{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 9064,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022067747986317995,
      "grad_norm": 35072.0,
      "learning_rate": 1.982378854625551e-07,
      "loss": 127.9879,
      "mean_token_accuracy": 0.4198507584631443,
      "num_tokens": 1158893.0,
      "step": 10
    },
    {
      "epoch": 0.004413549597263599,
      "grad_norm": 34304.0,
      "learning_rate": 4.1850220264317185e-07,
      "loss": 132.0537,
      "mean_token_accuracy": 0.40315874963998793,
      "num_tokens": 2293560.0,
      "step": 20
    },
    {
      "epoch": 0.006620324395895399,
      "grad_norm": 33792.0,
      "learning_rate": 6.387665198237886e-07,
      "loss": 122.3714,
      "mean_token_accuracy": 0.42501229494810105,
      "num_tokens": 3455157.0,
      "step": 30
    },
    {
      "epoch": 0.008827099194527198,
      "grad_norm": 29184.0,
      "learning_rate": 8.590308370044054e-07,
      "loss": 109.5747,
      "mean_token_accuracy": 0.44182041212916373,
      "num_tokens": 4588729.0,
      "step": 40
    },
    {
      "epoch": 0.011033873993158997,
      "grad_norm": 23296.0,
      "learning_rate": 1.0792951541850223e-06,
      "loss": 88.3339,
      "mean_token_accuracy": 0.49573995769023893,
      "num_tokens": 5734400.0,
      "step": 50
    },
    {
      "epoch": 0.013240648791790799,
      "grad_norm": 10624.0,
      "learning_rate": 1.299559471365639e-06,
      "loss": 50.6193,
      "mean_token_accuracy": 0.6909133523702622,
      "num_tokens": 6882569.0,
      "step": 60
    },
    {
      "epoch": 0.015447423590422598,
      "grad_norm": 5920.0,
      "learning_rate": 1.5198237885462555e-06,
      "loss": 32.1324,
      "mean_token_accuracy": 0.8550660878419876,
      "num_tokens": 8034141.0,
      "step": 70
    },
    {
      "epoch": 0.017654198389054396,
      "grad_norm": 6432.0,
      "learning_rate": 1.7400881057268722e-06,
      "loss": 22.276,
      "mean_token_accuracy": 0.8650980219244957,
      "num_tokens": 9185000.0,
      "step": 80
    },
    {
      "epoch": 0.019860973187686197,
      "grad_norm": 804.0,
      "learning_rate": 1.960352422907489e-06,
      "loss": 10.7625,
      "mean_token_accuracy": 0.9150429755449295,
      "num_tokens": 10337565.0,
      "step": 90
    },
    {
      "epoch": 0.022067747986317995,
      "grad_norm": 324.0,
      "learning_rate": 2.180616740088106e-06,
      "loss": 6.4788,
      "mean_token_accuracy": 0.9349653095006942,
      "num_tokens": 11472738.0,
      "step": 100
    },
    {
      "epoch": 0.024274522784949796,
      "grad_norm": 201.0,
      "learning_rate": 2.400881057268723e-06,
      "loss": 4.7023,
      "mean_token_accuracy": 0.9414406657218933,
      "num_tokens": 12612721.0,
      "step": 110
    },
    {
      "epoch": 0.026481297583581597,
      "grad_norm": 136.0,
      "learning_rate": 2.6211453744493394e-06,
      "loss": 4.2014,
      "mean_token_accuracy": 0.946342870593071,
      "num_tokens": 13775315.0,
      "step": 120
    },
    {
      "epoch": 0.028688072382213395,
      "grad_norm": 174.0,
      "learning_rate": 2.841409691629956e-06,
      "loss": 3.6812,
      "mean_token_accuracy": 0.9507869705557823,
      "num_tokens": 14919796.0,
      "step": 130
    },
    {
      "epoch": 0.030894847180845196,
      "grad_norm": 52.0,
      "learning_rate": 3.061674008810573e-06,
      "loss": 3.3338,
      "mean_token_accuracy": 0.9483595371246338,
      "num_tokens": 16076676.0,
      "step": 140
    },
    {
      "epoch": 0.033101621979477,
      "grad_norm": 56.0,
      "learning_rate": 3.2819383259911898e-06,
      "loss": 3.3154,
      "mean_token_accuracy": 0.9494132816791534,
      "num_tokens": 17220322.0,
      "step": 150
    },
    {
      "epoch": 0.03530839677810879,
      "grad_norm": 111.0,
      "learning_rate": 3.5022026431718063e-06,
      "loss": 3.1446,
      "mean_token_accuracy": 0.9552441149950027,
      "num_tokens": 18363831.0,
      "step": 160
    },
    {
      "epoch": 0.03751517157674059,
      "grad_norm": 65.5,
      "learning_rate": 3.7224669603524232e-06,
      "loss": 3.2151,
      "mean_token_accuracy": 0.9499802276492119,
      "num_tokens": 19523552.0,
      "step": 170
    },
    {
      "epoch": 0.039721946375372394,
      "grad_norm": 101.0,
      "learning_rate": 3.94273127753304e-06,
      "loss": 3.1206,
      "mean_token_accuracy": 0.9534510284662246,
      "num_tokens": 20677532.0,
      "step": 180
    },
    {
      "epoch": 0.041928721174004195,
      "grad_norm": 65.0,
      "learning_rate": 4.162995594713657e-06,
      "loss": 2.8463,
      "mean_token_accuracy": 0.9595387071371079,
      "num_tokens": 21821335.0,
      "step": 190
    },
    {
      "epoch": 0.04413549597263599,
      "grad_norm": 192.0,
      "learning_rate": 4.383259911894274e-06,
      "loss": 3.0298,
      "mean_token_accuracy": 0.9533383026719093,
      "num_tokens": 22972210.0,
      "step": 200
    },
    {
      "epoch": 0.04634227077126779,
      "grad_norm": 54.0,
      "learning_rate": 4.60352422907489e-06,
      "loss": 3.1375,
      "mean_token_accuracy": 0.9533056274056435,
      "num_tokens": 24131759.0,
      "step": 210
    },
    {
      "epoch": 0.04854904556989959,
      "grad_norm": 69.5,
      "learning_rate": 4.823788546255507e-06,
      "loss": 3.0169,
      "mean_token_accuracy": 0.9545826122164727,
      "num_tokens": 25279653.0,
      "step": 220
    },
    {
      "epoch": 0.05075582036853139,
      "grad_norm": 90.0,
      "learning_rate": 5.044052863436124e-06,
      "loss": 2.9447,
      "mean_token_accuracy": 0.9577911093831062,
      "num_tokens": 26429259.0,
      "step": 230
    },
    {
      "epoch": 0.052962595167163194,
      "grad_norm": 38.0,
      "learning_rate": 5.2643171806167406e-06,
      "loss": 2.7535,
      "mean_token_accuracy": 0.9580179870128631,
      "num_tokens": 27579200.0,
      "step": 240
    },
    {
      "epoch": 0.05516936996579499,
      "grad_norm": 73.0,
      "learning_rate": 5.484581497797358e-06,
      "loss": 2.856,
      "mean_token_accuracy": 0.9566797330975533,
      "num_tokens": 28742498.0,
      "step": 250
    },
    {
      "epoch": 0.05737614476442679,
      "grad_norm": 86.5,
      "learning_rate": 5.704845814977974e-06,
      "loss": 2.9445,
      "mean_token_accuracy": 0.9531215146183968,
      "num_tokens": 29895308.0,
      "step": 260
    },
    {
      "epoch": 0.05958291956305859,
      "grad_norm": 66.0,
      "learning_rate": 5.925110132158591e-06,
      "loss": 2.9515,
      "mean_token_accuracy": 0.9529277339577675,
      "num_tokens": 31051444.0,
      "step": 270
    },
    {
      "epoch": 0.06178969436169039,
      "grad_norm": 227.0,
      "learning_rate": 6.1453744493392075e-06,
      "loss": 2.8731,
      "mean_token_accuracy": 0.957319438457489,
      "num_tokens": 32212821.0,
      "step": 280
    },
    {
      "epoch": 0.06399646916032219,
      "grad_norm": 78.0,
      "learning_rate": 6.365638766519824e-06,
      "loss": 2.8961,
      "mean_token_accuracy": 0.9561361238360405,
      "num_tokens": 33359370.0,
      "step": 290
    },
    {
      "epoch": 0.066203243958954,
      "grad_norm": 57.25,
      "learning_rate": 6.585903083700441e-06,
      "loss": 3.0397,
      "mean_token_accuracy": 0.9531881302595139,
      "num_tokens": 34491274.0,
      "step": 300
    },
    {
      "epoch": 0.06841001875758579,
      "grad_norm": 65.0,
      "learning_rate": 6.806167400881057e-06,
      "loss": 2.7639,
      "mean_token_accuracy": 0.9597050786018372,
      "num_tokens": 35627797.0,
      "step": 310
    },
    {
      "epoch": 0.07061679355621758,
      "grad_norm": 84.0,
      "learning_rate": 7.026431718061674e-06,
      "loss": 2.9271,
      "mean_token_accuracy": 0.9565465092658997,
      "num_tokens": 36788468.0,
      "step": 320
    },
    {
      "epoch": 0.07282356835484939,
      "grad_norm": 144.0,
      "learning_rate": 7.246696035242291e-06,
      "loss": 3.0301,
      "mean_token_accuracy": 0.9516592517495155,
      "num_tokens": 37946453.0,
      "step": 330
    },
    {
      "epoch": 0.07503034315348119,
      "grad_norm": 47.0,
      "learning_rate": 7.466960352422908e-06,
      "loss": 2.7975,
      "mean_token_accuracy": 0.9557692691683769,
      "num_tokens": 39116128.0,
      "step": 340
    },
    {
      "epoch": 0.077237117952113,
      "grad_norm": 121.5,
      "learning_rate": 7.687224669603525e-06,
      "loss": 2.6678,
      "mean_token_accuracy": 0.959360970556736,
      "num_tokens": 40266495.0,
      "step": 350
    },
    {
      "epoch": 0.07944389275074479,
      "grad_norm": 33.75,
      "learning_rate": 7.907488986784141e-06,
      "loss": 2.8127,
      "mean_token_accuracy": 0.9544507667422295,
      "num_tokens": 41431490.0,
      "step": 360
    },
    {
      "epoch": 0.08165066754937658,
      "grad_norm": 36.25,
      "learning_rate": 8.127753303964758e-06,
      "loss": 2.7782,
      "mean_token_accuracy": 0.9572808161377907,
      "num_tokens": 42582300.0,
      "step": 370
    },
    {
      "epoch": 0.08385744234800839,
      "grad_norm": 86.0,
      "learning_rate": 8.348017621145376e-06,
      "loss": 2.874,
      "mean_token_accuracy": 0.9567968577146531,
      "num_tokens": 43720343.0,
      "step": 380
    },
    {
      "epoch": 0.08606421714664018,
      "grad_norm": 49.0,
      "learning_rate": 8.568281938325993e-06,
      "loss": 2.7388,
      "mean_token_accuracy": 0.9586963757872582,
      "num_tokens": 44876871.0,
      "step": 390
    },
    {
      "epoch": 0.08827099194527198,
      "grad_norm": 108.0,
      "learning_rate": 8.788546255506607e-06,
      "loss": 2.7022,
      "mean_token_accuracy": 0.9587051913142204,
      "num_tokens": 46016653.0,
      "step": 400
    },
    {
      "epoch": 0.09047776674390379,
      "grad_norm": 46.25,
      "learning_rate": 9.008810572687226e-06,
      "loss": 2.6447,
      "mean_token_accuracy": 0.958084474503994,
      "num_tokens": 47178496.0,
      "step": 410
    },
    {
      "epoch": 0.09268454154253558,
      "grad_norm": 61.0,
      "learning_rate": 9.229074889867842e-06,
      "loss": 2.8646,
      "mean_token_accuracy": 0.9562040224671364,
      "num_tokens": 48336902.0,
      "step": 420
    },
    {
      "epoch": 0.09489131634116739,
      "grad_norm": 120.0,
      "learning_rate": 9.449339207048459e-06,
      "loss": 2.8754,
      "mean_token_accuracy": 0.9574764847755433,
      "num_tokens": 49487989.0,
      "step": 430
    },
    {
      "epoch": 0.09709809113979918,
      "grad_norm": 95.5,
      "learning_rate": 9.669603524229075e-06,
      "loss": 2.8072,
      "mean_token_accuracy": 0.9568351075053215,
      "num_tokens": 50623988.0,
      "step": 440
    },
    {
      "epoch": 0.09930486593843098,
      "grad_norm": 126.5,
      "learning_rate": 9.889867841409693e-06,
      "loss": 2.7554,
      "mean_token_accuracy": 0.9575024515390396,
      "num_tokens": 51777451.0,
      "step": 450
    },
    {
      "epoch": 0.10151164073706279,
      "grad_norm": 67.5,
      "learning_rate": 9.99999167904182e-06,
      "loss": 2.8122,
      "mean_token_accuracy": 0.9539386913180351,
      "num_tokens": 52921713.0,
      "step": 460
    },
    {
      "epoch": 0.10371841553569458,
      "grad_norm": 109.0,
      "learning_rate": 9.999925111542544e-06,
      "loss": 2.7388,
      "mean_token_accuracy": 0.9589674293994903,
      "num_tokens": 54064629.0,
      "step": 470
    },
    {
      "epoch": 0.10592519033432639,
      "grad_norm": 40.75,
      "learning_rate": 9.999791977430238e-06,
      "loss": 2.646,
      "mean_token_accuracy": 0.9602646142244339,
      "num_tokens": 55216744.0,
      "step": 480
    },
    {
      "epoch": 0.10813196513295818,
      "grad_norm": 91.5,
      "learning_rate": 9.999592278477389e-06,
      "loss": 2.6333,
      "mean_token_accuracy": 0.9577486470341683,
      "num_tokens": 56364553.0,
      "step": 490
    },
    {
      "epoch": 0.11033873993158998,
      "grad_norm": 77.0,
      "learning_rate": 9.999326017342688e-06,
      "loss": 2.7762,
      "mean_token_accuracy": 0.9563986629247665,
      "num_tokens": 57506700.0,
      "step": 500
    },
    {
      "epoch": 0.11254551473022179,
      "grad_norm": 50.75,
      "learning_rate": 9.998993197571014e-06,
      "loss": 2.8133,
      "mean_token_accuracy": 0.9564774289727211,
      "num_tokens": 58662842.0,
      "step": 510
    },
    {
      "epoch": 0.11475228952885358,
      "grad_norm": 34.25,
      "learning_rate": 9.99859382359337e-06,
      "loss": 2.7132,
      "mean_token_accuracy": 0.9581861853599548,
      "num_tokens": 59826463.0,
      "step": 520
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 106.0,
      "learning_rate": 9.998127900726825e-06,
      "loss": 2.8188,
      "mean_token_accuracy": 0.9551180854439736,
      "num_tokens": 60977307.0,
      "step": 530
    },
    {
      "epoch": 0.11916583912611718,
      "grad_norm": 37.5,
      "learning_rate": 9.997595435174461e-06,
      "loss": 2.588,
      "mean_token_accuracy": 0.9604722619056701,
      "num_tokens": 62123313.0,
      "step": 540
    },
    {
      "epoch": 0.12137261392474898,
      "grad_norm": 51.25,
      "learning_rate": 9.996996434025264e-06,
      "loss": 2.5104,
      "mean_token_accuracy": 0.9609525024890899,
      "num_tokens": 63265019.0,
      "step": 550
    },
    {
      "epoch": 0.12357938872338078,
      "grad_norm": 76.5,
      "learning_rate": 9.99633090525405e-06,
      "loss": 2.6432,
      "mean_token_accuracy": 0.957705968618393,
      "num_tokens": 64417905.0,
      "step": 560
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": 96.0,
      "learning_rate": 9.995598857721354e-06,
      "loss": 2.5968,
      "mean_token_accuracy": 0.9587825626134873,
      "num_tokens": 65577278.0,
      "step": 570
    },
    {
      "epoch": 0.12799293832064437,
      "grad_norm": 74.5,
      "learning_rate": 9.994800301173303e-06,
      "loss": 2.6556,
      "mean_token_accuracy": 0.9606878533959389,
      "num_tokens": 66718763.0,
      "step": 580
    },
    {
      "epoch": 0.13019971311927617,
      "grad_norm": 107.0,
      "learning_rate": 9.9939352462415e-06,
      "loss": 2.6829,
      "mean_token_accuracy": 0.9607311606407165,
      "num_tokens": 67866232.0,
      "step": 590
    },
    {
      "epoch": 0.132406487917908,
      "grad_norm": 36.25,
      "learning_rate": 9.99300370444287e-06,
      "loss": 2.8079,
      "mean_token_accuracy": 0.9593664944171906,
      "num_tokens": 69026176.0,
      "step": 600
    },
    {
      "epoch": 0.13461326271653978,
      "grad_norm": 39.5,
      "learning_rate": 9.992005688179518e-06,
      "loss": 2.7589,
      "mean_token_accuracy": 0.9582408994436264,
      "num_tokens": 70179142.0,
      "step": 610
    },
    {
      "epoch": 0.13682003751517158,
      "grad_norm": 60.0,
      "learning_rate": 9.990941210738553e-06,
      "loss": 2.5683,
      "mean_token_accuracy": 0.9601910769939422,
      "num_tokens": 71341360.0,
      "step": 620
    },
    {
      "epoch": 0.13902681231380337,
      "grad_norm": 37.5,
      "learning_rate": 9.989810286291923e-06,
      "loss": 2.5831,
      "mean_token_accuracy": 0.959646712243557,
      "num_tokens": 72481378.0,
      "step": 630
    },
    {
      "epoch": 0.14123358711243517,
      "grad_norm": 121.5,
      "learning_rate": 9.988612929896211e-06,
      "loss": 2.6847,
      "mean_token_accuracy": 0.9600049823522567,
      "num_tokens": 73638168.0,
      "step": 640
    },
    {
      "epoch": 0.143440361911067,
      "grad_norm": 95.0,
      "learning_rate": 9.98734915749245e-06,
      "loss": 2.5501,
      "mean_token_accuracy": 0.9631100237369538,
      "num_tokens": 74770020.0,
      "step": 650
    },
    {
      "epoch": 0.14564713670969878,
      "grad_norm": 116.5,
      "learning_rate": 9.986018985905901e-06,
      "loss": 2.6863,
      "mean_token_accuracy": 0.9581478059291839,
      "num_tokens": 75929468.0,
      "step": 660
    },
    {
      "epoch": 0.14785391150833058,
      "grad_norm": 82.0,
      "learning_rate": 9.984622432845835e-06,
      "loss": 2.5096,
      "mean_token_accuracy": 0.9625503912568092,
      "num_tokens": 77084264.0,
      "step": 670
    },
    {
      "epoch": 0.15006068630696237,
      "grad_norm": 36.5,
      "learning_rate": 9.983159516905287e-06,
      "loss": 2.5931,
      "mean_token_accuracy": 0.9623690828680992,
      "num_tokens": 78244631.0,
      "step": 680
    },
    {
      "epoch": 0.15226746110559417,
      "grad_norm": 68.5,
      "learning_rate": 9.981630257560825e-06,
      "loss": 2.5641,
      "mean_token_accuracy": 0.9612786695361137,
      "num_tokens": 79381562.0,
      "step": 690
    },
    {
      "epoch": 0.154474235904226,
      "grad_norm": 70.5,
      "learning_rate": 9.980034675172274e-06,
      "loss": 2.4743,
      "mean_token_accuracy": 0.9626874148845672,
      "num_tokens": 80545754.0,
      "step": 700
    },
    {
      "epoch": 0.15668101070285778,
      "grad_norm": 38.0,
      "learning_rate": 9.978372790982457e-06,
      "loss": 2.6163,
      "mean_token_accuracy": 0.9608708754181862,
      "num_tokens": 81697063.0,
      "step": 710
    },
    {
      "epoch": 0.15888778550148958,
      "grad_norm": 29.875,
      "learning_rate": 9.976644627116906e-06,
      "loss": 2.5865,
      "mean_token_accuracy": 0.962155269086361,
      "num_tokens": 82847344.0,
      "step": 720
    },
    {
      "epoch": 0.16109456030012137,
      "grad_norm": 28.75,
      "learning_rate": 9.97485020658357e-06,
      "loss": 2.5868,
      "mean_token_accuracy": 0.9601317137479782,
      "num_tokens": 83996879.0,
      "step": 730
    },
    {
      "epoch": 0.16330133509875316,
      "grad_norm": 33.0,
      "learning_rate": 9.972989553272501e-06,
      "loss": 2.6427,
      "mean_token_accuracy": 0.9635660454630852,
      "num_tokens": 85160887.0,
      "step": 740
    },
    {
      "epoch": 0.16550810989738496,
      "grad_norm": 28.5,
      "learning_rate": 9.971062691955553e-06,
      "loss": 2.6651,
      "mean_token_accuracy": 0.9586639389395714,
      "num_tokens": 86322015.0,
      "step": 750
    },
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 70.5,
      "learning_rate": 9.969069648286034e-06,
      "loss": 2.4916,
      "mean_token_accuracy": 0.9633258700370788,
      "num_tokens": 87471908.0,
      "step": 760
    },
    {
      "epoch": 0.16992165949464857,
      "grad_norm": 50.0,
      "learning_rate": 9.967010448798376e-06,
      "loss": 2.6078,
      "mean_token_accuracy": 0.9591722801327706,
      "num_tokens": 88631163.0,
      "step": 770
    },
    {
      "epoch": 0.17212843429328037,
      "grad_norm": 125.0,
      "learning_rate": 9.964885120907777e-06,
      "loss": 2.5831,
      "mean_token_accuracy": 0.9590150415897369,
      "num_tokens": 89795187.0,
      "step": 780
    },
    {
      "epoch": 0.17433520909191216,
      "grad_norm": 80.0,
      "learning_rate": 9.962693692909834e-06,
      "loss": 2.4504,
      "mean_token_accuracy": 0.9655511677265167,
      "num_tokens": 90935889.0,
      "step": 790
    },
    {
      "epoch": 0.17654198389054396,
      "grad_norm": 31.125,
      "learning_rate": 9.960436193980175e-06,
      "loss": 2.4798,
      "mean_token_accuracy": 0.962042161822319,
      "num_tokens": 92081345.0,
      "step": 800
    },
    {
      "epoch": 0.17874875868917578,
      "grad_norm": 81.5,
      "learning_rate": 9.958112654174058e-06,
      "loss": 2.7135,
      "mean_token_accuracy": 0.9616910234093666,
      "num_tokens": 93198801.0,
      "step": 810
    },
    {
      "epoch": 0.18095553348780757,
      "grad_norm": 45.75,
      "learning_rate": 9.955723104425986e-06,
      "loss": 2.6111,
      "mean_token_accuracy": 0.9619805797934532,
      "num_tokens": 94337864.0,
      "step": 820
    },
    {
      "epoch": 0.18316230828643937,
      "grad_norm": 28.375,
      "learning_rate": 9.953267576549279e-06,
      "loss": 2.5513,
      "mean_token_accuracy": 0.9610829636454582,
      "num_tokens": 95494807.0,
      "step": 830
    },
    {
      "epoch": 0.18536908308507116,
      "grad_norm": 56.25,
      "learning_rate": 9.950746103235663e-06,
      "loss": 2.3147,
      "mean_token_accuracy": 0.9650572776794434,
      "num_tokens": 96645723.0,
      "step": 840
    },
    {
      "epoch": 0.18757585788370296,
      "grad_norm": 27.75,
      "learning_rate": 9.948158718054828e-06,
      "loss": 2.3418,
      "mean_token_accuracy": 0.9654249668121337,
      "num_tokens": 97801303.0,
      "step": 850
    },
    {
      "epoch": 0.18978263268233478,
      "grad_norm": 51.0,
      "learning_rate": 9.945505455453983e-06,
      "loss": 2.5469,
      "mean_token_accuracy": 0.962736339867115,
      "num_tokens": 98960359.0,
      "step": 860
    },
    {
      "epoch": 0.19198940748096657,
      "grad_norm": 25.125,
      "learning_rate": 9.942786350757398e-06,
      "loss": 2.5394,
      "mean_token_accuracy": 0.9604154780507088,
      "num_tokens": 100121451.0,
      "step": 870
    },
    {
      "epoch": 0.19419618227959837,
      "grad_norm": 119.0,
      "learning_rate": 9.940001440165934e-06,
      "loss": 2.4546,
      "mean_token_accuracy": 0.9624143466353416,
      "num_tokens": 101277861.0,
      "step": 880
    },
    {
      "epoch": 0.19640295707823016,
      "grad_norm": 92.5,
      "learning_rate": 9.93715076075656e-06,
      "loss": 2.487,
      "mean_token_accuracy": 0.9629015192389488,
      "num_tokens": 102429499.0,
      "step": 890
    },
    {
      "epoch": 0.19860973187686196,
      "grad_norm": 33.25,
      "learning_rate": 9.934234350481856e-06,
      "loss": 2.5472,
      "mean_token_accuracy": 0.9608551502227783,
      "num_tokens": 103582879.0,
      "step": 900
    },
    {
      "epoch": 0.20081650667549378,
      "grad_norm": 47.75,
      "learning_rate": 9.931252248169518e-06,
      "loss": 2.4658,
      "mean_token_accuracy": 0.9619848027825355,
      "num_tokens": 104727856.0,
      "step": 910
    },
    {
      "epoch": 0.20302328147412557,
      "grad_norm": 94.0,
      "learning_rate": 9.92820449352183e-06,
      "loss": 2.3843,
      "mean_token_accuracy": 0.9661209225654602,
      "num_tokens": 105867599.0,
      "step": 920
    },
    {
      "epoch": 0.20523005627275737,
      "grad_norm": 97.5,
      "learning_rate": 9.925091127115139e-06,
      "loss": 2.403,
      "mean_token_accuracy": 0.9649116635322571,
      "num_tokens": 106989144.0,
      "step": 930
    },
    {
      "epoch": 0.20743683107138916,
      "grad_norm": 84.5,
      "learning_rate": 9.921912190399317e-06,
      "loss": 2.4899,
      "mean_token_accuracy": 0.9606701314449311,
      "num_tokens": 108139309.0,
      "step": 940
    },
    {
      "epoch": 0.20964360587002095,
      "grad_norm": 33.25,
      "learning_rate": 9.91866772569721e-06,
      "loss": 2.3691,
      "mean_token_accuracy": 0.9642886847257615,
      "num_tokens": 109299402.0,
      "step": 950
    },
    {
      "epoch": 0.21185038066865278,
      "grad_norm": 27.375,
      "learning_rate": 9.91535777620407e-06,
      "loss": 2.6744,
      "mean_token_accuracy": 0.9582440212368966,
      "num_tokens": 110444962.0,
      "step": 960
    },
    {
      "epoch": 0.21405715546728457,
      "grad_norm": 93.5,
      "learning_rate": 9.91198238598698e-06,
      "loss": 2.2383,
      "mean_token_accuracy": 0.9647313490509987,
      "num_tokens": 111604731.0,
      "step": 970
    },
    {
      "epoch": 0.21626393026591637,
      "grad_norm": 39.5,
      "learning_rate": 9.908541599984276e-06,
      "loss": 2.4552,
      "mean_token_accuracy": 0.964093579351902,
      "num_tokens": 112761627.0,
      "step": 980
    },
    {
      "epoch": 0.21847070506454816,
      "grad_norm": 41.75,
      "learning_rate": 9.905035464004935e-06,
      "loss": 2.5513,
      "mean_token_accuracy": 0.9628371596336365,
      "num_tokens": 113906065.0,
      "step": 990
    },
    {
      "epoch": 0.22067747986317995,
      "grad_norm": 84.0,
      "learning_rate": 9.901464024727976e-06,
      "loss": 2.3728,
      "mean_token_accuracy": 0.9664550170302391,
      "num_tokens": 115056456.0,
      "step": 1000
    },
    {
      "epoch": 0.22288425466181178,
      "grad_norm": 30.125,
      "learning_rate": 9.897827329701834e-06,
      "loss": 2.4261,
      "mean_token_accuracy": 0.963290685415268,
      "num_tokens": 116190018.0,
      "step": 1010
    },
    {
      "epoch": 0.22509102946044357,
      "grad_norm": 134.0,
      "learning_rate": 9.89412542734373e-06,
      "loss": 2.6902,
      "mean_token_accuracy": 0.9617101430892945,
      "num_tokens": 117323921.0,
      "step": 1020
    },
    {
      "epoch": 0.22729780425907536,
      "grad_norm": 78.0,
      "learning_rate": 9.890358366939021e-06,
      "loss": 2.6029,
      "mean_token_accuracy": 0.963995173573494,
      "num_tokens": 118476348.0,
      "step": 1030
    },
    {
      "epoch": 0.22950457905770716,
      "grad_norm": 76.0,
      "learning_rate": 9.88652619864055e-06,
      "loss": 2.3973,
      "mean_token_accuracy": 0.9648420304059983,
      "num_tokens": 119618276.0,
      "step": 1040
    },
    {
      "epoch": 0.23171135385633895,
      "grad_norm": 43.5,
      "learning_rate": 9.882628973467972e-06,
      "loss": 2.4065,
      "mean_token_accuracy": 0.966393555700779,
      "num_tokens": 120776256.0,
      "step": 1050
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 125.5,
      "learning_rate": 9.878666743307083e-06,
      "loss": 2.3249,
      "mean_token_accuracy": 0.9663713455200196,
      "num_tokens": 121927985.0,
      "step": 1060
    },
    {
      "epoch": 0.23612490345360257,
      "grad_norm": 30.375,
      "learning_rate": 9.874639560909118e-06,
      "loss": 2.3088,
      "mean_token_accuracy": 0.9675253227353096,
      "num_tokens": 123080549.0,
      "step": 1070
    },
    {
      "epoch": 0.23833167825223436,
      "grad_norm": 33.5,
      "learning_rate": 9.870547479890062e-06,
      "loss": 2.5497,
      "mean_token_accuracy": 0.9643093049526215,
      "num_tokens": 124230629.0,
      "step": 1080
    },
    {
      "epoch": 0.24053845305086616,
      "grad_norm": 23.0,
      "learning_rate": 9.866390554729923e-06,
      "loss": 2.4956,
      "mean_token_accuracy": 0.9651616990566254,
      "num_tokens": 125390142.0,
      "step": 1090
    },
    {
      "epoch": 0.24274522784949795,
      "grad_norm": 38.25,
      "learning_rate": 9.862168840772018e-06,
      "loss": 2.4476,
      "mean_token_accuracy": 0.9643542259931565,
      "num_tokens": 126545718.0,
      "step": 1100
    },
    {
      "epoch": 0.24495200264812975,
      "grad_norm": 76.0,
      "learning_rate": 9.857882394222225e-06,
      "loss": 2.5227,
      "mean_token_accuracy": 0.9637098580598831,
      "num_tokens": 127692122.0,
      "step": 1110
    },
    {
      "epoch": 0.24715877744676157,
      "grad_norm": 38.75,
      "learning_rate": 9.853531272148248e-06,
      "loss": 2.4703,
      "mean_token_accuracy": 0.9644091233611107,
      "num_tokens": 128840384.0,
      "step": 1120
    },
    {
      "epoch": 0.24936555224539336,
      "grad_norm": 43.0,
      "learning_rate": 9.849115532478848e-06,
      "loss": 2.483,
      "mean_token_accuracy": 0.9634609088301659,
      "num_tokens": 130004140.0,
      "step": 1130
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 54.75,
      "learning_rate": 9.844635234003067e-06,
      "loss": 2.4446,
      "mean_token_accuracy": 0.9646256938576698,
      "num_tokens": 131152238.0,
      "step": 1140
    },
    {
      "epoch": 0.25377910184265695,
      "grad_norm": 40.0,
      "learning_rate": 9.840090436369458e-06,
      "loss": 2.2836,
      "mean_token_accuracy": 0.9668354943394661,
      "num_tokens": 132305852.0,
      "step": 1150
    },
    {
      "epoch": 0.25598587664128875,
      "grad_norm": 78.0,
      "learning_rate": 9.83548120008529e-06,
      "loss": 2.3112,
      "mean_token_accuracy": 0.9659123718738556,
      "num_tokens": 133459118.0,
      "step": 1160
    },
    {
      "epoch": 0.25819265143992054,
      "grad_norm": 50.0,
      "learning_rate": 9.830807586515726e-06,
      "loss": 2.436,
      "mean_token_accuracy": 0.9653922632336617,
      "num_tokens": 134619378.0,
      "step": 1170
    },
    {
      "epoch": 0.26039942623855233,
      "grad_norm": 29.625,
      "learning_rate": 9.826069657883027e-06,
      "loss": 2.2187,
      "mean_token_accuracy": 0.9661240383982659,
      "num_tokens": 135763226.0,
      "step": 1180
    },
    {
      "epoch": 0.26260620103718413,
      "grad_norm": 56.5,
      "learning_rate": 9.821267477265705e-06,
      "loss": 2.4291,
      "mean_token_accuracy": 0.9658174440264702,
      "num_tokens": 136919931.0,
      "step": 1190
    },
    {
      "epoch": 0.264812975835816,
      "grad_norm": 88.5,
      "learning_rate": 9.816401108597704e-06,
      "loss": 2.5394,
      "mean_token_accuracy": 0.961602446436882,
      "num_tokens": 138081130.0,
      "step": 1200
    },
    {
      "epoch": 0.2670197506344478,
      "grad_norm": 36.0,
      "learning_rate": 9.811470616667525e-06,
      "loss": 2.5134,
      "mean_token_accuracy": 0.9625838294625282,
      "num_tokens": 139233437.0,
      "step": 1210
    },
    {
      "epoch": 0.26922652543307957,
      "grad_norm": 51.25,
      "learning_rate": 9.806476067117384e-06,
      "loss": 2.4085,
      "mean_token_accuracy": 0.9661199882626533,
      "num_tokens": 140393910.0,
      "step": 1220
    },
    {
      "epoch": 0.27143330023171136,
      "grad_norm": 27.875,
      "learning_rate": 9.801417526442326e-06,
      "loss": 2.4051,
      "mean_token_accuracy": 0.9669907361268997,
      "num_tokens": 141547585.0,
      "step": 1230
    },
    {
      "epoch": 0.27364007503034316,
      "grad_norm": 35.0,
      "learning_rate": 9.79629506198934e-06,
      "loss": 2.533,
      "mean_token_accuracy": 0.9635807365179062,
      "num_tokens": 142702841.0,
      "step": 1240
    },
    {
      "epoch": 0.27584684982897495,
      "grad_norm": 184.0,
      "learning_rate": 9.791108741956476e-06,
      "loss": 2.4782,
      "mean_token_accuracy": 0.9641298696398735,
      "num_tokens": 143841896.0,
      "step": 1250
    },
    {
      "epoch": 0.27805362462760674,
      "grad_norm": 52.25,
      "learning_rate": 9.785858635391913e-06,
      "loss": 2.505,
      "mean_token_accuracy": 0.9625312894582748,
      "num_tokens": 144997681.0,
      "step": 1260
    },
    {
      "epoch": 0.28026039942623854,
      "grad_norm": 80.5,
      "learning_rate": 9.780544812193065e-06,
      "loss": 2.4243,
      "mean_token_accuracy": 0.9655213013291359,
      "num_tokens": 146170846.0,
      "step": 1270
    },
    {
      "epoch": 0.28246717422487033,
      "grad_norm": 39.75,
      "learning_rate": 9.77516734310563e-06,
      "loss": 2.4296,
      "mean_token_accuracy": 0.9646094188094139,
      "num_tokens": 147320400.0,
      "step": 1280
    },
    {
      "epoch": 0.2846739490235021,
      "grad_norm": 48.0,
      "learning_rate": 9.769726299722668e-06,
      "loss": 2.365,
      "mean_token_accuracy": 0.9665022194385529,
      "num_tokens": 148501676.0,
      "step": 1290
    },
    {
      "epoch": 0.286880723822134,
      "grad_norm": 70.0,
      "learning_rate": 9.764221754483623e-06,
      "loss": 2.2581,
      "mean_token_accuracy": 0.968066719174385,
      "num_tokens": 149671956.0,
      "step": 1300
    },
    {
      "epoch": 0.28908749862076577,
      "grad_norm": 65.0,
      "learning_rate": 9.758653780673381e-06,
      "loss": 2.3334,
      "mean_token_accuracy": 0.9677918672561645,
      "num_tokens": 150840868.0,
      "step": 1310
    },
    {
      "epoch": 0.29129427341939756,
      "grad_norm": 64.5,
      "learning_rate": 9.753022452421286e-06,
      "loss": 2.3027,
      "mean_token_accuracy": 0.9655709505081177,
      "num_tokens": 152005694.0,
      "step": 1320
    },
    {
      "epoch": 0.29350104821802936,
      "grad_norm": 30.75,
      "learning_rate": 9.747327844700147e-06,
      "loss": 2.2958,
      "mean_token_accuracy": 0.966034634411335,
      "num_tokens": 153165015.0,
      "step": 1330
    },
    {
      "epoch": 0.29570782301666115,
      "grad_norm": 46.25,
      "learning_rate": 9.741570033325254e-06,
      "loss": 2.3682,
      "mean_token_accuracy": 0.9649452283978462,
      "num_tokens": 154325061.0,
      "step": 1340
    },
    {
      "epoch": 0.29791459781529295,
      "grad_norm": 26.0,
      "learning_rate": 9.73574909495335e-06,
      "loss": 2.4025,
      "mean_token_accuracy": 0.9647112742066384,
      "num_tokens": 155475633.0,
      "step": 1350
    },
    {
      "epoch": 0.30012137261392474,
      "grad_norm": 30.125,
      "learning_rate": 9.729865107081631e-06,
      "loss": 2.4665,
      "mean_token_accuracy": 0.9647145554423332,
      "num_tokens": 156642023.0,
      "step": 1360
    },
    {
      "epoch": 0.30232814741255654,
      "grad_norm": 36.75,
      "learning_rate": 9.723918148046696e-06,
      "loss": 2.3926,
      "mean_token_accuracy": 0.9677468553185463,
      "num_tokens": 157792568.0,
      "step": 1370
    },
    {
      "epoch": 0.30453492221118833,
      "grad_norm": 44.0,
      "learning_rate": 9.717908297023517e-06,
      "loss": 2.4731,
      "mean_token_accuracy": 0.964520788192749,
      "num_tokens": 158954415.0,
      "step": 1380
    },
    {
      "epoch": 0.3067416970098201,
      "grad_norm": 26.5,
      "learning_rate": 9.711835634024378e-06,
      "loss": 2.1733,
      "mean_token_accuracy": 0.970021191239357,
      "num_tokens": 160126079.0,
      "step": 1390
    },
    {
      "epoch": 0.308948471808452,
      "grad_norm": 25.625,
      "learning_rate": 9.705700239897809e-06,
      "loss": 2.2803,
      "mean_token_accuracy": 0.9674491137266159,
      "num_tokens": 161277711.0,
      "step": 1400
    },
    {
      "epoch": 0.31115524660708377,
      "grad_norm": 68.5,
      "learning_rate": 9.699502196327515e-06,
      "loss": 2.4253,
      "mean_token_accuracy": 0.9644299671053886,
      "num_tokens": 162424273.0,
      "step": 1410
    },
    {
      "epoch": 0.31336202140571556,
      "grad_norm": 27.25,
      "learning_rate": 9.69324158583129e-06,
      "loss": 2.3011,
      "mean_token_accuracy": 0.9668093726038933,
      "num_tokens": 163563475.0,
      "step": 1420
    },
    {
      "epoch": 0.31556879620434736,
      "grad_norm": 33.25,
      "learning_rate": 9.686918491759904e-06,
      "loss": 2.3263,
      "mean_token_accuracy": 0.966026459634304,
      "num_tokens": 164730359.0,
      "step": 1430
    },
    {
      "epoch": 0.31777557100297915,
      "grad_norm": 39.25,
      "learning_rate": 9.68053299829601e-06,
      "loss": 2.2862,
      "mean_token_accuracy": 0.9667583256959915,
      "num_tokens": 165904507.0,
      "step": 1440
    },
    {
      "epoch": 0.31998234580161095,
      "grad_norm": 132.0,
      "learning_rate": 9.67408519045302e-06,
      "loss": 2.2402,
      "mean_token_accuracy": 0.9660430416464806,
      "num_tokens": 167026147.0,
      "step": 1450
    },
    {
      "epoch": 0.32218912060024274,
      "grad_norm": 40.75,
      "learning_rate": 9.667575154073962e-06,
      "loss": 2.2994,
      "mean_token_accuracy": 0.9682269170880318,
      "num_tokens": 168181751.0,
      "step": 1460
    },
    {
      "epoch": 0.32439589539887453,
      "grad_norm": 31.25,
      "learning_rate": 9.66100297583035e-06,
      "loss": 2.2895,
      "mean_token_accuracy": 0.9683508425951004,
      "num_tokens": 169314982.0,
      "step": 1470
    },
    {
      "epoch": 0.32660267019750633,
      "grad_norm": 34.25,
      "learning_rate": 9.654368743221022e-06,
      "loss": 2.3217,
      "mean_token_accuracy": 0.9677969500422478,
      "num_tokens": 170457387.0,
      "step": 1480
    },
    {
      "epoch": 0.3288094449961381,
      "grad_norm": 75.5,
      "learning_rate": 9.647672544570981e-06,
      "loss": 2.2997,
      "mean_token_accuracy": 0.9690256834030151,
      "num_tokens": 171609482.0,
      "step": 1490
    },
    {
      "epoch": 0.3310162197947699,
      "grad_norm": 26.625,
      "learning_rate": 9.640914469030216e-06,
      "loss": 2.2317,
      "mean_token_accuracy": 0.967070896923542,
      "num_tokens": 172763347.0,
      "step": 1500
    },
    {
      "epoch": 0.33322299459340177,
      "grad_norm": 26.0,
      "learning_rate": 9.634094606572515e-06,
      "loss": 2.2098,
      "mean_token_accuracy": 0.9684022516012192,
      "num_tokens": 173906059.0,
      "step": 1510
    },
    {
      "epoch": 0.33542976939203356,
      "grad_norm": 27.0,
      "learning_rate": 9.627213047994265e-06,
      "loss": 2.2717,
      "mean_token_accuracy": 0.968683534860611,
      "num_tokens": 175056528.0,
      "step": 1520
    },
    {
      "epoch": 0.33763654419066536,
      "grad_norm": 38.25,
      "learning_rate": 9.620269884913247e-06,
      "loss": 2.2239,
      "mean_token_accuracy": 0.9698158174753189,
      "num_tokens": 176216895.0,
      "step": 1530
    },
    {
      "epoch": 0.33984331898929715,
      "grad_norm": 46.5,
      "learning_rate": 9.613265209767417e-06,
      "loss": 2.4008,
      "mean_token_accuracy": 0.9657038792967796,
      "num_tokens": 177382380.0,
      "step": 1540
    },
    {
      "epoch": 0.34205009378792894,
      "grad_norm": 36.75,
      "learning_rate": 9.606199115813672e-06,
      "loss": 2.2793,
      "mean_token_accuracy": 0.9694080829620362,
      "num_tokens": 178541743.0,
      "step": 1550
    },
    {
      "epoch": 0.34425686858656074,
      "grad_norm": 28.375,
      "learning_rate": 9.599071697126608e-06,
      "loss": 2.2745,
      "mean_token_accuracy": 0.9676408231258392,
      "num_tokens": 179690359.0,
      "step": 1560
    },
    {
      "epoch": 0.34646364338519253,
      "grad_norm": 34.0,
      "learning_rate": 9.591883048597273e-06,
      "loss": 2.3501,
      "mean_token_accuracy": 0.9658555924892426,
      "num_tokens": 180857119.0,
      "step": 1570
    },
    {
      "epoch": 0.3486704181838243,
      "grad_norm": 39.5,
      "learning_rate": 9.584633265931894e-06,
      "loss": 2.2474,
      "mean_token_accuracy": 0.9687186673283577,
      "num_tokens": 181999028.0,
      "step": 1580
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 43.0,
      "learning_rate": 9.577322445650616e-06,
      "loss": 2.374,
      "mean_token_accuracy": 0.9668631985783577,
      "num_tokens": 183161337.0,
      "step": 1590
    },
    {
      "epoch": 0.3530839677810879,
      "grad_norm": 50.25,
      "learning_rate": 9.569950685086202e-06,
      "loss": 2.3152,
      "mean_token_accuracy": 0.968401524424553,
      "num_tokens": 184314452.0,
      "step": 1600
    },
    {
      "epoch": 0.35529074257971976,
      "grad_norm": 44.0,
      "learning_rate": 9.562518082382751e-06,
      "loss": 2.4425,
      "mean_token_accuracy": 0.9645825639367104,
      "num_tokens": 185464891.0,
      "step": 1610
    },
    {
      "epoch": 0.35749751737835156,
      "grad_norm": 38.25,
      "learning_rate": 9.555024736494382e-06,
      "loss": 2.1862,
      "mean_token_accuracy": 0.96970224827528,
      "num_tokens": 186629335.0,
      "step": 1620
    },
    {
      "epoch": 0.35970429217698335,
      "grad_norm": 27.125,
      "learning_rate": 9.54747074718392e-06,
      "loss": 2.5521,
      "mean_token_accuracy": 0.9630803406238556,
      "num_tokens": 187792990.0,
      "step": 1630
    },
    {
      "epoch": 0.36191106697561515,
      "grad_norm": 50.25,
      "learning_rate": 9.539856215021568e-06,
      "loss": 2.3001,
      "mean_token_accuracy": 0.9681154564023018,
      "num_tokens": 188941540.0,
      "step": 1640
    },
    {
      "epoch": 0.36411784177424694,
      "grad_norm": 29.5,
      "learning_rate": 9.53218124138357e-06,
      "loss": 2.3927,
      "mean_token_accuracy": 0.9630109906196594,
      "num_tokens": 190109790.0,
      "step": 1650
    },
    {
      "epoch": 0.36632461657287874,
      "grad_norm": 86.0,
      "learning_rate": 9.524445928450851e-06,
      "loss": 2.3391,
      "mean_token_accuracy": 0.9650105178356171,
      "num_tokens": 191253589.0,
      "step": 1660
    },
    {
      "epoch": 0.36853139137151053,
      "grad_norm": 82.0,
      "learning_rate": 9.516650379207677e-06,
      "loss": 2.3133,
      "mean_token_accuracy": 0.9696876212954522,
      "num_tokens": 192386106.0,
      "step": 1670
    },
    {
      "epoch": 0.3707381661701423,
      "grad_norm": 53.25,
      "learning_rate": 9.508794697440257e-06,
      "loss": 2.3493,
      "mean_token_accuracy": 0.9684646859765053,
      "num_tokens": 193527888.0,
      "step": 1680
    },
    {
      "epoch": 0.3729449409687741,
      "grad_norm": 36.0,
      "learning_rate": 9.50087898773539e-06,
      "loss": 2.2985,
      "mean_token_accuracy": 0.9692732781171799,
      "num_tokens": 194689653.0,
      "step": 1690
    },
    {
      "epoch": 0.3751517157674059,
      "grad_norm": 45.0,
      "learning_rate": 9.492903355479047e-06,
      "loss": 2.3694,
      "mean_token_accuracy": 0.9660176306962966,
      "num_tokens": 195835780.0,
      "step": 1700
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 68.0,
      "learning_rate": 9.484867906854986e-06,
      "loss": 2.3309,
      "mean_token_accuracy": 0.9669578969478607,
      "num_tokens": 196990250.0,
      "step": 1710
    },
    {
      "epoch": 0.37956526536466956,
      "grad_norm": 33.0,
      "learning_rate": 9.476772748843327e-06,
      "loss": 2.225,
      "mean_token_accuracy": 0.9675502896308898,
      "num_tokens": 198128385.0,
      "step": 1720
    },
    {
      "epoch": 0.38177204016330135,
      "grad_norm": 25.75,
      "learning_rate": 9.468617989219136e-06,
      "loss": 2.2592,
      "mean_token_accuracy": 0.9690595448017121,
      "num_tokens": 199270632.0,
      "step": 1730
    },
    {
      "epoch": 0.38397881496193315,
      "grad_norm": 38.75,
      "learning_rate": 9.460403736550982e-06,
      "loss": 2.1368,
      "mean_token_accuracy": 0.97012959420681,
      "num_tokens": 200408726.0,
      "step": 1740
    },
    {
      "epoch": 0.38618558976056494,
      "grad_norm": 58.5,
      "learning_rate": 9.452130100199504e-06,
      "loss": 2.2226,
      "mean_token_accuracy": 0.9691491723060608,
      "num_tokens": 201567549.0,
      "step": 1750
    },
    {
      "epoch": 0.38839236455919673,
      "grad_norm": 37.0,
      "learning_rate": 9.443797190315938e-06,
      "loss": 2.2619,
      "mean_token_accuracy": 0.9689684405922889,
      "num_tokens": 202715410.0,
      "step": 1760
    },
    {
      "epoch": 0.39059913935782853,
      "grad_norm": 47.75,
      "learning_rate": 9.435405117840662e-06,
      "loss": 2.4012,
      "mean_token_accuracy": 0.9674781620502472,
      "num_tokens": 203862993.0,
      "step": 1770
    },
    {
      "epoch": 0.3928059141564603,
      "grad_norm": 32.75,
      "learning_rate": 9.42695399450172e-06,
      "loss": 2.2962,
      "mean_token_accuracy": 0.9677872568368912,
      "num_tokens": 205027241.0,
      "step": 1780
    },
    {
      "epoch": 0.3950126889550921,
      "grad_norm": 41.5,
      "learning_rate": 9.418443932813328e-06,
      "loss": 2.3077,
      "mean_token_accuracy": 0.9679502516984939,
      "num_tokens": 206188556.0,
      "step": 1790
    },
    {
      "epoch": 0.3972194637537239,
      "grad_norm": 32.25,
      "learning_rate": 9.409875046074379e-06,
      "loss": 2.2889,
      "mean_token_accuracy": 0.9702284663915635,
      "num_tokens": 207335561.0,
      "step": 1800
    },
    {
      "epoch": 0.3994262385523557,
      "grad_norm": 31.875,
      "learning_rate": 9.401247448366937e-06,
      "loss": 2.4358,
      "mean_token_accuracy": 0.9653665542602539,
      "num_tokens": 208475730.0,
      "step": 1810
    },
    {
      "epoch": 0.40163301335098756,
      "grad_norm": 31.625,
      "learning_rate": 9.392561254554712e-06,
      "loss": 2.3267,
      "mean_token_accuracy": 0.9662824124097824,
      "num_tokens": 209615143.0,
      "step": 1820
    },
    {
      "epoch": 0.40383978814961935,
      "grad_norm": 23.25,
      "learning_rate": 9.383816580281539e-06,
      "loss": 2.2844,
      "mean_token_accuracy": 0.9669794410467147,
      "num_tokens": 210770105.0,
      "step": 1830
    },
    {
      "epoch": 0.40604656294825114,
      "grad_norm": 25.125,
      "learning_rate": 9.375013541969828e-06,
      "loss": 2.2747,
      "mean_token_accuracy": 0.9688897132873535,
      "num_tokens": 211919518.0,
      "step": 1840
    },
    {
      "epoch": 0.40825333774688294,
      "grad_norm": 31.75,
      "learning_rate": 9.366152256819025e-06,
      "loss": 2.4818,
      "mean_token_accuracy": 0.9641079470515251,
      "num_tokens": 213075286.0,
      "step": 1850
    },
    {
      "epoch": 0.41046011254551473,
      "grad_norm": 32.5,
      "learning_rate": 9.357232842804045e-06,
      "loss": 2.3937,
      "mean_token_accuracy": 0.9639065489172935,
      "num_tokens": 214241852.0,
      "step": 1860
    },
    {
      "epoch": 0.4126668873441465,
      "grad_norm": 109.5,
      "learning_rate": 9.348255418673702e-06,
      "loss": 2.3037,
      "mean_token_accuracy": 0.9661361396312713,
      "num_tokens": 215391101.0,
      "step": 1870
    },
    {
      "epoch": 0.4148736621427783,
      "grad_norm": 103.5,
      "learning_rate": 9.339220103949132e-06,
      "loss": 2.4911,
      "mean_token_accuracy": 0.9644875302910805,
      "num_tokens": 216535129.0,
      "step": 1880
    },
    {
      "epoch": 0.4170804369414101,
      "grad_norm": 97.5,
      "learning_rate": 9.330127018922195e-06,
      "loss": 2.1134,
      "mean_token_accuracy": 0.9706643253564835,
      "num_tokens": 217681553.0,
      "step": 1890
    },
    {
      "epoch": 0.4192872117400419,
      "grad_norm": 26.75,
      "learning_rate": 9.320976284653877e-06,
      "loss": 2.174,
      "mean_token_accuracy": 0.9696374729275703,
      "num_tokens": 218833071.0,
      "step": 1900
    },
    {
      "epoch": 0.4214939865386737,
      "grad_norm": 53.25,
      "learning_rate": 9.311768022972682e-06,
      "loss": 2.2255,
      "mean_token_accuracy": 0.966447976231575,
      "num_tokens": 219974902.0,
      "step": 1910
    },
    {
      "epoch": 0.42370076133730555,
      "grad_norm": 52.25,
      "learning_rate": 9.302502356473006e-06,
      "loss": 2.4281,
      "mean_token_accuracy": 0.962953969836235,
      "num_tokens": 221140517.0,
      "step": 1920
    },
    {
      "epoch": 0.42590753613593735,
      "grad_norm": 52.0,
      "learning_rate": 9.293179408513501e-06,
      "loss": 2.4009,
      "mean_token_accuracy": 0.9657657817006111,
      "num_tokens": 222292419.0,
      "step": 1930
    },
    {
      "epoch": 0.42811431093456914,
      "grad_norm": 37.75,
      "learning_rate": 9.283799303215442e-06,
      "loss": 2.3334,
      "mean_token_accuracy": 0.9634455770254136,
      "num_tokens": 223458807.0,
      "step": 1940
    },
    {
      "epoch": 0.43032108573320094,
      "grad_norm": 38.5,
      "learning_rate": 9.274362165461064e-06,
      "loss": 2.3296,
      "mean_token_accuracy": 0.9671370834112167,
      "num_tokens": 224604886.0,
      "step": 1950
    },
    {
      "epoch": 0.43252786053183273,
      "grad_norm": 55.75,
      "learning_rate": 9.264868120891913e-06,
      "loss": 2.4311,
      "mean_token_accuracy": 0.966274832189083,
      "num_tokens": 225746965.0,
      "step": 1960
    },
    {
      "epoch": 0.4347346353304645,
      "grad_norm": 31.5,
      "learning_rate": 9.255317295907158e-06,
      "loss": 2.328,
      "mean_token_accuracy": 0.9669025555253029,
      "num_tokens": 226913200.0,
      "step": 1970
    },
    {
      "epoch": 0.4369414101290963,
      "grad_norm": 77.0,
      "learning_rate": 9.245709817661917e-06,
      "loss": 2.1147,
      "mean_token_accuracy": 0.9688583508133888,
      "num_tokens": 228066878.0,
      "step": 1980
    },
    {
      "epoch": 0.4391481849277281,
      "grad_norm": 26.125,
      "learning_rate": 9.236045814065563e-06,
      "loss": 2.1511,
      "mean_token_accuracy": 0.967818745970726,
      "num_tokens": 229211377.0,
      "step": 1990
    },
    {
      "epoch": 0.4413549597263599,
      "grad_norm": 33.5,
      "learning_rate": 9.226325413780021e-06,
      "loss": 2.2553,
      "mean_token_accuracy": 0.9709501743316651,
      "num_tokens": 230347755.0,
      "step": 2000
    },
    {
      "epoch": 0.4435617345249917,
      "grad_norm": 88.5,
      "learning_rate": 9.216548746218056e-06,
      "loss": 2.2576,
      "mean_token_accuracy": 0.9685494884848594,
      "num_tokens": 231508177.0,
      "step": 2010
    },
    {
      "epoch": 0.44576850932362355,
      "grad_norm": 35.75,
      "learning_rate": 9.206715941541547e-06,
      "loss": 2.2184,
      "mean_token_accuracy": 0.9694117784500123,
      "num_tokens": 232654808.0,
      "step": 2020
    },
    {
      "epoch": 0.44797528412225535,
      "grad_norm": 33.5,
      "learning_rate": 9.196827130659752e-06,
      "loss": 2.4001,
      "mean_token_accuracy": 0.964475291967392,
      "num_tokens": 233821713.0,
      "step": 2030
    },
    {
      "epoch": 0.45018205892088714,
      "grad_norm": 41.25,
      "learning_rate": 9.186882445227572e-06,
      "loss": 2.1556,
      "mean_token_accuracy": 0.9712439984083175,
      "num_tokens": 234969349.0,
      "step": 2040
    },
    {
      "epoch": 0.45238883371951893,
      "grad_norm": 29.75,
      "learning_rate": 9.1768820176438e-06,
      "loss": 2.3453,
      "mean_token_accuracy": 0.9664183363318444,
      "num_tokens": 236103583.0,
      "step": 2050
    },
    {
      "epoch": 0.45459560851815073,
      "grad_norm": 30.25,
      "learning_rate": 9.166825981049345e-06,
      "loss": 2.3052,
      "mean_token_accuracy": 0.9680563971400261,
      "num_tokens": 237255347.0,
      "step": 2060
    },
    {
      "epoch": 0.4568023833167825,
      "grad_norm": 30.375,
      "learning_rate": 9.156714469325474e-06,
      "loss": 2.311,
      "mean_token_accuracy": 0.9676059067249299,
      "num_tokens": 238408728.0,
      "step": 2070
    },
    {
      "epoch": 0.4590091581154143,
      "grad_norm": 25.875,
      "learning_rate": 9.14654761709202e-06,
      "loss": 2.1935,
      "mean_token_accuracy": 0.9701084122061729,
      "num_tokens": 239565441.0,
      "step": 2080
    },
    {
      "epoch": 0.4612159329140461,
      "grad_norm": 35.0,
      "learning_rate": 9.136325559705593e-06,
      "loss": 2.0259,
      "mean_token_accuracy": 0.9703326031565667,
      "num_tokens": 240728868.0,
      "step": 2090
    },
    {
      "epoch": 0.4634227077126779,
      "grad_norm": 27.625,
      "learning_rate": 9.12604843325778e-06,
      "loss": 2.2043,
      "mean_token_accuracy": 0.9687738925218582,
      "num_tokens": 241881571.0,
      "step": 2100
    },
    {
      "epoch": 0.4656294825113097,
      "grad_norm": 40.75,
      "learning_rate": 9.11571637457333e-06,
      "loss": 2.4851,
      "mean_token_accuracy": 0.9667060732841491,
      "num_tokens": 243031077.0,
      "step": 2110
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 52.5,
      "learning_rate": 9.105329521208334e-06,
      "loss": 2.293,
      "mean_token_accuracy": 0.9649059772491455,
      "num_tokens": 244183526.0,
      "step": 2120
    },
    {
      "epoch": 0.47004303210857334,
      "grad_norm": 60.0,
      "learning_rate": 9.094888011448391e-06,
      "loss": 2.4825,
      "mean_token_accuracy": 0.9651537433266639,
      "num_tokens": 245350675.0,
      "step": 2130
    },
    {
      "epoch": 0.47224980690720514,
      "grad_norm": 73.5,
      "learning_rate": 9.084391984306775e-06,
      "loss": 2.3972,
      "mean_token_accuracy": 0.9642259508371354,
      "num_tokens": 246493568.0,
      "step": 2140
    },
    {
      "epoch": 0.47445658170583693,
      "grad_norm": 26.25,
      "learning_rate": 9.073841579522571e-06,
      "loss": 2.2809,
      "mean_token_accuracy": 0.9687073454260826,
      "num_tokens": 247628717.0,
      "step": 2150
    },
    {
      "epoch": 0.4766633565044687,
      "grad_norm": 36.5,
      "learning_rate": 9.063236937558826e-06,
      "loss": 2.1135,
      "mean_token_accuracy": 0.9713551491498947,
      "num_tokens": 248778776.0,
      "step": 2160
    },
    {
      "epoch": 0.4788701313031005,
      "grad_norm": 32.0,
      "learning_rate": 9.052578199600675e-06,
      "loss": 2.3261,
      "mean_token_accuracy": 0.9696324050426484,
      "num_tokens": 249941829.0,
      "step": 2170
    },
    {
      "epoch": 0.4810769061017323,
      "grad_norm": 62.25,
      "learning_rate": 9.041865507553458e-06,
      "loss": 2.2303,
      "mean_token_accuracy": 0.9702025711536407,
      "num_tokens": 251093922.0,
      "step": 2180
    },
    {
      "epoch": 0.4832836809003641,
      "grad_norm": 44.25,
      "learning_rate": 9.031099004040841e-06,
      "loss": 2.0751,
      "mean_token_accuracy": 0.9709090188145637,
      "num_tokens": 252241596.0,
      "step": 2190
    },
    {
      "epoch": 0.4854904556989959,
      "grad_norm": 48.25,
      "learning_rate": 9.020278832402902e-06,
      "loss": 2.379,
      "mean_token_accuracy": 0.9674508139491081,
      "num_tokens": 253396378.0,
      "step": 2200
    },
    {
      "epoch": 0.4876972304976277,
      "grad_norm": 27.0,
      "learning_rate": 9.009405136694234e-06,
      "loss": 2.2068,
      "mean_token_accuracy": 0.9695529088377952,
      "num_tokens": 254545434.0,
      "step": 2210
    },
    {
      "epoch": 0.4899040052962595,
      "grad_norm": 30.5,
      "learning_rate": 8.998478061682025e-06,
      "loss": 2.2644,
      "mean_token_accuracy": 0.9688047289848327,
      "num_tokens": 255698903.0,
      "step": 2220
    },
    {
      "epoch": 0.49211078009489134,
      "grad_norm": 50.5,
      "learning_rate": 8.987497752844132e-06,
      "loss": 2.1311,
      "mean_token_accuracy": 0.9704986691474915,
      "num_tokens": 256850100.0,
      "step": 2230
    },
    {
      "epoch": 0.49431755489352314,
      "grad_norm": 32.5,
      "learning_rate": 8.976464356367133e-06,
      "loss": 2.2786,
      "mean_token_accuracy": 0.9677370265126228,
      "num_tokens": 257993006.0,
      "step": 2240
    },
    {
      "epoch": 0.49652432969215493,
      "grad_norm": 40.5,
      "learning_rate": 8.965378019144397e-06,
      "loss": 2.203,
      "mean_token_accuracy": 0.9703607648611069,
      "num_tokens": 259142750.0,
      "step": 2250
    },
    {
      "epoch": 0.4987311044907867,
      "grad_norm": 94.5,
      "learning_rate": 8.95423888877412e-06,
      "loss": 2.3396,
      "mean_token_accuracy": 0.968078376352787,
      "num_tokens": 260305182.0,
      "step": 2260
    },
    {
      "epoch": 0.5009378792894185,
      "grad_norm": 46.75,
      "learning_rate": 8.943047113557358e-06,
      "loss": 2.3251,
      "mean_token_accuracy": 0.9666526198387146,
      "num_tokens": 261465998.0,
      "step": 2270
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 40.75,
      "learning_rate": 8.931802842496056e-06,
      "loss": 2.3316,
      "mean_token_accuracy": 0.9695447832345963,
      "num_tokens": 262623192.0,
      "step": 2280
    },
    {
      "epoch": 0.5053514288866822,
      "grad_norm": 89.0,
      "learning_rate": 8.920506225291067e-06,
      "loss": 2.1414,
      "mean_token_accuracy": 0.9706215053796768,
      "num_tokens": 263782530.0,
      "step": 2290
    },
    {
      "epoch": 0.5075582036853139,
      "grad_norm": 41.25,
      "learning_rate": 8.90915741234015e-06,
      "loss": 2.4683,
      "mean_token_accuracy": 0.9681061506271362,
      "num_tokens": 264917551.0,
      "step": 2300
    },
    {
      "epoch": 0.5097649784839458,
      "grad_norm": 29.0,
      "learning_rate": 8.897756554735976e-06,
      "loss": 2.3191,
      "mean_token_accuracy": 0.9655913576483727,
      "num_tokens": 266067631.0,
      "step": 2310
    },
    {
      "epoch": 0.5119717532825775,
      "grad_norm": 45.0,
      "learning_rate": 8.886303804264117e-06,
      "loss": 2.1917,
      "mean_token_accuracy": 0.9677790090441704,
      "num_tokens": 267224470.0,
      "step": 2320
    },
    {
      "epoch": 0.5141785280812093,
      "grad_norm": 59.0,
      "learning_rate": 8.874799313401014e-06,
      "loss": 2.0965,
      "mean_token_accuracy": 0.9708941861987114,
      "num_tokens": 268368173.0,
      "step": 2330
    },
    {
      "epoch": 0.5163853028798411,
      "grad_norm": 23.5,
      "learning_rate": 8.863243235311964e-06,
      "loss": 2.2567,
      "mean_token_accuracy": 0.9683190450072289,
      "num_tokens": 269521032.0,
      "step": 2340
    },
    {
      "epoch": 0.5185920776784729,
      "grad_norm": 27.5,
      "learning_rate": 8.851635723849062e-06,
      "loss": 2.2438,
      "mean_token_accuracy": 0.9680898264050484,
      "num_tokens": 270660849.0,
      "step": 2350
    },
    {
      "epoch": 0.5207988524771047,
      "grad_norm": 25.75,
      "learning_rate": 8.839976933549173e-06,
      "loss": 2.2324,
      "mean_token_accuracy": 0.9692135348916053,
      "num_tokens": 271814303.0,
      "step": 2360
    },
    {
      "epoch": 0.5230056272757365,
      "grad_norm": 54.0,
      "learning_rate": 8.828267019631852e-06,
      "loss": 2.2684,
      "mean_token_accuracy": 0.9690634965896606,
      "num_tokens": 272973336.0,
      "step": 2370
    },
    {
      "epoch": 0.5252124020743683,
      "grad_norm": 53.0,
      "learning_rate": 8.8165061379973e-06,
      "loss": 2.3381,
      "mean_token_accuracy": 0.965342877805233,
      "num_tokens": 274111194.0,
      "step": 2380
    },
    {
      "epoch": 0.5274191768730001,
      "grad_norm": 38.0,
      "learning_rate": 8.804694445224274e-06,
      "loss": 2.2465,
      "mean_token_accuracy": 0.9686747953295708,
      "num_tokens": 275259048.0,
      "step": 2390
    },
    {
      "epoch": 0.529625951671632,
      "grad_norm": 52.5,
      "learning_rate": 8.792832098568002e-06,
      "loss": 2.2175,
      "mean_token_accuracy": 0.970515850186348,
      "num_tokens": 276425321.0,
      "step": 2400
    },
    {
      "epoch": 0.5318327264702637,
      "grad_norm": 61.0,
      "learning_rate": 8.7809192559581e-06,
      "loss": 2.31,
      "mean_token_accuracy": 0.9675430282950401,
      "num_tokens": 277589607.0,
      "step": 2410
    },
    {
      "epoch": 0.5340395012688955,
      "grad_norm": 58.0,
      "learning_rate": 8.76895607599646e-06,
      "loss": 2.1759,
      "mean_token_accuracy": 0.9692975118756294,
      "num_tokens": 278744612.0,
      "step": 2420
    },
    {
      "epoch": 0.5362462760675273,
      "grad_norm": 55.0,
      "learning_rate": 8.756942717955142e-06,
      "loss": 2.1784,
      "mean_token_accuracy": 0.9700711444020271,
      "num_tokens": 279891771.0,
      "step": 2430
    },
    {
      "epoch": 0.5384530508661591,
      "grad_norm": 35.75,
      "learning_rate": 8.744879341774251e-06,
      "loss": 2.298,
      "mean_token_accuracy": 0.9677460372447968,
      "num_tokens": 281039349.0,
      "step": 2440
    },
    {
      "epoch": 0.5406598256647909,
      "grad_norm": 29.125,
      "learning_rate": 8.732766108059814e-06,
      "loss": 2.3372,
      "mean_token_accuracy": 0.9666269764304161,
      "num_tokens": 282192901.0,
      "step": 2450
    },
    {
      "epoch": 0.5428666004634227,
      "grad_norm": 32.0,
      "learning_rate": 8.720603178081632e-06,
      "loss": 2.2421,
      "mean_token_accuracy": 0.9688358440995216,
      "num_tokens": 283350829.0,
      "step": 2460
    },
    {
      "epoch": 0.5450733752620545,
      "grad_norm": 30.875,
      "learning_rate": 8.708390713771145e-06,
      "loss": 2.1647,
      "mean_token_accuracy": 0.9711746796965599,
      "num_tokens": 284496558.0,
      "step": 2470
    },
    {
      "epoch": 0.5472801500606863,
      "grad_norm": 26.75,
      "learning_rate": 8.696128877719258e-06,
      "loss": 2.294,
      "mean_token_accuracy": 0.9695102021098136,
      "num_tokens": 285649122.0,
      "step": 2480
    },
    {
      "epoch": 0.5494869248593182,
      "grad_norm": 35.5,
      "learning_rate": 8.683817833174204e-06,
      "loss": 2.0604,
      "mean_token_accuracy": 0.9690757155418396,
      "num_tokens": 286805979.0,
      "step": 2490
    },
    {
      "epoch": 0.5516936996579499,
      "grad_norm": 57.25,
      "learning_rate": 8.67145774403934e-06,
      "loss": 2.3768,
      "mean_token_accuracy": 0.965617473423481,
      "num_tokens": 287967501.0,
      "step": 2500
    },
    {
      "epoch": 0.5539004744565817,
      "grad_norm": 30.125,
      "learning_rate": 8.659048774870986e-06,
      "loss": 2.1376,
      "mean_token_accuracy": 0.9703375771641731,
      "num_tokens": 289123305.0,
      "step": 2510
    },
    {
      "epoch": 0.5561072492552135,
      "grad_norm": 44.25,
      "learning_rate": 8.646591090876225e-06,
      "loss": 2.086,
      "mean_token_accuracy": 0.9709781780838966,
      "num_tokens": 290255229.0,
      "step": 2520
    },
    {
      "epoch": 0.5583140240538453,
      "grad_norm": 57.25,
      "learning_rate": 8.634084857910709e-06,
      "loss": 2.3211,
      "mean_token_accuracy": 0.9684085294604301,
      "num_tokens": 291393248.0,
      "step": 2530
    },
    {
      "epoch": 0.5605207988524771,
      "grad_norm": 28.375,
      "learning_rate": 8.621530242476446e-06,
      "loss": 2.2369,
      "mean_token_accuracy": 0.9693953603506088,
      "num_tokens": 292536784.0,
      "step": 2540
    },
    {
      "epoch": 0.5627275736511089,
      "grad_norm": 46.0,
      "learning_rate": 8.608927411719585e-06,
      "loss": 2.2892,
      "mean_token_accuracy": 0.9678306207060814,
      "num_tokens": 293691169.0,
      "step": 2550
    },
    {
      "epoch": 0.5649343484497407,
      "grad_norm": 74.5,
      "learning_rate": 8.59627653342819e-06,
      "loss": 2.377,
      "mean_token_accuracy": 0.9672712400555611,
      "num_tokens": 294839102.0,
      "step": 2560
    },
    {
      "epoch": 0.5671411232483725,
      "grad_norm": 84.0,
      "learning_rate": 8.583577776030005e-06,
      "loss": 2.1822,
      "mean_token_accuracy": 0.9671956941485405,
      "num_tokens": 296022598.0,
      "step": 2570
    },
    {
      "epoch": 0.5693478980470043,
      "grad_norm": 95.5,
      "learning_rate": 8.570831308590219e-06,
      "loss": 2.1975,
      "mean_token_accuracy": 0.9708220675587654,
      "num_tokens": 297174948.0,
      "step": 2580
    },
    {
      "epoch": 0.5715546728456361,
      "grad_norm": 48.5,
      "learning_rate": 8.558037300809209e-06,
      "loss": 2.2436,
      "mean_token_accuracy": 0.9687622368335724,
      "num_tokens": 298320791.0,
      "step": 2590
    },
    {
      "epoch": 0.573761447644268,
      "grad_norm": 42.75,
      "learning_rate": 8.545195923020273e-06,
      "loss": 2.162,
      "mean_token_accuracy": 0.9687483668327331,
      "num_tokens": 299463593.0,
      "step": 2600
    },
    {
      "epoch": 0.5759682224428997,
      "grad_norm": 51.5,
      "learning_rate": 8.532307346187384e-06,
      "loss": 2.1797,
      "mean_token_accuracy": 0.97235436886549,
      "num_tokens": 300610885.0,
      "step": 2610
    },
    {
      "epoch": 0.5781749972415315,
      "grad_norm": 31.25,
      "learning_rate": 8.519371741902888e-06,
      "loss": 2.1312,
      "mean_token_accuracy": 0.9692936658859252,
      "num_tokens": 301767297.0,
      "step": 2620
    },
    {
      "epoch": 0.5803817720401633,
      "grad_norm": 52.75,
      "learning_rate": 8.506389282385242e-06,
      "loss": 2.0742,
      "mean_token_accuracy": 0.9726780265569687,
      "num_tokens": 302914250.0,
      "step": 2630
    },
    {
      "epoch": 0.5825885468387951,
      "grad_norm": 30.5,
      "learning_rate": 8.493360140476699e-06,
      "loss": 2.2093,
      "mean_token_accuracy": 0.9678682669997215,
      "num_tokens": 304078421.0,
      "step": 2640
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 40.5,
      "learning_rate": 8.480284489641034e-06,
      "loss": 2.1967,
      "mean_token_accuracy": 0.9684683859348298,
      "num_tokens": 305246598.0,
      "step": 2650
    },
    {
      "epoch": 0.5870020964360587,
      "grad_norm": 33.75,
      "learning_rate": 8.467162503961209e-06,
      "loss": 2.3628,
      "mean_token_accuracy": 0.9664306521415711,
      "num_tokens": 306403518.0,
      "step": 2660
    },
    {
      "epoch": 0.5892088712346905,
      "grad_norm": 31.0,
      "learning_rate": 8.45399435813707e-06,
      "loss": 2.2629,
      "mean_token_accuracy": 0.968101155757904,
      "num_tokens": 307551805.0,
      "step": 2670
    },
    {
      "epoch": 0.5914156460333223,
      "grad_norm": 26.75,
      "learning_rate": 8.440780227483016e-06,
      "loss": 2.2753,
      "mean_token_accuracy": 0.9677685379981995,
      "num_tokens": 308697429.0,
      "step": 2680
    },
    {
      "epoch": 0.593622420831954,
      "grad_norm": 98.5,
      "learning_rate": 8.427520287925669e-06,
      "loss": 2.1616,
      "mean_token_accuracy": 0.9697274029254913,
      "num_tokens": 309857041.0,
      "step": 2690
    },
    {
      "epoch": 0.5958291956305859,
      "grad_norm": 61.5,
      "learning_rate": 8.414214716001519e-06,
      "loss": 2.3417,
      "mean_token_accuracy": 0.9682802945375443,
      "num_tokens": 311006379.0,
      "step": 2700
    },
    {
      "epoch": 0.5980359704292177,
      "grad_norm": 27.375,
      "learning_rate": 8.400863688854598e-06,
      "loss": 2.1063,
      "mean_token_accuracy": 0.9709339514374733,
      "num_tokens": 312144080.0,
      "step": 2710
    },
    {
      "epoch": 0.6002427452278495,
      "grad_norm": 27.125,
      "learning_rate": 8.387467384234096e-06,
      "loss": 2.2477,
      "mean_token_accuracy": 0.9708619490265846,
      "num_tokens": 313292785.0,
      "step": 2720
    },
    {
      "epoch": 0.6024495200264813,
      "grad_norm": 97.5,
      "learning_rate": 8.37402598049201e-06,
      "loss": 2.1449,
      "mean_token_accuracy": 0.971640095114708,
      "num_tokens": 314424933.0,
      "step": 2730
    },
    {
      "epoch": 0.6046562948251131,
      "grad_norm": 49.25,
      "learning_rate": 8.360539656580768e-06,
      "loss": 2.2201,
      "mean_token_accuracy": 0.9700899377465249,
      "num_tokens": 315584036.0,
      "step": 2740
    },
    {
      "epoch": 0.6068630696237449,
      "grad_norm": 33.0,
      "learning_rate": 8.347008592050834e-06,
      "loss": 2.2112,
      "mean_token_accuracy": 0.970268526673317,
      "num_tokens": 316722761.0,
      "step": 2750
    },
    {
      "epoch": 0.6090698444223767,
      "grad_norm": 68.0,
      "learning_rate": 8.333432967048339e-06,
      "loss": 2.3118,
      "mean_token_accuracy": 0.9659661173820495,
      "num_tokens": 317876682.0,
      "step": 2760
    },
    {
      "epoch": 0.6112766192210085,
      "grad_norm": 44.0,
      "learning_rate": 8.319812962312662e-06,
      "loss": 2.2375,
      "mean_token_accuracy": 0.9685799524188041,
      "num_tokens": 319024910.0,
      "step": 2770
    },
    {
      "epoch": 0.6134833940196402,
      "grad_norm": 75.0,
      "learning_rate": 8.306148759174036e-06,
      "loss": 2.1592,
      "mean_token_accuracy": 0.9718134820461273,
      "num_tokens": 320158889.0,
      "step": 2780
    },
    {
      "epoch": 0.6156901688182721,
      "grad_norm": 81.5,
      "learning_rate": 8.292440539551132e-06,
      "loss": 2.4029,
      "mean_token_accuracy": 0.9661935493350029,
      "num_tokens": 321318555.0,
      "step": 2790
    },
    {
      "epoch": 0.617896943616904,
      "grad_norm": 73.5,
      "learning_rate": 8.278688485948634e-06,
      "loss": 2.2134,
      "mean_token_accuracy": 0.9695664927363395,
      "num_tokens": 322454391.0,
      "step": 2800
    },
    {
      "epoch": 0.6201037184155357,
      "grad_norm": 34.5,
      "learning_rate": 8.264892781454807e-06,
      "loss": 2.2496,
      "mean_token_accuracy": 0.9668081119656563,
      "num_tokens": 323606695.0,
      "step": 2810
    },
    {
      "epoch": 0.6223104932141675,
      "grad_norm": 43.0,
      "learning_rate": 8.25105360973907e-06,
      "loss": 2.2249,
      "mean_token_accuracy": 0.9695513039827347,
      "num_tokens": 324765910.0,
      "step": 2820
    },
    {
      "epoch": 0.6245172680127993,
      "grad_norm": 42.5,
      "learning_rate": 8.237171155049539e-06,
      "loss": 2.0895,
      "mean_token_accuracy": 0.970494681596756,
      "num_tokens": 325902759.0,
      "step": 2830
    },
    {
      "epoch": 0.6267240428114311,
      "grad_norm": 26.625,
      "learning_rate": 8.22324560221058e-06,
      "loss": 2.1077,
      "mean_token_accuracy": 0.9717783167958259,
      "num_tokens": 327054288.0,
      "step": 2840
    },
    {
      "epoch": 0.6289308176100629,
      "grad_norm": 27.125,
      "learning_rate": 8.209277136620348e-06,
      "loss": 2.2056,
      "mean_token_accuracy": 0.9685600847005844,
      "num_tokens": 328208344.0,
      "step": 2850
    },
    {
      "epoch": 0.6311375924086947,
      "grad_norm": 28.125,
      "learning_rate": 8.195265944248315e-06,
      "loss": 2.2738,
      "mean_token_accuracy": 0.9689912527799607,
      "num_tokens": 329356990.0,
      "step": 2860
    },
    {
      "epoch": 0.6333443672073265,
      "grad_norm": 85.5,
      "learning_rate": 8.1812122116328e-06,
      "loss": 2.3829,
      "mean_token_accuracy": 0.96807861328125,
      "num_tokens": 330517106.0,
      "step": 2870
    },
    {
      "epoch": 0.6355511420059583,
      "grad_norm": 90.0,
      "learning_rate": 8.167116125878483e-06,
      "loss": 2.3083,
      "mean_token_accuracy": 0.9689312994480133,
      "num_tokens": 331665781.0,
      "step": 2880
    },
    {
      "epoch": 0.63775791680459,
      "grad_norm": 82.0,
      "learning_rate": 8.152977874653909e-06,
      "loss": 2.1648,
      "mean_token_accuracy": 0.9709917888045311,
      "num_tokens": 332818811.0,
      "step": 2890
    },
    {
      "epoch": 0.6399646916032219,
      "grad_norm": 60.75,
      "learning_rate": 8.138797646189e-06,
      "loss": 2.3127,
      "mean_token_accuracy": 0.9688727170228958,
      "num_tokens": 333972881.0,
      "step": 2900
    },
    {
      "epoch": 0.6421714664018537,
      "grad_norm": 32.25,
      "learning_rate": 8.12457562927254e-06,
      "loss": 2.0957,
      "mean_token_accuracy": 0.9714623034000397,
      "num_tokens": 335124741.0,
      "step": 2910
    },
    {
      "epoch": 0.6443782412004855,
      "grad_norm": 39.25,
      "learning_rate": 8.11031201324966e-06,
      "loss": 2.418,
      "mean_token_accuracy": 0.9668408274650574,
      "num_tokens": 336268246.0,
      "step": 2920
    },
    {
      "epoch": 0.6465850159991173,
      "grad_norm": 24.75,
      "learning_rate": 8.096006988019331e-06,
      "loss": 2.2089,
      "mean_token_accuracy": 0.9694518089294434,
      "num_tokens": 337408491.0,
      "step": 2930
    },
    {
      "epoch": 0.6487917907977491,
      "grad_norm": 50.25,
      "learning_rate": 8.081660744031818e-06,
      "loss": 2.2578,
      "mean_token_accuracy": 0.9702880099415779,
      "num_tokens": 338547657.0,
      "step": 2940
    },
    {
      "epoch": 0.6509985655963809,
      "grad_norm": 41.75,
      "learning_rate": 8.067273472286158e-06,
      "loss": 2.1453,
      "mean_token_accuracy": 0.9710926473140716,
      "num_tokens": 339694948.0,
      "step": 2950
    },
    {
      "epoch": 0.6532053403950127,
      "grad_norm": 32.25,
      "learning_rate": 8.052845364327609e-06,
      "loss": 2.2511,
      "mean_token_accuracy": 0.9682098478078842,
      "num_tokens": 340831900.0,
      "step": 2960
    },
    {
      "epoch": 0.6554121151936445,
      "grad_norm": 53.0,
      "learning_rate": 8.038376612245104e-06,
      "loss": 2.123,
      "mean_token_accuracy": 0.970916998386383,
      "num_tokens": 341976387.0,
      "step": 2970
    },
    {
      "epoch": 0.6576188899922762,
      "grad_norm": 75.0,
      "learning_rate": 8.023867408668692e-06,
      "loss": 2.1706,
      "mean_token_accuracy": 0.9689412295818329,
      "num_tokens": 343121358.0,
      "step": 2980
    },
    {
      "epoch": 0.6598256647909081,
      "grad_norm": 41.75,
      "learning_rate": 8.009317946766975e-06,
      "loss": 2.3627,
      "mean_token_accuracy": 0.9667907893657685,
      "num_tokens": 344286503.0,
      "step": 2990
    },
    {
      "epoch": 0.6620324395895398,
      "grad_norm": 66.0,
      "learning_rate": 7.994728420244533e-06,
      "loss": 2.2119,
      "mean_token_accuracy": 0.9699944481253624,
      "num_tokens": 345446119.0,
      "step": 3000
    },
    {
      "epoch": 0.6642392143881717,
      "grad_norm": 31.625,
      "learning_rate": 7.98009902333935e-06,
      "loss": 2.23,
      "mean_token_accuracy": 0.9680187299847602,
      "num_tokens": 346611461.0,
      "step": 3010
    },
    {
      "epoch": 0.6664459891868035,
      "grad_norm": 40.75,
      "learning_rate": 7.965429950820222e-06,
      "loss": 2.1812,
      "mean_token_accuracy": 0.9700601026415825,
      "num_tokens": 347762352.0,
      "step": 3020
    },
    {
      "epoch": 0.6686527639854353,
      "grad_norm": 41.25,
      "learning_rate": 7.95072139798417e-06,
      "loss": 2.134,
      "mean_token_accuracy": 0.970243364572525,
      "num_tokens": 348918299.0,
      "step": 3030
    },
    {
      "epoch": 0.6708595387840671,
      "grad_norm": 46.75,
      "learning_rate": 7.935973560653838e-06,
      "loss": 2.1777,
      "mean_token_accuracy": 0.9693630024790764,
      "num_tokens": 350054629.0,
      "step": 3040
    },
    {
      "epoch": 0.6730663135826989,
      "grad_norm": 32.75,
      "learning_rate": 7.92118663517488e-06,
      "loss": 2.2211,
      "mean_token_accuracy": 0.9712678596377373,
      "num_tokens": 351206148.0,
      "step": 3050
    },
    {
      "epoch": 0.6752730883813307,
      "grad_norm": 72.5,
      "learning_rate": 7.906360818413354e-06,
      "loss": 2.3031,
      "mean_token_accuracy": 0.9691796407103539,
      "num_tokens": 352359524.0,
      "step": 3060
    },
    {
      "epoch": 0.6774798631799624,
      "grad_norm": 68.5,
      "learning_rate": 7.891496307753099e-06,
      "loss": 2.1769,
      "mean_token_accuracy": 0.9693485498428345,
      "num_tokens": 353503230.0,
      "step": 3070
    },
    {
      "epoch": 0.6796866379785943,
      "grad_norm": 32.25,
      "learning_rate": 7.876593301093104e-06,
      "loss": 2.161,
      "mean_token_accuracy": 0.9697745114564895,
      "num_tokens": 354658570.0,
      "step": 3080
    },
    {
      "epoch": 0.681893412777226,
      "grad_norm": 96.0,
      "learning_rate": 7.861651996844877e-06,
      "loss": 2.1521,
      "mean_token_accuracy": 0.9706450372934341,
      "num_tokens": 355812944.0,
      "step": 3090
    },
    {
      "epoch": 0.6841001875758579,
      "grad_norm": 63.75,
      "learning_rate": 7.8466725939298e-06,
      "loss": 2.1295,
      "mean_token_accuracy": 0.970659151673317,
      "num_tokens": 356972747.0,
      "step": 3100
    },
    {
      "epoch": 0.6863069623744897,
      "grad_norm": 28.5,
      "learning_rate": 7.831655291776484e-06,
      "loss": 2.2171,
      "mean_token_accuracy": 0.9697210371494294,
      "num_tokens": 358131882.0,
      "step": 3110
    },
    {
      "epoch": 0.6885137371731215,
      "grad_norm": 38.0,
      "learning_rate": 7.81660029031811e-06,
      "loss": 2.3997,
      "mean_token_accuracy": 0.9674816936254501,
      "num_tokens": 359299520.0,
      "step": 3120
    },
    {
      "epoch": 0.6907205119717533,
      "grad_norm": 68.0,
      "learning_rate": 7.801507789989775e-06,
      "loss": 2.2029,
      "mean_token_accuracy": 0.969719810783863,
      "num_tokens": 360454015.0,
      "step": 3130
    },
    {
      "epoch": 0.6929272867703851,
      "grad_norm": 38.75,
      "learning_rate": 7.786377991725813e-06,
      "loss": 2.1169,
      "mean_token_accuracy": 0.9702064484357834,
      "num_tokens": 361600146.0,
      "step": 3140
    },
    {
      "epoch": 0.6951340615690169,
      "grad_norm": 31.125,
      "learning_rate": 7.771211096957125e-06,
      "loss": 2.279,
      "mean_token_accuracy": 0.967810207605362,
      "num_tokens": 362760084.0,
      "step": 3150
    },
    {
      "epoch": 0.6973408363676487,
      "grad_norm": 64.5,
      "learning_rate": 7.756007307608498e-06,
      "loss": 2.0098,
      "mean_token_accuracy": 0.9730646580457687,
      "num_tokens": 363913574.0,
      "step": 3160
    },
    {
      "epoch": 0.6995476111662805,
      "grad_norm": 35.5,
      "learning_rate": 7.740766826095918e-06,
      "loss": 2.2482,
      "mean_token_accuracy": 0.9681272000074387,
      "num_tokens": 365077588.0,
      "step": 3170
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 40.0,
      "learning_rate": 7.725489855323869e-06,
      "loss": 2.0745,
      "mean_token_accuracy": 0.9710229575634003,
      "num_tokens": 366224173.0,
      "step": 3180
    },
    {
      "epoch": 0.7039611607635441,
      "grad_norm": 29.75,
      "learning_rate": 7.710176598682639e-06,
      "loss": 2.1824,
      "mean_token_accuracy": 0.9676875367760658,
      "num_tokens": 367384660.0,
      "step": 3190
    },
    {
      "epoch": 0.7061679355621758,
      "grad_norm": 53.5,
      "learning_rate": 7.694827260045608e-06,
      "loss": 2.1278,
      "mean_token_accuracy": 0.9691912084817886,
      "num_tokens": 368527453.0,
      "step": 3200
    },
    {
      "epoch": 0.7083747103608077,
      "grad_norm": 38.0,
      "learning_rate": 7.679442043766534e-06,
      "loss": 1.9477,
      "mean_token_accuracy": 0.973905871808529,
      "num_tokens": 369692607.0,
      "step": 3210
    },
    {
      "epoch": 0.7105814851594395,
      "grad_norm": 45.5,
      "learning_rate": 7.664021154676828e-06,
      "loss": 2.3203,
      "mean_token_accuracy": 0.9664703860878945,
      "num_tokens": 370843483.0,
      "step": 3220
    },
    {
      "epoch": 0.7127882599580713,
      "grad_norm": 41.25,
      "learning_rate": 7.648564798082842e-06,
      "loss": 2.1163,
      "mean_token_accuracy": 0.9698843285441399,
      "num_tokens": 371999795.0,
      "step": 3230
    },
    {
      "epoch": 0.7149950347567031,
      "grad_norm": 54.0,
      "learning_rate": 7.63307317976312e-06,
      "loss": 2.151,
      "mean_token_accuracy": 0.9703769400715828,
      "num_tokens": 373132504.0,
      "step": 3240
    },
    {
      "epoch": 0.7172018095553349,
      "grad_norm": 35.25,
      "learning_rate": 7.617546505965658e-06,
      "loss": 2.2942,
      "mean_token_accuracy": 0.966479840874672,
      "num_tokens": 374278633.0,
      "step": 3250
    },
    {
      "epoch": 0.7194085843539667,
      "grad_norm": 38.75,
      "learning_rate": 7.601984983405173e-06,
      "loss": 2.117,
      "mean_token_accuracy": 0.9694958493113518,
      "num_tokens": 375435610.0,
      "step": 3260
    },
    {
      "epoch": 0.7216153591525984,
      "grad_norm": 50.0,
      "learning_rate": 7.586388819260338e-06,
      "loss": 2.1566,
      "mean_token_accuracy": 0.9699361696839333,
      "num_tokens": 376585019.0,
      "step": 3270
    },
    {
      "epoch": 0.7238221339512303,
      "grad_norm": 52.25,
      "learning_rate": 7.5707582211710265e-06,
      "loss": 2.2013,
      "mean_token_accuracy": 0.969101183116436,
      "num_tokens": 377729221.0,
      "step": 3280
    },
    {
      "epoch": 0.726028908749862,
      "grad_norm": 48.75,
      "learning_rate": 7.555093397235553e-06,
      "loss": 2.2007,
      "mean_token_accuracy": 0.9683996975421906,
      "num_tokens": 378881369.0,
      "step": 3290
    },
    {
      "epoch": 0.7282356835484939,
      "grad_norm": 45.5,
      "learning_rate": 7.539394556007892e-06,
      "loss": 2.223,
      "mean_token_accuracy": 0.9706318378448486,
      "num_tokens": 380031674.0,
      "step": 3300
    },
    {
      "epoch": 0.7304424583471256,
      "grad_norm": 58.25,
      "learning_rate": 7.523661906494913e-06,
      "loss": 2.1031,
      "mean_token_accuracy": 0.9697265937924385,
      "num_tokens": 381203145.0,
      "step": 3310
    },
    {
      "epoch": 0.7326492331457575,
      "grad_norm": 24.625,
      "learning_rate": 7.507895658153594e-06,
      "loss": 2.2078,
      "mean_token_accuracy": 0.9686227768659592,
      "num_tokens": 382372687.0,
      "step": 3320
    },
    {
      "epoch": 0.7348560079443893,
      "grad_norm": 35.0,
      "learning_rate": 7.492096020888227e-06,
      "loss": 2.2918,
      "mean_token_accuracy": 0.9677627474069596,
      "num_tokens": 383536359.0,
      "step": 3330
    },
    {
      "epoch": 0.7370627827430211,
      "grad_norm": 31.625,
      "learning_rate": 7.476263205047629e-06,
      "loss": 2.2834,
      "mean_token_accuracy": 0.9691791132092475,
      "num_tokens": 384692264.0,
      "step": 3340
    },
    {
      "epoch": 0.7392695575416529,
      "grad_norm": 42.75,
      "learning_rate": 7.460397421422346e-06,
      "loss": 2.1553,
      "mean_token_accuracy": 0.9718567460775376,
      "num_tokens": 385854489.0,
      "step": 3350
    },
    {
      "epoch": 0.7414763323402846,
      "grad_norm": 32.75,
      "learning_rate": 7.444498881241835e-06,
      "loss": 2.057,
      "mean_token_accuracy": 0.9710417047142983,
      "num_tokens": 387020276.0,
      "step": 3360
    },
    {
      "epoch": 0.7436831071389165,
      "grad_norm": 45.0,
      "learning_rate": 7.428567796171662e-06,
      "loss": 2.0303,
      "mean_token_accuracy": 0.9736444726586342,
      "num_tokens": 388165843.0,
      "step": 3370
    },
    {
      "epoch": 0.7458898819375482,
      "grad_norm": 39.0,
      "learning_rate": 7.412604378310677e-06,
      "loss": 2.2021,
      "mean_token_accuracy": 0.9685842871665955,
      "num_tokens": 389329983.0,
      "step": 3380
    },
    {
      "epoch": 0.7480966567361801,
      "grad_norm": 36.0,
      "learning_rate": 7.3966088401881975e-06,
      "loss": 2.1184,
      "mean_token_accuracy": 0.9706351444125175,
      "num_tokens": 390480961.0,
      "step": 3390
    },
    {
      "epoch": 0.7503034315348118,
      "grad_norm": 47.75,
      "learning_rate": 7.380581394761169e-06,
      "loss": 2.1423,
      "mean_token_accuracy": 0.970880638062954,
      "num_tokens": 391648757.0,
      "step": 3400
    },
    {
      "epoch": 0.7525102063334437,
      "grad_norm": 34.25,
      "learning_rate": 7.364522255411342e-06,
      "loss": 2.186,
      "mean_token_accuracy": 0.9695756494998932,
      "num_tokens": 392812461.0,
      "step": 3410
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 31.875,
      "learning_rate": 7.348431635942421e-06,
      "loss": 2.1141,
      "mean_token_accuracy": 0.970392107963562,
      "num_tokens": 393984685.0,
      "step": 3420
    },
    {
      "epoch": 0.7569237559307073,
      "grad_norm": 27.0,
      "learning_rate": 7.3323097505772225e-06,
      "loss": 2.3518,
      "mean_token_accuracy": 0.968183945119381,
      "num_tokens": 395114801.0,
      "step": 3430
    },
    {
      "epoch": 0.7591305307293391,
      "grad_norm": 84.0,
      "learning_rate": 7.316156813954821e-06,
      "loss": 2.2499,
      "mean_token_accuracy": 0.9711868852376938,
      "num_tokens": 396258212.0,
      "step": 3440
    },
    {
      "epoch": 0.7613373055279709,
      "grad_norm": 31.375,
      "learning_rate": 7.299973041127695e-06,
      "loss": 2.3661,
      "mean_token_accuracy": 0.9679227098822594,
      "num_tokens": 397415678.0,
      "step": 3450
    },
    {
      "epoch": 0.7635440803266027,
      "grad_norm": 25.25,
      "learning_rate": 7.28375864755886e-06,
      "loss": 2.1926,
      "mean_token_accuracy": 0.9700787767767907,
      "num_tokens": 398569653.0,
      "step": 3460
    },
    {
      "epoch": 0.7657508551252344,
      "grad_norm": 30.5,
      "learning_rate": 7.267513849119001e-06,
      "loss": 2.2584,
      "mean_token_accuracy": 0.9703097060322762,
      "num_tokens": 399718564.0,
      "step": 3470
    },
    {
      "epoch": 0.7679576299238663,
      "grad_norm": 57.25,
      "learning_rate": 7.251238862083602e-06,
      "loss": 2.3861,
      "mean_token_accuracy": 0.9684068784117699,
      "num_tokens": 400873786.0,
      "step": 3480
    },
    {
      "epoch": 0.770164404722498,
      "grad_norm": 44.25,
      "learning_rate": 7.234933903130057e-06,
      "loss": 2.1549,
      "mean_token_accuracy": 0.9715155944228172,
      "num_tokens": 402027889.0,
      "step": 3490
    },
    {
      "epoch": 0.7723711795211299,
      "grad_norm": 59.25,
      "learning_rate": 7.218599189334799e-06,
      "loss": 2.2361,
      "mean_token_accuracy": 0.9680303514003754,
      "num_tokens": 403183692.0,
      "step": 3500
    },
    {
      "epoch": 0.7745779543197616,
      "grad_norm": 35.25,
      "learning_rate": 7.202234938170399e-06,
      "loss": 1.9599,
      "mean_token_accuracy": 0.9738339349627495,
      "num_tokens": 404332296.0,
      "step": 3510
    },
    {
      "epoch": 0.7767847291183935,
      "grad_norm": 62.0,
      "learning_rate": 7.185841367502675e-06,
      "loss": 2.2368,
      "mean_token_accuracy": 0.9698937430977821,
      "num_tokens": 405494063.0,
      "step": 3520
    },
    {
      "epoch": 0.7789915039170253,
      "grad_norm": 49.25,
      "learning_rate": 7.169418695587791e-06,
      "loss": 2.1939,
      "mean_token_accuracy": 0.9712285786867142,
      "num_tokens": 406624626.0,
      "step": 3530
    },
    {
      "epoch": 0.7811982787156571,
      "grad_norm": 61.0,
      "learning_rate": 7.152967141069351e-06,
      "loss": 2.2331,
      "mean_token_accuracy": 0.9684389129281044,
      "num_tokens": 407777186.0,
      "step": 3540
    },
    {
      "epoch": 0.7834050535142889,
      "grad_norm": 45.75,
      "learning_rate": 7.136486922975489e-06,
      "loss": 2.1869,
      "mean_token_accuracy": 0.9703427478671074,
      "num_tokens": 408930294.0,
      "step": 3550
    },
    {
      "epoch": 0.7856118283129206,
      "grad_norm": 39.0,
      "learning_rate": 7.1199782607159494e-06,
      "loss": 2.1512,
      "mean_token_accuracy": 0.9694010347127915,
      "num_tokens": 410069873.0,
      "step": 3560
    },
    {
      "epoch": 0.7878186031115525,
      "grad_norm": 35.25,
      "learning_rate": 7.1034413740791705e-06,
      "loss": 2.1389,
      "mean_token_accuracy": 0.9709518432617188,
      "num_tokens": 411241330.0,
      "step": 3570
    },
    {
      "epoch": 0.7900253779101842,
      "grad_norm": 32.0,
      "learning_rate": 7.086876483229359e-06,
      "loss": 2.2443,
      "mean_token_accuracy": 0.9706715017557144,
      "num_tokens": 412379922.0,
      "step": 3580
    },
    {
      "epoch": 0.7922321527088161,
      "grad_norm": 106.5,
      "learning_rate": 7.070283808703553e-06,
      "loss": 2.0442,
      "mean_token_accuracy": 0.9737736508250237,
      "num_tokens": 413513375.0,
      "step": 3590
    },
    {
      "epoch": 0.7944389275074478,
      "grad_norm": 36.25,
      "learning_rate": 7.05366357140869e-06,
      "loss": 2.0809,
      "mean_token_accuracy": 0.971409210562706,
      "num_tokens": 414647824.0,
      "step": 3600
    },
    {
      "epoch": 0.7966457023060797,
      "grad_norm": 47.25,
      "learning_rate": 7.0370159926186645e-06,
      "loss": 2.1795,
      "mean_token_accuracy": 0.9696406945586205,
      "num_tokens": 415793929.0,
      "step": 3610
    },
    {
      "epoch": 0.7988524771047114,
      "grad_norm": 64.0,
      "learning_rate": 7.020341293971383e-06,
      "loss": 2.2685,
      "mean_token_accuracy": 0.9679594472050667,
      "num_tokens": 416932978.0,
      "step": 3620
    },
    {
      "epoch": 0.8010592519033433,
      "grad_norm": 24.5,
      "learning_rate": 7.003639697465813e-06,
      "loss": 2.13,
      "mean_token_accuracy": 0.9732703790068626,
      "num_tokens": 418079331.0,
      "step": 3630
    },
    {
      "epoch": 0.8032660267019751,
      "grad_norm": 40.75,
      "learning_rate": 6.986911425459028e-06,
      "loss": 2.1354,
      "mean_token_accuracy": 0.9717668473720551,
      "num_tokens": 419238043.0,
      "step": 3640
    },
    {
      "epoch": 0.8054728015006068,
      "grad_norm": 36.75,
      "learning_rate": 6.970156700663244e-06,
      "loss": 2.3939,
      "mean_token_accuracy": 0.9658266544342041,
      "num_tokens": 420388302.0,
      "step": 3650
    },
    {
      "epoch": 0.8076795762992387,
      "grad_norm": 33.75,
      "learning_rate": 6.953375746142861e-06,
      "loss": 2.2143,
      "mean_token_accuracy": 0.9698402568697929,
      "num_tokens": 421540248.0,
      "step": 3660
    },
    {
      "epoch": 0.8098863510978704,
      "grad_norm": 29.125,
      "learning_rate": 6.936568785311484e-06,
      "loss": 2.4224,
      "mean_token_accuracy": 0.9658764123916626,
      "num_tokens": 422692464.0,
      "step": 3670
    },
    {
      "epoch": 0.8120931258965023,
      "grad_norm": 37.75,
      "learning_rate": 6.919736041928956e-06,
      "loss": 2.148,
      "mean_token_accuracy": 0.9716546013951302,
      "num_tokens": 423836708.0,
      "step": 3680
    },
    {
      "epoch": 0.814299900695134,
      "grad_norm": 81.0,
      "learning_rate": 6.902877740098377e-06,
      "loss": 2.1436,
      "mean_token_accuracy": 0.972576630115509,
      "num_tokens": 424974866.0,
      "step": 3690
    },
    {
      "epoch": 0.8165066754937659,
      "grad_norm": 58.75,
      "learning_rate": 6.885994104263122e-06,
      "loss": 2.3117,
      "mean_token_accuracy": 0.9651796117424964,
      "num_tokens": 426139483.0,
      "step": 3700
    },
    {
      "epoch": 0.8187134502923976,
      "grad_norm": 51.25,
      "learning_rate": 6.869085359203844e-06,
      "loss": 2.0199,
      "mean_token_accuracy": 0.9708087667822838,
      "num_tokens": 427285632.0,
      "step": 3710
    },
    {
      "epoch": 0.8209202250910295,
      "grad_norm": 36.25,
      "learning_rate": 6.852151730035497e-06,
      "loss": 2.1478,
      "mean_token_accuracy": 0.9697320938110352,
      "num_tokens": 428443780.0,
      "step": 3720
    },
    {
      "epoch": 0.8231269998896613,
      "grad_norm": 35.25,
      "learning_rate": 6.835193442204322e-06,
      "loss": 2.0671,
      "mean_token_accuracy": 0.9712067291140556,
      "num_tokens": 429598368.0,
      "step": 3730
    },
    {
      "epoch": 0.825333774688293,
      "grad_norm": 62.5,
      "learning_rate": 6.818210721484859e-06,
      "loss": 2.2025,
      "mean_token_accuracy": 0.9711135670542717,
      "num_tokens": 430730120.0,
      "step": 3740
    },
    {
      "epoch": 0.8275405494869249,
      "grad_norm": 34.5,
      "learning_rate": 6.801203793976933e-06,
      "loss": 2.1531,
      "mean_token_accuracy": 0.969491246342659,
      "num_tokens": 431876764.0,
      "step": 3750
    },
    {
      "epoch": 0.8297473242855566,
      "grad_norm": 38.0,
      "learning_rate": 6.784172886102649e-06,
      "loss": 2.2031,
      "mean_token_accuracy": 0.9689152419567109,
      "num_tokens": 433028529.0,
      "step": 3760
    },
    {
      "epoch": 0.8319540990841885,
      "grad_norm": 31.25,
      "learning_rate": 6.767118224603374e-06,
      "loss": 2.2791,
      "mean_token_accuracy": 0.9677178040146828,
      "num_tokens": 434182536.0,
      "step": 3770
    },
    {
      "epoch": 0.8341608738828202,
      "grad_norm": 36.25,
      "learning_rate": 6.750040036536718e-06,
      "loss": 2.0995,
      "mean_token_accuracy": 0.9715589880943298,
      "num_tokens": 435331431.0,
      "step": 3780
    },
    {
      "epoch": 0.8363676486814521,
      "grad_norm": 31.625,
      "learning_rate": 6.732938549273517e-06,
      "loss": 2.172,
      "mean_token_accuracy": 0.9717289835214615,
      "num_tokens": 436472717.0,
      "step": 3790
    },
    {
      "epoch": 0.8385744234800838,
      "grad_norm": 34.75,
      "learning_rate": 6.715813990494793e-06,
      "loss": 2.0393,
      "mean_token_accuracy": 0.9725094646215439,
      "num_tokens": 437624930.0,
      "step": 3800
    },
    {
      "epoch": 0.8407811982787157,
      "grad_norm": 39.25,
      "learning_rate": 6.698666588188738e-06,
      "loss": 2.1413,
      "mean_token_accuracy": 0.9715115517377854,
      "num_tokens": 438753341.0,
      "step": 3810
    },
    {
      "epoch": 0.8429879730773474,
      "grad_norm": 56.75,
      "learning_rate": 6.681496570647672e-06,
      "loss": 2.0705,
      "mean_token_accuracy": 0.971962621808052,
      "num_tokens": 439898241.0,
      "step": 3820
    },
    {
      "epoch": 0.8451947478759793,
      "grad_norm": 94.0,
      "learning_rate": 6.664304166465e-06,
      "loss": 2.2277,
      "mean_token_accuracy": 0.9713366910815239,
      "num_tokens": 441063233.0,
      "step": 3830
    },
    {
      "epoch": 0.8474015226746111,
      "grad_norm": 62.25,
      "learning_rate": 6.647089604532174e-06,
      "loss": 2.158,
      "mean_token_accuracy": 0.9703224316239357,
      "num_tokens": 442224063.0,
      "step": 3840
    },
    {
      "epoch": 0.8496082974732428,
      "grad_norm": 40.5,
      "learning_rate": 6.629853114035643e-06,
      "loss": 2.0658,
      "mean_token_accuracy": 0.9726517379283905,
      "num_tokens": 443373342.0,
      "step": 3850
    },
    {
      "epoch": 0.8518150722718747,
      "grad_norm": 47.5,
      "learning_rate": 6.612594924453801e-06,
      "loss": 2.1824,
      "mean_token_accuracy": 0.9697960764169693,
      "num_tokens": 444525326.0,
      "step": 3860
    },
    {
      "epoch": 0.8540218470705064,
      "grad_norm": 43.75,
      "learning_rate": 6.595315265553938e-06,
      "loss": 2.2072,
      "mean_token_accuracy": 0.9690119743347168,
      "num_tokens": 445680273.0,
      "step": 3870
    },
    {
      "epoch": 0.8562286218691383,
      "grad_norm": 70.5,
      "learning_rate": 6.578014367389173e-06,
      "loss": 2.1527,
      "mean_token_accuracy": 0.9700315907597542,
      "num_tokens": 446824826.0,
      "step": 3880
    },
    {
      "epoch": 0.85843539666777,
      "grad_norm": 55.25,
      "learning_rate": 6.5606924602953925e-06,
      "loss": 2.1316,
      "mean_token_accuracy": 0.9704404413700104,
      "num_tokens": 447982855.0,
      "step": 3890
    },
    {
      "epoch": 0.8606421714664019,
      "grad_norm": 109.0,
      "learning_rate": 6.543349774888188e-06,
      "loss": 2.1946,
      "mean_token_accuracy": 0.9705035299062729,
      "num_tokens": 449125897.0,
      "step": 3900
    },
    {
      "epoch": 0.8628489462650336,
      "grad_norm": 47.25,
      "learning_rate": 6.525986542059783e-06,
      "loss": 2.1488,
      "mean_token_accuracy": 0.9701983913779259,
      "num_tokens": 450261988.0,
      "step": 3910
    },
    {
      "epoch": 0.8650557210636655,
      "grad_norm": 41.0,
      "learning_rate": 6.508602992975963e-06,
      "loss": 2.1411,
      "mean_token_accuracy": 0.9700289443135262,
      "num_tokens": 451410402.0,
      "step": 3920
    },
    {
      "epoch": 0.8672624958622972,
      "grad_norm": 29.0,
      "learning_rate": 6.4911993590729885e-06,
      "loss": 2.2251,
      "mean_token_accuracy": 0.9700245752930641,
      "num_tokens": 452555348.0,
      "step": 3930
    },
    {
      "epoch": 0.869469270660929,
      "grad_norm": 62.75,
      "learning_rate": 6.473775872054522e-06,
      "loss": 2.3129,
      "mean_token_accuracy": 0.9669782489538192,
      "num_tokens": 453705084.0,
      "step": 3940
    },
    {
      "epoch": 0.8716760454595609,
      "grad_norm": 24.375,
      "learning_rate": 6.456332763888544e-06,
      "loss": 2.1233,
      "mean_token_accuracy": 0.9714548006653786,
      "num_tokens": 454860803.0,
      "step": 3950
    },
    {
      "epoch": 0.8738828202581926,
      "grad_norm": 27.5,
      "learning_rate": 6.438870266804258e-06,
      "loss": 2.0532,
      "mean_token_accuracy": 0.9719975471496582,
      "num_tokens": 456010882.0,
      "step": 3960
    },
    {
      "epoch": 0.8760895950568245,
      "grad_norm": 41.25,
      "learning_rate": 6.421388613289003e-06,
      "loss": 2.1424,
      "mean_token_accuracy": 0.9697850465774536,
      "num_tokens": 457172526.0,
      "step": 3970
    },
    {
      "epoch": 0.8782963698554562,
      "grad_norm": 52.25,
      "learning_rate": 6.403888036085155e-06,
      "loss": 2.1875,
      "mean_token_accuracy": 0.9693676277995109,
      "num_tokens": 458331301.0,
      "step": 3980
    },
    {
      "epoch": 0.8805031446540881,
      "grad_norm": 70.5,
      "learning_rate": 6.38636876818704e-06,
      "loss": 2.0496,
      "mean_token_accuracy": 0.9712049409747123,
      "num_tokens": 459478691.0,
      "step": 3990
    },
    {
      "epoch": 0.8827099194527198,
      "grad_norm": 40.75,
      "learning_rate": 6.368831042837813e-06,
      "loss": 1.9526,
      "mean_token_accuracy": 0.9714639782905579,
      "num_tokens": 460641537.0,
      "step": 4000
    },
    {
      "epoch": 0.8849166942513517,
      "grad_norm": 42.0,
      "learning_rate": 6.3512750935263664e-06,
      "loss": 2.3223,
      "mean_token_accuracy": 0.9700347036123276,
      "num_tokens": 461782096.0,
      "step": 4010
    },
    {
      "epoch": 0.8871234690499834,
      "grad_norm": 49.5,
      "learning_rate": 6.3337011539842195e-06,
      "loss": 2.219,
      "mean_token_accuracy": 0.9716098442673683,
      "num_tokens": 462937379.0,
      "step": 4020
    },
    {
      "epoch": 0.8893302438486153,
      "grad_norm": 81.0,
      "learning_rate": 6.316109458182402e-06,
      "loss": 2.0164,
      "mean_token_accuracy": 0.9738545373082161,
      "num_tokens": 464087113.0,
      "step": 4030
    },
    {
      "epoch": 0.8915370186472471,
      "grad_norm": 40.75,
      "learning_rate": 6.298500240328342e-06,
      "loss": 2.2067,
      "mean_token_accuracy": 0.9692172899842262,
      "num_tokens": 465247534.0,
      "step": 4040
    },
    {
      "epoch": 0.8937437934458788,
      "grad_norm": 63.25,
      "learning_rate": 6.2808737348627514e-06,
      "loss": 1.9944,
      "mean_token_accuracy": 0.9740445956587791,
      "num_tokens": 466410461.0,
      "step": 4050
    },
    {
      "epoch": 0.8959505682445107,
      "grad_norm": 79.5,
      "learning_rate": 6.263230176456497e-06,
      "loss": 2.2156,
      "mean_token_accuracy": 0.968986214697361,
      "num_tokens": 467567854.0,
      "step": 4060
    },
    {
      "epoch": 0.8981573430431424,
      "grad_norm": 33.25,
      "learning_rate": 6.245569800007484e-06,
      "loss": 2.1584,
      "mean_token_accuracy": 0.9694019123911858,
      "num_tokens": 468711819.0,
      "step": 4070
    },
    {
      "epoch": 0.9003641178417743,
      "grad_norm": 36.5,
      "learning_rate": 6.227892840637521e-06,
      "loss": 2.0792,
      "mean_token_accuracy": 0.9719090461730957,
      "num_tokens": 469870580.0,
      "step": 4080
    },
    {
      "epoch": 0.902570892640406,
      "grad_norm": 70.5,
      "learning_rate": 6.210199533689196e-06,
      "loss": 2.2069,
      "mean_token_accuracy": 0.9688645884394645,
      "num_tokens": 471035721.0,
      "step": 4090
    },
    {
      "epoch": 0.9047776674390379,
      "grad_norm": 29.0,
      "learning_rate": 6.192490114722741e-06,
      "loss": 2.0292,
      "mean_token_accuracy": 0.9723895654082299,
      "num_tokens": 472203289.0,
      "step": 4100
    },
    {
      "epoch": 0.9069844422376696,
      "grad_norm": 27.375,
      "learning_rate": 6.174764819512895e-06,
      "loss": 2.1306,
      "mean_token_accuracy": 0.9709984570741653,
      "num_tokens": 473356133.0,
      "step": 4110
    },
    {
      "epoch": 0.9091912170363015,
      "grad_norm": 50.75,
      "learning_rate": 6.157023884045766e-06,
      "loss": 2.2381,
      "mean_token_accuracy": 0.9695079743862152,
      "num_tokens": 474505797.0,
      "step": 4120
    },
    {
      "epoch": 0.9113979918349332,
      "grad_norm": 42.75,
      "learning_rate": 6.139267544515689e-06,
      "loss": 2.2993,
      "mean_token_accuracy": 0.9680793553590774,
      "num_tokens": 475655265.0,
      "step": 4130
    },
    {
      "epoch": 0.913604766633565,
      "grad_norm": 31.75,
      "learning_rate": 6.121496037322081e-06,
      "loss": 2.1528,
      "mean_token_accuracy": 0.9709464639425278,
      "num_tokens": 476812532.0,
      "step": 4140
    },
    {
      "epoch": 0.9158115414321969,
      "grad_norm": 61.75,
      "learning_rate": 6.103709599066293e-06,
      "loss": 2.2167,
      "mean_token_accuracy": 0.9696009382605553,
      "num_tokens": 477945245.0,
      "step": 4150
    },
    {
      "epoch": 0.9180183162308286,
      "grad_norm": 35.0,
      "learning_rate": 6.0859084665484645e-06,
      "loss": 2.0862,
      "mean_token_accuracy": 0.9713777989149094,
      "num_tokens": 479088823.0,
      "step": 4160
    },
    {
      "epoch": 0.9202250910294605,
      "grad_norm": 31.125,
      "learning_rate": 6.068092876764365e-06,
      "loss": 2.2009,
      "mean_token_accuracy": 0.9701585471630096,
      "num_tokens": 480259334.0,
      "step": 4170
    },
    {
      "epoch": 0.9224318658280922,
      "grad_norm": 27.25,
      "learning_rate": 6.050263066902239e-06,
      "loss": 2.0828,
      "mean_token_accuracy": 0.9715811550617218,
      "num_tokens": 481410657.0,
      "step": 4180
    },
    {
      "epoch": 0.9246386406267241,
      "grad_norm": 40.5,
      "learning_rate": 6.032419274339654e-06,
      "loss": 1.9798,
      "mean_token_accuracy": 0.9738684058189392,
      "num_tokens": 482565499.0,
      "step": 4190
    },
    {
      "epoch": 0.9268454154253558,
      "grad_norm": 32.0,
      "learning_rate": 6.014561736640334e-06,
      "loss": 2.2245,
      "mean_token_accuracy": 0.9722442194819451,
      "num_tokens": 483720896.0,
      "step": 4200
    },
    {
      "epoch": 0.9290521902239877,
      "grad_norm": 30.375,
      "learning_rate": 5.996690691551002e-06,
      "loss": 2.1283,
      "mean_token_accuracy": 0.9713008061051369,
      "num_tokens": 484876264.0,
      "step": 4210
    },
    {
      "epoch": 0.9312589650226194,
      "grad_norm": 34.75,
      "learning_rate": 5.978806376998209e-06,
      "loss": 2.3606,
      "mean_token_accuracy": 0.9672145918011665,
      "num_tokens": 486043467.0,
      "step": 4220
    },
    {
      "epoch": 0.9334657398212513,
      "grad_norm": 37.75,
      "learning_rate": 5.960909031085173e-06,
      "loss": 2.0585,
      "mean_token_accuracy": 0.9726249516010285,
      "num_tokens": 487199636.0,
      "step": 4230
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 59.5,
      "learning_rate": 5.942998892088598e-06,
      "loss": 2.1389,
      "mean_token_accuracy": 0.9708730757236481,
      "num_tokens": 488358973.0,
      "step": 4240
    },
    {
      "epoch": 0.9378792894185148,
      "grad_norm": 30.5,
      "learning_rate": 5.925076198455517e-06,
      "loss": 2.076,
      "mean_token_accuracy": 0.9727498173713685,
      "num_tokens": 489491808.0,
      "step": 4250
    },
    {
      "epoch": 0.9400860642171467,
      "grad_norm": 29.375,
      "learning_rate": 5.907141188800106e-06,
      "loss": 1.95,
      "mean_token_accuracy": 0.9738984912633896,
      "num_tokens": 490644658.0,
      "step": 4260
    },
    {
      "epoch": 0.9422928390157784,
      "grad_norm": 63.5,
      "learning_rate": 5.8891941019005095e-06,
      "loss": 2.3177,
      "mean_token_accuracy": 0.9676681727170944,
      "num_tokens": 491805320.0,
      "step": 4270
    },
    {
      "epoch": 0.9444996138144103,
      "grad_norm": 30.625,
      "learning_rate": 5.871235176695664e-06,
      "loss": 2.2267,
      "mean_token_accuracy": 0.9693229615688324,
      "num_tokens": 492957724.0,
      "step": 4280
    },
    {
      "epoch": 0.946706388613042,
      "grad_norm": 28.75,
      "learning_rate": 5.853264652282118e-06,
      "loss": 2.2029,
      "mean_token_accuracy": 0.9682526499032974,
      "num_tokens": 494123799.0,
      "step": 4290
    },
    {
      "epoch": 0.9489131634116739,
      "grad_norm": 42.25,
      "learning_rate": 5.835282767910841e-06,
      "loss": 2.2085,
      "mean_token_accuracy": 0.970974650979042,
      "num_tokens": 495270311.0,
      "step": 4300
    },
    {
      "epoch": 0.9511199382103056,
      "grad_norm": 35.25,
      "learning_rate": 5.817289762984048e-06,
      "loss": 1.952,
      "mean_token_accuracy": 0.9728008791804313,
      "num_tokens": 496407368.0,
      "step": 4310
    },
    {
      "epoch": 0.9533267130089375,
      "grad_norm": 74.5,
      "learning_rate": 5.799285877052007e-06,
      "loss": 2.0579,
      "mean_token_accuracy": 0.970618762075901,
      "num_tokens": 497557772.0,
      "step": 4320
    },
    {
      "epoch": 0.9555334878075692,
      "grad_norm": 68.0,
      "learning_rate": 5.781271349809845e-06,
      "loss": 2.2085,
      "mean_token_accuracy": 0.9685943841934204,
      "num_tokens": 498693143.0,
      "step": 4330
    },
    {
      "epoch": 0.957740262606201,
      "grad_norm": 41.5,
      "learning_rate": 5.763246421094373e-06,
      "loss": 2.0453,
      "mean_token_accuracy": 0.9726010173559189,
      "num_tokens": 499840246.0,
      "step": 4340
    },
    {
      "epoch": 0.9599470374048328,
      "grad_norm": 36.0,
      "learning_rate": 5.745211330880872e-06,
      "loss": 2.2036,
      "mean_token_accuracy": 0.9725089892745018,
      "num_tokens": 500979381.0,
      "step": 4350
    },
    {
      "epoch": 0.9621538122034646,
      "grad_norm": 87.5,
      "learning_rate": 5.727166319279915e-06,
      "loss": 2.0543,
      "mean_token_accuracy": 0.970716480910778,
      "num_tokens": 502139137.0,
      "step": 4360
    },
    {
      "epoch": 0.9643605870020965,
      "grad_norm": 30.5,
      "learning_rate": 5.709111626534161e-06,
      "loss": 2.135,
      "mean_token_accuracy": 0.971952211856842,
      "num_tokens": 503279592.0,
      "step": 4370
    },
    {
      "epoch": 0.9665673618007282,
      "grad_norm": 25.25,
      "learning_rate": 5.691047493015157e-06,
      "loss": 2.0225,
      "mean_token_accuracy": 0.9722469002008438,
      "num_tokens": 504430413.0,
      "step": 4380
    },
    {
      "epoch": 0.9687741365993601,
      "grad_norm": 41.25,
      "learning_rate": 5.672974159220145e-06,
      "loss": 2.2397,
      "mean_token_accuracy": 0.9713874563574791,
      "num_tokens": 505570863.0,
      "step": 4390
    },
    {
      "epoch": 0.9709809113979918,
      "grad_norm": 38.0,
      "learning_rate": 5.65489186576885e-06,
      "loss": 2.1319,
      "mean_token_accuracy": 0.9702115073800087,
      "num_tokens": 506719123.0,
      "step": 4400
    },
    {
      "epoch": 0.9731876861966237,
      "grad_norm": 33.25,
      "learning_rate": 5.636800853400285e-06,
      "loss": 2.1298,
      "mean_token_accuracy": 0.9736479625105858,
      "num_tokens": 507867011.0,
      "step": 4410
    },
    {
      "epoch": 0.9753944609952554,
      "grad_norm": 43.5,
      "learning_rate": 5.618701362969541e-06,
      "loss": 2.1295,
      "mean_token_accuracy": 0.9713974446058273,
      "num_tokens": 509021659.0,
      "step": 4420
    },
    {
      "epoch": 0.9776012357938872,
      "grad_norm": 42.25,
      "learning_rate": 5.600593635444583e-06,
      "loss": 2.2219,
      "mean_token_accuracy": 0.9694741204380989,
      "num_tokens": 510182725.0,
      "step": 4430
    },
    {
      "epoch": 0.979808010592519,
      "grad_norm": 56.25,
      "learning_rate": 5.582477911903039e-06,
      "loss": 2.248,
      "mean_token_accuracy": 0.9681018337607383,
      "num_tokens": 511344854.0,
      "step": 4440
    },
    {
      "epoch": 0.9820147853911508,
      "grad_norm": 105.0,
      "learning_rate": 5.564354433528993e-06,
      "loss": 2.1012,
      "mean_token_accuracy": 0.9712380051612854,
      "num_tokens": 512488195.0,
      "step": 4450
    },
    {
      "epoch": 0.9842215601897827,
      "grad_norm": 42.75,
      "learning_rate": 5.546223441609775e-06,
      "loss": 2.119,
      "mean_token_accuracy": 0.9722514092922211,
      "num_tokens": 513631766.0,
      "step": 4460
    },
    {
      "epoch": 0.9864283349884144,
      "grad_norm": 81.5,
      "learning_rate": 5.5280851775327435e-06,
      "loss": 2.1416,
      "mean_token_accuracy": 0.9721418365836143,
      "num_tokens": 514787130.0,
      "step": 4470
    },
    {
      "epoch": 0.9886351097870463,
      "grad_norm": 33.25,
      "learning_rate": 5.509939882782077e-06,
      "loss": 2.1681,
      "mean_token_accuracy": 0.9717108353972435,
      "num_tokens": 515935657.0,
      "step": 4480
    },
    {
      "epoch": 0.990841884585678,
      "grad_norm": 23.875,
      "learning_rate": 5.491787798935557e-06,
      "loss": 2.1738,
      "mean_token_accuracy": 0.9681940034031868,
      "num_tokens": 517085947.0,
      "step": 4490
    },
    {
      "epoch": 0.9930486593843099,
      "grad_norm": 52.0,
      "learning_rate": 5.47362916766135e-06,
      "loss": 2.1871,
      "mean_token_accuracy": 0.9699540555477142,
      "num_tokens": 518245804.0,
      "step": 4500
    },
    {
      "epoch": 0.9952554341829416,
      "grad_norm": 64.5,
      "learning_rate": 5.455464230714794e-06,
      "loss": 2.0545,
      "mean_token_accuracy": 0.9713645100593566,
      "num_tokens": 519392437.0,
      "step": 4510
    },
    {
      "epoch": 0.9974622089815735,
      "grad_norm": 30.5,
      "learning_rate": 5.437293229935178e-06,
      "loss": 2.3195,
      "mean_token_accuracy": 0.9689386203885079,
      "num_tokens": 520544705.0,
      "step": 4520
    },
    {
      "epoch": 0.9996689837802052,
      "grad_norm": 26.5,
      "learning_rate": 5.4191164072425185e-06,
      "loss": 2.0375,
      "mean_token_accuracy": 0.9715640798211098,
      "num_tokens": 521712409.0,
      "step": 4530
    },
    {
      "epoch": 1.0017654198389054,
      "grad_norm": 52.25,
      "learning_rate": 5.400934004634346e-06,
      "loss": 1.8719,
      "mean_token_accuracy": 0.972184303559755,
      "num_tokens": 522797977.0,
      "step": 4540
    },
    {
      "epoch": 1.0039721946375373,
      "grad_norm": 53.75,
      "learning_rate": 5.38274626418248e-06,
      "loss": 2.1563,
      "mean_token_accuracy": 0.971350584924221,
      "num_tokens": 523945363.0,
      "step": 4550
    },
    {
      "epoch": 1.0061789694361691,
      "grad_norm": 36.5,
      "learning_rate": 5.364553428029797e-06,
      "loss": 2.1597,
      "mean_token_accuracy": 0.9714147970080376,
      "num_tokens": 525107360.0,
      "step": 4560
    },
    {
      "epoch": 1.0083857442348008,
      "grad_norm": 40.25,
      "learning_rate": 5.346355738387028e-06,
      "loss": 2.0476,
      "mean_token_accuracy": 0.9728688940405845,
      "num_tokens": 526261535.0,
      "step": 4570
    },
    {
      "epoch": 1.0105925190334326,
      "grad_norm": 54.0,
      "learning_rate": 5.328153437529512e-06,
      "loss": 2.1399,
      "mean_token_accuracy": 0.9719408199191093,
      "num_tokens": 527418116.0,
      "step": 4580
    },
    {
      "epoch": 1.0127992938320645,
      "grad_norm": 28.25,
      "learning_rate": 5.309946767793982e-06,
      "loss": 2.0825,
      "mean_token_accuracy": 0.9701297760009766,
      "num_tokens": 528576439.0,
      "step": 4590
    },
    {
      "epoch": 1.0150060686306963,
      "grad_norm": 45.75,
      "learning_rate": 5.291735971575336e-06,
      "loss": 2.0035,
      "mean_token_accuracy": 0.9720251992344856,
      "num_tokens": 529730593.0,
      "step": 4600
    },
    {
      "epoch": 1.017212843429328,
      "grad_norm": 42.0,
      "learning_rate": 5.273521291323411e-06,
      "loss": 2.1425,
      "mean_token_accuracy": 0.9693983480334282,
      "num_tokens": 530908237.0,
      "step": 4610
    },
    {
      "epoch": 1.0194196182279598,
      "grad_norm": 45.25,
      "learning_rate": 5.255302969539753e-06,
      "loss": 2.056,
      "mean_token_accuracy": 0.9731623455882072,
      "num_tokens": 532068523.0,
      "step": 4620
    },
    {
      "epoch": 1.0216263930265916,
      "grad_norm": 56.5,
      "learning_rate": 5.237081248774391e-06,
      "loss": 2.1072,
      "mean_token_accuracy": 0.9716246962547302,
      "num_tokens": 533227407.0,
      "step": 4630
    },
    {
      "epoch": 1.0238331678252235,
      "grad_norm": 31.25,
      "learning_rate": 5.218856371622605e-06,
      "loss": 2.0965,
      "mean_token_accuracy": 0.9722180128097534,
      "num_tokens": 534363317.0,
      "step": 4640
    },
    {
      "epoch": 1.0260399426238553,
      "grad_norm": 30.75,
      "learning_rate": 5.200628580721698e-06,
      "loss": 2.1126,
      "mean_token_accuracy": 0.9732374116778374,
      "num_tokens": 535517138.0,
      "step": 4650
    },
    {
      "epoch": 1.028246717422487,
      "grad_norm": 68.0,
      "learning_rate": 5.182398118747766e-06,
      "loss": 2.1939,
      "mean_token_accuracy": 0.9687327653169632,
      "num_tokens": 536682266.0,
      "step": 4660
    },
    {
      "epoch": 1.0304534922211188,
      "grad_norm": 34.75,
      "learning_rate": 5.1641652284124645e-06,
      "loss": 2.0198,
      "mean_token_accuracy": 0.9732640951871872,
      "num_tokens": 537820737.0,
      "step": 4670
    },
    {
      "epoch": 1.0326602670197507,
      "grad_norm": 34.5,
      "learning_rate": 5.145930152459782e-06,
      "loss": 2.0822,
      "mean_token_accuracy": 0.971691156923771,
      "num_tokens": 538980001.0,
      "step": 4680
    },
    {
      "epoch": 1.0348670418183825,
      "grad_norm": 31.375,
      "learning_rate": 5.127693133662801e-06,
      "loss": 2.1578,
      "mean_token_accuracy": 0.9711513608694077,
      "num_tokens": 540130919.0,
      "step": 4690
    },
    {
      "epoch": 1.0370738166170141,
      "grad_norm": 35.75,
      "learning_rate": 5.109454414820475e-06,
      "loss": 2.0835,
      "mean_token_accuracy": 0.972567793726921,
      "num_tokens": 541284787.0,
      "step": 4700
    },
    {
      "epoch": 1.039280591415646,
      "grad_norm": 63.0,
      "learning_rate": 5.091214238754387e-06,
      "loss": 2.0297,
      "mean_token_accuracy": 0.9728048413991928,
      "num_tokens": 542430717.0,
      "step": 4710
    },
    {
      "epoch": 1.0414873662142778,
      "grad_norm": 36.0,
      "learning_rate": 5.072972848305525e-06,
      "loss": 1.9277,
      "mean_token_accuracy": 0.9755252420902252,
      "num_tokens": 543571400.0,
      "step": 4720
    },
    {
      "epoch": 1.0436941410129097,
      "grad_norm": 59.25,
      "learning_rate": 5.054730486331041e-06,
      "loss": 1.9244,
      "mean_token_accuracy": 0.9727811023592949,
      "num_tokens": 544715376.0,
      "step": 4730
    },
    {
      "epoch": 1.0459009158115413,
      "grad_norm": 43.5,
      "learning_rate": 5.036487395701021e-06,
      "loss": 1.7429,
      "mean_token_accuracy": 0.9747304782271385,
      "num_tokens": 545866473.0,
      "step": 4740
    },
    {
      "epoch": 1.0481076906101732,
      "grad_norm": 35.5,
      "learning_rate": 5.018243819295256e-06,
      "loss": 2.164,
      "mean_token_accuracy": 0.9709397032856941,
      "num_tokens": 547031516.0,
      "step": 4750
    },
    {
      "epoch": 1.050314465408805,
      "grad_norm": 80.5,
      "learning_rate": 5e-06,
      "loss": 2.0213,
      "mean_token_accuracy": 0.9745332911610604,
      "num_tokens": 548191961.0,
      "step": 4760
    },
    {
      "epoch": 1.0525212402074369,
      "grad_norm": 114.0,
      "learning_rate": 4.981756180704746e-06,
      "loss": 2.0589,
      "mean_token_accuracy": 0.9719554871320725,
      "num_tokens": 549338774.0,
      "step": 4770
    },
    {
      "epoch": 1.0547280150060687,
      "grad_norm": 30.5,
      "learning_rate": 4.963512604298981e-06,
      "loss": 2.0589,
      "mean_token_accuracy": 0.9747210055589676,
      "num_tokens": 550495643.0,
      "step": 4780
    },
    {
      "epoch": 1.0569347898047003,
      "grad_norm": 61.0,
      "learning_rate": 4.945269513668962e-06,
      "loss": 2.0405,
      "mean_token_accuracy": 0.9715715765953064,
      "num_tokens": 551650992.0,
      "step": 4790
    },
    {
      "epoch": 1.0591415646033322,
      "grad_norm": 42.0,
      "learning_rate": 4.927027151694478e-06,
      "loss": 2.0761,
      "mean_token_accuracy": 0.9712958037853241,
      "num_tokens": 552799818.0,
      "step": 4800
    },
    {
      "epoch": 1.061348339401964,
      "grad_norm": 34.75,
      "learning_rate": 4.908785761245615e-06,
      "loss": 2.0516,
      "mean_token_accuracy": 0.9724678829312324,
      "num_tokens": 553942218.0,
      "step": 4810
    },
    {
      "epoch": 1.063555114200596,
      "grad_norm": 32.5,
      "learning_rate": 4.890545585179527e-06,
      "loss": 1.972,
      "mean_token_accuracy": 0.9731212154030799,
      "num_tokens": 555081142.0,
      "step": 4820
    },
    {
      "epoch": 1.0657618889992277,
      "grad_norm": 43.25,
      "learning_rate": 4.8723068663372005e-06,
      "loss": 2.1507,
      "mean_token_accuracy": 0.9695998519659043,
      "num_tokens": 556226987.0,
      "step": 4830
    },
    {
      "epoch": 1.0679686637978594,
      "grad_norm": 33.0,
      "learning_rate": 4.85406984754022e-06,
      "loss": 2.1781,
      "mean_token_accuracy": 0.9709591627120971,
      "num_tokens": 557363409.0,
      "step": 4840
    },
    {
      "epoch": 1.0701754385964912,
      "grad_norm": 40.75,
      "learning_rate": 4.835834771587537e-06,
      "loss": 2.2027,
      "mean_token_accuracy": 0.9691419571638107,
      "num_tokens": 558519321.0,
      "step": 4850
    },
    {
      "epoch": 1.072382213395123,
      "grad_norm": 28.5,
      "learning_rate": 4.817601881252236e-06,
      "loss": 2.1923,
      "mean_token_accuracy": 0.9706800401210784,
      "num_tokens": 559673648.0,
      "step": 4860
    },
    {
      "epoch": 1.074588988193755,
      "grad_norm": 24.5,
      "learning_rate": 4.799371419278303e-06,
      "loss": 1.944,
      "mean_token_accuracy": 0.9728835090994835,
      "num_tokens": 560815025.0,
      "step": 4870
    },
    {
      "epoch": 1.0767957629923866,
      "grad_norm": 49.25,
      "learning_rate": 4.781143628377396e-06,
      "loss": 1.9834,
      "mean_token_accuracy": 0.971730187535286,
      "num_tokens": 561990920.0,
      "step": 4880
    },
    {
      "epoch": 1.0790025377910184,
      "grad_norm": 78.5,
      "learning_rate": 4.76291875122561e-06,
      "loss": 2.0251,
      "mean_token_accuracy": 0.9724144697189331,
      "num_tokens": 563152430.0,
      "step": 4890
    },
    {
      "epoch": 1.0812093125896503,
      "grad_norm": 51.0,
      "learning_rate": 4.744697030460248e-06,
      "loss": 2.1181,
      "mean_token_accuracy": 0.9720061182975769,
      "num_tokens": 564301290.0,
      "step": 4900
    },
    {
      "epoch": 1.083416087388282,
      "grad_norm": 32.25,
      "learning_rate": 4.72647870867659e-06,
      "loss": 1.9922,
      "mean_token_accuracy": 0.9753932848572731,
      "num_tokens": 565460149.0,
      "step": 4910
    },
    {
      "epoch": 1.0856228621869137,
      "grad_norm": 47.75,
      "learning_rate": 4.708264028424666e-06,
      "loss": 2.151,
      "mean_token_accuracy": 0.9674713924527168,
      "num_tokens": 566606830.0,
      "step": 4920
    },
    {
      "epoch": 1.0878296369855456,
      "grad_norm": 38.75,
      "learning_rate": 4.69005323220602e-06,
      "loss": 1.9615,
      "mean_token_accuracy": 0.9720168381929397,
      "num_tokens": 567741343.0,
      "step": 4930
    },
    {
      "epoch": 1.0900364117841774,
      "grad_norm": 42.75,
      "learning_rate": 4.671846562470489e-06,
      "loss": 2.1074,
      "mean_token_accuracy": 0.9713210538029671,
      "num_tokens": 568892447.0,
      "step": 4940
    },
    {
      "epoch": 1.0922431865828093,
      "grad_norm": 40.25,
      "learning_rate": 4.653644261612972e-06,
      "loss": 2.0117,
      "mean_token_accuracy": 0.9737262845039367,
      "num_tokens": 570030671.0,
      "step": 4950
    },
    {
      "epoch": 1.0944499613814411,
      "grad_norm": 61.75,
      "learning_rate": 4.635446571970203e-06,
      "loss": 2.0694,
      "mean_token_accuracy": 0.9716535240411759,
      "num_tokens": 571182670.0,
      "step": 4960
    },
    {
      "epoch": 1.0966567361800728,
      "grad_norm": 40.75,
      "learning_rate": 4.617253735817522e-06,
      "loss": 2.0265,
      "mean_token_accuracy": 0.9717065066099166,
      "num_tokens": 572344441.0,
      "step": 4970
    },
    {
      "epoch": 1.0988635109787046,
      "grad_norm": 35.75,
      "learning_rate": 4.599065995365655e-06,
      "loss": 2.0287,
      "mean_token_accuracy": 0.9709518000483512,
      "num_tokens": 573492414.0,
      "step": 4980
    },
    {
      "epoch": 1.1010702857773365,
      "grad_norm": 33.75,
      "learning_rate": 4.580883592757482e-06,
      "loss": 2.0548,
      "mean_token_accuracy": 0.9719038605690002,
      "num_tokens": 574642118.0,
      "step": 4990
    },
    {
      "epoch": 1.1032770605759683,
      "grad_norm": 38.75,
      "learning_rate": 4.562706770064824e-06,
      "loss": 2.0436,
      "mean_token_accuracy": 0.9706536591053009,
      "num_tokens": 575797031.0,
      "step": 5000
    },
    {
      "epoch": 1.1054838353746,
      "grad_norm": 122.5,
      "learning_rate": 4.544535769285207e-06,
      "loss": 2.0862,
      "mean_token_accuracy": 0.9695298299193382,
      "num_tokens": 576946511.0,
      "step": 5010
    },
    {
      "epoch": 1.1076906101732318,
      "grad_norm": 37.25,
      "learning_rate": 4.526370832338652e-06,
      "loss": 1.9459,
      "mean_token_accuracy": 0.9751071646809578,
      "num_tokens": 578078352.0,
      "step": 5020
    },
    {
      "epoch": 1.1098973849718636,
      "grad_norm": 73.0,
      "learning_rate": 4.508212201064446e-06,
      "loss": 1.922,
      "mean_token_accuracy": 0.9743077546358109,
      "num_tokens": 579230344.0,
      "step": 5030
    },
    {
      "epoch": 1.1121041597704955,
      "grad_norm": 41.5,
      "learning_rate": 4.490060117217925e-06,
      "loss": 2.1398,
      "mean_token_accuracy": 0.9705320090055466,
      "num_tokens": 580394388.0,
      "step": 5040
    },
    {
      "epoch": 1.114310934569127,
      "grad_norm": 41.75,
      "learning_rate": 4.471914822467259e-06,
      "loss": 2.091,
      "mean_token_accuracy": 0.9709875896573067,
      "num_tokens": 581536226.0,
      "step": 5050
    },
    {
      "epoch": 1.116517709367759,
      "grad_norm": 79.5,
      "learning_rate": 4.453776558390225e-06,
      "loss": 1.9748,
      "mean_token_accuracy": 0.9727663412690163,
      "num_tokens": 582677619.0,
      "step": 5060
    },
    {
      "epoch": 1.1187244841663908,
      "grad_norm": 72.5,
      "learning_rate": 4.435645566471007e-06,
      "loss": 2.102,
      "mean_token_accuracy": 0.9707919478416442,
      "num_tokens": 583830811.0,
      "step": 5070
    },
    {
      "epoch": 1.1209312589650227,
      "grad_norm": 42.0,
      "learning_rate": 4.4175220880969625e-06,
      "loss": 1.7694,
      "mean_token_accuracy": 0.9760160639882087,
      "num_tokens": 584976018.0,
      "step": 5080
    },
    {
      "epoch": 1.1231380337636545,
      "grad_norm": 35.75,
      "learning_rate": 4.3994063645554185e-06,
      "loss": 2.1976,
      "mean_token_accuracy": 0.9705511912703514,
      "num_tokens": 586130461.0,
      "step": 5090
    },
    {
      "epoch": 1.1253448085622861,
      "grad_norm": 35.25,
      "learning_rate": 4.381298637030461e-06,
      "loss": 2.1163,
      "mean_token_accuracy": 0.9701086178421974,
      "num_tokens": 587277506.0,
      "step": 5100
    },
    {
      "epoch": 1.127551583360918,
      "grad_norm": 29.375,
      "learning_rate": 4.363199146599717e-06,
      "loss": 2.079,
      "mean_token_accuracy": 0.9719017505645752,
      "num_tokens": 588429402.0,
      "step": 5110
    },
    {
      "epoch": 1.1297583581595498,
      "grad_norm": 81.0,
      "learning_rate": 4.345108134231152e-06,
      "loss": 2.0717,
      "mean_token_accuracy": 0.9706048741936684,
      "num_tokens": 589569193.0,
      "step": 5120
    },
    {
      "epoch": 1.1319651329581817,
      "grad_norm": 29.75,
      "learning_rate": 4.327025840779857e-06,
      "loss": 2.2428,
      "mean_token_accuracy": 0.9707401916384697,
      "num_tokens": 590726713.0,
      "step": 5130
    },
    {
      "epoch": 1.1341719077568135,
      "grad_norm": 43.25,
      "learning_rate": 4.308952506984844e-06,
      "loss": 1.9522,
      "mean_token_accuracy": 0.974059708416462,
      "num_tokens": 591872463.0,
      "step": 5140
    },
    {
      "epoch": 1.1363786825554452,
      "grad_norm": 36.75,
      "learning_rate": 4.290888373465841e-06,
      "loss": 2.0444,
      "mean_token_accuracy": 0.9726229995489121,
      "num_tokens": 593023782.0,
      "step": 5150
    },
    {
      "epoch": 1.138585457354077,
      "grad_norm": 28.375,
      "learning_rate": 4.272833680720086e-06,
      "loss": 2.0646,
      "mean_token_accuracy": 0.9724480271339416,
      "num_tokens": 594182249.0,
      "step": 5160
    },
    {
      "epoch": 1.1407922321527089,
      "grad_norm": 39.75,
      "learning_rate": 4.254788669119127e-06,
      "loss": 2.045,
      "mean_token_accuracy": 0.9713110208511353,
      "num_tokens": 595332632.0,
      "step": 5170
    },
    {
      "epoch": 1.1429990069513407,
      "grad_norm": 28.25,
      "learning_rate": 4.236753578905627e-06,
      "loss": 2.12,
      "mean_token_accuracy": 0.9702134445309639,
      "num_tokens": 596478168.0,
      "step": 5180
    },
    {
      "epoch": 1.1452057817499723,
      "grad_norm": 51.0,
      "learning_rate": 4.218728650190155e-06,
      "loss": 1.9835,
      "mean_token_accuracy": 0.9724645748734474,
      "num_tokens": 597634860.0,
      "step": 5190
    },
    {
      "epoch": 1.1474125565486042,
      "grad_norm": 36.25,
      "learning_rate": 4.2007141229479955e-06,
      "loss": 2.1067,
      "mean_token_accuracy": 0.9707230404019356,
      "num_tokens": 598796015.0,
      "step": 5200
    },
    {
      "epoch": 1.149619331347236,
      "grad_norm": 34.25,
      "learning_rate": 4.1827102370159526e-06,
      "loss": 2.2641,
      "mean_token_accuracy": 0.9715961620211602,
      "num_tokens": 599944690.0,
      "step": 5210
    },
    {
      "epoch": 1.151826106145868,
      "grad_norm": 69.0,
      "learning_rate": 4.1647172320891595e-06,
      "loss": 2.1937,
      "mean_token_accuracy": 0.9670615553855896,
      "num_tokens": 601095606.0,
      "step": 5220
    },
    {
      "epoch": 1.1540328809444995,
      "grad_norm": 116.0,
      "learning_rate": 4.146735347717883e-06,
      "loss": 2.0541,
      "mean_token_accuracy": 0.9697577267885208,
      "num_tokens": 602242421.0,
      "step": 5230
    },
    {
      "epoch": 1.1562396557431314,
      "grad_norm": 31.875,
      "learning_rate": 4.1287648233043366e-06,
      "loss": 2.1375,
      "mean_token_accuracy": 0.9709837049245834,
      "num_tokens": 603393922.0,
      "step": 5240
    },
    {
      "epoch": 1.1584464305417632,
      "grad_norm": 88.5,
      "learning_rate": 4.110805898099492e-06,
      "loss": 1.9658,
      "mean_token_accuracy": 0.9729313775897026,
      "num_tokens": 604558266.0,
      "step": 5250
    },
    {
      "epoch": 1.160653205340395,
      "grad_norm": 64.5,
      "learning_rate": 4.092858811199896e-06,
      "loss": 2.0256,
      "mean_token_accuracy": 0.9735493749380112,
      "num_tokens": 605699821.0,
      "step": 5260
    },
    {
      "epoch": 1.162859980139027,
      "grad_norm": 27.75,
      "learning_rate": 4.074923801544485e-06,
      "loss": 1.9753,
      "mean_token_accuracy": 0.9725518003106117,
      "num_tokens": 606861912.0,
      "step": 5270
    },
    {
      "epoch": 1.1650667549376585,
      "grad_norm": 31.125,
      "learning_rate": 4.057001107911404e-06,
      "loss": 2.0867,
      "mean_token_accuracy": 0.9718861475586891,
      "num_tokens": 608015619.0,
      "step": 5280
    },
    {
      "epoch": 1.1672735297362904,
      "grad_norm": 48.75,
      "learning_rate": 4.039090968914828e-06,
      "loss": 2.2446,
      "mean_token_accuracy": 0.9679182320833206,
      "num_tokens": 609178030.0,
      "step": 5290
    },
    {
      "epoch": 1.1694803045349222,
      "grad_norm": 41.75,
      "learning_rate": 4.0211936230017915e-06,
      "loss": 1.9893,
      "mean_token_accuracy": 0.9721043214201928,
      "num_tokens": 610335548.0,
      "step": 5300
    },
    {
      "epoch": 1.171687079333554,
      "grad_norm": 43.75,
      "learning_rate": 4.003309308448998e-06,
      "loss": 2.0029,
      "mean_token_accuracy": 0.9716233789920807,
      "num_tokens": 611464518.0,
      "step": 5310
    },
    {
      "epoch": 1.1738938541321857,
      "grad_norm": 39.5,
      "learning_rate": 3.985438263359667e-06,
      "loss": 1.9832,
      "mean_token_accuracy": 0.9729538008570671,
      "num_tokens": 612605369.0,
      "step": 5320
    },
    {
      "epoch": 1.1761006289308176,
      "grad_norm": 62.5,
      "learning_rate": 3.967580725660348e-06,
      "loss": 2.1598,
      "mean_token_accuracy": 0.9705301880836487,
      "num_tokens": 613769083.0,
      "step": 5330
    },
    {
      "epoch": 1.1783074037294494,
      "grad_norm": 59.5,
      "learning_rate": 3.949736933097763e-06,
      "loss": 2.2221,
      "mean_token_accuracy": 0.9688659504055976,
      "num_tokens": 614910229.0,
      "step": 5340
    },
    {
      "epoch": 1.1805141785280813,
      "grad_norm": 42.75,
      "learning_rate": 3.931907123235638e-06,
      "loss": 1.9903,
      "mean_token_accuracy": 0.972883440554142,
      "num_tokens": 616068687.0,
      "step": 5350
    },
    {
      "epoch": 1.182720953326713,
      "grad_norm": 74.0,
      "learning_rate": 3.914091533451537e-06,
      "loss": 2.0762,
      "mean_token_accuracy": 0.9719195187091827,
      "num_tokens": 617211438.0,
      "step": 5360
    },
    {
      "epoch": 1.1849277281253447,
      "grad_norm": 28.625,
      "learning_rate": 3.896290400933709e-06,
      "loss": 2.0534,
      "mean_token_accuracy": 0.9724638417363167,
      "num_tokens": 618348189.0,
      "step": 5370
    },
    {
      "epoch": 1.1871345029239766,
      "grad_norm": 38.75,
      "learning_rate": 3.878503962677921e-06,
      "loss": 1.9708,
      "mean_token_accuracy": 0.9740056306123733,
      "num_tokens": 619513774.0,
      "step": 5380
    },
    {
      "epoch": 1.1893412777226084,
      "grad_norm": 37.0,
      "learning_rate": 3.860732455484314e-06,
      "loss": 2.0544,
      "mean_token_accuracy": 0.9718249082565308,
      "num_tokens": 620658294.0,
      "step": 5390
    },
    {
      "epoch": 1.1915480525212403,
      "grad_norm": 41.0,
      "learning_rate": 3.8429761159542345e-06,
      "loss": 1.9866,
      "mean_token_accuracy": 0.9722783520817757,
      "num_tokens": 621822786.0,
      "step": 5400
    },
    {
      "epoch": 1.193754827319872,
      "grad_norm": 46.5,
      "learning_rate": 3.825235180487105e-06,
      "loss": 2.0521,
      "mean_token_accuracy": 0.9718651354312897,
      "num_tokens": 622968221.0,
      "step": 5410
    },
    {
      "epoch": 1.1959616021185038,
      "grad_norm": 38.0,
      "learning_rate": 3.8075098852772607e-06,
      "loss": 1.9163,
      "mean_token_accuracy": 0.9721212074160576,
      "num_tokens": 624116917.0,
      "step": 5420
    },
    {
      "epoch": 1.1981683769171356,
      "grad_norm": 57.25,
      "learning_rate": 3.7898004663108055e-06,
      "loss": 2.0902,
      "mean_token_accuracy": 0.97244141548872,
      "num_tokens": 625275805.0,
      "step": 5430
    },
    {
      "epoch": 1.2003751517157675,
      "grad_norm": 31.0,
      "learning_rate": 3.7721071593624806e-06,
      "loss": 2.0692,
      "mean_token_accuracy": 0.9735848516225815,
      "num_tokens": 626412494.0,
      "step": 5440
    },
    {
      "epoch": 1.2025819265143993,
      "grad_norm": 45.5,
      "learning_rate": 3.7544301999925176e-06,
      "loss": 1.9953,
      "mean_token_accuracy": 0.9725841730833054,
      "num_tokens": 627581796.0,
      "step": 5450
    },
    {
      "epoch": 1.204788701313031,
      "grad_norm": 30.625,
      "learning_rate": 3.7367698235435036e-06,
      "loss": 2.0643,
      "mean_token_accuracy": 0.9706020817160607,
      "num_tokens": 628749061.0,
      "step": 5460
    },
    {
      "epoch": 1.2069954761116628,
      "grad_norm": 47.0,
      "learning_rate": 3.7191262651372502e-06,
      "loss": 1.9379,
      "mean_token_accuracy": 0.9748807206749917,
      "num_tokens": 629902166.0,
      "step": 5470
    },
    {
      "epoch": 1.2092022509102947,
      "grad_norm": 46.5,
      "learning_rate": 3.7014997596716596e-06,
      "loss": 2.0212,
      "mean_token_accuracy": 0.9725807011127472,
      "num_tokens": 631045876.0,
      "step": 5480
    },
    {
      "epoch": 1.2114090257089263,
      "grad_norm": 43.25,
      "learning_rate": 3.6838905418176006e-06,
      "loss": 2.0844,
      "mean_token_accuracy": 0.9709960043430328,
      "num_tokens": 632198013.0,
      "step": 5490
    },
    {
      "epoch": 1.2136158005075581,
      "grad_norm": 78.5,
      "learning_rate": 3.666298846015783e-06,
      "loss": 1.9147,
      "mean_token_accuracy": 0.9720228418707848,
      "num_tokens": 633348344.0,
      "step": 5500
    },
    {
      "epoch": 1.21582257530619,
      "grad_norm": 35.25,
      "learning_rate": 3.6487249064736352e-06,
      "loss": 2.0788,
      "mean_token_accuracy": 0.9700503304600716,
      "num_tokens": 634502768.0,
      "step": 5510
    },
    {
      "epoch": 1.2180293501048218,
      "grad_norm": 38.5,
      "learning_rate": 3.6311689571621873e-06,
      "loss": 2.2196,
      "mean_token_accuracy": 0.9718668460845947,
      "num_tokens": 635652274.0,
      "step": 5520
    },
    {
      "epoch": 1.2202361249034537,
      "grad_norm": 71.5,
      "learning_rate": 3.61363123181296e-06,
      "loss": 2.1669,
      "mean_token_accuracy": 0.9698523536324501,
      "num_tokens": 636803608.0,
      "step": 5530
    },
    {
      "epoch": 1.2224428997020853,
      "grad_norm": 27.875,
      "learning_rate": 3.5961119639148443e-06,
      "loss": 2.1297,
      "mean_token_accuracy": 0.9709449097514152,
      "num_tokens": 637958795.0,
      "step": 5540
    },
    {
      "epoch": 1.2246496745007172,
      "grad_norm": 32.5,
      "learning_rate": 3.5786113867109994e-06,
      "loss": 2.0674,
      "mean_token_accuracy": 0.9748511016368866,
      "num_tokens": 639105490.0,
      "step": 5550
    },
    {
      "epoch": 1.226856449299349,
      "grad_norm": 71.5,
      "learning_rate": 3.561129733195744e-06,
      "loss": 2.1327,
      "mean_token_accuracy": 0.9690723076462746,
      "num_tokens": 640260157.0,
      "step": 5560
    },
    {
      "epoch": 1.2290632240979809,
      "grad_norm": 36.5,
      "learning_rate": 3.543667236111458e-06,
      "loss": 2.0633,
      "mean_token_accuracy": 0.9720786109566688,
      "num_tokens": 641408567.0,
      "step": 5570
    },
    {
      "epoch": 1.2312699988966127,
      "grad_norm": 38.75,
      "learning_rate": 3.526224127945479e-06,
      "loss": 2.0891,
      "mean_token_accuracy": 0.97109884172678,
      "num_tokens": 642573013.0,
      "step": 5580
    },
    {
      "epoch": 1.2334767736952443,
      "grad_norm": 54.5,
      "learning_rate": 3.5088006409270136e-06,
      "loss": 2.1669,
      "mean_token_accuracy": 0.9713895127177239,
      "num_tokens": 643726591.0,
      "step": 5590
    },
    {
      "epoch": 1.2356835484938762,
      "grad_norm": 47.25,
      "learning_rate": 3.4913970070240388e-06,
      "loss": 1.9585,
      "mean_token_accuracy": 0.9738426744937897,
      "num_tokens": 644892695.0,
      "step": 5600
    },
    {
      "epoch": 1.237890323292508,
      "grad_norm": 49.75,
      "learning_rate": 3.474013457940218e-06,
      "loss": 2.0243,
      "mean_token_accuracy": 0.970925672352314,
      "num_tokens": 646053963.0,
      "step": 5610
    },
    {
      "epoch": 1.2400970980911399,
      "grad_norm": 32.75,
      "learning_rate": 3.456650225111815e-06,
      "loss": 2.2216,
      "mean_token_accuracy": 0.9686313286423683,
      "num_tokens": 647206734.0,
      "step": 5620
    },
    {
      "epoch": 1.2423038728897715,
      "grad_norm": 39.0,
      "learning_rate": 3.4393075397046105e-06,
      "loss": 2.2147,
      "mean_token_accuracy": 0.9688821420073509,
      "num_tokens": 648354326.0,
      "step": 5630
    },
    {
      "epoch": 1.2445106476884034,
      "grad_norm": 48.75,
      "learning_rate": 3.4219856326108276e-06,
      "loss": 1.9989,
      "mean_token_accuracy": 0.9716936990618705,
      "num_tokens": 649495009.0,
      "step": 5640
    },
    {
      "epoch": 1.2467174224870352,
      "grad_norm": 64.5,
      "learning_rate": 3.4046847344460608e-06,
      "loss": 2.1613,
      "mean_token_accuracy": 0.9714754074811935,
      "num_tokens": 650641836.0,
      "step": 5650
    },
    {
      "epoch": 1.248924197285667,
      "grad_norm": 42.25,
      "learning_rate": 3.3874050755461984e-06,
      "loss": 2.1036,
      "mean_token_accuracy": 0.971159029006958,
      "num_tokens": 651790330.0,
      "step": 5660
    },
    {
      "epoch": 1.2511309720842987,
      "grad_norm": 28.625,
      "learning_rate": 3.3701468859643583e-06,
      "loss": 2.0812,
      "mean_token_accuracy": 0.9718174040317535,
      "num_tokens": 652951960.0,
      "step": 5670
    },
    {
      "epoch": 1.2533377468829305,
      "grad_norm": 32.5,
      "learning_rate": 3.352910395467827e-06,
      "loss": 1.9353,
      "mean_token_accuracy": 0.9726988717913627,
      "num_tokens": 654101888.0,
      "step": 5680
    },
    {
      "epoch": 1.2555445216815624,
      "grad_norm": 26.25,
      "learning_rate": 3.335695833535001e-06,
      "loss": 2.0634,
      "mean_token_accuracy": 0.9709341689944267,
      "num_tokens": 655273030.0,
      "step": 5690
    },
    {
      "epoch": 1.2577512964801942,
      "grad_norm": 43.75,
      "learning_rate": 3.31850342935233e-06,
      "loss": 2.1445,
      "mean_token_accuracy": 0.9714302137494087,
      "num_tokens": 656415802.0,
      "step": 5700
    },
    {
      "epoch": 1.259958071278826,
      "grad_norm": 32.25,
      "learning_rate": 3.301333411811264e-06,
      "loss": 2.1556,
      "mean_token_accuracy": 0.970471453666687,
      "num_tokens": 657566900.0,
      "step": 5710
    },
    {
      "epoch": 1.2621648460774577,
      "grad_norm": 45.25,
      "learning_rate": 3.2841860095052096e-06,
      "loss": 1.9311,
      "mean_token_accuracy": 0.9735459670424461,
      "num_tokens": 658729945.0,
      "step": 5720
    },
    {
      "epoch": 1.2643716208760896,
      "grad_norm": 34.75,
      "learning_rate": 3.2670614507264863e-06,
      "loss": 2.0729,
      "mean_token_accuracy": 0.9702731445431709,
      "num_tokens": 659871577.0,
      "step": 5730
    },
    {
      "epoch": 1.2665783956747214,
      "grad_norm": 56.25,
      "learning_rate": 3.249959963463283e-06,
      "loss": 1.9025,
      "mean_token_accuracy": 0.9752660349011422,
      "num_tokens": 661036888.0,
      "step": 5740
    },
    {
      "epoch": 1.2687851704733533,
      "grad_norm": 48.5,
      "learning_rate": 3.232881775396626e-06,
      "loss": 2.0132,
      "mean_token_accuracy": 0.971823462843895,
      "num_tokens": 662190333.0,
      "step": 5750
    },
    {
      "epoch": 1.2709919452719851,
      "grad_norm": 50.75,
      "learning_rate": 3.215827113897351e-06,
      "loss": 2.0621,
      "mean_token_accuracy": 0.9716164857149124,
      "num_tokens": 663339112.0,
      "step": 5760
    },
    {
      "epoch": 1.2731987200706167,
      "grad_norm": 47.25,
      "learning_rate": 3.1987962060230674e-06,
      "loss": 1.9797,
      "mean_token_accuracy": 0.9743097245693206,
      "num_tokens": 664486373.0,
      "step": 5770
    },
    {
      "epoch": 1.2754054948692486,
      "grad_norm": 46.5,
      "learning_rate": 3.1817892785151426e-06,
      "loss": 2.1234,
      "mean_token_accuracy": 0.9717991754412652,
      "num_tokens": 665618395.0,
      "step": 5780
    },
    {
      "epoch": 1.2776122696678804,
      "grad_norm": 30.0,
      "learning_rate": 3.164806557795679e-06,
      "loss": 2.1144,
      "mean_token_accuracy": 0.9715682148933411,
      "num_tokens": 666752016.0,
      "step": 5790
    },
    {
      "epoch": 1.279819044466512,
      "grad_norm": 29.125,
      "learning_rate": 3.1478482699645052e-06,
      "loss": 1.983,
      "mean_token_accuracy": 0.972720344364643,
      "num_tokens": 667906714.0,
      "step": 5800
    },
    {
      "epoch": 1.282025819265144,
      "grad_norm": 37.25,
      "learning_rate": 3.1309146407961565e-06,
      "loss": 2.0577,
      "mean_token_accuracy": 0.9726598918437958,
      "num_tokens": 669062941.0,
      "step": 5810
    },
    {
      "epoch": 1.2842325940637758,
      "grad_norm": 57.5,
      "learning_rate": 3.11400589573688e-06,
      "loss": 1.8659,
      "mean_token_accuracy": 0.9751516312360764,
      "num_tokens": 670205902.0,
      "step": 5820
    },
    {
      "epoch": 1.2864393688624076,
      "grad_norm": 31.5,
      "learning_rate": 3.0971222599016237e-06,
      "loss": 1.9692,
      "mean_token_accuracy": 0.9735979035496711,
      "num_tokens": 671363091.0,
      "step": 5830
    },
    {
      "epoch": 1.2886461436610395,
      "grad_norm": 46.0,
      "learning_rate": 3.0802639580710465e-06,
      "loss": 2.0629,
      "mean_token_accuracy": 0.9703319683670998,
      "num_tokens": 672499228.0,
      "step": 5840
    },
    {
      "epoch": 1.290852918459671,
      "grad_norm": 28.75,
      "learning_rate": 3.0634312146885193e-06,
      "loss": 2.2553,
      "mean_token_accuracy": 0.9700239449739456,
      "num_tokens": 673659411.0,
      "step": 5850
    },
    {
      "epoch": 1.293059693258303,
      "grad_norm": 48.25,
      "learning_rate": 3.0466242538571423e-06,
      "loss": 1.9339,
      "mean_token_accuracy": 0.9731740996241569,
      "num_tokens": 674822650.0,
      "step": 5860
    },
    {
      "epoch": 1.2952664680569348,
      "grad_norm": 37.0,
      "learning_rate": 3.0298432993367577e-06,
      "loss": 1.8052,
      "mean_token_accuracy": 0.975373849272728,
      "num_tokens": 675984971.0,
      "step": 5870
    },
    {
      "epoch": 1.2974732428555666,
      "grad_norm": 34.5,
      "learning_rate": 3.0130885745409744e-06,
      "loss": 2.0833,
      "mean_token_accuracy": 0.9721586912870407,
      "num_tokens": 677148669.0,
      "step": 5880
    },
    {
      "epoch": 1.2996800176541985,
      "grad_norm": 33.75,
      "learning_rate": 2.9963603025341894e-06,
      "loss": 2.0466,
      "mean_token_accuracy": 0.971629399061203,
      "num_tokens": 678304909.0,
      "step": 5890
    },
    {
      "epoch": 1.3018867924528301,
      "grad_norm": 27.125,
      "learning_rate": 2.979658706028619e-06,
      "loss": 1.9999,
      "mean_token_accuracy": 0.9727662190794945,
      "num_tokens": 679456014.0,
      "step": 5900
    },
    {
      "epoch": 1.304093567251462,
      "grad_norm": 57.75,
      "learning_rate": 2.9629840073813376e-06,
      "loss": 2.0285,
      "mean_token_accuracy": 0.9715612307190895,
      "num_tokens": 680593369.0,
      "step": 5910
    },
    {
      "epoch": 1.3063003420500938,
      "grad_norm": 45.5,
      "learning_rate": 2.9463364285913117e-06,
      "loss": 2.0501,
      "mean_token_accuracy": 0.9701596021652221,
      "num_tokens": 681741941.0,
      "step": 5920
    },
    {
      "epoch": 1.3085071168487254,
      "grad_norm": 42.0,
      "learning_rate": 2.9297161912964476e-06,
      "loss": 2.0812,
      "mean_token_accuracy": 0.9711472198367119,
      "num_tokens": 682896982.0,
      "step": 5930
    },
    {
      "epoch": 1.3107138916473575,
      "grad_norm": 36.0,
      "learning_rate": 2.913123516770642e-06,
      "loss": 2.1695,
      "mean_token_accuracy": 0.9718584313988685,
      "num_tokens": 684035727.0,
      "step": 5940
    },
    {
      "epoch": 1.3129206664459891,
      "grad_norm": 40.0,
      "learning_rate": 2.8965586259208295e-06,
      "loss": 1.9976,
      "mean_token_accuracy": 0.9730417460203171,
      "num_tokens": 685182208.0,
      "step": 5950
    },
    {
      "epoch": 1.315127441244621,
      "grad_norm": 39.5,
      "learning_rate": 2.880021739284053e-06,
      "loss": 2.0794,
      "mean_token_accuracy": 0.9723026305437088,
      "num_tokens": 686343119.0,
      "step": 5960
    },
    {
      "epoch": 1.3173342160432528,
      "grad_norm": 72.0,
      "learning_rate": 2.8635130770245124e-06,
      "loss": 2.0568,
      "mean_token_accuracy": 0.9721500769257545,
      "num_tokens": 687496119.0,
      "step": 5970
    },
    {
      "epoch": 1.3195409908418845,
      "grad_norm": 32.25,
      "learning_rate": 2.8470328589306508e-06,
      "loss": 1.9782,
      "mean_token_accuracy": 0.9719040229916572,
      "num_tokens": 688642777.0,
      "step": 5980
    },
    {
      "epoch": 1.3217477656405163,
      "grad_norm": 48.25,
      "learning_rate": 2.83058130441221e-06,
      "loss": 2.0636,
      "mean_token_accuracy": 0.9710184082388877,
      "num_tokens": 689793698.0,
      "step": 5990
    },
    {
      "epoch": 1.3239545404391482,
      "grad_norm": 56.75,
      "learning_rate": 2.8141586324973248e-06,
      "loss": 2.1058,
      "mean_token_accuracy": 0.9711653172969819,
      "num_tokens": 690949839.0,
      "step": 6000
    },
    {
      "epoch": 1.32616131523778,
      "grad_norm": 32.5,
      "learning_rate": 2.7977650618296026e-06,
      "loss": 1.9183,
      "mean_token_accuracy": 0.9732666924595833,
      "num_tokens": 692115106.0,
      "step": 6010
    },
    {
      "epoch": 1.3283680900364119,
      "grad_norm": 40.75,
      "learning_rate": 2.781400810665201e-06,
      "loss": 2.1809,
      "mean_token_accuracy": 0.9706536576151847,
      "num_tokens": 693262382.0,
      "step": 6020
    },
    {
      "epoch": 1.3305748648350435,
      "grad_norm": 31.25,
      "learning_rate": 2.765066096869945e-06,
      "loss": 2.0059,
      "mean_token_accuracy": 0.9730835050344467,
      "num_tokens": 694440462.0,
      "step": 6030
    },
    {
      "epoch": 1.3327816396336754,
      "grad_norm": 102.5,
      "learning_rate": 2.7487611379163997e-06,
      "loss": 2.2233,
      "mean_token_accuracy": 0.9687234997749329,
      "num_tokens": 695596599.0,
      "step": 6040
    },
    {
      "epoch": 1.3349884144323072,
      "grad_norm": 78.5,
      "learning_rate": 2.7324861508810007e-06,
      "loss": 2.0559,
      "mean_token_accuracy": 0.9726975917816162,
      "num_tokens": 696742749.0,
      "step": 6050
    },
    {
      "epoch": 1.337195189230939,
      "grad_norm": 29.875,
      "learning_rate": 2.716241352441141e-06,
      "loss": 2.0659,
      "mean_token_accuracy": 0.9707060709595681,
      "num_tokens": 697910420.0,
      "step": 6060
    },
    {
      "epoch": 1.339401964029571,
      "grad_norm": 39.5,
      "learning_rate": 2.7000269588723073e-06,
      "loss": 1.8232,
      "mean_token_accuracy": 0.9742976903915406,
      "num_tokens": 699056083.0,
      "step": 6070
    },
    {
      "epoch": 1.3416087388282025,
      "grad_norm": 45.75,
      "learning_rate": 2.6838431860451797e-06,
      "loss": 1.9095,
      "mean_token_accuracy": 0.9712084516882896,
      "num_tokens": 700215731.0,
      "step": 6080
    },
    {
      "epoch": 1.3438155136268344,
      "grad_norm": 49.25,
      "learning_rate": 2.6676902494227795e-06,
      "loss": 2.252,
      "mean_token_accuracy": 0.9673631563782692,
      "num_tokens": 701356240.0,
      "step": 6090
    },
    {
      "epoch": 1.3460222884254662,
      "grad_norm": 37.0,
      "learning_rate": 2.65156836405758e-06,
      "loss": 1.9963,
      "mean_token_accuracy": 0.9736059322953224,
      "num_tokens": 702524355.0,
      "step": 6100
    },
    {
      "epoch": 1.3482290632240979,
      "grad_norm": 52.5,
      "learning_rate": 2.635477744588658e-06,
      "loss": 1.9752,
      "mean_token_accuracy": 0.9736613526940345,
      "num_tokens": 703660966.0,
      "step": 6110
    },
    {
      "epoch": 1.3504358380227297,
      "grad_norm": 34.5,
      "learning_rate": 2.6194186052388323e-06,
      "loss": 2.0196,
      "mean_token_accuracy": 0.9730469718575477,
      "num_tokens": 704814830.0,
      "step": 6120
    },
    {
      "epoch": 1.3526426128213616,
      "grad_norm": 49.25,
      "learning_rate": 2.6033911598118037e-06,
      "loss": 2.1366,
      "mean_token_accuracy": 0.9713971391320229,
      "num_tokens": 705962264.0,
      "step": 6130
    },
    {
      "epoch": 1.3548493876199934,
      "grad_norm": 51.5,
      "learning_rate": 2.587395621689325e-06,
      "loss": 1.9355,
      "mean_token_accuracy": 0.9762338832020759,
      "num_tokens": 707111319.0,
      "step": 6140
    },
    {
      "epoch": 1.3570561624186253,
      "grad_norm": 36.75,
      "learning_rate": 2.571432203828339e-06,
      "loss": 2.023,
      "mean_token_accuracy": 0.9733693838119507,
      "num_tokens": 708259268.0,
      "step": 6150
    },
    {
      "epoch": 1.3592629372172569,
      "grad_norm": 79.0,
      "learning_rate": 2.555501118758167e-06,
      "loss": 2.2807,
      "mean_token_accuracy": 0.9684775248169899,
      "num_tokens": 709384260.0,
      "step": 6160
    },
    {
      "epoch": 1.3614697120158887,
      "grad_norm": 64.0,
      "learning_rate": 2.5396025785776545e-06,
      "loss": 2.0319,
      "mean_token_accuracy": 0.9731385380029678,
      "num_tokens": 710543299.0,
      "step": 6170
    },
    {
      "epoch": 1.3636764868145206,
      "grad_norm": 67.0,
      "learning_rate": 2.523736794952373e-06,
      "loss": 2.2599,
      "mean_token_accuracy": 0.9703476592898369,
      "num_tokens": 711693117.0,
      "step": 6180
    },
    {
      "epoch": 1.3658832616131524,
      "grad_norm": 46.25,
      "learning_rate": 2.5079039791117748e-06,
      "loss": 2.0309,
      "mean_token_accuracy": 0.9706747367978096,
      "num_tokens": 712829801.0,
      "step": 6190
    },
    {
      "epoch": 1.3680900364117843,
      "grad_norm": 50.25,
      "learning_rate": 2.4921043418464085e-06,
      "loss": 2.1617,
      "mean_token_accuracy": 0.9705612942576408,
      "num_tokens": 713974429.0,
      "step": 6200
    },
    {
      "epoch": 1.370296811210416,
      "grad_norm": 30.125,
      "learning_rate": 2.4763380935050878e-06,
      "loss": 2.0898,
      "mean_token_accuracy": 0.9711591824889183,
      "num_tokens": 715107968.0,
      "step": 6210
    },
    {
      "epoch": 1.3725035860090478,
      "grad_norm": 35.0,
      "learning_rate": 2.460605443992109e-06,
      "loss": 2.0719,
      "mean_token_accuracy": 0.9731900662183761,
      "num_tokens": 716262488.0,
      "step": 6220
    },
    {
      "epoch": 1.3747103608076796,
      "grad_norm": 56.0,
      "learning_rate": 2.4449066027644473e-06,
      "loss": 2.0054,
      "mean_token_accuracy": 0.9747842282056809,
      "num_tokens": 717399703.0,
      "step": 6230
    },
    {
      "epoch": 1.3769171356063112,
      "grad_norm": 77.5,
      "learning_rate": 2.4292417788289735e-06,
      "loss": 2.1907,
      "mean_token_accuracy": 0.970676988363266,
      "num_tokens": 718558165.0,
      "step": 6240
    },
    {
      "epoch": 1.3791239104049433,
      "grad_norm": 84.0,
      "learning_rate": 2.4136111807396617e-06,
      "loss": 2.083,
      "mean_token_accuracy": 0.9717174306511879,
      "num_tokens": 719712112.0,
      "step": 6250
    },
    {
      "epoch": 1.381330685203575,
      "grad_norm": 62.5,
      "learning_rate": 2.398015016594828e-06,
      "loss": 1.9984,
      "mean_token_accuracy": 0.9724332094192505,
      "num_tokens": 720860531.0,
      "step": 6260
    },
    {
      "epoch": 1.3835374600022068,
      "grad_norm": 66.0,
      "learning_rate": 2.382453494034344e-06,
      "loss": 1.9424,
      "mean_token_accuracy": 0.9725833252072335,
      "num_tokens": 722012739.0,
      "step": 6270
    },
    {
      "epoch": 1.3857442348008386,
      "grad_norm": 34.25,
      "learning_rate": 2.366926820236882e-06,
      "loss": 2.1019,
      "mean_token_accuracy": 0.9718847304582596,
      "num_tokens": 723177458.0,
      "step": 6280
    },
    {
      "epoch": 1.3879510095994703,
      "grad_norm": 53.75,
      "learning_rate": 2.351435201917159e-06,
      "loss": 2.0167,
      "mean_token_accuracy": 0.9735344961285591,
      "num_tokens": 724326268.0,
      "step": 6290
    },
    {
      "epoch": 1.3901577843981021,
      "grad_norm": 39.0,
      "learning_rate": 2.3359788453231723e-06,
      "loss": 1.9003,
      "mean_token_accuracy": 0.9740667581558228,
      "num_tokens": 725486233.0,
      "step": 6300
    },
    {
      "epoch": 1.392364559196734,
      "grad_norm": 48.75,
      "learning_rate": 2.3205579562334696e-06,
      "loss": 2.0713,
      "mean_token_accuracy": 0.9720068842172622,
      "num_tokens": 726653829.0,
      "step": 6310
    },
    {
      "epoch": 1.3945713339953658,
      "grad_norm": 40.5,
      "learning_rate": 2.3051727399543934e-06,
      "loss": 2.0832,
      "mean_token_accuracy": 0.972083905339241,
      "num_tokens": 727794399.0,
      "step": 6320
    },
    {
      "epoch": 1.3967781087939977,
      "grad_norm": 73.0,
      "learning_rate": 2.289823401317363e-06,
      "loss": 2.1738,
      "mean_token_accuracy": 0.9695032462477684,
      "num_tokens": 728964825.0,
      "step": 6330
    },
    {
      "epoch": 1.3989848835926293,
      "grad_norm": 40.0,
      "learning_rate": 2.274510144676131e-06,
      "loss": 2.0707,
      "mean_token_accuracy": 0.9730754122138023,
      "num_tokens": 730130565.0,
      "step": 6340
    },
    {
      "epoch": 1.4011916583912611,
      "grad_norm": 31.625,
      "learning_rate": 2.259233173904084e-06,
      "loss": 2.0504,
      "mean_token_accuracy": 0.9708613395690918,
      "num_tokens": 731287831.0,
      "step": 6350
    },
    {
      "epoch": 1.403398433189893,
      "grad_norm": 63.0,
      "learning_rate": 2.2439926923915022e-06,
      "loss": 2.121,
      "mean_token_accuracy": 0.9723618626594543,
      "num_tokens": 732434828.0,
      "step": 6360
    },
    {
      "epoch": 1.4056052079885248,
      "grad_norm": 36.0,
      "learning_rate": 2.228788903042877e-06,
      "loss": 2.0245,
      "mean_token_accuracy": 0.9727164760231972,
      "num_tokens": 733607627.0,
      "step": 6370
    },
    {
      "epoch": 1.4078119827871567,
      "grad_norm": 51.0,
      "learning_rate": 2.2136220082741876e-06,
      "loss": 2.2004,
      "mean_token_accuracy": 0.9686874210834503,
      "num_tokens": 734757141.0,
      "step": 6380
    },
    {
      "epoch": 1.4100187575857883,
      "grad_norm": 38.75,
      "learning_rate": 2.198492210010226e-06,
      "loss": 2.0869,
      "mean_token_accuracy": 0.9721286237239838,
      "num_tokens": 735904820.0,
      "step": 6390
    },
    {
      "epoch": 1.4122255323844202,
      "grad_norm": 52.25,
      "learning_rate": 2.1833997096818897e-06,
      "loss": 2.1087,
      "mean_token_accuracy": 0.9717398911714554,
      "num_tokens": 737044631.0,
      "step": 6400
    },
    {
      "epoch": 1.414432307183052,
      "grad_norm": 97.0,
      "learning_rate": 2.168344708223519e-06,
      "loss": 2.0527,
      "mean_token_accuracy": 0.973566535115242,
      "num_tokens": 738208645.0,
      "step": 6410
    },
    {
      "epoch": 1.4166390819816836,
      "grad_norm": 65.0,
      "learning_rate": 2.1533274060702015e-06,
      "loss": 2.0756,
      "mean_token_accuracy": 0.9710081234574318,
      "num_tokens": 739365910.0,
      "step": 6420
    },
    {
      "epoch": 1.4188458567803155,
      "grad_norm": 47.5,
      "learning_rate": 2.1383480031551257e-06,
      "loss": 1.945,
      "mean_token_accuracy": 0.9735840231180191,
      "num_tokens": 740521431.0,
      "step": 6430
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 30.625,
      "learning_rate": 2.1234066989068972e-06,
      "loss": 2.1109,
      "mean_token_accuracy": 0.9721017107367516,
      "num_tokens": 741682181.0,
      "step": 6440
    },
    {
      "epoch": 1.4232594063775792,
      "grad_norm": 40.0,
      "learning_rate": 2.1085036922469017e-06,
      "loss": 1.9956,
      "mean_token_accuracy": 0.9740138977766037,
      "num_tokens": 742833342.0,
      "step": 6450
    },
    {
      "epoch": 1.425466181176211,
      "grad_norm": 103.0,
      "learning_rate": 2.093639181586647e-06,
      "loss": 1.8386,
      "mean_token_accuracy": 0.9750812038779259,
      "num_tokens": 743980679.0,
      "step": 6460
    },
    {
      "epoch": 1.4276729559748427,
      "grad_norm": 51.75,
      "learning_rate": 2.0788133648251207e-06,
      "loss": 2.0585,
      "mean_token_accuracy": 0.9712428838014603,
      "num_tokens": 745144275.0,
      "step": 6470
    },
    {
      "epoch": 1.4298797307734745,
      "grad_norm": 56.75,
      "learning_rate": 2.064026439346163e-06,
      "loss": 1.9104,
      "mean_token_accuracy": 0.9742664054036141,
      "num_tokens": 746284459.0,
      "step": 6480
    },
    {
      "epoch": 1.4320865055721064,
      "grad_norm": 44.5,
      "learning_rate": 2.049278602015829e-06,
      "loss": 2.0128,
      "mean_token_accuracy": 0.9726312100887299,
      "num_tokens": 747434490.0,
      "step": 6490
    },
    {
      "epoch": 1.4342932803707382,
      "grad_norm": 57.0,
      "learning_rate": 2.0345700491797786e-06,
      "loss": 2.0051,
      "mean_token_accuracy": 0.9731343209743499,
      "num_tokens": 748576563.0,
      "step": 6500
    },
    {
      "epoch": 1.43650005516937,
      "grad_norm": 29.125,
      "learning_rate": 2.019900976660651e-06,
      "loss": 2.1034,
      "mean_token_accuracy": 0.9715386927127838,
      "num_tokens": 749715849.0,
      "step": 6510
    },
    {
      "epoch": 1.4387068299680017,
      "grad_norm": 58.0,
      "learning_rate": 2.005271579755469e-06,
      "loss": 2.308,
      "mean_token_accuracy": 0.9675611928105354,
      "num_tokens": 750886184.0,
      "step": 6520
    },
    {
      "epoch": 1.4409136047666335,
      "grad_norm": 72.5,
      "learning_rate": 1.9906820532330262e-06,
      "loss": 2.2962,
      "mean_token_accuracy": 0.9679251447319984,
      "num_tokens": 752058746.0,
      "step": 6530
    },
    {
      "epoch": 1.4431203795652654,
      "grad_norm": 30.625,
      "learning_rate": 1.97613259133131e-06,
      "loss": 2.2414,
      "mean_token_accuracy": 0.9688615322113037,
      "num_tokens": 753212790.0,
      "step": 6540
    },
    {
      "epoch": 1.445327154363897,
      "grad_norm": 31.0,
      "learning_rate": 1.961623387754897e-06,
      "loss": 2.0215,
      "mean_token_accuracy": 0.973488450050354,
      "num_tokens": 754359329.0,
      "step": 6550
    },
    {
      "epoch": 1.447533929162529,
      "grad_norm": 58.25,
      "learning_rate": 1.947154635672393e-06,
      "loss": 2.0635,
      "mean_token_accuracy": 0.9706815198063851,
      "num_tokens": 755523206.0,
      "step": 6560
    },
    {
      "epoch": 1.4497407039611607,
      "grad_norm": 48.5,
      "learning_rate": 1.932726527713843e-06,
      "loss": 2.0059,
      "mean_token_accuracy": 0.9729144275188446,
      "num_tokens": 756672031.0,
      "step": 6570
    },
    {
      "epoch": 1.4519474787597926,
      "grad_norm": 40.0,
      "learning_rate": 1.9183392559681812e-06,
      "loss": 2.098,
      "mean_token_accuracy": 0.9698581099510193,
      "num_tokens": 757820723.0,
      "step": 6580
    },
    {
      "epoch": 1.4541542535584244,
      "grad_norm": 43.5,
      "learning_rate": 1.9039930119806698e-06,
      "loss": 2.0952,
      "mean_token_accuracy": 0.9696508347988129,
      "num_tokens": 758975440.0,
      "step": 6590
    },
    {
      "epoch": 1.456361028357056,
      "grad_norm": 35.25,
      "learning_rate": 1.8896879867503392e-06,
      "loss": 1.9366,
      "mean_token_accuracy": 0.9748910591006279,
      "num_tokens": 760146513.0,
      "step": 6600
    },
    {
      "epoch": 1.458567803155688,
      "grad_norm": 43.25,
      "learning_rate": 1.8754243707274617e-06,
      "loss": 2.1238,
      "mean_token_accuracy": 0.9706553891301155,
      "num_tokens": 761304174.0,
      "step": 6610
    },
    {
      "epoch": 1.4607745779543198,
      "grad_norm": 66.0,
      "learning_rate": 1.8612023538109998e-06,
      "loss": 2.1235,
      "mean_token_accuracy": 0.9708872303366661,
      "num_tokens": 762439915.0,
      "step": 6620
    },
    {
      "epoch": 1.4629813527529516,
      "grad_norm": 45.25,
      "learning_rate": 1.847022125346092e-06,
      "loss": 1.9493,
      "mean_token_accuracy": 0.9736669182777404,
      "num_tokens": 763597054.0,
      "step": 6630
    },
    {
      "epoch": 1.4651881275515835,
      "grad_norm": 38.75,
      "learning_rate": 1.8328838741215187e-06,
      "loss": 2.0516,
      "mean_token_accuracy": 0.9728484004735947,
      "num_tokens": 764750468.0,
      "step": 6640
    },
    {
      "epoch": 1.467394902350215,
      "grad_norm": 32.25,
      "learning_rate": 1.8187877883672024e-06,
      "loss": 2.0216,
      "mean_token_accuracy": 0.9743900761008263,
      "num_tokens": 765904561.0,
      "step": 6650
    },
    {
      "epoch": 1.469601677148847,
      "grad_norm": 53.75,
      "learning_rate": 1.8047340557516867e-06,
      "loss": 2.0232,
      "mean_token_accuracy": 0.9735488444566727,
      "num_tokens": 767061972.0,
      "step": 6660
    },
    {
      "epoch": 1.4718084519474788,
      "grad_norm": 33.0,
      "learning_rate": 1.7907228633796553e-06,
      "loss": 2.1222,
      "mean_token_accuracy": 0.969277748465538,
      "num_tokens": 768223438.0,
      "step": 6670
    },
    {
      "epoch": 1.4740152267461106,
      "grad_norm": 33.5,
      "learning_rate": 1.7767543977894198e-06,
      "loss": 1.9451,
      "mean_token_accuracy": 0.9740255236625671,
      "num_tokens": 769360598.0,
      "step": 6680
    },
    {
      "epoch": 1.4762220015447425,
      "grad_norm": 39.5,
      "learning_rate": 1.7628288449504615e-06,
      "loss": 2.0575,
      "mean_token_accuracy": 0.9710416316986084,
      "num_tokens": 770506647.0,
      "step": 6690
    },
    {
      "epoch": 1.478428776343374,
      "grad_norm": 46.5,
      "learning_rate": 1.7489463902609294e-06,
      "loss": 2.0406,
      "mean_token_accuracy": 0.9717944994568825,
      "num_tokens": 771643701.0,
      "step": 6700
    },
    {
      "epoch": 1.480635551142006,
      "grad_norm": 64.5,
      "learning_rate": 1.7351072185451934e-06,
      "loss": 2.0093,
      "mean_token_accuracy": 0.9712977677583694,
      "num_tokens": 772788494.0,
      "step": 6710
    },
    {
      "epoch": 1.4828423259406378,
      "grad_norm": 46.0,
      "learning_rate": 1.7213115140513687e-06,
      "loss": 2.0926,
      "mean_token_accuracy": 0.9719087481498718,
      "num_tokens": 773936585.0,
      "step": 6720
    },
    {
      "epoch": 1.4850491007392694,
      "grad_norm": 86.5,
      "learning_rate": 1.7075594604488689e-06,
      "loss": 2.0476,
      "mean_token_accuracy": 0.9723167300224305,
      "num_tokens": 775083782.0,
      "step": 6730
    },
    {
      "epoch": 1.4872558755379013,
      "grad_norm": 39.0,
      "learning_rate": 1.6938512408259655e-06,
      "loss": 2.1373,
      "mean_token_accuracy": 0.9698946535587311,
      "num_tokens": 776235006.0,
      "step": 6740
    },
    {
      "epoch": 1.4894626503365331,
      "grad_norm": 38.0,
      "learning_rate": 1.6801870376873402e-06,
      "loss": 2.3699,
      "mean_token_accuracy": 0.9687036126852036,
      "num_tokens": 777392437.0,
      "step": 6750
    },
    {
      "epoch": 1.491669425135165,
      "grad_norm": 34.5,
      "learning_rate": 1.6665670329516643e-06,
      "loss": 1.8606,
      "mean_token_accuracy": 0.9759853675961494,
      "num_tokens": 778544664.0,
      "step": 6760
    },
    {
      "epoch": 1.4938761999337968,
      "grad_norm": 75.5,
      "learning_rate": 1.652991407949167e-06,
      "loss": 2.1637,
      "mean_token_accuracy": 0.9710831940174103,
      "num_tokens": 779689432.0,
      "step": 6770
    },
    {
      "epoch": 1.4960829747324285,
      "grad_norm": 41.25,
      "learning_rate": 1.6394603434192351e-06,
      "loss": 2.0394,
      "mean_token_accuracy": 0.972575829923153,
      "num_tokens": 780862995.0,
      "step": 6780
    },
    {
      "epoch": 1.4982897495310603,
      "grad_norm": 61.5,
      "learning_rate": 1.6259740195079903e-06,
      "loss": 2.2586,
      "mean_token_accuracy": 0.9687326654791832,
      "num_tokens": 782006485.0,
      "step": 6790
    },
    {
      "epoch": 1.5004965243296922,
      "grad_norm": 35.25,
      "learning_rate": 1.6125326157659048e-06,
      "loss": 1.9084,
      "mean_token_accuracy": 0.9758684694766998,
      "num_tokens": 783177825.0,
      "step": 6800
    },
    {
      "epoch": 1.5027032991283238,
      "grad_norm": 28.875,
      "learning_rate": 1.5991363111454023e-06,
      "loss": 2.2111,
      "mean_token_accuracy": 0.9708895862102509,
      "num_tokens": 784326073.0,
      "step": 6810
    },
    {
      "epoch": 1.5049100739269559,
      "grad_norm": 43.0,
      "learning_rate": 1.5857852839984816e-06,
      "loss": 2.1056,
      "mean_token_accuracy": 0.9709335967898369,
      "num_tokens": 785480380.0,
      "step": 6820
    },
    {
      "epoch": 1.5071168487255875,
      "grad_norm": 35.5,
      "learning_rate": 1.572479712074333e-06,
      "loss": 1.9599,
      "mean_token_accuracy": 0.9729704424738884,
      "num_tokens": 786627917.0,
      "step": 6830
    },
    {
      "epoch": 1.5093236235242193,
      "grad_norm": 34.5,
      "learning_rate": 1.5592197725169844e-06,
      "loss": 2.0573,
      "mean_token_accuracy": 0.9718131139874459,
      "num_tokens": 787779534.0,
      "step": 6840
    },
    {
      "epoch": 1.5115303983228512,
      "grad_norm": 42.75,
      "learning_rate": 1.54600564186293e-06,
      "loss": 2.2108,
      "mean_token_accuracy": 0.97033331990242,
      "num_tokens": 788929621.0,
      "step": 6850
    },
    {
      "epoch": 1.5137371731214828,
      "grad_norm": 39.5,
      "learning_rate": 1.532837496038792e-06,
      "loss": 2.0957,
      "mean_token_accuracy": 0.972550243139267,
      "num_tokens": 790077509.0,
      "step": 6860
    },
    {
      "epoch": 1.5159439479201149,
      "grad_norm": 37.5,
      "learning_rate": 1.5197155103589666e-06,
      "loss": 2.0455,
      "mean_token_accuracy": 0.9723348423838616,
      "num_tokens": 791226601.0,
      "step": 6870
    },
    {
      "epoch": 1.5181507227187465,
      "grad_norm": 58.75,
      "learning_rate": 1.5066398595233022e-06,
      "loss": 2.2292,
      "mean_token_accuracy": 0.970213831961155,
      "num_tokens": 792386119.0,
      "step": 6880
    },
    {
      "epoch": 1.5203574975173784,
      "grad_norm": 34.75,
      "learning_rate": 1.4936107176147606e-06,
      "loss": 2.0307,
      "mean_token_accuracy": 0.9704331666231155,
      "num_tokens": 793533664.0,
      "step": 6890
    },
    {
      "epoch": 1.5225642723160102,
      "grad_norm": 33.75,
      "learning_rate": 1.4806282580971133e-06,
      "loss": 2.0927,
      "mean_token_accuracy": 0.970127372443676,
      "num_tokens": 794673077.0,
      "step": 6900
    },
    {
      "epoch": 1.5247710471146418,
      "grad_norm": 59.25,
      "learning_rate": 1.4676926538126185e-06,
      "loss": 2.1242,
      "mean_token_accuracy": 0.9691689878702163,
      "num_tokens": 795837119.0,
      "step": 6910
    },
    {
      "epoch": 1.526977821913274,
      "grad_norm": 34.0,
      "learning_rate": 1.4548040769797255e-06,
      "loss": 2.0189,
      "mean_token_accuracy": 0.9722217470407486,
      "num_tokens": 796994585.0,
      "step": 6920
    },
    {
      "epoch": 1.5291845967119055,
      "grad_norm": 34.0,
      "learning_rate": 1.4419626991907925e-06,
      "loss": 2.1584,
      "mean_token_accuracy": 0.9697286561131477,
      "num_tokens": 798129000.0,
      "step": 6930
    },
    {
      "epoch": 1.5313913715105374,
      "grad_norm": 30.75,
      "learning_rate": 1.4291686914097802e-06,
      "loss": 2.1451,
      "mean_token_accuracy": 0.9697655245661736,
      "num_tokens": 799286955.0,
      "step": 6940
    },
    {
      "epoch": 1.5335981463091692,
      "grad_norm": 52.5,
      "learning_rate": 1.416422223969996e-06,
      "loss": 2.0862,
      "mean_token_accuracy": 0.9736831590533257,
      "num_tokens": 800434799.0,
      "step": 6950
    },
    {
      "epoch": 1.5358049211078009,
      "grad_norm": 51.75,
      "learning_rate": 1.4037234665718118e-06,
      "loss": 2.1657,
      "mean_token_accuracy": 0.9691461607813835,
      "num_tokens": 801591336.0,
      "step": 6960
    },
    {
      "epoch": 1.5380116959064327,
      "grad_norm": 46.5,
      "learning_rate": 1.3910725882804166e-06,
      "loss": 2.1066,
      "mean_token_accuracy": 0.9721064269542694,
      "num_tokens": 802753222.0,
      "step": 6970
    },
    {
      "epoch": 1.5402184707050646,
      "grad_norm": 48.75,
      "learning_rate": 1.378469757523554e-06,
      "loss": 2.1357,
      "mean_token_accuracy": 0.9704466626048088,
      "num_tokens": 803902417.0,
      "step": 6980
    },
    {
      "epoch": 1.5424252455036962,
      "grad_norm": 81.0,
      "learning_rate": 1.3659151420892912e-06,
      "loss": 2.1088,
      "mean_token_accuracy": 0.9696682214736938,
      "num_tokens": 805057419.0,
      "step": 6990
    },
    {
      "epoch": 1.5446320203023283,
      "grad_norm": 63.0,
      "learning_rate": 1.3534089091237757e-06,
      "loss": 2.0413,
      "mean_token_accuracy": 0.9716299846768379,
      "num_tokens": 806201965.0,
      "step": 7000
    },
    {
      "epoch": 1.54683879510096,
      "grad_norm": 53.5,
      "learning_rate": 1.3409512251290164e-06,
      "loss": 2.0239,
      "mean_token_accuracy": 0.9709809094667434,
      "num_tokens": 807367764.0,
      "step": 7010
    },
    {
      "epoch": 1.5490455698995917,
      "grad_norm": 40.75,
      "learning_rate": 1.3285422559606615e-06,
      "loss": 2.0704,
      "mean_token_accuracy": 0.9714602679014206,
      "num_tokens": 808520934.0,
      "step": 7020
    },
    {
      "epoch": 1.5512523446982236,
      "grad_norm": 44.0,
      "learning_rate": 1.3161821668257969e-06,
      "loss": 2.0912,
      "mean_token_accuracy": 0.9707298710942268,
      "num_tokens": 809676061.0,
      "step": 7030
    },
    {
      "epoch": 1.5534591194968552,
      "grad_norm": 35.25,
      "learning_rate": 1.303871122280742e-06,
      "loss": 2.0005,
      "mean_token_accuracy": 0.9741318985819817,
      "num_tokens": 810819820.0,
      "step": 7040
    },
    {
      "epoch": 1.5556658942954873,
      "grad_norm": 42.25,
      "learning_rate": 1.2916092862288571e-06,
      "loss": 1.9537,
      "mean_token_accuracy": 0.9739655807614327,
      "num_tokens": 811971595.0,
      "step": 7050
    },
    {
      "epoch": 1.557872669094119,
      "grad_norm": 91.5,
      "learning_rate": 1.279396821918369e-06,
      "loss": 2.107,
      "mean_token_accuracy": 0.9708173856139183,
      "num_tokens": 813126837.0,
      "step": 7060
    },
    {
      "epoch": 1.5600794438927508,
      "grad_norm": 29.125,
      "learning_rate": 1.2672338919401866e-06,
      "loss": 2.0219,
      "mean_token_accuracy": 0.9728605598211288,
      "num_tokens": 814260797.0,
      "step": 7070
    },
    {
      "epoch": 1.5622862186913826,
      "grad_norm": 32.75,
      "learning_rate": 1.2551206582257502e-06,
      "loss": 1.9658,
      "mean_token_accuracy": 0.9735543593764305,
      "num_tokens": 815410332.0,
      "step": 7080
    },
    {
      "epoch": 1.5644929934900142,
      "grad_norm": 35.25,
      "learning_rate": 1.2430572820448593e-06,
      "loss": 2.0914,
      "mean_token_accuracy": 0.9721888631582261,
      "num_tokens": 816572165.0,
      "step": 7090
    },
    {
      "epoch": 1.566699768288646,
      "grad_norm": 95.5,
      "learning_rate": 1.2310439240035415e-06,
      "loss": 2.1523,
      "mean_token_accuracy": 0.9696663841605186,
      "num_tokens": 817717275.0,
      "step": 7100
    },
    {
      "epoch": 1.568906543087278,
      "grad_norm": 39.5,
      "learning_rate": 1.2190807440419012e-06,
      "loss": 2.0624,
      "mean_token_accuracy": 0.972392062842846,
      "num_tokens": 818867937.0,
      "step": 7110
    },
    {
      "epoch": 1.5711133178859096,
      "grad_norm": 38.0,
      "learning_rate": 1.2071679014320003e-06,
      "loss": 2.2465,
      "mean_token_accuracy": 0.9708309337496758,
      "num_tokens": 820019631.0,
      "step": 7120
    },
    {
      "epoch": 1.5733200926845416,
      "grad_norm": 50.0,
      "learning_rate": 1.195305554775728e-06,
      "loss": 2.0017,
      "mean_token_accuracy": 0.972875888645649,
      "num_tokens": 821170174.0,
      "step": 7130
    },
    {
      "epoch": 1.5755268674831733,
      "grad_norm": 37.75,
      "learning_rate": 1.183493862002702e-06,
      "loss": 2.0278,
      "mean_token_accuracy": 0.9716301292181015,
      "num_tokens": 822319040.0,
      "step": 7140
    },
    {
      "epoch": 1.5777336422818051,
      "grad_norm": 27.0,
      "learning_rate": 1.1717329803681492e-06,
      "loss": 2.0078,
      "mean_token_accuracy": 0.9711211830377579,
      "num_tokens": 823479239.0,
      "step": 7150
    },
    {
      "epoch": 1.579940417080437,
      "grad_norm": 37.0,
      "learning_rate": 1.1600230664508288e-06,
      "loss": 2.0329,
      "mean_token_accuracy": 0.9712790653109551,
      "num_tokens": 824648476.0,
      "step": 7160
    },
    {
      "epoch": 1.5821471918790686,
      "grad_norm": 34.5,
      "learning_rate": 1.1483642761509388e-06,
      "loss": 2.0054,
      "mean_token_accuracy": 0.9735493838787079,
      "num_tokens": 825784841.0,
      "step": 7170
    },
    {
      "epoch": 1.5843539666777007,
      "grad_norm": 33.0,
      "learning_rate": 1.1367567646880374e-06,
      "loss": 2.0226,
      "mean_token_accuracy": 0.973577344417572,
      "num_tokens": 826921913.0,
      "step": 7180
    },
    {
      "epoch": 1.5865607414763323,
      "grad_norm": 32.75,
      "learning_rate": 1.1252006865989868e-06,
      "loss": 2.0372,
      "mean_token_accuracy": 0.9715592041611671,
      "num_tokens": 828076982.0,
      "step": 7190
    },
    {
      "epoch": 1.5887675162749642,
      "grad_norm": 64.5,
      "learning_rate": 1.1136961957358843e-06,
      "loss": 2.0284,
      "mean_token_accuracy": 0.9722562924027442,
      "num_tokens": 829237186.0,
      "step": 7200
    },
    {
      "epoch": 1.590974291073596,
      "grad_norm": 51.25,
      "learning_rate": 1.1022434452640252e-06,
      "loss": 1.9535,
      "mean_token_accuracy": 0.975220488011837,
      "num_tokens": 830386049.0,
      "step": 7210
    },
    {
      "epoch": 1.5931810658722276,
      "grad_norm": 58.25,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 1.8771,
      "mean_token_accuracy": 0.9735103845596313,
      "num_tokens": 831529912.0,
      "step": 7220
    },
    {
      "epoch": 1.5953878406708597,
      "grad_norm": 30.375,
      "learning_rate": 1.079493774708935e-06,
      "loss": 1.9615,
      "mean_token_accuracy": 0.972948993742466,
      "num_tokens": 832706067.0,
      "step": 7230
    },
    {
      "epoch": 1.5975946154694913,
      "grad_norm": 37.75,
      "learning_rate": 1.0681971575039445e-06,
      "loss": 2.139,
      "mean_token_accuracy": 0.9720718502998352,
      "num_tokens": 833868526.0,
      "step": 7240
    },
    {
      "epoch": 1.5998013902681232,
      "grad_norm": 40.75,
      "learning_rate": 1.0569528864426444e-06,
      "loss": 2.0972,
      "mean_token_accuracy": 0.9720918238162994,
      "num_tokens": 835015773.0,
      "step": 7250
    },
    {
      "epoch": 1.602008165066755,
      "grad_norm": 45.0,
      "learning_rate": 1.0457611112258813e-06,
      "loss": 2.1322,
      "mean_token_accuracy": 0.9722673565149307,
      "num_tokens": 836158800.0,
      "step": 7260
    },
    {
      "epoch": 1.6042149398653867,
      "grad_norm": 40.75,
      "learning_rate": 1.034621980855603e-06,
      "loss": 1.9585,
      "mean_token_accuracy": 0.9732309311628342,
      "num_tokens": 837317686.0,
      "step": 7270
    },
    {
      "epoch": 1.6064217146640185,
      "grad_norm": 38.75,
      "learning_rate": 1.0235356436328675e-06,
      "loss": 1.9625,
      "mean_token_accuracy": 0.9725876554846764,
      "num_tokens": 838484460.0,
      "step": 7280
    },
    {
      "epoch": 1.6086284894626504,
      "grad_norm": 58.5,
      "learning_rate": 1.0125022471558694e-06,
      "loss": 2.0453,
      "mean_token_accuracy": 0.9716051414608955,
      "num_tokens": 839629176.0,
      "step": 7290
    },
    {
      "epoch": 1.610835264261282,
      "grad_norm": 30.5,
      "learning_rate": 1.001521938317974e-06,
      "loss": 2.1437,
      "mean_token_accuracy": 0.9712317198514938,
      "num_tokens": 840767656.0,
      "step": 7300
    },
    {
      "epoch": 1.613042039059914,
      "grad_norm": 48.25,
      "learning_rate": 9.905948633057666e-07,
      "loss": 2.1394,
      "mean_token_accuracy": 0.9718304380774498,
      "num_tokens": 841914828.0,
      "step": 7310
    },
    {
      "epoch": 1.6152488138585457,
      "grad_norm": 27.125,
      "learning_rate": 9.79721167597099e-07,
      "loss": 2.2107,
      "mean_token_accuracy": 0.9686139896512032,
      "num_tokens": 843066268.0,
      "step": 7320
    },
    {
      "epoch": 1.6174555886571775,
      "grad_norm": 56.5,
      "learning_rate": 9.689009959591605e-07,
      "loss": 2.1175,
      "mean_token_accuracy": 0.969736847281456,
      "num_tokens": 844210515.0,
      "step": 7330
    },
    {
      "epoch": 1.6196623634558094,
      "grad_norm": 30.625,
      "learning_rate": 9.58134492446543e-07,
      "loss": 2.1211,
      "mean_token_accuracy": 0.9714574560523033,
      "num_tokens": 845354376.0,
      "step": 7340
    },
    {
      "epoch": 1.621869138254441,
      "grad_norm": 30.125,
      "learning_rate": 9.474218003993275e-07,
      "loss": 1.9607,
      "mean_token_accuracy": 0.9728839039802551,
      "num_tokens": 846502889.0,
      "step": 7350
    },
    {
      "epoch": 1.624075913053073,
      "grad_norm": 40.75,
      "learning_rate": 9.367630624411766e-07,
      "loss": 2.0003,
      "mean_token_accuracy": 0.9729885131120681,
      "num_tokens": 847654739.0,
      "step": 7360
    },
    {
      "epoch": 1.6262826878517047,
      "grad_norm": 37.5,
      "learning_rate": 9.26158420477431e-07,
      "loss": 2.0484,
      "mean_token_accuracy": 0.9726179569959641,
      "num_tokens": 848798881.0,
      "step": 7370
    },
    {
      "epoch": 1.6284894626503366,
      "grad_norm": 29.0,
      "learning_rate": 9.156080156932262e-07,
      "loss": 2.1583,
      "mean_token_accuracy": 0.9698956087231636,
      "num_tokens": 849966563.0,
      "step": 7380
    },
    {
      "epoch": 1.6306962374489684,
      "grad_norm": 61.0,
      "learning_rate": 9.051119885516085e-07,
      "loss": 1.9773,
      "mean_token_accuracy": 0.9722832351922989,
      "num_tokens": 851113926.0,
      "step": 7390
    },
    {
      "epoch": 1.6329030122476,
      "grad_norm": 69.5,
      "learning_rate": 8.946704787916676e-07,
      "loss": 2.1404,
      "mean_token_accuracy": 0.973810151219368,
      "num_tokens": 852270523.0,
      "step": 7400
    },
    {
      "epoch": 1.6351097870462319,
      "grad_norm": 40.25,
      "learning_rate": 8.842836254266707e-07,
      "loss": 2.0762,
      "mean_token_accuracy": 0.9714523822069168,
      "num_tokens": 853435020.0,
      "step": 7410
    },
    {
      "epoch": 1.6373165618448637,
      "grad_norm": 33.25,
      "learning_rate": 8.739515667422211e-07,
      "loss": 2.0901,
      "mean_token_accuracy": 0.9708333104848862,
      "num_tokens": 854591521.0,
      "step": 7420
    },
    {
      "epoch": 1.6395233366434954,
      "grad_norm": 43.5,
      "learning_rate": 8.636744402944075e-07,
      "loss": 2.1919,
      "mean_token_accuracy": 0.9691047623753548,
      "num_tokens": 855749875.0,
      "step": 7430
    },
    {
      "epoch": 1.6417301114421274,
      "grad_norm": 30.125,
      "learning_rate": 8.534523829079816e-07,
      "loss": 2.1207,
      "mean_token_accuracy": 0.9710880756378174,
      "num_tokens": 856890857.0,
      "step": 7440
    },
    {
      "epoch": 1.643936886240759,
      "grad_norm": 29.5,
      "learning_rate": 8.432855306745264e-07,
      "loss": 2.0775,
      "mean_token_accuracy": 0.9715194016695022,
      "num_tokens": 858044917.0,
      "step": 7450
    },
    {
      "epoch": 1.646143661039391,
      "grad_norm": 30.75,
      "learning_rate": 8.33174018950656e-07,
      "loss": 1.999,
      "mean_token_accuracy": 0.9722257912158966,
      "num_tokens": 859209419.0,
      "step": 7460
    },
    {
      "epoch": 1.6483504358380228,
      "grad_norm": 55.5,
      "learning_rate": 8.231179823562008e-07,
      "loss": 2.0854,
      "mean_token_accuracy": 0.9688320323824883,
      "num_tokens": 860342766.0,
      "step": 7470
    },
    {
      "epoch": 1.6505572106366544,
      "grad_norm": 31.75,
      "learning_rate": 8.131175547724291e-07,
      "loss": 2.022,
      "mean_token_accuracy": 0.9720481425523758,
      "num_tokens": 861491592.0,
      "step": 7480
    },
    {
      "epoch": 1.6527639854352865,
      "grad_norm": 42.5,
      "learning_rate": 8.031728693402502e-07,
      "loss": 2.0478,
      "mean_token_accuracy": 0.9726708501577377,
      "num_tokens": 862631995.0,
      "step": 7490
    },
    {
      "epoch": 1.654970760233918,
      "grad_norm": 51.0,
      "learning_rate": 7.932840584584544e-07,
      "loss": 2.0466,
      "mean_token_accuracy": 0.9717046096920967,
      "num_tokens": 863797160.0,
      "step": 7500
    },
    {
      "epoch": 1.65717753503255,
      "grad_norm": 48.25,
      "learning_rate": 7.834512537819444e-07,
      "loss": 2.1317,
      "mean_token_accuracy": 0.9714762687683105,
      "num_tokens": 864956568.0,
      "step": 7510
    },
    {
      "epoch": 1.6593843098311818,
      "grad_norm": 54.75,
      "learning_rate": 7.736745862199785e-07,
      "loss": 2.0352,
      "mean_token_accuracy": 0.9716887414455414,
      "num_tokens": 866099607.0,
      "step": 7520
    },
    {
      "epoch": 1.6615910846298134,
      "grad_norm": 30.125,
      "learning_rate": 7.639541859344385e-07,
      "loss": 2.1381,
      "mean_token_accuracy": 0.9717371121048928,
      "num_tokens": 867263485.0,
      "step": 7530
    },
    {
      "epoch": 1.6637978594284455,
      "grad_norm": 82.5,
      "learning_rate": 7.542901823380844e-07,
      "loss": 2.1668,
      "mean_token_accuracy": 0.9712492927908898,
      "num_tokens": 868406792.0,
      "step": 7540
    },
    {
      "epoch": 1.6660046342270771,
      "grad_norm": 36.25,
      "learning_rate": 7.446827040928439e-07,
      "loss": 1.9357,
      "mean_token_accuracy": 0.9734378889203071,
      "num_tokens": 869555653.0,
      "step": 7550
    },
    {
      "epoch": 1.668211409025709,
      "grad_norm": 43.5,
      "learning_rate": 7.351318791080881e-07,
      "loss": 2.005,
      "mean_token_accuracy": 0.9729954108595849,
      "num_tokens": 870700028.0,
      "step": 7560
    },
    {
      "epoch": 1.6704181838243408,
      "grad_norm": 35.0,
      "learning_rate": 7.25637834538937e-07,
      "loss": 2.118,
      "mean_token_accuracy": 0.9732496395707131,
      "num_tokens": 871838540.0,
      "step": 7570
    },
    {
      "epoch": 1.6726249586229724,
      "grad_norm": 48.0,
      "learning_rate": 7.162006967845602e-07,
      "loss": 2.014,
      "mean_token_accuracy": 0.97105952501297,
      "num_tokens": 872989045.0,
      "step": 7580
    },
    {
      "epoch": 1.6748317334216043,
      "grad_norm": 36.5,
      "learning_rate": 7.068205914865012e-07,
      "loss": 2.0115,
      "mean_token_accuracy": 0.9721890851855278,
      "num_tokens": 874118868.0,
      "step": 7590
    },
    {
      "epoch": 1.6770385082202361,
      "grad_norm": 60.0,
      "learning_rate": 6.974976435269953e-07,
      "loss": 1.9501,
      "mean_token_accuracy": 0.9722740620374679,
      "num_tokens": 875278822.0,
      "step": 7600
    },
    {
      "epoch": 1.6792452830188678,
      "grad_norm": 49.75,
      "learning_rate": 6.882319770273193e-07,
      "loss": 2.0011,
      "mean_token_accuracy": 0.973717799782753,
      "num_tokens": 876415819.0,
      "step": 7610
    },
    {
      "epoch": 1.6814520578174998,
      "grad_norm": 31.375,
      "learning_rate": 6.790237153461244e-07,
      "loss": 2.0672,
      "mean_token_accuracy": 0.9711730435490609,
      "num_tokens": 877576379.0,
      "step": 7620
    },
    {
      "epoch": 1.6836588326161315,
      "grad_norm": 51.25,
      "learning_rate": 6.698729810778065e-07,
      "loss": 2.1188,
      "mean_token_accuracy": 0.9709119975566864,
      "num_tokens": 878728181.0,
      "step": 7630
    },
    {
      "epoch": 1.6858656074147633,
      "grad_norm": 37.75,
      "learning_rate": 6.607798960508693e-07,
      "loss": 1.9873,
      "mean_token_accuracy": 0.9729375317692757,
      "num_tokens": 879893736.0,
      "step": 7640
    },
    {
      "epoch": 1.6880723822133952,
      "grad_norm": 33.25,
      "learning_rate": 6.517445813262985e-07,
      "loss": 2.1797,
      "mean_token_accuracy": 0.9696862816810607,
      "num_tokens": 881043763.0,
      "step": 7650
    },
    {
      "epoch": 1.6902791570120268,
      "grad_norm": 45.5,
      "learning_rate": 6.42767157195957e-07,
      "loss": 1.9654,
      "mean_token_accuracy": 0.9742277681827545,
      "num_tokens": 882201644.0,
      "step": 7660
    },
    {
      "epoch": 1.6924859318106589,
      "grad_norm": 33.0,
      "learning_rate": 6.338477431809764e-07,
      "loss": 2.1417,
      "mean_token_accuracy": 0.9706949338316917,
      "num_tokens": 883356680.0,
      "step": 7670
    },
    {
      "epoch": 1.6946927066092905,
      "grad_norm": 35.25,
      "learning_rate": 6.24986458030174e-07,
      "loss": 2.1473,
      "mean_token_accuracy": 0.9713629007339477,
      "num_tokens": 884515378.0,
      "step": 7680
    },
    {
      "epoch": 1.6968994814079223,
      "grad_norm": 43.75,
      "learning_rate": 6.16183419718463e-07,
      "loss": 2.0601,
      "mean_token_accuracy": 0.9726741090416908,
      "num_tokens": 885654893.0,
      "step": 7690
    },
    {
      "epoch": 1.6991062562065542,
      "grad_norm": 51.25,
      "learning_rate": 6.074387454452891e-07,
      "loss": 2.0579,
      "mean_token_accuracy": 0.972286669909954,
      "num_tokens": 886799692.0,
      "step": 7700
    },
    {
      "epoch": 1.7013130310051858,
      "grad_norm": 69.5,
      "learning_rate": 5.987525516330639e-07,
      "loss": 1.963,
      "mean_token_accuracy": 0.9727952882647515,
      "num_tokens": 887943262.0,
      "step": 7710
    },
    {
      "epoch": 1.7035198058038177,
      "grad_norm": 39.75,
      "learning_rate": 5.901249539256215e-07,
      "loss": 2.0637,
      "mean_token_accuracy": 0.9720316395163536,
      "num_tokens": 889099090.0,
      "step": 7720
    },
    {
      "epoch": 1.7057265806024495,
      "grad_norm": 34.75,
      "learning_rate": 5.815560671866721e-07,
      "loss": 2.1191,
      "mean_token_accuracy": 0.9708709806203842,
      "num_tokens": 890238575.0,
      "step": 7730
    },
    {
      "epoch": 1.7079333554010812,
      "grad_norm": 31.75,
      "learning_rate": 5.730460054982806e-07,
      "loss": 2.2218,
      "mean_token_accuracy": 0.970518171787262,
      "num_tokens": 891401883.0,
      "step": 7740
    },
    {
      "epoch": 1.7101401301997132,
      "grad_norm": 35.25,
      "learning_rate": 5.645948821593384e-07,
      "loss": 2.2501,
      "mean_token_accuracy": 0.9675888404250145,
      "num_tokens": 892541055.0,
      "step": 7750
    },
    {
      "epoch": 1.7123469049983449,
      "grad_norm": 55.0,
      "learning_rate": 5.562028096840638e-07,
      "loss": 1.9937,
      "mean_token_accuracy": 0.9745137065649032,
      "num_tokens": 893701428.0,
      "step": 7760
    },
    {
      "epoch": 1.7145536797969767,
      "grad_norm": 40.25,
      "learning_rate": 5.478698998004967e-07,
      "loss": 1.9651,
      "mean_token_accuracy": 0.9739260256290436,
      "num_tokens": 894866648.0,
      "step": 7770
    },
    {
      "epoch": 1.7167604545956086,
      "grad_norm": 54.0,
      "learning_rate": 5.395962634490182e-07,
      "loss": 2.2767,
      "mean_token_accuracy": 0.9687472566962242,
      "num_tokens": 896019860.0,
      "step": 7780
    },
    {
      "epoch": 1.7189672293942402,
      "grad_norm": 36.75,
      "learning_rate": 5.313820107808665e-07,
      "loss": 2.1564,
      "mean_token_accuracy": 0.9713079541921615,
      "num_tokens": 897161732.0,
      "step": 7790
    },
    {
      "epoch": 1.7211740041928723,
      "grad_norm": 25.75,
      "learning_rate": 5.232272511566744e-07,
      "loss": 1.8731,
      "mean_token_accuracy": 0.9750093907117844,
      "num_tokens": 898310931.0,
      "step": 7800
    },
    {
      "epoch": 1.7233807789915039,
      "grad_norm": 48.0,
      "learning_rate": 5.15132093145016e-07,
      "loss": 1.965,
      "mean_token_accuracy": 0.9733878612518311,
      "num_tokens": 899470545.0,
      "step": 7810
    },
    {
      "epoch": 1.7255875537901357,
      "grad_norm": 35.75,
      "learning_rate": 5.07096644520954e-07,
      "loss": 1.9553,
      "mean_token_accuracy": 0.9752668336033821,
      "num_tokens": 900616929.0,
      "step": 7820
    },
    {
      "epoch": 1.7277943285887676,
      "grad_norm": 45.5,
      "learning_rate": 4.991210122646117e-07,
      "loss": 2.0659,
      "mean_token_accuracy": 0.9726020514965057,
      "num_tokens": 901753539.0,
      "step": 7830
    },
    {
      "epoch": 1.7300011033873992,
      "grad_norm": 28.5,
      "learning_rate": 4.91205302559743e-07,
      "loss": 1.9884,
      "mean_token_accuracy": 0.9747185051441193,
      "num_tokens": 902884735.0,
      "step": 7840
    },
    {
      "epoch": 1.7322078781860313,
      "grad_norm": 39.0,
      "learning_rate": 4.83349620792325e-07,
      "loss": 1.9999,
      "mean_token_accuracy": 0.9716772183775901,
      "num_tokens": 904029168.0,
      "step": 7850
    },
    {
      "epoch": 1.734414652984663,
      "grad_norm": 37.5,
      "learning_rate": 4.7555407154914855e-07,
      "loss": 2.1205,
      "mean_token_accuracy": 0.9712923109531403,
      "num_tokens": 905172256.0,
      "step": 7860
    },
    {
      "epoch": 1.7366214277832948,
      "grad_norm": 35.75,
      "learning_rate": 4.678187586164318e-07,
      "loss": 2.0697,
      "mean_token_accuracy": 0.9702929228544235,
      "num_tokens": 906314973.0,
      "step": 7870
    },
    {
      "epoch": 1.7388282025819266,
      "grad_norm": 67.0,
      "learning_rate": 4.601437849784318e-07,
      "loss": 2.0419,
      "mean_token_accuracy": 0.9708929598331452,
      "num_tokens": 907464012.0,
      "step": 7880
    },
    {
      "epoch": 1.7410349773805582,
      "grad_norm": 37.75,
      "learning_rate": 4.525292528160813e-07,
      "loss": 1.9635,
      "mean_token_accuracy": 0.9719430968165398,
      "num_tokens": 908618543.0,
      "step": 7890
    },
    {
      "epoch": 1.74324175217919,
      "grad_norm": 58.5,
      "learning_rate": 4.449752635056187e-07,
      "loss": 2.1559,
      "mean_token_accuracy": 0.9704511150717735,
      "num_tokens": 909765551.0,
      "step": 7900
    },
    {
      "epoch": 1.745448526977822,
      "grad_norm": 35.25,
      "learning_rate": 4.374819176172501e-07,
      "loss": 2.1415,
      "mean_token_accuracy": 0.971914105117321,
      "num_tokens": 910911710.0,
      "step": 7910
    },
    {
      "epoch": 1.7476553017764536,
      "grad_norm": 45.25,
      "learning_rate": 4.3004931491379906e-07,
      "loss": 2.167,
      "mean_token_accuracy": 0.9703967437148094,
      "num_tokens": 912054146.0,
      "step": 7920
    },
    {
      "epoch": 1.7498620765750856,
      "grad_norm": 45.0,
      "learning_rate": 4.2267755434938605e-07,
      "loss": 1.9739,
      "mean_token_accuracy": 0.9738942295312881,
      "num_tokens": 913194503.0,
      "step": 7930
    },
    {
      "epoch": 1.7520688513737173,
      "grad_norm": 42.75,
      "learning_rate": 4.153667340681067e-07,
      "loss": 2.0736,
      "mean_token_accuracy": 0.9722946628928184,
      "num_tokens": 914350105.0,
      "step": 7940
    },
    {
      "epoch": 1.7542756261723491,
      "grad_norm": 56.5,
      "learning_rate": 4.081169514027289e-07,
      "loss": 1.9458,
      "mean_token_accuracy": 0.9733357861638069,
      "num_tokens": 915509236.0,
      "step": 7950
    },
    {
      "epoch": 1.756482400970981,
      "grad_norm": 38.0,
      "learning_rate": 4.009283028733929e-07,
      "loss": 2.1764,
      "mean_token_accuracy": 0.9709475204348564,
      "num_tokens": 916658298.0,
      "step": 7960
    },
    {
      "epoch": 1.7586891757696126,
      "grad_norm": 35.25,
      "learning_rate": 3.938008841863289e-07,
      "loss": 1.976,
      "mean_token_accuracy": 0.9722469970583916,
      "num_tokens": 917797467.0,
      "step": 7970
    },
    {
      "epoch": 1.7608959505682447,
      "grad_norm": 35.75,
      "learning_rate": 3.8673479023258464e-07,
      "loss": 1.9668,
      "mean_token_accuracy": 0.9747024863958359,
      "num_tokens": 918929082.0,
      "step": 7980
    },
    {
      "epoch": 1.7631027253668763,
      "grad_norm": 43.0,
      "learning_rate": 3.797301150867544e-07,
      "loss": 2.1188,
      "mean_token_accuracy": 0.973191611468792,
      "num_tokens": 920082190.0,
      "step": 7990
    },
    {
      "epoch": 1.7653095001655081,
      "grad_norm": 33.75,
      "learning_rate": 3.7278695200573754e-07,
      "loss": 1.9952,
      "mean_token_accuracy": 0.9738741293549538,
      "num_tokens": 921235813.0,
      "step": 8000
    },
    {
      "epoch": 1.76751627496414,
      "grad_norm": 64.5,
      "learning_rate": 3.6590539342748645e-07,
      "loss": 2.0674,
      "mean_token_accuracy": 0.9709431260824204,
      "num_tokens": 922380449.0,
      "step": 8010
    },
    {
      "epoch": 1.7697230497627716,
      "grad_norm": 29.5,
      "learning_rate": 3.590855309697844e-07,
      "loss": 1.8465,
      "mean_token_accuracy": 0.9753936052322387,
      "num_tokens": 923532540.0,
      "step": 8020
    },
    {
      "epoch": 1.7719298245614035,
      "grad_norm": 33.25,
      "learning_rate": 3.52327455429019e-07,
      "loss": 2.0296,
      "mean_token_accuracy": 0.9728592067956925,
      "num_tokens": 924682038.0,
      "step": 8030
    },
    {
      "epoch": 1.7741365993600353,
      "grad_norm": 31.125,
      "learning_rate": 3.4563125677897936e-07,
      "loss": 1.8672,
      "mean_token_accuracy": 0.9767834961414337,
      "num_tokens": 925829422.0,
      "step": 8040
    },
    {
      "epoch": 1.776343374158667,
      "grad_norm": 40.25,
      "learning_rate": 3.3899702416965166e-07,
      "loss": 2.0178,
      "mean_token_accuracy": 0.9722177684307098,
      "num_tokens": 927003779.0,
      "step": 8050
    },
    {
      "epoch": 1.778550148957299,
      "grad_norm": 61.5,
      "learning_rate": 3.324248459260393e-07,
      "loss": 1.9174,
      "mean_token_accuracy": 0.9747939512133599,
      "num_tokens": 928158326.0,
      "step": 8060
    },
    {
      "epoch": 1.7807569237559306,
      "grad_norm": 29.125,
      "learning_rate": 3.2591480954698107e-07,
      "loss": 2.0192,
      "mean_token_accuracy": 0.9723817110061646,
      "num_tokens": 929312957.0,
      "step": 8070
    },
    {
      "epoch": 1.7829636985545625,
      "grad_norm": 34.25,
      "learning_rate": 3.194670017039897e-07,
      "loss": 2.0185,
      "mean_token_accuracy": 0.9726116612553597,
      "num_tokens": 930473164.0,
      "step": 8080
    },
    {
      "epoch": 1.7851704733531943,
      "grad_norm": 34.25,
      "learning_rate": 3.1308150824009785e-07,
      "loss": 1.8569,
      "mean_token_accuracy": 0.9756187111139297,
      "num_tokens": 931618845.0,
      "step": 8090
    },
    {
      "epoch": 1.787377248151826,
      "grad_norm": 56.25,
      "learning_rate": 3.0675841416871186e-07,
      "loss": 2.0933,
      "mean_token_accuracy": 0.9721642076969147,
      "num_tokens": 932784403.0,
      "step": 8100
    },
    {
      "epoch": 1.789584022950458,
      "grad_norm": 40.25,
      "learning_rate": 3.004978036724854e-07,
      "loss": 2.1832,
      "mean_token_accuracy": 0.9701064124703407,
      "num_tokens": 933918479.0,
      "step": 8110
    },
    {
      "epoch": 1.7917907977490897,
      "grad_norm": 44.25,
      "learning_rate": 2.942997601021924e-07,
      "loss": 1.9497,
      "mean_token_accuracy": 0.9735993355512619,
      "num_tokens": 935062458.0,
      "step": 8120
    },
    {
      "epoch": 1.7939975725477215,
      "grad_norm": 82.0,
      "learning_rate": 2.8816436597562336e-07,
      "loss": 1.9985,
      "mean_token_accuracy": 0.9721275955438614,
      "num_tokens": 936208787.0,
      "step": 8130
    },
    {
      "epoch": 1.7962043473463534,
      "grad_norm": 53.5,
      "learning_rate": 2.82091702976483e-07,
      "loss": 2.0741,
      "mean_token_accuracy": 0.971569475531578,
      "num_tokens": 937362609.0,
      "step": 8140
    },
    {
      "epoch": 1.798411122144985,
      "grad_norm": 42.0,
      "learning_rate": 2.760818519533037e-07,
      "loss": 2.0957,
      "mean_token_accuracy": 0.9712625026702881,
      "num_tokens": 938516307.0,
      "step": 8150
    },
    {
      "epoch": 1.800617896943617,
      "grad_norm": 36.75,
      "learning_rate": 2.701348929183695e-07,
      "loss": 2.0359,
      "mean_token_accuracy": 0.9721588283777237,
      "num_tokens": 939677209.0,
      "step": 8160
    },
    {
      "epoch": 1.8028246717422487,
      "grad_norm": 39.0,
      "learning_rate": 2.642509050466502e-07,
      "loss": 2.0473,
      "mean_token_accuracy": 0.9722105696797371,
      "num_tokens": 940831595.0,
      "step": 8170
    },
    {
      "epoch": 1.8050314465408805,
      "grad_norm": 54.75,
      "learning_rate": 2.584299666747475e-07,
      "loss": 1.9234,
      "mean_token_accuracy": 0.9739458382129669,
      "num_tokens": 941977946.0,
      "step": 8180
    },
    {
      "epoch": 1.8072382213395124,
      "grad_norm": 30.5,
      "learning_rate": 2.5267215529985346e-07,
      "loss": 1.9346,
      "mean_token_accuracy": 0.9739042535424233,
      "num_tokens": 943123031.0,
      "step": 8190
    },
    {
      "epoch": 1.809444996138144,
      "grad_norm": 32.25,
      "learning_rate": 2.4697754757871504e-07,
      "loss": 2.0461,
      "mean_token_accuracy": 0.9731713324785233,
      "num_tokens": 944273941.0,
      "step": 8200
    },
    {
      "epoch": 1.8116517709367759,
      "grad_norm": 42.75,
      "learning_rate": 2.4134621932661916e-07,
      "loss": 2.1882,
      "mean_token_accuracy": 0.9692026615142822,
      "num_tokens": 945412830.0,
      "step": 8210
    },
    {
      "epoch": 1.8138585457354077,
      "grad_norm": 37.75,
      "learning_rate": 2.3577824551637818e-07,
      "loss": 2.1983,
      "mean_token_accuracy": 0.9701014026999474,
      "num_tokens": 946560307.0,
      "step": 8220
    },
    {
      "epoch": 1.8160653205340394,
      "grad_norm": 39.5,
      "learning_rate": 2.3027370027733308e-07,
      "loss": 2.1022,
      "mean_token_accuracy": 0.9740872040390969,
      "num_tokens": 947702446.0,
      "step": 8230
    },
    {
      "epoch": 1.8182720953326714,
      "grad_norm": 108.0,
      "learning_rate": 2.2483265689436929e-07,
      "loss": 2.2295,
      "mean_token_accuracy": 0.9702272340655327,
      "num_tokens": 948842508.0,
      "step": 8240
    },
    {
      "epoch": 1.820478870131303,
      "grad_norm": 44.5,
      "learning_rate": 2.194551878069362e-07,
      "loss": 2.0059,
      "mean_token_accuracy": 0.9725719034671784,
      "num_tokens": 949996024.0,
      "step": 8250
    },
    {
      "epoch": 1.822685644929935,
      "grad_norm": 67.0,
      "learning_rate": 2.141413646080881e-07,
      "loss": 2.0815,
      "mean_token_accuracy": 0.9719247072935104,
      "num_tokens": 951155186.0,
      "step": 8260
    },
    {
      "epoch": 1.8248924197285668,
      "grad_norm": 62.5,
      "learning_rate": 2.0889125804352595e-07,
      "loss": 1.9589,
      "mean_token_accuracy": 0.9718130439519882,
      "num_tokens": 952309745.0,
      "step": 8270
    },
    {
      "epoch": 1.8270991945271984,
      "grad_norm": 40.0,
      "learning_rate": 2.0370493801066038e-07,
      "loss": 2.1526,
      "mean_token_accuracy": 0.9705539584159851,
      "num_tokens": 953464997.0,
      "step": 8280
    },
    {
      "epoch": 1.8293059693258304,
      "grad_norm": 33.75,
      "learning_rate": 1.985824735576758e-07,
      "loss": 1.9694,
      "mean_token_accuracy": 0.9738747671246528,
      "num_tokens": 954601830.0,
      "step": 8290
    },
    {
      "epoch": 1.831512744124462,
      "grad_norm": 30.625,
      "learning_rate": 1.9352393288261717e-07,
      "loss": 1.9859,
      "mean_token_accuracy": 0.9722137659788131,
      "num_tokens": 955764590.0,
      "step": 8300
    },
    {
      "epoch": 1.833719518923094,
      "grad_norm": 48.25,
      "learning_rate": 1.8852938333247527e-07,
      "loss": 2.0491,
      "mean_token_accuracy": 0.9716416522860527,
      "num_tokens": 956903842.0,
      "step": 8310
    },
    {
      "epoch": 1.8359262937217258,
      "grad_norm": 54.5,
      "learning_rate": 1.8359889140229738e-07,
      "loss": 2.3036,
      "mean_token_accuracy": 0.9689033165574074,
      "num_tokens": 958062923.0,
      "step": 8320
    },
    {
      "epoch": 1.8381330685203574,
      "grad_norm": 60.75,
      "learning_rate": 1.787325227342951e-07,
      "loss": 2.031,
      "mean_token_accuracy": 0.9712080925703048,
      "num_tokens": 959220528.0,
      "step": 8330
    },
    {
      "epoch": 1.8403398433189893,
      "grad_norm": 34.0,
      "learning_rate": 1.7393034211697524e-07,
      "loss": 2.2172,
      "mean_token_accuracy": 0.971020159125328,
      "num_tokens": 960361218.0,
      "step": 8340
    },
    {
      "epoch": 1.842546618117621,
      "grad_norm": 31.0,
      "learning_rate": 1.6919241348427485e-07,
      "loss": 2.1152,
      "mean_token_accuracy": 0.9742466166615487,
      "num_tokens": 961512553.0,
      "step": 8350
    },
    {
      "epoch": 1.8447533929162527,
      "grad_norm": 30.25,
      "learning_rate": 1.6451879991471186e-07,
      "loss": 1.8873,
      "mean_token_accuracy": 0.974276153743267,
      "num_tokens": 962651073.0,
      "step": 8360
    },
    {
      "epoch": 1.8469601677148848,
      "grad_norm": 70.0,
      "learning_rate": 1.59909563630542e-07,
      "loss": 2.0553,
      "mean_token_accuracy": 0.9721343412995338,
      "num_tokens": 963788631.0,
      "step": 8370
    },
    {
      "epoch": 1.8491669425135164,
      "grad_norm": 35.0,
      "learning_rate": 1.553647659969354e-07,
      "loss": 2.0071,
      "mean_token_accuracy": 0.9735460400581359,
      "num_tokens": 964941646.0,
      "step": 8380
    },
    {
      "epoch": 1.8513737173121483,
      "grad_norm": 33.25,
      "learning_rate": 1.5088446752115403e-07,
      "loss": 1.8506,
      "mean_token_accuracy": 0.9752474725246429,
      "num_tokens": 966071138.0,
      "step": 8390
    },
    {
      "epoch": 1.8535804921107801,
      "grad_norm": 41.75,
      "learning_rate": 1.4646872785175182e-07,
      "loss": 2.0138,
      "mean_token_accuracy": 0.9729744389653205,
      "num_tokens": 967222718.0,
      "step": 8400
    },
    {
      "epoch": 1.8557872669094118,
      "grad_norm": 74.0,
      "learning_rate": 1.4211760577777567e-07,
      "loss": 2.1171,
      "mean_token_accuracy": 0.9701059252023697,
      "num_tokens": 968388811.0,
      "step": 8410
    },
    {
      "epoch": 1.8579940417080438,
      "grad_norm": 56.75,
      "learning_rate": 1.378311592279835e-07,
      "loss": 2.1106,
      "mean_token_accuracy": 0.9707264408469201,
      "num_tokens": 969545212.0,
      "step": 8420
    },
    {
      "epoch": 1.8602008165066755,
      "grad_norm": 32.0,
      "learning_rate": 1.3360944527007758e-07,
      "loss": 2.1197,
      "mean_token_accuracy": 0.9717460289597512,
      "num_tokens": 970707357.0,
      "step": 8430
    },
    {
      "epoch": 1.8624075913053073,
      "grad_norm": 26.875,
      "learning_rate": 1.2945252010993836e-07,
      "loss": 1.9026,
      "mean_token_accuracy": 0.9737710073590279,
      "num_tokens": 971855325.0,
      "step": 8440
    },
    {
      "epoch": 1.8646143661039392,
      "grad_norm": 32.5,
      "learning_rate": 1.253604390908819e-07,
      "loss": 2.1121,
      "mean_token_accuracy": 0.9712524697184562,
      "num_tokens": 973004582.0,
      "step": 8450
    },
    {
      "epoch": 1.8668211409025708,
      "grad_norm": 68.5,
      "learning_rate": 1.2133325669291818e-07,
      "loss": 1.9448,
      "mean_token_accuracy": 0.9729618296027184,
      "num_tokens": 974150966.0,
      "step": 8460
    },
    {
      "epoch": 1.8690279157012029,
      "grad_norm": 74.0,
      "learning_rate": 1.1737102653202825e-07,
      "loss": 2.1982,
      "mean_token_accuracy": 0.9715160578489304,
      "num_tokens": 975305148.0,
      "step": 8470
    },
    {
      "epoch": 1.8712346904998345,
      "grad_norm": 45.25,
      "learning_rate": 1.1347380135945108e-07,
      "loss": 2.0097,
      "mean_token_accuracy": 0.9728082567453384,
      "num_tokens": 976473337.0,
      "step": 8480
    },
    {
      "epoch": 1.8734414652984663,
      "grad_norm": 54.75,
      "learning_rate": 1.0964163306098007e-07,
      "loss": 2.1735,
      "mean_token_accuracy": 0.9684741124510765,
      "num_tokens": 977639676.0,
      "step": 8490
    },
    {
      "epoch": 1.8756482400970982,
      "grad_norm": 40.5,
      "learning_rate": 1.0587457265627099e-07,
      "loss": 1.9927,
      "mean_token_accuracy": 0.9719024330377579,
      "num_tokens": 978791690.0,
      "step": 8500
    },
    {
      "epoch": 1.8778550148957298,
      "grad_norm": 38.0,
      "learning_rate": 1.0217267029816736e-07,
      "loss": 2.0263,
      "mean_token_accuracy": 0.9727027878165245,
      "num_tokens": 979948778.0,
      "step": 8510
    },
    {
      "epoch": 1.8800617896943617,
      "grad_norm": 56.75,
      "learning_rate": 9.853597527202608e-08,
      "loss": 1.9744,
      "mean_token_accuracy": 0.9710759162902832,
      "num_tokens": 981124882.0,
      "step": 8520
    },
    {
      "epoch": 1.8822685644929935,
      "grad_norm": 63.5,
      "learning_rate": 9.496453599506683e-08,
      "loss": 1.9742,
      "mean_token_accuracy": 0.9734450191259384,
      "num_tokens": 982276679.0,
      "step": 8530
    },
    {
      "epoch": 1.8844753392916251,
      "grad_norm": 56.5,
      "learning_rate": 9.145840001572537e-08,
      "loss": 2.1345,
      "mean_token_accuracy": 0.9723558008670807,
      "num_tokens": 983430849.0,
      "step": 8540
    },
    {
      "epoch": 1.8866821140902572,
      "grad_norm": 39.75,
      "learning_rate": 8.801761401302012e-08,
      "loss": 2.1164,
      "mean_token_accuracy": 0.9715082153677941,
      "num_tokens": 984588235.0,
      "step": 8550
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 44.0,
      "learning_rate": 8.464222379593157e-08,
      "loss": 2.0179,
      "mean_token_accuracy": 0.9715511262416839,
      "num_tokens": 985724223.0,
      "step": 8560
    },
    {
      "epoch": 1.8910956636875207,
      "grad_norm": 29.125,
      "learning_rate": 8.133227430279055e-08,
      "loss": 2.1197,
      "mean_token_accuracy": 0.9714652240276337,
      "num_tokens": 986878816.0,
      "step": 8570
    },
    {
      "epoch": 1.8933024384861525,
      "grad_norm": 51.75,
      "learning_rate": 7.808780960068374e-08,
      "loss": 2.0863,
      "mean_token_accuracy": 0.9722049072384834,
      "num_tokens": 988048180.0,
      "step": 8580
    },
    {
      "epoch": 1.8955092132847842,
      "grad_norm": 49.0,
      "learning_rate": 7.490887288486293e-08,
      "loss": 2.0019,
      "mean_token_accuracy": 0.9722190052270889,
      "num_tokens": 989193104.0,
      "step": 8590
    },
    {
      "epoch": 1.8977159880834162,
      "grad_norm": 35.25,
      "learning_rate": 7.179550647817224e-08,
      "loss": 2.147,
      "mean_token_accuracy": 0.9713039547204971,
      "num_tokens": 990357136.0,
      "step": 8600
    },
    {
      "epoch": 1.8999227628820479,
      "grad_norm": 36.25,
      "learning_rate": 6.8747751830483e-08,
      "loss": 2.1755,
      "mean_token_accuracy": 0.96804458796978,
      "num_tokens": 991522520.0,
      "step": 8610
    },
    {
      "epoch": 1.9021295376806797,
      "grad_norm": 33.25,
      "learning_rate": 6.576564951814468e-08,
      "loss": 2.1008,
      "mean_token_accuracy": 0.9700887709856033,
      "num_tokens": 992681250.0,
      "step": 8620
    },
    {
      "epoch": 1.9043363124793116,
      "grad_norm": 43.0,
      "learning_rate": 6.28492392434421e-08,
      "loss": 1.9206,
      "mean_token_accuracy": 0.9746546059846878,
      "num_tokens": 993832727.0,
      "step": 8630
    },
    {
      "epoch": 1.9065430872779432,
      "grad_norm": 69.0,
      "learning_rate": 5.999855983406688e-08,
      "loss": 2.2324,
      "mean_token_accuracy": 0.9685314312577248,
      "num_tokens": 994974350.0,
      "step": 8640
    },
    {
      "epoch": 1.908749862076575,
      "grad_norm": 37.75,
      "learning_rate": 5.7213649242602865e-08,
      "loss": 2.0456,
      "mean_token_accuracy": 0.9723233506083488,
      "num_tokens": 996123250.0,
      "step": 8650
    },
    {
      "epoch": 1.910956636875207,
      "grad_norm": 56.25,
      "learning_rate": 5.4494544546018216e-08,
      "loss": 2.0758,
      "mean_token_accuracy": 0.9713181182742119,
      "num_tokens": 997275499.0,
      "step": 8660
    },
    {
      "epoch": 1.9131634116738385,
      "grad_norm": 34.0,
      "learning_rate": 5.184128194517302e-08,
      "loss": 2.156,
      "mean_token_accuracy": 0.9679503574967384,
      "num_tokens": 998427968.0,
      "step": 8670
    },
    {
      "epoch": 1.9153701864724706,
      "grad_norm": 36.25,
      "learning_rate": 4.925389676433745e-08,
      "loss": 2.0123,
      "mean_token_accuracy": 0.9714771032333374,
      "num_tokens": 999578497.0,
      "step": 8680
    },
    {
      "epoch": 1.9175769612711022,
      "grad_norm": 45.5,
      "learning_rate": 4.67324234507216e-08,
      "loss": 2.1258,
      "mean_token_accuracy": 0.9722574591636658,
      "num_tokens": 1000720591.0,
      "step": 8690
    },
    {
      "epoch": 1.919783736069734,
      "grad_norm": 35.25,
      "learning_rate": 4.427689557401471e-08,
      "loss": 2.0748,
      "mean_token_accuracy": 0.9719079181551933,
      "num_tokens": 1001885635.0,
      "step": 8700
    },
    {
      "epoch": 1.921990510868366,
      "grad_norm": 31.25,
      "learning_rate": 4.188734582594223e-08,
      "loss": 1.9799,
      "mean_token_accuracy": 0.9727680742740631,
      "num_tokens": 1003035953.0,
      "step": 8710
    },
    {
      "epoch": 1.9241972856669975,
      "grad_norm": 48.25,
      "learning_rate": 3.956380601982668e-08,
      "loss": 2.0354,
      "mean_token_accuracy": 0.9731521651148796,
      "num_tokens": 1004186983.0,
      "step": 8720
    },
    {
      "epoch": 1.9264040604656296,
      "grad_norm": 41.25,
      "learning_rate": 3.730630709016747e-08,
      "loss": 2.2734,
      "mean_token_accuracy": 0.9702733591198921,
      "num_tokens": 1005337640.0,
      "step": 8730
    },
    {
      "epoch": 1.9286108352642612,
      "grad_norm": 42.0,
      "learning_rate": 3.5114879092225104e-08,
      "loss": 2.0995,
      "mean_token_accuracy": 0.9706131368875504,
      "num_tokens": 1006512664.0,
      "step": 8740
    },
    {
      "epoch": 1.930817610062893,
      "grad_norm": 30.625,
      "learning_rate": 3.2989551201624836e-08,
      "loss": 2.1147,
      "mean_token_accuracy": 0.9697392374277115,
      "num_tokens": 1007670382.0,
      "step": 8750
    },
    {
      "epoch": 1.933024384861525,
      "grad_norm": 32.5,
      "learning_rate": 3.093035171396641e-08,
      "loss": 1.9969,
      "mean_token_accuracy": 0.9729149028658867,
      "num_tokens": 1008816857.0,
      "step": 8760
    },
    {
      "epoch": 1.9352311596601566,
      "grad_norm": 32.5,
      "learning_rate": 2.893730804444772e-08,
      "loss": 2.1395,
      "mean_token_accuracy": 0.9717914223670959,
      "num_tokens": 1009986863.0,
      "step": 8770
    },
    {
      "epoch": 1.9374379344587886,
      "grad_norm": 57.0,
      "learning_rate": 2.7010446727498974e-08,
      "loss": 2.0657,
      "mean_token_accuracy": 0.9721935659646987,
      "num_tokens": 1011143146.0,
      "step": 8780
    },
    {
      "epoch": 1.9396447092574203,
      "grad_norm": 60.75,
      "learning_rate": 2.514979341643131e-08,
      "loss": 2.2305,
      "mean_token_accuracy": 0.968778133392334,
      "num_tokens": 1012294422.0,
      "step": 8790
    },
    {
      "epoch": 1.9418514840560521,
      "grad_norm": 53.25,
      "learning_rate": 2.3355372883093197e-08,
      "loss": 2.0584,
      "mean_token_accuracy": 0.972294670343399,
      "num_tokens": 1013435222.0,
      "step": 8800
    },
    {
      "epoch": 1.944058258854684,
      "grad_norm": 43.25,
      "learning_rate": 2.162720901754234e-08,
      "loss": 2.03,
      "mean_token_accuracy": 0.9717721834778785,
      "num_tokens": 1014598338.0,
      "step": 8810
    },
    {
      "epoch": 1.9462650336533156,
      "grad_norm": 104.5,
      "learning_rate": 1.996532482772595e-08,
      "loss": 1.9996,
      "mean_token_accuracy": 0.9727108582854271,
      "num_tokens": 1015761488.0,
      "step": 8820
    },
    {
      "epoch": 1.9484718084519475,
      "grad_norm": 45.25,
      "learning_rate": 1.8369742439175997e-08,
      "loss": 2.0988,
      "mean_token_accuracy": 0.9703604876995087,
      "num_tokens": 1016880438.0,
      "step": 8830
    },
    {
      "epoch": 1.9506785832505793,
      "grad_norm": 55.0,
      "learning_rate": 1.6840483094713867e-08,
      "loss": 2.193,
      "mean_token_accuracy": 0.9703435808420181,
      "num_tokens": 1018040918.0,
      "step": 8840
    },
    {
      "epoch": 1.952885358049211,
      "grad_norm": 29.75,
      "learning_rate": 1.5377567154167274e-08,
      "loss": 2.0238,
      "mean_token_accuracy": 0.974012142419815,
      "num_tokens": 1019209080.0,
      "step": 8850
    },
    {
      "epoch": 1.955092132847843,
      "grad_norm": 46.25,
      "learning_rate": 1.3981014094099354e-08,
      "loss": 2.1487,
      "mean_token_accuracy": 0.9714743450284005,
      "num_tokens": 1020352084.0,
      "step": 8860
    },
    {
      "epoch": 1.9572989076464746,
      "grad_norm": 34.0,
      "learning_rate": 1.2650842507550554e-08,
      "loss": 2.0875,
      "mean_token_accuracy": 0.972684046626091,
      "num_tokens": 1021497976.0,
      "step": 8870
    },
    {
      "epoch": 1.9595056824451065,
      "grad_norm": 64.5,
      "learning_rate": 1.138707010378992e-08,
      "loss": 2.0831,
      "mean_token_accuracy": 0.9724696770310401,
      "num_tokens": 1022655116.0,
      "step": 8880
    },
    {
      "epoch": 1.9617124572437383,
      "grad_norm": 88.5,
      "learning_rate": 1.0189713708078086e-08,
      "loss": 2.0295,
      "mean_token_accuracy": 0.9726877480745315,
      "num_tokens": 1023814495.0,
      "step": 8890
    },
    {
      "epoch": 1.96391923204237,
      "grad_norm": 73.5,
      "learning_rate": 9.058789261446876e-09,
      "loss": 2.1253,
      "mean_token_accuracy": 0.9692231133580208,
      "num_tokens": 1024958911.0,
      "step": 8900
    },
    {
      "epoch": 1.966126006841002,
      "grad_norm": 52.75,
      "learning_rate": 7.994311820482825e-09,
      "loss": 1.9933,
      "mean_token_accuracy": 0.9737365961074829,
      "num_tokens": 1026100278.0,
      "step": 8910
    },
    {
      "epoch": 1.9683327816396337,
      "grad_norm": 33.5,
      "learning_rate": 6.996295557131216e-09,
      "loss": 1.9095,
      "mean_token_accuracy": 0.9748351275920868,
      "num_tokens": 1027251930.0,
      "step": 8920
    },
    {
      "epoch": 1.9705395564382655,
      "grad_norm": 28.875,
      "learning_rate": 6.0647537585017956e-09,
      "loss": 1.9787,
      "mean_token_accuracy": 0.9752794340252876,
      "num_tokens": 1028405074.0,
      "step": 8930
    },
    {
      "epoch": 1.9727463312368974,
      "grad_norm": 56.75,
      "learning_rate": 5.199698826697796e-09,
      "loss": 2.2834,
      "mean_token_accuracy": 0.9668238922953606,
      "num_tokens": 1029561237.0,
      "step": 8940
    },
    {
      "epoch": 1.974953106035529,
      "grad_norm": 53.5,
      "learning_rate": 4.401142278647186e-09,
      "loss": 2.145,
      "mean_token_accuracy": 0.9706821337342262,
      "num_tokens": 1030694833.0,
      "step": 8950
    },
    {
      "epoch": 1.9771598808341608,
      "grad_norm": 40.5,
      "learning_rate": 3.669094745950008e-09,
      "loss": 2.1062,
      "mean_token_accuracy": 0.9721989169716835,
      "num_tokens": 1031855806.0,
      "step": 8960
    },
    {
      "epoch": 1.9793666556327927,
      "grad_norm": 44.25,
      "learning_rate": 3.003565974736833e-09,
      "loss": 2.1098,
      "mean_token_accuracy": 0.9703268200159073,
      "num_tokens": 1033016720.0,
      "step": 8970
    },
    {
      "epoch": 1.9815734304314243,
      "grad_norm": 33.0,
      "learning_rate": 2.404564825539968e-09,
      "loss": 2.1513,
      "mean_token_accuracy": 0.9720895797014236,
      "num_tokens": 1034169444.0,
      "step": 8980
    },
    {
      "epoch": 1.9837802052300564,
      "grad_norm": 44.0,
      "learning_rate": 1.8720992731741104e-09,
      "loss": 1.9031,
      "mean_token_accuracy": 0.9733749136328698,
      "num_tokens": 1035314307.0,
      "step": 8990
    },
    {
      "epoch": 1.985986980028688,
      "grad_norm": 31.0,
      "learning_rate": 1.406176406631432e-09,
      "loss": 2.1511,
      "mean_token_accuracy": 0.9715326592326164,
      "num_tokens": 1036476142.0,
      "step": 9000
    },
    {
      "epoch": 1.9881937548273199,
      "grad_norm": 46.5,
      "learning_rate": 1.0068024289860978e-09,
      "loss": 2.112,
      "mean_token_accuracy": 0.9728882282972335,
      "num_tokens": 1037615528.0,
      "step": 9010
    },
    {
      "epoch": 1.9904005296259517,
      "grad_norm": 41.5,
      "learning_rate": 6.739826573121111e-10,
      "loss": 2.1051,
      "mean_token_accuracy": 0.9704681783914566,
      "num_tokens": 1038763476.0,
      "step": 9020
    },
    {
      "epoch": 1.9926073044245833,
      "grad_norm": 42.5,
      "learning_rate": 4.0772152261336906e-10,
      "loss": 2.1258,
      "mean_token_accuracy": 0.971473716199398,
      "num_tokens": 1039917315.0,
      "step": 9030
    },
    {
      "epoch": 1.9948140792232154,
      "grad_norm": 48.0,
      "learning_rate": 2.080225697631555e-10,
      "loss": 2.2201,
      "mean_token_accuracy": 0.969491545855999,
      "num_tokens": 1041047624.0,
      "step": 9040
    },
    {
      "epoch": 1.997020854021847,
      "grad_norm": 62.75,
      "learning_rate": 7.48884574575115e-11,
      "loss": 2.1103,
      "mean_token_accuracy": 0.9706789389252662,
      "num_tokens": 1042193833.0,
      "step": 9050
    },
    {
      "epoch": 1.9992276288204789,
      "grad_norm": 41.25,
      "learning_rate": 8.320958180818572e-12,
      "loss": 2.2199,
      "mean_token_accuracy": 0.9687318444252014,
      "num_tokens": 1043350004.0,
      "step": 9060
    }
  ],
  "logging_steps": 10,
  "max_steps": 9064,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3917940804985815e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}