{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.993050193050193,
  "eval_steps": 500,
  "global_step": 969,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03088803088803089,
      "grad_norm": 109.2129922948738,
      "learning_rate": 5e-06,
      "loss": 0.8218,
      "step": 10
    },
    {
      "epoch": 0.06177606177606178,
      "grad_norm": 1.5509789288186628,
      "learning_rate": 5e-06,
      "loss": 0.7505,
      "step": 20
    },
    {
      "epoch": 0.09266409266409266,
      "grad_norm": 1.0237535334293637,
      "learning_rate": 5e-06,
      "loss": 0.7022,
      "step": 30
    },
    {
      "epoch": 0.12355212355212356,
      "grad_norm": 0.9555198347715455,
      "learning_rate": 5e-06,
      "loss": 0.6862,
      "step": 40
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": 0.9962768534382307,
      "learning_rate": 5e-06,
      "loss": 0.6721,
      "step": 50
    },
    {
      "epoch": 0.18532818532818532,
      "grad_norm": 1.7530907194148484,
      "learning_rate": 5e-06,
      "loss": 0.6509,
      "step": 60
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.7959383217983834,
      "learning_rate": 5e-06,
      "loss": 0.6472,
      "step": 70
    },
    {
      "epoch": 0.2471042471042471,
      "grad_norm": 0.7944327039168986,
      "learning_rate": 5e-06,
      "loss": 0.65,
      "step": 80
    },
    {
      "epoch": 0.277992277992278,
      "grad_norm": 0.6922868471685667,
      "learning_rate": 5e-06,
      "loss": 0.639,
      "step": 90
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": 0.6117044147831933,
      "learning_rate": 5e-06,
      "loss": 0.6398,
      "step": 100
    },
    {
      "epoch": 0.33976833976833976,
      "grad_norm": 0.6349747322397297,
      "learning_rate": 5e-06,
      "loss": 0.6335,
      "step": 110
    },
    {
      "epoch": 0.37065637065637064,
      "grad_norm": 0.6236670890266053,
      "learning_rate": 5e-06,
      "loss": 0.6337,
      "step": 120
    },
    {
      "epoch": 0.4015444015444015,
      "grad_norm": 0.6724570938621872,
      "learning_rate": 5e-06,
      "loss": 0.6255,
      "step": 130
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.8157933757633341,
      "learning_rate": 5e-06,
      "loss": 0.6283,
      "step": 140
    },
    {
      "epoch": 0.46332046332046334,
      "grad_norm": 0.5839495663310666,
      "learning_rate": 5e-06,
      "loss": 0.6214,
      "step": 150
    },
    {
      "epoch": 0.4942084942084942,
      "grad_norm": 0.5048909710838132,
      "learning_rate": 5e-06,
      "loss": 0.6243,
      "step": 160
    },
    {
      "epoch": 0.525096525096525,
      "grad_norm": 0.8095059876811945,
      "learning_rate": 5e-06,
      "loss": 0.6251,
      "step": 170
    },
    {
      "epoch": 0.555984555984556,
      "grad_norm": 0.5136815801780633,
      "learning_rate": 5e-06,
      "loss": 0.6145,
      "step": 180
    },
    {
      "epoch": 0.5868725868725869,
      "grad_norm": 0.6364035663779027,
      "learning_rate": 5e-06,
      "loss": 0.6298,
      "step": 190
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": 0.6844817393850995,
      "learning_rate": 5e-06,
      "loss": 0.6197,
      "step": 200
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.7483950060039181,
      "learning_rate": 5e-06,
      "loss": 0.6269,
      "step": 210
    },
    {
      "epoch": 0.6795366795366795,
      "grad_norm": 0.7350511698635498,
      "learning_rate": 5e-06,
      "loss": 0.6175,
      "step": 220
    },
    {
      "epoch": 0.7104247104247104,
      "grad_norm": 0.6246522556489467,
      "learning_rate": 5e-06,
      "loss": 0.6172,
      "step": 230
    },
    {
      "epoch": 0.7413127413127413,
      "grad_norm": 0.5845884993818068,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 240
    },
    {
      "epoch": 0.7722007722007722,
      "grad_norm": 0.6246906999878916,
      "learning_rate": 5e-06,
      "loss": 0.6191,
      "step": 250
    },
    {
      "epoch": 0.803088803088803,
      "grad_norm": 0.5725768617907299,
      "learning_rate": 5e-06,
      "loss": 0.6111,
      "step": 260
    },
    {
      "epoch": 0.833976833976834,
      "grad_norm": 0.7575125169415168,
      "learning_rate": 5e-06,
      "loss": 0.6078,
      "step": 270
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.6292537869493213,
      "learning_rate": 5e-06,
      "loss": 0.6119,
      "step": 280
    },
    {
      "epoch": 0.8957528957528957,
      "grad_norm": 0.6613666650568315,
      "learning_rate": 5e-06,
      "loss": 0.6219,
      "step": 290
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": 0.482392770012809,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 300
    },
    {
      "epoch": 0.9575289575289575,
      "grad_norm": 0.5691595473530817,
      "learning_rate": 5e-06,
      "loss": 0.6137,
      "step": 310
    },
    {
      "epoch": 0.9884169884169884,
      "grad_norm": 0.5605696956503327,
      "learning_rate": 5e-06,
      "loss": 0.6059,
      "step": 320
    },
    {
      "epoch": 0.9976833976833976,
      "eval_loss": 0.611504316329956,
      "eval_runtime": 174.6046,
      "eval_samples_per_second": 49.941,
      "eval_steps_per_second": 0.395,
      "step": 323
    },
    {
      "epoch": 1.0193050193050193,
      "grad_norm": 0.7653552774499555,
      "learning_rate": 5e-06,
      "loss": 0.577,
      "step": 330
    },
    {
      "epoch": 1.05019305019305,
      "grad_norm": 0.6717959962039358,
      "learning_rate": 5e-06,
      "loss": 0.5516,
      "step": 340
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.7810736772266839,
      "learning_rate": 5e-06,
      "loss": 0.5527,
      "step": 350
    },
    {
      "epoch": 1.111969111969112,
      "grad_norm": 0.5222987434687074,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 360
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.6086528109996991,
      "learning_rate": 5e-06,
      "loss": 0.559,
      "step": 370
    },
    {
      "epoch": 1.1737451737451738,
      "grad_norm": 0.5603581613184462,
      "learning_rate": 5e-06,
      "loss": 0.5557,
      "step": 380
    },
    {
      "epoch": 1.2046332046332047,
      "grad_norm": 0.5733679682136087,
      "learning_rate": 5e-06,
      "loss": 0.5523,
      "step": 390
    },
    {
      "epoch": 1.2355212355212355,
      "grad_norm": 0.5892263714928079,
      "learning_rate": 5e-06,
      "loss": 0.5581,
      "step": 400
    },
    {
      "epoch": 1.2664092664092665,
      "grad_norm": 0.5383912423961117,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 410
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.5266690487444351,
      "learning_rate": 5e-06,
      "loss": 0.5538,
      "step": 420
    },
    {
      "epoch": 1.3281853281853282,
      "grad_norm": 0.6329004292969694,
      "learning_rate": 5e-06,
      "loss": 0.5621,
      "step": 430
    },
    {
      "epoch": 1.359073359073359,
      "grad_norm": 0.7361457930766753,
      "learning_rate": 5e-06,
      "loss": 0.5507,
      "step": 440
    },
    {
      "epoch": 1.3899613899613898,
      "grad_norm": 0.5514849953088692,
      "learning_rate": 5e-06,
      "loss": 0.5458,
      "step": 450
    },
    {
      "epoch": 1.420849420849421,
      "grad_norm": 0.6157873717956057,
      "learning_rate": 5e-06,
      "loss": 0.5576,
      "step": 460
    },
    {
      "epoch": 1.4517374517374517,
      "grad_norm": 0.6133558219166387,
      "learning_rate": 5e-06,
      "loss": 0.5549,
      "step": 470
    },
    {
      "epoch": 1.4826254826254825,
      "grad_norm": 0.8739126560777261,
      "learning_rate": 5e-06,
      "loss": 0.5544,
      "step": 480
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.6361501246308614,
      "learning_rate": 5e-06,
      "loss": 0.5593,
      "step": 490
    },
    {
      "epoch": 1.5444015444015444,
      "grad_norm": 0.5962865704485671,
      "learning_rate": 5e-06,
      "loss": 0.5536,
      "step": 500
    },
    {
      "epoch": 1.5752895752895753,
      "grad_norm": 0.5717477466618819,
      "learning_rate": 5e-06,
      "loss": 0.5613,
      "step": 510
    },
    {
      "epoch": 1.606177606177606,
      "grad_norm": 0.66303577521287,
      "learning_rate": 5e-06,
      "loss": 0.5515,
      "step": 520
    },
    {
      "epoch": 1.637065637065637,
      "grad_norm": 0.567568871578932,
      "learning_rate": 5e-06,
      "loss": 0.552,
      "step": 530
    },
    {
      "epoch": 1.667953667953668,
      "grad_norm": 0.6260947334671597,
      "learning_rate": 5e-06,
      "loss": 0.5523,
      "step": 540
    },
    {
      "epoch": 1.698841698841699,
      "grad_norm": 0.5443908156986677,
      "learning_rate": 5e-06,
      "loss": 0.5597,
      "step": 550
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.5875127617844319,
      "learning_rate": 5e-06,
      "loss": 0.5577,
      "step": 560
    },
    {
      "epoch": 1.7606177606177607,
      "grad_norm": 0.5839768971343271,
      "learning_rate": 5e-06,
      "loss": 0.5556,
      "step": 570
    },
    {
      "epoch": 1.7915057915057915,
      "grad_norm": 0.5415996097268374,
      "learning_rate": 5e-06,
      "loss": 0.5541,
      "step": 580
    },
    {
      "epoch": 1.8223938223938223,
      "grad_norm": 0.5047758992113026,
      "learning_rate": 5e-06,
      "loss": 0.5498,
      "step": 590
    },
    {
      "epoch": 1.8532818532818531,
      "grad_norm": 0.6095158836516334,
      "learning_rate": 5e-06,
      "loss": 0.5577,
      "step": 600
    },
    {
      "epoch": 1.8841698841698842,
      "grad_norm": 0.6179499758866378,
      "learning_rate": 5e-06,
      "loss": 0.5561,
      "step": 610
    },
    {
      "epoch": 1.915057915057915,
      "grad_norm": 0.6168326581011625,
      "learning_rate": 5e-06,
      "loss": 0.5623,
      "step": 620
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 0.5503294354981652,
      "learning_rate": 5e-06,
      "loss": 0.5513,
      "step": 630
    },
    {
      "epoch": 1.9768339768339769,
      "grad_norm": 0.5514628691685661,
      "learning_rate": 5e-06,
      "loss": 0.5543,
      "step": 640
    },
    {
      "epoch": 1.9984555984555985,
      "eval_loss": 0.6036180853843689,
      "eval_runtime": 175.7287,
      "eval_samples_per_second": 49.622,
      "eval_steps_per_second": 0.393,
      "step": 647
    },
    {
      "epoch": 2.0077220077220077,
      "grad_norm": 1.1966714312564959,
      "learning_rate": 5e-06,
      "loss": 0.5432,
      "step": 650
    },
    {
      "epoch": 2.0386100386100385,
      "grad_norm": 0.6689403789809841,
      "learning_rate": 5e-06,
      "loss": 0.5094,
      "step": 660
    },
    {
      "epoch": 2.0694980694980694,
      "grad_norm": 0.61180285844113,
      "learning_rate": 5e-06,
      "loss": 0.5053,
      "step": 670
    },
    {
      "epoch": 2.1003861003861,
      "grad_norm": 0.6066089470745547,
      "learning_rate": 5e-06,
      "loss": 0.5038,
      "step": 680
    },
    {
      "epoch": 2.1312741312741315,
      "grad_norm": 0.7339359470891843,
      "learning_rate": 5e-06,
      "loss": 0.4866,
      "step": 690
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.6280327917691826,
      "learning_rate": 5e-06,
      "loss": 0.4925,
      "step": 700
    },
    {
      "epoch": 2.193050193050193,
      "grad_norm": 0.6228681526915294,
      "learning_rate": 5e-06,
      "loss": 0.4964,
      "step": 710
    },
    {
      "epoch": 2.223938223938224,
      "grad_norm": 0.7409827598226171,
      "learning_rate": 5e-06,
      "loss": 0.4991,
      "step": 720
    },
    {
      "epoch": 2.2548262548262548,
      "grad_norm": 0.5789864024622833,
      "learning_rate": 5e-06,
      "loss": 0.5047,
      "step": 730
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.6184054511523953,
      "learning_rate": 5e-06,
      "loss": 0.4983,
      "step": 740
    },
    {
      "epoch": 2.3166023166023164,
      "grad_norm": 0.7218033338604144,
      "learning_rate": 5e-06,
      "loss": 0.5006,
      "step": 750
    },
    {
      "epoch": 2.3474903474903477,
      "grad_norm": 0.5488090893995611,
      "learning_rate": 5e-06,
      "loss": 0.4982,
      "step": 760
    },
    {
      "epoch": 2.3783783783783785,
      "grad_norm": 0.7369531886408642,
      "learning_rate": 5e-06,
      "loss": 0.4967,
      "step": 770
    },
    {
      "epoch": 2.4092664092664093,
      "grad_norm": 0.5519469047632208,
      "learning_rate": 5e-06,
      "loss": 0.4965,
      "step": 780
    },
    {
      "epoch": 2.44015444015444,
      "grad_norm": 0.6584775748338472,
      "learning_rate": 5e-06,
      "loss": 0.501,
      "step": 790
    },
    {
      "epoch": 2.471042471042471,
      "grad_norm": 0.6589409942831427,
      "learning_rate": 5e-06,
      "loss": 0.5006,
      "step": 800
    },
    {
      "epoch": 2.501930501930502,
      "grad_norm": 0.6035656966090169,
      "learning_rate": 5e-06,
      "loss": 0.504,
      "step": 810
    },
    {
      "epoch": 2.532818532818533,
      "grad_norm": 0.5939046793612662,
      "learning_rate": 5e-06,
      "loss": 0.4962,
      "step": 820
    },
    {
      "epoch": 2.563706563706564,
      "grad_norm": 0.6332349300931522,
      "learning_rate": 5e-06,
      "loss": 0.5184,
      "step": 830
    },
    {
      "epoch": 2.5945945945945947,
      "grad_norm": 0.5980197287456133,
      "learning_rate": 5e-06,
      "loss": 0.4989,
      "step": 840
    },
    {
      "epoch": 2.6254826254826256,
      "grad_norm": 0.5239673559847541,
      "learning_rate": 5e-06,
      "loss": 0.5013,
      "step": 850
    },
    {
      "epoch": 2.6563706563706564,
      "grad_norm": 0.6161550811061723,
      "learning_rate": 5e-06,
      "loss": 0.4979,
      "step": 860
    },
    {
      "epoch": 2.687258687258687,
      "grad_norm": 0.5658973017035395,
      "learning_rate": 5e-06,
      "loss": 0.5069,
      "step": 870
    },
    {
      "epoch": 2.718146718146718,
      "grad_norm": 0.5709137558646814,
      "learning_rate": 5e-06,
      "loss": 0.5065,
      "step": 880
    },
    {
      "epoch": 2.749034749034749,
      "grad_norm": 0.6389113703934911,
      "learning_rate": 5e-06,
      "loss": 0.5037,
      "step": 890
    },
    {
      "epoch": 2.7799227799227797,
      "grad_norm": 0.6445028760804165,
      "learning_rate": 5e-06,
      "loss": 0.5064,
      "step": 900
    },
    {
      "epoch": 2.810810810810811,
      "grad_norm": 0.6013274832800054,
      "learning_rate": 5e-06,
      "loss": 0.5032,
      "step": 910
    },
    {
      "epoch": 2.841698841698842,
      "grad_norm": 0.5664869441381479,
      "learning_rate": 5e-06,
      "loss": 0.5068,
      "step": 920
    },
    {
      "epoch": 2.8725868725868726,
      "grad_norm": 0.6735218011480151,
      "learning_rate": 5e-06,
      "loss": 0.5076,
      "step": 930
    },
    {
      "epoch": 2.9034749034749034,
      "grad_norm": 1.6394857976813213,
      "learning_rate": 5e-06,
      "loss": 0.5032,
      "step": 940
    },
    {
      "epoch": 2.9343629343629343,
      "grad_norm": 0.5576873331550094,
      "learning_rate": 5e-06,
      "loss": 0.504,
      "step": 950
    },
    {
      "epoch": 2.965250965250965,
      "grad_norm": 0.5637202117054834,
      "learning_rate": 5e-06,
      "loss": 0.5012,
      "step": 960
    },
    {
      "epoch": 2.993050193050193,
      "eval_loss": 0.611685574054718,
      "eval_runtime": 175.5767,
      "eval_samples_per_second": 49.665,
      "eval_steps_per_second": 0.393,
      "step": 969
    },
    {
      "epoch": 2.993050193050193,
      "step": 969,
      "total_flos": 1622692331520000.0,
      "train_loss": 0.5660572312810719,
      "train_runtime": 29124.935,
      "train_samples_per_second": 17.065,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 969,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1622692331520000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}