grad_norm": 0.020399397239089012,
      "learning_rate": 9.23072734072892e-05,
      "loss": 0.0087,
      "step": 509
    },
    {
      "epoch": 1.3067563240473903,
      "grad_norm": 0.025535760447382927,
      "learning_rate": 9.225950427718975e-05,
      "loss": 0.0104,
      "step": 510
    },
    {
      "epoch": 1.3093179634966379,
      "grad_norm": 0.03579006716609001,
      "learning_rate": 9.221159973115112e-05,
      "loss": 0.0191,
      "step": 511
    },
    {
      "epoch": 1.3118796029458855,
      "grad_norm": 0.029484592378139496,
      "learning_rate": 9.21635599226782e-05,
      "loss": 0.0132,
      "step": 512
    },
    {
      "epoch": 1.3144412423951328,
      "grad_norm": 0.025395115837454796,
      "learning_rate": 9.211538500570925e-05,
      "loss": 0.0093,
      "step": 513
    },
    {
      "epoch": 1.3170028818443804,
      "grad_norm": 0.03858427330851555,
      "learning_rate": 9.206707513461551e-05,
      "loss": 0.0159,
      "step": 514
    },
    {
      "epoch": 1.319564521293628,
      "grad_norm": 0.018974190577864647,
      "learning_rate": 9.201863046420065e-05,
      "loss": 0.0076,
      "step": 515
    },
    {
      "epoch": 1.3221261607428754,
      "grad_norm": 0.030375462025403976,
      "learning_rate": 9.19700511497003e-05,
      "loss": 0.0145,
      "step": 516
    },
    {
      "epoch": 1.324687800192123,
      "grad_norm": 0.02294369973242283,
      "learning_rate": 9.192133734678155e-05,
      "loss": 0.0104,
      "step": 517
    },
    {
      "epoch": 1.3272494396413705,
      "grad_norm": 0.033602748066186905,
      "learning_rate": 9.187248921154239e-05,
      "loss": 0.0098,
      "step": 518
    },
    {
      "epoch": 1.329811079090618,
      "grad_norm": 0.019165707752108574,
      "learning_rate": 9.182350690051133e-05,
      "loss": 0.0111,
      "step": 519
    },
    {
      "epoch": 1.3323727185398655,
      "grad_norm": 0.021407922729849815,
      "learning_rate": 9.177439057064683e-05,
      "loss": 0.0091,
      "step": 520
    },
    {
      "epoch": 1.334934357989113,
      "grad_norm": 0.03057362511754036,
      "learning_rate": 9.172514037933673e-05,
      "loss": 0.0192,
      "step": 521
    },
    {
      "epoch": 1.3374959974383605,
      "grad_norm": 0.016315093263983727,
      "learning_rate": 9.167575648439788e-05,
      "loss": 0.0072,
      "step": 522
    },
    {
      "epoch": 1.340057636887608,
      "grad_norm": 0.025471271947026253,
      "learning_rate": 9.162623904407553e-05,
      "loss": 0.014,
      "step": 523
    },
    {
      "epoch": 1.3426192763368556,
      "grad_norm": 0.022852519527077675,
      "learning_rate": 9.15765882170429e-05,
      "loss": 0.0102,
      "step": 524
    },
    {
      "epoch": 1.345180915786103,
      "grad_norm": 0.015502731315791607,
      "learning_rate": 9.152680416240059e-05,
      "loss": 0.0073,
      "step": 525
    },
    {
      "epoch": 1.345180915786103,
      "eval_loss": 0.008211835287511349,
      "eval_runtime": 15.7775,
      "eval_samples_per_second": 6.338,
      "eval_steps_per_second": 1.585,
      "step": 525
    },
    {
      "epoch": 1.3477425552353506,
      "grad_norm": 0.01804802566766739,
      "learning_rate": 9.147688703967614e-05,
      "loss": 0.0056,
      "step": 526
    },
    {
      "epoch": 1.3503041946845982,
      "grad_norm": 0.026565713807940483,
      "learning_rate": 9.142683700882351e-05,
      "loss": 0.0158,
      "step": 527
    },
    {
      "epoch": 1.3528658341338455,
      "grad_norm": 0.023307789117097855,
      "learning_rate": 9.13766542302225e-05,
      "loss": 0.0132,
      "step": 528
    },
    {
      "epoch": 1.3554274735830931,
      "grad_norm": 0.03050735965371132,
      "learning_rate": 9.132633886467831e-05,
      "loss": 0.0177,
      "step": 529
    },
    {
      "epoch": 1.3579891130323407,
      "grad_norm": 0.014245600439608097,
      "learning_rate": 9.1275891073421e-05,
      "loss": 0.0072,
      "step": 530
    },
    {
      "epoch": 1.3605507524815883,
      "grad_norm": 0.018063992261886597,
      "learning_rate": 9.122531101810501e-05,
      "loss": 0.0074,
      "step": 531
    },
    {
      "epoch": 1.3631123919308357,
      "grad_norm": 0.03403697907924652,
      "learning_rate": 9.117459886080854e-05,
      "loss": 0.0233,
      "step": 532
    },
    {
      "epoch": 1.3656740313800833,
      "grad_norm": 0.02282620035111904,
      "learning_rate": 9.112375476403312e-05,
      "loss": 0.0109,
      "step": 533
    },
    {
      "epoch": 1.3682356708293308,
      "grad_norm": 0.017634566873311996,
      "learning_rate": 9.107277889070309e-05,
      "loss": 0.0093,
      "step": 534
    },
    {
      "epoch": 1.3707973102785782,
      "grad_norm": 0.01788763515651226,
      "learning_rate": 9.102167140416503e-05,
      "loss": 0.0098,
      "step": 535
    },
    {
      "epoch": 1.3733589497278258,
      "grad_norm": 0.02422240935266018,
      "learning_rate": 9.097043246818727e-05,
      "loss": 0.0112,
      "step": 536
    },
    {
      "epoch": 1.3759205891770734,
      "grad_norm": 0.02159043774008751,
      "learning_rate": 9.091906224695935e-05,
      "loss": 0.0137,
      "step": 537
    },
    {
      "epoch": 1.378482228626321,
      "grad_norm": 0.031434234231710434,
      "learning_rate": 9.08675609050915e-05,
      "loss": 0.0159,
      "step": 538
    },
    {
      "epoch": 1.3810438680755683,
      "grad_norm": 0.029942264780402184,
      "learning_rate": 9.081592860761412e-05,
      "loss": 0.0156,
      "step": 539
    },
    {
      "epoch": 1.383605507524816,
      "grad_norm": 0.02360542118549347,
      "learning_rate": 9.076416551997721e-05,
      "loss": 0.0064,
      "step": 540
    },
    {
      "epoch": 1.3861671469740635,
      "grad_norm": 0.025887703523039818,
      "learning_rate": 9.071227180804994e-05,
      "loss": 0.0107,
      "step": 541
    },
    {
      "epoch": 1.3887287864233109,
      "grad_norm": 0.018033858388662338,
      "learning_rate": 9.066024763811997e-05,
      "loss": 0.0092,
      "step": 542
    },
    {
      "epoch": 1.3912904258725585,
      "grad_norm": 0.02424168959259987,
      "learning_rate": 9.060809317689308e-05,
      "loss": 0.0122,
      "step": 543
    },
    {
      "epoch": 1.393852065321806,
      "grad_norm": 0.025377338752150536,
      "learning_rate": 9.055580859149246e-05,
      "loss": 0.0093,
      "step": 544
    },
    {
      "epoch": 1.3964137047710534,
      "grad_norm": 0.02267155982553959,
      "learning_rate": 9.050339404945833e-05,
      "loss": 0.0177,
      "step": 545
    },
    {
      "epoch": 1.398975344220301,
      "grad_norm": 0.023138578981161118,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0088,
      "step": 546
    },
    {
      "epoch": 1.4015369836695486,
      "grad_norm": 0.0254532340914011,
      "learning_rate": 9.03981757677321e-05,
      "loss": 0.012,
      "step": 547
    },
    {
      "epoch": 1.404098623118796,
      "grad_norm": 0.043509308248758316,
      "learning_rate": 9.034537236520039e-05,
      "loss": 0.018,
      "step": 548
    },
    {
      "epoch": 1.4066602625680436,
      "grad_norm": 0.017051199451088905,
      "learning_rate": 9.029243968035496e-05,
      "loss": 0.0083,
      "step": 549
    },
    {
      "epoch": 1.4092219020172911,
      "grad_norm": 0.023373804986476898,
      "learning_rate": 9.023937788281278e-05,
      "loss": 0.0114,
      "step": 550
    },
    {
      "epoch": 1.4092219020172911,
      "eval_loss": 0.009199035353958607,
      "eval_runtime": 15.7746,
      "eval_samples_per_second": 6.339,
      "eval_steps_per_second": 1.585,
      "step": 550
    },
    {
      "epoch": 1.4117835414665385,
      "grad_norm": 0.027553927153348923,
      "learning_rate": 9.018618714260453e-05,
      "loss": 0.0181,
      "step": 551
    },
    {
      "epoch": 1.414345180915786,
      "grad_norm": 0.013546819798648357,
      "learning_rate": 9.013286763017415e-05,
      "loss": 0.0057,
      "step": 552
    },
    {
      "epoch": 1.4169068203650337,
      "grad_norm": 0.01957760564982891,
      "learning_rate": 9.00794195163781e-05,
      "loss": 0.007,
      "step": 553
    },
    {
      "epoch": 1.419468459814281,
      "grad_norm": 0.023621102795004845,
      "learning_rate": 9.002584297248502e-05,
      "loss": 0.0102,
      "step": 554
    },
    {
      "epoch": 1.4220300992635286,
      "grad_norm": 0.027797885239124298,
      "learning_rate": 8.997213817017507e-05,
      "loss": 0.011,
      "step": 555
    },
    {
      "epoch": 1.4245917387127762,
      "grad_norm": 0.026531843468546867,
      "learning_rate": 8.991830528153935e-05,
      "loss": 0.0073,
      "step": 556
    },
    {
      "epoch": 1.4271533781620236,
      "grad_norm": 0.02077258750796318,
      "learning_rate": 8.986434447907948e-05,
      "loss": 0.0085,
      "step": 557
    },
    {
      "epoch": 1.4297150176112712,
      "grad_norm": 0.018663110211491585,
      "learning_rate": 8.98102559357069e-05,
      "loss": 0.0097,
      "step": 558
    },
    {
      "epoch": 1.4322766570605188,
      "grad_norm": 0.02353561483323574,
      "learning_rate": 8.97560398247424e-05,
      "loss": 0.0092,
      "step": 559
    },
    {
      "epoch": 1.4348382965097661,
      "grad_norm": 0.02463211864233017,
      "learning_rate": 8.970169631991556e-05,
      "loss": 0.0096,
      "step": 560
    },
    {
      "epoch": 1.4373999359590137,
      "grad_norm": 0.023898137733340263,
      "learning_rate": 8.964722559536418e-05,
      "loss": 0.0107,
      "step": 561
    },
    {
      "epoch": 1.4399615754082613,
      "grad_norm": 0.018616532906889915,
      "learning_rate": 8.959262782563372e-05,
      "loss": 0.0124,
      "step": 562
    },
    {
      "epoch": 1.4425232148575087,
      "grad_norm": 0.026767538860440254,
      "learning_rate": 8.95379031856767e-05,
      "loss": 0.016,
      "step": 563
    },
    {
      "epoch": 1.4450848543067563,
      "grad_norm": 0.019774265587329865,
      "learning_rate": 8.948305185085225e-05,
      "loss": 0.0073,
      "step": 564
    },
    {
      "epoch": 1.4476464937560038,
      "grad_norm": 0.026325702667236328,
      "learning_rate": 8.942807399692543e-05,
      "loss": 0.0114,
      "step": 565
    },
    {
      "epoch": 1.4502081332052514,
      "grad_norm": 0.02122092805802822,
      "learning_rate": 8.937296980006675e-05,
      "loss": 0.0114,
      "step": 566
    },
    {
      "epoch": 1.4527697726544988,
      "grad_norm": 0.017576023936271667,
      "learning_rate": 8.931773943685155e-05,
      "loss": 0.01,
      "step": 567
    },
    {
      "epoch": 1.4553314121037464,
      "grad_norm": 0.01859590783715248,
      "learning_rate": 8.926238308425945e-05,
      "loss": 0.0142,
      "step": 568
    },
    {
      "epoch": 1.457893051552994,
      "grad_norm": 0.02905329316854477,
      "learning_rate": 8.92069009196738e-05,
      "loss": 0.0186,
      "step": 569
    },
    {
      "epoch": 1.4604546910022416,
      "grad_norm": 0.014791314490139484,
      "learning_rate": 8.915129312088112e-05,
      "loss": 0.0049,
      "step": 570
    },
    {
      "epoch": 1.463016330451489,
      "grad_norm": 0.0218088086694479,
      "learning_rate": 8.909555986607048e-05,
      "loss": 0.0146,
      "step": 571
    },
    {
      "epoch": 1.4655779699007365,
      "grad_norm": 0.014257200062274933,
      "learning_rate": 8.903970133383297e-05,
      "loss": 0.0059,
      "step": 572
    },
    {
      "epoch": 1.468139609349984,
      "grad_norm": 0.02303312160074711,
      "learning_rate": 8.898371770316111e-05,
      "loss": 0.0114,
      "step": 573
    },
    {
      "epoch": 1.4707012487992315,
      "grad_norm": 0.014151007868349552,
      "learning_rate": 8.892760915344834e-05,
      "loss": 0.0067,
      "step": 574
    },
    {
      "epoch": 1.473262888248479,
      "grad_norm": 0.019835256040096283,
      "learning_rate": 8.88713758644883e-05,
      "loss": 0.0085,
      "step": 575
    },
    {
      "epoch": 1.473262888248479,
      "eval_loss": 0.008619890548288822,
      "eval_runtime": 15.8078,
      "eval_samples_per_second": 6.326,
      "eval_steps_per_second": 1.582,
      "step": 575
    },
    {
      "epoch": 1.4758245276977267,
      "grad_norm": 0.026124896481633186,
      "learning_rate": 8.88150180164744e-05,
      "loss": 0.0131,
      "step": 576
    },
    {
      "epoch": 1.478386167146974,
      "grad_norm": 0.033744972199201584,
      "learning_rate": 8.875853578999918e-05,
      "loss": 0.0187,
      "step": 577
    },
    {
      "epoch": 1.4809478065962216,
      "grad_norm": 0.02144186943769455,
      "learning_rate": 8.870192936605372e-05,
      "loss": 0.0114,
      "step": 578
    },
    {
      "epoch": 1.4835094460454692,
      "grad_norm": 0.020475219935178757,
      "learning_rate": 8.86451989260271e-05,
      "loss": 0.0079,
      "step": 579
    },
    {
      "epoch": 1.4860710854947166,
      "grad_norm": 0.01916237361729145,
      "learning_rate": 8.858834465170576e-05,
      "loss": 0.0075,
      "step": 580
    },
    {
      "epoch": 1.4886327249439641,
      "grad_norm": 0.016654282808303833,
      "learning_rate": 8.853136672527299e-05,
      "loss": 0.0085,
      "step": 581
    },
    {
      "epoch": 1.4911943643932117,
      "grad_norm": 0.026485484093427658,
      "learning_rate": 8.847426532930831e-05,
      "loss": 0.0145,
      "step": 582
    },
    {
      "epoch": 1.493756003842459,
      "grad_norm": 0.019145099446177483,
      "learning_rate": 8.841704064678684e-05,
      "loss": 0.0092,
      "step": 583
    },
    {
      "epoch": 1.4963176432917067,
      "grad_norm": 0.024889731779694557,
      "learning_rate": 8.835969286107881e-05,
      "loss": 0.0085,
      "step": 584
    },
    {
      "epoch": 1.4988792827409543,
      "grad_norm": 0.01563897170126438,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0086,
      "step": 585
    },
    {
      "epoch": 1.5014409221902016,
      "grad_norm": 0.02054821327328682,
      "learning_rate": 8.824462871555568e-05,
      "loss": 0.0075,
      "step": 586
    },
    {
      "epoch": 1.5040025616394492,
      "grad_norm": 0.021489789709448814,
      "learning_rate": 8.818691272445098e-05,
      "loss": 0.008,
      "step": 587
    },
    {
      "epoch": 1.5065642010886968,
      "grad_norm": 0.018730612471699715,
      "learning_rate": 8.812907436757935e-05,
      "loss": 0.009,
      "step": 588
    },
    {
      "epoch": 1.5091258405379442,
      "grad_norm": 0.01786506175994873,
      "learning_rate": 8.807111383027748e-05,
      "loss": 0.0096,
      "step": 589
    },
    {
      "epoch": 1.5116874799871918,
      "grad_norm": 0.026313120499253273,
      "learning_rate": 8.801303129827352e-05,
      "loss": 0.0169,
      "step": 590
    },
    {
      "epoch": 1.5142491194364394,
      "grad_norm": 0.015450164675712585,
      "learning_rate": 8.795482695768658e-05,
      "loss": 0.0074,
      "step": 591
    },
    {
      "epoch": 1.5168107588856867,
      "grad_norm": 0.02219979465007782,
      "learning_rate": 8.789650099502606e-05,
      "loss": 0.0091,
      "step": 592
    },
    {
      "epoch": 1.5193723983349343,
      "grad_norm": 0.018070019781589508,
      "learning_rate": 8.783805359719113e-05,
      "loss": 0.0105,
      "step": 593
    },
    {
      "epoch": 1.521934037784182,
      "grad_norm": 0.01956484653055668,
      "learning_rate": 8.777948495147001e-05,
      "loss": 0.0108,
      "step": 594
    },
    {
      "epoch": 1.5244956772334293,
      "grad_norm": 0.020401043817400932,
      "learning_rate": 8.772079524553951e-05,
      "loss": 0.009,
      "step": 595
    },
    {
      "epoch": 1.527057316682677,
      "grad_norm": 0.022120250388979912,
      "learning_rate": 8.766198466746437e-05,
      "loss": 0.0129,
      "step": 596
    },
    {
      "epoch": 1.5296189561319244,
      "grad_norm": 0.023862425237894058,
      "learning_rate": 8.760305340569661e-05,
      "loss": 0.016,
      "step": 597
    },
    {
      "epoch": 1.5321805955811718,
      "grad_norm": 0.01728702336549759,
      "learning_rate": 8.754400164907497e-05,
      "loss": 0.0085,
      "step": 598
    },
    {
      "epoch": 1.5347422350304196,
      "grad_norm": 0.018914831802248955,
      "learning_rate": 8.748482958682433e-05,
      "loss": 0.0082,
      "step": 599
    },
    {
      "epoch": 1.537303874479667,
      "grad_norm": 0.023846952244639397,
      "learning_rate": 8.742553740855506e-05,
      "loss": 0.0139,
      "step": 600
    },
    {
      "epoch": 1.537303874479667,
      "eval_loss": 0.009778290055692196,
      "eval_runtime": 15.8286,
      "eval_samples_per_second": 6.318,
      "eval_steps_per_second": 1.579,
      "step": 600
    },
    {
      "epoch": 1.5398655139289144,
      "grad_norm": 0.01700327731668949,
      "learning_rate": 8.736612530426245e-05,
      "loss": 0.0074,
      "step": 601
    },
    {
      "epoch": 1.5424271533781622,
      "grad_norm": 0.016836758702993393,
      "learning_rate": 8.730659346432602e-05,
      "loss": 0.0068,
      "step": 602
    },
    {
      "epoch": 1.5449887928274095,
      "grad_norm": 0.020055629312992096,
      "learning_rate": 8.724694207950906e-05,
      "loss": 0.0073,
      "step": 603
    },
    {
      "epoch": 1.547550432276657,
      "grad_norm": 0.029256854206323624,
      "learning_rate": 8.718717134095784e-05,
      "loss": 0.0211,
      "step": 604
    },
    {
      "epoch": 1.5501120717259047,
      "grad_norm": 0.03150349482893944,
      "learning_rate": 8.712728144020118e-05,
      "loss": 0.0211,
      "step": 605
    },
    {
      "epoch": 1.552673711175152,
      "grad_norm": 0.02234642021358013,
      "learning_rate": 8.706727256914961e-05,
      "loss": 0.0106,
      "step": 606
    },
    {
      "epoch": 1.5552353506243997,
      "grad_norm": 0.02711409516632557,
      "learning_rate": 8.700714492009501e-05,
      "loss": 0.0151,
      "step": 607
    },
    {
      "epoch": 1.5577969900736472,
      "grad_norm": 0.021641191095113754,
      "learning_rate": 8.694689868570984e-05,
      "loss": 0.0099,
      "step": 608
    },
    {
      "epoch": 1.5603586295228946,
      "grad_norm": 0.02513721212744713,
      "learning_rate": 8.688653405904652e-05,
      "loss": 0.0174,
      "step": 609
    },
    {
      "epoch": 1.5629202689721422,
      "grad_norm": 0.017550567165017128,
      "learning_rate": 8.682605123353685e-05,
      "loss": 0.0075,
      "step": 610
    },
    {
      "epoch": 1.5654819084213898,
      "grad_norm": 0.04532385244965553,
      "learning_rate": 8.676545040299145e-05,
      "loss": 0.018,
      "step": 611
    },
    {
      "epoch": 1.5680435478706372,
      "grad_norm": 0.021223684772849083,
      "learning_rate": 8.670473176159896e-05,
      "loss": 0.011,
      "step": 612
    },
    {
      "epoch": 1.5706051873198847,
      "grad_norm": 0.02921074442565441,
      "learning_rate": 8.664389550392564e-05,
      "loss": 0.014,
      "step": 613
    },
    {
      "epoch": 1.5731668267691323,
      "grad_norm": 0.01453994307667017,
      "learning_rate": 8.658294182491457e-05,
      "loss": 0.0067,
      "step": 614
    },
    {
      "epoch": 1.5757284662183797,
      "grad_norm": 0.02055704966187477,
      "learning_rate": 8.652187091988517e-05,
      "loss": 0.0136,
      "step": 615
    },
    {
      "epoch": 1.5782901056676273,
      "grad_norm": 0.020393170416355133,
      "learning_rate": 8.646068298453238e-05,
      "loss": 0.0085,
      "step": 616
    },
    {
      "epoch": 1.5808517451168749,
      "grad_norm": 0.018596651032567024,
      "learning_rate": 8.639937821492624e-05,
      "loss": 0.0093,
      "step": 617
    },
    {
      "epoch": 1.5834133845661222,
      "grad_norm": 0.01737053133547306,
      "learning_rate": 8.633795680751116e-05,
      "loss": 0.0085,
      "step": 618
    },
    {
      "epoch": 1.5859750240153698,
      "grad_norm": 0.035250473767519,
      "learning_rate": 8.62764189591053e-05,
      "loss": 0.0162,
      "step": 619
    },
    {
      "epoch": 1.5885366634646174,
      "grad_norm": 0.01704743504524231,
      "learning_rate": 8.621476486689992e-05,
      "loss": 0.0082,
      "step": 620
    },
    {
      "epoch": 1.5910983029138648,
      "grad_norm": 0.020262829959392548,
      "learning_rate": 8.615299472845877e-05,
      "loss": 0.0152,
      "step": 621
    },
    {
      "epoch": 1.5936599423631124,
      "grad_norm": 0.02265034057199955,
      "learning_rate": 8.609110874171751e-05,
      "loss": 0.0114,
      "step": 622
    },
    {
      "epoch": 1.59622158181236,
      "grad_norm": 0.02068282850086689,
      "learning_rate": 8.602910710498295e-05,
      "loss": 0.0112,
      "step": 623
    },
    {
      "epoch": 1.5987832212616073,
      "grad_norm": 0.022094765678048134,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0096,
      "step": 624
    },
    {
      "epoch": 1.601344860710855,
      "grad_norm": 0.03619355335831642,
      "learning_rate": 8.59047576766137e-05,
      "loss": 0.0101,
      "step": 625
    },
    {
      "epoch": 1.601344860710855,
      "eval_loss": 0.008696233853697777,
      "eval_runtime": 15.7787,
      "eval_samples_per_second": 6.338,
      "eval_steps_per_second": 1.584,
      "step": 625
    },
    {
      "epoch": 1.6039065001601025,
      "grad_norm": 0.038272786885499954,
      "learning_rate": 8.584241028344308e-05,
      "loss": 0.0146,
      "step": 626
    },
    {
      "epoch": 1.6064681396093499,
      "grad_norm": 0.02607797272503376,
      "learning_rate": 8.577994803720606e-05,
      "loss": 0.0108,
      "step": 627
    },
    {
      "epoch": 1.6090297790585975,
      "grad_norm": 0.02368808165192604,
      "learning_rate": 8.571737113805606e-05,
      "loss": 0.0157,
      "step": 628
    },
    {
      "epoch": 1.611591418507845,
      "grad_norm": 0.017954347655177116,
      "learning_rate": 8.565467978651387e-05,
      "loss": 0.0058,
      "step": 629
    },
    {
      "epoch": 1.6141530579570924,
      "grad_norm": 0.03589998185634613,
      "learning_rate": 8.559187418346703e-05,
      "loss": 0.0234,
      "step": 630
    },
    {
      "epoch": 1.6167146974063402,
      "grad_norm": 0.02698587067425251,
      "learning_rate": 8.552895453016922e-05,
      "loss": 0.0136,
      "step": 631
    },
    {
      "epoch": 1.6192763368555876,
      "grad_norm": 0.02276044897735119,
      "learning_rate": 8.546592102823955e-05,
      "loss": 0.0094,
      "step": 632
    },
    {
      "epoch": 1.621837976304835,
      "grad_norm": 0.018764210864901543,
      "learning_rate": 8.540277387966194e-05,
      "loss": 0.0074,
      "step": 633
    },
    {
      "epoch": 1.6243996157540828,
      "grad_norm": 0.019631950184702873,
      "learning_rate": 8.53395132867845e-05,
      "loss": 0.0077,
      "step": 634
    },
    {
      "epoch": 1.6269612552033301,
      "grad_norm": 0.017163440585136414,
      "learning_rate": 8.527613945231885e-05,
      "loss": 0.0088,
      "step": 635
    },
    {
      "epoch": 1.6295228946525775,
      "grad_norm": 0.01980568654835224,
      "learning_rate": 8.521265257933948e-05,
      "loss": 0.0105,
      "step": 636
    },
    {
      "epoch": 1.6320845341018253,
      "grad_norm": 0.0192473866045475,
      "learning_rate": 8.51490528712831e-05,
      "loss": 0.0096,
      "step": 637
    },
    {
      "epoch": 1.6346461735510727,
      "grad_norm": 0.023643024265766144,
      "learning_rate": 8.508534053194798e-05,
      "loss": 0.0115,
      "step": 638
    },
    {
      "epoch": 1.6372078130003203,
      "grad_norm": 0.031089499592781067,
      "learning_rate": 8.502151576549333e-05,
      "loss": 0.0218,
      "step": 639
    },
    {
      "epoch": 1.6397694524495678,
      "grad_norm": 0.021543102338910103,
      "learning_rate": 8.495757877643858e-05,
      "loss": 0.0111,
      "step": 640
    },
    {
      "epoch": 1.6423310918988152,
      "grad_norm": 0.019607752561569214,
      "learning_rate": 8.48935297696628e-05,
      "loss": 0.0124,
      "step": 641
    },
    {
      "epoch": 1.6448927313480628,
      "grad_norm": 0.012617550790309906,
      "learning_rate": 8.482936895040403e-05,
      "loss": 0.005,
      "step": 642
    },
    {
      "epoch": 1.6474543707973104,
      "grad_norm": 0.019957462325692177,
      "learning_rate": 8.476509652425851e-05,
      "loss": 0.0069,
      "step": 643
    },
    {
      "epoch": 1.6500160102465578,
      "grad_norm": 0.02268521673977375,
      "learning_rate": 8.470071269718019e-05,
      "loss": 0.0091,
      "step": 644
    },
    {
      "epoch": 1.6525776496958053,
      "grad_norm": 0.0193330105394125,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.0095,
      "step": 645
    },
    {
      "epoch": 1.655139289145053,
      "grad_norm": 0.021894952282309532,
      "learning_rate": 8.457161166582507e-05,
      "loss": 0.008,
      "step": 646
    },
    {
      "epoch": 1.6577009285943003,
      "grad_norm": 0.021809278056025505,
      "learning_rate": 8.450689487523836e-05,
      "loss": 0.0063,
      "step": 647
    },
    {
      "epoch": 1.6602625680435479,
      "grad_norm": 0.02643033117055893,
      "learning_rate": 8.444206751109767e-05,
      "loss": 0.0117,
      "step": 648
    },
    {
      "epoch": 1.6628242074927955,
      "grad_norm": 0.033799465745687485,
      "learning_rate": 8.437712978113516e-05,
      "loss": 0.0214,
      "step": 649
    },
    {
      "epoch": 1.6653858469420428,
      "grad_norm": 0.024205051362514496,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.0111,
      "step": 650
    },
    {
      "epoch": 1.6653858469420428,
      "eval_loss": 0.008477776311337948,
      "eval_runtime": 15.7954,
      "eval_samples_per_second": 6.331,
      "eval_steps_per_second": 1.583,
      "step": 650
    },
    {
      "epoch": 1.6679474863912904,
      "grad_norm": 0.021455738693475723,
      "learning_rate": 8.424692405644102e-05,
      "loss": 0.0076,
      "step": 651
    },
    {
      "epoch": 1.670509125840538,
      "grad_norm": 0.012590169906616211,
      "learning_rate": 8.418165647893931e-05,
      "loss": 0.0048,
      "step": 652
    },
    {
      "epoch": 1.6730707652897854,
      "grad_norm": 0.025595275685191154,
      "learning_rate": 8.411627937007433e-05,
      "loss": 0.0127,
      "step": 653
    },
    {
      "epoch": 1.675632404739033,
      "grad_norm": 0.02153213880956173,
      "learning_rate": 8.405079293933986e-05,
      "loss": 0.0086,
      "step": 654
    },
    {
      "epoch": 1.6781940441882806,
      "grad_norm": 0.03660966455936432,
      "learning_rate": 8.398519739657996e-05,
      "loss": 0.0196,
      "step": 655
    },
    {
      "epoch": 1.680755683637528,
      "grad_norm": 0.019230369478464127,
      "learning_rate": 8.391949295198836e-05,
      "loss": 0.0086,
      "step": 656
    },
    {
      "epoch": 1.6833173230867755,
      "grad_norm": 0.020435554906725883,
      "learning_rate": 8.38536798161077e-05,
      "loss": 0.0079,
      "step": 657
    },
    {
      "epoch": 1.685878962536023,
      "grad_norm": 0.03471748158335686,
      "learning_rate": 8.378775819982896e-05,
      "loss": 0.0216,
      "step": 658
    },
    {
      "epoch": 1.6884406019852705,
      "grad_norm": 0.026042545214295387,
      "learning_rate": 8.372172831439072e-05,
      "loss": 0.01,
      "step": 659
    },
    {
      "epoch": 1.691002241434518,
      "grad_norm": 0.021988200023770332,
      "learning_rate": 8.365559037137852e-05,
      "loss": 0.0081,
      "step": 660
    },
    {
      "epoch": 1.6935638808837656,
      "grad_norm": 0.020411528646945953,
      "learning_rate": 8.358934458272409e-05,
      "loss": 0.0089,
      "step": 661
    },
    {
      "epoch": 1.696125520333013,
      "grad_norm": 0.03231273591518402,
      "learning_rate": 8.352299116070481e-05,
      "loss": 0.0139,
      "step": 662
    },
    {
      "epoch": 1.6986871597822606,
      "grad_norm": 0.02595127373933792,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0046,
      "step": 663
    },
    {
      "epoch": 1.7012487992315082,
      "grad_norm": 0.02997523732483387,
      "learning_rate": 8.33899622674049e-05,
      "loss": 0.0136,
      "step": 664
    },
    {
      "epoch": 1.7038104386807555,
      "grad_norm": 0.020632093772292137,
      "learning_rate": 8.332328722240073e-05,
      "loss": 0.0101,
      "step": 665
    },
    {
      "epoch": 1.7063720781300034,
      "grad_norm": 0.016184786334633827,
      "learning_rate": 8.32565053965833e-05,
      "loss": 0.0069,
      "step": 666
    },
    {
      "epoch": 1.7089337175792507,
      "grad_norm": 0.02015138790011406,
      "learning_rate": 8.31896170039476e-05,
      "loss": 0.0093,
      "step": 667
    },
    {
      "epoch": 1.711495357028498,
      "grad_norm": 0.023183198645710945,
      "learning_rate": 8.312262225883019e-05,
      "loss": 0.0095,
      "step": 668
    },
    {
      "epoch": 1.714056996477746,
      "grad_norm": 0.02725174091756344,
      "learning_rate": 8.305552137590832e-05,
      "loss": 0.0146,
      "step": 669
    },
    {
      "epoch": 1.7166186359269933,
      "grad_norm": 0.022738030180335045,
      "learning_rate": 8.298831457019942e-05,
      "loss": 0.0081,
      "step": 670
    },
    {
      "epoch": 1.7191802753762406,
      "grad_norm": 0.018372569233179092,
      "learning_rate": 8.29210020570603e-05,
      "loss": 0.0071,
      "step": 671
    },
    {
      "epoch": 1.7217419148254884,
      "grad_norm": 0.03261580318212509,
      "learning_rate": 8.285358405218655e-05,
      "loss": 0.0257,
      "step": 672
    },
    {
      "epoch": 1.7243035542747358,
      "grad_norm": 0.03144574537873268,
      "learning_rate": 8.27860607716117e-05,
      "loss": 0.0147,
      "step": 673
    },
    {
      "epoch": 1.7268651937239834,
      "grad_norm": 0.019830984994769096,
      "learning_rate": 8.271843243170677e-05,
      "loss": 0.008,
      "step": 674
    },
    {
      "epoch": 1.729426833173231,
      "grad_norm": 0.01626870594918728,
      "learning_rate": 8.265069924917925e-05,
      "loss": 0.0075,
      "step": 675
    },
    {
      "epoch": 1.729426833173231,
      "eval_loss": 0.007765541784465313,
      "eval_runtime": 15.7645,
      "eval_samples_per_second": 6.343,
      "eval_steps_per_second": 1.586,
      "step": 675
    },
    {
      "epoch": 1.7319884726224783,
      "grad_norm": 0.030844878405332565,
      "learning_rate": 8.258286144107276e-05,
      "loss": 0.0109,
      "step": 676
    },
    {
      "epoch": 1.734550112071726,
      "grad_norm": 0.019611435011029243,
      "learning_rate": 8.251491922476609e-05,
      "loss": 0.0069,
      "step": 677
    },
    {
      "epoch": 1.7371117515209735,
      "grad_norm": 0.02465008571743965,
      "learning_rate": 8.244687281797255e-05,
      "loss": 0.0112,
      "step": 678
    },
    {
      "epoch": 1.739673390970221,
      "grad_norm": 0.015665439888834953,
      "learning_rate": 8.237872243873945e-05,
      "loss": 0.0059,
      "step": 679
    },
    {
      "epoch": 1.7422350304194685,
      "grad_norm": 0.02098284289240837,
      "learning_rate": 8.231046830544716e-05,
      "loss": 0.0078,
      "step": 680
    },
    {
      "epoch": 1.744796669868716,
      "grad_norm": 0.02483079396188259,
      "learning_rate": 8.224211063680853e-05,
      "loss": 0.0139,
      "step": 681
    },
    {
      "epoch": 1.7473583093179634,
      "grad_norm": 0.014874100685119629,
      "learning_rate": 8.217364965186824e-05,
      "loss": 0.0083,
      "step": 682
    },
    {
      "epoch": 1.749919948767211,
      "grad_norm": 0.017594069242477417,
      "learning_rate": 8.2105085570002e-05,
      "loss": 0.0092,
      "step": 683
    },
    {
      "epoch": 1.7524815882164586,
      "grad_norm": 0.01697852835059166,
      "learning_rate": 8.203641861091583e-05,
      "loss": 0.0077,
      "step": 684
    },
    {
      "epoch": 1.755043227665706,
      "grad_norm": 0.019407397136092186,
      "learning_rate": 8.196764899464551e-05,
      "loss": 0.0064,
      "step": 685
    },
    {
      "epoch": 1.7576048671149536,
      "grad_norm": 0.024107495322823524,
      "learning_rate": 8.189877694155568e-05,
      "loss": 0.0143,
      "step": 686
    },
    {
      "epoch": 1.7601665065642011,
      "grad_norm": 0.033490199595689774,
      "learning_rate": 8.182980267233929e-05,
      "loss": 0.0077,
      "step": 687
    },
    {
      "epoch": 1.7627281460134485,
      "grad_norm": 0.02660991996526718,
      "learning_rate": 8.17607264080168e-05,
      "loss": 0.0087,
      "step": 688
    },
    {
      "epoch": 1.765289785462696,
      "grad_norm": 0.020847605541348457,
      "learning_rate": 8.169154836993551e-05,
      "loss": 0.0085,
      "step": 689
    },
    {
      "epoch": 1.7678514249119437,
      "grad_norm": 0.01973964460194111,
      "learning_rate": 8.162226877976887e-05,
      "loss": 0.0083,
      "step": 690
    },
    {
      "epoch": 1.770413064361191,
      "grad_norm": 0.01618560589849949,
      "learning_rate": 8.155288785951569e-05,
      "loss": 0.009,
      "step": 691
    },
    {
      "epoch": 1.7729747038104386,
      "grad_norm": 0.0218571238219738,
      "learning_rate": 8.148340583149949e-05,
      "loss": 0.0088,
      "step": 692
    },
    {
      "epoch": 1.7755363432596862,
      "grad_norm": 0.015629569068551064,
      "learning_rate": 8.141382291836784e-05,
      "loss": 0.0062,
      "step": 693
    },
    {
      "epoch": 1.7780979827089336,
      "grad_norm": 0.01955568976700306,
      "learning_rate": 8.134413934309151e-05,
      "loss": 0.0107,
      "step": 694
    },
    {
      "epoch": 1.7806596221581812,
      "grad_norm": 0.028023671358823776,
      "learning_rate": 8.127435532896388e-05,
      "loss": 0.0139,
      "step": 695
    },
    {
      "epoch": 1.7832212616074288,
      "grad_norm": 0.018414363265037537,
      "learning_rate": 8.120447109960014e-05,
      "loss": 0.0082,
      "step": 696
    },
    {
      "epoch": 1.7857829010566761,
      "grad_norm": 0.024728137999773026,
      "learning_rate": 8.113448687893664e-05,
      "loss": 0.0111,
      "step": 697
    },
    {
      "epoch": 1.788344540505924,
      "grad_norm": 0.04410293325781822,
      "learning_rate": 8.106440289123011e-05,
      "loss": 0.0265,
      "step": 698
    },
    {
      "epoch": 1.7909061799551713,
      "grad_norm": 0.012759803794324398,
      "learning_rate": 8.099421936105702e-05,
      "loss": 0.0047,
      "step": 699
    },
    {
      "epoch": 1.7934678194044187,
      "grad_norm": 0.017002368345856667,
      "learning_rate": 8.092393651331275e-05,
      "loss": 0.0077,
      "step": 700
    },
    {
      "epoch": 1.7934678194044187,
      "eval_loss": 0.008254488930106163,
      "eval_runtime": 15.7858,
      "eval_samples_per_second": 6.335,
      "eval_steps_per_second": 1.584,
      "step": 700
    },
    {
      "epoch": 1.7960294588536665,
      "grad_norm": 0.017149921506643295,
      "learning_rate": 8.085355457321098e-05,
      "loss": 0.0085,
      "step": 701
    },
    {
      "epoch": 1.7985910983029139,
      "grad_norm": 0.013030176050961018,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0058,
      "step": 702
    },
    {
      "epoch": 1.8011527377521612,
      "grad_norm": 0.02273356355726719,
      "learning_rate": 8.071249431837655e-05,
      "loss": 0.0071,
      "step": 703
    },
    {
      "epoch": 1.803714377201409,
      "grad_norm": 0.017565427348017693,
      "learning_rate": 8.064181645565596e-05,
      "loss": 0.0093,
      "step": 704
    },
    {
      "epoch": 1.8062760166506564,
      "grad_norm": 0.019855517894029617,
      "learning_rate": 8.057104040460062e-05,
      "loss": 0.0113,
      "step": 705
    },
    {
      "epoch": 1.808837656099904,
      "grad_norm": 0.014578789472579956,
      "learning_rate": 8.050016639200458e-05,
      "loss": 0.0068,
      "step": 706
    },
    {
      "epoch": 1.8113992955491516,
      "grad_norm": 0.02611469104886055,
      "learning_rate": 8.042919464497584e-05,
      "loss": 0.0173,
      "step": 707
    },
    {
      "epoch": 1.813960934998399,
      "grad_norm": 0.017057769000530243,
      "learning_rate": 8.035812539093557e-05,
      "loss": 0.0088,
      "step": 708
    },
    {
      "epoch": 1.8165225744476465,
      "grad_norm": 0.01934835873544216,
      "learning_rate": 8.028695885761738e-05,
      "loss": 0.0103,
      "step": 709
    },
    {
      "epoch": 1.8190842138968941,
      "grad_norm": 0.026960475370287895,
      "learning_rate": 8.021569527306662e-05,
      "loss": 0.0161,
      "step": 710
    },
    {
      "epoch": 1.8216458533461415,
      "grad_norm": 0.022418903186917305,
      "learning_rate": 8.014433486563961e-05,
      "loss": 0.0072,
      "step": 711
    },
    {
      "epoch": 1.824207492795389,
      "grad_norm": 0.017390521243214607,
      "learning_rate": 8.007287786400295e-05,
      "loss": 0.0063,
      "step": 712
    },
    {
      "epoch": 1.8267691322446367,
      "grad_norm": 0.018205352127552032,
      "learning_rate": 8.000132449713272e-05,
      "loss": 0.0089,
      "step": 713
    },
    {
      "epoch": 1.829330771693884,
      "grad_norm": 0.025925058871507645,
      "learning_rate": 7.992967499431386e-05,
      "loss": 0.0182,
      "step": 714
    },
    {
      "epoch": 1.8318924111431316,
      "grad_norm": 0.025157589465379715,
      "learning_rate": 7.985792958513931e-05,
      "loss": 0.0093,
      "step": 715
    },
    {
      "epoch": 1.8344540505923792,
      "grad_norm": 0.024524198845028877,
      "learning_rate": 7.978608849950935e-05,
      "loss": 0.0099,
      "step": 716
    },
    {
      "epoch": 1.8370156900416266,
      "grad_norm": 0.02669604681432247,
      "learning_rate": 7.971415196763088e-05,
      "loss": 0.0134,
      "step": 717
    },
    {
      "epoch": 1.8395773294908742,
      "grad_norm": 0.016144055873155594,
      "learning_rate": 7.964212022001658e-05,
      "loss": 0.0086,
      "step": 718
    },
    {
      "epoch": 1.8421389689401217,
      "grad_norm": 0.019035059958696365,
      "learning_rate": 7.956999348748427e-05,
      "loss": 0.0089,
      "step": 719
    },
    {
      "epoch": 1.8447006083893691,
      "grad_norm": 0.026147911325097084,
      "learning_rate": 7.949777200115616e-05,
      "loss": 0.0095,
      "step": 720
    },
    {
      "epoch": 1.8472622478386167,
      "grad_norm": 0.01551744807511568,
      "learning_rate": 7.942545599245805e-05,
      "loss": 0.0071,
      "step": 721
    },
    {
      "epoch": 1.8498238872878643,
      "grad_norm": 0.02032046765089035,
      "learning_rate": 7.935304569311867e-05,
      "loss": 0.0088,
      "step": 722
    },
    {
      "epoch": 1.8523855267371117,
      "grad_norm": 0.014912649989128113,
      "learning_rate": 7.928054133516884e-05,
      "loss": 0.0062,
      "step": 723
    },
    {
      "epoch": 1.8549471661863592,
      "grad_norm": 0.021932363510131836,
      "learning_rate": 7.920794315094084e-05,
      "loss": 0.0129,
      "step": 724
    },
    {
      "epoch": 1.8575088056356068,
      "grad_norm": 0.023239847272634506,
      "learning_rate": 7.913525137306756e-05,
      "loss": 0.0105,
      "step": 725
    },
    {
      "epoch": 1.8575088056356068,
      "eval_loss": 0.00722088199108839,
      "eval_runtime": 15.8215,
      "eval_samples_per_second": 6.321,
      "eval_steps_per_second": 1.58,
      "step": 725
    },
    {
      "epoch": 1.8600704450848542,
      "grad_norm": 0.014573454856872559,
      "learning_rate": 7.906246623448183e-05,
      "loss": 0.0066,
      "step": 726
    },
    {
      "epoch": 1.8626320845341018,
      "grad_norm": 0.017306188121438026,
      "learning_rate": 7.898958796841563e-05,
      "loss": 0.007,
      "step": 727
    },
    {
      "epoch": 1.8651937239833494,
      "grad_norm": 0.02267426811158657,
      "learning_rate": 7.891661680839932e-05,
      "loss": 0.01,
      "step": 728
    },
    {
      "epoch": 1.8677553634325967,
      "grad_norm": 0.0263497456908226,
      "learning_rate": 7.884355298826102e-05,
      "loss": 0.0114,
      "step": 729
    },
    {
      "epoch": 1.8703170028818443,
      "grad_norm": 0.020164979621767998,
      "learning_rate": 7.877039674212569e-05,
      "loss": 0.0081,
      "step": 730
    },
    {
      "epoch": 1.872878642331092,
      "grad_norm": 0.013917827978730202,
      "learning_rate": 7.869714830441448e-05,
      "loss": 0.006,
      "step": 731
    },
    {
      "epoch": 1.8754402817803393,
      "grad_norm": 0.027471866458654404,
      "learning_rate": 7.862380790984396e-05,
      "loss": 0.0115,
      "step": 732
    },
    {
      "epoch": 1.878001921229587,
      "grad_norm": 0.022532496601343155,
      "learning_rate": 7.855037579342539e-05,
      "loss": 0.0094,
      "step": 733
    },
    {
      "epoch": 1.8805635606788345,
      "grad_norm": 0.01607378013432026,
      "learning_rate": 7.84768521904639e-05,
      "loss": 0.0055,
      "step": 734
    },
    {
      "epoch": 1.8831252001280818,
      "grad_norm": 0.016221843659877777,
      "learning_rate": 7.840323733655778e-05,
      "loss": 0.0075,
      "step": 735
    },
    {
      "epoch": 1.8856868395773296,
      "grad_norm": 0.03252291679382324,
      "learning_rate": 7.832953146759781e-05,
      "loss": 0.0171,
      "step": 736
    },
    {
      "epoch": 1.888248479026577,
      "grad_norm": 0.021966032683849335,
      "learning_rate": 7.825573481976629e-05,
      "loss": 0.0082,
      "step": 737
    },
    {
      "epoch": 1.8908101184758244,
      "grad_norm": 0.021348660811781883,
      "learning_rate": 7.818184762953648e-05,
      "loss": 0.0074,
      "step": 738
    },
    {
      "epoch": 1.8933717579250722,
      "grad_norm": 0.03429243341088295,
      "learning_rate": 7.810787013367178e-05,
      "loss": 0.0161,
      "step": 739
    },
    {
      "epoch": 1.8959333973743195,
      "grad_norm": 0.019160069525241852,
      "learning_rate": 7.803380256922495e-05,
      "loss": 0.0096,
      "step": 740
    },
    {
      "epoch": 1.8984950368235671,
      "grad_norm": 0.019925393164157867,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0073,
      "step": 741
    },
    {
      "epoch": 1.9010566762728147,
      "grad_norm": 0.02276492677628994,
      "learning_rate": 7.788539818423822e-05,
      "loss": 0.0084,
      "step": 742
    },
    {
      "epoch": 1.903618315722062,
      "grad_norm": 0.025005770847201347,
      "learning_rate": 7.781106183924385e-05,
      "loss": 0.0095,
      "step": 743
    },
    {
      "epoch": 1.9061799551713097,
      "grad_norm": 0.0237042848020792,
      "learning_rate": 7.773663637675694e-05,
      "loss": 0.0115,
      "step": 744
    },
    {
      "epoch": 1.9087415946205573,
      "grad_norm": 0.02170964702963829,
      "learning_rate": 7.76621220352657e-05,
      "loss": 0.0112,
      "step": 745
    },
    {
      "epoch": 1.9113032340698046,
      "grad_norm": 0.01486461516469717,
      "learning_rate": 7.758751905354311e-05,
      "loss": 0.0058,
      "step": 746
    },
    {
      "epoch": 1.9138648735190522,
      "grad_norm": 0.018541356548666954,
      "learning_rate": 7.751282767064627e-05,
      "loss": 0.0087,
      "step": 747
    },
    {
      "epoch": 1.9164265129682998,
      "grad_norm": 0.016604872420430183,
      "learning_rate": 7.74380481259155e-05,
      "loss": 0.0066,
      "step": 748
    },
    {
      "epoch": 1.9189881524175472,
      "grad_norm": 0.022073280066251755,
      "learning_rate": 7.736318065897362e-05,
      "loss": 0.0114,
      "step": 749
    },
    {
      "epoch": 1.9215497918667948,
      "grad_norm": 0.021899666637182236,
      "learning_rate": 7.728822550972523e-05,
      "loss": 0.0089,
      "step": 750
    },
    {
      "epoch": 1.9215497918667948,
      "eval_loss": 0.0077704195864498615,
      "eval_runtime": 15.7892,
      "eval_samples_per_second": 6.333,
      "eval_steps_per_second": 1.583,
      "step": 750
    },
    {
      "epoch": 1.9241114313160423,
      "grad_norm": 0.024171432480216026,
      "learning_rate": 7.721318291835586e-05,
      "loss": 0.0084,
      "step": 751
    },
    {
      "epoch": 1.9266730707652897,
      "grad_norm": 0.027852538973093033,
      "learning_rate": 7.713805312533126e-05,
      "loss": 0.0116,
      "step": 752
    },
    {
      "epoch": 1.9292347102145373,
      "grad_norm": 0.02583443932235241,
      "learning_rate": 7.706283637139658e-05,
      "loss": 0.01,
      "step": 753
    },
    {
      "epoch": 1.9317963496637849,
      "grad_norm": 0.022306324914097786,
      "learning_rate": 7.698753289757565e-05,
      "loss": 0.0111,
      "step": 754
    },
    {
      "epoch": 1.9343579891130323,
      "grad_norm": 0.023564163595438004,
      "learning_rate": 7.69121429451702e-05,
      "loss": 0.0094,
      "step": 755
    },
    {
      "epoch": 1.9369196285622798,
      "grad_norm": 0.02647082880139351,
      "learning_rate": 7.683666675575901e-05,
      "loss": 0.0131,
      "step": 756
    },
    {
      "epoch": 1.9394812680115274,
      "grad_norm": 0.021390896290540695,
      "learning_rate": 7.676110457119727e-05,
      "loss": 0.0073,
      "step": 757
    },
    {
      "epoch": 1.9420429074607748,
      "grad_norm": 0.022772209718823433,
      "learning_rate": 7.66854566336157e-05,
      "loss": 0.0107,
      "step": 758
    },
    {
      "epoch": 1.9446045469100224,
      "grad_norm": 0.021806808188557625,
      "learning_rate": 7.660972318541982e-05,
      "loss": 0.0104,
      "step": 759
    },
    {
      "epoch": 1.94716618635927,
      "grad_norm": 0.03225119784474373,
      "learning_rate": 7.653390446928909e-05,
      "loss": 0.0206,
      "step": 760
    },
    {
      "epoch": 1.9497278258085173,
      "grad_norm": 0.03250499814748764,
      "learning_rate": 7.64580007281763e-05,
      "loss": 0.0158,
      "step": 761
    },
    {
      "epoch": 1.952289465257765,
      "grad_norm": 0.023754483088850975,
      "learning_rate": 7.638201220530665e-05,
      "loss": 0.0119,
      "step": 762
    },
    {
      "epoch": 1.9548511047070125,
      "grad_norm": 0.014481264166533947,
      "learning_rate": 7.630593914417699e-05,
      "loss": 0.0063,
      "step": 763
    },
    {
      "epoch": 1.9574127441562599,
      "grad_norm": 0.02314913645386696,
      "learning_rate": 7.622978178855511e-05,
      "loss": 0.0126,
      "step": 764
    },
    {
      "epoch": 1.9599743836055077,
      "grad_norm": 0.025454895570874214,
      "learning_rate": 7.615354038247888e-05,
      "loss": 0.0097,
      "step": 765
    },
    {
      "epoch": 1.962536023054755,
      "grad_norm": 0.02636459842324257,
      "learning_rate": 7.607721517025552e-05,
      "loss": 0.0077,
      "step": 766
    },
    {
      "epoch": 1.9650976625040024,
      "grad_norm": 0.024306008592247963,
      "learning_rate": 7.600080639646077e-05,
      "loss": 0.0096,
      "step": 767
    },
    {
      "epoch": 1.9676593019532502,
      "grad_norm": 0.017479566857218742,
      "learning_rate": 7.592431430593818e-05,
      "loss": 0.0062,
      "step": 768
    },
    {
      "epoch": 1.9702209414024976,
      "grad_norm": 0.023251403123140335,
      "learning_rate": 7.584773914379823e-05,
      "loss": 0.0125,
      "step": 769
    },
    {
      "epoch": 1.972782580851745,
      "grad_norm": 0.019164303317666054,
      "learning_rate": 7.577108115541761e-05,
      "loss": 0.009,
      "step": 770
    },
    {
      "epoch": 1.9753442203009928,
      "grad_norm": 0.016869869083166122,
      "learning_rate": 7.569434058643844e-05,
      "loss": 0.0085,
      "step": 771
    },
    {
      "epoch": 1.9779058597502401,
      "grad_norm": 0.02194080501794815,
      "learning_rate": 7.561751768276744e-05,
      "loss": 0.0107,
      "step": 772
    },
    {
      "epoch": 1.9804674991994877,
      "grad_norm": 0.019984381273388863,
      "learning_rate": 7.554061269057515e-05,
      "loss": 0.0098,
      "step": 773
    },
    {
      "epoch": 1.9830291386487353,
      "grad_norm": 0.013338621705770493,
      "learning_rate": 7.546362585629518e-05,
      "loss": 0.0052,
      "step": 774
    },
    {
      "epoch": 1.9855907780979827,
      "grad_norm": 0.028268542140722275,
      "learning_rate": 7.53865574266234e-05,
      "loss": 0.0132,
      "step": 775
    },
    {
      "epoch": 1.9855907780979827,
      "eval_loss": 0.008421124890446663,
      "eval_runtime": 15.7765,
      "eval_samples_per_second": 6.339,
      "eval_steps_per_second": 1.585,
      "step": 775
    },
    {
      "epoch": 1.9881524175472303,
      "grad_norm": 0.015591204166412354,
      "learning_rate": 7.530940764851708e-05,
      "loss": 0.0083,
      "step": 776
    },
    {
      "epoch": 1.9907140569964779,
      "grad_norm": 0.01851005293428898,
      "learning_rate": 7.523217676919427e-05,
      "loss": 0.0078,
      "step": 777
    },
    {
      "epoch": 1.9932756964457252,
      "grad_norm": 0.014990904368460178,
      "learning_rate": 7.515486503613278e-05,
      "loss": 0.0061,
      "step": 778
    },
    {
      "epoch": 1.9958373358949728,
      "grad_norm": 0.018165841698646545,
      "learning_rate": 7.507747269706962e-05,
      "loss": 0.0073,
      "step": 779
    },
    {
      "epoch": 1.9983989753442204,
      "grad_norm": 0.021395908668637276,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0084,
      "step": 780
    },
    {
      "epoch": 2.0012808197246237,
      "grad_norm": 0.12048190832138062,
      "learning_rate": 7.492244719317668e-05,
      "loss": 0.0199,
      "step": 781
    },
    {
      "epoch": 2.0038424591738715,
      "grad_norm": 0.027717135846614838,
      "learning_rate": 7.484481452510913e-05,
      "loss": 0.0102,
      "step": 782
    },
    {
      "epoch": 2.006404098623119,
      "grad_norm": 0.036011483520269394,
      "learning_rate": 7.476710224456267e-05,
      "loss": 0.0092,
      "step": 783
    },
    {
      "epoch": 2.0089657380723662,
      "grad_norm": 0.030577300116419792,
      "learning_rate": 7.468931060055777e-05,
      "loss": 0.0082,
      "step": 784
    },
    {
      "epoch": 2.011527377521614,
      "grad_norm": 0.033715181052684784,
      "learning_rate": 7.461143984236924e-05,
      "loss": 0.0123,
      "step": 785
    },
    {
      "epoch": 2.0140890169708614,
      "grad_norm": 0.01578759402036667,
      "learning_rate": 7.453349021952533e-05,
      "loss": 0.0049,
      "step": 786
    },
    {
      "epoch": 2.0166506564201088,
      "grad_norm": 0.017665740102529526,
      "learning_rate": 7.44554619818071e-05,
      "loss": 0.0078,
      "step": 787
    },
    {
      "epoch": 2.0192122958693566,
      "grad_norm": 0.0218870397657156,
      "learning_rate": 7.437735537924742e-05,
      "loss": 0.0073,
      "step": 788
    },
    {
      "epoch": 2.021773935318604,
      "grad_norm": 0.02893979661166668,
      "learning_rate": 7.42991706621303e-05,
      "loss": 0.01,
      "step": 789
    },
    {
      "epoch": 2.0243355747678513,
      "grad_norm": 0.03510141000151634,
      "learning_rate": 7.422090808099014e-05,
      "loss": 0.0101,
      "step": 790
    },
    {
      "epoch": 2.026897214217099,
      "grad_norm": 0.020581314340233803,
      "learning_rate": 7.414256788661074e-05,
      "loss": 0.0069,
      "step": 791
    },
    {
      "epoch": 2.0294588536663465,
      "grad_norm": 0.025523610413074493,
      "learning_rate": 7.406415033002463e-05,
      "loss": 0.0094,
      "step": 792
    },
    {
      "epoch": 2.032020493115594,
      "grad_norm": 0.017144009470939636,
      "learning_rate": 7.398565566251232e-05,
      "loss": 0.005,
      "step": 793
    },
    {
      "epoch": 2.0345821325648417,
      "grad_norm": 0.02107195369899273,
      "learning_rate": 7.390708413560129e-05,
      "loss": 0.0072,
      "step": 794
    },
    {
      "epoch": 2.037143772014089,
      "grad_norm": 0.012858357280492783,
      "learning_rate": 7.38284360010654e-05,
      "loss": 0.0036,
      "step": 795
    },
    {
      "epoch": 2.0397054114633364,
      "grad_norm": 0.04638303071260452,
      "learning_rate": 7.374971151092395e-05,
      "loss": 0.0129,
      "step": 796
    },
    {
      "epoch": 2.042267050912584,
      "grad_norm": 0.03213483840227127,
      "learning_rate": 7.367091091744089e-05,
      "loss": 0.0083,
      "step": 797
    },
    {
      "epoch": 2.0448286903618316,
      "grad_norm": 0.021228497847914696,
      "learning_rate": 7.35920344731241e-05,
      "loss": 0.0069,
      "step": 798
    },
    {
      "epoch": 2.047390329811079,
      "grad_norm": 0.037191636860370636,
      "learning_rate": 7.35130824307245e-05,
      "loss": 0.0097,
      "step": 799
    },
    {
      "epoch": 2.0499519692603267,
      "grad_norm": 0.026018405333161354,
      "learning_rate": 7.343405504323519e-05,
      "loss": 0.0104,
      "step": 800
    },
    {
      "epoch": 2.0499519692603267,
      "eval_loss": 0.009080244228243828,
      "eval_runtime": 15.7393,
      "eval_samples_per_second": 6.354,
      "eval_steps_per_second": 1.588,
      "step": 800
    },
    {
      "epoch": 2.052513608709574,
      "grad_norm": 0.02520827390253544,
      "learning_rate": 7.335495256389078e-05,
      "loss": 0.0063,
      "step": 801
    },
    {
      "epoch": 2.0550752481588215,
      "grad_norm": 0.03224215283989906,
      "learning_rate": 7.327577524616646e-05,
      "loss": 0.0122,
      "step": 802
    },
    {
      "epoch": 2.0576368876080693,
      "grad_norm": 0.02962084673345089,
      "learning_rate": 7.319652334377725e-05,
      "loss": 0.0105,
      "step": 803
    },
    {
      "epoch": 2.0601985270573167,
      "grad_norm": 0.019580401480197906,
      "learning_rate": 7.311719711067717e-05,
      "loss": 0.0062,
      "step": 804
    },
    {
      "epoch": 2.062760166506564,
      "grad_norm": 0.03741897642612457,
      "learning_rate": 7.303779680105843e-05,
      "loss": 0.0133,
      "step": 805
    },
    {
      "epoch": 2.065321805955812,
      "grad_norm": 0.02220587432384491,
      "learning_rate": 7.295832266935059e-05,
      "loss": 0.0096,
      "step": 806
    },
    {
      "epoch": 2.067883445405059,
      "grad_norm": 0.020196085795760155,
      "learning_rate": 7.287877497021978e-05,
      "loss": 0.01,
      "step": 807
    },
    {
      "epoch": 2.0704450848543066,
      "grad_norm": 0.014655430801212788,
      "learning_rate": 7.279915395856782e-05,
      "loss": 0.0047,
      "step": 808
    },
    {
      "epoch": 2.0730067243035544,
      "grad_norm": 0.026845693588256836,
      "learning_rate": 7.271945988953157e-05,
      "loss": 0.0089,
      "step": 809
    },
    {
      "epoch": 2.0755683637528017,
      "grad_norm": 0.024815455079078674,
      "learning_rate": 7.263969301848188e-05,
      "loss": 0.0069,
      "step": 810
    },
    {
      "epoch": 2.078130003202049,
      "grad_norm": 0.026393510401248932,
      "learning_rate": 7.255985360102291e-05,
      "loss": 0.0083,
      "step": 811
    },
    {
      "epoch": 2.080691642651297,
      "grad_norm": 0.015269361436367035,
      "learning_rate": 7.247994189299132e-05,
      "loss": 0.0045,
      "step": 812
    },
    {
      "epoch": 2.0832532821005443,
      "grad_norm": 0.020210297778248787,
      "learning_rate": 7.239995815045542e-05,
      "loss": 0.008,
      "step": 813
    },
    {
      "epoch": 2.085814921549792,
      "grad_norm": 0.027442224323749542,
      "learning_rate": 7.231990262971428e-05,
      "loss": 0.0121,
      "step": 814
    },
    {
      "epoch": 2.0883765609990395,
      "grad_norm": 0.023403724655508995,
      "learning_rate": 7.223977558729706e-05,
      "loss": 0.0091,
      "step": 815
    },
    {
      "epoch": 2.090938200448287,
      "grad_norm": 0.034363970160484314,
      "learning_rate": 7.215957727996207e-05,
      "loss": 0.0104,
      "step": 816
    },
    {
      "epoch": 2.0934998398975346,
      "grad_norm": 0.0232424046844244,
      "learning_rate": 7.207930796469595e-05,
      "loss": 0.0088,
      "step": 817
    },
    {
      "epoch": 2.096061479346782,
      "grad_norm": 0.02351643331348896,
      "learning_rate": 7.19989678987129e-05,
      "loss": 0.0128,
      "step": 818
    },
    {
      "epoch": 2.0986231187960294,
      "grad_norm": 0.02835538238286972,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0108,
      "step": 819
    },
    {
      "epoch": 2.101184758245277,
      "grad_norm": 0.019840311259031296,
      "learning_rate": 7.183807654458564e-05,
      "loss": 0.0064,
      "step": 820
    },
    {
      "epoch": 2.1037463976945245,
      "grad_norm": 0.022916074842214584,
      "learning_rate": 7.175752577200007e-05,
      "loss": 0.009,
      "step": 821
    },
    {
      "epoch": 2.106308037143772,
      "grad_norm": 0.019078776240348816,
      "learning_rate": 7.167690527981328e-05,
      "loss": 0.0058,
      "step": 822
    },
    {
      "epoch": 2.1088696765930197,
      "grad_norm": 0.018315337598323822,
      "learning_rate": 7.159621532636477e-05,
      "loss": 0.006,
      "step": 823
    },
    {
      "epoch": 2.111431316042267,
      "grad_norm": 0.027668718248605728,
      "learning_rate": 7.151545617021663e-05,
      "loss": 0.0109,
      "step": 824
    },
    {
      "epoch": 2.1139929554915144,
      "grad_norm": 0.025120360776782036,
      "learning_rate": 7.143462807015271e-05,
      "loss": 0.0084,
      "step": 825
    },
    {
      "epoch": 2.1139929554915144,
      "eval_loss": 0.008172542788088322,
      "eval_runtime": 15.7492,
      "eval_samples_per_second": 6.35,
      "eval_steps_per_second": 1.587,
      "step": 825
    },
    {
      "epoch": 2.1165545949407623,
      "grad_norm": 0.01747150532901287,
      "learning_rate": 7.135373128517778e-05,
      "loss": 0.0066,
      "step": 826
    },
    {
      "epoch": 2.1191162343900096,
      "grad_norm": 0.024094821885228157,
      "learning_rate": 7.12727660745167e-05,
      "loss": 0.0124,
      "step": 827
    },
    {
      "epoch": 2.121677873839257,
      "grad_norm": 0.03347666934132576,
      "learning_rate": 7.119173269761358e-05,
      "loss": 0.0149,
      "step": 828
    },
    {
      "epoch": 2.124239513288505,
      "grad_norm": 0.01727481372654438,
      "learning_rate": 7.111063141413098e-05,
      "loss": 0.0047,
      "step": 829
    },
    {
      "epoch": 2.126801152737752,
      "grad_norm": 0.052980441600084305,
      "learning_rate": 7.102946248394909e-05,
      "loss": 0.0136,
      "step": 830
    },
    {
      "epoch": 2.1293627921869995,
      "grad_norm": 0.02497376874089241,
      "learning_rate": 7.094822616716476e-05,
      "loss": 0.0096,
      "step": 831
    },
    {
      "epoch": 2.1319244316362473,
      "grad_norm": 0.025692777708172798,
      "learning_rate": 7.08669227240909e-05,
      "loss": 0.0062,
      "step": 832
    },
    {
      "epoch": 2.1344860710854947,
      "grad_norm": 0.019108694046735764,
      "learning_rate": 7.078555241525545e-05,
      "loss": 0.0075,
      "step": 833
    },
    {
      "epoch": 2.137047710534742,
      "grad_norm": 0.020909873768687248,
      "learning_rate": 7.07041155014006e-05,
      "loss": 0.0082,
      "step": 834
    },
    {
      "epoch": 2.13960934998399,
      "grad_norm": 0.02559494785964489,
      "learning_rate": 7.062261224348203e-05,
      "loss": 0.0103,
      "step": 835
    },
    {
      "epoch": 2.1421709894332372,
      "grad_norm": 0.02691330574452877,
      "learning_rate": 7.054104290266796e-05,
      "loss": 0.0079,
      "step": 836
    },
    {
      "epoch": 2.1447326288824846,
      "grad_norm": 0.01753104105591774,
      "learning_rate": 7.045940774033838e-05,
      "loss": 0.0062,
      "step": 837
    },
    {
      "epoch": 2.1472942683317324,
      "grad_norm": 0.011550121009349823,
      "learning_rate": 7.037770701808421e-05,
      "loss": 0.0036,
      "step": 838
    },
    {
      "epoch": 2.14985590778098,
      "grad_norm": 0.027242513373494148,
      "learning_rate": 7.029594099770642e-05,
      "loss": 0.0062,
      "step": 839
    },
    {
      "epoch": 2.152417547230227,
      "grad_norm": 0.019376887008547783,
      "learning_rate": 7.021410994121525e-05,
      "loss": 0.0072,
      "step": 840
    },
    {
      "epoch": 2.154979186679475,
      "grad_norm": 0.012071039527654648,
      "learning_rate": 7.013221411082935e-05,
      "loss": 0.0038,
      "step": 841
    },
    {
      "epoch": 2.1575408261287223,
      "grad_norm": 0.018893806263804436,
      "learning_rate": 7.005025376897489e-05,
      "loss": 0.0054,
      "step": 842
    },
    {
      "epoch": 2.1601024655779697,
      "grad_norm": 0.01803342066705227,
      "learning_rate": 6.996822917828477e-05,
      "loss": 0.0065,
      "step": 843
    },
    {
      "epoch": 2.1626641050272175,
      "grad_norm": 0.017229989171028137,
      "learning_rate": 6.988614060159783e-05,
      "loss": 0.0039,
      "step": 844
    },
    {
      "epoch": 2.165225744476465,
      "grad_norm": 0.024557722732424736,
      "learning_rate": 6.980398830195785e-05,
      "loss": 0.006,
      "step": 845
    },
    {
      "epoch": 2.1677873839257122,
      "grad_norm": 0.025856252759695053,
      "learning_rate": 6.972177254261287e-05,
      "loss": 0.0072,
      "step": 846
    },
    {
      "epoch": 2.17034902337496,
      "grad_norm": 0.014871695078909397,
      "learning_rate": 6.963949358701424e-05,
      "loss": 0.0057,
      "step": 847
    },
    {
      "epoch": 2.1729106628242074,
      "grad_norm": 0.020170217379927635,
      "learning_rate": 6.955715169881585e-05,
      "loss": 0.0061,
      "step": 848
    },
    {
      "epoch": 2.1754723022734552,
      "grad_norm": 0.021420400589704514,
      "learning_rate": 6.947474714187324e-05,
      "loss": 0.0061,
      "step": 849
    },
    {
      "epoch": 2.1780339417227026,
      "grad_norm": 0.02425125241279602,
      "learning_rate": 6.939228018024275e-05,
      "loss": 0.0081,
      "step": 850
    },
    {
      "epoch": 2.1780339417227026,
      "eval_loss": 0.008289722725749016,
      "eval_runtime": 15.7617,
      "eval_samples_per_second": 6.344,
      "eval_steps_per_second": 1.586,
      "step": 850
    },
    {
      "epoch": 2.18059558117195,
      "grad_norm": 0.015109110623598099,
      "learning_rate": 6.93097510781807e-05,
      "loss": 0.0057,
      "step": 851
    },
    {
      "epoch": 2.1831572206211978,
      "grad_norm": 0.020135734230279922,
      "learning_rate": 6.922716010014255e-05,
      "loss": 0.0079,
      "step": 852
    },
    {
      "epoch": 2.185718860070445,
      "grad_norm": 0.020137479528784752,
      "learning_rate": 6.914450751078199e-05,
      "loss": 0.0099,
      "step": 853
    },
    {
      "epoch": 2.1882804995196925,
      "grad_norm": 0.015187174081802368,
      "learning_rate": 6.906179357495016e-05,
      "loss": 0.0066,
      "step": 854
    },
    {
      "epoch": 2.1908421389689403,
      "grad_norm": 0.017928671091794968,
      "learning_rate": 6.897901855769483e-05,
      "loss": 0.0065,
      "step": 855
    },
    {
      "epoch": 2.1934037784181877,
      "grad_norm": 0.022515594959259033,
      "learning_rate": 6.88961827242594e-05,
      "loss": 0.0093,
      "step": 856
    },
    {
      "epoch": 2.195965417867435,
      "grad_norm": 0.019031262025237083,
      "learning_rate": 6.88132863400822e-05,
      "loss": 0.0078,
      "step": 857
    },
    {
      "epoch": 2.198527057316683,
      "grad_norm": 0.018223704770207405,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0081,
      "step": 858
    },
    {
      "epoch": 2.20108869676593,
      "grad_norm": 0.024755829945206642,
      "learning_rate": 6.864731298222515e-05,
      "loss": 0.0078,
      "step": 859
    },
    {
      "epoch": 2.2036503362151776,
      "grad_norm": 0.01624191738665104,
      "learning_rate": 6.856423654038868e-05,
      "loss": 0.0049,
      "step": 860
    },
    {
      "epoch": 2.2062119756644254,
      "grad_norm": 0.01638570800423622,
      "learning_rate": 6.848110061149556e-05,
      "loss": 0.006,
      "step": 861
    },
    {
      "epoch": 2.2087736151136728,
      "grad_norm": 0.01753126084804535,
      "learning_rate": 6.839790546194569e-05,
      "loss": 0.0064,
      "step": 862
    },
    {
      "epoch": 2.21133525456292,
      "grad_norm": 0.02570418082177639,
      "learning_rate": 6.831465135832883e-05,
      "loss": 0.0077,
      "step": 863
    },
    {
      "epoch": 2.213896894012168,
      "grad_norm": 0.03022204339504242,
      "learning_rate": 6.823133856742359e-05,
      "loss": 0.0122,
      "step": 864
    },
    {
      "epoch": 2.2164585334614153,
      "grad_norm": 0.021783053874969482,
      "learning_rate": 6.814796735619663e-05,
      "loss": 0.0064,
      "step": 865
    },
    {
      "epoch": 2.2190201729106627,
      "grad_norm": 0.0161015372723341,
      "learning_rate": 6.806453799180191e-05,
      "loss": 0.0052,
      "step": 866
    },
    {
      "epoch": 2.2215818123599105,
      "grad_norm": 0.01819256693124771,
      "learning_rate": 6.798105074157958e-05,
      "loss": 0.0078,
      "step": 867
    },
    {
      "epoch": 2.224143451809158,
      "grad_norm": 0.015615181997418404,
      "learning_rate": 6.789750587305544e-05,
      "loss": 0.0053,
      "step": 868
    },
    {
      "epoch": 2.226705091258405,
      "grad_norm": 0.026892973110079765,
      "learning_rate": 6.78139036539398e-05,
      "loss": 0.0075,
      "step": 869
    },
    {
      "epoch": 2.229266730707653,
      "grad_norm": 0.02187221497297287,
      "learning_rate": 6.773024435212678e-05,
      "loss": 0.0064,
      "step": 870
    },
    {
      "epoch": 2.2318283701569004,
      "grad_norm": 0.0163852721452713,
      "learning_rate": 6.764652823569344e-05,
      "loss": 0.0074,
      "step": 871
    },
    {
      "epoch": 2.2343900096061478,
      "grad_norm": 0.014609121717512608,
      "learning_rate": 6.75627555728989e-05,
      "loss": 0.005,
      "step": 872
    },
    {
      "epoch": 2.2369516490553956,
      "grad_norm": 0.03244280070066452,
      "learning_rate": 6.74789266321834e-05,
      "loss": 0.0126,
      "step": 873
    },
    {
      "epoch": 2.239513288504643,
      "grad_norm": 0.017335107550024986,
      "learning_rate": 6.739504168216762e-05,
      "loss": 0.0083,
      "step": 874
    },
    {
      "epoch": 2.2420749279538903,
      "grad_norm": 0.01658845879137516,
      "learning_rate": 6.731110099165164e-05,
      "loss": 0.0065,
      "step": 875
    },
    {
      "epoch": 2.2420749279538903,
      "eval_loss": 0.007803728803992271,
      "eval_runtime": 15.7858,
      "eval_samples_per_second": 6.335,
      "eval_steps_per_second": 1.584,
      "step": 875
    },
    {
      "epoch": 2.244636567403138,
      "grad_norm": 0.020299553871154785,
      "learning_rate": 6.722710482961419e-05,
      "loss": 0.0096,
      "step": 876
    },
    {
      "epoch": 2.2471982068523855,
      "grad_norm": 0.017362618818879128,
      "learning_rate": 6.714305346521174e-05,
      "loss": 0.0059,
      "step": 877
    },
    {
      "epoch": 2.249759846301633,
      "grad_norm": 0.017628263682127,
      "learning_rate": 6.705894716777768e-05,
      "loss": 0.0069,
      "step": 878
    },
    {
      "epoch": 2.2523214857508806,
      "grad_norm": 0.019219299778342247,
      "learning_rate": 6.697478620682137e-05,
      "loss": 0.0084,
      "step": 879
    },
    {
      "epoch": 2.254883125200128,
      "grad_norm": 0.016255104914307594,
      "learning_rate": 6.689057085202737e-05,
      "loss": 0.006,
      "step": 880
    },
    {
      "epoch": 2.2574447646493754,
      "grad_norm": 0.016757622361183167,
      "learning_rate": 6.680630137325453e-05,
      "loss": 0.0053,
      "step": 881
    },
    {
      "epoch": 2.260006404098623,
      "grad_norm": 0.012115413323044777,
      "learning_rate": 6.672197804053516e-05,
      "loss": 0.0044,
      "step": 882
    },
    {
      "epoch": 2.2625680435478706,
      "grad_norm": 0.01831790618598461,
      "learning_rate": 6.663760112407411e-05,
      "loss": 0.0079,
      "step": 883
    },
    {
      "epoch": 2.2651296829971184,
      "grad_norm": 0.015823351219296455,
      "learning_rate": 6.65531708942479e-05,
      "loss": 0.0055,
      "step": 884
    },
    {
      "epoch": 2.2676913224463657,
      "grad_norm": 0.026958780363202095,
      "learning_rate": 6.646868762160399e-05,
      "loss": 0.012,
      "step": 885
    },
    {
      "epoch": 2.270252961895613,
      "grad_norm": 0.022467253729701042,
      "learning_rate": 6.63841515768597e-05,
      "loss": 0.0082,
      "step": 886
    },
    {
      "epoch": 2.2728146013448605,
      "grad_norm": 0.024623310193419456,
      "learning_rate": 6.629956303090151e-05,
      "loss": 0.0088,
      "step": 887
    },
    {
      "epoch": 2.2753762407941083,
      "grad_norm": 0.022642867639660835,
      "learning_rate": 6.621492225478414e-05,
      "loss": 0.0087,
      "step": 888
    },
    {
      "epoch": 2.2779378802433556,
      "grad_norm": 0.01657482422888279,
      "learning_rate": 6.613022951972963e-05,
      "loss": 0.0046,
      "step": 889
    },
    {
      "epoch": 2.2804995196926034,
      "grad_norm": 0.017057588323950768,
      "learning_rate": 6.604548509712658e-05,
      "loss": 0.0071,
      "step": 890
    },
    {
      "epoch": 2.283061159141851,
      "grad_norm": 0.01688271202147007,
      "learning_rate": 6.596068925852916e-05,
      "loss": 0.0063,
      "step": 891
    },
    {
      "epoch": 2.285622798591098,
      "grad_norm": 0.024504490196704865,
      "learning_rate": 6.587584227565631e-05,
      "loss": 0.0059,
      "step": 892
    },
    {
      "epoch": 2.288184438040346,
      "grad_norm": 0.016235264018177986,
      "learning_rate": 6.579094442039091e-05,
      "loss": 0.0068,
      "step": 893
    },
    {
      "epoch": 2.2907460774895934,
      "grad_norm": 0.018847160041332245,
      "learning_rate": 6.570599596477876e-05,
      "loss": 0.0065,
      "step": 894
    },
    {
      "epoch": 2.2933077169388407,
      "grad_norm": 0.029839105904102325,
      "learning_rate": 6.562099718102788e-05,
      "loss": 0.0119,
      "step": 895
    },
    {
      "epoch": 2.2958693563880885,
      "grad_norm": 0.015048625878989697,
      "learning_rate": 6.553594834150754e-05,
      "loss": 0.0062,
      "step": 896
    },
    {
      "epoch": 2.298430995837336,
      "grad_norm": 0.01649918593466282,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0048,
      "step": 897
    },
    {
      "epoch": 2.3009926352865833,
      "grad_norm": 0.02212654985487461,
      "learning_rate": 6.53657015854366e-05,
      "loss": 0.0065,
      "step": 898
    },
    {
      "epoch": 2.303554274735831,
      "grad_norm": 0.016795290634036064,
      "learning_rate": 6.528050421442306e-05,
      "loss": 0.0051,
      "step": 899
    },
    {
      "epoch": 2.3061159141850784,
      "grad_norm": 0.014818985015153885,
      "learning_rate": 6.519525787871235e-05,
      "loss": 0.0055,
      "step": 900
    },
    {
      "epoch": 2.3061159141850784,
      "eval_loss": 0.007624690420925617,
      "eval_runtime": 15.7609,
      "eval_samples_per_second": 6.345,
      "eval_steps_per_second": 1.586,
      "step": 900
    },
    {
      "epoch": 2.308677553634326,
      "grad_norm": 0.020696334540843964,
      "learning_rate": 6.5109962851467e-05,
      "loss": 0.0103,
      "step": 901
    },
    {
      "epoch": 2.3112391930835736,
      "grad_norm": 0.02347083017230034,
      "learning_rate": 6.502461940600555e-05,
      "loss": 0.0078,
      "step": 902
    },
    {
      "epoch": 2.313800832532821,
      "grad_norm": 0.01726224087178707,
      "learning_rate": 6.49392278158017e-05,
      "loss": 0.0064,
      "step": 903
    },
    {
      "epoch": 2.3163624719820683,
      "grad_norm": 0.024909283965826035,
      "learning_rate": 6.485378835448342e-05,
      "loss": 0.0124,
      "step": 904
    },
    {
      "epoch": 2.318924111431316,
      "grad_norm": 0.01956700161099434,
      "learning_rate": 6.476830129583206e-05,
      "loss": 0.006,
      "step": 905
    },
    {
      "epoch": 2.3214857508805635,
      "grad_norm": 0.030146628618240356,
      "learning_rate": 6.468276691378155e-05,
      "loss": 0.0081,
      "step": 906
    },
    {
      "epoch": 2.324047390329811,
      "grad_norm": 0.01578514277935028,
      "learning_rate": 6.459718548241738e-05,
      "loss": 0.0064,
      "step": 907
    },
    {
      "epoch": 2.3266090297790587,
      "grad_norm": 0.020581640303134918,
      "learning_rate": 6.451155727597586e-05,
      "loss": 0.0064,
      "step": 908
    },
    {
      "epoch": 2.329170669228306,
      "grad_norm": 0.01611717976629734,
      "learning_rate": 6.442588256884318e-05,
      "loss": 0.0061,
      "step": 909
    },
    {
      "epoch": 2.3317323086775534,
      "grad_norm": 0.025673942640423775,
      "learning_rate": 6.434016163555452e-05,
      "loss": 0.0099,
      "step": 910
    },
    {
      "epoch": 2.3342939481268012,
      "grad_norm": 0.025654910132288933,
      "learning_rate": 6.42543947507932e-05,
      "loss": 0.0087,
      "step": 911
    },
    {
      "epoch": 2.3368555875760486,
      "grad_norm": 0.01794145628809929,
      "learning_rate": 6.416858218938976e-05,
      "loss": 0.0063,
      "step": 912
    },
    {
      "epoch": 2.3394172270252964,
      "grad_norm": 0.019059333950281143,
      "learning_rate": 6.408272422632114e-05,
      "loss": 0.0063,
      "step": 913
    },
    {
      "epoch": 2.341978866474544,
      "grad_norm": 0.018267640843987465,
      "learning_rate": 6.399682113670978e-05,
      "loss": 0.0055,
      "step": 914
    },
    {
      "epoch": 2.344540505923791,
      "grad_norm": 0.028884587809443474,
      "learning_rate": 6.391087319582264e-05,
      "loss": 0.0091,
      "step": 915
    },
    {
      "epoch": 2.3471021453730385,
      "grad_norm": 0.02319938875734806,
      "learning_rate": 6.382488067907047e-05,
      "loss": 0.009,
      "step": 916
    },
    {
      "epoch": 2.3496637848222863,
      "grad_norm": 0.019833754748106003,
      "learning_rate": 6.373884386200689e-05,
      "loss": 0.0074,
      "step": 917
    },
    {
      "epoch": 2.3522254242715337,
      "grad_norm": 0.02763204462826252,
      "learning_rate": 6.365276302032737e-05,
      "loss": 0.009,
      "step": 918
    },
    {
      "epoch": 2.3547870637207815,
      "grad_norm": 0.024364588782191277,
      "learning_rate": 6.356663842986854e-05,
      "loss": 0.0091,
      "step": 919
    },
    {
      "epoch": 2.357348703170029,
      "grad_norm": 0.01990056037902832,
      "learning_rate": 6.34804703666072e-05,
      "loss": 0.0097,
      "step": 920
    },
    {
      "epoch": 2.3599103426192762,
      "grad_norm": 0.024780521169304848,
      "learning_rate": 6.339425910665941e-05,
      "loss": 0.0095,
      "step": 921
    },
    {
      "epoch": 2.362471982068524,
      "grad_norm": 0.02050694450736046,
      "learning_rate": 6.33080049262797e-05,
      "loss": 0.0068,
      "step": 922
    },
    {
      "epoch": 2.3650336215177714,
      "grad_norm": 0.01734190620481968,
      "learning_rate": 6.322170810186012e-05,
      "loss": 0.0065,
      "step": 923
    },
    {
      "epoch": 2.3675952609670188,
      "grad_norm": 0.02429112046957016,
      "learning_rate": 6.313536890992935e-05,
      "loss": 0.0071,
      "step": 924
    },
    {
      "epoch": 2.3701569004162666,
      "grad_norm": 0.01471394207328558,
      "learning_rate": 6.304898762715186e-05,
      "loss": 0.0043,
      "step": 925
    },
    {
      "epoch": 2.3701569004162666,
      "eval_loss": 0.007436561398208141,
      "eval_runtime": 15.7935,
      "eval_samples_per_second": 6.332,
      "eval_steps_per_second": 1.583,
      "step": 925
    },
    {
      "epoch": 2.372718539865514,
      "grad_norm": 0.019127381965517998,
      "learning_rate": 6.296256453032698e-05,
      "loss": 0.006,
      "step": 926
    },
    {
      "epoch": 2.3752801793147613,
      "grad_norm": 0.025896169245243073,
      "learning_rate": 6.287609989638801e-05,
      "loss": 0.0091,
      "step": 927
    },
    {
      "epoch": 2.377841818764009,
      "grad_norm": 0.021031564101576805,
      "learning_rate": 6.278959400240141e-05,
      "loss": 0.0089,
      "step": 928
    },
    {
      "epoch": 2.3804034582132565,
      "grad_norm": 0.022658109664916992,
      "learning_rate": 6.270304712556578e-05,
      "loss": 0.0072,
      "step": 929
    },
    {
      "epoch": 2.382965097662504,
      "grad_norm": 0.03344877436757088,
      "learning_rate": 6.261645954321109e-05,
      "loss": 0.0077,
      "step": 930
    },
    {
      "epoch": 2.3855267371117517,
      "grad_norm": 0.02661379799246788,
      "learning_rate": 6.252983153279775e-05,
      "loss": 0.0092,
      "step": 931
    },
    {
      "epoch": 2.388088376560999,
      "grad_norm": 0.016638459637761116,
      "learning_rate": 6.244316337191567e-05,
      "loss": 0.0056,
      "step": 932
    },
    {
      "epoch": 2.3906500160102464,
      "grad_norm": 0.02403213083744049,
      "learning_rate": 6.235645533828349e-05,
      "loss": 0.0081,
      "step": 933
    },
    {
      "epoch": 2.393211655459494,
      "grad_norm": 0.021478185430169106,
      "learning_rate": 6.226970770974754e-05,
      "loss": 0.0066,
      "step": 934
    },
    {
      "epoch": 2.3957732949087416,
      "grad_norm": 0.021162012591958046,
      "learning_rate": 6.21829207642811e-05,
      "loss": 0.0068,
      "step": 935
    },
    {
      "epoch": 2.398334934357989,
      "grad_norm": 0.016740530729293823,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0063,
      "step": 936
    },
    {
      "epoch": 2.4008965738072368,
      "grad_norm": 0.02144131250679493,
      "learning_rate": 6.200923003507875e-05,
      "loss": 0.008,
      "step": 937
    },
    {
      "epoch": 2.403458213256484,
      "grad_norm": 0.032675664871931076,
      "learning_rate": 6.192232680791567e-05,
      "loss": 0.0119,
      "step": 938
    },
    {
      "epoch": 2.4060198527057315,
      "grad_norm": 0.02699361927807331,
      "learning_rate": 6.183538537696605e-05,
      "loss": 0.0086,
      "step": 939
    },
    {
      "epoch": 2.4085814921549793,
      "grad_norm": 0.018751805648207664,
      "learning_rate": 6.174840602082412e-05,
      "loss": 0.007,
      "step": 940
    },
    {
      "epoch": 2.4111431316042267,
      "grad_norm": 0.013862990774214268,
      "learning_rate": 6.166138901820567e-05,
      "loss": 0.0044,
      "step": 941
    },
    {
      "epoch": 2.413704771053474,
      "grad_norm": 0.018660085275769234,
      "learning_rate": 6.157433464794716e-05,
      "loss": 0.007,
      "step": 942
    },
    {
      "epoch": 2.416266410502722,
      "grad_norm": 0.016144121065735817,
      "learning_rate": 6.148724318900472e-05,
      "loss": 0.0052,
      "step": 943
    },
    {
      "epoch": 2.418828049951969,
      "grad_norm": 0.020236199721693993,
      "learning_rate": 6.140011492045338e-05,
      "loss": 0.0072,
      "step": 944
    },
    {
      "epoch": 2.4213896894012166,
      "grad_norm": 0.02062610536813736,
      "learning_rate": 6.131295012148612e-05,
      "loss": 0.0076,
      "step": 945
    },
    {
      "epoch": 2.4239513288504644,
      "grad_norm": 0.0255962535738945,
      "learning_rate": 6.122574907141291e-05,
      "loss": 0.0108,
      "step": 946
    },
    {
      "epoch": 2.4265129682997117,
      "grad_norm": 0.01486723218113184,
      "learning_rate": 6.113851204966001e-05,
      "loss": 0.0068,
      "step": 947
    },
    {
      "epoch": 2.4290746077489596,
      "grad_norm": 0.01589619740843773,
      "learning_rate": 6.105123933576882e-05,
      "loss": 0.0051,
      "step": 948
    },
    {
      "epoch": 2.431636247198207,
      "grad_norm": 0.018491653725504875,
      "learning_rate": 6.096393120939516e-05,
      "loss": 0.0075,
      "step": 949
    },
    {
      "epoch": 2.4341978866474543,
      "grad_norm": 0.015982965007424355,
      "learning_rate": 6.087658795030837e-05,
      "loss": 0.0063,
      "step": 950
    },
    {
      "epoch": 2.4341978866474543,
      "eval_loss": 0.0073355091735720634,
      "eval_runtime": 15.7799,
      "eval_samples_per_second": 6.337,
      "eval_steps_per_second": 1.584,
      "step": 950
    },
    {
      "epoch": 2.4367595260967017,
      "grad_norm": 0.016064204275608063,
      "learning_rate": 6.078920983839031e-05,
      "loss": 0.0054,
      "step": 951
    },
    {
      "epoch": 2.4393211655459495,
      "grad_norm": 0.03509011119604111,
      "learning_rate": 6.070179715363453e-05,
      "loss": 0.0154,
      "step": 952
    },
    {
      "epoch": 2.441882804995197,
      "grad_norm": 0.018619479611516,
      "learning_rate": 6.06143501761454e-05,
      "loss": 0.0069,
      "step": 953
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.019991964101791382,
      "learning_rate": 6.052686918613712e-05,
      "loss": 0.0083,
      "step": 954
    },
    {
      "epoch": 2.447006083893692,
      "grad_norm": 0.01930798403918743,
      "learning_rate": 6.043935446393294e-05,
      "loss": 0.0079,
      "step": 955
    },
    {
      "epoch": 2.4495677233429394,
      "grad_norm": 0.01885543018579483,
      "learning_rate": 6.035180628996416e-05,
      "loss": 0.0071,
      "step": 956
    },
    {
      "epoch": 2.452129362792187,
      "grad_norm": 0.021524138748645782,
      "learning_rate": 6.02642249447693e-05,
      "loss": 0.0081,
      "step": 957
    },
    {
      "epoch": 2.4546910022414345,
      "grad_norm": 0.020283209159970284,
      "learning_rate": 6.017661070899314e-05,
      "loss": 0.0057,
      "step": 958
    },
    {
      "epoch": 2.457252641690682,
      "grad_norm": 0.02511567436158657,
      "learning_rate": 6.0088963863385886e-05,
      "loss": 0.0073,
      "step": 959
    },
    {
      "epoch": 2.4598142811399297,
      "grad_norm": 0.013706948608160019,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 0.0039,
      "step": 960
    },
    {
      "epoch": 2.462375920589177,
      "grad_norm": 0.025410829111933708,
      "learning_rate": 5.9913573466200444e-05,
      "loss": 0.0113,
      "step": 961
    },
    {
      "epoch": 2.4649375600384245,
      "grad_norm": 0.017684413120150566,
      "learning_rate": 5.982583047664151e-05,
      "loss": 0.0076,
      "step": 962
    },
    {
      "epoch": 2.4674991994876723,
      "grad_norm": 0.017570337280631065,
      "learning_rate": 5.97380560012882e-05,
      "loss": 0.0075,
      "step": 963
    },
    {
      "epoch": 2.4700608389369196,
      "grad_norm": 0.020053574815392494,
      "learning_rate": 5.965025032140419e-05,
      "loss": 0.0109,
      "step": 964
    },
    {
      "epoch": 2.472622478386167,
      "grad_norm": 0.01965426467359066,
      "learning_rate": 5.956241371835312e-05,
      "loss": 0.0056,
      "step": 965
    },
    {
      "epoch": 2.475184117835415,
      "grad_norm": 0.020925339311361313,
      "learning_rate": 5.947454647359774e-05,
      "loss": 0.0082,
      "step": 966
    },
    {
      "epoch": 2.477745757284662,
      "grad_norm": 0.017741505056619644,
      "learning_rate": 5.938664886869897e-05,
      "loss": 0.0056,
      "step": 967
    },
    {
      "epoch": 2.4803073967339095,
      "grad_norm": 0.028152042999863625,
      "learning_rate": 5.9298721185315053e-05,
      "loss": 0.0135,
      "step": 968
    },
    {
      "epoch": 2.4828690361831574,
      "grad_norm": 0.028088664636015892,
      "learning_rate": 5.921076370520058e-05,
      "loss": 0.0054,
      "step": 969
    },
    {
      "epoch": 2.4854306756324047,
      "grad_norm": 0.011729970574378967,
      "learning_rate": 5.912277671020564e-05,
      "loss": 0.0038,
      "step": 970
    },
    {
      "epoch": 2.487992315081652,
      "grad_norm": 0.031858205795288086,
      "learning_rate": 5.9034760482274875e-05,
      "loss": 0.0096,
      "step": 971
    },
    {
      "epoch": 2.4905539545309,
      "grad_norm": 0.02154734544456005,
      "learning_rate": 5.894671530344664e-05,
      "loss": 0.0125,
      "step": 972
    },
    {
      "epoch": 2.4931155939801473,
      "grad_norm": 0.021228833124041557,
      "learning_rate": 5.8858641455852036e-05,
      "loss": 0.0057,
      "step": 973
    },
    {
      "epoch": 2.4956772334293946,
      "grad_norm": 0.018846942111849785,
      "learning_rate": 5.8770539221714014e-05,
      "loss": 0.0064,
      "step": 974
    },
    {
      "epoch": 2.4982388728786424,
      "grad_norm": 0.02012551948428154,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0056,
      "step": 975
    },
    {
      "epoch": 2.4982388728786424,
      "eval_loss": 0.007884026505053043,
      "eval_runtime": 15.7805,
      "eval_samples_per_second": 6.337,
      "eval_steps_per_second": 1.584,
      "step": 975
    },
    {
      "epoch": 2.50080051232789,
      "grad_norm": 0.023805588483810425,
      "learning_rate": 5.8594250723153544e-05,
      "loss": 0.0076,
      "step": 976
    },
    {
      "epoch": 2.5033621517771376,
      "grad_norm": 0.01971352845430374,
      "learning_rate": 5.850606502362822e-05,
      "loss": 0.006,
      "step": 977
    },
    {
      "epoch": 2.505923791226385,
      "grad_norm": 0.015985120087862015,
      "learning_rate": 5.841785206735192e-05,
      "loss": 0.0056,
      "step": 978
    },
    {
      "epoch": 2.5084854306756323,
      "grad_norm": 0.022680046036839485,
      "learning_rate": 5.8329612136993414e-05,
      "loss": 0.0074,
      "step": 979
    },
    {
      "epoch": 2.5110470701248797,
      "grad_norm": 0.019912639632821083,
      "learning_rate": 5.824134551530783e-05,
      "loss": 0.007,
      "step": 980
    },
    {
      "epoch": 2.5136087095741275,
      "grad_norm": 0.022760851308703423,
      "learning_rate": 5.815305248513587e-05,
      "loss": 0.0069,
      "step": 981
    },
    {
      "epoch": 2.516170349023375,
      "grad_norm": 0.02517043985426426,
      "learning_rate": 5.8064733329402856e-05,
      "loss": 0.0087,
      "step": 982
    },
    {
      "epoch": 2.5187319884726227,
      "grad_norm": 0.027291610836982727,
      "learning_rate": 5.7976388331117807e-05,
      "loss": 0.0113,
      "step": 983
    },
    {
      "epoch": 2.52129362792187,
      "grad_norm": 0.02210170030593872,
      "learning_rate": 5.788801777337257e-05,
      "loss": 0.0078,
      "step": 984
    },
    {
      "epoch": 2.5238552673711174,
      "grad_norm": 0.01957295462489128,
      "learning_rate": 5.7799621939340896e-05,
      "loss": 0.0066,
      "step": 985
    },
    {
      "epoch": 2.526416906820365,
      "grad_norm": 0.019617103040218353,
      "learning_rate": 5.771120111227751e-05,
      "loss": 0.0074,
      "step": 986
    },
    {
      "epoch": 2.5289785462696126,
      "grad_norm": 0.028092211112380028,
      "learning_rate": 5.762275557551727e-05,
      "loss": 0.0071,
      "step": 987
    },
    {
      "epoch": 2.53154018571886,
      "grad_norm": 0.024590661749243736,
      "learning_rate": 5.753428561247416e-05,
      "loss": 0.0084,
      "step": 988
    },
    {
      "epoch": 2.534101825168108,
      "grad_norm": 0.024077923968434334,
      "learning_rate": 5.744579150664046e-05,
      "loss": 0.0086,
      "step": 989
    },
    {
      "epoch": 2.536663464617355,
      "grad_norm": 0.017687125131487846,
      "learning_rate": 5.735727354158581e-05,
      "loss": 0.0066,
      "step": 990
    },
    {
      "epoch": 2.5392251040666025,
      "grad_norm": 0.022700879722833633,
      "learning_rate": 5.7268732000956304e-05,
      "loss": 0.0096,
      "step": 991
    },
    {
      "epoch": 2.54178674351585,
      "grad_norm": 0.022096680477261543,
      "learning_rate": 5.718016716847359e-05,
      "loss": 0.0114,
      "step": 992
    },
    {
      "epoch": 2.5443483829650977,
      "grad_norm": 0.01778617687523365,
      "learning_rate": 5.709157932793394e-05,
      "loss": 0.0061,
      "step": 993
    },
    {
      "epoch": 2.546910022414345,
      "grad_norm": 0.01681138202548027,
      "learning_rate": 5.7002968763207364e-05,
      "loss": 0.005,
      "step": 994
    },
    {
      "epoch": 2.549471661863593,
      "grad_norm": 0.028049584478139877,
      "learning_rate": 5.691433575823666e-05,
      "loss": 0.0102,
      "step": 995
    },
    {
      "epoch": 2.5520333013128402,
      "grad_norm": 0.016301583498716354,
      "learning_rate": 5.682568059703659e-05,
      "loss": 0.0058,
      "step": 996
    },
    {
      "epoch": 2.5545949407620876,
      "grad_norm": 0.016592754051089287,
      "learning_rate": 5.6737003563692834e-05,
      "loss": 0.0061,
      "step": 997
    },
    {
      "epoch": 2.5571565802113354,
      "grad_norm": 0.019314013421535492,
      "learning_rate": 5.664830494236126e-05,
      "loss": 0.0083,
      "step": 998
    },
    {
      "epoch": 2.5597182196605828,
      "grad_norm": 0.019145967438817024,
      "learning_rate": 5.6559585017266826e-05,
      "loss": 0.0069,
      "step": 999
    },
    {
      "epoch": 2.56227985910983,
      "grad_norm": 0.02137383259832859,
      "learning_rate": 5.6470844072702764e-05,
      "loss": 0.0076,
      "step": 1000
    },
    {
      "epoch": 2.56227985910983,
      "eval_loss": 0.0072718774899840355,
      "eval_runtime": 15.766,
      "eval_samples_per_second": 6.343,
      "eval_steps_per_second": 1.586,
      "step": 1000
    },
    {
      "epoch": 2.564841498559078,
      "grad_norm": 0.017583675682544708,
      "learning_rate": 5.6382082393029746e-05,
      "loss": 0.0059,
      "step": 1001
    },
    {
      "epoch": 2.5674031380083253,
      "grad_norm": 0.018566062673926353,
      "learning_rate": 5.6293300262674755e-05,
      "loss": 0.0077,
      "step": 1002
    },
    {
      "epoch": 2.5699647774575727,
      "grad_norm": 0.02141863852739334,
      "learning_rate": 5.62044979661304e-05,
      "loss": 0.0081,
      "step": 1003
    },
    {
      "epoch": 2.5725264169068205,
      "grad_norm": 0.01930375210940838,
      "learning_rate": 5.611567578795392e-05,
      "loss": 0.0067,
      "step": 1004
    },
    {
      "epoch": 2.575088056356068,
      "grad_norm": 0.025137510150671005,
      "learning_rate": 5.602683401276615e-05,
      "loss": 0.0087,
      "step": 1005
    },
    {
      "epoch": 2.5776496958053157,
      "grad_norm": 0.021621698513627052,
      "learning_rate": 5.593797292525087e-05,
      "loss": 0.007,
      "step": 1006
    },
    {
      "epoch": 2.580211335254563,
      "grad_norm": 0.02559741400182247,
      "learning_rate": 5.5849092810153666e-05,
      "loss": 0.0116,
      "step": 1007
    },
    {
      "epoch": 2.5827729747038104,
      "grad_norm": 0.022138088941574097,
      "learning_rate": 5.5760193952281056e-05,
      "loss": 0.0083,
      "step": 1008
    },
    {
      "epoch": 2.5853346141530578,
      "grad_norm": 0.01950952783226967,
      "learning_rate": 5.5671276636499714e-05,
      "loss": 0.0056,
      "step": 1009
    },
    {
      "epoch": 2.5878962536023056,
      "grad_norm": 0.02397429198026657,
      "learning_rate": 5.55823411477354e-05,
      "loss": 0.0105,
      "step": 1010
    },
    {
      "epoch": 2.590457893051553,
      "grad_norm": 0.014748901128768921,
      "learning_rate": 5.549338777097208e-05,
      "loss": 0.0053,
      "step": 1011
    },
    {
      "epoch": 2.5930195325008008,
      "grad_norm": 0.02159014530479908,
      "learning_rate": 5.540441679125112e-05,
      "loss": 0.0071,
      "step": 1012
    },
    {
      "epoch": 2.595581171950048,
      "grad_norm": 0.023283282294869423,
      "learning_rate": 5.531542849367026e-05,
      "loss": 0.0056,
      "step": 1013
    },
    {
      "epoch": 2.5981428113992955,
      "grad_norm": 0.019547423347830772,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0066,
      "step": 1014
    },
    {
      "epoch": 2.600704450848543,
      "grad_norm": 0.02325627952814102,
      "learning_rate": 5.513740108559622e-05,
      "loss": 0.0056,
      "step": 1015
    },
    {
      "epoch": 2.6032660902977907,
      "grad_norm": 0.015685738995671272,
      "learning_rate": 5.5048362545572304e-05,
      "loss": 0.0046,
      "step": 1016
    },
    {
      "epoch": 2.605827729747038,
      "grad_norm": 0.027276068925857544,
      "learning_rate": 5.495930782862522e-05,
      "loss": 0.0093,
      "step": 1017
    },
    {
      "epoch": 2.608389369196286,
      "grad_norm": 0.019772149622440338,
      "learning_rate": 5.4870237220120976e-05,
      "loss": 0.0056,
      "step": 1018
    },
    {
      "epoch": 2.610951008645533,
      "grad_norm": 0.016364077106118202,
      "learning_rate": 5.478115100547656e-05,
      "loss": 0.0056,
      "step": 1019
    },
    {
      "epoch": 2.6135126480947806,
      "grad_norm": 0.026881124824285507,
      "learning_rate": 5.469204947015897e-05,
      "loss": 0.0101,
      "step": 1020
    },
    {
      "epoch": 2.616074287544028,
      "grad_norm": 0.03398275375366211,
      "learning_rate": 5.460293289968429e-05,
      "loss": 0.0081,
      "step": 1021
    },
    {
      "epoch": 2.6186359269932757,
      "grad_norm": 0.028755880892276764,
      "learning_rate": 5.451380157961676e-05,
      "loss": 0.0085,
      "step": 1022
    },
    {
      "epoch": 2.621197566442523,
      "grad_norm": 0.01581442728638649,
      "learning_rate": 5.442465579556793e-05,
      "loss": 0.0055,
      "step": 1023
    },
    {
      "epoch": 2.623759205891771,
      "grad_norm": 0.01677510514855385,
      "learning_rate": 5.433549583319565e-05,
      "loss": 0.0051,
      "step": 1024
    },
    {
      "epoch": 2.6263208453410183,
      "grad_norm": 0.01671496219933033,
      "learning_rate": 5.424632197820324e-05,
      "loss": 0.0054,
      "step": 1025
    },
    {
      "epoch": 2.6263208453410183,
      "eval_loss": 0.0073104496113955975,
      "eval_runtime": 15.8028,
      "eval_samples_per_second": 6.328,
      "eval_steps_per_second": 1.582,
      "step": 1025
    },
    {
      "epoch": 2.6288824847902657,
      "grad_norm": 0.013602949678897858,
      "learning_rate": 5.415713451633853e-05,
      "loss": 0.0042,
      "step": 1026
    },
    {
      "epoch": 2.631444124239513,
      "grad_norm": 0.02331901527941227,
      "learning_rate": 5.4067933733392915e-05,
      "loss": 0.0092,
      "step": 1027
    },
    {
      "epoch": 2.634005763688761,
      "grad_norm": 0.027525432407855988,
      "learning_rate": 5.397871991520054e-05,
      "loss": 0.0103,
      "step": 1028
    },
    {
      "epoch": 2.636567403138008,
      "grad_norm": 0.025305457413196564,
      "learning_rate": 5.388949334763724e-05,
      "loss": 0.0096,
      "step": 1029
    },
    {
      "epoch": 2.639129042587256,
      "grad_norm": 0.017113184556365013,
      "learning_rate": 5.3800254316619806e-05,
      "loss": 0.0047,
      "step": 1030
    },
    {
      "epoch": 2.6416906820365034,
      "grad_norm": 0.02039264515042305,
      "learning_rate": 5.371100310810486e-05,
      "loss": 0.0064,
      "step": 1031
    },
    {
      "epoch": 2.6442523214857507,
      "grad_norm": 0.01747237518429756,
      "learning_rate": 5.3621740008088126e-05,
      "loss": 0.0064,
      "step": 1032
    },
    {
      "epoch": 2.6468139609349985,
      "grad_norm": 0.0253047663718462,
      "learning_rate": 5.353246530260339e-05,
      "loss": 0.0084,
      "step": 1033
    },
    {
      "epoch": 2.649375600384246,
      "grad_norm": 0.01626812294125557,
      "learning_rate": 5.344317927772163e-05,
      "loss": 0.0053,
      "step": 1034
    },
    {
      "epoch": 2.6519372398334933,
      "grad_norm": 0.042853761464357376,
      "learning_rate": 5.335388221955012e-05,
      "loss": 0.0064,
      "step": 1035
    },
    {
      "epoch": 2.654498879282741,
      "grad_norm": 0.017256347462534904,
      "learning_rate": 5.3264574414231475e-05,
      "loss": 0.0055,
      "step": 1036
    },
    {
      "epoch": 2.6570605187319885,
      "grad_norm": 0.020623289048671722,
      "learning_rate": 5.317525614794273e-05,
      "loss": 0.0083,
      "step": 1037
    },
    {
      "epoch": 2.659622158181236,
      "grad_norm": 0.018989235162734985,
      "learning_rate": 5.308592770689448e-05,
      "loss": 0.0067,
      "step": 1038
    },
    {
      "epoch": 2.6621837976304836,
      "grad_norm": 0.014944621361792088,
      "learning_rate": 5.299658937732988e-05,
      "loss": 0.0055,
      "step": 1039
    },
    {
      "epoch": 2.664745437079731,
      "grad_norm": 0.01713753305375576,
      "learning_rate": 5.290724144552379e-05,
      "loss": 0.0053,
      "step": 1040
    },
    {
      "epoch": 2.667307076528979,
      "grad_norm": 0.027423840016126633,
      "learning_rate": 5.281788419778187e-05,
      "loss": 0.0091,
      "step": 1041
    },
    {
      "epoch": 2.669868715978226,
      "grad_norm": 0.02789049781858921,
      "learning_rate": 5.272851792043959e-05,
      "loss": 0.0086,
      "step": 1042
    },
    {
      "epoch": 2.6724303554274735,
      "grad_norm": 0.01847296766936779,
      "learning_rate": 5.263914289986136e-05,
      "loss": 0.0067,
      "step": 1043
    },
    {
      "epoch": 2.674991994876721,
      "grad_norm": 0.016148822382092476,
      "learning_rate": 5.254975942243963e-05,
      "loss": 0.0043,
      "step": 1044
    },
    {
      "epoch": 2.6775536343259687,
      "grad_norm": 0.02496311441063881,
      "learning_rate": 5.246036777459391e-05,
      "loss": 0.0076,
      "step": 1045
    },
    {
      "epoch": 2.680115273775216,
      "grad_norm": 0.014748088084161282,
      "learning_rate": 5.2370968242769946e-05,
      "loss": 0.0044,
      "step": 1046
    },
    {
      "epoch": 2.682676913224464,
      "grad_norm": 0.01946377381682396,
      "learning_rate": 5.22815611134387e-05,
      "loss": 0.0053,
      "step": 1047
    },
    {
      "epoch": 2.6852385526737113,
      "grad_norm": 0.026910366490483284,
      "learning_rate": 5.219214667309551e-05,
      "loss": 0.0087,
      "step": 1048
    },
    {
      "epoch": 2.6878001921229586,
      "grad_norm": 0.01077069342136383,
      "learning_rate": 5.210272520825911e-05,
      "loss": 0.0035,
      "step": 1049
    },
    {
      "epoch": 2.690361831572206,
      "grad_norm": 0.02103227563202381,
      "learning_rate": 5.201329700547076e-05,
      "loss": 0.01,
      "step": 1050
    },
    {
      "epoch": 2.690361831572206,
      "eval_loss": 0.006800453644245863,
      "eval_runtime": 15.7754,
      "eval_samples_per_second": 6.339,
      "eval_steps_per_second": 1.585,
      "step": 1050
    },
    {
      "epoch": 2.692923471021454,
      "grad_norm": 0.01600644364953041,
      "learning_rate": 5.192386235129332e-05,
      "loss": 0.0058,
      "step": 1051
    },
    {
      "epoch": 2.695485110470701,
      "grad_norm": 0.01561508234590292,
      "learning_rate": 5.183442153231034e-05,
      "loss": 0.0055,
      "step": 1052
    },
    {
      "epoch": 2.698046749919949,
      "grad_norm": 0.014669963158667088,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0046,
      "step": 1053
    },
    {
      "epoch": 2.7006083893691963,
      "grad_norm": 0.02971458062529564,
      "learning_rate": 5.165552254635959e-05,
      "loss": 0.0115,
      "step": 1054
    },
    {
      "epoch": 2.7031700288184437,
      "grad_norm": 0.022039420902729034,
      "learning_rate": 5.1566064952654014e-05,
      "loss": 0.008,
      "step": 1055
    },
    {
      "epoch": 2.705731668267691,
      "grad_norm": 0.02216564118862152,
      "learning_rate": 5.147660234066533e-05,
      "loss": 0.0097,
      "step": 1056
    },
    {
      "epoch": 2.708293307716939,
      "grad_norm": 0.02106768824160099,
      "learning_rate": 5.1387134997066634e-05,
      "loss": 0.008,
      "step": 1057
    },
    {
      "epoch": 2.7108549471661862,
      "grad_norm": 0.01805659383535385,
      "learning_rate": 5.1297663208546234e-05,
      "loss": 0.0061,
      "step": 1058
    },
    {
      "epoch": 2.713416586615434,
      "grad_norm": 0.024404456838965416,
      "learning_rate": 5.1208187261806615e-05,
      "loss": 0.0077,
      "step": 1059
    },
    {
      "epoch": 2.7159782260646814,
      "grad_norm": 0.023735761642456055,
      "learning_rate": 5.1118707443563665e-05,
      "loss": 0.0105,
      "step": 1060
    },
    {
      "epoch": 2.718539865513929,
      "grad_norm": 0.022548731416463852,
      "learning_rate": 5.1029224040545585e-05,
      "loss": 0.0058,
      "step": 1061
    },
    {
      "epoch": 2.7211015049631766,
      "grad_norm": 0.017163462936878204,
      "learning_rate": 5.0939737339492124e-05,
      "loss": 0.0049,
      "step": 1062
    },
    {
      "epoch": 2.723663144412424,
      "grad_norm": 0.021907225251197815,
      "learning_rate": 5.08502476271536e-05,
      "loss": 0.0085,
      "step": 1063
    },
    {
      "epoch": 2.7262247838616713,
      "grad_norm": 0.01215510256588459,
      "learning_rate": 5.0760755190289964e-05,
      "loss": 0.0036,
      "step": 1064
    },
    {
      "epoch": 2.728786423310919,
      "grad_norm": 0.015955861657857895,
      "learning_rate": 5.0671260315669875e-05,
      "loss": 0.0048,
      "step": 1065
    },
    {
      "epoch": 2.7313480627601665,
      "grad_norm": 0.01937129907310009,
      "learning_rate": 5.0581763290069865e-05,
      "loss": 0.0068,
      "step": 1066
    },
    {
      "epoch": 2.733909702209414,
      "grad_norm": 0.02090214006602764,
      "learning_rate": 5.049226440027328e-05,
      "loss": 0.0073,
      "step": 1067
    },
    {
      "epoch": 2.7364713416586617,
      "grad_norm": 0.021622899919748306,
      "learning_rate": 5.0402763933069496e-05,
      "loss": 0.007,
      "step": 1068
    },
    {
      "epoch": 2.739032981107909,
      "grad_norm": 0.01952539198100567,
      "learning_rate": 5.031326217525296e-05,
      "loss": 0.0051,
      "step": 1069
    },
    {
      "epoch": 2.7415946205571564,
      "grad_norm": 0.01868268847465515,
      "learning_rate": 5.022375941362217e-05,
      "loss": 0.0058,
      "step": 1070
    },
    {
      "epoch": 2.7441562600064042,
      "grad_norm": 0.022691085934638977,
      "learning_rate": 5.0134255934978924e-05,
      "loss": 0.0069,
      "step": 1071
    },
    {
      "epoch": 2.7467178994556516,
      "grad_norm": 0.025523167103528976,
      "learning_rate": 5.004475202612731e-05,
      "loss": 0.0076,
      "step": 1072
    },
    {
      "epoch": 2.749279538904899,
      "grad_norm": 0.018498631194233894,
      "learning_rate": 4.995524797387272e-05,
      "loss": 0.0059,
      "step": 1073
    },
    {
      "epoch": 2.7518411783541468,
      "grad_norm": 0.015959061682224274,
      "learning_rate": 4.986574406502108e-05,
      "loss": 0.0053,
      "step": 1074
    },
    {
      "epoch": 2.754402817803394,
      "grad_norm": 0.036607638001441956,
      "learning_rate": 4.977624058637783e-05,
      "loss": 0.0064,
      "step": 1075
    },
    {
      "epoch": 2.754402817803394,
      "eval_loss": 0.007549135480076075,
      "eval_runtime": 15.7053,
      "eval_samples_per_second": 6.367,
      "eval_steps_per_second": 1.592,
      "step": 1075
    },
    {
      "epoch": 2.756964457252642,
      "grad_norm": 0.01559431292116642,
      "learning_rate": 4.9686737824747064e-05,
      "loss": 0.0052,
      "step": 1076
    },
    {
      "epoch": 2.7595260967018893,
      "grad_norm": 0.017336146906018257,
      "learning_rate": 4.9597236066930516e-05,
      "loss": 0.0053,
      "step": 1077
    },
    {
      "epoch": 2.7620877361511367,
      "grad_norm": 0.0237768292427063,
      "learning_rate": 4.9507735599726726e-05,
      "loss": 0.009,
      "step": 1078
    },
    {
      "epoch": 2.764649375600384,
      "grad_norm": 0.016704855486750603,
      "learning_rate": 4.941823670993016e-05,
      "loss": 0.0056,
      "step": 1079
    },
    {
      "epoch": 2.767211015049632,
      "grad_norm": 0.02107900008559227,
      "learning_rate": 4.9328739684330137e-05,
      "loss": 0.0056,
      "step": 1080
    },
    {
      "epoch": 2.769772654498879,
      "grad_norm": 0.01982649229466915,
      "learning_rate": 4.923924480971004e-05,
      "loss": 0.0051,
      "step": 1081
    },
    {
      "epoch": 2.772334293948127,
      "grad_norm": 0.017537608742713928,
      "learning_rate": 4.9149752372846404e-05,
      "loss": 0.0055,
      "step": 1082
    },
    {
      "epoch": 2.7748959333973744,
      "grad_norm": 0.02003137394785881,
      "learning_rate": 4.906026266050789e-05,
      "loss": 0.006,
      "step": 1083
    },
    {
      "epoch": 2.7774575728466218,
      "grad_norm": 0.02151995524764061,
      "learning_rate": 4.8970775959454427e-05,
      "loss": 0.0076,
      "step": 1084
    },
    {
      "epoch": 2.780019212295869,
      "grad_norm": 0.01217377558350563,
      "learning_rate": 4.8881292556436354e-05,
      "loss": 0.0037,
      "step": 1085
    },
    {
      "epoch": 2.782580851745117,
      "grad_norm": 0.018807468935847282,
      "learning_rate": 4.87918127381934e-05,
      "loss": 0.0058,
      "step": 1086
    },
    {
      "epoch": 2.7851424911943643,
      "grad_norm": 0.02241814136505127,
      "learning_rate": 4.870233679145378e-05,
      "loss": 0.0073,
      "step": 1087
    },
    {
      "epoch": 2.787704130643612,
      "grad_norm": 0.014323737472295761,
      "learning_rate": 4.861286500293338e-05,
      "loss": 0.0047,
      "step": 1088
    },
    {
      "epoch": 2.7902657700928595,
      "grad_norm": 0.01725595071911812,
      "learning_rate": 4.8523397659334704e-05,
      "loss": 0.005,
      "step": 1089
    },
    {
      "epoch": 2.792827409542107,
      "grad_norm": 0.032416146248579025,
      "learning_rate": 4.8433935047346e-05,
      "loss": 0.009,
      "step": 1090
    },
    {
      "epoch": 2.795389048991354,
      "grad_norm": 0.02138088457286358,
      "learning_rate": 4.834447745364041e-05,
      "loss": 0.0064,
      "step": 1091
    },
    {
      "epoch": 2.797950688440602,
      "grad_norm": 0.012949190102517605,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0036,
      "step": 1092
    },
    {
      "epoch": 2.8005123278898494,
      "grad_norm": 0.021004170179367065,
      "learning_rate": 4.8165578467689674e-05,
      "loss": 0.0063,
      "step": 1093
    },
    {
      "epoch": 2.803073967339097,
      "grad_norm": 0.02376505918800831,
      "learning_rate": 4.8076137648706674e-05,
      "loss": 0.0067,
      "step": 1094
    },
    {
      "epoch": 2.8056356067883446,
      "grad_norm": 0.01954122632741928,
      "learning_rate": 4.798670299452926e-05,
      "loss": 0.0054,
      "step": 1095
    },
    {
      "epoch": 2.808197246237592,
      "grad_norm": 0.019754689186811447,
      "learning_rate": 4.78972747917409e-05,
      "loss": 0.0073,
      "step": 1096
    },
    {
      "epoch": 2.8107588856868397,
      "grad_norm": 0.02440563589334488,
      "learning_rate": 4.7807853326904504e-05,
      "loss": 0.0072,
      "step": 1097
    },
    {
      "epoch": 2.813320525136087,
      "grad_norm": 0.027994103729724884,
      "learning_rate": 4.7718438886561316e-05,
      "loss": 0.0098,
      "step": 1098
    },
    {
      "epoch": 2.8158821645853345,
      "grad_norm": 0.021733155474066734,
      "learning_rate": 4.7629031757230066e-05,
      "loss": 0.0073,
      "step": 1099
    },
    {
      "epoch": 2.8184438040345823,
      "grad_norm": 0.01901175267994404,
      "learning_rate": 4.7539632225406095e-05,
      "loss": 0.0066,
      "step": 1100
    },
    {
      "epoch": 2.8184438040345823,
      "eval_loss": 0.007056466303765774,
      "eval_runtime": 15.7048,
      "eval_samples_per_second": 6.367,
      "eval_steps_per_second": 1.592,
      "step": 1100
    },
    {
      "epoch": 2.8210054434838296,
      "grad_norm": 0.019699299708008766,
      "learning_rate": 4.745024057756037e-05,
      "loss": 0.0054,
      "step": 1101
    },
    {
      "epoch": 2.823567082933077,
      "grad_norm": 0.02164098061621189,
      "learning_rate": 4.736085710013865e-05,
      "loss": 0.0078,
      "step": 1102
    },
    {
      "epoch": 2.826128722382325,
      "grad_norm": 0.019722308963537216,
      "learning_rate": 4.727148207956042e-05,
      "loss": 0.0061,
      "step": 1103
    },
    {
      "epoch": 2.828690361831572,
      "grad_norm": 0.019483914598822594,
      "learning_rate": 4.7182115802218126e-05,
      "loss": 0.0064,
      "step": 1104
    },
    {
      "epoch": 2.83125200128082,
      "grad_norm": 0.01710042729973793,
      "learning_rate": 4.709275855447621e-05,
      "loss": 0.0051,
      "step": 1105
    },
    {
      "epoch": 2.8338136407300674,
      "grad_norm": 0.022047800943255424,
      "learning_rate": 4.7003410622670134e-05,
      "loss": 0.0081,
      "step": 1106
    },
    {
      "epoch": 2.8363752801793147,
      "grad_norm": 0.016609322279691696,
      "learning_rate": 4.691407229310553e-05,
      "loss": 0.006,
      "step": 1107
    },
    {
      "epoch": 2.838936919628562,
      "grad_norm": 0.023373253643512726,
      "learning_rate": 4.682474385205728e-05,
      "loss": 0.0066,
      "step": 1108
    },
    {
      "epoch": 2.84149855907781,
      "grad_norm": 0.021889397874474525,
      "learning_rate": 4.6735425585768536e-05,
      "loss": 0.0066,
      "step": 1109
    },
    {
      "epoch": 2.8440601985270573,
      "grad_norm": 0.028596634045243263,
      "learning_rate": 4.6646117780449876e-05,
      "loss": 0.0087,
      "step": 1110
    },
    {
      "epoch": 2.846621837976305,
      "grad_norm": 0.0335087887942791,
      "learning_rate": 4.6556820722278393e-05,
      "loss": 0.01,
      "step": 1111
    },
    {
      "epoch": 2.8491834774255524,
      "grad_norm": 0.02548697032034397,
      "learning_rate": 4.646753469739662e-05,
      "loss": 0.0066,
      "step": 1112
    },
    {
      "epoch": 2.8517451168748,
      "grad_norm": 0.026222119107842445,
      "learning_rate": 4.6378259991911886e-05,
      "loss": 0.008,
      "step": 1113
    },
    {
      "epoch": 2.854306756324047,
      "grad_norm": 0.018268585205078125,
      "learning_rate": 4.628899689189516e-05,
      "loss": 0.0058,
      "step": 1114
    },
    {
      "epoch": 2.856868395773295,
      "grad_norm": 0.012070003896951675,
      "learning_rate": 4.6199745683380206e-05,
      "loss": 0.0039,
      "step": 1115
    },
    {
      "epoch": 2.8594300352225424,
      "grad_norm": 0.01760229282081127,
      "learning_rate": 4.611050665236276e-05,
      "loss": 0.0071,
      "step": 1116
    },
    {
      "epoch": 2.86199167467179,
      "grad_norm": 0.021311108022928238,
      "learning_rate": 4.602128008479949e-05,
      "loss": 0.0077,
      "step": 1117
    },
    {
      "epoch": 2.8645533141210375,
      "grad_norm": 0.020954597741365433,
      "learning_rate": 4.593206626660709e-05,
      "loss": 0.0091,
      "step": 1118
    },
    {
      "epoch": 2.867114953570285,
      "grad_norm": 0.024132655933499336,
      "learning_rate": 4.584286548366148e-05,
      "loss": 0.0066,
      "step": 1119
    },
    {
      "epoch": 2.8696765930195323,
      "grad_norm": 0.023584892973303795,
      "learning_rate": 4.5753678021796755e-05,
      "loss": 0.0091,
      "step": 1120
    },
    {
      "epoch": 2.87223823246878,
      "grad_norm": 0.02193642593920231,
      "learning_rate": 4.5664504166804356e-05,
      "loss": 0.0081,
      "step": 1121
    },
    {
      "epoch": 2.8747998719180274,
      "grad_norm": 0.015388750471174717,
      "learning_rate": 4.5575344204432084e-05,
      "loss": 0.0047,
      "step": 1122
    },
    {
      "epoch": 2.8773615113672752,
      "grad_norm": 0.018353408202528954,
      "learning_rate": 4.5486198420383244e-05,
      "loss": 0.0057,
      "step": 1123
    },
    {
      "epoch": 2.8799231508165226,
      "grad_norm": 0.01442483440041542,
      "learning_rate": 4.5397067100315734e-05,
      "loss": 0.0053,
      "step": 1124
    },
    {
      "epoch": 2.88248479026577,
      "grad_norm": 0.039199162274599075,
      "learning_rate": 4.530795052984104e-05,
      "loss": 0.0168,
      "step": 1125
    },
    {
      "epoch": 2.88248479026577,
      "eval_loss": 0.008591169491410255,
      "eval_runtime": 15.6964,
      "eval_samples_per_second": 6.371,
      "eval_steps_per_second": 1.593,
      "step": 1125
    },
    {
      "epoch": 2.8850464297150173,
      "grad_norm": 0.018906261771917343,
      "learning_rate": 4.5218848994523446e-05,
      "loss": 0.0057,
      "step": 1126
    },
    {
      "epoch": 2.887608069164265,
      "grad_norm": 0.024255679920315742,
      "learning_rate": 4.512976277987904e-05,
      "loss": 0.01,
      "step": 1127
    },
    {
      "epoch": 2.8901697086135125,
      "grad_norm": 0.025274179875850677,
      "learning_rate": 4.50406921713748e-05,
      "loss": 0.0108,
      "step": 1128
    },
    {
      "epoch": 2.8927313480627603,
      "grad_norm": 0.020932083949446678,
      "learning_rate": 4.495163745442769e-05,
      "loss": 0.0063,
      "step": 1129
    },
    {
      "epoch": 2.8952929875120077,
      "grad_norm": 0.013744296506047249,
      "learning_rate": 4.48625989144038e-05,
      "loss": 0.0049,
      "step": 1130
    },
    {
      "epoch": 2.897854626961255,
      "grad_norm": 0.013666169717907906,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0043,
      "step": 1131
    },
    {
      "epoch": 2.900416266410503,
      "grad_norm": 0.015672704204916954,
      "learning_rate": 4.468457150632975e-05,
      "loss": 0.0064,
      "step": 1132
    },
    {
      "epoch": 2.9029779058597502,
      "grad_norm": 0.01978994347155094,
      "learning_rate": 4.459558320874888e-05,
      "loss": 0.0067,
      "step": 1133
    },
    {
      "epoch": 2.9055395453089976,
      "grad_norm": 0.03054462932050228,
      "learning_rate": 4.450661222902793e-05,
      "loss": 0.0163,
      "step": 1134
    },
    {
      "epoch": 2.9081011847582454,
      "grad_norm": 0.0375843346118927,
      "learning_rate": 4.4417658852264614e-05,
      "loss": 0.0098,
      "step": 1135
    },
    {
      "epoch": 2.910662824207493,
      "grad_norm": 0.019927896559238434,
      "learning_rate": 4.43287233635003e-05,
      "loss": 0.0084,
      "step": 1136
    },
    {
      "epoch": 2.91322446365674,
      "grad_norm": 0.015810800716280937,
      "learning_rate": 4.423980604771895e-05,
      "loss": 0.0044,
      "step": 1137
    },
    {
      "epoch": 2.915786103105988,
      "grad_norm": 0.0203675776720047,
      "learning_rate": 4.4150907189846345e-05,
      "loss": 0.0064,
      "step": 1138
    },
    {
      "epoch": 2.9183477425552353,
      "grad_norm": 0.015811270102858543,
      "learning_rate": 4.4062027074749126e-05,
      "loss": 0.0055,
      "step": 1139
    },
    {
      "epoch": 2.920909382004483,
      "grad_norm": 0.02347410097718239,
      "learning_rate": 4.397316598723385e-05,
      "loss": 0.0088,
      "step": 1140
    },
    {
      "epoch": 2.9234710214537305,
      "grad_norm": 0.017205510288476944,
      "learning_rate": 4.38843242120461e-05,
      "loss": 0.0058,
      "step": 1141
    },
    {
      "epoch": 2.926032660902978,
      "grad_norm": 0.015807706862688065,
      "learning_rate": 4.37955020338696e-05,
      "loss": 0.0058,
      "step": 1142
    },
    {
      "epoch": 2.9285943003522252,
      "grad_norm": 0.02101590670645237,
      "learning_rate": 4.370669973732527e-05,
      "loss": 0.0045,
      "step": 1143
    },
    {
      "epoch": 2.931155939801473,
      "grad_norm": 0.015992263332009315,
      "learning_rate": 4.361791760697027e-05,
      "loss": 0.0056,
      "step": 1144
    },
    {
      "epoch": 2.9337175792507204,
      "grad_norm": 0.0318165086209774,
      "learning_rate": 4.352915592729723e-05,
      "loss": 0.0125,
      "step": 1145
    },
    {
      "epoch": 2.936279218699968,
      "grad_norm": 0.016865696758031845,
      "learning_rate": 4.34404149827332e-05,
      "loss": 0.0053,
      "step": 1146
    },
    {
      "epoch": 2.9388408581492156,
      "grad_norm": 0.039752960205078125,
      "learning_rate": 4.335169505763874e-05,
      "loss": 0.0088,
      "step": 1147
    },
    {
      "epoch": 2.941402497598463,
      "grad_norm": 0.022740483283996582,
      "learning_rate": 4.326299643630716e-05,
      "loss": 0.0065,
      "step": 1148
    },
    {
      "epoch": 2.9439641370477103,
      "grad_norm": 0.023348230868577957,
      "learning_rate": 4.317431940296343e-05,
      "loss": 0.0074,
      "step": 1149
    },
    {
      "epoch": 2.946525776496958,
      "grad_norm": 0.04514496400952339,
      "learning_rate": 4.308566424176336e-05,
      "loss": 0.013,
      "step": 1150
    },
    {
      "epoch": 2.946525776496958,
      "eval_loss": 0.006918873637914658,
      "eval_runtime": 15.7249,
      "eval_samples_per_second": 6.359,
      "eval_steps_per_second": 1.59,
      "step": 1150
    },
    {
      "epoch": 2.9490874159462055,
      "grad_norm": 0.01825115457177162,
      "learning_rate": 4.299703123679265e-05,
      "loss": 0.0069,
      "step": 1151
    },
    {
      "epoch": 2.9516490553954533,
      "grad_norm": 0.022036191076040268,
      "learning_rate": 4.290842067206608e-05,
      "loss": 0.0075,
      "step": 1152
    },
    {
      "epoch": 2.9542106948447007,
      "grad_norm": 0.016818994656205177,
      "learning_rate": 4.281983283152643e-05,
      "loss": 0.0049,
      "step": 1153
    },
    {
      "epoch": 2.956772334293948,
      "grad_norm": 0.01692839525640011,
      "learning_rate": 4.27312679990437e-05,
      "loss": 0.0039,
      "step": 1154
    },
    {
      "epoch": 2.9593339737431954,
      "grad_norm": 0.027776619419455528,
      "learning_rate": 4.264272645841419e-05,
      "loss": 0.0079,
      "step": 1155
    },
    {
      "epoch": 2.961895613192443,
      "grad_norm": 0.021229857578873634,
      "learning_rate": 4.255420849335956e-05,
      "loss": 0.0056,
      "step": 1156
    },
    {
      "epoch": 2.9644572526416906,
      "grad_norm": 0.0324573740363121,
      "learning_rate": 4.246571438752585e-05,
      "loss": 0.0088,
      "step": 1157
    },
    {
      "epoch": 2.9670188920909384,
      "grad_norm": 0.021437501534819603,
      "learning_rate": 4.237724442448273e-05,
      "loss": 0.0093,
      "step": 1158
    },
    {
      "epoch": 2.9695805315401858,
      "grad_norm": 0.020703041926026344,
      "learning_rate": 4.2288798887722494e-05,
      "loss": 0.0077,
      "step": 1159
    },
    {
      "epoch": 2.972142170989433,
      "grad_norm": 0.01659969985485077,
      "learning_rate": 4.2200378060659116e-05,
      "loss": 0.0038,
      "step": 1160
    },
    {
      "epoch": 2.9747038104386805,
      "grad_norm": 0.018442777916789055,
      "learning_rate": 4.2111982226627436e-05,
      "loss": 0.005,
      "step": 1161
    },
    {
      "epoch": 2.9772654498879283,
      "grad_norm": 0.02515353262424469,
      "learning_rate": 4.202361166888222e-05,
      "loss": 0.0059,
      "step": 1162
    },
    {
      "epoch": 2.9798270893371757,
      "grad_norm": 0.029337922111153603,
      "learning_rate": 4.193526667059716e-05,
      "loss": 0.0087,
      "step": 1163
    },
    {
      "epoch": 2.9823887287864235,
      "grad_norm": 0.030802778899669647,
      "learning_rate": 4.184694751486414e-05,
      "loss": 0.0112,
      "step": 1164
    },
    {
      "epoch": 2.984950368235671,
      "grad_norm": 0.03156080096960068,
      "learning_rate": 4.1758654484692186e-05,
      "loss": 0.0117,
      "step": 1165
    },
    {
      "epoch": 2.987512007684918,
      "grad_norm": 0.025577133521437645,
      "learning_rate": 4.167038786300659e-05,
      "loss": 0.0076,
      "step": 1166
    },
    {
      "epoch": 2.990073647134166,
      "grad_norm": 0.030604520812630653,
      "learning_rate": 4.1582147932648074e-05,
      "loss": 0.012,
      "step": 1167
    },
    {
      "epoch": 2.9926352865834134,
      "grad_norm": 0.023930441588163376,
      "learning_rate": 4.14939349763718e-05,
      "loss": 0.0056,
      "step": 1168
    },
    {
      "epoch": 2.9951969260326607,
      "grad_norm": 0.019746793434023857,
      "learning_rate": 4.140574927684647e-05,
      "loss": 0.0081,
      "step": 1169
    },
    {
      "epoch": 2.9977585654819086,
      "grad_norm": 0.0151827996596694,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0042,
      "step": 1170
    },
    {
      "epoch": 3.000640409862312,
      "grad_norm": 0.061972830444574356,
      "learning_rate": 4.1229460778286004e-05,
      "loss": 0.02,
      "step": 1171
    },
    {
      "epoch": 3.003202049311559,
      "grad_norm": 0.010719524696469307,
      "learning_rate": 4.1141358544147976e-05,
      "loss": 0.0026,
      "step": 1172
    },
    {
      "epoch": 3.005763688760807,
      "grad_norm": 0.012511296197772026,
      "learning_rate": 4.105328469655336e-05,
      "loss": 0.0048,
      "step": 1173
    },
    {
      "epoch": 3.0083253282100544,
      "grad_norm": 0.02187875472009182,
      "learning_rate": 4.0965239517725117e-05,
      "loss": 0.0077,
      "step": 1174
    },
    {
      "epoch": 3.0108869676593017,
      "grad_norm": 0.016843268647789955,
      "learning_rate": 4.087722328979438e-05,
      "loss": 0.0058,
      "step": 1175
    },
    {
      "epoch": 3.0108869676593017,
      "eval_loss": 0.007106189616024494,
      "eval_runtime": 15.6924,
      "eval_samples_per_second": 6.373,
      "eval_steps_per_second": 1.593,
      "step": 1175
    },
    {
      "epoch": 3.0134486071085496,
      "grad_norm": 0.014118392020463943,
      "learning_rate": 4.078923629479943e-05,
      "loss": 0.0039,
      "step": 1176
    },
    {
      "epoch": 3.016010246557797,
      "grad_norm": 0.017133532091975212,
      "learning_rate": 4.0701278814684945e-05,
      "loss": 0.007,
      "step": 1177
    },
    {
      "epoch": 3.0185718860070443,
      "grad_norm": 0.015284501016139984,
      "learning_rate": 4.0613351131301036e-05,
      "loss": 0.0054,
      "step": 1178
    },
    {
      "epoch": 3.021133525456292,
      "grad_norm": 0.025085574015975,
      "learning_rate": 4.052545352640228e-05,
      "loss": 0.004,
      "step": 1179
    },
    {
      "epoch": 3.0236951649055395,
      "grad_norm": 0.018907958641648293,
      "learning_rate": 4.043758628164688e-05,
      "loss": 0.0044,
      "step": 1180
    },
    {
      "epoch": 3.0262568043547873,
      "grad_norm": 0.017235899344086647,
      "learning_rate": 4.034974967859582e-05,
      "loss": 0.0042,
      "step": 1181
    },
    {
      "epoch": 3.0288184438040346,
      "grad_norm": 0.01964586041867733,
      "learning_rate": 4.026194399871181e-05,
      "loss": 0.0038,
      "step": 1182
    },
    {
      "epoch": 3.031380083253282,
      "grad_norm": 0.019763899967074394,
      "learning_rate": 4.017416952335849e-05,
      "loss": 0.0037,
      "step": 1183
    },
    {
      "epoch": 3.03394172270253,
      "grad_norm": 0.020342646166682243,
      "learning_rate": 4.008642653379957e-05,
      "loss": 0.0042,
      "step": 1184
    },
    {
      "epoch": 3.036503362151777,
      "grad_norm": 0.021486425772309303,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 0.005,
      "step": 1185
    },
    {
      "epoch": 3.0390650016010246,
      "grad_norm": 0.012984909117221832,
      "learning_rate": 3.991103613661412e-05,
      "loss": 0.0026,
      "step": 1186
    },
    {
      "epoch": 3.0416266410502724,
      "grad_norm": 0.022616276517510414,
      "learning_rate": 3.982338929100688e-05,
      "loss": 0.0041,
      "step": 1187
    },
    {
      "epoch": 3.0441882804995197,
      "grad_norm": 0.01583174802362919,
      "learning_rate": 3.973577505523072e-05,
      "loss": 0.0034,
      "step": 1188
    },
    {
      "epoch": 3.046749919948767,
      "grad_norm": 0.01628080941736698,
      "learning_rate": 3.964819371003585e-05,
      "loss": 0.0034,
      "step": 1189
    },
    {
      "epoch": 3.049311559398015,
      "grad_norm": 0.02016085386276245,
      "learning_rate": 3.956064553606708e-05,
      "loss": 0.0041,
      "step": 1190
    },
    {
      "epoch": 3.0518731988472623,
      "grad_norm": 0.02444877102971077,
      "learning_rate": 3.947313081386289e-05,
      "loss": 0.0059,
      "step": 1191
    },
    {
      "epoch": 3.0544348382965096,
      "grad_norm": 0.028850266709923744,
      "learning_rate": 3.938564982385462e-05,
      "loss": 0.0069,
      "step": 1192
    },
    {
      "epoch": 3.0569964777457574,
      "grad_norm": 0.024146832525730133,
      "learning_rate": 3.9298202846365466e-05,
      "loss": 0.004,
      "step": 1193
    },
    {
      "epoch": 3.059558117195005,
      "grad_norm": 0.03326459228992462,
      "learning_rate": 3.92107901616097e-05,
      "loss": 0.0064,
      "step": 1194
    },
    {
      "epoch": 3.062119756644252,
      "grad_norm": 0.02041238360106945,
      "learning_rate": 3.912341204969164e-05,
      "loss": 0.0042,
      "step": 1195
    },
    {
      "epoch": 3.0646813960935,
      "grad_norm": 0.02406291291117668,
      "learning_rate": 3.903606879060483e-05,
      "loss": 0.0044,
      "step": 1196
    },
    {
      "epoch": 3.0672430355427474,
      "grad_norm": 0.017291957512497902,
      "learning_rate": 3.8948760664231195e-05,
      "loss": 0.003,
      "step": 1197
    },
    {
      "epoch": 3.0698046749919947,
      "grad_norm": 0.013232097029685974,
      "learning_rate": 3.886148795034001e-05,
      "loss": 0.0034,
      "step": 1198
    },
    {
      "epoch": 3.0723663144412425,
      "grad_norm": 0.026490524411201477,
      "learning_rate": 3.877425092858708e-05,
      "loss": 0.0058,
      "step": 1199
    },
    {
      "epoch": 3.07492795389049,
      "grad_norm": 0.018783340230584145,
      "learning_rate": 3.86870498785139e-05,
      "loss": 0.0057,
      "step": 1200
    },
    {
      "epoch": 3.07492795389049,
      "eval_loss": 0.0069786058738827705,
      "eval_runtime": 15.681,
      "eval_samples_per_second": 6.377,
      "eval_steps_per_second": 1.594,
      "step": 1200
    },
    {
      "epoch": 3.0774895933397373,
      "grad_norm": 0.016674773767590523,
      "learning_rate": 3.859988507954663e-05,
      "loss": 0.0034,
      "step": 1201
    },
    {
      "epoch": 3.080051232788985,
      "grad_norm": 0.01833149790763855,
      "learning_rate": 3.851275681099528e-05,
      "loss": 0.0047,
      "step": 1202
    },
    {
      "epoch": 3.0826128722382324,
      "grad_norm": 0.012066060677170753,
      "learning_rate": 3.842566535205286e-05,
      "loss": 0.0025,
      "step": 1203
    },
    {
      "epoch": 3.08517451168748,
      "grad_norm": 0.026396669447422028,
      "learning_rate": 3.8338610981794344e-05,
      "loss": 0.0052,
      "step": 1204
    },
    {
      "epoch": 3.0877361511367276,
      "grad_norm": 0.018845973536372185,
      "learning_rate": 3.825159397917589e-05,
      "loss": 0.0054,
      "step": 1205
    },
    {
      "epoch": 3.090297790585975,
      "grad_norm": 0.020172514021396637,
      "learning_rate": 3.8164614623033975e-05,
      "loss": 0.0032,
      "step": 1206
    },
    {
      "epoch": 3.0928594300352223,
      "grad_norm": 0.025464298203587532,
      "learning_rate": 3.807767319208435e-05,
      "loss": 0.0055,
      "step": 1207
    },
    {
      "epoch": 3.09542106948447,
      "grad_norm": 0.020005084574222565,
      "learning_rate": 3.799076996492127e-05,
      "loss": 0.004,
      "step": 1208
    },
    {
      "epoch": 3.0979827089337175,
      "grad_norm": 0.017038699239492416,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0045,
      "step": 1209
    },
    {
      "epoch": 3.100544348382965,
      "grad_norm": 0.025118080899119377,
      "learning_rate": 3.781707923571891e-05,
      "loss": 0.0046,
      "step": 1210
    },
    {
      "epoch": 3.1031059878322127,
      "grad_norm": 0.014508400112390518,
      "learning_rate": 3.773029229025245e-05,
      "loss": 0.0027,
      "step": 1211
    },
    {
      "epoch": 3.10566762728146,
      "grad_norm": 0.01848450116813183,
      "learning_rate": 3.764354466171652e-05,
      "loss": 0.0047,
      "step": 1212
    },
    {
      "epoch": 3.1082292667307074,
      "grad_norm": 0.019989987835288048,
      "learning_rate": 3.755683662808434e-05,
      "loss": 0.004,
      "step": 1213
    },
    {
      "epoch": 3.1107909061799552,
      "grad_norm": 0.023956049233675003,
      "learning_rate": 3.747016846720226e-05,
      "loss": 0.0057,
      "step": 1214
    },
    {
      "epoch": 3.1133525456292026,
      "grad_norm": 0.015794293954968452,
      "learning_rate": 3.738354045678891e-05,
      "loss": 0.0031,
      "step": 1215
    },
    {
      "epoch": 3.1159141850784504,
      "grad_norm": 0.018386952579021454,
      "learning_rate": 3.7296952874434234e-05,
      "loss": 0.0043,
      "step": 1216
    },
    {
      "epoch": 3.118475824527698,
      "grad_norm": 0.03184031322598457,
      "learning_rate": 3.7210405997598596e-05,
      "loss": 0.0065,
      "step": 1217
    },
    {
      "epoch": 3.121037463976945,
      "grad_norm": 0.02117329277098179,
      "learning_rate": 3.712390010361198e-05,
      "loss": 0.0053,
      "step": 1218
    },
    {
      "epoch": 3.123599103426193,
      "grad_norm": 0.02299274317920208,
      "learning_rate": 3.703743546967304e-05,
      "loss": 0.005,
      "step": 1219
    },
    {
      "epoch": 3.1261607428754403,
      "grad_norm": 0.019891448318958282,
      "learning_rate": 3.695101237284815e-05,
      "loss": 0.0047,
      "step": 1220
    },
    {
      "epoch": 3.1287223823246877,
      "grad_norm": 0.07732272148132324,
      "learning_rate": 3.6864631090070655e-05,
      "loss": 0.0061,
      "step": 1221
    },
    {
      "epoch": 3.1312840217739355,
      "grad_norm": 0.019109439104795456,
      "learning_rate": 3.67782918981399e-05,
      "loss": 0.0042,
      "step": 1222
    },
    {
      "epoch": 3.133845661223183,
      "grad_norm": 0.020790351554751396,
      "learning_rate": 3.6691995073720306e-05,
      "loss": 0.0048,
      "step": 1223
    },
    {
      "epoch": 3.1364073006724302,
      "grad_norm": 0.017758572474122047,
      "learning_rate": 3.66057408933406e-05,
      "loss": 0.0038,
      "step": 1224
    },
    {
      "epoch": 3.138968940121678,
      "grad_norm": 0.034487027674913406,
      "learning_rate": 3.651952963339282e-05,
      "loss": 0.0075,
      "step": 1225
    },
    {
      "epoch": 3.138968940121678,
      "eval_loss": 0.0067987870424985886,
      "eval_runtime": 15.7069,
      "eval_samples_per_second": 6.367,
      "eval_steps_per_second": 1.592,
      "step": 1225
    },
    {
      "epoch": 3.1415305795709254,
      "grad_norm": 0.022508880123496056,
      "learning_rate": 3.643336157013147e-05,
      "loss": 0.0056,
      "step": 1226
    },
    {
      "epoch": 3.1440922190201728,
      "grad_norm": 0.01572093553841114,
      "learning_rate": 3.634723697967263e-05,
      "loss": 0.003,
      "step": 1227
    },
    {
      "epoch": 3.1466538584694206,
      "grad_norm": 0.02083379589021206,
      "learning_rate": 3.6261156137993116e-05,
      "loss": 0.004,
      "step": 1228
    },
    {
      "epoch": 3.149215497918668,
      "grad_norm": 0.0228340495377779,
      "learning_rate": 3.617511932092953e-05,
      "loss": 0.0055,
      "step": 1229
    },
    {
      "epoch": 3.1517771373679153,
      "grad_norm": 0.020101532340049744,
      "learning_rate": 3.608912680417737e-05,
      "loss": 0.0037,
      "step": 1230
    },
    {
      "epoch": 3.154338776817163,
      "grad_norm": 0.017341822385787964,
      "learning_rate": 3.6003178863290235e-05,
      "loss": 0.0037,
      "step": 1231
    },
    {
      "epoch": 3.1569004162664105,
      "grad_norm": 0.016037769615650177,
      "learning_rate": 3.591727577367887e-05,
      "loss": 0.0036,
      "step": 1232
    },
    {
      "epoch": 3.159462055715658,
      "grad_norm": 0.014761366881430149,
      "learning_rate": 3.583141781061024e-05,
      "loss": 0.0027,
      "step": 1233
    },
    {
      "epoch": 3.1620236951649057,
      "grad_norm": 0.017608877271413803,
      "learning_rate": 3.5745605249206816e-05,
      "loss": 0.0045,
      "step": 1234
    },
    {
      "epoch": 3.164585334614153,
      "grad_norm": 0.019648857414722443,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.0042,
      "step": 1235
    },
    {
      "epoch": 3.1671469740634004,
      "grad_norm": 0.01928468607366085,
      "learning_rate": 3.557411743115683e-05,
      "loss": 0.0041,
      "step": 1236
    },
    {
      "epoch": 3.169708613512648,
      "grad_norm": 0.01620553433895111,
      "learning_rate": 3.548844272402415e-05,
      "loss": 0.0039,
      "step": 1237
    },
    {
      "epoch": 3.1722702529618956,
      "grad_norm": 0.019136866554617882,
      "learning_rate": 3.5402814517582644e-05,
      "loss": 0.0047,
      "step": 1238
    },
    {
      "epoch": 3.174831892411143,
      "grad_norm": 0.022867608815431595,
      "learning_rate": 3.531723308621847e-05,
      "loss": 0.0046,
      "step": 1239
    },
    {
      "epoch": 3.1773935318603908,
      "grad_norm": 0.027643466368317604,
      "learning_rate": 3.523169870416795e-05,
      "loss": 0.0055,
      "step": 1240
    },
    {
      "epoch": 3.179955171309638,
      "grad_norm": 0.029165679588913918,
      "learning_rate": 3.5146211645516615e-05,
      "loss": 0.0069,
      "step": 1241
    },
    {
      "epoch": 3.1825168107588855,
      "grad_norm": 0.021566109731793404,
      "learning_rate": 3.506077218419832e-05,
      "loss": 0.005,
      "step": 1242
    },
    {
      "epoch": 3.1850784502081333,
      "grad_norm": 0.023212000727653503,
      "learning_rate": 3.497538059399447e-05,
      "loss": 0.0045,
      "step": 1243
    },
    {
      "epoch": 3.1876400896573807,
      "grad_norm": 0.022735675796866417,
      "learning_rate": 3.489003714853303e-05,
      "loss": 0.005,
      "step": 1244
    },
    {
      "epoch": 3.1902017291066285,
      "grad_norm": 0.018199926242232323,
      "learning_rate": 3.480474212128766e-05,
      "loss": 0.0038,
      "step": 1245
    },
    {
      "epoch": 3.192763368555876,
      "grad_norm": 0.027111992239952087,
      "learning_rate": 3.471949578557695e-05,
      "loss": 0.0051,
      "step": 1246
    },
    {
      "epoch": 3.195325008005123,
      "grad_norm": 0.0206306129693985,
      "learning_rate": 3.463429841456339e-05,
      "loss": 0.005,
      "step": 1247
    },
    {
      "epoch": 3.1978866474543706,
      "grad_norm": 0.015546630136668682,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0029,
      "step": 1248
    },
    {
      "epoch": 3.2004482869036184,
      "grad_norm": 0.017362765967845917,
      "learning_rate": 3.446405165849248e-05,
      "loss": 0.0041,
      "step": 1249
    },
    {
      "epoch": 3.2030099263528657,
      "grad_norm": 0.016959575936198235,
      "learning_rate": 3.4379002818972124e-05,
      "loss": 0.0035,
      "step": 1250
    },
    {
      "epoch": 3.2030099263528657,
      "eval_loss": 0.007326140534132719,
      "eval_runtime": 15.7231,
      "eval_samples_per_second": 6.36,
      "eval_steps_per_second": 1.59,
      "step": 1250
    },
    {
      "epoch": 3.2055715658021136,
      "grad_norm": 0.019312283024191856,
      "learning_rate": 3.429400403522125e-05,
      "loss": 0.0047,
      "step": 1251
    },
    {
      "epoch": 3.208133205251361,
      "grad_norm": 0.018146058544516563,
      "learning_rate": 3.420905557960911e-05,
      "loss": 0.0039,
      "step": 1252
    },
    {
      "epoch": 3.2106948447006083,
      "grad_norm": 0.016642430797219276,
      "learning_rate": 3.412415772434368e-05,
      "loss": 0.0037,
      "step": 1253
    },
    {
      "epoch": 3.213256484149856,
      "grad_norm": 0.018599150702357292,
      "learning_rate": 3.4039310741470855e-05,
      "loss": 0.0046,
      "step": 1254
    },
    {
      "epoch": 3.2158181235991035,
      "grad_norm": 0.01898500695824623,
      "learning_rate": 3.3954514902873425e-05,
      "loss": 0.0053,
      "step": 1255
    },
    {
      "epoch": 3.218379763048351,
      "grad_norm": 0.035850610584020615,
      "learning_rate": 3.3869770480270354e-05,
      "loss": 0.0046,
      "step": 1256
    },
    {
      "epoch": 3.2209414024975986,
      "grad_norm": 0.017346277832984924,
      "learning_rate": 3.3785077745215873e-05,
      "loss": 0.0043,
      "step": 1257
    },
    {
      "epoch": 3.223503041946846,
      "grad_norm": 0.02053334005177021,
      "learning_rate": 3.370043696909849e-05,
      "loss": 0.005,
      "step": 1258
    },
    {
      "epoch": 3.2260646813960934,
      "grad_norm": 0.012268176302313805,
      "learning_rate": 3.36158484231403e-05,
      "loss": 0.0022,
      "step": 1259
    },
    {
      "epoch": 3.228626320845341,
      "grad_norm": 0.021979577839374542,
      "learning_rate": 3.3531312378396026e-05,
      "loss": 0.006,
      "step": 1260
    },
    {
      "epoch": 3.2311879602945885,
      "grad_norm": 0.01328719686716795,
      "learning_rate": 3.34468291057521e-05,
      "loss": 0.003,
      "step": 1261
    },
    {
      "epoch": 3.233749599743836,
      "grad_norm": 0.019954100251197815,
      "learning_rate": 3.3362398875925904e-05,
      "loss": 0.0057,
      "step": 1262
    },
    {
      "epoch": 3.2363112391930837,
      "grad_norm": 0.015923641622066498,
      "learning_rate": 3.327802195946486e-05,
      "loss": 0.0042,
      "step": 1263
    },
    {
      "epoch": 3.238872878642331,
      "grad_norm": 0.018225105479359627,
      "learning_rate": 3.319369862674547e-05,
      "loss": 0.0047,
      "step": 1264
    },
    {
      "epoch": 3.2414345180915785,
      "grad_norm": 0.02089548483490944,
      "learning_rate": 3.310942914797265e-05,
      "loss": 0.0057,
      "step": 1265
    },
    {
      "epoch": 3.2439961575408263,
      "grad_norm": 0.015877477824687958,
      "learning_rate": 3.3025213793178646e-05,
      "loss": 0.004,
      "step": 1266
    },
    {
      "epoch": 3.2465577969900736,
      "grad_norm": 0.020146911963820457,
      "learning_rate": 3.294105283222234e-05,
      "loss": 0.0044,
      "step": 1267
    },
    {
      "epoch": 3.249119436439321,
      "grad_norm": 0.017449114471673965,
      "learning_rate": 3.285694653478827e-05,
      "loss": 0.0036,
      "step": 1268
    },
    {
      "epoch": 3.251681075888569,
      "grad_norm": 0.019350802525877953,
      "learning_rate": 3.277289517038582e-05,
      "loss": 0.0046,
      "step": 1269
    },
    {
      "epoch": 3.254242715337816,
      "grad_norm": 0.019596491008996964,
      "learning_rate": 3.2688899008348386e-05,
      "loss": 0.005,
      "step": 1270
    },
    {
      "epoch": 3.2568043547870635,
      "grad_norm": 0.037712205201387405,
      "learning_rate": 3.26049583178324e-05,
      "loss": 0.006,
      "step": 1271
    },
    {
      "epoch": 3.2593659942363113,
      "grad_norm": 0.016859978437423706,
      "learning_rate": 3.25210733678166e-05,
      "loss": 0.0036,
      "step": 1272
    },
    {
      "epoch": 3.2619276336855587,
      "grad_norm": 0.01952943578362465,
      "learning_rate": 3.243724442710112e-05,
      "loss": 0.0043,
      "step": 1273
    },
    {
      "epoch": 3.2644892731348065,
      "grad_norm": 0.021825823932886124,
      "learning_rate": 3.235347176430656e-05,
      "loss": 0.0054,
      "step": 1274
    },
    {
      "epoch": 3.267050912584054,
      "grad_norm": 0.027096325531601906,
      "learning_rate": 3.226975564787322e-05,
      "loss": 0.0065,
      "step": 1275
    },
    {
      "epoch": 3.267050912584054,
      "eval_loss": 0.0074441577307879925,
      "eval_runtime": 15.7576,
      "eval_samples_per_second": 6.346,
      "eval_steps_per_second": 1.587,
      "step": 1275
    },
    {
      "epoch": 3.2696125520333013,
      "grad_norm": 0.017573341727256775,
      "learning_rate": 3.218609634606021e-05,
      "loss": 0.004,
      "step": 1276
    },
    {
      "epoch": 3.2721741914825486,
      "grad_norm": 0.017359409481287003,
      "learning_rate": 3.2102494126944574e-05,
      "loss": 0.0039,
      "step": 1277
    },
    {
      "epoch": 3.2747358309317964,
      "grad_norm": 0.025902550667524338,
      "learning_rate": 3.201894925842041e-05,
      "loss": 0.0046,
      "step": 1278
    },
    {
      "epoch": 3.277297470381044,
      "grad_norm": 0.02130158431828022,
      "learning_rate": 3.1935462008198116e-05,
      "loss": 0.0034,
      "step": 1279
    },
    {
      "epoch": 3.2798591098302916,
      "grad_norm": 0.021285217255353928,
      "learning_rate": 3.185203264380338e-05,
      "loss": 0.0045,
      "step": 1280
    },
    {
      "epoch": 3.282420749279539,
      "grad_norm": 0.017796866595745087,
      "learning_rate": 3.176866143257643e-05,
      "loss": 0.0032,
      "step": 1281
    },
    {
      "epoch": 3.2849823887287863,
      "grad_norm": 0.022058211266994476,
      "learning_rate": 3.1685348641671196e-05,
      "loss": 0.004,
      "step": 1282
    },
    {
      "epoch": 3.2875440281780337,
      "grad_norm": 0.018691932782530785,
      "learning_rate": 3.1602094538054326e-05,
      "loss": 0.0037,
      "step": 1283
    },
    {
      "epoch": 3.2901056676272815,
      "grad_norm": 0.013120202347636223,
      "learning_rate": 3.151889938850445e-05,
      "loss": 0.0019,
      "step": 1284
    },
    {
      "epoch": 3.292667307076529,
      "grad_norm": 0.02618294209241867,
      "learning_rate": 3.143576345961132e-05,
      "loss": 0.0046,
      "step": 1285
    },
    {
      "epoch": 3.2952289465257767,
      "grad_norm": 0.018655234947800636,
      "learning_rate": 3.1352687017774864e-05,
      "loss": 0.0042,
      "step": 1286
    },
    {
      "epoch": 3.297790585975024,
      "grad_norm": 0.023432090878486633,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0044,
      "step": 1287
    },
    {
      "epoch": 3.3003522254242714,
      "grad_norm": 0.026196971535682678,
      "learning_rate": 3.118671365991781e-05,
      "loss": 0.0049,
      "step": 1288
    },
    {
      "epoch": 3.3029138648735192,
      "grad_norm": 0.0182013139128685,
      "learning_rate": 3.110381727574063e-05,
      "loss": 0.0034,
      "step": 1289
    },
    {
      "epoch": 3.3054755043227666,
      "grad_norm": 0.021666232496500015,
      "learning_rate": 3.1020981442305184e-05,
      "loss": 0.0039,
      "step": 1290
    },
    {
      "epoch": 3.308037143772014,
      "grad_norm": 0.021782975643873215,
      "learning_rate": 3.093820642504983e-05,
      "loss": 0.0047,
      "step": 1291
    },
    {
      "epoch": 3.3105987832212618,
      "grad_norm": 0.022409774363040924,
      "learning_rate": 3.085549248921803e-05,
      "loss": 0.0037,
      "step": 1292
    },
    {
      "epoch": 3.313160422670509,
      "grad_norm": 0.017817934975028038,
      "learning_rate": 3.0772839899857464e-05,
      "loss": 0.0038,
      "step": 1293
    },
    {
      "epoch": 3.3157220621197565,
      "grad_norm": 0.024781012907624245,
      "learning_rate": 3.06902489218193e-05,
      "loss": 0.005,
      "step": 1294
    },
    {
      "epoch": 3.3182837015690043,
      "grad_norm": 0.023359034210443497,
      "learning_rate": 3.060771981975726e-05,
      "loss": 0.0056,
      "step": 1295
    },
    {
      "epoch": 3.3208453410182517,
      "grad_norm": 0.01976236328482628,
      "learning_rate": 3.052525285812677e-05,
      "loss": 0.0054,
      "step": 1296
    },
    {
      "epoch": 3.323406980467499,
      "grad_norm": 0.030070582404732704,
      "learning_rate": 3.0442848301184158e-05,
      "loss": 0.0062,
      "step": 1297
    },
    {
      "epoch": 3.325968619916747,
      "grad_norm": 0.028238259255886078,
      "learning_rate": 3.036050641298578e-05,
      "loss": 0.006,
      "step": 1298
    },
    {
      "epoch": 3.3285302593659942,
      "grad_norm": 0.015943922102451324,
      "learning_rate": 3.0278227457387147e-05,
      "loss": 0.0036,
      "step": 1299
    },
    {
      "epoch": 3.3310918988152416,
      "grad_norm": 0.018986733630299568,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.0039,
      "step": 1300
    },
    {
      "epoch": 3.3310918988152416,
      "eval_loss": 0.007093509659171104,
      "eval_runtime": 15.7479,
      "eval_samples_per_second": 6.35,
      "eval_steps_per_second": 1.588,
      "step": 1300
    },
    {
      "epoch": 3.3336535382644894,
      "grad_norm": 0.018647341057658195,
      "learning_rate": 3.0113859398402188e-05,
      "loss": 0.0035,
      "step": 1301
    },
    {
      "epoch": 3.3362151777137368,
      "grad_norm": 0.04162399098277092,
      "learning_rate": 3.003177082171523e-05,
      "loss": 0.0153,
      "step": 1302
    },
    {
      "epoch": 3.338776817162984,
      "grad_norm": 0.038681481033563614,
      "learning_rate": 2.994974623102512e-05,
      "loss": 0.0063,
      "step": 1303
    },
    {
      "epoch": 3.341338456612232,
      "grad_norm": 0.02795899473130703,
      "learning_rate": 2.9867785889170662e-05,
      "loss": 0.0055,
      "step": 1304
    },
    {
      "epoch": 3.3439000960614793,
      "grad_norm": 0.021580150350928307,
      "learning_rate": 2.978589005878476e-05,
      "loss": 0.0048,
      "step": 1305
    },
    {
      "epoch": 3.3464617355107267,
      "grad_norm": 0.02223021350800991,
      "learning_rate": 2.9704059002293593e-05,
      "loss": 0.0067,
      "step": 1306
    },
    {
      "epoch": 3.3490233749599745,
      "grad_norm": 0.016967158764600754,
      "learning_rate": 2.9622292981915806e-05,
      "loss": 0.0037,
      "step": 1307
    },
    {
      "epoch": 3.351585014409222,
      "grad_norm": 0.022687457501888275,
      "learning_rate": 2.9540592259661637e-05,
      "loss": 0.0058,
      "step": 1308
    },
    {
      "epoch": 3.3541466538584697,
      "grad_norm": 0.022553442046046257,
      "learning_rate": 2.945895709733205e-05,
      "loss": 0.0035,
      "step": 1309
    },
    {
      "epoch": 3.356708293307717,
      "grad_norm": 0.022646233439445496,
      "learning_rate": 2.9377387756517982e-05,
      "loss": 0.0056,
      "step": 1310
    },
    {
      "epoch": 3.3592699327569644,
      "grad_norm": 0.035119421780109406,
      "learning_rate": 2.9295884498599414e-05,
      "loss": 0.009,
      "step": 1311
    },
    {
      "epoch": 3.3618315722062118,
      "grad_norm": 0.015311050228774548,
      "learning_rate": 2.9214447584744565e-05,
      "loss": 0.0041,
      "step": 1312
    },
    {
      "epoch": 3.3643932116554596,
      "grad_norm": 0.021092480048537254,
      "learning_rate": 2.9133077275909108e-05,
      "loss": 0.0047,
      "step": 1313
    },
    {
      "epoch": 3.366954851104707,
      "grad_norm": 0.017000602558255196,
      "learning_rate": 2.905177383283526e-05,
      "loss": 0.0041,
      "step": 1314
    },
    {
      "epoch": 3.3695164905539547,
      "grad_norm": 0.020628029480576515,
      "learning_rate": 2.897053751605093e-05,
      "loss": 0.0049,
      "step": 1315
    },
    {
      "epoch": 3.372078130003202,
      "grad_norm": 0.014183783903717995,
      "learning_rate": 2.8889368585869014e-05,
      "loss": 0.0029,
      "step": 1316
    },
    {
      "epoch": 3.3746397694524495,
      "grad_norm": 0.020699163898825645,
      "learning_rate": 2.880826730238643e-05,
      "loss": 0.0052,
      "step": 1317
    },
    {
      "epoch": 3.377201408901697,
      "grad_norm": 0.017421424388885498,
      "learning_rate": 2.872723392548332e-05,
      "loss": 0.0051,
      "step": 1318
    },
    {
      "epoch": 3.3797630483509447,
      "grad_norm": 0.016957523301243782,
      "learning_rate": 2.8646268714822227e-05,
      "loss": 0.0038,
      "step": 1319
    },
    {
      "epoch": 3.382324687800192,
      "grad_norm": 0.019371114671230316,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 0.0036,
      "step": 1320
    },
    {
      "epoch": 3.38488632724944,
      "grad_norm": 0.01660952717065811,
      "learning_rate": 2.8484543829783378e-05,
      "loss": 0.0045,
      "step": 1321
    },
    {
      "epoch": 3.387447966698687,
      "grad_norm": 0.014318636618554592,
      "learning_rate": 2.840378467363523e-05,
      "loss": 0.0034,
      "step": 1322
    },
    {
      "epoch": 3.3900096061479346,
      "grad_norm": 0.02716119773685932,
      "learning_rate": 2.8323094720186728e-05,
      "loss": 0.0077,
      "step": 1323
    },
    {
      "epoch": 3.3925712455971824,
      "grad_norm": 0.01730690523982048,
      "learning_rate": 2.824247422799995e-05,
      "loss": 0.0039,
      "step": 1324
    },
    {
      "epoch": 3.3951328850464297,
      "grad_norm": 0.018140211701393127,
      "learning_rate": 2.8161923455414367e-05,
      "loss": 0.0047,
      "step": 1325
    },
    {
      "epoch": 3.3951328850464297,
      "eval_loss": 0.006955994758754969,
      "eval_runtime": 15.7837,
      "eval_samples_per_second": 6.336,
      "eval_steps_per_second": 1.584,
      "step": 1325
    },
    {
      "epoch": 3.397694524495677,
      "grad_norm": 0.017170537263154984,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0033,
      "step": 1326
    },
    {
      "epoch": 3.400256163944925,
      "grad_norm": 0.01794111169874668,
      "learning_rate": 2.8001032101287095e-05,
      "loss": 0.0036,
      "step": 1327
    },
    {
      "epoch": 3.4028178033941723,
      "grad_norm": 0.035149358212947845,
      "learning_rate": 2.7920692035304052e-05,
      "loss": 0.0076,
      "step": 1328
    },
    {
      "epoch": 3.4053794428434196,
      "grad_norm": 0.015975119546055794,
      "learning_rate": 2.784042272003794e-05,
      "loss": 0.0032,
      "step": 1329
    },
    {
      "epoch": 3.4079410822926675,
      "grad_norm": 0.018400490283966064,
      "learning_rate": 2.776022441270295e-05,
      "loss": 0.0046,
      "step": 1330
    },
    {
      "epoch": 3.410502721741915,
      "grad_norm": 0.01995062455534935,
      "learning_rate": 2.7680097370285723e-05,
      "loss": 0.0051,
      "step": 1331
    },
    {
      "epoch": 3.413064361191162,
      "grad_norm": 0.022594042122364044,
      "learning_rate": 2.760004184954459e-05,
      "loss": 0.0056,
      "step": 1332
    },
    {
      "epoch": 3.41562600064041,
      "grad_norm": 0.024578507989645004,
      "learning_rate": 2.752005810700869e-05,
      "loss": 0.0047,
      "step": 1333
    },
    {
      "epoch": 3.4181876400896574,
      "grad_norm": 0.01541770901530981,
      "learning_rate": 2.7440146398977097e-05,
      "loss": 0.0036,
      "step": 1334
    },
    {
      "epoch": 3.4207492795389047,
      "grad_norm": 0.015968957915902138,
      "learning_rate": 2.7360306981518146e-05,
      "loss": 0.0038,
      "step": 1335
    },
    {
      "epoch": 3.4233109189881525,
      "grad_norm": 0.023852817714214325,
      "learning_rate": 2.7280540110468455e-05,
      "loss": 0.005,
      "step": 1336
    },
    {
      "epoch": 3.4258725584374,
      "grad_norm": 0.018949022516608238,
      "learning_rate": 2.720084604143218e-05,
      "loss": 0.0047,
      "step": 1337
    },
    {
      "epoch": 3.4284341978866473,
      "grad_norm": 0.018564656376838684,
      "learning_rate": 2.712122502978024e-05,
      "loss": 0.0049,
      "step": 1338
    },
    {
      "epoch": 3.430995837335895,
      "grad_norm": 0.01999684050679207,
      "learning_rate": 2.7041677330649407e-05,
      "loss": 0.0041,
      "step": 1339
    },
    {
      "epoch": 3.4335574767851424,
      "grad_norm": 0.014954477548599243,
      "learning_rate": 2.6962203198941587e-05,
      "loss": 0.0026,
      "step": 1340
    },
    {
      "epoch": 3.43611911623439,
      "grad_norm": 0.023138830438256264,
      "learning_rate": 2.6882802889322834e-05,
      "loss": 0.0051,
      "step": 1341
    },
    {
      "epoch": 3.4386807556836376,
      "grad_norm": 0.01983695477247238,
      "learning_rate": 2.680347665622275e-05,
      "loss": 0.0032,
      "step": 1342
    },
    {
      "epoch": 3.441242395132885,
      "grad_norm": 0.02612839825451374,
      "learning_rate": 2.672422475383356e-05,
      "loss": 0.0053,
      "step": 1343
    },
    {
      "epoch": 3.443804034582133,
      "grad_norm": 0.015107940882444382,
      "learning_rate": 2.6645047436109226e-05,
      "loss": 0.0037,
      "step": 1344
    },
    {
      "epoch": 3.44636567403138,
      "grad_norm": 0.013161804527044296,
      "learning_rate": 2.656594495676482e-05,
      "loss": 0.003,
      "step": 1345
    },
    {
      "epoch": 3.4489273134806275,
      "grad_norm": 0.015442034229636192,
      "learning_rate": 2.6486917569275528e-05,
      "loss": 0.0031,
      "step": 1346
    },
    {
      "epoch": 3.451488952929875,
      "grad_norm": 0.019541800022125244,
      "learning_rate": 2.64079655268759e-05,
      "loss": 0.0045,
      "step": 1347
    },
    {
      "epoch": 3.4540505923791227,
      "grad_norm": 0.01665390469133854,
      "learning_rate": 2.632908908255911e-05,
      "loss": 0.0031,
      "step": 1348
    },
    {
      "epoch": 3.45661223182837,
      "grad_norm": 0.018763909116387367,
      "learning_rate": 2.6250288489076074e-05,
      "loss": 0.0038,
      "step": 1349
    },
    {
      "epoch": 3.459173871277618,
      "grad_norm": 0.031971413642168045,
      "learning_rate": 2.6171563998934605e-05,
      "loss": 0.0046,
      "step": 1350
    },
    {
      "epoch": 3.459173871277618,
      "eval_loss": 0.006668676156550646,
      "eval_runtime": 15.761,
      "eval_samples_per_second": 6.345,
      "eval_steps_per_second": 1.586,
      "step": 1350
    },
    {
      "epoch": 3.4617355107268653,
      "grad_norm": 0.020659996196627617,
      "learning_rate": 2.6092915864398722e-05,
      "loss": 0.0036,
      "step": 1351
    },
    {
      "epoch": 3.4642971501761126,
      "grad_norm": 0.02322494424879551,
      "learning_rate": 2.6014344337487707e-05,
      "loss": 0.0041,
      "step": 1352
    },
    {
      "epoch": 3.46685878962536,
      "grad_norm": 0.018928896635770798,
      "learning_rate": 2.5935849669975378e-05,
      "loss": 0.0043,
      "step": 1353
    },
    {
      "epoch": 3.469420429074608,
      "grad_norm": 0.02125394716858864,
      "learning_rate": 2.5857432113389273e-05,
      "loss": 0.0047,
      "step": 1354
    },
    {
      "epoch": 3.471982068523855,
      "grad_norm": 0.02026151679456234,
      "learning_rate": 2.5779091919009877e-05,
      "loss": 0.0031,
      "step": 1355
    },
    {
      "epoch": 3.474543707973103,
      "grad_norm": 0.01922105997800827,
      "learning_rate": 2.57008293378697e-05,
      "loss": 0.004,
      "step": 1356
    },
    {
      "epoch": 3.4771053474223503,
      "grad_norm": 0.024818353354930878,
      "learning_rate": 2.5622644620752606e-05,
      "loss": 0.0043,
      "step": 1357
    },
    {
      "epoch": 3.4796669868715977,
      "grad_norm": 0.03687607869505882,
      "learning_rate": 2.554453801819291e-05,
      "loss": 0.007,
      "step": 1358
    },
    {
      "epoch": 3.4822286263208455,
      "grad_norm": 0.02132255584001541,
      "learning_rate": 2.546650978047467e-05,
      "loss": 0.0046,
      "step": 1359
    },
    {
      "epoch": 3.484790265770093,
      "grad_norm": 0.021544774994254112,
      "learning_rate": 2.5388560157630765e-05,
      "loss": 0.0045,
      "step": 1360
    },
    {
      "epoch": 3.4873519052193402,
      "grad_norm": 0.018406540155410767,
      "learning_rate": 2.5310689399442223e-05,
      "loss": 0.0043,
      "step": 1361
    },
    {
      "epoch": 3.489913544668588,
      "grad_norm": 0.02386508323252201,
      "learning_rate": 2.5232897755437344e-05,
      "loss": 0.0035,
      "step": 1362
    },
    {
      "epoch": 3.4924751841178354,
      "grad_norm": 0.020438361912965775,
      "learning_rate": 2.5155185474890897e-05,
      "loss": 0.0042,
      "step": 1363
    },
    {
      "epoch": 3.495036823567083,
      "grad_norm": 0.0224450696259737,
      "learning_rate": 2.5077552806823318e-05,
      "loss": 0.0053,
      "step": 1364
    },
    {
      "epoch": 3.4975984630163306,
      "grad_norm": 0.024398161098361015,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0051,
      "step": 1365
    },
    {
      "epoch": 3.500160102465578,
      "grad_norm": 0.020685985684394836,
      "learning_rate": 2.4922527302930388e-05,
      "loss": 0.0033,
      "step": 1366
    },
    {
      "epoch": 3.5027217419148253,
      "grad_norm": 0.027152569964528084,
      "learning_rate": 2.4845134963867207e-05,
      "loss": 0.0061,
      "step": 1367
    },
    {
      "epoch": 3.505283381364073,
      "grad_norm": 0.022943297401070595,
      "learning_rate": 2.476782323080574e-05,
      "loss": 0.0064,
      "step": 1368
    },
    {
      "epoch": 3.5078450208133205,
      "grad_norm": 0.020930426195263863,
      "learning_rate": 2.4690592351482934e-05,
      "loss": 0.0039,
      "step": 1369
    },
    {
      "epoch": 3.510406660262568,
      "grad_norm": 0.02447371743619442,
      "learning_rate": 2.461344257337662e-05,
      "loss": 0.0049,
      "step": 1370
    },
    {
      "epoch": 3.5129682997118157,
      "grad_norm": 0.016021478921175003,
      "learning_rate": 2.4536374143704838e-05,
      "loss": 0.0033,
      "step": 1371
    },
    {
      "epoch": 3.515529939161063,
      "grad_norm": 0.0182783342897892,
      "learning_rate": 2.4459387309424865e-05,
      "loss": 0.0039,
      "step": 1372
    },
    {
      "epoch": 3.518091578610311,
      "grad_norm": 0.020285986363887787,
      "learning_rate": 2.4382482317232568e-05,
      "loss": 0.0034,
      "step": 1373
    },
    {
      "epoch": 3.520653218059558,
      "grad_norm": 0.023470548912882805,
      "learning_rate": 2.430565941356157e-05,
      "loss": 0.0047,
      "step": 1374
    },
    {
      "epoch": 3.5232148575088056,
      "grad_norm": 0.02091079019010067,
      "learning_rate": 2.422891884458241e-05,
      "loss": 0.0047,
      "step": 1375
    },
    {
      "epoch": 3.5232148575088056,
      "eval_loss": 0.0071318005211651325,
      "eval_runtime": 15.7705,
      "eval_samples_per_second": 6.341,
      "eval_steps_per_second": 1.585,
      "step": 1375
    },
    {
      "epoch": 3.525776496958053,
      "grad_norm": 0.028989002108573914,
      "learning_rate": 2.4152260856201787e-05,
      "loss": 0.0064,
      "step": 1376
    },
    {
      "epoch": 3.5283381364073008,
      "grad_norm": 0.023004917427897453,
      "learning_rate": 2.4075685694061822e-05,
      "loss": 0.0034,
      "step": 1377
    },
    {
      "epoch": 3.530899775856548,
      "grad_norm": 0.02438783086836338,
      "learning_rate": 2.399919360353923e-05,
      "loss": 0.005,
      "step": 1378
    },
    {
      "epoch": 3.533461415305796,
      "grad_norm": 0.016736894845962524,
      "learning_rate": 2.39227848297445e-05,
      "loss": 0.004,
      "step": 1379
    },
    {
      "epoch": 3.5360230547550433,
      "grad_norm": 0.019711444154381752,
      "learning_rate": 2.3846459617521128e-05,
      "loss": 0.0048,
      "step": 1380
    },
    {
      "epoch": 3.5385846942042907,
      "grad_norm": 0.020827678963541985,
      "learning_rate": 2.3770218211444907e-05,
      "loss": 0.0044,
      "step": 1381
    },
    {
      "epoch": 3.541146333653538,
      "grad_norm": 0.02978433296084404,
      "learning_rate": 2.369406085582302e-05,
      "loss": 0.0061,
      "step": 1382
    },
    {
      "epoch": 3.543707973102786,
      "grad_norm": 0.022353358566761017,
      "learning_rate": 2.361798779469336e-05,
      "loss": 0.0037,
      "step": 1383
    },
    {
      "epoch": 3.546269612552033,
      "grad_norm": 0.017815707251429558,
      "learning_rate": 2.354199927182371e-05,
      "loss": 0.0035,
      "step": 1384
    },
    {
      "epoch": 3.548831252001281,
      "grad_norm": 0.03284938260912895,
      "learning_rate": 2.346609553071093e-05,
      "loss": 0.0053,
      "step": 1385
    },
    {
      "epoch": 3.5513928914505284,
      "grad_norm": 0.016769099980592728,
      "learning_rate": 2.3390276814580204e-05,
      "loss": 0.0039,
      "step": 1386
    },
    {
      "epoch": 3.5539545308997758,
      "grad_norm": 0.01981167122721672,
      "learning_rate": 2.331454336638431e-05,
      "loss": 0.0046,
      "step": 1387
    },
    {
      "epoch": 3.556516170349023,
      "grad_norm": 0.016274696215987206,
      "learning_rate": 2.323889542880273e-05,
      "loss": 0.0032,
      "step": 1388
    },
    {
      "epoch": 3.559077809798271,
      "grad_norm": 0.02920779027044773,
      "learning_rate": 2.3163333244240987e-05,
      "loss": 0.0057,
      "step": 1389
    },
    {
      "epoch": 3.5616394492475183,
      "grad_norm": 0.016290957108139992,
      "learning_rate": 2.308785705482982e-05,
      "loss": 0.003,
      "step": 1390
    },
    {
      "epoch": 3.564201088696766,
      "grad_norm": 0.014574081636965275,
      "learning_rate": 2.3012467102424373e-05,
      "loss": 0.0033,
      "step": 1391
    },
    {
      "epoch": 3.5667627281460135,
      "grad_norm": 0.020299769937992096,
      "learning_rate": 2.2937163628603435e-05,
      "loss": 0.0035,
      "step": 1392
    },
    {
      "epoch": 3.569324367595261,
      "grad_norm": 0.029202919453382492,
      "learning_rate": 2.286194687466875e-05,
      "loss": 0.0033,
      "step": 1393
    },
    {
      "epoch": 3.5718860070445086,
      "grad_norm": 0.024974342435598373,
      "learning_rate": 2.2786817081644147e-05,
      "loss": 0.0042,
      "step": 1394
    },
    {
      "epoch": 3.574447646493756,
      "grad_norm": 0.028322022408246994,
      "learning_rate": 2.2711774490274766e-05,
      "loss": 0.0048,
      "step": 1395
    },
    {
      "epoch": 3.5770092859430034,
      "grad_norm": 0.01611924171447754,
      "learning_rate": 2.263681934102639e-05,
      "loss": 0.0031,
      "step": 1396
    },
    {
      "epoch": 3.579570925392251,
      "grad_norm": 0.026567207649350166,
      "learning_rate": 2.2561951874084524e-05,
      "loss": 0.0046,
      "step": 1397
    },
    {
      "epoch": 3.5821325648414986,
      "grad_norm": 0.017477042973041534,
      "learning_rate": 2.2487172329353746e-05,
      "loss": 0.0029,
      "step": 1398
    },
    {
      "epoch": 3.584694204290746,
      "grad_norm": 0.03424292802810669,
      "learning_rate": 2.2412480946456893e-05,
      "loss": 0.0057,
      "step": 1399
    },
    {
      "epoch": 3.5872558437399937,
      "grad_norm": 0.02512899786233902,
      "learning_rate": 2.233787796473432e-05,
      "loss": 0.0039,
      "step": 1400
    },
    {
      "epoch": 3.5872558437399937,
      "eval_loss": 0.00698334164917469,
      "eval_runtime": 15.7713,
      "eval_samples_per_second": 6.341,
      "eval_steps_per_second": 1.585,
      "step": 1400
    },
    {
      "epoch": 3.589817483189241,
      "grad_norm": 0.02017313428223133,
      "learning_rate": 2.2263363623243054e-05,
      "loss": 0.0043,
      "step": 1401
    },
    {
      "epoch": 3.592379122638489,
      "grad_norm": 0.037246350198984146,
      "learning_rate": 2.218893816075615e-05,
      "loss": 0.0069,
      "step": 1402
    },
    {
      "epoch": 3.5949407620877363,
      "grad_norm": 0.015876617282629013,
      "learning_rate": 2.2114601815761808e-05,
      "loss": 0.0035,
      "step": 1403
    },
    {
      "epoch": 3.5975024015369836,
      "grad_norm": 0.01643594354391098,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0039,
      "step": 1404
    },
    {
      "epoch": 3.600064040986231,
      "grad_norm": 0.023170500993728638,
      "learning_rate": 2.1966197430775053e-05,
      "loss": 0.0045,
      "step": 1405
    },
    {
      "epoch": 3.602625680435479,
      "grad_norm": 0.03175827115774155,
      "learning_rate": 2.1892129866328232e-05,
      "loss": 0.0063,
      "step": 1406
    },
    {
      "epoch": 3.605187319884726,
      "grad_norm": 0.011946959421038628,
      "learning_rate": 2.1818152370463523e-05,
      "loss": 0.0025,
      "step": 1407
    },
    {
      "epoch": 3.607748959333974,
      "grad_norm": 0.02114485576748848,
      "learning_rate": 2.174426518023373e-05,
      "loss": 0.0045,
      "step": 1408
    },
    {
      "epoch": 3.6103105987832214,
      "grad_norm": 0.017472948879003525,
      "learning_rate": 2.1670468532402215e-05,
      "loss": 0.0035,
      "step": 1409
    },
    {
      "epoch": 3.6128722382324687,
      "grad_norm": 0.02146715112030506,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 0.004,
      "step": 1410
    },
    {
      "epoch": 3.615433877681716,
      "grad_norm": 0.037003446370363235,
      "learning_rate": 2.152314780953611e-05,
      "loss": 0.0025,
      "step": 1411
    },
    {
      "epoch": 3.617995517130964,
      "grad_norm": 0.02539096027612686,
      "learning_rate": 2.144962420657461e-05,
      "loss": 0.0043,
      "step": 1412
    },
    {
      "epoch": 3.6205571565802113,
      "grad_norm": 0.020174555480480194,
      "learning_rate": 2.1376192090156044e-05,
      "loss": 0.0042,
      "step": 1413
    },
    {
      "epoch": 3.623118796029459,
      "grad_norm": 0.028370022773742676,
      "learning_rate": 2.1302851695585535e-05,
      "loss": 0.0049,
      "step": 1414
    },
    {
      "epoch": 3.6256804354787064,
      "grad_norm": 0.03755459561944008,
      "learning_rate": 2.122960325787432e-05,
      "loss": 0.0044,
      "step": 1415
    },
    {
      "epoch": 3.628242074927954,
      "grad_norm": 0.021341577172279358,
      "learning_rate": 2.115644701173899e-05,
      "loss": 0.004,
      "step": 1416
    },
    {
      "epoch": 3.630803714377201,
      "grad_norm": 0.01897352933883667,
      "learning_rate": 2.1083383191600674e-05,
      "loss": 0.0041,
      "step": 1417
    },
    {
      "epoch": 3.633365353826449,
      "grad_norm": 0.013568758964538574,
      "learning_rate": 2.1010412031584386e-05,
      "loss": 0.0028,
      "step": 1418
    },
    {
      "epoch": 3.6359269932756964,
      "grad_norm": 0.01961873658001423,
      "learning_rate": 2.0937533765518187e-05,
      "loss": 0.0037,
      "step": 1419
    },
    {
      "epoch": 3.638488632724944,
      "grad_norm": 0.04281854256987572,
      "learning_rate": 2.086474862693244e-05,
      "loss": 0.0062,
      "step": 1420
    },
    {
      "epoch": 3.6410502721741915,
      "grad_norm": 0.0375184640288353,
      "learning_rate": 2.0792056849059155e-05,
      "loss": 0.0059,
      "step": 1421
    },
    {
      "epoch": 3.643611911623439,
      "grad_norm": 0.027061646804213524,
      "learning_rate": 2.0719458664831165e-05,
      "loss": 0.0062,
      "step": 1422
    },
    {
      "epoch": 3.6461735510726863,
      "grad_norm": 0.01808282546699047,
      "learning_rate": 2.064695430688134e-05,
      "loss": 0.0033,
      "step": 1423
    },
    {
      "epoch": 3.648735190521934,
      "grad_norm": 0.023773295804858208,
      "learning_rate": 2.0574544007541962e-05,
      "loss": 0.0041,
      "step": 1424
    },
    {
      "epoch": 3.6512968299711814,
      "grad_norm": 0.022816844284534454,
      "learning_rate": 2.050222799884387e-05,
      "loss": 0.0049,
      "step": 1425
    },
    {
      "epoch": 3.6512968299711814,
      "eval_loss": 0.007150666788220406,
      "eval_runtime": 15.8192,
      "eval_samples_per_second": 6.321,
      "eval_steps_per_second": 1.58,
      "step": 1425
    },
    {
      "epoch": 3.6538584694204292,
      "grad_norm": 0.0231269933283329,
      "learning_rate": 2.043000651251575e-05,
      "loss": 0.0059,
      "step": 1426
    },
    {
      "epoch": 3.6564201088696766,
      "grad_norm": 0.018816029652953148,
      "learning_rate": 2.0357879779983435e-05,
      "loss": 0.0039,
      "step": 1427
    },
    {
      "epoch": 3.658981748318924,
      "grad_norm": 0.023829815909266472,
      "learning_rate": 2.0285848032369137e-05,
      "loss": 0.0074,
      "step": 1428
    },
    {
      "epoch": 3.661543387768172,
      "grad_norm": 0.03465423360466957,
      "learning_rate": 2.0213911500490647e-05,
      "loss": 0.0054,
      "step": 1429
    },
    {
      "epoch": 3.664105027217419,
      "grad_norm": 0.024734264239668846,
      "learning_rate": 2.0142070414860704e-05,
      "loss": 0.0045,
      "step": 1430
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.015112842433154583,
      "learning_rate": 2.0070325005686147e-05,
      "loss": 0.0024,
      "step": 1431
    },
    {
      "epoch": 3.6692283061159143,
      "grad_norm": 0.017952393740415573,
      "learning_rate": 1.9998675502867286e-05,
      "loss": 0.0043,
      "step": 1432
    },
    {
      "epoch": 3.6717899455651617,
      "grad_norm": 0.020078269764780998,
      "learning_rate": 1.9927122135997063e-05,
      "loss": 0.0041,
      "step": 1433
    },
    {
      "epoch": 3.674351585014409,
      "grad_norm": 0.01992672309279442,
      "learning_rate": 1.9855665134360386e-05,
      "loss": 0.0043,
      "step": 1434
    },
    {
      "epoch": 3.676913224463657,
      "grad_norm": 0.016725733876228333,
      "learning_rate": 1.9784304726933383e-05,
      "loss": 0.0035,
      "step": 1435
    },
    {
      "epoch": 3.6794748639129042,
      "grad_norm": 0.021456018090248108,
      "learning_rate": 1.971304114238263e-05,
      "loss": 0.0038,
      "step": 1436
    },
    {
      "epoch": 3.682036503362152,
      "grad_norm": 0.017350321635603905,
      "learning_rate": 1.9641874609064443e-05,
      "loss": 0.0043,
      "step": 1437
    },
    {
      "epoch": 3.6845981428113994,
      "grad_norm": 0.02247788943350315,
      "learning_rate": 1.957080535502418e-05,
      "loss": 0.0065,
      "step": 1438
    },
    {
      "epoch": 3.687159782260647,
      "grad_norm": 0.021594872698187828,
      "learning_rate": 1.949983360799543e-05,
      "loss": 0.0037,
      "step": 1439
    },
    {
      "epoch": 3.689721421709894,
      "grad_norm": 0.020270483568310738,
      "learning_rate": 1.942895959539939e-05,
      "loss": 0.0034,
      "step": 1440
    },
    {
      "epoch": 3.692283061159142,
      "grad_norm": 0.020229430869221687,
      "learning_rate": 1.9358183544344044e-05,
      "loss": 0.0046,
      "step": 1441
    },
    {
      "epoch": 3.6948447006083893,
      "grad_norm": 0.017405830323696136,
      "learning_rate": 1.928750568162347e-05,
      "loss": 0.0033,
      "step": 1442
    },
    {
      "epoch": 3.697406340057637,
      "grad_norm": 0.02286132425069809,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0053,
      "step": 1443
    },
    {
      "epoch": 3.6999679795068845,
      "grad_norm": 0.02939784526824951,
      "learning_rate": 1.914644542678903e-05,
      "loss": 0.0074,
      "step": 1444
    },
    {
      "epoch": 3.702529618956132,
      "grad_norm": 0.014939618296921253,
      "learning_rate": 1.9076063486687256e-05,
      "loss": 0.0027,
      "step": 1445
    },
    {
      "epoch": 3.7050912584053792,
      "grad_norm": 0.024590235203504562,
      "learning_rate": 1.9005780638942982e-05,
      "loss": 0.0084,
      "step": 1446
    },
    {
      "epoch": 3.707652897854627,
      "grad_norm": 0.017727019265294075,
      "learning_rate": 1.8935597108769893e-05,
      "loss": 0.0045,
      "step": 1447
    },
    {
      "epoch": 3.7102145373038744,
      "grad_norm": 0.020679691806435585,
      "learning_rate": 1.8865513121063383e-05,
      "loss": 0.0042,
      "step": 1448
    },
    {
      "epoch": 3.712776176753122,
      "grad_norm": 0.019846631214022636,
      "learning_rate": 1.879552890039987e-05,
      "loss": 0.0035,
      "step": 1449
    },
    {
      "epoch": 3.7153378162023696,
      "grad_norm": 0.01740499958395958,
      "learning_rate": 1.8725644671036126e-05,
      "loss": 0.0045,
      "step": 1450
    },
    {
      "epoch": 3.7153378162023696,
      "eval_loss": 0.0069673252291977406,
      "eval_runtime": 15.759,
      "eval_samples_per_second": 6.346,
      "eval_steps_per_second": 1.586,
      "step": 1450
    },
    {
      "epoch": 3.717899455651617,
      "grad_norm": 0.022572670131921768,
      "learning_rate": 1.8655860656908497e-05,
      "loss": 0.0071,
      "step": 1451
    },
    {
      "epoch": 3.7204610951008643,
      "grad_norm": 0.01428269874304533,
      "learning_rate": 1.8586177081632162e-05,
      "loss": 0.0028,
      "step": 1452
    },
    {
      "epoch": 3.723022734550112,
      "grad_norm": 0.027408719062805176,
      "learning_rate": 1.8516594168500513e-05,
      "loss": 0.0023,
      "step": 1453
    },
    {
      "epoch": 3.7255843739993595,
      "grad_norm": 0.016997095197439194,
      "learning_rate": 1.844711214048434e-05,
      "loss": 0.0031,
      "step": 1454
    },
    {
      "epoch": 3.7281460134486073,
      "grad_norm": 0.027528347447514534,
      "learning_rate": 1.837773122023114e-05,
      "loss": 0.0044,
      "step": 1455
    },
    {
      "epoch": 3.7307076528978547,
      "grad_norm": 0.015830373391509056,
      "learning_rate": 1.8308451630064484e-05,
      "loss": 0.0035,
      "step": 1456
    },
    {
      "epoch": 3.733269292347102,
      "grad_norm": 0.022276075556874275,
      "learning_rate": 1.823927359198321e-05,
      "loss": 0.0046,
      "step": 1457
    },
    {
      "epoch": 3.7358309317963494,
      "grad_norm": 0.021877508610486984,
      "learning_rate": 1.8170197327660733e-05,
      "loss": 0.004,
      "step": 1458
    },
    {
      "epoch": 3.738392571245597,
      "grad_norm": 0.017875684425234795,
      "learning_rate": 1.8101223058444333e-05,
      "loss": 0.0035,
      "step": 1459
    },
    {
      "epoch": 3.7409542106948446,
      "grad_norm": 0.022446325048804283,
      "learning_rate": 1.803235100535452e-05,
      "loss": 0.0059,
      "step": 1460
    },
    {
      "epoch": 3.7435158501440924,
      "grad_norm": 0.02225191332399845,
      "learning_rate": 1.7963581389084178e-05,
      "loss": 0.003,
      "step": 1461
    },
    {
      "epoch": 3.7460774895933397,
      "grad_norm": 0.017582381144165993,
      "learning_rate": 1.7894914429998012e-05,
      "loss": 0.0029,
      "step": 1462
    },
    {
      "epoch": 3.748639129042587,
      "grad_norm": 0.018602004274725914,
      "learning_rate": 1.782635034813176e-05,
      "loss": 0.0035,
      "step": 1463
    },
    {
      "epoch": 3.751200768491835,
      "grad_norm": 0.017477497458457947,
      "learning_rate": 1.7757889363191483e-05,
      "loss": 0.0032,
      "step": 1464
    },
    {
      "epoch": 3.7537624079410823,
      "grad_norm": 0.0241811852902174,
      "learning_rate": 1.7689531694552863e-05,
      "loss": 0.0049,
      "step": 1465
    },
    {
      "epoch": 3.7563240473903297,
      "grad_norm": 0.012605165131390095,
      "learning_rate": 1.762127756126056e-05,
      "loss": 0.0024,
      "step": 1466
    },
    {
      "epoch": 3.7588856868395775,
      "grad_norm": 0.028144102543592453,
      "learning_rate": 1.7553127182027455e-05,
      "loss": 0.0064,
      "step": 1467
    },
    {
      "epoch": 3.761447326288825,
      "grad_norm": 0.01943473145365715,
      "learning_rate": 1.748508077523393e-05,
      "loss": 0.0042,
      "step": 1468
    },
    {
      "epoch": 3.764008965738072,
      "grad_norm": 0.020696593448519707,
      "learning_rate": 1.7417138558927244e-05,
      "loss": 0.0042,
      "step": 1469
    },
    {
      "epoch": 3.76657060518732,
      "grad_norm": 0.021954044699668884,
      "learning_rate": 1.734930075082076e-05,
      "loss": 0.0039,
      "step": 1470
    },
    {
      "epoch": 3.7691322446365674,
      "grad_norm": 0.022788338363170624,
      "learning_rate": 1.728156756829325e-05,
      "loss": 0.0043,
      "step": 1471
    },
    {
      "epoch": 3.771693884085815,
      "grad_norm": 0.019136719405651093,
      "learning_rate": 1.7213939228388287e-05,
      "loss": 0.0029,
      "step": 1472
    },
    {
      "epoch": 3.7742555235350626,
      "grad_norm": 0.03452589362859726,
      "learning_rate": 1.714641594781347e-05,
      "loss": 0.0046,
      "step": 1473
    },
    {
      "epoch": 3.77681716298431,
      "grad_norm": 0.02517046593129635,
      "learning_rate": 1.7078997942939695e-05,
      "loss": 0.0057,
      "step": 1474
    },
    {
      "epoch": 3.7793788024335573,
      "grad_norm": 0.02047286182641983,
      "learning_rate": 1.7011685429800595e-05,
      "loss": 0.0043,
      "step": 1475
    },
    {
      "epoch": 3.7793788024335573,
      "eval_loss": 0.006774227134883404,
      "eval_runtime": 15.8345,
      "eval_samples_per_second": 6.315,
      "eval_steps_per_second": 1.579,
      "step": 1475
    },
    {
      "epoch": 3.781940441882805,
      "grad_norm": 0.018452035263180733,
      "learning_rate": 1.6944478624091704e-05,
      "loss": 0.0036,
      "step": 1476
    },
    {
      "epoch": 3.7845020813320525,
      "grad_norm": 0.020415108650922775,
      "learning_rate": 1.6877377741169827e-05,
      "loss": 0.0025,
      "step": 1477
    },
    {
      "epoch": 3.7870637207813003,
      "grad_norm": 0.030411340296268463,
      "learning_rate": 1.6810382996052394e-05,
      "loss": 0.0052,
      "step": 1478
    },
    {
      "epoch": 3.7896253602305476,
      "grad_norm": 0.016582481563091278,
      "learning_rate": 1.6743494603416714e-05,
      "loss": 0.004,
      "step": 1479
    },
    {
      "epoch": 3.792186999679795,
      "grad_norm": 0.022396402433514595,
      "learning_rate": 1.6676712777599273e-05,
      "loss": 0.0051,
      "step": 1480
    },
    {
      "epoch": 3.7947486391290424,
      "grad_norm": 0.03476893901824951,
      "learning_rate": 1.6610037732595123e-05,
      "loss": 0.0093,
      "step": 1481
    },
    {
      "epoch": 3.79731027857829,
      "grad_norm": 0.019850311800837517,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0044,
      "step": 1482
    },
    {
      "epoch": 3.7998719180275375,
      "grad_norm": 0.025984439998865128,
      "learning_rate": 1.6477008839295203e-05,
      "loss": 0.0043,
      "step": 1483
    },
    {
      "epoch": 3.8024335574767854,
      "grad_norm": 0.01581578701734543,
      "learning_rate": 1.6410655417275917e-05,
      "loss": 0.0033,
      "step": 1484
    },
    {
      "epoch": 3.8049951969260327,
      "grad_norm": 0.013997646979987621,
      "learning_rate": 1.6344409628621484e-05,
      "loss": 0.0037,
      "step": 1485
    },
    {
      "epoch": 3.80755683637528,
      "grad_norm": 0.020644215866923332,
      "learning_rate": 1.6278271685609274e-05,
      "loss": 0.0052,
      "step": 1486
    },
    {
      "epoch": 3.8101184758245275,
      "grad_norm": 0.023151680827140808,
      "learning_rate": 1.6212241800171052e-05,
      "loss": 0.004,
      "step": 1487
    },
    {
      "epoch": 3.8126801152737753,
      "grad_norm": 0.020557168871164322,
      "learning_rate": 1.614632018389231e-05,
      "loss": 0.0039,
      "step": 1488
    },
    {
      "epoch": 3.8152417547230226,
      "grad_norm": 0.018763143569231033,
      "learning_rate": 1.6080507048011666e-05,
      "loss": 0.0037,
      "step": 1489
    },
    {
      "epoch": 3.8178033941722704,
      "grad_norm": 0.019956249743700027,
      "learning_rate": 1.6014802603420044e-05,
      "loss": 0.0036,
      "step": 1490
    },
    {
      "epoch": 3.820365033621518,
      "grad_norm": 0.01779358461499214,
      "learning_rate": 1.5949207060660138e-05,
      "loss": 0.0032,
      "step": 1491
    },
    {
      "epoch": 3.822926673070765,
      "grad_norm": 0.01736687310039997,
      "learning_rate": 1.5883720629925687e-05,
      "loss": 0.004,
      "step": 1492
    },
    {
      "epoch": 3.8254883125200125,
      "grad_norm": 0.036861103028059006,
      "learning_rate": 1.58183435210607e-05,
      "loss": 0.0054,
      "step": 1493
    },
    {
      "epoch": 3.8280499519692603,
      "grad_norm": 0.023185743018984795,
      "learning_rate": 1.5753075943558987e-05,
      "loss": 0.0057,
      "step": 1494
    },
    {
      "epoch": 3.8306115914185077,
      "grad_norm": 0.02160869538784027,
      "learning_rate": 1.5687918106563326e-05,
      "loss": 0.0057,
      "step": 1495
    },
    {
      "epoch": 3.8331732308677555,
      "grad_norm": 0.021889541298151016,
      "learning_rate": 1.5622870218864833e-05,
      "loss": 0.0039,
      "step": 1496
    },
    {
      "epoch": 3.835734870317003,
      "grad_norm": 0.020682981237769127,
      "learning_rate": 1.5557932488902338e-05,
      "loss": 0.0065,
      "step": 1497
    },
    {
      "epoch": 3.8382965097662503,
      "grad_norm": 0.018665673211216927,
      "learning_rate": 1.5493105124761657e-05,
      "loss": 0.004,
      "step": 1498
    },
    {
      "epoch": 3.840858149215498,
      "grad_norm": 0.015613999217748642,
      "learning_rate": 1.542838833417493e-05,
      "loss": 0.0036,
      "step": 1499
    },
    {
      "epoch": 3.8434197886647454,
      "grad_norm": 0.018136585131287575,
      "learning_rate": 1.536378232452003e-05,
      "loss": 0.0036,
      "step": 1500
    },
    {
      "epoch": 3.8434197886647454,
      "eval_loss": 0.006774452514946461,
      "eval_runtime": 15.7383,
      "eval_samples_per_second": 6.354,
      "eval_steps_per_second": 1.588,
      "step": 1500
    }
  ],
  "logging_steps": 1,
  "max_steps": 1950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9464478969624e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}