{
  "best_global_step": 200,
  "best_metric": 0.11372174322605133,
  "best_model_checkpoint": "saves/lora/mistral-7b-instruct/train_copa_1745950331/checkpoint-200",
  "epoch": 444.44444444444446,
  "eval_steps": 200,
  "global_step": 40000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 4.12986421585083,
      "learning_rate": 4.999999876629946e-05,
      "loss": 0.3536,
      "num_input_tokens_seen": 1392,
      "step": 5
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.2044599056243896,
      "learning_rate": 4.999999375439123e-05,
      "loss": 0.1388,
      "num_input_tokens_seen": 2800,
      "step": 10
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.8995859026908875,
      "learning_rate": 4.9999984887169785e-05,
      "loss": 0.247,
      "num_input_tokens_seen": 4224,
      "step": 15
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.08357473462820053,
      "learning_rate": 4.9999972164636506e-05,
      "loss": 0.2303,
      "num_input_tokens_seen": 5648,
      "step": 20
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.33392706513404846,
      "learning_rate": 4.999995558679334e-05,
      "loss": 0.0298,
      "num_input_tokens_seen": 7040,
      "step": 25
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 9.216818809509277,
      "learning_rate": 4.999993515364287e-05,
      "loss": 0.1076,
      "num_input_tokens_seen": 8432,
      "step": 30
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 32.53804016113281,
      "learning_rate": 4.999991086518822e-05,
      "loss": 0.1874,
      "num_input_tokens_seen": 9840,
      "step": 35
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.006262697745114565,
      "learning_rate": 4.999988272143315e-05,
      "loss": 0.0114,
      "num_input_tokens_seen": 11200,
      "step": 40
    },
    {
      "epoch": 0.5,
      "grad_norm": 52.94791793823242,
      "learning_rate": 4.999985072238199e-05,
      "loss": 0.4715,
      "num_input_tokens_seen": 12640,
      "step": 45
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 13.805788040161133,
      "learning_rate": 4.999981486803969e-05,
      "loss": 0.4279,
      "num_input_tokens_seen": 14064,
      "step": 50
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 1.5784074068069458,
      "learning_rate": 4.999977515841176e-05,
      "loss": 0.0883,
      "num_input_tokens_seen": 15488,
      "step": 55
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 34.086875915527344,
      "learning_rate": 4.9999731593504344e-05,
      "loss": 0.1077,
      "num_input_tokens_seen": 16896,
      "step": 60
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 15.348000526428223,
      "learning_rate": 4.999968417332415e-05,
      "loss": 0.1558,
      "num_input_tokens_seen": 18336,
      "step": 65
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 7.811664581298828,
      "learning_rate": 4.999963289787848e-05,
      "loss": 0.0742,
      "num_input_tokens_seen": 19760,
      "step": 70
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.1912801265716553,
      "learning_rate": 4.999957776717526e-05,
      "loss": 0.1122,
      "num_input_tokens_seen": 21136,
      "step": 75
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.009184256196022034,
      "learning_rate": 4.9999518781222984e-05,
      "loss": 0.2608,
      "num_input_tokens_seen": 22560,
      "step": 80
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.09792476147413254,
      "learning_rate": 4.9999455940030746e-05,
      "loss": 0.0559,
      "num_input_tokens_seen": 23936,
      "step": 85
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1140887439250946,
      "learning_rate": 4.999938924360824e-05,
      "loss": 0.2861,
      "num_input_tokens_seen": 25296,
      "step": 90
    },
    {
      "epoch": 1.0555555555555556,
      "grad_norm": 0.1629357486963272,
      "learning_rate": 4.999931869196575e-05,
      "loss": 0.0234,
      "num_input_tokens_seen": 26704,
      "step": 95
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2761296033859253,
      "learning_rate": 4.999924428511416e-05,
      "loss": 0.0059,
      "num_input_tokens_seen": 28080,
      "step": 100
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 14.430259704589844,
      "learning_rate": 4.999916602306494e-05,
      "loss": 0.0055,
      "num_input_tokens_seen": 29472,
      "step": 105
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.006240399554371834,
      "learning_rate": 4.999908390583016e-05,
      "loss": 0.0002,
      "num_input_tokens_seen": 30880,
      "step": 110
    },
    {
      "epoch": 1.2777777777777777,
      "grad_norm": 0.0032748342491686344,
      "learning_rate": 4.999899793342247e-05,
      "loss": 0.0032,
      "num_input_tokens_seen": 32272,
      "step": 115
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.02218768373131752,
      "learning_rate": 4.999890810585516e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 33632,
      "step": 120
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 0.0010601389221847057,
      "learning_rate": 4.999881442314206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 35072,
      "step": 125
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.29845288395881653,
      "learning_rate": 4.9998716885297617e-05,
      "loss": 0.049,
      "num_input_tokens_seen": 36528,
      "step": 130
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.0007384298951365054,
      "learning_rate": 4.999861549233688e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 37936,
      "step": 135
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.0004643955617211759,
      "learning_rate": 4.999851024427548e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 39328,
      "step": 140
    },
    {
      "epoch": 1.6111111111111112,
      "grad_norm": 0.003859361167997122,
      "learning_rate": 4.999840114112965e-05,
      "loss": 0.1647,
      "num_input_tokens_seen": 40752,
      "step": 145
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.14379090070724487,
      "learning_rate": 4.999828818291621e-05,
      "loss": 0.0839,
      "num_input_tokens_seen": 42112,
      "step": 150
    },
    {
      "epoch": 1.7222222222222223,
      "grad_norm": 2.5364973545074463,
      "learning_rate": 4.999817136965259e-05,
      "loss": 0.0029,
      "num_input_tokens_seen": 43504,
      "step": 155
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.012062950059771538,
      "learning_rate": 4.9998050701356794e-05,
      "loss": 0.0006,
      "num_input_tokens_seen": 44864,
      "step": 160
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 0.01023898646235466,
      "learning_rate": 4.999792617804744e-05,
      "loss": 0.0036,
      "num_input_tokens_seen": 46224,
      "step": 165
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.16165591776371002,
      "learning_rate": 4.9997797799743724e-05,
      "loss": 0.0004,
      "num_input_tokens_seen": 47584,
      "step": 170
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 33.479393005371094,
      "learning_rate": 4.999766556646545e-05,
      "loss": 0.0768,
      "num_input_tokens_seen": 49008,
      "step": 175
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0068855793215334415,
      "learning_rate": 4.9997529478232996e-05,
      "loss": 0.0416,
      "num_input_tokens_seen": 50416,
      "step": 180
    },
    {
      "epoch": 2.0555555555555554,
      "grad_norm": 0.0068300021812319756,
      "learning_rate": 4.9997389535067365e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 51840,
      "step": 185
    },
    {
      "epoch": 2.111111111111111,
      "grad_norm": 0.001452439115382731,
      "learning_rate": 4.999724573699012e-05,
      "loss": 0.045,
      "num_input_tokens_seen": 53216,
      "step": 190
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 0.0013135751942172647,
      "learning_rate": 4.9997098084023457e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 54624,
      "step": 195
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.006432564929127693,
      "learning_rate": 4.999694657619013e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 56064,
      "step": 200
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 0.11372174322605133,
      "eval_runtime": 1.3102,
      "eval_samples_per_second": 30.53,
      "eval_steps_per_second": 15.265,
      "num_input_tokens_seen": 56064,
      "step": 200
    },
    {
      "epoch": 2.2777777777777777,
      "grad_norm": 2.240823268890381,
      "learning_rate": 4.999679121351352e-05,
      "loss": 0.0012,
      "num_input_tokens_seen": 57472,
      "step": 205
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.0026429700665175915,
      "learning_rate": 4.9996631996017565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 58800,
      "step": 210
    },
    {
      "epoch": 2.388888888888889,
      "grad_norm": 0.0009138459572568536,
      "learning_rate": 4.9996468923726835e-05,
      "loss": 0.0001,
      "num_input_tokens_seen": 60160,
      "step": 215
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 0.0014732031850144267,
      "learning_rate": 4.999630199666647e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 61520,
      "step": 220
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.0013888808898627758,
      "learning_rate": 4.999613121486222e-05,
      "loss": 0.0013,
      "num_input_tokens_seen": 62944,
      "step": 225
    },
    {
      "epoch": 2.5555555555555554,
      "grad_norm": 0.0006369794136844575,
      "learning_rate": 4.999595657834041e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 64336,
      "step": 230
    },
    {
      "epoch": 2.611111111111111,
      "grad_norm": 0.001021548523567617,
      "learning_rate": 4.999577808712798e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 65760,
      "step": 235
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.0016283011063933372,
      "learning_rate": 4.999559574125244e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 67168,
      "step": 240
    },
    {
      "epoch": 2.7222222222222223,
      "grad_norm": 0.006349765695631504,
      "learning_rate": 4.9995409540741934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 68592,
      "step": 245
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.010487156920135021,
      "learning_rate": 4.999521948562516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 70000,
      "step": 250
    },
    {
      "epoch": 2.8333333333333335,
      "grad_norm": 0.0005248455563560128,
      "learning_rate": 4.999502557593143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 71440,
      "step": 255
    },
    {
      "epoch": 2.888888888888889,
      "grad_norm": 0.0009344802820123732,
      "learning_rate": 4.999482781169066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 72880,
      "step": 260
    },
    {
      "epoch": 2.9444444444444446,
      "grad_norm": 0.0004173697088845074,
      "learning_rate": 4.9994626192933324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 74320,
      "step": 265
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0003769329923670739,
      "learning_rate": 4.999442071969054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 75696,
      "step": 270
    },
    {
      "epoch": 3.0555555555555554,
      "grad_norm": 0.0008351559517905116,
      "learning_rate": 4.999421139199397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 77104,
      "step": 275
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 0.0003571281849872321,
      "learning_rate": 4.999399820987592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 78576,
      "step": 280
    },
    {
      "epoch": 3.1666666666666665,
      "grad_norm": 0.00547214737161994,
      "learning_rate": 4.999378117336924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 79984,
      "step": 285
    },
    {
      "epoch": 3.2222222222222223,
      "grad_norm": 0.00019385218911338598,
      "learning_rate": 4.9993560282507415e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 81392,
      "step": 290
    },
    {
      "epoch": 3.2777777777777777,
      "grad_norm": 0.0004656127421185374,
      "learning_rate": 4.9993335537324495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 82752,
      "step": 295
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.005983070004731417,
      "learning_rate": 4.999310693785516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 84176,
      "step": 300
    },
    {
      "epoch": 3.388888888888889,
      "grad_norm": 0.00044840789632871747,
      "learning_rate": 4.9992874484134653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 85584,
      "step": 305
    },
    {
      "epoch": 3.4444444444444446,
      "grad_norm": 0.000323506974382326,
      "learning_rate": 4.999263817619882e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 86976,
      "step": 310
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.000322989042615518,
      "learning_rate": 4.9992398014084105e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 88336,
      "step": 315
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.0027159282471984625,
      "learning_rate": 4.999215399782754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 89744,
      "step": 320
    },
    {
      "epoch": 3.611111111111111,
      "grad_norm": 0.0005186090129427612,
      "learning_rate": 4.999190612746675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 91152,
      "step": 325
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.00021672050934284925,
      "learning_rate": 4.999165440303998e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 92576,
      "step": 330
    },
    {
      "epoch": 3.7222222222222223,
      "grad_norm": 0.0002868769224733114,
      "learning_rate": 4.999139882458603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 93952,
      "step": 335
    },
    {
      "epoch": 3.7777777777777777,
      "grad_norm": 0.0002535161911509931,
      "learning_rate": 4.9991139392144314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 95376,
      "step": 340
    },
    {
      "epoch": 3.8333333333333335,
      "grad_norm": 0.0004679118865169585,
      "learning_rate": 4.999087610575485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 96800,
      "step": 345
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.00017252587713301182,
      "learning_rate": 4.999060896545824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 98192,
      "step": 350
    },
    {
      "epoch": 3.9444444444444446,
      "grad_norm": 0.00024268293054774404,
      "learning_rate": 4.999033797129568e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 99568,
      "step": 355
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0002193184627685696,
      "learning_rate": 4.999006312330894e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 100928,
      "step": 360
    },
    {
      "epoch": 4.055555555555555,
      "grad_norm": 0.0002533817896619439,
      "learning_rate": 4.998978442154043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 102368,
      "step": 365
    },
    {
      "epoch": 4.111111111111111,
      "grad_norm": 0.002154052024707198,
      "learning_rate": 4.9989501866033125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 103760,
      "step": 370
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 0.0002282343339174986,
      "learning_rate": 4.998921545683059e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 105120,
      "step": 375
    },
    {
      "epoch": 4.222222222222222,
      "grad_norm": 0.0003028937499038875,
      "learning_rate": 4.9988925193976996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 106512,
      "step": 380
    },
    {
      "epoch": 4.277777777777778,
      "grad_norm": 0.005751729477196932,
      "learning_rate": 4.998863107751711e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 107888,
      "step": 385
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 0.00012344223796389997,
      "learning_rate": 4.998833310749629e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 109312,
      "step": 390
    },
    {
      "epoch": 4.388888888888889,
      "grad_norm": 0.0009078117436729372,
      "learning_rate": 4.998803128396047e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 110688,
      "step": 395
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.00015476260159630328,
      "learning_rate": 4.9987725606956215e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 112064,
      "step": 400
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 0.15980732440948486,
      "eval_runtime": 1.3078,
      "eval_samples_per_second": 30.585,
      "eval_steps_per_second": 15.292,
      "num_input_tokens_seen": 112064,
      "step": 400
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.0036649624817073345,
      "learning_rate": 4.998741607653066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 113456,
      "step": 405
    },
    {
      "epoch": 4.555555555555555,
      "grad_norm": 0.0002551766228862107,
      "learning_rate": 4.9987102692731523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 114864,
      "step": 410
    },
    {
      "epoch": 4.611111111111111,
      "grad_norm": 0.0001745289337122813,
      "learning_rate": 4.9986785455607157e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 116224,
      "step": 415
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.0001067143602995202,
      "learning_rate": 4.9986464365206456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 117664,
      "step": 420
    },
    {
      "epoch": 4.722222222222222,
      "grad_norm": 0.00026923822588287294,
      "learning_rate": 4.9986139421578956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 119056,
      "step": 425
    },
    {
      "epoch": 4.777777777777778,
      "grad_norm": 0.00011671226820908487,
      "learning_rate": 4.998581062477477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 120480,
      "step": 430
    },
    {
      "epoch": 4.833333333333333,
      "grad_norm": 9.660539944889024e-05,
      "learning_rate": 4.998547797484458e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 121920,
      "step": 435
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 0.00016510998830199242,
      "learning_rate": 4.9985141471839706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 123328,
      "step": 440
    },
    {
      "epoch": 4.944444444444445,
      "grad_norm": 0.00011291720875306055,
      "learning_rate": 4.998480111581203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 124704,
      "step": 445
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.0001870635460363701,
      "learning_rate": 4.998445690681405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 126128,
      "step": 450
    },
    {
      "epoch": 5.055555555555555,
      "grad_norm": 0.0011391888838261366,
      "learning_rate": 4.9984108844898834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 127488,
      "step": 455
    },
    {
      "epoch": 5.111111111111111,
      "grad_norm": 0.00016768986824899912,
      "learning_rate": 4.9983756930120076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 128896,
      "step": 460
    },
    {
      "epoch": 5.166666666666667,
      "grad_norm": 0.0001046436300384812,
      "learning_rate": 4.9983401162532025e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 130320,
      "step": 465
    },
    {
      "epoch": 5.222222222222222,
      "grad_norm": 0.0003071317041758448,
      "learning_rate": 4.998304154218955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 131680,
      "step": 470
    },
    {
      "epoch": 5.277777777777778,
      "grad_norm": 0.0001632221828913316,
      "learning_rate": 4.998267806914812e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 133088,
      "step": 475
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 9.266538836527616e-05,
      "learning_rate": 4.998231074346378e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 134464,
      "step": 480
    },
    {
      "epoch": 5.388888888888889,
      "grad_norm": 0.00019117689225822687,
      "learning_rate": 4.998193956519317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 135952,
      "step": 485
    },
    {
      "epoch": 5.444444444444445,
      "grad_norm": 0.00036532190279103816,
      "learning_rate": 4.9981564534393545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 137344,
      "step": 490
    },
    {
      "epoch": 5.5,
      "grad_norm": 9.905063052428886e-05,
      "learning_rate": 4.998118565112272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 138720,
      "step": 495
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.00011724106298061088,
      "learning_rate": 4.998080291543914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 140128,
      "step": 500
    },
    {
      "epoch": 5.611111111111111,
      "grad_norm": 8.477746450807899e-05,
      "learning_rate": 4.9980416327401826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 141520,
      "step": 505
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 0.00011712034756783396,
      "learning_rate": 4.998002588707038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 142944,
      "step": 510
    },
    {
      "epoch": 5.722222222222222,
      "grad_norm": 7.292597729247063e-05,
      "learning_rate": 4.997963159450503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 144400,
      "step": 515
    },
    {
      "epoch": 5.777777777777778,
      "grad_norm": 0.00010354100231779739,
      "learning_rate": 4.9979233449766575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 145776,
      "step": 520
    },
    {
      "epoch": 5.833333333333333,
      "grad_norm": 0.00015706689737271518,
      "learning_rate": 4.997883145291641e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 147152,
      "step": 525
    },
    {
      "epoch": 5.888888888888889,
      "grad_norm": 0.00010531899897614494,
      "learning_rate": 4.9978425604016536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 148544,
      "step": 530
    },
    {
      "epoch": 5.944444444444445,
      "grad_norm": 9.393637446919456e-05,
      "learning_rate": 4.9978015903129536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 149904,
      "step": 535
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00011471439938759431,
      "learning_rate": 4.997760235031859e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 151296,
      "step": 540
    },
    {
      "epoch": 6.055555555555555,
      "grad_norm": 0.00010144519910681993,
      "learning_rate": 4.9977184945647473e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 152704,
      "step": 545
    },
    {
      "epoch": 6.111111111111111,
      "grad_norm": 0.00018205970991402864,
      "learning_rate": 4.997676368918055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 154112,
      "step": 550
    },
    {
      "epoch": 6.166666666666667,
      "grad_norm": 0.00013052103167865425,
      "learning_rate": 4.9976338580982794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 155504,
      "step": 555
    },
    {
      "epoch": 6.222222222222222,
      "grad_norm": 0.0014396576443687081,
      "learning_rate": 4.9975909621119755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 156928,
      "step": 560
    },
    {
      "epoch": 6.277777777777778,
      "grad_norm": 7.525581168010831e-05,
      "learning_rate": 4.997547680965758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 158368,
      "step": 565
    },
    {
      "epoch": 6.333333333333333,
      "grad_norm": 0.0001333229010924697,
      "learning_rate": 4.997504014666302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 159776,
      "step": 570
    },
    {
      "epoch": 6.388888888888889,
      "grad_norm": 0.00010636622027959675,
      "learning_rate": 4.997459963220342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 161136,
      "step": 575
    },
    {
      "epoch": 6.444444444444445,
      "grad_norm": 9.36347569222562e-05,
      "learning_rate": 4.997415526634671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 162528,
      "step": 580
    },
    {
      "epoch": 6.5,
      "grad_norm": 0.00010028990072896704,
      "learning_rate": 4.99737070491614e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 163904,
      "step": 585
    },
    {
      "epoch": 6.555555555555555,
      "grad_norm": 0.0016975256148725748,
      "learning_rate": 4.997325498071663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 165312,
      "step": 590
    },
    {
      "epoch": 6.611111111111111,
      "grad_norm": 0.0001009727202472277,
      "learning_rate": 4.997279906108211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 166688,
      "step": 595
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 8.731285925023258e-05,
      "learning_rate": 4.9972339290328155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 168096,
      "step": 600
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 0.16979970037937164,
      "eval_runtime": 1.3164,
      "eval_samples_per_second": 30.385,
      "eval_steps_per_second": 15.193,
      "num_input_tokens_seen": 168096,
      "step": 600
    },
    {
      "epoch": 6.722222222222222,
      "grad_norm": 5.239329766482115e-05,
      "learning_rate": 4.9971875668525646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 169488,
      "step": 605
    },
    {
      "epoch": 6.777777777777778,
      "grad_norm": 0.0009223901433870196,
      "learning_rate": 4.997140819574609e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 170880,
      "step": 610
    },
    {
      "epoch": 6.833333333333333,
      "grad_norm": 0.0005437728832475841,
      "learning_rate": 4.997093687206159e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 172256,
      "step": 615
    },
    {
      "epoch": 6.888888888888889,
      "grad_norm": 8.02566937636584e-05,
      "learning_rate": 4.997046169754482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 173664,
      "step": 620
    },
    {
      "epoch": 6.944444444444445,
      "grad_norm": 7.4571325967554e-05,
      "learning_rate": 4.996998267226905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 175040,
      "step": 625
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.00011629416258074343,
      "learning_rate": 4.996949979630817e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 176416,
      "step": 630
    },
    {
      "epoch": 7.055555555555555,
      "grad_norm": 0.00010985069820890203,
      "learning_rate": 4.996901306973663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 177840,
      "step": 635
    },
    {
      "epoch": 7.111111111111111,
      "grad_norm": 6.207582919159904e-05,
      "learning_rate": 4.996852249262949e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 179232,
      "step": 640
    },
    {
      "epoch": 7.166666666666667,
      "grad_norm": 8.802345109870657e-05,
      "learning_rate": 4.996802806506241e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 180608,
      "step": 645
    },
    {
      "epoch": 7.222222222222222,
      "grad_norm": 7.144174014683813e-05,
      "learning_rate": 4.996752978711164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 182032,
      "step": 650
    },
    {
      "epoch": 7.277777777777778,
      "grad_norm": 0.0003288887091912329,
      "learning_rate": 4.996702765885401e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 183424,
      "step": 655
    },
    {
      "epoch": 7.333333333333333,
      "grad_norm": 0.0002480756083969027,
      "learning_rate": 4.9966521680366964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 184816,
      "step": 660
    },
    {
      "epoch": 7.388888888888889,
      "grad_norm": 5.048919047112577e-05,
      "learning_rate": 4.9966011851728524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 186224,
      "step": 665
    },
    {
      "epoch": 7.444444444444445,
      "grad_norm": 4.1027240513358265e-05,
      "learning_rate": 4.996549817301731e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 187616,
      "step": 670
    },
    {
      "epoch": 7.5,
      "grad_norm": 5.799326390842907e-05,
      "learning_rate": 4.9964980644312544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 189008,
      "step": 675
    },
    {
      "epoch": 7.555555555555555,
      "grad_norm": 0.0006506103090941906,
      "learning_rate": 4.996445926569403e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 190416,
      "step": 680
    },
    {
      "epoch": 7.611111111111111,
      "grad_norm": 0.000492508290335536,
      "learning_rate": 4.996393403724218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 191824,
      "step": 685
    },
    {
      "epoch": 7.666666666666667,
      "grad_norm": 4.117953358218074e-05,
      "learning_rate": 4.9963404959037985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 193168,
      "step": 690
    },
    {
      "epoch": 7.722222222222222,
      "grad_norm": 4.776201240019873e-05,
      "learning_rate": 4.996287203116303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 194592,
      "step": 695
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 5.6545843108324334e-05,
      "learning_rate": 4.996233525369951e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 196032,
      "step": 700
    },
    {
      "epoch": 7.833333333333333,
      "grad_norm": 7.186604489106685e-05,
      "learning_rate": 4.99617946267302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 197472,
      "step": 705
    },
    {
      "epoch": 7.888888888888889,
      "grad_norm": 4.405024810694158e-05,
      "learning_rate": 4.996125015033846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 198896,
      "step": 710
    },
    {
      "epoch": 7.944444444444445,
      "grad_norm": 9.149660036200657e-05,
      "learning_rate": 4.996070182460827e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 200272,
      "step": 715
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.3661464335164055e-05,
      "learning_rate": 4.996014964962418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 201680,
      "step": 720
    },
    {
      "epoch": 8.055555555555555,
      "grad_norm": 0.0014746884116902947,
      "learning_rate": 4.9959593625471344e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 203136,
      "step": 725
    },
    {
      "epoch": 8.11111111111111,
      "grad_norm": 6.509574450319633e-05,
      "learning_rate": 4.995903375223552e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 204496,
      "step": 730
    },
    {
      "epoch": 8.166666666666666,
      "grad_norm": 7.038337935227901e-05,
      "learning_rate": 4.995847003000302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 205904,
      "step": 735
    },
    {
      "epoch": 8.222222222222221,
      "grad_norm": 5.9139845689060166e-05,
      "learning_rate": 4.9957902458860804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 207344,
      "step": 740
    },
    {
      "epoch": 8.277777777777779,
      "grad_norm": 5.6927903642645106e-05,
      "learning_rate": 4.995733103889639e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 208672,
      "step": 745
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 0.0006658190977759659,
      "learning_rate": 4.99567557701979e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 210096,
      "step": 750
    },
    {
      "epoch": 8.38888888888889,
      "grad_norm": 7.715868559898809e-05,
      "learning_rate": 4.995617665285403e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 211488,
      "step": 755
    },
    {
      "epoch": 8.444444444444445,
      "grad_norm": 8.78547944012098e-05,
      "learning_rate": 4.99555936869541e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 212912,
      "step": 760
    },
    {
      "epoch": 8.5,
      "grad_norm": 5.9982430684613064e-05,
      "learning_rate": 4.995500687258803e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 214304,
      "step": 765
    },
    {
      "epoch": 8.555555555555555,
      "grad_norm": 4.556933345156722e-05,
      "learning_rate": 4.995441620984628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 215760,
      "step": 770
    },
    {
      "epoch": 8.61111111111111,
      "grad_norm": 5.738185427617282e-05,
      "learning_rate": 4.995382169881996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 217136,
      "step": 775
    },
    {
      "epoch": 8.666666666666666,
      "grad_norm": 6.194488378241658e-05,
      "learning_rate": 4.9953223339600755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 218512,
      "step": 780
    },
    {
      "epoch": 8.722222222222221,
      "grad_norm": 3.988463504356332e-05,
      "learning_rate": 4.995262113228091e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 219856,
      "step": 785
    },
    {
      "epoch": 8.777777777777779,
      "grad_norm": 6.221572402864695e-05,
      "learning_rate": 4.995201507695332e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 221280,
      "step": 790
    },
    {
      "epoch": 8.833333333333334,
      "grad_norm": 2.9216975235613063e-05,
      "learning_rate": 4.995140517371144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 222688,
      "step": 795
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 4.2091731302207336e-05,
      "learning_rate": 4.995079142264932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 224048,
      "step": 800
    },
    {
      "epoch": 8.88888888888889,
      "eval_loss": 0.1828708052635193,
      "eval_runtime": 1.3274,
      "eval_samples_per_second": 30.133,
      "eval_steps_per_second": 15.067,
      "num_input_tokens_seen": 224048,
      "step": 800
    },
    {
      "epoch": 8.944444444444445,
      "grad_norm": 4.440880729816854e-05,
      "learning_rate": 4.995017382386162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 225456,
      "step": 805
    },
    {
      "epoch": 9.0,
      "grad_norm": 4.260615969542414e-05,
      "learning_rate": 4.994955237744356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 226864,
      "step": 810
    },
    {
      "epoch": 9.055555555555555,
      "grad_norm": 3.081997056142427e-05,
      "learning_rate": 4.994892708349101e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 228256,
      "step": 815
    },
    {
      "epoch": 9.11111111111111,
      "grad_norm": 6.77211137372069e-05,
      "learning_rate": 4.994829794210035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 229680,
      "step": 820
    },
    {
      "epoch": 9.166666666666666,
      "grad_norm": 6.863159069325775e-05,
      "learning_rate": 4.994766495336864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 231024,
      "step": 825
    },
    {
      "epoch": 9.222222222222221,
      "grad_norm": 4.328360955696553e-05,
      "learning_rate": 4.994702811739348e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 232432,
      "step": 830
    },
    {
      "epoch": 9.277777777777779,
      "grad_norm": 4.60708761238493e-05,
      "learning_rate": 4.994638743427308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 233840,
      "step": 835
    },
    {
      "epoch": 9.333333333333334,
      "grad_norm": 3.2570911571383476e-05,
      "learning_rate": 4.994574290410624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 235280,
      "step": 840
    },
    {
      "epoch": 9.38888888888889,
      "grad_norm": 0.00011122846626676619,
      "learning_rate": 4.9945094526992364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 236688,
      "step": 845
    },
    {
      "epoch": 9.444444444444445,
      "grad_norm": 3.737900624400936e-05,
      "learning_rate": 4.994444230303142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 238080,
      "step": 850
    },
    {
      "epoch": 9.5,
      "grad_norm": 7.085297693265602e-05,
      "learning_rate": 4.994378623232402e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 239472,
      "step": 855
    },
    {
      "epoch": 9.555555555555555,
      "grad_norm": 3.512734838295728e-05,
      "learning_rate": 4.99431263149713e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 240896,
      "step": 860
    },
    {
      "epoch": 9.61111111111111,
      "grad_norm": 4.0360871935263276e-05,
      "learning_rate": 4.9942462551075056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 242272,
      "step": 865
    },
    {
      "epoch": 9.666666666666666,
      "grad_norm": 3.323900091345422e-05,
      "learning_rate": 4.994179494073764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 243632,
      "step": 870
    },
    {
      "epoch": 9.722222222222221,
      "grad_norm": 2.6672221792978235e-05,
      "learning_rate": 4.9941123484062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 245008,
      "step": 875
    },
    {
      "epoch": 9.777777777777779,
      "grad_norm": 2.7063124434789643e-05,
      "learning_rate": 4.99404481811517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 246416,
      "step": 880
    },
    {
      "epoch": 9.833333333333334,
      "grad_norm": 3.874051253660582e-05,
      "learning_rate": 4.9939769032110864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 247856,
      "step": 885
    },
    {
      "epoch": 9.88888888888889,
      "grad_norm": 3.2344425562769175e-05,
      "learning_rate": 4.993908603704423e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 249216,
      "step": 890
    },
    {
      "epoch": 9.944444444444445,
      "grad_norm": 0.00036639132304117084,
      "learning_rate": 4.9938399196057126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 250640,
      "step": 895
    },
    {
      "epoch": 10.0,
      "grad_norm": 5.2123643399681896e-05,
      "learning_rate": 4.993770850925547e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 252000,
      "step": 900
    },
    {
      "epoch": 10.055555555555555,
      "grad_norm": 3.012244269484654e-05,
      "learning_rate": 4.993701397674577e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 253440,
      "step": 905
    },
    {
      "epoch": 10.11111111111111,
      "grad_norm": 2.3660379156353883e-05,
      "learning_rate": 4.993631559863515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 254816,
      "step": 910
    },
    {
      "epoch": 10.166666666666666,
      "grad_norm": 4.361174433142878e-05,
      "learning_rate": 4.9935613375031283e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 256240,
      "step": 915
    },
    {
      "epoch": 10.222222222222221,
      "grad_norm": 5.7712844863999635e-05,
      "learning_rate": 4.993490730604248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 257664,
      "step": 920
    },
    {
      "epoch": 10.277777777777779,
      "grad_norm": 2.80544554698281e-05,
      "learning_rate": 4.993419739177761e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 259104,
      "step": 925
    },
    {
      "epoch": 10.333333333333334,
      "grad_norm": 3.0323071769089438e-05,
      "learning_rate": 4.9933483632346164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 260512,
      "step": 930
    },
    {
      "epoch": 10.38888888888889,
      "grad_norm": 3.447167182457633e-05,
      "learning_rate": 4.993276602785821e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 261968,
      "step": 935
    },
    {
      "epoch": 10.444444444444445,
      "grad_norm": 2.0058369045727886e-05,
      "learning_rate": 4.993204457842441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 263360,
      "step": 940
    },
    {
      "epoch": 10.5,
      "grad_norm": 2.8742415452143177e-05,
      "learning_rate": 4.993131928415602e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 264800,
      "step": 945
    },
    {
      "epoch": 10.555555555555555,
      "grad_norm": 3.336052759550512e-05,
      "learning_rate": 4.993059014516489e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 266192,
      "step": 950
    },
    {
      "epoch": 10.61111111111111,
      "grad_norm": 4.77339890494477e-05,
      "learning_rate": 4.9929857161563464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 267600,
      "step": 955
    },
    {
      "epoch": 10.666666666666666,
      "grad_norm": 2.852082070603501e-05,
      "learning_rate": 4.992912033346477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 268960,
      "step": 960
    },
    {
      "epoch": 10.722222222222221,
      "grad_norm": 6.0087892052251846e-05,
      "learning_rate": 4.992837966098245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 270352,
      "step": 965
    },
    {
      "epoch": 10.777777777777779,
      "grad_norm": 2.2876392904436216e-05,
      "learning_rate": 4.992763514423071e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 271728,
      "step": 970
    },
    {
      "epoch": 10.833333333333334,
      "grad_norm": 3.078957524849102e-05,
      "learning_rate": 4.992688678332437e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 273120,
      "step": 975
    },
    {
      "epoch": 10.88888888888889,
      "grad_norm": 4.4325792259769514e-05,
      "learning_rate": 4.992613457837884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 274496,
      "step": 980
    },
    {
      "epoch": 10.944444444444445,
      "grad_norm": 3.1834293622523546e-05,
      "learning_rate": 4.992537852951011e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 275888,
      "step": 985
    },
    {
      "epoch": 11.0,
      "grad_norm": 4.065641405759379e-05,
      "learning_rate": 4.9924618636834785e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 277280,
      "step": 990
    },
    {
      "epoch": 11.055555555555555,
      "grad_norm": 2.596398553578183e-05,
      "learning_rate": 4.9923854900470046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 278656,
      "step": 995
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 2.7446145395515487e-05,
      "learning_rate": 4.992308732053367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 280048,
      "step": 1000
    },
    {
      "epoch": 11.11111111111111,
      "eval_loss": 0.19405324757099152,
      "eval_runtime": 1.2882,
      "eval_samples_per_second": 31.051,
      "eval_steps_per_second": 15.525,
      "num_input_tokens_seen": 280048,
      "step": 1000
    },
    {
      "epoch": 11.166666666666666,
      "grad_norm": 2.5758272386156023e-05,
      "learning_rate": 4.992231589714402e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 281488,
      "step": 1005
    },
    {
      "epoch": 11.222222222222221,
      "grad_norm": 2.6770645490614697e-05,
      "learning_rate": 4.992154063042007e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 282880,
      "step": 1010
    },
    {
      "epoch": 11.277777777777779,
      "grad_norm": 2.8651087632169947e-05,
      "learning_rate": 4.992076152048136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 284272,
      "step": 1015
    },
    {
      "epoch": 11.333333333333334,
      "grad_norm": 2.3185648387880065e-05,
      "learning_rate": 4.991997856744807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 285664,
      "step": 1020
    },
    {
      "epoch": 11.38888888888889,
      "grad_norm": 2.440629032207653e-05,
      "learning_rate": 4.9919191771440905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 287040,
      "step": 1025
    },
    {
      "epoch": 11.444444444444445,
      "grad_norm": 3.39917532983236e-05,
      "learning_rate": 4.991840113258122e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 288400,
      "step": 1030
    },
    {
      "epoch": 11.5,
      "grad_norm": 2.297773608006537e-05,
      "learning_rate": 4.9917606650990933e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 289792,
      "step": 1035
    },
    {
      "epoch": 11.555555555555555,
      "grad_norm": 2.8581638616742566e-05,
      "learning_rate": 4.9916808326792566e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 291168,
      "step": 1040
    },
    {
      "epoch": 11.61111111111111,
      "grad_norm": 3.585240847314708e-05,
      "learning_rate": 4.9916006160109235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 292528,
      "step": 1045
    },
    {
      "epoch": 11.666666666666666,
      "grad_norm": 5.0540893425932154e-05,
      "learning_rate": 4.991520015106464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 293968,
      "step": 1050
    },
    {
      "epoch": 11.722222222222221,
      "grad_norm": 2.0655221305787563e-05,
      "learning_rate": 4.991439029978308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 295344,
      "step": 1055
    },
    {
      "epoch": 11.777777777777779,
      "grad_norm": 2.755809146037791e-05,
      "learning_rate": 4.9913576606389434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 296736,
      "step": 1060
    },
    {
      "epoch": 11.833333333333334,
      "grad_norm": 1.8386343072052114e-05,
      "learning_rate": 4.991275907100919e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 298128,
      "step": 1065
    },
    {
      "epoch": 11.88888888888889,
      "grad_norm": 2.4101560484268703e-05,
      "learning_rate": 4.9911937693768434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 299600,
      "step": 1070
    },
    {
      "epoch": 11.944444444444445,
      "grad_norm": 2.231023790955078e-05,
      "learning_rate": 4.991111247479382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 300992,
      "step": 1075
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.6504674931638874e-05,
      "learning_rate": 4.9910283414212605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 302352,
      "step": 1080
    },
    {
      "epoch": 12.055555555555555,
      "grad_norm": 1.9772263840422966e-05,
      "learning_rate": 4.990945051215265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 303760,
      "step": 1085
    },
    {
      "epoch": 12.11111111111111,
      "grad_norm": 1.3240562111604959e-05,
      "learning_rate": 4.99086137687424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 305120,
      "step": 1090
    },
    {
      "epoch": 12.166666666666666,
      "grad_norm": 3.180370185873471e-05,
      "learning_rate": 4.9907773184110874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 306544,
      "step": 1095
    },
    {
      "epoch": 12.222222222222221,
      "grad_norm": 1.808653905754909e-05,
      "learning_rate": 4.9906928758387715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 307968,
      "step": 1100
    },
    {
      "epoch": 12.277777777777779,
      "grad_norm": 1.8848702893592417e-05,
      "learning_rate": 4.9906080491703146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 309360,
      "step": 1105
    },
    {
      "epoch": 12.333333333333334,
      "grad_norm": 0.0002500058908481151,
      "learning_rate": 4.990522838418797e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 310768,
      "step": 1110
    },
    {
      "epoch": 12.38888888888889,
      "grad_norm": 2.260574729007203e-05,
      "learning_rate": 4.9904372435973604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 312160,
      "step": 1115
    },
    {
      "epoch": 12.444444444444445,
      "grad_norm": 2.7936583137488924e-05,
      "learning_rate": 4.990351264719203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 313600,
      "step": 1120
    },
    {
      "epoch": 12.5,
      "grad_norm": 2.4834060241119005e-05,
      "learning_rate": 4.990264901797586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 314976,
      "step": 1125
    },
    {
      "epoch": 12.555555555555555,
      "grad_norm": 1.6862681150087155e-05,
      "learning_rate": 4.990178154845826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 316384,
      "step": 1130
    },
    {
      "epoch": 12.61111111111111,
      "grad_norm": 1.8821661797119305e-05,
      "learning_rate": 4.9900910238773014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 317776,
      "step": 1135
    },
    {
      "epoch": 12.666666666666666,
      "grad_norm": 3.402827132958919e-05,
      "learning_rate": 4.990003508905448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 319136,
      "step": 1140
    },
    {
      "epoch": 12.722222222222221,
      "grad_norm": 0.0001002519711619243,
      "learning_rate": 4.989915609943763e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 320544,
      "step": 1145
    },
    {
      "epoch": 12.777777777777779,
      "grad_norm": 1.957470885827206e-05,
      "learning_rate": 4.9898273270058e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 321936,
      "step": 1150
    },
    {
      "epoch": 12.833333333333334,
      "grad_norm": 2.782708361337427e-05,
      "learning_rate": 4.989738660105174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 323344,
      "step": 1155
    },
    {
      "epoch": 12.88888888888889,
      "grad_norm": 1.1033391274395399e-05,
      "learning_rate": 4.989649609255559e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 324736,
      "step": 1160
    },
    {
      "epoch": 12.944444444444445,
      "grad_norm": 0.00013544985267799348,
      "learning_rate": 4.989560174470687e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 326176,
      "step": 1165
    },
    {
      "epoch": 13.0,
      "grad_norm": 4.8447858716826886e-05,
      "learning_rate": 4.989470355764351e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 327584,
      "step": 1170
    },
    {
      "epoch": 13.055555555555555,
      "grad_norm": 1.5711824744357727e-05,
      "learning_rate": 4.9893801531504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 328992,
      "step": 1175
    },
    {
      "epoch": 13.11111111111111,
      "grad_norm": 1.3920656783739105e-05,
      "learning_rate": 4.9892895666427475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 330384,
      "step": 1180
    },
    {
      "epoch": 13.166666666666666,
      "grad_norm": 0.00030852091731503606,
      "learning_rate": 4.9891985962553606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 331808,
      "step": 1185
    },
    {
      "epoch": 13.222222222222221,
      "grad_norm": 2.537210275477264e-05,
      "learning_rate": 4.989107242002269e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 333184,
      "step": 1190
    },
    {
      "epoch": 13.277777777777779,
      "grad_norm": 2.313690674782265e-05,
      "learning_rate": 4.989015503897561e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 334640,
      "step": 1195
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 2.3533633793704212e-05,
      "learning_rate": 4.988923381955383e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 336032,
      "step": 1200
    },
    {
      "epoch": 13.333333333333334,
      "eval_loss": 0.18756745755672455,
      "eval_runtime": 1.3167,
      "eval_samples_per_second": 30.379,
      "eval_steps_per_second": 15.19,
      "num_input_tokens_seen": 336032,
      "step": 1200
    },
    {
      "epoch": 13.38888888888889,
      "grad_norm": 1.8729178918874823e-05,
      "learning_rate": 4.988830876189942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 337440,
      "step": 1205
    },
    {
      "epoch": 13.444444444444445,
      "grad_norm": 2.594203397165984e-05,
      "learning_rate": 4.988737986615503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 338832,
      "step": 1210
    },
    {
      "epoch": 13.5,
      "grad_norm": 2.2160791559144855e-05,
      "learning_rate": 4.988644713246391e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 340224,
      "step": 1215
    },
    {
      "epoch": 13.555555555555555,
      "grad_norm": 1.696117215033155e-05,
      "learning_rate": 4.988551056096991e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 341584,
      "step": 1220
    },
    {
      "epoch": 13.61111111111111,
      "grad_norm": 1.117551073548384e-05,
      "learning_rate": 4.988457015181743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 342960,
      "step": 1225
    },
    {
      "epoch": 13.666666666666666,
      "grad_norm": 8.331183926202357e-05,
      "learning_rate": 4.988362590515153e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 344400,
      "step": 1230
    },
    {
      "epoch": 13.722222222222221,
      "grad_norm": 0.00011163161252625287,
      "learning_rate": 4.9882677821117805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 345840,
      "step": 1235
    },
    {
      "epoch": 13.777777777777779,
      "grad_norm": 2.947120083263144e-05,
      "learning_rate": 4.988172589986246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 347264,
      "step": 1240
    },
    {
      "epoch": 13.833333333333334,
      "grad_norm": 6.222853699000552e-05,
      "learning_rate": 4.9880770141532304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 348688,
      "step": 1245
    },
    {
      "epoch": 13.88888888888889,
      "grad_norm": 0.00010227476013824344,
      "learning_rate": 4.987981054627472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 350048,
      "step": 1250
    },
    {
      "epoch": 13.944444444444445,
      "grad_norm": 1.7371521607856266e-05,
      "learning_rate": 4.987884711423769e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 351440,
      "step": 1255
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.3236928680271376e-05,
      "learning_rate": 4.9877879845569784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 352848,
      "step": 1260
    },
    {
      "epoch": 14.055555555555555,
      "grad_norm": 2.46555882768007e-05,
      "learning_rate": 4.9876908740420175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 354256,
      "step": 1265
    },
    {
      "epoch": 14.11111111111111,
      "grad_norm": 2.108790613419842e-05,
      "learning_rate": 4.987593379893861e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 355680,
      "step": 1270
    },
    {
      "epoch": 14.166666666666666,
      "grad_norm": 2.250490251753945e-05,
      "learning_rate": 4.987495502127545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 357072,
      "step": 1275
    },
    {
      "epoch": 14.222222222222221,
      "grad_norm": 2.4133054466801696e-05,
      "learning_rate": 4.987397240758162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 358480,
      "step": 1280
    },
    {
      "epoch": 14.277777777777779,
      "grad_norm": 1.1501267181301955e-05,
      "learning_rate": 4.9872985958008664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 359920,
      "step": 1285
    },
    {
      "epoch": 14.333333333333334,
      "grad_norm": 1.446391615900211e-05,
      "learning_rate": 4.987199567270871e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 361360,
      "step": 1290
    },
    {
      "epoch": 14.38888888888889,
      "grad_norm": 2.354309253860265e-05,
      "learning_rate": 4.9871001551834444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 362800,
      "step": 1295
    },
    {
      "epoch": 14.444444444444445,
      "grad_norm": 3.491077950457111e-05,
      "learning_rate": 4.98700035955392e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 364160,
      "step": 1300
    },
    {
      "epoch": 14.5,
      "grad_norm": 1.429550684406422e-05,
      "learning_rate": 4.986900180397686e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 365504,
      "step": 1305
    },
    {
      "epoch": 14.555555555555555,
      "grad_norm": 1.661984424572438e-05,
      "learning_rate": 4.9867996177301926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 366864,
      "step": 1310
    },
    {
      "epoch": 14.61111111111111,
      "grad_norm": 1.3270124327391386e-05,
      "learning_rate": 4.9866986715669464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 368272,
      "step": 1315
    },
    {
      "epoch": 14.666666666666666,
      "grad_norm": 2.312470314791426e-05,
      "learning_rate": 4.9865973419235155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 369680,
      "step": 1320
    },
    {
      "epoch": 14.722222222222221,
      "grad_norm": 1.1135860404465348e-05,
      "learning_rate": 4.986495628815526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 371056,
      "step": 1325
    },
    {
      "epoch": 14.777777777777779,
      "grad_norm": 2.7111147574032657e-05,
      "learning_rate": 4.986393532258663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 372448,
      "step": 1330
    },
    {
      "epoch": 14.833333333333334,
      "grad_norm": 1.4085681868891697e-05,
      "learning_rate": 4.986291052268671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 373824,
      "step": 1335
    },
    {
      "epoch": 14.88888888888889,
      "grad_norm": 2.0297631635912694e-05,
      "learning_rate": 4.986188188861355e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 375232,
      "step": 1340
    },
    {
      "epoch": 14.944444444444445,
      "grad_norm": 1.282524590351386e-05,
      "learning_rate": 4.9860849420525766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 376608,
      "step": 1345
    },
    {
      "epoch": 15.0,
      "grad_norm": 1.2852452528022695e-05,
      "learning_rate": 4.9859813118582575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 378016,
      "step": 1350
    },
    {
      "epoch": 15.055555555555555,
      "grad_norm": 1.9418048395891674e-05,
      "learning_rate": 4.98587729829438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 379440,
      "step": 1355
    },
    {
      "epoch": 15.11111111111111,
      "grad_norm": 1.3427494195639156e-05,
      "learning_rate": 4.985772901376983e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 380864,
      "step": 1360
    },
    {
      "epoch": 15.166666666666666,
      "grad_norm": 1.223575873154914e-05,
      "learning_rate": 4.9856681211221666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 382240,
      "step": 1365
    },
    {
      "epoch": 15.222222222222221,
      "grad_norm": 1.175797024188796e-05,
      "learning_rate": 4.985562957546089e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 383632,
      "step": 1370
    },
    {
      "epoch": 15.277777777777779,
      "grad_norm": 1.540242192277219e-05,
      "learning_rate": 4.9854574106649686e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 384976,
      "step": 1375
    },
    {
      "epoch": 15.333333333333334,
      "grad_norm": 2.259183929709252e-05,
      "learning_rate": 4.985351480495081e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 386384,
      "step": 1380
    },
    {
      "epoch": 15.38888888888889,
      "grad_norm": 9.309734195994679e-06,
      "learning_rate": 4.985245167052762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 387808,
      "step": 1385
    },
    {
      "epoch": 15.444444444444445,
      "grad_norm": 0.00012173367576906458,
      "learning_rate": 4.9851384703544066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 389184,
      "step": 1390
    },
    {
      "epoch": 15.5,
      "grad_norm": 3.0991701351013035e-05,
      "learning_rate": 4.985031390416469e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 390560,
      "step": 1395
    },
    {
      "epoch": 15.555555555555555,
      "grad_norm": 2.3663715182919987e-05,
      "learning_rate": 4.984923927255461e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 392032,
      "step": 1400
    },
    {
      "epoch": 15.555555555555555,
      "eval_loss": 0.17438191175460815,
      "eval_runtime": 1.2976,
      "eval_samples_per_second": 30.827,
      "eval_steps_per_second": 15.413,
      "num_input_tokens_seen": 392032,
      "step": 1400
    },
    {
      "epoch": 15.61111111111111,
      "grad_norm": 1.5550487660220824e-05,
      "learning_rate": 4.984816080887958e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 393456,
      "step": 1405
    },
    {
      "epoch": 15.666666666666666,
      "grad_norm": 1.1220718079130165e-05,
      "learning_rate": 4.9847078513305875e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 394880,
      "step": 1410
    },
    {
      "epoch": 15.722222222222221,
      "grad_norm": 1.1490797078295145e-05,
      "learning_rate": 4.984599238600043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 396272,
      "step": 1415
    },
    {
      "epoch": 15.777777777777779,
      "grad_norm": 1.2670852811424993e-05,
      "learning_rate": 4.9844902427130716e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 397616,
      "step": 1420
    },
    {
      "epoch": 15.833333333333334,
      "grad_norm": 8.266789336630609e-06,
      "learning_rate": 4.984380863686482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 399024,
      "step": 1425
    },
    {
      "epoch": 15.88888888888889,
      "grad_norm": 0.00014388705312740058,
      "learning_rate": 4.984271101537143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 400432,
      "step": 1430
    },
    {
      "epoch": 15.944444444444445,
      "grad_norm": 1.1853881005663425e-05,
      "learning_rate": 4.9841609562819816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 401792,
      "step": 1435
    },
    {
      "epoch": 16.0,
      "grad_norm": 1.5347650332842022e-05,
      "learning_rate": 4.984050427937983e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 403200,
      "step": 1440
    },
    {
      "epoch": 16.055555555555557,
      "grad_norm": 1.1418389476602897e-05,
      "learning_rate": 4.983939516522191e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 404624,
      "step": 1445
    },
    {
      "epoch": 16.11111111111111,
      "grad_norm": 1.1775635357480496e-05,
      "learning_rate": 4.983828222051711e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 405984,
      "step": 1450
    },
    {
      "epoch": 16.166666666666668,
      "grad_norm": 0.00010570139420451596,
      "learning_rate": 4.983716544543705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 407344,
      "step": 1455
    },
    {
      "epoch": 16.22222222222222,
      "grad_norm": 1.413027257513022e-05,
      "learning_rate": 4.983604484015395e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 408768,
      "step": 1460
    },
    {
      "epoch": 16.27777777777778,
      "grad_norm": 3.43346873705741e-05,
      "learning_rate": 4.983492040484064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 410160,
      "step": 1465
    },
    {
      "epoch": 16.333333333333332,
      "grad_norm": 1.7182344890898094e-05,
      "learning_rate": 4.98337921396705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 411616,
      "step": 1470
    },
    {
      "epoch": 16.38888888888889,
      "grad_norm": 1.6277866961900145e-05,
      "learning_rate": 4.983266004481753e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 413008,
      "step": 1475
    },
    {
      "epoch": 16.444444444444443,
      "grad_norm": 1.1532619282661472e-05,
      "learning_rate": 4.9831524120456316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 414384,
      "step": 1480
    },
    {
      "epoch": 16.5,
      "grad_norm": 3.229361755074933e-05,
      "learning_rate": 4.9830384366762026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 415808,
      "step": 1485
    },
    {
      "epoch": 16.555555555555557,
      "grad_norm": 0.0001093542596208863,
      "learning_rate": 4.9829240783910436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 417232,
      "step": 1490
    },
    {
      "epoch": 16.61111111111111,
      "grad_norm": 1.0620502507663332e-05,
      "learning_rate": 4.982809337207789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 418608,
      "step": 1495
    },
    {
      "epoch": 16.666666666666668,
      "grad_norm": 1.1127584002679214e-05,
      "learning_rate": 4.9826942131441337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 420016,
      "step": 1500
    },
    {
      "epoch": 16.72222222222222,
      "grad_norm": 1.1357120456523262e-05,
      "learning_rate": 4.9825787062178315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 421456,
      "step": 1505
    },
    {
      "epoch": 16.77777777777778,
      "grad_norm": 8.056042133830488e-06,
      "learning_rate": 4.9824628164466945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 422816,
      "step": 1510
    },
    {
      "epoch": 16.833333333333332,
      "grad_norm": 9.360472176922485e-06,
      "learning_rate": 4.982346543848595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 424256,
      "step": 1515
    },
    {
      "epoch": 16.88888888888889,
      "grad_norm": 7.214864308480173e-05,
      "learning_rate": 4.9822298884414626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 425648,
      "step": 1520
    },
    {
      "epoch": 16.944444444444443,
      "grad_norm": 1.1933362657146063e-05,
      "learning_rate": 4.982112850243288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 427024,
      "step": 1525
    },
    {
      "epoch": 17.0,
      "grad_norm": 1.527903623355087e-05,
      "learning_rate": 4.98199542927212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 428432,
      "step": 1530
    },
    {
      "epoch": 17.055555555555557,
      "grad_norm": 1.254318340215832e-05,
      "learning_rate": 4.981877625546066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 429840,
      "step": 1535
    },
    {
      "epoch": 17.11111111111111,
      "grad_norm": 1.375853935314808e-05,
      "learning_rate": 4.981759439083293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 431296,
      "step": 1540
    },
    {
      "epoch": 17.166666666666668,
      "grad_norm": 2.086279164359439e-05,
      "learning_rate": 4.981640869902027e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 432704,
      "step": 1545
    },
    {
      "epoch": 17.22222222222222,
      "grad_norm": 0.00016026824596337974,
      "learning_rate": 4.9815219180205517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 434096,
      "step": 1550
    },
    {
      "epoch": 17.27777777777778,
      "grad_norm": 6.766900241927942e-06,
      "learning_rate": 4.9814025834572126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 435488,
      "step": 1555
    },
    {
      "epoch": 17.333333333333332,
      "grad_norm": 1.2325365787546616e-05,
      "learning_rate": 4.981282866230411e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 436864,
      "step": 1560
    },
    {
      "epoch": 17.38888888888889,
      "grad_norm": 1.1929122592846397e-05,
      "learning_rate": 4.981162766358611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 438224,
      "step": 1565
    },
    {
      "epoch": 17.444444444444443,
      "grad_norm": 8.416589116677642e-05,
      "learning_rate": 4.9810422838603316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 439648,
      "step": 1570
    },
    {
      "epoch": 17.5,
      "grad_norm": 8.97952304512728e-06,
      "learning_rate": 4.9809214187541533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 441088,
      "step": 1575
    },
    {
      "epoch": 17.555555555555557,
      "grad_norm": 9.85767474048771e-06,
      "learning_rate": 4.980800171058715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 442496,
      "step": 1580
    },
    {
      "epoch": 17.61111111111111,
      "grad_norm": 1.2903969945909921e-05,
      "learning_rate": 4.980678540792715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 443888,
      "step": 1585
    },
    {
      "epoch": 17.666666666666668,
      "grad_norm": 1.7795046005630866e-05,
      "learning_rate": 4.980556527974909e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 445344,
      "step": 1590
    },
    {
      "epoch": 17.72222222222222,
      "grad_norm": 1.9075165255344473e-05,
      "learning_rate": 4.980434132624114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 446752,
      "step": 1595
    },
    {
      "epoch": 17.77777777777778,
      "grad_norm": 6.619228224735707e-05,
      "learning_rate": 4.980311354759205e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 448128,
      "step": 1600
    },
    {
      "epoch": 17.77777777777778,
      "eval_loss": 0.2256428301334381,
      "eval_runtime": 1.3253,
      "eval_samples_per_second": 30.182,
      "eval_steps_per_second": 15.091,
      "num_input_tokens_seen": 448128,
      "step": 1600
    },
    {
      "epoch": 17.833333333333332,
      "grad_norm": 8.98801317816833e-06,
      "learning_rate": 4.980188194399116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 449520,
      "step": 1605
    },
    {
      "epoch": 17.88888888888889,
      "grad_norm": 1.1664252269838471e-05,
      "learning_rate": 4.9800646515628384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 450896,
      "step": 1610
    },
    {
      "epoch": 17.944444444444443,
      "grad_norm": 8.879203960532323e-06,
      "learning_rate": 4.979940726269426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 452240,
      "step": 1615
    },
    {
      "epoch": 18.0,
      "grad_norm": 1.218364923261106e-05,
      "learning_rate": 4.979816418537988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 453632,
      "step": 1620
    },
    {
      "epoch": 18.055555555555557,
      "grad_norm": 3.5401149943936616e-05,
      "learning_rate": 4.979691728387696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 455040,
      "step": 1625
    },
    {
      "epoch": 18.11111111111111,
      "grad_norm": 8.078999235294759e-05,
      "learning_rate": 4.979566655837776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 456400,
      "step": 1630
    },
    {
      "epoch": 18.166666666666668,
      "grad_norm": 1.3809009033138864e-05,
      "learning_rate": 4.9794412009075184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 457824,
      "step": 1635
    },
    {
      "epoch": 18.22222222222222,
      "grad_norm": 1.0901022506004665e-05,
      "learning_rate": 4.979315363616269e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 459168,
      "step": 1640
    },
    {
      "epoch": 18.27777777777778,
      "grad_norm": 9.455587132833898e-06,
      "learning_rate": 4.979189143983434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 460592,
      "step": 1645
    },
    {
      "epoch": 18.333333333333332,
      "grad_norm": 9.022756785270758e-06,
      "learning_rate": 4.979062542028478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 462048,
      "step": 1650
    },
    {
      "epoch": 18.38888888888889,
      "grad_norm": 9.97610914055258e-06,
      "learning_rate": 4.978935557770923e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 463456,
      "step": 1655
    },
    {
      "epoch": 18.444444444444443,
      "grad_norm": 7.656707566638943e-06,
      "learning_rate": 4.978808191230353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 464832,
      "step": 1660
    },
    {
      "epoch": 18.5,
      "grad_norm": 7.506377642130246e-06,
      "learning_rate": 4.9786804424264085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 466208,
      "step": 1665
    },
    {
      "epoch": 18.555555555555557,
      "grad_norm": 8.589181561546866e-06,
      "learning_rate": 4.978552311378792e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 467552,
      "step": 1670
    },
    {
      "epoch": 18.61111111111111,
      "grad_norm": 6.205269073689124e-06,
      "learning_rate": 4.978423798107261e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 468960,
      "step": 1675
    },
    {
      "epoch": 18.666666666666668,
      "grad_norm": 6.270068752201041e-06,
      "learning_rate": 4.978294902631635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 470352,
      "step": 1680
    },
    {
      "epoch": 18.72222222222222,
      "grad_norm": 1.9594896002672613e-05,
      "learning_rate": 4.9781656249717914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 471728,
      "step": 1685
    },
    {
      "epoch": 18.77777777777778,
      "grad_norm": 9.189858246827498e-06,
      "learning_rate": 4.9780359651476645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 473104,
      "step": 1690
    },
    {
      "epoch": 18.833333333333332,
      "grad_norm": 1.0304534043825697e-05,
      "learning_rate": 4.977905923179251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 474544,
      "step": 1695
    },
    {
      "epoch": 18.88888888888889,
      "grad_norm": 7.1722374741511885e-06,
      "learning_rate": 4.977775499086606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 475968,
      "step": 1700
    },
    {
      "epoch": 18.944444444444443,
      "grad_norm": 6.335387752187671e-06,
      "learning_rate": 4.97764469288984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 477392,
      "step": 1705
    },
    {
      "epoch": 19.0,
      "grad_norm": 6.633682914980454e-06,
      "learning_rate": 4.977513504609127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 478800,
      "step": 1710
    },
    {
      "epoch": 19.055555555555557,
      "grad_norm": 6.493330147350207e-06,
      "learning_rate": 4.9773819342646965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 480208,
      "step": 1715
    },
    {
      "epoch": 19.11111111111111,
      "grad_norm": 9.437974767934065e-06,
      "learning_rate": 4.97724998187684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 481568,
      "step": 1720
    },
    {
      "epoch": 19.166666666666668,
      "grad_norm": 7.326530976570211e-06,
      "learning_rate": 4.9771176474659045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 482960,
      "step": 1725
    },
    {
      "epoch": 19.22222222222222,
      "grad_norm": 7.499686944356654e-06,
      "learning_rate": 4.976984931052299e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 484384,
      "step": 1730
    },
    {
      "epoch": 19.27777777777778,
      "grad_norm": 8.306231393362395e-06,
      "learning_rate": 4.976851832656489e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 485776,
      "step": 1735
    },
    {
      "epoch": 19.333333333333332,
      "grad_norm": 4.447731043910608e-05,
      "learning_rate": 4.9767183522990004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 487216,
      "step": 1740
    },
    {
      "epoch": 19.38888888888889,
      "grad_norm": 1.2537091606645845e-05,
      "learning_rate": 4.9765844900004176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 488544,
      "step": 1745
    },
    {
      "epoch": 19.444444444444443,
      "grad_norm": 1.150511161540635e-05,
      "learning_rate": 4.9764502457813834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 489904,
      "step": 1750
    },
    {
      "epoch": 19.5,
      "grad_norm": 9.545061402604915e-06,
      "learning_rate": 4.9763156196626005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 491344,
      "step": 1755
    },
    {
      "epoch": 19.555555555555557,
      "grad_norm": 7.314058166230097e-06,
      "learning_rate": 4.97618061166483e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 492720,
      "step": 1760
    },
    {
      "epoch": 19.61111111111111,
      "grad_norm": 6.791024588892469e-06,
      "learning_rate": 4.9760452218088915e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 494128,
      "step": 1765
    },
    {
      "epoch": 19.666666666666668,
      "grad_norm": 7.919884410512168e-06,
      "learning_rate": 4.975909450115663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 495504,
      "step": 1770
    },
    {
      "epoch": 19.72222222222222,
      "grad_norm": 6.976028544158908e-06,
      "learning_rate": 4.975773296606084e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 496928,
      "step": 1775
    },
    {
      "epoch": 19.77777777777778,
      "grad_norm": 1.9824188711936586e-05,
      "learning_rate": 4.97563676130115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 498304,
      "step": 1780
    },
    {
      "epoch": 19.833333333333332,
      "grad_norm": 1.0112522431882098e-05,
      "learning_rate": 4.9754998442219166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 499712,
      "step": 1785
    },
    {
      "epoch": 19.88888888888889,
      "grad_norm": 8.713256647752132e-06,
      "learning_rate": 4.9753625453894984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 501088,
      "step": 1790
    },
    {
      "epoch": 19.944444444444443,
      "grad_norm": 7.08990864950465e-06,
      "learning_rate": 4.975224864825068e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 502480,
      "step": 1795
    },
    {
      "epoch": 20.0,
      "grad_norm": 5.7028823903237935e-06,
      "learning_rate": 4.9750868025498576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 503904,
      "step": 1800
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.22095215320587158,
      "eval_runtime": 1.2849,
      "eval_samples_per_second": 31.131,
      "eval_steps_per_second": 15.565,
      "num_input_tokens_seen": 503904,
      "step": 1800
    },
    {
      "epoch": 20.055555555555557,
      "grad_norm": 7.747088602627628e-06,
      "learning_rate": 4.974948358585158e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 505280,
      "step": 1805
    },
    {
      "epoch": 20.11111111111111,
      "grad_norm": 4.9173754632647615e-06,
      "learning_rate": 4.9748095329523205e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 506656,
      "step": 1810
    },
    {
      "epoch": 20.166666666666668,
      "grad_norm": 6.680999831587542e-06,
      "learning_rate": 4.974670325672752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 508080,
      "step": 1815
    },
    {
      "epoch": 20.22222222222222,
      "grad_norm": 6.009117441863054e-06,
      "learning_rate": 4.974530736767921e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 509472,
      "step": 1820
    },
    {
      "epoch": 20.27777777777778,
      "grad_norm": 1.6912836144911125e-05,
      "learning_rate": 4.9743907662593524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 510896,
      "step": 1825
    },
    {
      "epoch": 20.333333333333332,
      "grad_norm": 7.182998160715215e-06,
      "learning_rate": 4.974250414168633e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 512304,
      "step": 1830
    },
    {
      "epoch": 20.38888888888889,
      "grad_norm": 8.916745173337404e-06,
      "learning_rate": 4.974109680517407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 513728,
      "step": 1835
    },
    {
      "epoch": 20.444444444444443,
      "grad_norm": 6.9843117671553046e-06,
      "learning_rate": 4.973968565327376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 515152,
      "step": 1840
    },
    {
      "epoch": 20.5,
      "grad_norm": 7.3715259532036725e-06,
      "learning_rate": 4.973827068620303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 516576,
      "step": 1845
    },
    {
      "epoch": 20.555555555555557,
      "grad_norm": 1.018877446767874e-05,
      "learning_rate": 4.973685190418008e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 517952,
      "step": 1850
    },
    {
      "epoch": 20.61111111111111,
      "grad_norm": 1.1346550309099257e-05,
      "learning_rate": 4.97354293074237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 519328,
      "step": 1855
    },
    {
      "epoch": 20.666666666666668,
      "grad_norm": 9.133298590313643e-06,
      "learning_rate": 4.9734002896153276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 520720,
      "step": 1860
    },
    {
      "epoch": 20.72222222222222,
      "grad_norm": 2.569626121839974e-05,
      "learning_rate": 4.973257267058877e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 522112,
      "step": 1865
    },
    {
      "epoch": 20.77777777777778,
      "grad_norm": 3.874141839332879e-06,
      "learning_rate": 4.973113863095076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 523536,
      "step": 1870
    },
    {
      "epoch": 20.833333333333332,
      "grad_norm": 8.428131877735723e-06,
      "learning_rate": 4.9729700777460384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 524896,
      "step": 1875
    },
    {
      "epoch": 20.88888888888889,
      "grad_norm": 1.037254241964547e-05,
      "learning_rate": 4.972825911033937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 526272,
      "step": 1880
    },
    {
      "epoch": 20.944444444444443,
      "grad_norm": 7.465974340448156e-05,
      "learning_rate": 4.9726813629810056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 527664,
      "step": 1885
    },
    {
      "epoch": 21.0,
      "grad_norm": 5.947704266873188e-06,
      "learning_rate": 4.9725364336095326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 529088,
      "step": 1890
    },
    {
      "epoch": 21.055555555555557,
      "grad_norm": 1.076253829523921e-05,
      "learning_rate": 4.972391122941871e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 530480,
      "step": 1895
    },
    {
      "epoch": 21.11111111111111,
      "grad_norm": 8.22188303573057e-06,
      "learning_rate": 4.972245431000428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 531888,
      "step": 1900
    },
    {
      "epoch": 21.166666666666668,
      "grad_norm": 5.515549219126115e-06,
      "learning_rate": 4.972099357807671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 533264,
      "step": 1905
    },
    {
      "epoch": 21.22222222222222,
      "grad_norm": 6.540836693602614e-06,
      "learning_rate": 4.971952903386127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 534656,
      "step": 1910
    },
    {
      "epoch": 21.27777777777778,
      "grad_norm": 6.024743015586864e-06,
      "learning_rate": 4.971806067758381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 536080,
      "step": 1915
    },
    {
      "epoch": 21.333333333333332,
      "grad_norm": 4.71800603918382e-06,
      "learning_rate": 4.971658850947076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 537488,
      "step": 1920
    },
    {
      "epoch": 21.38888888888889,
      "grad_norm": 9.77055424300488e-06,
      "learning_rate": 4.9715112529749165e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 538912,
      "step": 1925
    },
    {
      "epoch": 21.444444444444443,
      "grad_norm": 4.5206006689113565e-06,
      "learning_rate": 4.9713632738646624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 540336,
      "step": 1930
    },
    {
      "epoch": 21.5,
      "grad_norm": 1.979164153453894e-05,
      "learning_rate": 4.971214913639134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 541744,
      "step": 1935
    },
    {
      "epoch": 21.555555555555557,
      "grad_norm": 5.618757768388605e-06,
      "learning_rate": 4.9710661723212104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 543120,
      "step": 1940
    },
    {
      "epoch": 21.61111111111111,
      "grad_norm": 1.1160384019603953e-05,
      "learning_rate": 4.9709170499338295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 544560,
      "step": 1945
    },
    {
      "epoch": 21.666666666666668,
      "grad_norm": 8.73686803970486e-06,
      "learning_rate": 4.9707675464999895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 545952,
      "step": 1950
    },
    {
      "epoch": 21.72222222222222,
      "grad_norm": 8.473664820485283e-06,
      "learning_rate": 4.970617662042743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 547312,
      "step": 1955
    },
    {
      "epoch": 21.77777777777778,
      "grad_norm": 6.735861006745836e-06,
      "learning_rate": 4.970467396585206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 548784,
      "step": 1960
    },
    {
      "epoch": 21.833333333333332,
      "grad_norm": 1.804686507966835e-05,
      "learning_rate": 4.97031675015055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 550192,
      "step": 1965
    },
    {
      "epoch": 21.88888888888889,
      "grad_norm": 5.084827989776386e-06,
      "learning_rate": 4.9701657227620075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 551568,
      "step": 1970
    },
    {
      "epoch": 21.944444444444443,
      "grad_norm": 3.8163452700246125e-06,
      "learning_rate": 4.9700143144428685e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 552976,
      "step": 1975
    },
    {
      "epoch": 22.0,
      "grad_norm": 8.006470125110354e-06,
      "learning_rate": 4.969862525216482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 554352,
      "step": 1980
    },
    {
      "epoch": 22.055555555555557,
      "grad_norm": 5.171199973119656e-06,
      "learning_rate": 4.9697103551062556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 555776,
      "step": 1985
    },
    {
      "epoch": 22.11111111111111,
      "grad_norm": 5.07671438754187e-06,
      "learning_rate": 4.9695578041356565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 557136,
      "step": 1990
    },
    {
      "epoch": 22.166666666666668,
      "grad_norm": 7.151153113227338e-06,
      "learning_rate": 4.969404872328209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 558544,
      "step": 1995
    },
    {
      "epoch": 22.22222222222222,
      "grad_norm": 9.2482887339429e-06,
      "learning_rate": 4.969251559707498e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 559936,
      "step": 2000
    },
    {
      "epoch": 22.22222222222222,
      "eval_loss": 0.22411350905895233,
      "eval_runtime": 1.3137,
      "eval_samples_per_second": 30.448,
      "eval_steps_per_second": 15.224,
      "num_input_tokens_seen": 559936,
      "step": 2000
    },
    {
      "epoch": 22.27777777777778,
      "grad_norm": 5.742789198848186e-06,
      "learning_rate": 4.9690978662971674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 561344,
      "step": 2005
    },
    {
      "epoch": 22.333333333333332,
      "grad_norm": 4.9099016905529425e-06,
      "learning_rate": 4.968943792120916e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 562704,
      "step": 2010
    },
    {
      "epoch": 22.38888888888889,
      "grad_norm": 5.29383260072791e-06,
      "learning_rate": 4.9687893372025046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 564144,
      "step": 2015
    },
    {
      "epoch": 22.444444444444443,
      "grad_norm": 1.277660976484185e-05,
      "learning_rate": 4.9686345015657535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 565552,
      "step": 2020
    },
    {
      "epoch": 22.5,
      "grad_norm": 1.0742582162492909e-05,
      "learning_rate": 4.968479285234538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 566944,
      "step": 2025
    },
    {
      "epoch": 22.555555555555557,
      "grad_norm": 6.167592073325068e-05,
      "learning_rate": 4.9683236882327974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 568320,
      "step": 2030
    },
    {
      "epoch": 22.61111111111111,
      "grad_norm": 9.516417776467279e-06,
      "learning_rate": 4.968167710584526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 569712,
      "step": 2035
    },
    {
      "epoch": 22.666666666666668,
      "grad_norm": 3.2146457670023665e-05,
      "learning_rate": 4.968011352313775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 571152,
      "step": 2040
    },
    {
      "epoch": 22.72222222222222,
      "grad_norm": 6.9908328441670164e-06,
      "learning_rate": 4.967854613444659e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 572560,
      "step": 2045
    },
    {
      "epoch": 22.77777777777778,
      "grad_norm": 6.524969194288133e-06,
      "learning_rate": 4.967697494001349e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 573904,
      "step": 2050
    },
    {
      "epoch": 22.833333333333332,
      "grad_norm": 5.760852218372747e-06,
      "learning_rate": 4.9675399940080736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 575312,
      "step": 2055
    },
    {
      "epoch": 22.88888888888889,
      "grad_norm": 4.362849267636193e-06,
      "learning_rate": 4.9673821134891226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 576688,
      "step": 2060
    },
    {
      "epoch": 22.944444444444443,
      "grad_norm": 4.471053671295522e-06,
      "learning_rate": 4.967223852468842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 578144,
      "step": 2065
    },
    {
      "epoch": 23.0,
      "grad_norm": 9.032137313624844e-06,
      "learning_rate": 4.967065210971639e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 579536,
      "step": 2070
    },
    {
      "epoch": 23.055555555555557,
      "grad_norm": 7.412776540149935e-06,
      "learning_rate": 4.966906189021977e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 580976,
      "step": 2075
    },
    {
      "epoch": 23.11111111111111,
      "grad_norm": 2.8190061129862443e-05,
      "learning_rate": 4.966746786644379e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 582368,
      "step": 2080
    },
    {
      "epoch": 23.166666666666668,
      "grad_norm": 1.093677019525785e-05,
      "learning_rate": 4.966587003863429e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 583728,
      "step": 2085
    },
    {
      "epoch": 23.22222222222222,
      "grad_norm": 9.048331776284613e-06,
      "learning_rate": 4.966426840703765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 585184,
      "step": 2090
    },
    {
      "epoch": 23.27777777777778,
      "grad_norm": 4.6444770305242855e-06,
      "learning_rate": 4.9662662971900875e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 586544,
      "step": 2095
    },
    {
      "epoch": 23.333333333333332,
      "grad_norm": 3.9988194657780696e-06,
      "learning_rate": 4.9661053733471534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 587936,
      "step": 2100
    },
    {
      "epoch": 23.38888888888889,
      "grad_norm": 3.7681750200135866e-06,
      "learning_rate": 4.965944069199781e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 589328,
      "step": 2105
    },
    {
      "epoch": 23.444444444444443,
      "grad_norm": 4.3734612518164795e-06,
      "learning_rate": 4.965782384772842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 590800,
      "step": 2110
    },
    {
      "epoch": 23.5,
      "grad_norm": 5.409862751548644e-06,
      "learning_rate": 4.9656203200912734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 592176,
      "step": 2115
    },
    {
      "epoch": 23.555555555555557,
      "grad_norm": 3.5230764297011774e-06,
      "learning_rate": 4.965457875180067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 593568,
      "step": 2120
    },
    {
      "epoch": 23.61111111111111,
      "grad_norm": 9.09581831365358e-06,
      "learning_rate": 4.9652950500642724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 594928,
      "step": 2125
    },
    {
      "epoch": 23.666666666666668,
      "grad_norm": 1.1157748303958215e-05,
      "learning_rate": 4.965131844769001e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 596320,
      "step": 2130
    },
    {
      "epoch": 23.72222222222222,
      "grad_norm": 6.4857299548748415e-06,
      "learning_rate": 4.96496825931942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 597744,
      "step": 2135
    },
    {
      "epoch": 23.77777777777778,
      "grad_norm": 4.90225193061633e-06,
      "learning_rate": 4.9648042937407566e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 599168,
      "step": 2140
    },
    {
      "epoch": 23.833333333333332,
      "grad_norm": 6.267526259762235e-06,
      "learning_rate": 4.964639948058297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 600560,
      "step": 2145
    },
    {
      "epoch": 23.88888888888889,
      "grad_norm": 6.319317435554694e-06,
      "learning_rate": 4.9644752222973846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 601952,
      "step": 2150
    },
    {
      "epoch": 23.944444444444443,
      "grad_norm": 5.560955287364777e-06,
      "learning_rate": 4.964310116483422e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 603312,
      "step": 2155
    },
    {
      "epoch": 24.0,
      "grad_norm": 1.0282921721227467e-05,
      "learning_rate": 4.964144630641872e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 604736,
      "step": 2160
    },
    {
      "epoch": 24.055555555555557,
      "grad_norm": 6.4655873757146765e-06,
      "learning_rate": 4.9639787647982525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 606144,
      "step": 2165
    },
    {
      "epoch": 24.11111111111111,
      "grad_norm": 2.7486392355058342e-05,
      "learning_rate": 4.963812518978143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 607536,
      "step": 2170
    },
    {
      "epoch": 24.166666666666668,
      "grad_norm": 2.9077339149807813e-06,
      "learning_rate": 4.963645893207182e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 608944,
      "step": 2175
    },
    {
      "epoch": 24.22222222222222,
      "grad_norm": 3.4437009617249714e-06,
      "learning_rate": 4.963478887511063e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 610352,
      "step": 2180
    },
    {
      "epoch": 24.27777777777778,
      "grad_norm": 4.815226930077188e-06,
      "learning_rate": 4.963311501915542e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 611792,
      "step": 2185
    },
    {
      "epoch": 24.333333333333332,
      "grad_norm": 1.0370923519076314e-05,
      "learning_rate": 4.963143736446432e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 613136,
      "step": 2190
    },
    {
      "epoch": 24.38888888888889,
      "grad_norm": 3.493099711704417e-06,
      "learning_rate": 4.962975591129603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 614576,
      "step": 2195
    },
    {
      "epoch": 24.444444444444443,
      "grad_norm": 5.471341410157038e-06,
      "learning_rate": 4.962807065990986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 615968,
      "step": 2200
    },
    {
      "epoch": 24.444444444444443,
      "eval_loss": 0.23023538291454315,
      "eval_runtime": 1.3134,
      "eval_samples_per_second": 30.455,
      "eval_steps_per_second": 15.227,
      "num_input_tokens_seen": 615968,
      "step": 2200
    },
    {
      "epoch": 24.5,
      "grad_norm": 4.222955794830341e-06,
      "learning_rate": 4.9626381610565714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 617360,
      "step": 2205
    },
    {
      "epoch": 24.555555555555557,
      "grad_norm": 5.499573944689473e-06,
      "learning_rate": 4.9624688763524043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 618736,
      "step": 2210
    },
    {
      "epoch": 24.61111111111111,
      "grad_norm": 4.729530701297335e-06,
      "learning_rate": 4.962299211904591e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 620144,
      "step": 2215
    },
    {
      "epoch": 24.666666666666668,
      "grad_norm": 3.405799589017988e-06,
      "learning_rate": 4.962129167739296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 621488,
      "step": 2220
    },
    {
      "epoch": 24.72222222222222,
      "grad_norm": 0.00015843055734876543,
      "learning_rate": 4.961958743882742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 622864,
      "step": 2225
    },
    {
      "epoch": 24.77777777777778,
      "grad_norm": 7.085133347572992e-06,
      "learning_rate": 4.961787940361211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 624304,
      "step": 2230
    },
    {
      "epoch": 24.833333333333332,
      "grad_norm": 6.849715646239929e-06,
      "learning_rate": 4.961616757201043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 625712,
      "step": 2235
    },
    {
      "epoch": 24.88888888888889,
      "grad_norm": 4.364891083241673e-06,
      "learning_rate": 4.961445194428637e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 627136,
      "step": 2240
    },
    {
      "epoch": 24.944444444444443,
      "grad_norm": 7.805480709066615e-05,
      "learning_rate": 4.9612732520704486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 628512,
      "step": 2245
    },
    {
      "epoch": 25.0,
      "grad_norm": 5.504276941792341e-06,
      "learning_rate": 4.961100930152994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 629968,
      "step": 2250
    },
    {
      "epoch": 25.055555555555557,
      "grad_norm": 4.45081013822346e-06,
      "learning_rate": 4.960928228702849e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 631328,
      "step": 2255
    },
    {
      "epoch": 25.11111111111111,
      "grad_norm": 4.562302365229698e-06,
      "learning_rate": 4.960755147746645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 632720,
      "step": 2260
    },
    {
      "epoch": 25.166666666666668,
      "grad_norm": 1.865323429228738e-05,
      "learning_rate": 4.9605816873110736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 634192,
      "step": 2265
    },
    {
      "epoch": 25.22222222222222,
      "grad_norm": 5.38294398211292e-06,
      "learning_rate": 4.960407847422883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 635584,
      "step": 2270
    },
    {
      "epoch": 25.27777777777778,
      "grad_norm": 4.2565861804177985e-06,
      "learning_rate": 4.960233628108885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 637008,
      "step": 2275
    },
    {
      "epoch": 25.333333333333332,
      "grad_norm": 3.837368694803445e-06,
      "learning_rate": 4.960059029395942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 638400,
      "step": 2280
    },
    {
      "epoch": 25.38888888888889,
      "grad_norm": 6.749585008947179e-05,
      "learning_rate": 4.959884051310983e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 639824,
      "step": 2285
    },
    {
      "epoch": 25.444444444444443,
      "grad_norm": 5.0831640692194924e-05,
      "learning_rate": 4.959708693880991e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 641248,
      "step": 2290
    },
    {
      "epoch": 25.5,
      "grad_norm": 2.6554491341812536e-05,
      "learning_rate": 4.9595329571330074e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 642608,
      "step": 2295
    },
    {
      "epoch": 25.555555555555557,
      "grad_norm": 7.167500825744355e-06,
      "learning_rate": 4.9593568410941326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 644000,
      "step": 2300
    },
    {
      "epoch": 25.61111111111111,
      "grad_norm": 4.198303031444084e-06,
      "learning_rate": 4.959180345791528e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 645392,
      "step": 2305
    },
    {
      "epoch": 25.666666666666668,
      "grad_norm": 4.4419120968086645e-06,
      "learning_rate": 4.9590034712524086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 646752,
      "step": 2310
    },
    {
      "epoch": 25.72222222222222,
      "grad_norm": 4.513417025009403e-06,
      "learning_rate": 4.958826217504053e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 648160,
      "step": 2315
    },
    {
      "epoch": 25.77777777777778,
      "grad_norm": 4.239597728883382e-06,
      "learning_rate": 4.958648584573795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 649552,
      "step": 2320
    },
    {
      "epoch": 25.833333333333332,
      "grad_norm": 5.609223535429919e-06,
      "learning_rate": 4.958470572489028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 650976,
      "step": 2325
    },
    {
      "epoch": 25.88888888888889,
      "grad_norm": 6.8353115239006e-06,
      "learning_rate": 4.958292181277203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 652384,
      "step": 2330
    },
    {
      "epoch": 25.944444444444443,
      "grad_norm": 4.371329396235524e-06,
      "learning_rate": 4.958113410965832e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 653792,
      "step": 2335
    },
    {
      "epoch": 26.0,
      "grad_norm": 5.108646746521117e-06,
      "learning_rate": 4.957934261582481e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 655200,
      "step": 2340
    },
    {
      "epoch": 26.055555555555557,
      "grad_norm": 5.010180757381022e-06,
      "learning_rate": 4.95775473315478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 656592,
      "step": 2345
    },
    {
      "epoch": 26.11111111111111,
      "grad_norm": 6.036718332325108e-06,
      "learning_rate": 4.9575748257104124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 658000,
      "step": 2350
    },
    {
      "epoch": 26.166666666666668,
      "grad_norm": 3.4178381156380055e-06,
      "learning_rate": 4.9573945392771224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 659440,
      "step": 2355
    },
    {
      "epoch": 26.22222222222222,
      "grad_norm": 3.6639055451814784e-06,
      "learning_rate": 4.9572138738827134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 660848,
      "step": 2360
    },
    {
      "epoch": 26.27777777777778,
      "grad_norm": 4.806870947504649e-06,
      "learning_rate": 4.957032829555046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 662240,
      "step": 2365
    },
    {
      "epoch": 26.333333333333332,
      "grad_norm": 3.36351990881667e-06,
      "learning_rate": 4.956851406322039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 663664,
      "step": 2370
    },
    {
      "epoch": 26.38888888888889,
      "grad_norm": 4.660798367694952e-06,
      "learning_rate": 4.9566696042116704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 665104,
      "step": 2375
    },
    {
      "epoch": 26.444444444444443,
      "grad_norm": 4.076584446011111e-06,
      "learning_rate": 4.9564874232519766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 666512,
      "step": 2380
    },
    {
      "epoch": 26.5,
      "grad_norm": 4.020541837235214e-06,
      "learning_rate": 4.9563048634710516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 667920,
      "step": 2385
    },
    {
      "epoch": 26.555555555555557,
      "grad_norm": 7.26372491044458e-06,
      "learning_rate": 4.956121924897049e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 669312,
      "step": 2390
    },
    {
      "epoch": 26.61111111111111,
      "grad_norm": 6.775066867703572e-05,
      "learning_rate": 4.955938607558181e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 670720,
      "step": 2395
    },
    {
      "epoch": 26.666666666666668,
      "grad_norm": 2.374866744503379e-05,
      "learning_rate": 4.955754911482715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 672064,
      "step": 2400
    },
    {
      "epoch": 26.666666666666668,
      "eval_loss": 0.22735659778118134,
      "eval_runtime": 1.2993,
      "eval_samples_per_second": 30.786,
      "eval_steps_per_second": 15.393,
      "num_input_tokens_seen": 672064,
      "step": 2400
    },
    {
      "epoch": 26.72222222222222,
      "grad_norm": 6.029150881659007e-06,
      "learning_rate": 4.9555708366989804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 673440,
      "step": 2405
    },
    {
      "epoch": 26.77777777777778,
      "grad_norm": 3.693285862027551e-06,
      "learning_rate": 4.9553863832353655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 674784,
      "step": 2410
    },
    {
      "epoch": 26.833333333333332,
      "grad_norm": 4.199398517812369e-06,
      "learning_rate": 4.955201551120313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 676176,
      "step": 2415
    },
    {
      "epoch": 26.88888888888889,
      "grad_norm": 2.6383731892565265e-06,
      "learning_rate": 4.955016340382328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 677568,
      "step": 2420
    },
    {
      "epoch": 26.944444444444443,
      "grad_norm": 5.905059879296459e-06,
      "learning_rate": 4.954830751049972e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 678992,
      "step": 2425
    },
    {
      "epoch": 27.0,
      "grad_norm": 3.1212293833959848e-06,
      "learning_rate": 4.954644783151864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 680464,
      "step": 2430
    },
    {
      "epoch": 27.055555555555557,
      "grad_norm": 3.6818714761466254e-06,
      "learning_rate": 4.954458436716684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 681840,
      "step": 2435
    },
    {
      "epoch": 27.11111111111111,
      "grad_norm": 8.030873686948325e-06,
      "learning_rate": 4.954271711773168e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 683232,
      "step": 2440
    },
    {
      "epoch": 27.166666666666668,
      "grad_norm": 6.415794814529363e-06,
      "learning_rate": 4.9540846083501115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 684624,
      "step": 2445
    },
    {
      "epoch": 27.22222222222222,
      "grad_norm": 3.3663570775388507e-06,
      "learning_rate": 4.953897126476369e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 686032,
      "step": 2450
    },
    {
      "epoch": 27.27777777777778,
      "grad_norm": 7.735013241472188e-06,
      "learning_rate": 4.9537092661808514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 687456,
      "step": 2455
    },
    {
      "epoch": 27.333333333333332,
      "grad_norm": 3.050012537642033e-06,
      "learning_rate": 4.9535210274925306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 688864,
      "step": 2460
    },
    {
      "epoch": 27.38888888888889,
      "grad_norm": 2.566640887380345e-06,
      "learning_rate": 4.953332410440435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 690256,
      "step": 2465
    },
    {
      "epoch": 27.444444444444443,
      "grad_norm": 3.979715529567329e-06,
      "learning_rate": 4.9531434150536496e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 691664,
      "step": 2470
    },
    {
      "epoch": 27.5,
      "grad_norm": 3.4833612971851835e-06,
      "learning_rate": 4.952954041361322e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 693056,
      "step": 2475
    },
    {
      "epoch": 27.555555555555557,
      "grad_norm": 4.083353815076407e-06,
      "learning_rate": 4.952764289392655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 694416,
      "step": 2480
    },
    {
      "epoch": 27.61111111111111,
      "grad_norm": 2.211066930613015e-05,
      "learning_rate": 4.952574159176912e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 695840,
      "step": 2485
    },
    {
      "epoch": 27.666666666666668,
      "grad_norm": 3.2455866403324762e-06,
      "learning_rate": 4.952383650743413e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 697248,
      "step": 2490
    },
    {
      "epoch": 27.72222222222222,
      "grad_norm": 3.268826503699529e-06,
      "learning_rate": 4.952192764121536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 698688,
      "step": 2495
    },
    {
      "epoch": 27.77777777777778,
      "grad_norm": 5.296942617860623e-06,
      "learning_rate": 4.9520014993407185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 700096,
      "step": 2500
    },
    {
      "epoch": 27.833333333333332,
      "grad_norm": 4.482448275666684e-06,
      "learning_rate": 4.951809856430456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 701520,
      "step": 2505
    },
    {
      "epoch": 27.88888888888889,
      "grad_norm": 2.700232244023937e-06,
      "learning_rate": 4.951617835420303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 702896,
      "step": 2510
    },
    {
      "epoch": 27.944444444444443,
      "grad_norm": 5.449451236927416e-06,
      "learning_rate": 4.951425436339869e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 704288,
      "step": 2515
    },
    {
      "epoch": 28.0,
      "grad_norm": 3.7578499814117095e-06,
      "learning_rate": 4.9512326592188274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 705680,
      "step": 2520
    },
    {
      "epoch": 28.055555555555557,
      "grad_norm": 4.959458237863146e-06,
      "learning_rate": 4.9510395040869054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 707056,
      "step": 2525
    },
    {
      "epoch": 28.11111111111111,
      "grad_norm": 2.7136652533954475e-06,
      "learning_rate": 4.9508459709738905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 708528,
      "step": 2530
    },
    {
      "epoch": 28.166666666666668,
      "grad_norm": 4.200444436719408e-06,
      "learning_rate": 4.950652059909627e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 709888,
      "step": 2535
    },
    {
      "epoch": 28.22222222222222,
      "grad_norm": 5.091372713650344e-06,
      "learning_rate": 4.95045777092402e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 711264,
      "step": 2540
    },
    {
      "epoch": 28.27777777777778,
      "grad_norm": 4.325231657276163e-06,
      "learning_rate": 4.950263104047031e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 712640,
      "step": 2545
    },
    {
      "epoch": 28.333333333333332,
      "grad_norm": 3.248452003390412e-06,
      "learning_rate": 4.9500680593086775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 714048,
      "step": 2550
    },
    {
      "epoch": 28.38888888888889,
      "grad_norm": 2.1866893803235143e-05,
      "learning_rate": 4.94987263673904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 715440,
      "step": 2555
    },
    {
      "epoch": 28.444444444444443,
      "grad_norm": 7.421875579893822e-06,
      "learning_rate": 4.949676836368256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 716848,
      "step": 2560
    },
    {
      "epoch": 28.5,
      "grad_norm": 4.4777639232052024e-06,
      "learning_rate": 4.949480658226518e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 718256,
      "step": 2565
    },
    {
      "epoch": 28.555555555555557,
      "grad_norm": 2.525120635255007e-06,
      "learning_rate": 4.949284102344082e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 719664,
      "step": 2570
    },
    {
      "epoch": 28.61111111111111,
      "grad_norm": 3.2194366212934256e-06,
      "learning_rate": 4.9490871687512565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 721056,
      "step": 2575
    },
    {
      "epoch": 28.666666666666668,
      "grad_norm": 5.015260830987245e-05,
      "learning_rate": 4.948889857478413e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 722448,
      "step": 2580
    },
    {
      "epoch": 28.72222222222222,
      "grad_norm": 4.956169959768886e-06,
      "learning_rate": 4.948692168555978e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 723888,
      "step": 2585
    },
    {
      "epoch": 28.77777777777778,
      "grad_norm": 4.151251687289914e-06,
      "learning_rate": 4.94849410201444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 725312,
      "step": 2590
    },
    {
      "epoch": 28.833333333333332,
      "grad_norm": 2.9461489248205908e-06,
      "learning_rate": 4.948295657884341e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 726720,
      "step": 2595
    },
    {
      "epoch": 28.88888888888889,
      "grad_norm": 4.7737325985508505e-06,
      "learning_rate": 4.9480968361962835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 728128,
      "step": 2600
    },
    {
      "epoch": 28.88888888888889,
      "eval_loss": 0.232314795255661,
      "eval_runtime": 1.3106,
      "eval_samples_per_second": 30.52,
      "eval_steps_per_second": 15.26,
      "num_input_tokens_seen": 728128,
      "step": 2600
    },
    {
      "epoch": 28.944444444444443,
      "grad_norm": 3.731582182808779e-06,
      "learning_rate": 4.9478976369809305e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 729536,
      "step": 2605
    },
    {
      "epoch": 29.0,
      "grad_norm": 4.485706995183136e-06,
      "learning_rate": 4.947698060268999e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 730928,
      "step": 2610
    },
    {
      "epoch": 29.055555555555557,
      "grad_norm": 5.1026372602791525e-06,
      "learning_rate": 4.9474981060912665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 732336,
      "step": 2615
    },
    {
      "epoch": 29.11111111111111,
      "grad_norm": 3.169690671711578e-06,
      "learning_rate": 4.94729777447857e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 733744,
      "step": 2620
    },
    {
      "epoch": 29.166666666666668,
      "grad_norm": 6.791165105823893e-06,
      "learning_rate": 4.947097065461801e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 735152,
      "step": 2625
    },
    {
      "epoch": 29.22222222222222,
      "grad_norm": 2.082120772683993e-05,
      "learning_rate": 4.9468959790719125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 736560,
      "step": 2630
    },
    {
      "epoch": 29.27777777777778,
      "grad_norm": 3.2054254006652627e-06,
      "learning_rate": 4.9466945153399146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 737936,
      "step": 2635
    },
    {
      "epoch": 29.333333333333332,
      "grad_norm": 3.1038900942803593e-06,
      "learning_rate": 4.9464926742968755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 739296,
      "step": 2640
    },
    {
      "epoch": 29.38888888888889,
      "grad_norm": 5.185684585740091e-06,
      "learning_rate": 4.946290455973921e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 740688,
      "step": 2645
    },
    {
      "epoch": 29.444444444444443,
      "grad_norm": 4.445878403203096e-06,
      "learning_rate": 4.9460878604022365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 742048,
      "step": 2650
    },
    {
      "epoch": 29.5,
      "grad_norm": 5.693032107956242e-06,
      "learning_rate": 4.945884887613065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 743408,
      "step": 2655
    },
    {
      "epoch": 29.555555555555557,
      "grad_norm": 5.059518116468098e-06,
      "learning_rate": 4.9456815376377055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 744784,
      "step": 2660
    },
    {
      "epoch": 29.61111111111111,
      "grad_norm": 4.211914074403467e-06,
      "learning_rate": 4.9454778105075195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 746160,
      "step": 2665
    },
    {
      "epoch": 29.666666666666668,
      "grad_norm": 2.8031702186126495e-06,
      "learning_rate": 4.945273706253924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 747584,
      "step": 2670
    },
    {
      "epoch": 29.72222222222222,
      "grad_norm": 3.2356792871723883e-06,
      "learning_rate": 4.9450692249083925e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 749024,
      "step": 2675
    },
    {
      "epoch": 29.77777777777778,
      "grad_norm": 4.004746188002173e-06,
      "learning_rate": 4.9448643665024605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 750464,
      "step": 2680
    },
    {
      "epoch": 29.833333333333332,
      "grad_norm": 4.251663085597102e-06,
      "learning_rate": 4.944659131067719e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 751888,
      "step": 2685
    },
    {
      "epoch": 29.88888888888889,
      "grad_norm": 2.489455937393359e-06,
      "learning_rate": 4.944453518635818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 753280,
      "step": 2690
    },
    {
      "epoch": 29.944444444444443,
      "grad_norm": 2.031347094089142e-06,
      "learning_rate": 4.944247529238465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 754656,
      "step": 2695
    },
    {
      "epoch": 30.0,
      "grad_norm": 3.974893388658529e-06,
      "learning_rate": 4.944041162907427e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 756080,
      "step": 2700
    },
    {
      "epoch": 30.055555555555557,
      "grad_norm": 4.272628757462371e-06,
      "learning_rate": 4.943834419674529e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 757536,
      "step": 2705
    },
    {
      "epoch": 30.11111111111111,
      "grad_norm": 4.674643605540041e-06,
      "learning_rate": 4.9436272995716506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 758960,
      "step": 2710
    },
    {
      "epoch": 30.166666666666668,
      "grad_norm": 4.161133801972028e-06,
      "learning_rate": 4.943419802630735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 760384,
      "step": 2715
    },
    {
      "epoch": 30.22222222222222,
      "grad_norm": 2.7788944407802774e-06,
      "learning_rate": 4.94321192888378e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 761728,
      "step": 2720
    },
    {
      "epoch": 30.27777777777778,
      "grad_norm": 4.4820330913353246e-06,
      "learning_rate": 4.943003678362842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 763120,
      "step": 2725
    },
    {
      "epoch": 30.333333333333332,
      "grad_norm": 4.2683018364186864e-06,
      "learning_rate": 4.942795051100036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 764528,
      "step": 2730
    },
    {
      "epoch": 30.38888888888889,
      "grad_norm": 2.5802858090173686e-06,
      "learning_rate": 4.942586047127536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 765904,
      "step": 2735
    },
    {
      "epoch": 30.444444444444443,
      "grad_norm": 2.4710634534130804e-05,
      "learning_rate": 4.942376666477571e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 767296,
      "step": 2740
    },
    {
      "epoch": 30.5,
      "grad_norm": 2.642212621140061e-06,
      "learning_rate": 4.9421669091824304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 768672,
      "step": 2745
    },
    {
      "epoch": 30.555555555555557,
      "grad_norm": 3.042651314899558e-06,
      "learning_rate": 4.9419567752744634e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 770080,
      "step": 2750
    },
    {
      "epoch": 30.61111111111111,
      "grad_norm": 2.9843922675354406e-06,
      "learning_rate": 4.941746264786074e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 771488,
      "step": 2755
    },
    {
      "epoch": 30.666666666666668,
      "grad_norm": 4.414636805449845e-06,
      "learning_rate": 4.9415353777497254e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 772960,
      "step": 2760
    },
    {
      "epoch": 30.72222222222222,
      "grad_norm": 2.6698271540226415e-06,
      "learning_rate": 4.9413241141979394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 774352,
      "step": 2765
    },
    {
      "epoch": 30.77777777777778,
      "grad_norm": 2.6450338737049606e-06,
      "learning_rate": 4.9411124741632956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 775728,
      "step": 2770
    },
    {
      "epoch": 30.833333333333332,
      "grad_norm": 3.547332426023786e-06,
      "learning_rate": 4.940900457678431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 777120,
      "step": 2775
    },
    {
      "epoch": 30.88888888888889,
      "grad_norm": 4.638031896320172e-06,
      "learning_rate": 4.9406880647760425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 778544,
      "step": 2780
    },
    {
      "epoch": 30.944444444444443,
      "grad_norm": 1.2024617717543151e-05,
      "learning_rate": 4.9404752954888824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 779904,
      "step": 2785
    },
    {
      "epoch": 31.0,
      "grad_norm": 2.4989374196593417e-06,
      "learning_rate": 4.940262149849762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 781248,
      "step": 2790
    },
    {
      "epoch": 31.055555555555557,
      "grad_norm": 2.2476619960798416e-06,
      "learning_rate": 4.9400486278915526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 782640,
      "step": 2795
    },
    {
      "epoch": 31.11111111111111,
      "grad_norm": 2.5524682314426173e-06,
      "learning_rate": 4.939834729647181e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 784032,
      "step": 2800
    },
    {
      "epoch": 31.11111111111111,
      "eval_loss": 0.23051214218139648,
      "eval_runtime": 1.3185,
      "eval_samples_per_second": 30.337,
      "eval_steps_per_second": 15.169,
      "num_input_tokens_seen": 784032,
      "step": 2800
    },
    {
      "epoch": 31.166666666666668,
      "grad_norm": 2.0017159840790555e-06,
      "learning_rate": 4.9396204551496326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 785408,
      "step": 2805
    },
    {
      "epoch": 31.22222222222222,
      "grad_norm": 4.339855877333321e-06,
      "learning_rate": 4.939405804431952e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 786864,
      "step": 2810
    },
    {
      "epoch": 31.27777777777778,
      "grad_norm": 2.8614465463761007e-06,
      "learning_rate": 4.9391907775272414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 788256,
      "step": 2815
    },
    {
      "epoch": 31.333333333333332,
      "grad_norm": 3.599206593207782e-06,
      "learning_rate": 4.9389753744686604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 789648,
      "step": 2820
    },
    {
      "epoch": 31.38888888888889,
      "grad_norm": 3.7855165828659665e-06,
      "learning_rate": 4.938759595289426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 791040,
      "step": 2825
    },
    {
      "epoch": 31.444444444444443,
      "grad_norm": 2.9560478651546873e-06,
      "learning_rate": 4.938543440022815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 792400,
      "step": 2830
    },
    {
      "epoch": 31.5,
      "grad_norm": 3.930084858438931e-06,
      "learning_rate": 4.938326908702161e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 793856,
      "step": 2835
    },
    {
      "epoch": 31.555555555555557,
      "grad_norm": 4.226845248922473e-06,
      "learning_rate": 4.9381100013608554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 795264,
      "step": 2840
    },
    {
      "epoch": 31.61111111111111,
      "grad_norm": 2.991936980833998e-06,
      "learning_rate": 4.9378927180323485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 796704,
      "step": 2845
    },
    {
      "epoch": 31.666666666666668,
      "grad_norm": 1.7782508621166926e-06,
      "learning_rate": 4.937675058750148e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 798128,
      "step": 2850
    },
    {
      "epoch": 31.72222222222222,
      "grad_norm": 3.097260560025461e-06,
      "learning_rate": 4.937457023547819e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 799520,
      "step": 2855
    },
    {
      "epoch": 31.77777777777778,
      "grad_norm": 1.5867617548792623e-06,
      "learning_rate": 4.9372386124589876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 800928,
      "step": 2860
    },
    {
      "epoch": 31.833333333333332,
      "grad_norm": 4.5869446694268845e-06,
      "learning_rate": 4.937019825517333e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 802320,
      "step": 2865
    },
    {
      "epoch": 31.88888888888889,
      "grad_norm": 1.6301771665894194e-06,
      "learning_rate": 4.9368006627565954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 803664,
      "step": 2870
    },
    {
      "epoch": 31.944444444444443,
      "grad_norm": 2.5790716335905017e-06,
      "learning_rate": 4.936581124210573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 805072,
      "step": 2875
    },
    {
      "epoch": 32.0,
      "grad_norm": 3.9533993003715295e-06,
      "learning_rate": 4.9363612099131216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 806496,
      "step": 2880
    },
    {
      "epoch": 32.05555555555556,
      "grad_norm": 2.5164424641843652e-06,
      "learning_rate": 4.936140919898155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 807888,
      "step": 2885
    },
    {
      "epoch": 32.111111111111114,
      "grad_norm": 2.8900647066620877e-06,
      "learning_rate": 4.9359202541996426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 809312,
      "step": 2890
    },
    {
      "epoch": 32.166666666666664,
      "grad_norm": 3.0554874683730304e-06,
      "learning_rate": 4.935699212851616e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 810736,
      "step": 2895
    },
    {
      "epoch": 32.22222222222222,
      "grad_norm": 2.970786954392679e-05,
      "learning_rate": 4.935477795888162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 812160,
      "step": 2900
    },
    {
      "epoch": 32.27777777777778,
      "grad_norm": 3.531366246534162e-06,
      "learning_rate": 4.935256003343426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 813584,
      "step": 2905
    },
    {
      "epoch": 32.333333333333336,
      "grad_norm": 3.3714864002831746e-06,
      "learning_rate": 4.93503383525161e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 814928,
      "step": 2910
    },
    {
      "epoch": 32.388888888888886,
      "grad_norm": 4.116533546039136e-06,
      "learning_rate": 4.934811291646977e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 816320,
      "step": 2915
    },
    {
      "epoch": 32.44444444444444,
      "grad_norm": 2.251261321362108e-06,
      "learning_rate": 4.934588372563845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 817728,
      "step": 2920
    },
    {
      "epoch": 32.5,
      "grad_norm": 5.022233835916268e-06,
      "learning_rate": 4.93436507803659e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 819120,
      "step": 2925
    },
    {
      "epoch": 32.55555555555556,
      "grad_norm": 5.192536264075898e-06,
      "learning_rate": 4.934141408099649e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 820512,
      "step": 2930
    },
    {
      "epoch": 32.611111111111114,
      "grad_norm": 1.957683707587421e-06,
      "learning_rate": 4.9339173627875135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 821920,
      "step": 2935
    },
    {
      "epoch": 32.666666666666664,
      "grad_norm": 2.0602634322131053e-05,
      "learning_rate": 4.9336929421347335e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 823328,
      "step": 2940
    },
    {
      "epoch": 32.72222222222222,
      "grad_norm": 3.0758737921132706e-06,
      "learning_rate": 4.933468146175918e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 824688,
      "step": 2945
    },
    {
      "epoch": 32.77777777777778,
      "grad_norm": 2.0048287296958733e-06,
      "learning_rate": 4.933242974945734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 826144,
      "step": 2950
    },
    {
      "epoch": 32.833333333333336,
      "grad_norm": 3.84761051464011e-06,
      "learning_rate": 4.933017428478906e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 827504,
      "step": 2955
    },
    {
      "epoch": 32.888888888888886,
      "grad_norm": 2.7699049951479537e-06,
      "learning_rate": 4.932791506810214e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 828896,
      "step": 2960
    },
    {
      "epoch": 32.94444444444444,
      "grad_norm": 2.3417269403580576e-06,
      "learning_rate": 4.932565209974499e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 830304,
      "step": 2965
    },
    {
      "epoch": 33.0,
      "grad_norm": 1.74275064637186e-05,
      "learning_rate": 4.93233853800666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 831696,
      "step": 2970
    },
    {
      "epoch": 33.05555555555556,
      "grad_norm": 3.081259364989819e-06,
      "learning_rate": 4.932111490941651e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 833072,
      "step": 2975
    },
    {
      "epoch": 33.111111111111114,
      "grad_norm": 3.384335059308796e-06,
      "learning_rate": 4.9318840688144876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 834432,
      "step": 2980
    },
    {
      "epoch": 33.166666666666664,
      "grad_norm": 2.820703457473428e-06,
      "learning_rate": 4.9316562716602387e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 835840,
      "step": 2985
    },
    {
      "epoch": 33.22222222222222,
      "grad_norm": 3.199744242010638e-06,
      "learning_rate": 4.9314280995140346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 837232,
      "step": 2990
    },
    {
      "epoch": 33.27777777777778,
      "grad_norm": 2.5428698791074567e-06,
      "learning_rate": 4.931199552411063e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 838624,
      "step": 2995
    },
    {
      "epoch": 33.333333333333336,
      "grad_norm": 3.967765678680735e-06,
      "learning_rate": 4.930970630386568e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 839984,
      "step": 3000
    },
    {
      "epoch": 33.333333333333336,
      "eval_loss": 0.2234121561050415,
      "eval_runtime": 1.316,
      "eval_samples_per_second": 30.396,
      "eval_steps_per_second": 15.198,
      "num_input_tokens_seen": 839984,
      "step": 3000
    },
    {
      "epoch": 33.388888888888886,
      "grad_norm": 1.9089509351033485e-06,
      "learning_rate": 4.9307413334758524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 841376,
      "step": 3005
    },
    {
      "epoch": 33.44444444444444,
      "grad_norm": 2.2966021333559183e-06,
      "learning_rate": 4.930511661714276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 842800,
      "step": 3010
    },
    {
      "epoch": 33.5,
      "grad_norm": 3.1200256671581883e-06,
      "learning_rate": 4.9302816151372576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 844208,
      "step": 3015
    },
    {
      "epoch": 33.55555555555556,
      "grad_norm": 1.6617555047560018e-06,
      "learning_rate": 4.930051193780274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 845632,
      "step": 3020
    },
    {
      "epoch": 33.611111111111114,
      "grad_norm": 3.603103323257528e-05,
      "learning_rate": 4.929820397678858e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 847072,
      "step": 3025
    },
    {
      "epoch": 33.666666666666664,
      "grad_norm": 5.088820671517169e-06,
      "learning_rate": 4.9295892268686015e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 848480,
      "step": 3030
    },
    {
      "epoch": 33.72222222222222,
      "grad_norm": 2.6299862838641275e-06,
      "learning_rate": 4.9293576813851536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 849872,
      "step": 3035
    },
    {
      "epoch": 33.77777777777778,
      "grad_norm": 2.676509211596567e-06,
      "learning_rate": 4.929125761264223e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 851312,
      "step": 3040
    },
    {
      "epoch": 33.833333333333336,
      "grad_norm": 1.7509395320303156e-06,
      "learning_rate": 4.928893466541573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 852720,
      "step": 3045
    },
    {
      "epoch": 33.888888888888886,
      "grad_norm": 3.015515630977461e-06,
      "learning_rate": 4.928660797253027e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 854128,
      "step": 3050
    },
    {
      "epoch": 33.94444444444444,
      "grad_norm": 2.0858165044046473e-06,
      "learning_rate": 4.928427753434467e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 855536,
      "step": 3055
    },
    {
      "epoch": 34.0,
      "grad_norm": 3.0279315978987142e-06,
      "learning_rate": 4.9281943351218286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 856944,
      "step": 3060
    },
    {
      "epoch": 34.05555555555556,
      "grad_norm": 2.431127541058231e-06,
      "learning_rate": 4.9279605423511095e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 858368,
      "step": 3065
    },
    {
      "epoch": 34.111111111111114,
      "grad_norm": 1.670852543611545e-05,
      "learning_rate": 4.927726375158363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 859728,
      "step": 3070
    },
    {
      "epoch": 34.166666666666664,
      "grad_norm": 2.7564121864998015e-06,
      "learning_rate": 4.9274918335797004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 861120,
      "step": 3075
    },
    {
      "epoch": 34.22222222222222,
      "grad_norm": 2.437673629174242e-06,
      "learning_rate": 4.927256917651292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 862496,
      "step": 3080
    },
    {
      "epoch": 34.27777777777778,
      "grad_norm": 1.780015736585483e-06,
      "learning_rate": 4.927021627409364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 863904,
      "step": 3085
    },
    {
      "epoch": 34.333333333333336,
      "grad_norm": 6.2086419347906485e-06,
      "learning_rate": 4.9267859628902005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 865328,
      "step": 3090
    },
    {
      "epoch": 34.388888888888886,
      "grad_norm": 2.8231095257069683e-06,
      "learning_rate": 4.9265499241301454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 866704,
      "step": 3095
    },
    {
      "epoch": 34.44444444444444,
      "grad_norm": 2.5580102374078706e-06,
      "learning_rate": 4.926313511165598e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 868096,
      "step": 3100
    },
    {
      "epoch": 34.5,
      "grad_norm": 2.053340040220064e-06,
      "learning_rate": 4.926076724033016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 869456,
      "step": 3105
    },
    {
      "epoch": 34.55555555555556,
      "grad_norm": 2.7090823095932137e-06,
      "learning_rate": 4.9258395627689146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 870912,
      "step": 3110
    },
    {
      "epoch": 34.611111111111114,
      "grad_norm": 1.5114353573153494e-06,
      "learning_rate": 4.925602027409868e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 872272,
      "step": 3115
    },
    {
      "epoch": 34.666666666666664,
      "grad_norm": 4.557763077173149e-06,
      "learning_rate": 4.925364117992507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 873664,
      "step": 3120
    },
    {
      "epoch": 34.72222222222222,
      "grad_norm": 2.1469763851200696e-06,
      "learning_rate": 4.92512583455352e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 875072,
      "step": 3125
    },
    {
      "epoch": 34.77777777777778,
      "grad_norm": 2.2672602426609956e-06,
      "learning_rate": 4.9248871771296536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 876480,
      "step": 3130
    },
    {
      "epoch": 34.833333333333336,
      "grad_norm": 2.8800648124160944e-06,
      "learning_rate": 4.924648145757711e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 877936,
      "step": 3135
    },
    {
      "epoch": 34.888888888888886,
      "grad_norm": 1.867212063189072e-06,
      "learning_rate": 4.924408740474554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 879360,
      "step": 3140
    },
    {
      "epoch": 34.94444444444444,
      "grad_norm": 1.910879518618458e-06,
      "learning_rate": 4.924168961317103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 880752,
      "step": 3145
    },
    {
      "epoch": 35.0,
      "grad_norm": 2.2645250282948837e-05,
      "learning_rate": 4.9239288083223334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 882176,
      "step": 3150
    },
    {
      "epoch": 35.05555555555556,
      "grad_norm": 4.161066499364097e-06,
      "learning_rate": 4.9236882815272803e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 883616,
      "step": 3155
    },
    {
      "epoch": 35.111111111111114,
      "grad_norm": 1.8158769989895518e-06,
      "learning_rate": 4.9234473809690365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 885056,
      "step": 3160
    },
    {
      "epoch": 35.166666666666664,
      "grad_norm": 3.1381580356537597e-06,
      "learning_rate": 4.923206106684752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 886480,
      "step": 3165
    },
    {
      "epoch": 35.22222222222222,
      "grad_norm": 2.604246219561901e-06,
      "learning_rate": 4.922964458711634e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 887888,
      "step": 3170
    },
    {
      "epoch": 35.27777777777778,
      "grad_norm": 3.0846658773953095e-06,
      "learning_rate": 4.9227224370869474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 889264,
      "step": 3175
    },
    {
      "epoch": 35.333333333333336,
      "grad_norm": 1.1072077541030012e-05,
      "learning_rate": 4.9224800418480155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 890608,
      "step": 3180
    },
    {
      "epoch": 35.388888888888886,
      "grad_norm": 2.05100900529942e-06,
      "learning_rate": 4.9222372730322176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 892016,
      "step": 3185
    },
    {
      "epoch": 35.44444444444444,
      "grad_norm": 1.7967636267712805e-06,
      "learning_rate": 4.921994130676993e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 893456,
      "step": 3190
    },
    {
      "epoch": 35.5,
      "grad_norm": 1.1263218766544014e-05,
      "learning_rate": 4.9217506148198366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 894896,
      "step": 3195
    },
    {
      "epoch": 35.55555555555556,
      "grad_norm": 1.9207491277484223e-06,
      "learning_rate": 4.921506725498302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 896288,
      "step": 3200
    },
    {
      "epoch": 35.55555555555556,
      "eval_loss": 0.23261216282844543,
      "eval_runtime": 1.3013,
      "eval_samples_per_second": 30.739,
      "eval_steps_per_second": 15.37,
      "num_input_tokens_seen": 896288,
      "step": 3200
    },
    {
      "epoch": 35.611111111111114,
      "grad_norm": 2.431919938317151e-06,
      "learning_rate": 4.9212624627499994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 897680,
      "step": 3205
    },
    {
      "epoch": 35.666666666666664,
      "grad_norm": 2.596061449366971e-06,
      "learning_rate": 4.921017826612597e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 899056,
      "step": 3210
    },
    {
      "epoch": 35.72222222222222,
      "grad_norm": 1.6395027842008858e-06,
      "learning_rate": 4.9207728171238223e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 900432,
      "step": 3215
    },
    {
      "epoch": 35.77777777777778,
      "grad_norm": 1.4448854699367075e-06,
      "learning_rate": 4.920527434321458e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 901808,
      "step": 3220
    },
    {
      "epoch": 35.833333333333336,
      "grad_norm": 1.823076672735624e-05,
      "learning_rate": 4.920281678243345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 903232,
      "step": 3225
    },
    {
      "epoch": 35.888888888888886,
      "grad_norm": 1.8992276409335318e-06,
      "learning_rate": 4.920035548927381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 904640,
      "step": 3230
    },
    {
      "epoch": 35.94444444444444,
      "grad_norm": 1.5654579783586087e-06,
      "learning_rate": 4.919789046411525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 906016,
      "step": 3235
    },
    {
      "epoch": 36.0,
      "grad_norm": 1.68990754900733e-05,
      "learning_rate": 4.919542170733787e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 907408,
      "step": 3240
    },
    {
      "epoch": 36.05555555555556,
      "grad_norm": 1.6285929405057686e-06,
      "learning_rate": 4.919294921932242e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 908784,
      "step": 3245
    },
    {
      "epoch": 36.111111111111114,
      "grad_norm": 4.421720859681955e-06,
      "learning_rate": 4.919047300045016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 910192,
      "step": 3250
    },
    {
      "epoch": 36.166666666666664,
      "grad_norm": 1.7756716488293023e-06,
      "learning_rate": 4.918799305110299e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 911552,
      "step": 3255
    },
    {
      "epoch": 36.22222222222222,
      "grad_norm": 1.698822529760946e-06,
      "learning_rate": 4.918550937166331e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 912944,
      "step": 3260
    },
    {
      "epoch": 36.27777777777778,
      "grad_norm": 1.8331402316107415e-06,
      "learning_rate": 4.918302196251415e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 914368,
      "step": 3265
    },
    {
      "epoch": 36.333333333333336,
      "grad_norm": 1.3143907153789769e-06,
      "learning_rate": 4.91805308240391e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 915744,
      "step": 3270
    },
    {
      "epoch": 36.388888888888886,
      "grad_norm": 2.4973840027087135e-06,
      "learning_rate": 4.9178035956622326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 917152,
      "step": 3275
    },
    {
      "epoch": 36.44444444444444,
      "grad_norm": 1.603745204192819e-06,
      "learning_rate": 4.917553736064857e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 918592,
      "step": 3280
    },
    {
      "epoch": 36.5,
      "grad_norm": 1.0375125384598505e-05,
      "learning_rate": 4.917303503650314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 920000,
      "step": 3285
    },
    {
      "epoch": 36.55555555555556,
      "grad_norm": 1.6742454818086117e-06,
      "learning_rate": 4.917052898457194e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 921424,
      "step": 3290
    },
    {
      "epoch": 36.611111111111114,
      "grad_norm": 1.2215729839226697e-05,
      "learning_rate": 4.916801920524141e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 922832,
      "step": 3295
    },
    {
      "epoch": 36.666666666666664,
      "grad_norm": 1.543875328025024e-06,
      "learning_rate": 4.916550569889862e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 924224,
      "step": 3300
    },
    {
      "epoch": 36.72222222222222,
      "grad_norm": 3.25405812873214e-06,
      "learning_rate": 4.916298846593116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 925632,
      "step": 3305
    },
    {
      "epoch": 36.77777777777778,
      "grad_norm": 1.7023172631525085e-06,
      "learning_rate": 4.916046750672722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 927072,
      "step": 3310
    },
    {
      "epoch": 36.833333333333336,
      "grad_norm": 2.214716005255468e-06,
      "learning_rate": 4.915794282167559e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 928432,
      "step": 3315
    },
    {
      "epoch": 36.888888888888886,
      "grad_norm": 1.8495154563424876e-06,
      "learning_rate": 4.915541441116558e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 929840,
      "step": 3320
    },
    {
      "epoch": 36.94444444444444,
      "grad_norm": 1.915127086249413e-06,
      "learning_rate": 4.915288227558711e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 931248,
      "step": 3325
    },
    {
      "epoch": 37.0,
      "grad_norm": 2.0007048533443594e-06,
      "learning_rate": 4.915034641533066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 932656,
      "step": 3330
    },
    {
      "epoch": 37.05555555555556,
      "grad_norm": 2.172646190956584e-06,
      "learning_rate": 4.914780683078731e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 934080,
      "step": 3335
    },
    {
      "epoch": 37.111111111111114,
      "grad_norm": 1.7003003449644893e-05,
      "learning_rate": 4.9145263522348695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 935472,
      "step": 3340
    },
    {
      "epoch": 37.166666666666664,
      "grad_norm": 2.0012282675452298e-06,
      "learning_rate": 4.9142716490407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 936864,
      "step": 3345
    },
    {
      "epoch": 37.22222222222222,
      "grad_norm": 2.065671651507728e-06,
      "learning_rate": 4.914016573535504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 938320,
      "step": 3350
    },
    {
      "epoch": 37.27777777777778,
      "grad_norm": 3.0585445074393647e-06,
      "learning_rate": 4.9137611257586154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 939744,
      "step": 3355
    },
    {
      "epoch": 37.333333333333336,
      "grad_norm": 3.72069689547061e-06,
      "learning_rate": 4.9135053057494274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 941072,
      "step": 3360
    },
    {
      "epoch": 37.388888888888886,
      "grad_norm": 2.2654980966763105e-06,
      "learning_rate": 4.913249113547392e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 942448,
      "step": 3365
    },
    {
      "epoch": 37.44444444444444,
      "grad_norm": 2.8139013465988683e-06,
      "learning_rate": 4.912992549192016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 943824,
      "step": 3370
    },
    {
      "epoch": 37.5,
      "grad_norm": 4.382509814604418e-06,
      "learning_rate": 4.9127356127228665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 945216,
      "step": 3375
    },
    {
      "epoch": 37.55555555555556,
      "grad_norm": 2.6489644824323477e-06,
      "learning_rate": 4.912478304179564e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 946608,
      "step": 3380
    },
    {
      "epoch": 37.611111111111114,
      "grad_norm": 1.8300133888260461e-06,
      "learning_rate": 4.9122206236017896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 947952,
      "step": 3385
    },
    {
      "epoch": 37.666666666666664,
      "grad_norm": 1.977121428353712e-06,
      "learning_rate": 4.911962571029282e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 949344,
      "step": 3390
    },
    {
      "epoch": 37.72222222222222,
      "grad_norm": 2.1198377453401918e-06,
      "learning_rate": 4.9117041465018353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 950720,
      "step": 3395
    },
    {
      "epoch": 37.77777777777778,
      "grad_norm": 1.8909335040007136e-06,
      "learning_rate": 4.911445350059302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 952128,
      "step": 3400
    },
    {
      "epoch": 37.77777777777778,
      "eval_loss": 0.22534139454364777,
      "eval_runtime": 1.3004,
      "eval_samples_per_second": 30.759,
      "eval_steps_per_second": 15.38,
      "num_input_tokens_seen": 952128,
      "step": 3400
    },
    {
      "epoch": 37.833333333333336,
      "grad_norm": 1.4922728723831824e-06,
      "learning_rate": 4.9111861817415905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 953520,
      "step": 3405
    },
    {
      "epoch": 37.888888888888886,
      "grad_norm": 1.5179743968474213e-06,
      "learning_rate": 4.91092664158867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 954928,
      "step": 3410
    },
    {
      "epoch": 37.94444444444444,
      "grad_norm": 2.2312729015538935e-06,
      "learning_rate": 4.910666729640563e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 956320,
      "step": 3415
    },
    {
      "epoch": 38.0,
      "grad_norm": 1.8731125237536617e-06,
      "learning_rate": 4.910406445937353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 957696,
      "step": 3420
    },
    {
      "epoch": 38.05555555555556,
      "grad_norm": 2.568817535575363e-06,
      "learning_rate": 4.9101457905191774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 959056,
      "step": 3425
    },
    {
      "epoch": 38.111111111111114,
      "grad_norm": 2.004659336307668e-06,
      "learning_rate": 4.909884763426233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 960464,
      "step": 3430
    },
    {
      "epoch": 38.166666666666664,
      "grad_norm": 2.2248832465265878e-06,
      "learning_rate": 4.9096233646987736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 961904,
      "step": 3435
    },
    {
      "epoch": 38.22222222222222,
      "grad_norm": 1.6040818309193128e-06,
      "learning_rate": 4.9093615943771104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 963312,
      "step": 3440
    },
    {
      "epoch": 38.27777777777778,
      "grad_norm": 1.6101108712973655e-06,
      "learning_rate": 4.909099452501611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 964672,
      "step": 3445
    },
    {
      "epoch": 38.333333333333336,
      "grad_norm": 1.6054107163654407e-06,
      "learning_rate": 4.908836939112702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 966080,
      "step": 3450
    },
    {
      "epoch": 38.388888888888886,
      "grad_norm": 1.594694708728639e-06,
      "learning_rate": 4.908574054250865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 967456,
      "step": 3455
    },
    {
      "epoch": 38.44444444444444,
      "grad_norm": 1.5057582913868828e-06,
      "learning_rate": 4.9083107979566414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 968832,
      "step": 3460
    },
    {
      "epoch": 38.5,
      "grad_norm": 2.3685131509409985e-06,
      "learning_rate": 4.908047170270628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 970256,
      "step": 3465
    },
    {
      "epoch": 38.55555555555556,
      "grad_norm": 1.5050559341034386e-06,
      "learning_rate": 4.9077831712334784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 971664,
      "step": 3470
    },
    {
      "epoch": 38.611111111111114,
      "grad_norm": 1.8102780359186e-06,
      "learning_rate": 4.907518800885907e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 973104,
      "step": 3475
    },
    {
      "epoch": 38.666666666666664,
      "grad_norm": 1.9253077425673837e-06,
      "learning_rate": 4.907254059268681e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 974496,
      "step": 3480
    },
    {
      "epoch": 38.72222222222222,
      "grad_norm": 2.249076487714774e-06,
      "learning_rate": 4.906988946422628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 975920,
      "step": 3485
    },
    {
      "epoch": 38.77777777777778,
      "grad_norm": 2.0309903447923716e-06,
      "learning_rate": 4.9067234623886315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 977328,
      "step": 3490
    },
    {
      "epoch": 38.833333333333336,
      "grad_norm": 1.6675433016644092e-06,
      "learning_rate": 4.9064576072076316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 978736,
      "step": 3495
    },
    {
      "epoch": 38.888888888888886,
      "grad_norm": 1.93751748156501e-06,
      "learning_rate": 4.906191380920628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 980096,
      "step": 3500
    },
    {
      "epoch": 38.94444444444444,
      "grad_norm": 1.541418441775022e-06,
      "learning_rate": 4.905924783568675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 981520,
      "step": 3505
    },
    {
      "epoch": 39.0,
      "grad_norm": 1.1348030056979042e-05,
      "learning_rate": 4.905657815192886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 982928,
      "step": 3510
    },
    {
      "epoch": 39.05555555555556,
      "grad_norm": 1.6557413573536905e-06,
      "learning_rate": 4.90539047583443e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 984384,
      "step": 3515
    },
    {
      "epoch": 39.111111111111114,
      "grad_norm": 2.5424108116567368e-06,
      "learning_rate": 4.905122765534534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 985824,
      "step": 3520
    },
    {
      "epoch": 39.166666666666664,
      "grad_norm": 8.69053019414423e-06,
      "learning_rate": 4.9048546843344846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 987184,
      "step": 3525
    },
    {
      "epoch": 39.22222222222222,
      "grad_norm": 1.7208448070960003e-06,
      "learning_rate": 4.9045862322756206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 988640,
      "step": 3530
    },
    {
      "epoch": 39.27777777777778,
      "grad_norm": 1.764438820828218e-06,
      "learning_rate": 4.904317409399342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 990000,
      "step": 3535
    },
    {
      "epoch": 39.333333333333336,
      "grad_norm": 2.371839627812733e-06,
      "learning_rate": 4.904048215747104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 991440,
      "step": 3540
    },
    {
      "epoch": 39.388888888888886,
      "grad_norm": 2.828549213518272e-06,
      "learning_rate": 4.90377865136042e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 992832,
      "step": 3545
    },
    {
      "epoch": 39.44444444444444,
      "grad_norm": 1.8115262037099455e-06,
      "learning_rate": 4.90350871628086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 994224,
      "step": 3550
    },
    {
      "epoch": 39.5,
      "grad_norm": 1.988784333661897e-06,
      "learning_rate": 4.903238410550052e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 995616,
      "step": 3555
    },
    {
      "epoch": 39.55555555555556,
      "grad_norm": 1.922566980283591e-06,
      "learning_rate": 4.90296773420968e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 996944,
      "step": 3560
    },
    {
      "epoch": 39.611111111111114,
      "grad_norm": 2.388249185969471e-06,
      "learning_rate": 4.902696687301486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 998368,
      "step": 3565
    },
    {
      "epoch": 39.666666666666664,
      "grad_norm": 1.7381777297487133e-06,
      "learning_rate": 4.902425269867268e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 999792,
      "step": 3570
    },
    {
      "epoch": 39.72222222222222,
      "grad_norm": 1.426454218744766e-06,
      "learning_rate": 4.902153481948883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1001168,
      "step": 3575
    },
    {
      "epoch": 39.77777777777778,
      "grad_norm": 2.528397089918144e-06,
      "learning_rate": 4.901881323588244e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1002576,
      "step": 3580
    },
    {
      "epoch": 39.833333333333336,
      "grad_norm": 2.4630910502310144e-06,
      "learning_rate": 4.90160879482732e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1003952,
      "step": 3585
    },
    {
      "epoch": 39.888888888888886,
      "grad_norm": 1.6251836996161728e-06,
      "learning_rate": 4.9013358957081405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1005312,
      "step": 3590
    },
    {
      "epoch": 39.94444444444444,
      "grad_norm": 1.1237824764975812e-05,
      "learning_rate": 4.901062626272789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1006720,
      "step": 3595
    },
    {
      "epoch": 40.0,
      "grad_norm": 1.8160332047045813e-06,
      "learning_rate": 4.900788986563406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1008096,
      "step": 3600
    },
    {
      "epoch": 40.0,
      "eval_loss": 0.2456374615430832,
      "eval_runtime": 1.2995,
      "eval_samples_per_second": 30.782,
      "eval_steps_per_second": 15.391,
      "num_input_tokens_seen": 1008096,
      "step": 3600
    },
    {
      "epoch": 40.05555555555556,
      "grad_norm": 2.0953319108230062e-05,
      "learning_rate": 4.9005149766221915e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1009488,
      "step": 3605
    },
    {
      "epoch": 40.111111111111114,
      "grad_norm": 1.5157784218899906e-06,
      "learning_rate": 4.9002405964914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1010880,
      "step": 3610
    },
    {
      "epoch": 40.166666666666664,
      "grad_norm": 1.2410692761477549e-05,
      "learning_rate": 4.899965846213346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1012224,
      "step": 3615
    },
    {
      "epoch": 40.22222222222222,
      "grad_norm": 1.658799988035753e-06,
      "learning_rate": 4.899690725830399e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1013648,
      "step": 3620
    },
    {
      "epoch": 40.27777777777778,
      "grad_norm": 1.5267685284925392e-06,
      "learning_rate": 4.899415235384985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1015088,
      "step": 3625
    },
    {
      "epoch": 40.333333333333336,
      "grad_norm": 1.379135028400924e-06,
      "learning_rate": 4.899139374919589e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1016528,
      "step": 3630
    },
    {
      "epoch": 40.388888888888886,
      "grad_norm": 1.7389500044373563e-06,
      "learning_rate": 4.898863144476752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1017920,
      "step": 3635
    },
    {
      "epoch": 40.44444444444444,
      "grad_norm": 5.978025455988245e-06,
      "learning_rate": 4.898586544099072e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1019312,
      "step": 3640
    },
    {
      "epoch": 40.5,
      "grad_norm": 1.6262860071947216e-06,
      "learning_rate": 4.898309573829204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1020736,
      "step": 3645
    },
    {
      "epoch": 40.55555555555556,
      "grad_norm": 1.6658181039019837e-06,
      "learning_rate": 4.898032233709862e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1022096,
      "step": 3650
    },
    {
      "epoch": 40.611111111111114,
      "grad_norm": 2.0455411231523613e-06,
      "learning_rate": 4.8977545237838123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1023440,
      "step": 3655
    },
    {
      "epoch": 40.666666666666664,
      "grad_norm": 1.7508117480247165e-06,
      "learning_rate": 4.8974764440938836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1024800,
      "step": 3660
    },
    {
      "epoch": 40.72222222222222,
      "grad_norm": 1.8012153759627836e-06,
      "learning_rate": 4.897197994682959e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1026240,
      "step": 3665
    },
    {
      "epoch": 40.77777777777778,
      "grad_norm": 1.4252462960939738e-06,
      "learning_rate": 4.8969191755939786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1027696,
      "step": 3670
    },
    {
      "epoch": 40.833333333333336,
      "grad_norm": 1.4042608427189407e-06,
      "learning_rate": 4.8966399868699396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1029088,
      "step": 3675
    },
    {
      "epoch": 40.888888888888886,
      "grad_norm": 1.8681701021705521e-06,
      "learning_rate": 4.8963604285538965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1030448,
      "step": 3680
    },
    {
      "epoch": 40.94444444444444,
      "grad_norm": 1.9818787677650107e-06,
      "learning_rate": 4.8960805006889604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1031904,
      "step": 3685
    },
    {
      "epoch": 41.0,
      "grad_norm": 7.82491042627953e-06,
      "learning_rate": 4.8958002033183004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1033312,
      "step": 3690
    },
    {
      "epoch": 41.05555555555556,
      "grad_norm": 1.7957586351258215e-06,
      "learning_rate": 4.8955195364851414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1034752,
      "step": 3695
    },
    {
      "epoch": 41.111111111111114,
      "grad_norm": 1.7685500779407448e-06,
      "learning_rate": 4.895238500232766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1036144,
      "step": 3700
    },
    {
      "epoch": 41.166666666666664,
      "grad_norm": 2.3568225060444092e-06,
      "learning_rate": 4.8949570946045143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1037536,
      "step": 3705
    },
    {
      "epoch": 41.22222222222222,
      "grad_norm": 1.6558540210098727e-06,
      "learning_rate": 4.89467531964378e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1038928,
      "step": 3710
    },
    {
      "epoch": 41.27777777777778,
      "grad_norm": 2.1219327663857257e-06,
      "learning_rate": 4.894393175394019e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1040288,
      "step": 3715
    },
    {
      "epoch": 41.333333333333336,
      "grad_norm": 1.7607494555704761e-06,
      "learning_rate": 4.8941106618987406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1041664,
      "step": 3720
    },
    {
      "epoch": 41.388888888888886,
      "grad_norm": 1.8644883539309376e-06,
      "learning_rate": 4.893827779201512e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1043024,
      "step": 3725
    },
    {
      "epoch": 41.44444444444444,
      "grad_norm": 1.698240225778136e-06,
      "learning_rate": 4.893544527345957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1044416,
      "step": 3730
    },
    {
      "epoch": 41.5,
      "grad_norm": 1.6085525658127153e-06,
      "learning_rate": 4.8932609063757563e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1045840,
      "step": 3735
    },
    {
      "epoch": 41.55555555555556,
      "grad_norm": 1.9322226307849633e-06,
      "learning_rate": 4.8929769163346484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1047248,
      "step": 3740
    },
    {
      "epoch": 41.611111111111114,
      "grad_norm": 1.8410980828775791e-06,
      "learning_rate": 4.892692557266429e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1048640,
      "step": 3745
    },
    {
      "epoch": 41.666666666666664,
      "grad_norm": 1.946952579601202e-06,
      "learning_rate": 4.8924078292149464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1050064,
      "step": 3750
    },
    {
      "epoch": 41.72222222222222,
      "grad_norm": 1.6215352616200107e-06,
      "learning_rate": 4.892122732224114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1051440,
      "step": 3755
    },
    {
      "epoch": 41.77777777777778,
      "grad_norm": 1.0690247108868789e-05,
      "learning_rate": 4.8918372663378944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1052800,
      "step": 3760
    },
    {
      "epoch": 41.833333333333336,
      "grad_norm": 1.5269470168277621e-06,
      "learning_rate": 4.89155143160031e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1054208,
      "step": 3765
    },
    {
      "epoch": 41.888888888888886,
      "grad_norm": 1.603056261956226e-06,
      "learning_rate": 4.891265228055441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1055600,
      "step": 3770
    },
    {
      "epoch": 41.94444444444444,
      "grad_norm": 1.433971306141757e-06,
      "learning_rate": 4.890978655747424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1057040,
      "step": 3775
    },
    {
      "epoch": 42.0,
      "grad_norm": 1.7586417015991174e-06,
      "learning_rate": 4.89069171472045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1058448,
      "step": 3780
    },
    {
      "epoch": 42.05555555555556,
      "grad_norm": 1.6286720665448229e-06,
      "learning_rate": 4.890404405018772e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1059792,
      "step": 3785
    },
    {
      "epoch": 42.111111111111114,
      "grad_norm": 7.285990704986034e-06,
      "learning_rate": 4.8901167266866934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1061200,
      "step": 3790
    },
    {
      "epoch": 42.166666666666664,
      "grad_norm": 1.6592134670645464e-06,
      "learning_rate": 4.88982867976858e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1062560,
      "step": 3795
    },
    {
      "epoch": 42.22222222222222,
      "grad_norm": 1.8796104086504783e-06,
      "learning_rate": 4.889540264308852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1063984,
      "step": 3800
    },
    {
      "epoch": 42.22222222222222,
      "eval_loss": 0.26800304651260376,
      "eval_runtime": 1.3262,
      "eval_samples_per_second": 30.161,
      "eval_steps_per_second": 15.081,
      "num_input_tokens_seen": 1063984,
      "step": 3800
    },
    {
      "epoch": 42.27777777777778,
      "grad_norm": 1.506619469182624e-06,
      "learning_rate": 4.889251480351986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1065392,
      "step": 3805
    },
    {
      "epoch": 42.333333333333336,
      "grad_norm": 1.422245418325474e-06,
      "learning_rate": 4.888962327942517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1066784,
      "step": 3810
    },
    {
      "epoch": 42.388888888888886,
      "grad_norm": 1.4239117263059597e-06,
      "learning_rate": 4.8886728071250356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1068208,
      "step": 3815
    },
    {
      "epoch": 42.44444444444444,
      "grad_norm": 1.3670691032530158e-06,
      "learning_rate": 4.8883829179441884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1069616,
      "step": 3820
    },
    {
      "epoch": 42.5,
      "grad_norm": 1.7086169918911764e-06,
      "learning_rate": 4.888092660444682e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1071024,
      "step": 3825
    },
    {
      "epoch": 42.55555555555556,
      "grad_norm": 1.8859019519368303e-06,
      "learning_rate": 4.887802034671276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1072448,
      "step": 3830
    },
    {
      "epoch": 42.611111111111114,
      "grad_norm": 1.958510665645008e-06,
      "learning_rate": 4.88751104066879e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1073808,
      "step": 3835
    },
    {
      "epoch": 42.666666666666664,
      "grad_norm": 2.0258901258785045e-06,
      "learning_rate": 4.887219678482098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1075232,
      "step": 3840
    },
    {
      "epoch": 42.72222222222222,
      "grad_norm": 1.0052222023659851e-05,
      "learning_rate": 4.8869279481561316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1076624,
      "step": 3845
    },
    {
      "epoch": 42.77777777777778,
      "grad_norm": 1.990064220080967e-06,
      "learning_rate": 4.88663584973588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1078016,
      "step": 3850
    },
    {
      "epoch": 42.833333333333336,
      "grad_norm": 1.5724319837318035e-06,
      "learning_rate": 4.8863433832663874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1079440,
      "step": 3855
    },
    {
      "epoch": 42.888888888888886,
      "grad_norm": 1.5814953258086462e-06,
      "learning_rate": 4.886050548792757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1080800,
      "step": 3860
    },
    {
      "epoch": 42.94444444444444,
      "grad_norm": 2.3226881239679642e-05,
      "learning_rate": 4.8857573463601465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1082240,
      "step": 3865
    },
    {
      "epoch": 43.0,
      "grad_norm": 2.5028275558725e-06,
      "learning_rate": 4.885463776013772e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1083632,
      "step": 3870
    },
    {
      "epoch": 43.05555555555556,
      "grad_norm": 1.7089873836084735e-06,
      "learning_rate": 4.8851698377989056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1085088,
      "step": 3875
    },
    {
      "epoch": 43.111111111111114,
      "grad_norm": 1.5459917221960495e-06,
      "learning_rate": 4.884875531760876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1086496,
      "step": 3880
    },
    {
      "epoch": 43.166666666666664,
      "grad_norm": 1.507967112956976e-06,
      "learning_rate": 4.88458085794507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1087888,
      "step": 3885
    },
    {
      "epoch": 43.22222222222222,
      "grad_norm": 1.5273221833922435e-06,
      "learning_rate": 4.884285816396929e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1089280,
      "step": 3890
    },
    {
      "epoch": 43.27777777777778,
      "grad_norm": 1.3422095435089432e-06,
      "learning_rate": 4.8839904071619526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1090688,
      "step": 3895
    },
    {
      "epoch": 43.333333333333336,
      "grad_norm": 1.6717743847038946e-06,
      "learning_rate": 4.8836946302856955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1092096,
      "step": 3900
    },
    {
      "epoch": 43.388888888888886,
      "grad_norm": 2.8606948490050854e-06,
      "learning_rate": 4.8833984858137715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1093456,
      "step": 3905
    },
    {
      "epoch": 43.44444444444444,
      "grad_norm": 1.3483455404639244e-05,
      "learning_rate": 4.8831019737918494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1094880,
      "step": 3910
    },
    {
      "epoch": 43.5,
      "grad_norm": 1.5692146462242818e-06,
      "learning_rate": 4.882805094265655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1096288,
      "step": 3915
    },
    {
      "epoch": 43.55555555555556,
      "grad_norm": 1.4018779666002956e-06,
      "learning_rate": 4.8825078472809706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1097648,
      "step": 3920
    },
    {
      "epoch": 43.611111111111114,
      "grad_norm": 1.381150013912702e-06,
      "learning_rate": 4.882210232883635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1099024,
      "step": 3925
    },
    {
      "epoch": 43.666666666666664,
      "grad_norm": 2.4190492240450112e-06,
      "learning_rate": 4.881912251119546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1100464,
      "step": 3930
    },
    {
      "epoch": 43.72222222222222,
      "grad_norm": 1.8514303974370705e-06,
      "learning_rate": 4.881613902034654e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1101904,
      "step": 3935
    },
    {
      "epoch": 43.77777777777778,
      "grad_norm": 1.4606306422138005e-06,
      "learning_rate": 4.88131518567497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1103296,
      "step": 3940
    },
    {
      "epoch": 43.833333333333336,
      "grad_norm": 1.4660629403806524e-06,
      "learning_rate": 4.881016102086558e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1104704,
      "step": 3945
    },
    {
      "epoch": 43.888888888888886,
      "grad_norm": 1.998954758164473e-06,
      "learning_rate": 4.8807166513155425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1106112,
      "step": 3950
    },
    {
      "epoch": 43.94444444444444,
      "grad_norm": 1.2915032812088612e-06,
      "learning_rate": 4.8804168334081004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1107504,
      "step": 3955
    },
    {
      "epoch": 44.0,
      "grad_norm": 1.4037229902896797e-06,
      "learning_rate": 4.880116648410468e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1108928,
      "step": 3960
    },
    {
      "epoch": 44.05555555555556,
      "grad_norm": 1.655043661230593e-06,
      "learning_rate": 4.879816096368939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1110352,
      "step": 3965
    },
    {
      "epoch": 44.111111111111114,
      "grad_norm": 1.6899351749088964e-06,
      "learning_rate": 4.879515177329861e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1111744,
      "step": 3970
    },
    {
      "epoch": 44.166666666666664,
      "grad_norm": 5.807175057270797e-06,
      "learning_rate": 4.8792138913396394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1113120,
      "step": 3975
    },
    {
      "epoch": 44.22222222222222,
      "grad_norm": 1.8093041944666766e-06,
      "learning_rate": 4.8789122384447374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1114544,
      "step": 3980
    },
    {
      "epoch": 44.27777777777778,
      "grad_norm": 1.6985715774353594e-05,
      "learning_rate": 4.878610218691673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1115920,
      "step": 3985
    },
    {
      "epoch": 44.333333333333336,
      "grad_norm": 1.4552598486261559e-06,
      "learning_rate": 4.87830783212702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1117280,
      "step": 3990
    },
    {
      "epoch": 44.388888888888886,
      "grad_norm": 2.6939491363009438e-05,
      "learning_rate": 4.878005078797413e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1118672,
      "step": 3995
    },
    {
      "epoch": 44.44444444444444,
      "grad_norm": 2.1602500055450946e-06,
      "learning_rate": 4.877701958749539e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1120080,
      "step": 4000
    },
    {
      "epoch": 44.44444444444444,
      "eval_loss": 0.2292131930589676,
      "eval_runtime": 1.3172,
      "eval_samples_per_second": 30.368,
      "eval_steps_per_second": 15.184,
      "num_input_tokens_seen": 1120080,
      "step": 4000
    },
    {
      "epoch": 44.5,
      "grad_norm": 1.5559194253000896e-06,
      "learning_rate": 4.877398472030142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1121440,
      "step": 4005
    },
    {
      "epoch": 44.55555555555556,
      "grad_norm": 6.229448899830459e-06,
      "learning_rate": 4.877094618686024e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1122848,
      "step": 4010
    },
    {
      "epoch": 44.611111111111114,
      "grad_norm": 2.6773625450005056e-06,
      "learning_rate": 4.876790398764045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1124272,
      "step": 4015
    },
    {
      "epoch": 44.666666666666664,
      "grad_norm": 1.656476683820074e-06,
      "learning_rate": 4.8764858123111167e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1125648,
      "step": 4020
    },
    {
      "epoch": 44.72222222222222,
      "grad_norm": 1.588678856023762e-06,
      "learning_rate": 4.876180859374212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1127072,
      "step": 4025
    },
    {
      "epoch": 44.77777777777778,
      "grad_norm": 1.281916979678499e-06,
      "learning_rate": 4.875875540000357e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1128480,
      "step": 4030
    },
    {
      "epoch": 44.833333333333336,
      "grad_norm": 1.3057069736532867e-06,
      "learning_rate": 4.8755698542366376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1129904,
      "step": 4035
    },
    {
      "epoch": 44.888888888888886,
      "grad_norm": 1.3639353255712194e-06,
      "learning_rate": 4.875263802130193e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1131328,
      "step": 4040
    },
    {
      "epoch": 44.94444444444444,
      "grad_norm": 1.40620090860466e-06,
      "learning_rate": 4.8749573837282207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1132720,
      "step": 4045
    },
    {
      "epoch": 45.0,
      "grad_norm": 1.8163642607760266e-06,
      "learning_rate": 4.874650599077974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1134128,
      "step": 4050
    },
    {
      "epoch": 45.05555555555556,
      "grad_norm": 1.1456099855422508e-06,
      "learning_rate": 4.874343448226764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1135552,
      "step": 4055
    },
    {
      "epoch": 45.111111111111114,
      "grad_norm": 1.4261248679758864e-06,
      "learning_rate": 4.874035931221955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1136960,
      "step": 4060
    },
    {
      "epoch": 45.166666666666664,
      "grad_norm": 2.0787433641089592e-06,
      "learning_rate": 4.8737280481109724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1138352,
      "step": 4065
    },
    {
      "epoch": 45.22222222222222,
      "grad_norm": 1.0885944902838673e-05,
      "learning_rate": 4.873419798941294e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1139760,
      "step": 4070
    },
    {
      "epoch": 45.27777777777778,
      "grad_norm": 1.5734617591078859e-06,
      "learning_rate": 4.873111183760458e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1141184,
      "step": 4075
    },
    {
      "epoch": 45.333333333333336,
      "grad_norm": 1.8427869008519338e-06,
      "learning_rate": 4.8728022026160537e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1142560,
      "step": 4080
    },
    {
      "epoch": 45.388888888888886,
      "grad_norm": 1.7758819694790873e-06,
      "learning_rate": 4.872492855555732e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1143920,
      "step": 4085
    },
    {
      "epoch": 45.44444444444444,
      "grad_norm": 1.5798763115526526e-06,
      "learning_rate": 4.8721831426271956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1145312,
      "step": 4090
    },
    {
      "epoch": 45.5,
      "grad_norm": 1.1530300980666652e-05,
      "learning_rate": 4.87187306387821e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1146736,
      "step": 4095
    },
    {
      "epoch": 45.55555555555556,
      "grad_norm": 3.629762886703247e-06,
      "learning_rate": 4.87156261935659e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1148160,
      "step": 4100
    },
    {
      "epoch": 45.611111111111114,
      "grad_norm": 1.6208466604439309e-06,
      "learning_rate": 4.871251809110211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1149568,
      "step": 4105
    },
    {
      "epoch": 45.666666666666664,
      "grad_norm": 2.4492987904523034e-06,
      "learning_rate": 4.8709406331870044e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1150944,
      "step": 4110
    },
    {
      "epoch": 45.72222222222222,
      "grad_norm": 1.538481001261971e-06,
      "learning_rate": 4.8706290916349574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1152352,
      "step": 4115
    },
    {
      "epoch": 45.77777777777778,
      "grad_norm": 2.3938159756653477e-06,
      "learning_rate": 4.8703171845021134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1153760,
      "step": 4120
    },
    {
      "epoch": 45.833333333333336,
      "grad_norm": 2.962878170365002e-06,
      "learning_rate": 4.870004911836572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1155168,
      "step": 4125
    },
    {
      "epoch": 45.888888888888886,
      "grad_norm": 1.0895876584982034e-05,
      "learning_rate": 4.869692273686489e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1156560,
      "step": 4130
    },
    {
      "epoch": 45.94444444444444,
      "grad_norm": 2.5737210762599716e-06,
      "learning_rate": 4.869379270100079e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1157952,
      "step": 4135
    },
    {
      "epoch": 46.0,
      "grad_norm": 1.875751308944018e-06,
      "learning_rate": 4.86906590112561e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1159328,
      "step": 4140
    },
    {
      "epoch": 46.05555555555556,
      "grad_norm": 2.8720946829707827e-06,
      "learning_rate": 4.8687521668114064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1160720,
      "step": 4145
    },
    {
      "epoch": 46.111111111111114,
      "grad_norm": 1.431240434612846e-06,
      "learning_rate": 4.868438067205853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1162112,
      "step": 4150
    },
    {
      "epoch": 46.166666666666664,
      "grad_norm": 1.5439906064784736e-06,
      "learning_rate": 4.8681236023573844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1163536,
      "step": 4155
    },
    {
      "epoch": 46.22222222222222,
      "grad_norm": 1.4775779391129618e-06,
      "learning_rate": 4.867808772314497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1164992,
      "step": 4160
    },
    {
      "epoch": 46.27777777777778,
      "grad_norm": 1.6270188325506751e-06,
      "learning_rate": 4.867493577125741e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1166432,
      "step": 4165
    },
    {
      "epoch": 46.333333333333336,
      "grad_norm": 1.2270692195670563e-06,
      "learning_rate": 4.867178016839725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1167840,
      "step": 4170
    },
    {
      "epoch": 46.388888888888886,
      "grad_norm": 2.58865861724189e-06,
      "learning_rate": 4.8668620915051094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1169232,
      "step": 4175
    },
    {
      "epoch": 46.44444444444444,
      "grad_norm": 1.3363769539864734e-06,
      "learning_rate": 4.866545801170616e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1170624,
      "step": 4180
    },
    {
      "epoch": 46.5,
      "grad_norm": 2.1943426418147283e-06,
      "learning_rate": 4.86622914588502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1172048,
      "step": 4185
    },
    {
      "epoch": 46.55555555555556,
      "grad_norm": 2.2543542854691623e-06,
      "learning_rate": 4.865912125697154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1173456,
      "step": 4190
    },
    {
      "epoch": 46.611111111111114,
      "grad_norm": 1.612966116226744e-06,
      "learning_rate": 4.865594740655907e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1174864,
      "step": 4195
    },
    {
      "epoch": 46.666666666666664,
      "grad_norm": 1.4625477433583e-06,
      "learning_rate": 4.865276990810222e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1176240,
      "step": 4200
    },
    {
      "epoch": 46.666666666666664,
      "eval_loss": 0.24723908305168152,
      "eval_runtime": 1.3191,
      "eval_samples_per_second": 30.324,
      "eval_steps_per_second": 15.162,
      "num_input_tokens_seen": 1176240,
      "step": 4200
    },
    {
      "epoch": 46.72222222222222,
      "grad_norm": 1.666215325712983e-06,
      "learning_rate": 4.8649588762091016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1177616,
      "step": 4205
    },
    {
      "epoch": 46.77777777777778,
      "grad_norm": 1.3951591881777858e-06,
      "learning_rate": 4.8646403969016016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1178992,
      "step": 4210
    },
    {
      "epoch": 46.833333333333336,
      "grad_norm": 1.4432250736717833e-06,
      "learning_rate": 4.864321552936838e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1180384,
      "step": 4215
    },
    {
      "epoch": 46.888888888888886,
      "grad_norm": 1.5195007563306717e-06,
      "learning_rate": 4.864002344363978e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1181760,
      "step": 4220
    },
    {
      "epoch": 46.94444444444444,
      "grad_norm": 1.46597574257612e-06,
      "learning_rate": 4.863682771232248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1183184,
      "step": 4225
    },
    {
      "epoch": 47.0,
      "grad_norm": 1.3673759440280264e-06,
      "learning_rate": 4.8633628335909324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1184576,
      "step": 4230
    },
    {
      "epoch": 47.05555555555556,
      "grad_norm": 1.4822222738075652e-06,
      "learning_rate": 4.8630425314893676e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1185952,
      "step": 4235
    },
    {
      "epoch": 47.111111111111114,
      "grad_norm": 1.7522110056233942e-06,
      "learning_rate": 4.862721864976948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1187360,
      "step": 4240
    },
    {
      "epoch": 47.166666666666664,
      "grad_norm": 1.251180947292596e-06,
      "learning_rate": 4.862400834103125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1188784,
      "step": 4245
    },
    {
      "epoch": 47.22222222222222,
      "grad_norm": 1.955820152943488e-06,
      "learning_rate": 4.862079438917406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1190192,
      "step": 4250
    },
    {
      "epoch": 47.27777777777778,
      "grad_norm": 1.4548380704582087e-06,
      "learning_rate": 4.8617576794693536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1191584,
      "step": 4255
    },
    {
      "epoch": 47.333333333333336,
      "grad_norm": 4.7600249672541395e-05,
      "learning_rate": 4.8614355558085875e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1192976,
      "step": 4260
    },
    {
      "epoch": 47.388888888888886,
      "grad_norm": 1.6692788449290674e-06,
      "learning_rate": 4.861113067984783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1194336,
      "step": 4265
    },
    {
      "epoch": 47.44444444444444,
      "grad_norm": 1.7454195813115803e-06,
      "learning_rate": 4.860790216047671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1195760,
      "step": 4270
    },
    {
      "epoch": 47.5,
      "grad_norm": 1.4930641327737249e-06,
      "learning_rate": 4.860467000047041e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1197104,
      "step": 4275
    },
    {
      "epoch": 47.55555555555556,
      "grad_norm": 4.0621516745886765e-06,
      "learning_rate": 4.860143420032737e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1198496,
      "step": 4280
    },
    {
      "epoch": 47.611111111111114,
      "grad_norm": 1.2182196087451302e-06,
      "learning_rate": 4.859819476054657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1199888,
      "step": 4285
    },
    {
      "epoch": 47.666666666666664,
      "grad_norm": 1.946790916917962e-06,
      "learning_rate": 4.859495168162758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1201296,
      "step": 4290
    },
    {
      "epoch": 47.72222222222222,
      "grad_norm": 1.3806796914650477e-06,
      "learning_rate": 4.859170496407054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1202672,
      "step": 4295
    },
    {
      "epoch": 47.77777777777778,
      "grad_norm": 1.552563162476872e-06,
      "learning_rate": 4.8588454608376114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1204080,
      "step": 4300
    },
    {
      "epoch": 47.833333333333336,
      "grad_norm": 1.0416362101750565e-06,
      "learning_rate": 4.8585200615045555e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1205472,
      "step": 4305
    },
    {
      "epoch": 47.888888888888886,
      "grad_norm": 1.4930845964045147e-06,
      "learning_rate": 4.8581942984580674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1206944,
      "step": 4310
    },
    {
      "epoch": 47.94444444444444,
      "grad_norm": 1.4138267943053506e-06,
      "learning_rate": 4.857868171748384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1208416,
      "step": 4315
    },
    {
      "epoch": 48.0,
      "grad_norm": 1.4877656440148712e-06,
      "learning_rate": 4.8575416814257976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1209792,
      "step": 4320
    },
    {
      "epoch": 48.05555555555556,
      "grad_norm": 1.5316701365009067e-06,
      "learning_rate": 4.857214827540657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1211232,
      "step": 4325
    },
    {
      "epoch": 48.111111111111114,
      "grad_norm": 1.5770915524626616e-06,
      "learning_rate": 4.856887610143367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1212592,
      "step": 4330
    },
    {
      "epoch": 48.166666666666664,
      "grad_norm": 1.4164081676426576e-06,
      "learning_rate": 4.8565600292843896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1213984,
      "step": 4335
    },
    {
      "epoch": 48.22222222222222,
      "grad_norm": 1.3901158126827795e-06,
      "learning_rate": 4.856232085014241e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1215456,
      "step": 4340
    },
    {
      "epoch": 48.27777777777778,
      "grad_norm": 1.0560817827354185e-05,
      "learning_rate": 4.855903777383495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1216912,
      "step": 4345
    },
    {
      "epoch": 48.333333333333336,
      "grad_norm": 2.1063979147584178e-06,
      "learning_rate": 4.85557510644278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1218352,
      "step": 4350
    },
    {
      "epoch": 48.388888888888886,
      "grad_norm": 1.7622420500629232e-06,
      "learning_rate": 4.855246072242782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1219712,
      "step": 4355
    },
    {
      "epoch": 48.44444444444444,
      "grad_norm": 5.304242677084403e-06,
      "learning_rate": 4.8549166748342414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1221120,
      "step": 4360
    },
    {
      "epoch": 48.5,
      "grad_norm": 1.3950465245216037e-06,
      "learning_rate": 4.8545869142679556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1222448,
      "step": 4365
    },
    {
      "epoch": 48.55555555555556,
      "grad_norm": 1.294527805839607e-06,
      "learning_rate": 4.8542567905947776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1223808,
      "step": 4370
    },
    {
      "epoch": 48.611111111111114,
      "grad_norm": 1.4880123444527271e-06,
      "learning_rate": 4.853926303865618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1225200,
      "step": 4375
    },
    {
      "epoch": 48.666666666666664,
      "grad_norm": 1.3450943470161292e-06,
      "learning_rate": 4.853595454131441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1226560,
      "step": 4380
    },
    {
      "epoch": 48.72222222222222,
      "grad_norm": 1.414160692547739e-06,
      "learning_rate": 4.8532642414432674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1227952,
      "step": 4385
    },
    {
      "epoch": 48.77777777777778,
      "grad_norm": 1.4029936892256956e-06,
      "learning_rate": 4.8529326658521754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1229376,
      "step": 4390
    },
    {
      "epoch": 48.833333333333336,
      "grad_norm": 7.376646863122005e-06,
      "learning_rate": 4.8526007274092965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1230768,
      "step": 4395
    },
    {
      "epoch": 48.888888888888886,
      "grad_norm": 1.7502494529253454e-06,
      "learning_rate": 4.852268426165822e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1232160,
      "step": 4400
    },
    {
      "epoch": 48.888888888888886,
      "eval_loss": 0.2371339350938797,
      "eval_runtime": 1.3264,
      "eval_samples_per_second": 30.157,
      "eval_steps_per_second": 15.078,
      "num_input_tokens_seen": 1232160,
      "step": 4400
    },
    {
      "epoch": 48.94444444444444,
      "grad_norm": 1.2076543498551473e-06,
      "learning_rate": 4.851935762172995e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1233584,
      "step": 4405
    },
    {
      "epoch": 49.0,
      "grad_norm": 4.8116953621502034e-06,
      "learning_rate": 4.8516027354821175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1234976,
      "step": 4410
    },
    {
      "epoch": 49.05555555555556,
      "grad_norm": 1.6135722944454756e-06,
      "learning_rate": 4.851269346144546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1236320,
      "step": 4415
    },
    {
      "epoch": 49.111111111111114,
      "grad_norm": 5.962472641840577e-06,
      "learning_rate": 4.850935594211693e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1237760,
      "step": 4420
    },
    {
      "epoch": 49.166666666666664,
      "grad_norm": 1.3599753856397001e-06,
      "learning_rate": 4.850601479735029e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1239168,
      "step": 4425
    },
    {
      "epoch": 49.22222222222222,
      "grad_norm": 1.5728755897725932e-06,
      "learning_rate": 4.850267002766076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1240592,
      "step": 4430
    },
    {
      "epoch": 49.27777777777778,
      "grad_norm": 1.97625081455044e-06,
      "learning_rate": 4.849932163356417e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1242000,
      "step": 4435
    },
    {
      "epoch": 49.333333333333336,
      "grad_norm": 1.3812634733767482e-06,
      "learning_rate": 4.8495969615576864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1243408,
      "step": 4440
    },
    {
      "epoch": 49.388888888888886,
      "grad_norm": 1.1802657354564872e-05,
      "learning_rate": 4.849261397421577e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1244816,
      "step": 4445
    },
    {
      "epoch": 49.44444444444444,
      "grad_norm": 1.3930907698522788e-06,
      "learning_rate": 4.848925470999839e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1246256,
      "step": 4450
    },
    {
      "epoch": 49.5,
      "grad_norm": 1.1616599522312754e-06,
      "learning_rate": 4.848589182344273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1247664,
      "step": 4455
    },
    {
      "epoch": 49.55555555555556,
      "grad_norm": 1.480893502048275e-06,
      "learning_rate": 4.848252531506742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1249072,
      "step": 4460
    },
    {
      "epoch": 49.611111111111114,
      "grad_norm": 1.2988548405701295e-06,
      "learning_rate": 4.847915518539161e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1250464,
      "step": 4465
    },
    {
      "epoch": 49.666666666666664,
      "grad_norm": 1.4156736369841383e-06,
      "learning_rate": 4.847578143493501e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1251856,
      "step": 4470
    },
    {
      "epoch": 49.72222222222222,
      "grad_norm": 2.399377535766689e-06,
      "learning_rate": 4.847240406421789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1253248,
      "step": 4475
    },
    {
      "epoch": 49.77777777777778,
      "grad_norm": 1.2458290257200133e-06,
      "learning_rate": 4.84690230737611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1254592,
      "step": 4480
    },
    {
      "epoch": 49.833333333333336,
      "grad_norm": 1.4283347127275192e-06,
      "learning_rate": 4.846563846408602e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1255984,
      "step": 4485
    },
    {
      "epoch": 49.888888888888886,
      "grad_norm": 1.6209298792091431e-06,
      "learning_rate": 4.84622502357146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1257408,
      "step": 4490
    },
    {
      "epoch": 49.94444444444444,
      "grad_norm": 6.8652097979793325e-06,
      "learning_rate": 4.8458858389169345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1258752,
      "step": 4495
    },
    {
      "epoch": 50.0,
      "grad_norm": 1.5114729876586352e-06,
      "learning_rate": 4.8455462924973334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1260144,
      "step": 4500
    },
    {
      "epoch": 50.05555555555556,
      "grad_norm": 1.5551875094388379e-06,
      "learning_rate": 4.845206384365018e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1261552,
      "step": 4505
    },
    {
      "epoch": 50.111111111111114,
      "grad_norm": 1.4766764024898293e-06,
      "learning_rate": 4.844866114572405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1262944,
      "step": 4510
    },
    {
      "epoch": 50.166666666666664,
      "grad_norm": 1.8972315274368157e-06,
      "learning_rate": 4.8445254831719706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1264336,
      "step": 4515
    },
    {
      "epoch": 50.22222222222222,
      "grad_norm": 1.2971376008863444e-06,
      "learning_rate": 4.8441844902162434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1265728,
      "step": 4520
    },
    {
      "epoch": 50.27777777777778,
      "grad_norm": 1.3411965937848436e-06,
      "learning_rate": 4.843843135757809e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1267184,
      "step": 4525
    },
    {
      "epoch": 50.333333333333336,
      "grad_norm": 1.08900112536503e-05,
      "learning_rate": 4.843501419849308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1268592,
      "step": 4530
    },
    {
      "epoch": 50.388888888888886,
      "grad_norm": 1.31861293084512e-06,
      "learning_rate": 4.8431593425434386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1270032,
      "step": 4535
    },
    {
      "epoch": 50.44444444444444,
      "grad_norm": 1.2466025509638712e-06,
      "learning_rate": 4.8428169038929526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1271376,
      "step": 4540
    },
    {
      "epoch": 50.5,
      "grad_norm": 1.3363543303057668e-06,
      "learning_rate": 4.8424741039506575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1272784,
      "step": 4545
    },
    {
      "epoch": 50.55555555555556,
      "grad_norm": 1.2640809927688679e-06,
      "learning_rate": 4.842130942769419e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1274192,
      "step": 4550
    },
    {
      "epoch": 50.611111111111114,
      "grad_norm": 1.3994612118040095e-06,
      "learning_rate": 4.841787420402156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1275584,
      "step": 4555
    },
    {
      "epoch": 50.666666666666664,
      "grad_norm": 1.4078298136155354e-06,
      "learning_rate": 4.841443536901844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1277008,
      "step": 4560
    },
    {
      "epoch": 50.72222222222222,
      "grad_norm": 1.7492084225523286e-06,
      "learning_rate": 4.841099292321514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1278432,
      "step": 4565
    },
    {
      "epoch": 50.77777777777778,
      "grad_norm": 1.1549035434654797e-06,
      "learning_rate": 4.8407546867142525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1279808,
      "step": 4570
    },
    {
      "epoch": 50.833333333333336,
      "grad_norm": 8.28489828563761e-06,
      "learning_rate": 4.840409720133203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1281152,
      "step": 4575
    },
    {
      "epoch": 50.888888888888886,
      "grad_norm": 1.4844837323835236e-06,
      "learning_rate": 4.8400643926315634e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1282592,
      "step": 4580
    },
    {
      "epoch": 50.94444444444444,
      "grad_norm": 1.2163859537395183e-06,
      "learning_rate": 4.839718704262587e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1283968,
      "step": 4585
    },
    {
      "epoch": 51.0,
      "grad_norm": 1.0931793212876073e-06,
      "learning_rate": 4.839372655079585e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1285344,
      "step": 4590
    },
    {
      "epoch": 51.05555555555556,
      "grad_norm": 1.5230278904709849e-06,
      "learning_rate": 4.83902624513592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1286768,
      "step": 4595
    },
    {
      "epoch": 51.111111111111114,
      "grad_norm": 1.253954337698815e-06,
      "learning_rate": 4.838679474485014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1288160,
      "step": 4600
    },
    {
      "epoch": 51.111111111111114,
      "eval_loss": 0.2620989680290222,
      "eval_runtime": 1.3109,
      "eval_samples_per_second": 30.514,
      "eval_steps_per_second": 15.257,
      "num_input_tokens_seen": 1288160,
      "step": 4600
    },
    {
      "epoch": 51.166666666666664,
      "grad_norm": 1.4476887599812471e-06,
      "learning_rate": 4.838332343180343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1289536,
      "step": 4605
    },
    {
      "epoch": 51.22222222222222,
      "grad_norm": 1.0380126695963554e-06,
      "learning_rate": 4.83798485127544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1290912,
      "step": 4610
    },
    {
      "epoch": 51.27777777777778,
      "grad_norm": 1.0077767456095899e-06,
      "learning_rate": 4.837636998823892e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1292304,
      "step": 4615
    },
    {
      "epoch": 51.333333333333336,
      "grad_norm": 1.3277938251121668e-06,
      "learning_rate": 4.8372887858793414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1293664,
      "step": 4620
    },
    {
      "epoch": 51.388888888888886,
      "grad_norm": 1.2102630080335075e-06,
      "learning_rate": 4.836940212495489e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1295120,
      "step": 4625
    },
    {
      "epoch": 51.44444444444444,
      "grad_norm": 1.2938669442519313e-06,
      "learning_rate": 4.836591278726087e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1296560,
      "step": 4630
    },
    {
      "epoch": 51.5,
      "grad_norm": 1.4151884215607424e-06,
      "learning_rate": 4.836241984624947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1298000,
      "step": 4635
    },
    {
      "epoch": 51.55555555555556,
      "grad_norm": 8.203131983464118e-06,
      "learning_rate": 4.8358923302459336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1299408,
      "step": 4640
    },
    {
      "epoch": 51.611111111111114,
      "grad_norm": 1.1893105238414137e-06,
      "learning_rate": 4.835542315642968e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1300800,
      "step": 4645
    },
    {
      "epoch": 51.666666666666664,
      "grad_norm": 1.3970520740258507e-06,
      "learning_rate": 4.8351919408700274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1302176,
      "step": 4650
    },
    {
      "epoch": 51.72222222222222,
      "grad_norm": 1.2316691027081106e-06,
      "learning_rate": 4.834841205981144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1303568,
      "step": 4655
    },
    {
      "epoch": 51.77777777777778,
      "grad_norm": 1.978090494958451e-06,
      "learning_rate": 4.8344901110304054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1305008,
      "step": 4660
    },
    {
      "epoch": 51.833333333333336,
      "grad_norm": 1.3307993640410132e-06,
      "learning_rate": 4.8341386560719534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1306368,
      "step": 4665
    },
    {
      "epoch": 51.888888888888886,
      "grad_norm": 2.0813527044083457e-06,
      "learning_rate": 4.833786841159989e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1307760,
      "step": 4670
    },
    {
      "epoch": 51.94444444444444,
      "grad_norm": 7.610140073666116e-06,
      "learning_rate": 4.833434666348765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1309184,
      "step": 4675
    },
    {
      "epoch": 52.0,
      "grad_norm": 1.2180652220195043e-06,
      "learning_rate": 4.833082131692592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1310560,
      "step": 4680
    },
    {
      "epoch": 52.05555555555556,
      "grad_norm": 4.550517132884124e-06,
      "learning_rate": 4.832729237245835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1311920,
      "step": 4685
    },
    {
      "epoch": 52.111111111111114,
      "grad_norm": 5.474221325130202e-06,
      "learning_rate": 4.8323759830629145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1313312,
      "step": 4690
    },
    {
      "epoch": 52.166666666666664,
      "grad_norm": 1.1508640227475553e-06,
      "learning_rate": 4.8320223691983066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1314704,
      "step": 4695
    },
    {
      "epoch": 52.22222222222222,
      "grad_norm": 1.0321466106688604e-05,
      "learning_rate": 4.831668395706544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1316144,
      "step": 4700
    },
    {
      "epoch": 52.27777777777778,
      "grad_norm": 1.2893510756839532e-06,
      "learning_rate": 4.8313140626422125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1317536,
      "step": 4705
    },
    {
      "epoch": 52.333333333333336,
      "grad_norm": 3.9098254092095885e-06,
      "learning_rate": 4.830959370059956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1318928,
      "step": 4710
    },
    {
      "epoch": 52.388888888888886,
      "grad_norm": 1.1482356967462692e-06,
      "learning_rate": 4.830604318014472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1320320,
      "step": 4715
    },
    {
      "epoch": 52.44444444444444,
      "grad_norm": 1.3798393183606095e-06,
      "learning_rate": 4.830248906560514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1321760,
      "step": 4720
    },
    {
      "epoch": 52.5,
      "grad_norm": 1.4553413620888023e-06,
      "learning_rate": 4.829893135752891e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1323232,
      "step": 4725
    },
    {
      "epoch": 52.55555555555556,
      "grad_norm": 1.1743719596779556e-06,
      "learning_rate": 4.829537005646466e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1324608,
      "step": 4730
    },
    {
      "epoch": 52.611111111111114,
      "grad_norm": 1.3837270671501756e-06,
      "learning_rate": 4.8291805162961615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1326000,
      "step": 4735
    },
    {
      "epoch": 52.666666666666664,
      "grad_norm": 1.0830849532794673e-06,
      "learning_rate": 4.82882366775695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1327376,
      "step": 4740
    },
    {
      "epoch": 52.72222222222222,
      "grad_norm": 1.748478894114669e-06,
      "learning_rate": 4.828466460083864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1328752,
      "step": 4745
    },
    {
      "epoch": 52.77777777777778,
      "grad_norm": 1.2784578302671434e-06,
      "learning_rate": 4.8281088933319877e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1330112,
      "step": 4750
    },
    {
      "epoch": 52.833333333333336,
      "grad_norm": 1.026476365950657e-05,
      "learning_rate": 4.827750967556464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1331520,
      "step": 4755
    },
    {
      "epoch": 52.888888888888886,
      "grad_norm": 1.3026365195401013e-06,
      "learning_rate": 4.827392682812488e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1332928,
      "step": 4760
    },
    {
      "epoch": 52.94444444444444,
      "grad_norm": 1.3492040125129279e-06,
      "learning_rate": 4.827034039155312e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1334336,
      "step": 4765
    },
    {
      "epoch": 53.0,
      "grad_norm": 1.334524313278962e-06,
      "learning_rate": 4.8266750366402445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1335760,
      "step": 4770
    },
    {
      "epoch": 53.05555555555556,
      "grad_norm": 2.044546363322297e-06,
      "learning_rate": 4.8263156753226476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1337136,
      "step": 4775
    },
    {
      "epoch": 53.111111111111114,
      "grad_norm": 1.233241619047476e-06,
      "learning_rate": 4.8259559552579394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1338496,
      "step": 4780
    },
    {
      "epoch": 53.166666666666664,
      "grad_norm": 1.6089056771306787e-06,
      "learning_rate": 4.825595876501593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1339920,
      "step": 4785
    },
    {
      "epoch": 53.22222222222222,
      "grad_norm": 1.3659297337653697e-06,
      "learning_rate": 4.825235439109137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1341344,
      "step": 4790
    },
    {
      "epoch": 53.27777777777778,
      "grad_norm": 3.790860773733584e-06,
      "learning_rate": 4.824874643136156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1342768,
      "step": 4795
    },
    {
      "epoch": 53.333333333333336,
      "grad_norm": 1.3306747632668703e-06,
      "learning_rate": 4.824513488638288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1344160,
      "step": 4800
    },
    {
      "epoch": 53.333333333333336,
      "eval_loss": 0.2626498341560364,
      "eval_runtime": 1.314,
      "eval_samples_per_second": 30.441,
      "eval_steps_per_second": 15.221,
      "num_input_tokens_seen": 1344160,
      "step": 4800
    },
    {
      "epoch": 53.388888888888886,
      "grad_norm": 1.0817199154189439e-06,
      "learning_rate": 4.8241519756712293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1345552,
      "step": 4805
    },
    {
      "epoch": 53.44444444444444,
      "grad_norm": 1.0025052006312762e-06,
      "learning_rate": 4.8237901042907285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1346976,
      "step": 4810
    },
    {
      "epoch": 53.5,
      "grad_norm": 1.2328439424891258e-06,
      "learning_rate": 4.823427874552591e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1348400,
      "step": 4815
    },
    {
      "epoch": 53.55555555555556,
      "grad_norm": 1.200825522573723e-06,
      "learning_rate": 4.823065286512677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1349808,
      "step": 4820
    },
    {
      "epoch": 53.611111111111114,
      "grad_norm": 1.3964909157948568e-06,
      "learning_rate": 4.8227023402269025e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1351168,
      "step": 4825
    },
    {
      "epoch": 53.666666666666664,
      "grad_norm": 2.3920194962556707e-06,
      "learning_rate": 4.822339035751239e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1352560,
      "step": 4830
    },
    {
      "epoch": 53.72222222222222,
      "grad_norm": 2.2215092485566856e-06,
      "learning_rate": 4.8219753731417104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1353936,
      "step": 4835
    },
    {
      "epoch": 53.77777777777778,
      "grad_norm": 1.8550099412095733e-06,
      "learning_rate": 4.821611352454401e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1355328,
      "step": 4840
    },
    {
      "epoch": 53.833333333333336,
      "grad_norm": 1.3167675660952227e-06,
      "learning_rate": 4.8212469737454444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1356768,
      "step": 4845
    },
    {
      "epoch": 53.888888888888886,
      "grad_norm": 1.1514188145156368e-06,
      "learning_rate": 4.820882237071035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1358208,
      "step": 4850
    },
    {
      "epoch": 53.94444444444444,
      "grad_norm": 1.1628577567535103e-06,
      "learning_rate": 4.820517142487417e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1359616,
      "step": 4855
    },
    {
      "epoch": 54.0,
      "grad_norm": 1.2341936326265568e-06,
      "learning_rate": 4.8201516900508956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1361040,
      "step": 4860
    },
    {
      "epoch": 54.05555555555556,
      "grad_norm": 3.2765196920081507e-06,
      "learning_rate": 4.819785879817827e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1362416,
      "step": 4865
    },
    {
      "epoch": 54.111111111111114,
      "grad_norm": 1.3751143796980614e-06,
      "learning_rate": 4.8194197118446226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1363824,
      "step": 4870
    },
    {
      "epoch": 54.166666666666664,
      "grad_norm": 1.732743157845107e-06,
      "learning_rate": 4.819053186187752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1365216,
      "step": 4875
    },
    {
      "epoch": 54.22222222222222,
      "grad_norm": 1.263112267224642e-06,
      "learning_rate": 4.818686302903736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1366624,
      "step": 4880
    },
    {
      "epoch": 54.27777777777778,
      "grad_norm": 1.0791861768666422e-06,
      "learning_rate": 4.818319062049154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1368048,
      "step": 4885
    },
    {
      "epoch": 54.333333333333336,
      "grad_norm": 1.3151429811841808e-06,
      "learning_rate": 4.817951463680639e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1369424,
      "step": 4890
    },
    {
      "epoch": 54.388888888888886,
      "grad_norm": 1.6411415799666429e-06,
      "learning_rate": 4.817583507854879e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1370832,
      "step": 4895
    },
    {
      "epoch": 54.44444444444444,
      "grad_norm": 1.1896183877979638e-06,
      "learning_rate": 4.817215194628617e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1372272,
      "step": 4900
    },
    {
      "epoch": 54.5,
      "grad_norm": 1.5612663446518127e-06,
      "learning_rate": 4.816846524058653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1373680,
      "step": 4905
    },
    {
      "epoch": 54.55555555555556,
      "grad_norm": 1.263986632693559e-06,
      "learning_rate": 4.816477496201839e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1375072,
      "step": 4910
    },
    {
      "epoch": 54.611111111111114,
      "grad_norm": 1.319521970799542e-06,
      "learning_rate": 4.8161081111150845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1376448,
      "step": 4915
    },
    {
      "epoch": 54.666666666666664,
      "grad_norm": 1.4770296274946304e-06,
      "learning_rate": 4.815738368855354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1377856,
      "step": 4920
    },
    {
      "epoch": 54.72222222222222,
      "grad_norm": 1.6606618373771198e-06,
      "learning_rate": 4.815368269479664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1379216,
      "step": 4925
    },
    {
      "epoch": 54.77777777777778,
      "grad_norm": 1.3230727518021013e-06,
      "learning_rate": 4.814997813045092e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1380608,
      "step": 4930
    },
    {
      "epoch": 54.833333333333336,
      "grad_norm": 1.138263087341329e-06,
      "learning_rate": 4.814626999608764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1382016,
      "step": 4935
    },
    {
      "epoch": 54.888888888888886,
      "grad_norm": 4.2010560719063506e-06,
      "learning_rate": 4.814255829227865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1383408,
      "step": 4940
    },
    {
      "epoch": 54.94444444444444,
      "grad_norm": 1.8663461105461465e-06,
      "learning_rate": 4.813884301959635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1384832,
      "step": 4945
    },
    {
      "epoch": 55.0,
      "grad_norm": 1.2111704563722014e-06,
      "learning_rate": 4.813512417861368e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1386208,
      "step": 4950
    },
    {
      "epoch": 55.05555555555556,
      "grad_norm": 1.3891884691474843e-06,
      "learning_rate": 4.813140176990411e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1387584,
      "step": 4955
    },
    {
      "epoch": 55.111111111111114,
      "grad_norm": 1.3540376357923378e-06,
      "learning_rate": 4.8127675794041714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1389008,
      "step": 4960
    },
    {
      "epoch": 55.166666666666664,
      "grad_norm": 1.951103513420094e-06,
      "learning_rate": 4.812394625160107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1390432,
      "step": 4965
    },
    {
      "epoch": 55.22222222222222,
      "grad_norm": 1.4265760910348035e-06,
      "learning_rate": 4.812021314315732e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1391808,
      "step": 4970
    },
    {
      "epoch": 55.27777777777778,
      "grad_norm": 1.4694513765789452e-06,
      "learning_rate": 4.811647646928616e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1393232,
      "step": 4975
    },
    {
      "epoch": 55.333333333333336,
      "grad_norm": 1.2290486210986273e-06,
      "learning_rate": 4.8112736230563814e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1394592,
      "step": 4980
    },
    {
      "epoch": 55.388888888888886,
      "grad_norm": 1.6730930383346276e-06,
      "learning_rate": 4.81089924275671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1395984,
      "step": 4985
    },
    {
      "epoch": 55.44444444444444,
      "grad_norm": 1.5165976492426125e-06,
      "learning_rate": 4.810524506087335e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1397440,
      "step": 4990
    },
    {
      "epoch": 55.5,
      "grad_norm": 1.187898647003749e-06,
      "learning_rate": 4.810149413106044e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1398896,
      "step": 4995
    },
    {
      "epoch": 55.55555555555556,
      "grad_norm": 1.2072003983121249e-06,
      "learning_rate": 4.809773963870684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1400368,
      "step": 5000
    },
    {
      "epoch": 55.55555555555556,
      "eval_loss": 0.26760876178741455,
      "eval_runtime": 1.3179,
      "eval_samples_per_second": 30.35,
      "eval_steps_per_second": 15.175,
      "num_input_tokens_seen": 1400368,
      "step": 5000
    },
    {
      "epoch": 55.611111111111114,
      "grad_norm": 2.5593853933969513e-06,
      "learning_rate": 4.809398158439151e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1401776,
      "step": 5005
    },
    {
      "epoch": 55.666666666666664,
      "grad_norm": 1.3347407730179839e-06,
      "learning_rate": 4.8090219968694005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1403152,
      "step": 5010
    },
    {
      "epoch": 55.72222222222222,
      "grad_norm": 1.6816636616567848e-06,
      "learning_rate": 4.808645479219442e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1404528,
      "step": 5015
    },
    {
      "epoch": 55.77777777777778,
      "grad_norm": 7.850612746551633e-06,
      "learning_rate": 4.8082686055473375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1405904,
      "step": 5020
    },
    {
      "epoch": 55.833333333333336,
      "grad_norm": 1.3455700127451564e-06,
      "learning_rate": 4.8078913759112066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1407248,
      "step": 5025
    },
    {
      "epoch": 55.888888888888886,
      "grad_norm": 6.192241471580928e-06,
      "learning_rate": 4.807513790369223e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1408656,
      "step": 5030
    },
    {
      "epoch": 55.94444444444444,
      "grad_norm": 1.826194647946977e-06,
      "learning_rate": 4.8071358489796145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1410016,
      "step": 5035
    },
    {
      "epoch": 56.0,
      "grad_norm": 1.2858940863225143e-06,
      "learning_rate": 4.806757551800665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1411472,
      "step": 5040
    },
    {
      "epoch": 56.05555555555556,
      "grad_norm": 1.1254102219027118e-06,
      "learning_rate": 4.806378898890713e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1412896,
      "step": 5045
    },
    {
      "epoch": 56.111111111111114,
      "grad_norm": 1.3550587709687534e-06,
      "learning_rate": 4.80599989030815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1414320,
      "step": 5050
    },
    {
      "epoch": 56.166666666666664,
      "grad_norm": 9.058820182872296e-07,
      "learning_rate": 4.805620526111426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1415744,
      "step": 5055
    },
    {
      "epoch": 56.22222222222222,
      "grad_norm": 1.3243906096249702e-06,
      "learning_rate": 4.805240806359042e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1417152,
      "step": 5060
    },
    {
      "epoch": 56.27777777777778,
      "grad_norm": 1.9384494862606516e-06,
      "learning_rate": 4.804860731109557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1418576,
      "step": 5065
    },
    {
      "epoch": 56.333333333333336,
      "grad_norm": 1.0868126310015214e-06,
      "learning_rate": 4.804480300421581e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1419936,
      "step": 5070
    },
    {
      "epoch": 56.388888888888886,
      "grad_norm": 1.306432523051626e-06,
      "learning_rate": 4.804099514353784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1421312,
      "step": 5075
    },
    {
      "epoch": 56.44444444444444,
      "grad_norm": 1.0776612953122822e-06,
      "learning_rate": 4.8037183729648867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1422688,
      "step": 5080
    },
    {
      "epoch": 56.5,
      "grad_norm": 1.2775088862326811e-06,
      "learning_rate": 4.803336876313666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1424064,
      "step": 5085
    },
    {
      "epoch": 56.55555555555556,
      "grad_norm": 2.039293804045883e-06,
      "learning_rate": 4.802955024458953e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1425488,
      "step": 5090
    },
    {
      "epoch": 56.611111111111114,
      "grad_norm": 1.1100763686044957e-06,
      "learning_rate": 4.802572817459634e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1426912,
      "step": 5095
    },
    {
      "epoch": 56.666666666666664,
      "grad_norm": 1.017974341266381e-06,
      "learning_rate": 4.802190255374651e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1428320,
      "step": 5100
    },
    {
      "epoch": 56.72222222222222,
      "grad_norm": 1.0206008482782636e-06,
      "learning_rate": 4.801807338263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1429696,
      "step": 5105
    },
    {
      "epoch": 56.77777777777778,
      "grad_norm": 1.5424091088789282e-06,
      "learning_rate": 4.8014240661837306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1431120,
      "step": 5110
    },
    {
      "epoch": 56.833333333333336,
      "grad_norm": 1.0343569556425791e-06,
      "learning_rate": 4.80104043919595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1432496,
      "step": 5115
    },
    {
      "epoch": 56.888888888888886,
      "grad_norm": 1.267986704078794e-06,
      "learning_rate": 4.800656457358815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1433872,
      "step": 5120
    },
    {
      "epoch": 56.94444444444444,
      "grad_norm": 1.4624847608502023e-06,
      "learning_rate": 4.800272120731544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1435296,
      "step": 5125
    },
    {
      "epoch": 57.0,
      "grad_norm": 6.780910553061403e-06,
      "learning_rate": 4.799887429373404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1436688,
      "step": 5130
    },
    {
      "epoch": 57.05555555555556,
      "grad_norm": 9.081452390091727e-07,
      "learning_rate": 4.79950238334372e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1438144,
      "step": 5135
    },
    {
      "epoch": 57.111111111111114,
      "grad_norm": 1.1361446468072245e-06,
      "learning_rate": 4.799116982701872e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1439552,
      "step": 5140
    },
    {
      "epoch": 57.166666666666664,
      "grad_norm": 2.9068542062304914e-06,
      "learning_rate": 4.7987312275072926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1440960,
      "step": 5145
    },
    {
      "epoch": 57.22222222222222,
      "grad_norm": 1.2294319731154246e-06,
      "learning_rate": 4.79834511781947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1442320,
      "step": 5150
    },
    {
      "epoch": 57.27777777777778,
      "grad_norm": 9.994239462685073e-07,
      "learning_rate": 4.797958653697947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1443712,
      "step": 5155
    },
    {
      "epoch": 57.333333333333336,
      "grad_norm": 3.2868701964616776e-06,
      "learning_rate": 4.7975718352023225e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1445136,
      "step": 5160
    },
    {
      "epoch": 57.388888888888886,
      "grad_norm": 1.5030341273813974e-06,
      "learning_rate": 4.7971846623922476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1446544,
      "step": 5165
    },
    {
      "epoch": 57.44444444444444,
      "grad_norm": 1.1910177590834792e-06,
      "learning_rate": 4.7967971353274294e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1447936,
      "step": 5170
    },
    {
      "epoch": 57.5,
      "grad_norm": 1.308569608227117e-06,
      "learning_rate": 4.79640925406763e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1449344,
      "step": 5175
    },
    {
      "epoch": 57.55555555555556,
      "grad_norm": 1.25442761600425e-06,
      "learning_rate": 4.796021018672664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1450736,
      "step": 5180
    },
    {
      "epoch": 57.611111111111114,
      "grad_norm": 1.399751340613875e-06,
      "learning_rate": 4.795632429202405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1452144,
      "step": 5185
    },
    {
      "epoch": 57.666666666666664,
      "grad_norm": 1.322592197539052e-06,
      "learning_rate": 4.795243485716775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1453552,
      "step": 5190
    },
    {
      "epoch": 57.72222222222222,
      "grad_norm": 1.0401377039670479e-06,
      "learning_rate": 4.794854188275757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1454992,
      "step": 5195
    },
    {
      "epoch": 57.77777777777778,
      "grad_norm": 1.1765168892452493e-06,
      "learning_rate": 4.794464536939384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1456368,
      "step": 5200
    },
    {
      "epoch": 57.77777777777778,
      "eval_loss": 0.2591719925403595,
      "eval_runtime": 1.324,
      "eval_samples_per_second": 30.212,
      "eval_steps_per_second": 15.106,
      "num_input_tokens_seen": 1456368,
      "step": 5200
    },
    {
      "epoch": 57.833333333333336,
      "grad_norm": 1.4522323681376292e-06,
      "learning_rate": 4.794074531767745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1457760,
      "step": 5205
    },
    {
      "epoch": 57.888888888888886,
      "grad_norm": 1.3289444495967473e-06,
      "learning_rate": 4.7936841728209834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1459136,
      "step": 5210
    },
    {
      "epoch": 57.94444444444444,
      "grad_norm": 1.2853981843363727e-06,
      "learning_rate": 4.7932934601593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1460576,
      "step": 5215
    },
    {
      "epoch": 58.0,
      "grad_norm": 6.8872227529936936e-06,
      "learning_rate": 4.792902393842943e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1462000,
      "step": 5220
    },
    {
      "epoch": 58.05555555555556,
      "grad_norm": 1.3704840284844977e-06,
      "learning_rate": 4.792510973932225e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1463360,
      "step": 5225
    },
    {
      "epoch": 58.111111111111114,
      "grad_norm": 1.2236752127137152e-06,
      "learning_rate": 4.7921192004875036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1464768,
      "step": 5230
    },
    {
      "epoch": 58.166666666666664,
      "grad_norm": 1.442360257897235e-06,
      "learning_rate": 4.791727073569198e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1466160,
      "step": 5235
    },
    {
      "epoch": 58.22222222222222,
      "grad_norm": 9.87264115792641e-07,
      "learning_rate": 4.7913345932377775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1467568,
      "step": 5240
    },
    {
      "epoch": 58.27777777777778,
      "grad_norm": 1.8473689351594658e-06,
      "learning_rate": 4.790941759553769e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1468960,
      "step": 5245
    },
    {
      "epoch": 58.333333333333336,
      "grad_norm": 1.1135128943351447e-06,
      "learning_rate": 4.79054857257775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1470320,
      "step": 5250
    },
    {
      "epoch": 58.388888888888886,
      "grad_norm": 1.013741098176979e-06,
      "learning_rate": 4.790155032370357e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1471728,
      "step": 5255
    },
    {
      "epoch": 58.44444444444444,
      "grad_norm": 1.93084861166426e-06,
      "learning_rate": 4.789761138992278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1473184,
      "step": 5260
    },
    {
      "epoch": 58.5,
      "grad_norm": 1.0918682846750016e-06,
      "learning_rate": 4.7893668925042565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1474544,
      "step": 5265
    },
    {
      "epoch": 58.55555555555556,
      "grad_norm": 3.771002411667723e-06,
      "learning_rate": 4.78897229296709e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1475920,
      "step": 5270
    },
    {
      "epoch": 58.611111111111114,
      "grad_norm": 1.5052005437610205e-06,
      "learning_rate": 4.7885773404416315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1477296,
      "step": 5275
    },
    {
      "epoch": 58.666666666666664,
      "grad_norm": 1.7059417132259114e-06,
      "learning_rate": 4.788182034988786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1478704,
      "step": 5280
    },
    {
      "epoch": 58.72222222222222,
      "grad_norm": 1.2127848094678484e-06,
      "learning_rate": 4.787786376669516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1480064,
      "step": 5285
    },
    {
      "epoch": 58.77777777777778,
      "grad_norm": 1.2093458963136072e-06,
      "learning_rate": 4.787390365544837e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1481472,
      "step": 5290
    },
    {
      "epoch": 58.833333333333336,
      "grad_norm": 7.591649591631722e-06,
      "learning_rate": 4.786994001675818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1482880,
      "step": 5295
    },
    {
      "epoch": 58.888888888888886,
      "grad_norm": 1.0818108648891211e-06,
      "learning_rate": 4.786597285123584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1484272,
      "step": 5300
    },
    {
      "epoch": 58.94444444444444,
      "grad_norm": 1.0142034625459928e-06,
      "learning_rate": 4.7862002159493135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1485696,
      "step": 5305
    },
    {
      "epoch": 59.0,
      "grad_norm": 1.206609795190161e-06,
      "learning_rate": 4.785802794214239e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1487136,
      "step": 5310
    },
    {
      "epoch": 59.05555555555556,
      "grad_norm": 1.0749572538770735e-06,
      "learning_rate": 4.7854050199796495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1488544,
      "step": 5315
    },
    {
      "epoch": 59.111111111111114,
      "grad_norm": 1.1003234021700337e-06,
      "learning_rate": 4.7850068933068845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1489936,
      "step": 5320
    },
    {
      "epoch": 59.166666666666664,
      "grad_norm": 1.317304054282431e-06,
      "learning_rate": 4.7846084142573425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1491360,
      "step": 5325
    },
    {
      "epoch": 59.22222222222222,
      "grad_norm": 1.9108442756987642e-06,
      "learning_rate": 4.7842095828924725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1492752,
      "step": 5330
    },
    {
      "epoch": 59.27777777777778,
      "grad_norm": 7.702296898060013e-06,
      "learning_rate": 4.783810399273779e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1494128,
      "step": 5335
    },
    {
      "epoch": 59.333333333333336,
      "grad_norm": 1.08651181562891e-06,
      "learning_rate": 4.7834108634628226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1495520,
      "step": 5340
    },
    {
      "epoch": 59.388888888888886,
      "grad_norm": 1.5830712527531432e-06,
      "learning_rate": 4.783010975521216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1496928,
      "step": 5345
    },
    {
      "epoch": 59.44444444444444,
      "grad_norm": 1.0512289918551687e-06,
      "learning_rate": 4.782610735510626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1498272,
      "step": 5350
    },
    {
      "epoch": 59.5,
      "grad_norm": 8.594452651777829e-07,
      "learning_rate": 4.782210143492776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1499664,
      "step": 5355
    },
    {
      "epoch": 59.55555555555556,
      "grad_norm": 8.994891800284677e-07,
      "learning_rate": 4.781809199529442e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1501072,
      "step": 5360
    },
    {
      "epoch": 59.611111111111114,
      "grad_norm": 9.190022183247493e-07,
      "learning_rate": 4.781407903682454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1502512,
      "step": 5365
    },
    {
      "epoch": 59.666666666666664,
      "grad_norm": 6.556246717082104e-06,
      "learning_rate": 4.781006256013698e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1503936,
      "step": 5370
    },
    {
      "epoch": 59.72222222222222,
      "grad_norm": 1.0372377801104449e-06,
      "learning_rate": 4.7806042565851115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1505344,
      "step": 5375
    },
    {
      "epoch": 59.77777777777778,
      "grad_norm": 1.7560504375069286e-06,
      "learning_rate": 4.7802019054586895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1506736,
      "step": 5380
    },
    {
      "epoch": 59.833333333333336,
      "grad_norm": 3.9125452531152405e-06,
      "learning_rate": 4.779799202696479e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1508160,
      "step": 5385
    },
    {
      "epoch": 59.888888888888886,
      "grad_norm": 1.004035084406496e-06,
      "learning_rate": 4.779396148360581e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1509584,
      "step": 5390
    },
    {
      "epoch": 59.94444444444444,
      "grad_norm": 1.44152670600306e-06,
      "learning_rate": 4.7789927425131517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1510960,
      "step": 5395
    },
    {
      "epoch": 60.0,
      "grad_norm": 1.1497471632537781e-06,
      "learning_rate": 4.778588985216403e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1512336,
      "step": 5400
    },
    {
      "epoch": 60.0,
      "eval_loss": 0.2541940212249756,
      "eval_runtime": 1.2966,
      "eval_samples_per_second": 30.851,
      "eval_steps_per_second": 15.425,
      "num_input_tokens_seen": 1512336,
      "step": 5400
    },
    {
      "epoch": 60.05555555555556,
      "grad_norm": 9.476869422542222e-07,
      "learning_rate": 4.778184876532598e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1513728,
      "step": 5405
    },
    {
      "epoch": 60.111111111111114,
      "grad_norm": 1.192338913824642e-06,
      "learning_rate": 4.7777804165240556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1515104,
      "step": 5410
    },
    {
      "epoch": 60.166666666666664,
      "grad_norm": 1.190356670122128e-06,
      "learning_rate": 4.7773756052531485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1516512,
      "step": 5415
    },
    {
      "epoch": 60.22222222222222,
      "grad_norm": 1.173675514110073e-06,
      "learning_rate": 4.7769704427823035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1517888,
      "step": 5420
    },
    {
      "epoch": 60.27777777777778,
      "grad_norm": 1.2162835218987311e-06,
      "learning_rate": 4.776564929174003e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1519312,
      "step": 5425
    },
    {
      "epoch": 60.333333333333336,
      "grad_norm": 9.376439038533135e-07,
      "learning_rate": 4.7761590644907806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1520720,
      "step": 5430
    },
    {
      "epoch": 60.388888888888886,
      "grad_norm": 1.1814194067483186e-06,
      "learning_rate": 4.7757528487952263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1522080,
      "step": 5435
    },
    {
      "epoch": 60.44444444444444,
      "grad_norm": 1.1759194649130222e-06,
      "learning_rate": 4.7753462821499836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1523488,
      "step": 5440
    },
    {
      "epoch": 60.5,
      "grad_norm": 1.561387080073473e-06,
      "learning_rate": 4.774939364617751e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1524896,
      "step": 5445
    },
    {
      "epoch": 60.55555555555556,
      "grad_norm": 1.4529100553772878e-06,
      "learning_rate": 4.7745320962612795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1526352,
      "step": 5450
    },
    {
      "epoch": 60.611111111111114,
      "grad_norm": 9.380826213600812e-07,
      "learning_rate": 4.7741244771433756e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1527792,
      "step": 5455
    },
    {
      "epoch": 60.666666666666664,
      "grad_norm": 1.0610870049276855e-06,
      "learning_rate": 4.7737165073268985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1529168,
      "step": 5460
    },
    {
      "epoch": 60.72222222222222,
      "grad_norm": 1.2030259313178249e-06,
      "learning_rate": 4.7733081868747626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1530544,
      "step": 5465
    },
    {
      "epoch": 60.77777777777778,
      "grad_norm": 3.2798427582747536e-06,
      "learning_rate": 4.772899515849936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1531936,
      "step": 5470
    },
    {
      "epoch": 60.833333333333336,
      "grad_norm": 5.316711394698359e-06,
      "learning_rate": 4.7724904943154414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1533328,
      "step": 5475
    },
    {
      "epoch": 60.888888888888886,
      "grad_norm": 1.2509350426626042e-06,
      "learning_rate": 4.772081122334354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1534736,
      "step": 5480
    },
    {
      "epoch": 60.94444444444444,
      "grad_norm": 3.532036544129369e-06,
      "learning_rate": 4.771671399969806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1536128,
      "step": 5485
    },
    {
      "epoch": 61.0,
      "grad_norm": 9.562775176163996e-07,
      "learning_rate": 4.7712613272849794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1537504,
      "step": 5490
    },
    {
      "epoch": 61.05555555555556,
      "grad_norm": 1.1084009656769922e-06,
      "learning_rate": 4.770850904343114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1538896,
      "step": 5495
    },
    {
      "epoch": 61.111111111111114,
      "grad_norm": 9.82819301498239e-07,
      "learning_rate": 4.770440131207502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1540336,
      "step": 5500
    },
    {
      "epoch": 61.166666666666664,
      "grad_norm": 1.0694760703700013e-06,
      "learning_rate": 4.7700290079414896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1541728,
      "step": 5505
    },
    {
      "epoch": 61.22222222222222,
      "grad_norm": 1.1876404641952831e-06,
      "learning_rate": 4.769617534608477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1543168,
      "step": 5510
    },
    {
      "epoch": 61.27777777777778,
      "grad_norm": 1.1621739304246148e-06,
      "learning_rate": 4.7692057112719193e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1544608,
      "step": 5515
    },
    {
      "epoch": 61.333333333333336,
      "grad_norm": 1.0367009508627234e-06,
      "learning_rate": 4.7687935379953234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1545984,
      "step": 5520
    },
    {
      "epoch": 61.388888888888886,
      "grad_norm": 1.2818620689358795e-06,
      "learning_rate": 4.7683810148422534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1547376,
      "step": 5525
    },
    {
      "epoch": 61.44444444444444,
      "grad_norm": 1.2304991514611174e-06,
      "learning_rate": 4.767968141876324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1548768,
      "step": 5530
    },
    {
      "epoch": 61.5,
      "grad_norm": 1.4049654737391393e-06,
      "learning_rate": 4.767554919161207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1550112,
      "step": 5535
    },
    {
      "epoch": 61.55555555555556,
      "grad_norm": 1.575445253365615e-06,
      "learning_rate": 4.767141346760624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1551520,
      "step": 5540
    },
    {
      "epoch": 61.611111111111114,
      "grad_norm": 3.19851665153692e-06,
      "learning_rate": 4.766727424738356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1552928,
      "step": 5545
    },
    {
      "epoch": 61.666666666666664,
      "grad_norm": 1.0236319667455973e-06,
      "learning_rate": 4.7663131531582325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1554240,
      "step": 5550
    },
    {
      "epoch": 61.72222222222222,
      "grad_norm": 1.1741465186787536e-06,
      "learning_rate": 4.765898532084142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1555712,
      "step": 5555
    },
    {
      "epoch": 61.77777777777778,
      "grad_norm": 1.2013560990453698e-06,
      "learning_rate": 4.765483561580022e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1557120,
      "step": 5560
    },
    {
      "epoch": 61.833333333333336,
      "grad_norm": 1.2787116929757758e-06,
      "learning_rate": 4.7650682417098666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1558512,
      "step": 5565
    },
    {
      "epoch": 61.888888888888886,
      "grad_norm": 8.651711596030509e-07,
      "learning_rate": 4.7646525725377244e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1559920,
      "step": 5570
    },
    {
      "epoch": 61.94444444444444,
      "grad_norm": 1.2023162980767665e-06,
      "learning_rate": 4.764236554127696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1561344,
      "step": 5575
    },
    {
      "epoch": 62.0,
      "grad_norm": 1.2595967291417764e-06,
      "learning_rate": 4.7638201865439356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1562720,
      "step": 5580
    },
    {
      "epoch": 62.05555555555556,
      "grad_norm": 1.0744826113295858e-06,
      "learning_rate": 4.7634034698506545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1564128,
      "step": 5585
    },
    {
      "epoch": 62.111111111111114,
      "grad_norm": 3.961215043091215e-06,
      "learning_rate": 4.762986404112115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1565488,
      "step": 5590
    },
    {
      "epoch": 62.166666666666664,
      "grad_norm": 1.2440940508895437e-06,
      "learning_rate": 4.762568989392633e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1566848,
      "step": 5595
    },
    {
      "epoch": 62.22222222222222,
      "grad_norm": 1.3016885986871785e-06,
      "learning_rate": 4.76215122575658e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1568192,
      "step": 5600
    },
    {
      "epoch": 62.22222222222222,
      "eval_loss": 0.24483796954154968,
      "eval_runtime": 1.3234,
      "eval_samples_per_second": 30.226,
      "eval_steps_per_second": 15.113,
      "num_input_tokens_seen": 1568192,
      "step": 5600
    },
    {
      "epoch": 62.27777777777778,
      "grad_norm": 1.0476388752067578e-06,
      "learning_rate": 4.7617331132683795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1569600,
      "step": 5605
    },
    {
      "epoch": 62.333333333333336,
      "grad_norm": 1.0848229976545554e-06,
      "learning_rate": 4.7613146519925105e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1570992,
      "step": 5610
    },
    {
      "epoch": 62.388888888888886,
      "grad_norm": 1.0760462600956089e-06,
      "learning_rate": 4.7608958419935045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1572416,
      "step": 5615
    },
    {
      "epoch": 62.44444444444444,
      "grad_norm": 2.5544161417201394e-06,
      "learning_rate": 4.760476683335948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1573840,
      "step": 5620
    },
    {
      "epoch": 62.5,
      "grad_norm": 7.022244517429499e-06,
      "learning_rate": 4.760057176084479e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1575296,
      "step": 5625
    },
    {
      "epoch": 62.55555555555556,
      "grad_norm": 9.649055527916062e-07,
      "learning_rate": 4.759637320303793e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1576704,
      "step": 5630
    },
    {
      "epoch": 62.611111111111114,
      "grad_norm": 1.2890593552583596e-06,
      "learning_rate": 4.759217116058635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1578064,
      "step": 5635
    },
    {
      "epoch": 62.666666666666664,
      "grad_norm": 4.700119461631402e-06,
      "learning_rate": 4.758796563413807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1579456,
      "step": 5640
    },
    {
      "epoch": 62.72222222222222,
      "grad_norm": 7.4699969445646275e-06,
      "learning_rate": 4.758375662434163e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1580848,
      "step": 5645
    },
    {
      "epoch": 62.77777777777778,
      "grad_norm": 1.2336273584878654e-06,
      "learning_rate": 4.7579544131846114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1582304,
      "step": 5650
    },
    {
      "epoch": 62.833333333333336,
      "grad_norm": 1.043213956108957e-06,
      "learning_rate": 4.757532815730114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1583744,
      "step": 5655
    },
    {
      "epoch": 62.888888888888886,
      "grad_norm": 9.551700941301533e-07,
      "learning_rate": 4.7571108701356865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1585136,
      "step": 5660
    },
    {
      "epoch": 62.94444444444444,
      "grad_norm": 8.956570809459663e-07,
      "learning_rate": 4.756688576466398e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1586560,
      "step": 5665
    },
    {
      "epoch": 63.0,
      "grad_norm": 1.2341944284344208e-06,
      "learning_rate": 4.756265934787372e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1587936,
      "step": 5670
    },
    {
      "epoch": 63.05555555555556,
      "grad_norm": 8.696887334735948e-07,
      "learning_rate": 4.755842945163785e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1589376,
      "step": 5675
    },
    {
      "epoch": 63.111111111111114,
      "grad_norm": 9.848093895925558e-07,
      "learning_rate": 4.755419607660867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1590800,
      "step": 5680
    },
    {
      "epoch": 63.166666666666664,
      "grad_norm": 9.995385426009307e-07,
      "learning_rate": 4.7549959223439016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1592208,
      "step": 5685
    },
    {
      "epoch": 63.22222222222222,
      "grad_norm": 6.41899941911106e-06,
      "learning_rate": 4.754571889278228e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1593536,
      "step": 5690
    },
    {
      "epoch": 63.27777777777778,
      "grad_norm": 1.1384632898625568e-06,
      "learning_rate": 4.754147508529235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1594960,
      "step": 5695
    },
    {
      "epoch": 63.333333333333336,
      "grad_norm": 9.894728236758965e-07,
      "learning_rate": 4.75372278016237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1596352,
      "step": 5700
    },
    {
      "epoch": 63.388888888888886,
      "grad_norm": 1.0008546951212338e-06,
      "learning_rate": 4.753297704243129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1597760,
      "step": 5705
    },
    {
      "epoch": 63.44444444444444,
      "grad_norm": 1.1648913869066746e-06,
      "learning_rate": 4.752872280837066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1599152,
      "step": 5710
    },
    {
      "epoch": 63.5,
      "grad_norm": 1.0584278697933769e-06,
      "learning_rate": 4.752446510009786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1600528,
      "step": 5715
    },
    {
      "epoch": 63.55555555555556,
      "grad_norm": 1.2883483577752486e-06,
      "learning_rate": 4.7520203918269476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1601888,
      "step": 5720
    },
    {
      "epoch": 63.611111111111114,
      "grad_norm": 1.2783925740222912e-06,
      "learning_rate": 4.751593926354265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1603264,
      "step": 5725
    },
    {
      "epoch": 63.666666666666664,
      "grad_norm": 3.897883289027959e-06,
      "learning_rate": 4.751167113657503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1604656,
      "step": 5730
    },
    {
      "epoch": 63.72222222222222,
      "grad_norm": 2.170565494452603e-06,
      "learning_rate": 4.7507399538024834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1606064,
      "step": 5735
    },
    {
      "epoch": 63.77777777777778,
      "grad_norm": 8.088953222795681e-07,
      "learning_rate": 4.750312446855077e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1607472,
      "step": 5740
    },
    {
      "epoch": 63.833333333333336,
      "grad_norm": 1.3948057357993093e-06,
      "learning_rate": 4.749884592881212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1608880,
      "step": 5745
    },
    {
      "epoch": 63.888888888888886,
      "grad_norm": 1.13185762984358e-06,
      "learning_rate": 4.74945639194687e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1610304,
      "step": 5750
    },
    {
      "epoch": 63.94444444444444,
      "grad_norm": 1.0313411848983378e-06,
      "learning_rate": 4.749027844118083e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1611728,
      "step": 5755
    },
    {
      "epoch": 64.0,
      "grad_norm": 5.523945219465531e-06,
      "learning_rate": 4.7485989494609395e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1613088,
      "step": 5760
    },
    {
      "epoch": 64.05555555555556,
      "grad_norm": 1.1089555300713982e-06,
      "learning_rate": 4.748169708041581e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1614496,
      "step": 5765
    },
    {
      "epoch": 64.11111111111111,
      "grad_norm": 1.0374965313530993e-06,
      "learning_rate": 4.7477401199262004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1615856,
      "step": 5770
    },
    {
      "epoch": 64.16666666666667,
      "grad_norm": 9.112476959671767e-07,
      "learning_rate": 4.747310185181048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1617248,
      "step": 5775
    },
    {
      "epoch": 64.22222222222223,
      "grad_norm": 2.3394654817820992e-06,
      "learning_rate": 4.746879903872422e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1618640,
      "step": 5780
    },
    {
      "epoch": 64.27777777777777,
      "grad_norm": 1.3363561492951703e-06,
      "learning_rate": 4.746449276066679e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1620016,
      "step": 5785
    },
    {
      "epoch": 64.33333333333333,
      "grad_norm": 1.26027316582622e-06,
      "learning_rate": 4.746018301830227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1621408,
      "step": 5790
    },
    {
      "epoch": 64.38888888888889,
      "grad_norm": 8.570336831326131e-07,
      "learning_rate": 4.7455869812295275e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1622880,
      "step": 5795
    },
    {
      "epoch": 64.44444444444444,
      "grad_norm": 8.70266887886828e-07,
      "learning_rate": 4.7451553143310964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1624288,
      "step": 5800
    },
    {
      "epoch": 64.44444444444444,
      "eval_loss": 0.24876172840595245,
      "eval_runtime": 1.3197,
      "eval_samples_per_second": 30.309,
      "eval_steps_per_second": 15.155,
      "num_input_tokens_seen": 1624288,
      "step": 5800
    },
    {
      "epoch": 64.5,
      "grad_norm": 9.499445923211169e-07,
      "learning_rate": 4.744723301201501e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1625696,
      "step": 5805
    },
    {
      "epoch": 64.55555555555556,
      "grad_norm": 1.0419836371511337e-06,
      "learning_rate": 4.744290941907364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1627104,
      "step": 5810
    },
    {
      "epoch": 64.61111111111111,
      "grad_norm": 9.209618383465568e-07,
      "learning_rate": 4.7438582365153594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1628480,
      "step": 5815
    },
    {
      "epoch": 64.66666666666667,
      "grad_norm": 1.0096781579704839e-06,
      "learning_rate": 4.743425185092217e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1629936,
      "step": 5820
    },
    {
      "epoch": 64.72222222222223,
      "grad_norm": 1.1568857871679938e-06,
      "learning_rate": 4.742991787704719e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1631328,
      "step": 5825
    },
    {
      "epoch": 64.77777777777777,
      "grad_norm": 9.177866218124109e-07,
      "learning_rate": 4.7425580444196994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1632688,
      "step": 5830
    },
    {
      "epoch": 64.83333333333333,
      "grad_norm": 1.0817516340466682e-06,
      "learning_rate": 4.742123955304048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1634128,
      "step": 5835
    },
    {
      "epoch": 64.88888888888889,
      "grad_norm": 1.1922145404241746e-06,
      "learning_rate": 4.741689520424706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1635536,
      "step": 5840
    },
    {
      "epoch": 64.94444444444444,
      "grad_norm": 1.1279468026259565e-06,
      "learning_rate": 4.741254739848669e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1636896,
      "step": 5845
    },
    {
      "epoch": 65.0,
      "grad_norm": 1.2798716397810495e-06,
      "learning_rate": 4.740819613642987e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1638272,
      "step": 5850
    },
    {
      "epoch": 65.05555555555556,
      "grad_norm": 7.081153398758033e-06,
      "learning_rate": 4.74038414187476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1639632,
      "step": 5855
    },
    {
      "epoch": 65.11111111111111,
      "grad_norm": 1.0887230246225954e-06,
      "learning_rate": 4.739948324611144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1641008,
      "step": 5860
    },
    {
      "epoch": 65.16666666666667,
      "grad_norm": 1.1459767392807407e-06,
      "learning_rate": 4.7395121619193465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1642384,
      "step": 5865
    },
    {
      "epoch": 65.22222222222223,
      "grad_norm": 1.1166371223225724e-06,
      "learning_rate": 4.7390756538666313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1643760,
      "step": 5870
    },
    {
      "epoch": 65.27777777777777,
      "grad_norm": 3.983408078056527e-06,
      "learning_rate": 4.738638800520311e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1645216,
      "step": 5875
    },
    {
      "epoch": 65.33333333333333,
      "grad_norm": 1.1438947922215448e-06,
      "learning_rate": 4.738201601947757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1646576,
      "step": 5880
    },
    {
      "epoch": 65.38888888888889,
      "grad_norm": 1.2766809049935546e-06,
      "learning_rate": 4.7377640582163876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1647984,
      "step": 5885
    },
    {
      "epoch": 65.44444444444444,
      "grad_norm": 9.258533850697859e-07,
      "learning_rate": 4.7373261693936786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1649376,
      "step": 5890
    },
    {
      "epoch": 65.5,
      "grad_norm": 1.0971036772389198e-06,
      "learning_rate": 4.7368879355471595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1650784,
      "step": 5895
    },
    {
      "epoch": 65.55555555555556,
      "grad_norm": 1.0498731626285007e-06,
      "learning_rate": 4.736449356744409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1652160,
      "step": 5900
    },
    {
      "epoch": 65.61111111111111,
      "grad_norm": 8.187880666810088e-07,
      "learning_rate": 4.736010433053064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1653568,
      "step": 5905
    },
    {
      "epoch": 65.66666666666667,
      "grad_norm": 1.6576819916735985e-06,
      "learning_rate": 4.73557116454081e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1655008,
      "step": 5910
    },
    {
      "epoch": 65.72222222222223,
      "grad_norm": 1.0043019074146287e-06,
      "learning_rate": 4.735131551275389e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1656448,
      "step": 5915
    },
    {
      "epoch": 65.77777777777777,
      "grad_norm": 1.0153074754271074e-06,
      "learning_rate": 4.734691593324594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1657840,
      "step": 5920
    },
    {
      "epoch": 65.83333333333333,
      "grad_norm": 2.4410817331954604e-06,
      "learning_rate": 4.734251290756272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1659248,
      "step": 5925
    },
    {
      "epoch": 65.88888888888889,
      "grad_norm": 8.779214226706245e-07,
      "learning_rate": 4.7338106436383246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1660656,
      "step": 5930
    },
    {
      "epoch": 65.94444444444444,
      "grad_norm": 1.806152567951358e-06,
      "learning_rate": 4.733369652038703e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1662064,
      "step": 5935
    },
    {
      "epoch": 66.0,
      "grad_norm": 8.012033845261612e-07,
      "learning_rate": 4.7329283160254156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1663520,
      "step": 5940
    },
    {
      "epoch": 66.05555555555556,
      "grad_norm": 1.124775508287712e-06,
      "learning_rate": 4.732486635666521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1664864,
      "step": 5945
    },
    {
      "epoch": 66.11111111111111,
      "grad_norm": 7.617350092914421e-07,
      "learning_rate": 4.732044611030132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1666240,
      "step": 5950
    },
    {
      "epoch": 66.16666666666667,
      "grad_norm": 1.3396141866905964e-06,
      "learning_rate": 4.731602242184414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1667648,
      "step": 5955
    },
    {
      "epoch": 66.22222222222223,
      "grad_norm": 3.6419146454136353e-06,
      "learning_rate": 4.7311595291975864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1669040,
      "step": 5960
    },
    {
      "epoch": 66.27777777777777,
      "grad_norm": 5.810933089378523e-06,
      "learning_rate": 4.7307164721379216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1670400,
      "step": 5965
    },
    {
      "epoch": 66.33333333333333,
      "grad_norm": 7.827481454114604e-07,
      "learning_rate": 4.730273071073743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1671856,
      "step": 5970
    },
    {
      "epoch": 66.38888888888889,
      "grad_norm": 1.2971975138498237e-06,
      "learning_rate": 4.729829326073429e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1673248,
      "step": 5975
    },
    {
      "epoch": 66.44444444444444,
      "grad_norm": 8.434748792751634e-07,
      "learning_rate": 4.7293852372054126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1674672,
      "step": 5980
    },
    {
      "epoch": 66.5,
      "grad_norm": 1.0906285297096474e-06,
      "learning_rate": 4.728940804538176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1676080,
      "step": 5985
    },
    {
      "epoch": 66.55555555555556,
      "grad_norm": 7.670853960917157e-07,
      "learning_rate": 4.7284960281402556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1677504,
      "step": 5990
    },
    {
      "epoch": 66.61111111111111,
      "grad_norm": 1.1423280739109032e-06,
      "learning_rate": 4.728050908080244e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1678912,
      "step": 5995
    },
    {
      "epoch": 66.66666666666667,
      "grad_norm": 9.005744345813582e-07,
      "learning_rate": 4.727605444426782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1680352,
      "step": 6000
    },
    {
      "epoch": 66.66666666666667,
      "eval_loss": 0.24982008337974548,
      "eval_runtime": 1.3182,
      "eval_samples_per_second": 30.344,
      "eval_steps_per_second": 15.172,
      "num_input_tokens_seen": 1680352,
      "step": 6000
    },
    {
      "epoch": 66.72222222222223,
      "grad_norm": 9.199073360832699e-07,
      "learning_rate": 4.727159637248567e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1681744,
      "step": 6005
    },
    {
      "epoch": 66.77777777777777,
      "grad_norm": 1.1232124279558775e-06,
      "learning_rate": 4.7267134866143474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1683168,
      "step": 6010
    },
    {
      "epoch": 66.83333333333333,
      "grad_norm": 1.8820026070898166e-06,
      "learning_rate": 4.726266992592926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1684528,
      "step": 6015
    },
    {
      "epoch": 66.88888888888889,
      "grad_norm": 1.3370067790674511e-06,
      "learning_rate": 4.725820155253157e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1685904,
      "step": 6020
    },
    {
      "epoch": 66.94444444444444,
      "grad_norm": 1.0198400559602305e-06,
      "learning_rate": 4.725372974663948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1687280,
      "step": 6025
    },
    {
      "epoch": 67.0,
      "grad_norm": 2.7376270281820325e-06,
      "learning_rate": 4.724925450894262e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1688688,
      "step": 6030
    },
    {
      "epoch": 67.05555555555556,
      "grad_norm": 1.485090820096957e-06,
      "learning_rate": 4.72447758401311e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1690112,
      "step": 6035
    },
    {
      "epoch": 67.11111111111111,
      "grad_norm": 9.571691634846502e-07,
      "learning_rate": 4.7240293740895616e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1691568,
      "step": 6040
    },
    {
      "epoch": 67.16666666666667,
      "grad_norm": 1.105163391912356e-06,
      "learning_rate": 4.723580821192733e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1692960,
      "step": 6045
    },
    {
      "epoch": 67.22222222222223,
      "grad_norm": 9.307213986176066e-07,
      "learning_rate": 4.7231319253917996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1694352,
      "step": 6050
    },
    {
      "epoch": 67.27777777777777,
      "grad_norm": 1.1020308647857746e-06,
      "learning_rate": 4.722682686755986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1695744,
      "step": 6055
    },
    {
      "epoch": 67.33333333333333,
      "grad_norm": 1.0171403346248553e-06,
      "learning_rate": 4.722233105354569e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1697120,
      "step": 6060
    },
    {
      "epoch": 67.38888888888889,
      "grad_norm": 9.965906428988092e-07,
      "learning_rate": 4.7217831812568815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1698528,
      "step": 6065
    },
    {
      "epoch": 67.44444444444444,
      "grad_norm": 3.4703155051829526e-06,
      "learning_rate": 4.721332914532307e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1699920,
      "step": 6070
    },
    {
      "epoch": 67.5,
      "grad_norm": 1.331971475337923e-06,
      "learning_rate": 4.720882305250281e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1701312,
      "step": 6075
    },
    {
      "epoch": 67.55555555555556,
      "grad_norm": 1.1603763141465606e-06,
      "learning_rate": 4.720431353480295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1702688,
      "step": 6080
    },
    {
      "epoch": 67.61111111111111,
      "grad_norm": 9.244844818567799e-07,
      "learning_rate": 4.719980059291891e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1704096,
      "step": 6085
    },
    {
      "epoch": 67.66666666666667,
      "grad_norm": 1.2079590305802412e-06,
      "learning_rate": 4.7195284227546634e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1705520,
      "step": 6090
    },
    {
      "epoch": 67.72222222222223,
      "grad_norm": 1.014528493215039e-06,
      "learning_rate": 4.7190764439382604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1706976,
      "step": 6095
    },
    {
      "epoch": 67.77777777777777,
      "grad_norm": 1.1910152579730493e-06,
      "learning_rate": 4.7186241229123826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1708400,
      "step": 6100
    },
    {
      "epoch": 67.83333333333333,
      "grad_norm": 8.296777309624304e-07,
      "learning_rate": 4.718171459746785e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1709776,
      "step": 6105
    },
    {
      "epoch": 67.88888888888889,
      "grad_norm": 1.1642543995549204e-06,
      "learning_rate": 4.717718454511273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1711168,
      "step": 6110
    },
    {
      "epoch": 67.94444444444444,
      "grad_norm": 7.295103614524123e-07,
      "learning_rate": 4.7172651072757056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1712528,
      "step": 6115
    },
    {
      "epoch": 68.0,
      "grad_norm": 1.1292892168057733e-06,
      "learning_rate": 4.7168114181099945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1713920,
      "step": 6120
    },
    {
      "epoch": 68.05555555555556,
      "grad_norm": 1.669837274675956e-06,
      "learning_rate": 4.716357387084105e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1715296,
      "step": 6125
    },
    {
      "epoch": 68.11111111111111,
      "grad_norm": 8.665780342198559e-07,
      "learning_rate": 4.715903014268054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1716672,
      "step": 6130
    },
    {
      "epoch": 68.16666666666667,
      "grad_norm": 9.224176551470009e-07,
      "learning_rate": 4.715448299731911e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1718048,
      "step": 6135
    },
    {
      "epoch": 68.22222222222223,
      "grad_norm": 1.0645154588928563e-06,
      "learning_rate": 4.7149932435457986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1719456,
      "step": 6140
    },
    {
      "epoch": 68.27777777777777,
      "grad_norm": 1.1887075288541382e-06,
      "learning_rate": 4.714537845779894e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1720880,
      "step": 6145
    },
    {
      "epoch": 68.33333333333333,
      "grad_norm": 1.1224720992686343e-06,
      "learning_rate": 4.714082106504423e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1722288,
      "step": 6150
    },
    {
      "epoch": 68.38888888888889,
      "grad_norm": 9.574938530931831e-07,
      "learning_rate": 4.713626025789667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1723712,
      "step": 6155
    },
    {
      "epoch": 68.44444444444444,
      "grad_norm": 7.123362024685775e-07,
      "learning_rate": 4.7131696037059606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1725088,
      "step": 6160
    },
    {
      "epoch": 68.5,
      "grad_norm": 1.2154914657003246e-06,
      "learning_rate": 4.712712840323689e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1726464,
      "step": 6165
    },
    {
      "epoch": 68.55555555555556,
      "grad_norm": 1.0740135394371464e-06,
      "learning_rate": 4.71225573571329e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1727952,
      "step": 6170
    },
    {
      "epoch": 68.61111111111111,
      "grad_norm": 9.475166962147341e-07,
      "learning_rate": 4.711798289945256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1729360,
      "step": 6175
    },
    {
      "epoch": 68.66666666666667,
      "grad_norm": 1.5731919802419725e-06,
      "learning_rate": 4.71134050309013e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1730816,
      "step": 6180
    },
    {
      "epoch": 68.72222222222223,
      "grad_norm": 1.0003789157053689e-06,
      "learning_rate": 4.710882375218509e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1732256,
      "step": 6185
    },
    {
      "epoch": 68.77777777777777,
      "grad_norm": 9.996083463192917e-07,
      "learning_rate": 4.7104239064010424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1733648,
      "step": 6190
    },
    {
      "epoch": 68.83333333333333,
      "grad_norm": 8.880261361809971e-07,
      "learning_rate": 4.709965096708432e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1735008,
      "step": 6195
    },
    {
      "epoch": 68.88888888888889,
      "grad_norm": 1.1290513839412597e-06,
      "learning_rate": 4.709505946211431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1736384,
      "step": 6200
    },
    {
      "epoch": 68.88888888888889,
      "eval_loss": 0.232396200299263,
      "eval_runtime": 1.3211,
      "eval_samples_per_second": 30.278,
      "eval_steps_per_second": 15.139,
      "num_input_tokens_seen": 1736384,
      "step": 6200
    },
    {
      "epoch": 68.94444444444444,
      "grad_norm": 2.1000860215281136e-06,
      "learning_rate": 4.709046454980846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1737776,
      "step": 6205
    },
    {
      "epoch": 69.0,
      "grad_norm": 1.008350864140084e-06,
      "learning_rate": 4.708586623087538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1739184,
      "step": 6210
    },
    {
      "epoch": 69.05555555555556,
      "grad_norm": 2.4075682176771807e-06,
      "learning_rate": 4.708126450602418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1740592,
      "step": 6215
    },
    {
      "epoch": 69.11111111111111,
      "grad_norm": 1.7426939393772045e-06,
      "learning_rate": 4.7076659375964495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1741984,
      "step": 6220
    },
    {
      "epoch": 69.16666666666667,
      "grad_norm": 1.0592669923426001e-06,
      "learning_rate": 4.707205084140651e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1743408,
      "step": 6225
    },
    {
      "epoch": 69.22222222222223,
      "grad_norm": 9.30519490793813e-07,
      "learning_rate": 4.7067438903060904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1744848,
      "step": 6230
    },
    {
      "epoch": 69.27777777777777,
      "grad_norm": 8.619610980531434e-07,
      "learning_rate": 4.70628235616389e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1746240,
      "step": 6235
    },
    {
      "epoch": 69.33333333333333,
      "grad_norm": 1.2483702676036046e-06,
      "learning_rate": 4.7058204817852256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1747600,
      "step": 6240
    },
    {
      "epoch": 69.38888888888889,
      "grad_norm": 1.1466887599453912e-06,
      "learning_rate": 4.705358267241322e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1749008,
      "step": 6245
    },
    {
      "epoch": 69.44444444444444,
      "grad_norm": 9.684182487035287e-07,
      "learning_rate": 4.704895712603459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1750400,
      "step": 6250
    },
    {
      "epoch": 69.5,
      "grad_norm": 1.0237858987238724e-06,
      "learning_rate": 4.704432817942969e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1751856,
      "step": 6255
    },
    {
      "epoch": 69.55555555555556,
      "grad_norm": 9.488351793152106e-07,
      "learning_rate": 4.703969583331236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1753200,
      "step": 6260
    },
    {
      "epoch": 69.61111111111111,
      "grad_norm": 1.1409936178097269e-06,
      "learning_rate": 4.7035060088396965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1754560,
      "step": 6265
    },
    {
      "epoch": 69.66666666666667,
      "grad_norm": 1.182627215712273e-06,
      "learning_rate": 4.703042094539839e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1755968,
      "step": 6270
    },
    {
      "epoch": 69.72222222222223,
      "grad_norm": 1.0897859965552925e-06,
      "learning_rate": 4.702577840503206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1757376,
      "step": 6275
    },
    {
      "epoch": 69.77777777777777,
      "grad_norm": 7.668012358408305e-07,
      "learning_rate": 4.70211324680139e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1758768,
      "step": 6280
    },
    {
      "epoch": 69.83333333333333,
      "grad_norm": 8.858834803504578e-07,
      "learning_rate": 4.7016483135060386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1760208,
      "step": 6285
    },
    {
      "epoch": 69.88888888888889,
      "grad_norm": 1.0974459883072996e-06,
      "learning_rate": 4.701183040688849e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1761584,
      "step": 6290
    },
    {
      "epoch": 69.94444444444444,
      "grad_norm": 9.96919879980851e-07,
      "learning_rate": 4.700717428421573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1763040,
      "step": 6295
    },
    {
      "epoch": 70.0,
      "grad_norm": 8.116920184875198e-07,
      "learning_rate": 4.700251476776014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1764432,
      "step": 6300
    },
    {
      "epoch": 70.05555555555556,
      "grad_norm": 8.754911959840683e-07,
      "learning_rate": 4.699785185824026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1765808,
      "step": 6305
    },
    {
      "epoch": 70.11111111111111,
      "grad_norm": 3.7175639135966776e-06,
      "learning_rate": 4.699318555637519e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1767168,
      "step": 6310
    },
    {
      "epoch": 70.16666666666667,
      "grad_norm": 8.69423615768028e-07,
      "learning_rate": 4.6988515862884525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1768576,
      "step": 6315
    },
    {
      "epoch": 70.22222222222223,
      "grad_norm": 8.691565653862199e-07,
      "learning_rate": 4.698384277848838e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1770032,
      "step": 6320
    },
    {
      "epoch": 70.27777777777777,
      "grad_norm": 1.0440469395689433e-06,
      "learning_rate": 4.6979166303907425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1771392,
      "step": 6325
    },
    {
      "epoch": 70.33333333333333,
      "grad_norm": 1.0161098771277466e-06,
      "learning_rate": 4.697448643986281e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1772784,
      "step": 6330
    },
    {
      "epoch": 70.38888888888889,
      "grad_norm": 1.1203267149539897e-06,
      "learning_rate": 4.696980318707624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1774224,
      "step": 6335
    },
    {
      "epoch": 70.44444444444444,
      "grad_norm": 8.570094109927595e-07,
      "learning_rate": 4.6965116546269924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1775648,
      "step": 6340
    },
    {
      "epoch": 70.5,
      "grad_norm": 9.620390528652933e-07,
      "learning_rate": 4.6960426518166615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1777024,
      "step": 6345
    },
    {
      "epoch": 70.55555555555556,
      "grad_norm": 8.2852460536742e-07,
      "learning_rate": 4.6955733103489556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1778448,
      "step": 6350
    },
    {
      "epoch": 70.61111111111111,
      "grad_norm": 1.8304031073057558e-06,
      "learning_rate": 4.695103630296255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1779840,
      "step": 6355
    },
    {
      "epoch": 70.66666666666667,
      "grad_norm": 8.516147431691934e-07,
      "learning_rate": 4.694633611730988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1781264,
      "step": 6360
    },
    {
      "epoch": 70.72222222222223,
      "grad_norm": 1.1489138387332787e-06,
      "learning_rate": 4.694163254725639e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1782672,
      "step": 6365
    },
    {
      "epoch": 70.77777777777777,
      "grad_norm": 9.747290050654556e-07,
      "learning_rate": 4.693692559352743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1784080,
      "step": 6370
    },
    {
      "epoch": 70.83333333333333,
      "grad_norm": 8.32920420634764e-07,
      "learning_rate": 4.693221525684886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1785472,
      "step": 6375
    },
    {
      "epoch": 70.88888888888889,
      "grad_norm": 1.862668000285339e-06,
      "learning_rate": 4.6927501537947084e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1786880,
      "step": 6380
    },
    {
      "epoch": 70.94444444444444,
      "grad_norm": 9.057681609192514e-07,
      "learning_rate": 4.692278443754901e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1788256,
      "step": 6385
    },
    {
      "epoch": 71.0,
      "grad_norm": 1.4930973293303396e-06,
      "learning_rate": 4.691806395638208e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1789632,
      "step": 6390
    },
    {
      "epoch": 71.05555555555556,
      "grad_norm": 8.638912163405621e-07,
      "learning_rate": 4.6913340095174255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1791056,
      "step": 6395
    },
    {
      "epoch": 71.11111111111111,
      "grad_norm": 8.909938173928822e-07,
      "learning_rate": 4.690861285465399e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1792480,
      "step": 6400
    },
    {
      "epoch": 71.11111111111111,
      "eval_loss": 0.2660376727581024,
      "eval_runtime": 1.3296,
      "eval_samples_per_second": 30.085,
      "eval_steps_per_second": 15.042,
      "num_input_tokens_seen": 1792480,
      "step": 6400
    },
    {
      "epoch": 71.16666666666667,
      "grad_norm": 9.088904562304378e-07,
      "learning_rate": 4.690388223555031e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1793888,
      "step": 6405
    },
    {
      "epoch": 71.22222222222223,
      "grad_norm": 1.4236331935535418e-06,
      "learning_rate": 4.689914823859273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1795280,
      "step": 6410
    },
    {
      "epoch": 71.27777777777777,
      "grad_norm": 1.0227557822872768e-06,
      "learning_rate": 4.689441086451129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1796720,
      "step": 6415
    },
    {
      "epoch": 71.33333333333333,
      "grad_norm": 7.660611913706816e-07,
      "learning_rate": 4.688967011403655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1798144,
      "step": 6420
    },
    {
      "epoch": 71.38888888888889,
      "grad_norm": 1.3454420013658819e-06,
      "learning_rate": 4.68849259878996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1799504,
      "step": 6425
    },
    {
      "epoch": 71.44444444444444,
      "grad_norm": 1.4399457768377033e-06,
      "learning_rate": 4.6880178486832036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1800928,
      "step": 6430
    },
    {
      "epoch": 71.5,
      "grad_norm": 9.50254957388097e-07,
      "learning_rate": 4.687542761156598e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1802304,
      "step": 6435
    },
    {
      "epoch": 71.55555555555556,
      "grad_norm": 8.166085763150477e-07,
      "learning_rate": 4.6870673362834096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1803712,
      "step": 6440
    },
    {
      "epoch": 71.61111111111111,
      "grad_norm": 7.614386277055019e-07,
      "learning_rate": 4.6865915741369526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1805104,
      "step": 6445
    },
    {
      "epoch": 71.66666666666667,
      "grad_norm": 7.557684966741363e-07,
      "learning_rate": 4.686115474790597e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1806528,
      "step": 6450
    },
    {
      "epoch": 71.72222222222223,
      "grad_norm": 4.39445830124896e-06,
      "learning_rate": 4.685639038317762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1807904,
      "step": 6455
    },
    {
      "epoch": 71.77777777777777,
      "grad_norm": 7.672896913391014e-07,
      "learning_rate": 4.685162264791921e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1809280,
      "step": 6460
    },
    {
      "epoch": 71.83333333333333,
      "grad_norm": 8.998054568110092e-07,
      "learning_rate": 4.684685154286599e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1810640,
      "step": 6465
    },
    {
      "epoch": 71.88888888888889,
      "grad_norm": 7.674773883081798e-07,
      "learning_rate": 4.684207706875371e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1812064,
      "step": 6470
    },
    {
      "epoch": 71.94444444444444,
      "grad_norm": 1.1901626066901372e-06,
      "learning_rate": 4.683729922631866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1813472,
      "step": 6475
    },
    {
      "epoch": 72.0,
      "grad_norm": 1.2650683629544801e-06,
      "learning_rate": 4.683251801629765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1814864,
      "step": 6480
    },
    {
      "epoch": 72.05555555555556,
      "grad_norm": 1.3188964658183977e-06,
      "learning_rate": 4.6827733439428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1816304,
      "step": 6485
    },
    {
      "epoch": 72.11111111111111,
      "grad_norm": 7.639349632881931e-07,
      "learning_rate": 4.682294549644754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1817680,
      "step": 6490
    },
    {
      "epoch": 72.16666666666667,
      "grad_norm": 7.924524538793776e-07,
      "learning_rate": 4.681815418809464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1819104,
      "step": 6495
    },
    {
      "epoch": 72.22222222222223,
      "grad_norm": 1.0960349072774989e-06,
      "learning_rate": 4.681335951510819e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1820512,
      "step": 6500
    },
    {
      "epoch": 72.27777777777777,
      "grad_norm": 7.022071599749324e-07,
      "learning_rate": 4.6808561478227576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1821920,
      "step": 6505
    },
    {
      "epoch": 72.33333333333333,
      "grad_norm": 7.936166639410658e-07,
      "learning_rate": 4.680376007819271e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1823328,
      "step": 6510
    },
    {
      "epoch": 72.38888888888889,
      "grad_norm": 9.24372955068975e-07,
      "learning_rate": 4.679895531574405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1824672,
      "step": 6515
    },
    {
      "epoch": 72.44444444444444,
      "grad_norm": 1.2848632877648924e-06,
      "learning_rate": 4.679414719162253e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1826048,
      "step": 6520
    },
    {
      "epoch": 72.5,
      "grad_norm": 7.918882261037652e-07,
      "learning_rate": 4.6789335706569635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1827424,
      "step": 6525
    },
    {
      "epoch": 72.55555555555556,
      "grad_norm": 8.044816013352829e-07,
      "learning_rate": 4.678452086132734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1828832,
      "step": 6530
    },
    {
      "epoch": 72.61111111111111,
      "grad_norm": 1.187382395073655e-06,
      "learning_rate": 4.677970265663818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1830240,
      "step": 6535
    },
    {
      "epoch": 72.66666666666667,
      "grad_norm": 7.784421427459165e-07,
      "learning_rate": 4.677488109324517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1831616,
      "step": 6540
    },
    {
      "epoch": 72.72222222222223,
      "grad_norm": 9.650177617004374e-07,
      "learning_rate": 4.6770056171891846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1833024,
      "step": 6545
    },
    {
      "epoch": 72.77777777777777,
      "grad_norm": 8.663451467327832e-07,
      "learning_rate": 4.6765227893322286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1834416,
      "step": 6550
    },
    {
      "epoch": 72.83333333333333,
      "grad_norm": 2.0519203189905966e-06,
      "learning_rate": 4.676039625828107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1835856,
      "step": 6555
    },
    {
      "epoch": 72.88888888888889,
      "grad_norm": 9.184104783344083e-07,
      "learning_rate": 4.675556126751328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1837264,
      "step": 6560
    },
    {
      "epoch": 72.94444444444444,
      "grad_norm": 1.0733348290159483e-06,
      "learning_rate": 4.6750722921764556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1838672,
      "step": 6565
    },
    {
      "epoch": 73.0,
      "grad_norm": 1.0438139952384518e-06,
      "learning_rate": 4.674588122178102e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1840096,
      "step": 6570
    },
    {
      "epoch": 73.05555555555556,
      "grad_norm": 8.853918984641496e-07,
      "learning_rate": 4.674103616830931e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1841488,
      "step": 6575
    },
    {
      "epoch": 73.11111111111111,
      "grad_norm": 7.838846158847446e-07,
      "learning_rate": 4.673618776209663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1842880,
      "step": 6580
    },
    {
      "epoch": 73.16666666666667,
      "grad_norm": 8.446703532172251e-07,
      "learning_rate": 4.673133600389063e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1844288,
      "step": 6585
    },
    {
      "epoch": 73.22222222222223,
      "grad_norm": 8.798461408332514e-07,
      "learning_rate": 4.672648089443953e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1845696,
      "step": 6590
    },
    {
      "epoch": 73.27777777777777,
      "grad_norm": 8.504286483912438e-07,
      "learning_rate": 4.672162243449204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1847040,
      "step": 6595
    },
    {
      "epoch": 73.33333333333333,
      "grad_norm": 1.0225085134152323e-06,
      "learning_rate": 4.67167606247974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1848416,
      "step": 6600
    },
    {
      "epoch": 73.33333333333333,
      "eval_loss": 0.2606924772262573,
      "eval_runtime": 1.3101,
      "eval_samples_per_second": 30.533,
      "eval_steps_per_second": 15.266,
      "num_input_tokens_seen": 1848416,
      "step": 6600
    },
    {
      "epoch": 73.38888888888889,
      "grad_norm": 8.492779670632444e-07,
      "learning_rate": 4.671189546610536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1849792,
      "step": 6605
    },
    {
      "epoch": 73.44444444444444,
      "grad_norm": 8.023235409382323e-07,
      "learning_rate": 4.67070269591662e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1851168,
      "step": 6610
    },
    {
      "epoch": 73.5,
      "grad_norm": 6.97899736223917e-07,
      "learning_rate": 4.670215510473068e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1852592,
      "step": 6615
    },
    {
      "epoch": 73.55555555555556,
      "grad_norm": 8.774497928243363e-07,
      "learning_rate": 4.669727990355013e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1854000,
      "step": 6620
    },
    {
      "epoch": 73.61111111111111,
      "grad_norm": 8.309064583045256e-07,
      "learning_rate": 4.669240135637635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1855376,
      "step": 6625
    },
    {
      "epoch": 73.66666666666667,
      "grad_norm": 9.369677513859642e-07,
      "learning_rate": 4.6687519463961675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1856752,
      "step": 6630
    },
    {
      "epoch": 73.72222222222223,
      "grad_norm": 9.332504191661428e-07,
      "learning_rate": 4.668263422705896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1858176,
      "step": 6635
    },
    {
      "epoch": 73.77777777777777,
      "grad_norm": 9.498503459326457e-07,
      "learning_rate": 4.667774564642156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1859584,
      "step": 6640
    },
    {
      "epoch": 73.83333333333333,
      "grad_norm": 9.141896271103178e-07,
      "learning_rate": 4.6672853722803365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1860992,
      "step": 6645
    },
    {
      "epoch": 73.88888888888889,
      "grad_norm": 9.927814517141087e-07,
      "learning_rate": 4.666795845695877e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1862416,
      "step": 6650
    },
    {
      "epoch": 73.94444444444444,
      "grad_norm": 9.359137038700283e-07,
      "learning_rate": 4.666305984964269e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1863856,
      "step": 6655
    },
    {
      "epoch": 74.0,
      "grad_norm": 8.09714151728258e-07,
      "learning_rate": 4.6658157901610535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1865232,
      "step": 6660
    },
    {
      "epoch": 74.05555555555556,
      "grad_norm": 8.630748311588832e-07,
      "learning_rate": 4.665325261361826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1866672,
      "step": 6665
    },
    {
      "epoch": 74.11111111111111,
      "grad_norm": 1.5170312508416828e-06,
      "learning_rate": 4.664834398642232e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1868064,
      "step": 6670
    },
    {
      "epoch": 74.16666666666667,
      "grad_norm": 2.117408939739107e-06,
      "learning_rate": 4.6643432020779686e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1869456,
      "step": 6675
    },
    {
      "epoch": 74.22222222222223,
      "grad_norm": 7.973886226864124e-07,
      "learning_rate": 4.663851671744786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1870848,
      "step": 6680
    },
    {
      "epoch": 74.27777777777777,
      "grad_norm": 7.806220310158096e-07,
      "learning_rate": 4.6633598077184815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1872272,
      "step": 6685
    },
    {
      "epoch": 74.33333333333333,
      "grad_norm": 4.110551344638225e-06,
      "learning_rate": 4.662867610074908e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1873648,
      "step": 6690
    },
    {
      "epoch": 74.38888888888889,
      "grad_norm": 8.68291976985347e-07,
      "learning_rate": 4.6623750788899696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1875040,
      "step": 6695
    },
    {
      "epoch": 74.44444444444444,
      "grad_norm": 1.1741294656530954e-06,
      "learning_rate": 4.6618822142396195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1876368,
      "step": 6700
    },
    {
      "epoch": 74.5,
      "grad_norm": 9.55476480157813e-07,
      "learning_rate": 4.661389016199864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1877792,
      "step": 6705
    },
    {
      "epoch": 74.55555555555556,
      "grad_norm": 7.322337864934525e-07,
      "learning_rate": 4.660895484846761e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1879200,
      "step": 6710
    },
    {
      "epoch": 74.61111111111111,
      "grad_norm": 1.1219802900086506e-06,
      "learning_rate": 4.660401620256418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1880640,
      "step": 6715
    },
    {
      "epoch": 74.66666666666667,
      "grad_norm": 6.610211471524963e-07,
      "learning_rate": 4.659907422504997e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1882032,
      "step": 6720
    },
    {
      "epoch": 74.72222222222223,
      "grad_norm": 8.96343692602386e-07,
      "learning_rate": 4.6594128916687074e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1883472,
      "step": 6725
    },
    {
      "epoch": 74.77777777777777,
      "grad_norm": 9.579810011928203e-07,
      "learning_rate": 4.658918027823813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1884864,
      "step": 6730
    },
    {
      "epoch": 74.83333333333333,
      "grad_norm": 7.287953280865622e-07,
      "learning_rate": 4.658422831046628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1886256,
      "step": 6735
    },
    {
      "epoch": 74.88888888888889,
      "grad_norm": 8.654307634969882e-07,
      "learning_rate": 4.657927301413518e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1887648,
      "step": 6740
    },
    {
      "epoch": 74.94444444444444,
      "grad_norm": 8.498575425619492e-07,
      "learning_rate": 4.657431439000901e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1889040,
      "step": 6745
    },
    {
      "epoch": 75.0,
      "grad_norm": 7.784932449794724e-07,
      "learning_rate": 4.656935243885243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1890432,
      "step": 6750
    },
    {
      "epoch": 75.05555555555556,
      "grad_norm": 8.587492175138323e-07,
      "learning_rate": 4.656438716143066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1891824,
      "step": 6755
    },
    {
      "epoch": 75.11111111111111,
      "grad_norm": 1.1271987432337482e-06,
      "learning_rate": 4.6559418558509384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1893232,
      "step": 6760
    },
    {
      "epoch": 75.16666666666667,
      "grad_norm": 8.449052870673768e-07,
      "learning_rate": 4.6554446630854833e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1894640,
      "step": 6765
    },
    {
      "epoch": 75.22222222222223,
      "grad_norm": 7.556088235105562e-07,
      "learning_rate": 4.654947137923374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1896080,
      "step": 6770
    },
    {
      "epoch": 75.27777777777777,
      "grad_norm": 7.623410169799172e-07,
      "learning_rate": 4.654449280441335e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1897472,
      "step": 6775
    },
    {
      "epoch": 75.33333333333333,
      "grad_norm": 7.686651883886952e-07,
      "learning_rate": 4.653951090716143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1898864,
      "step": 6780
    },
    {
      "epoch": 75.38888888888889,
      "grad_norm": 7.40101029350626e-07,
      "learning_rate": 4.653452568824625e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1900272,
      "step": 6785
    },
    {
      "epoch": 75.44444444444444,
      "grad_norm": 7.766391263430705e-07,
      "learning_rate": 4.6529537148436585e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1901648,
      "step": 6790
    },
    {
      "epoch": 75.5,
      "grad_norm": 9.63302682066569e-07,
      "learning_rate": 4.6524545288501734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1903088,
      "step": 6795
    },
    {
      "epoch": 75.55555555555556,
      "grad_norm": 7.396976684503898e-07,
      "learning_rate": 4.6519550109211506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1904480,
      "step": 6800
    },
    {
      "epoch": 75.55555555555556,
      "eval_loss": 0.27321183681488037,
      "eval_runtime": 1.3362,
      "eval_samples_per_second": 29.937,
      "eval_steps_per_second": 14.968,
      "num_input_tokens_seen": 1904480,
      "step": 6800
    },
    {
      "epoch": 75.61111111111111,
      "grad_norm": 8.130550668283831e-07,
      "learning_rate": 4.651455161133622e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1905856,
      "step": 6805
    },
    {
      "epoch": 75.66666666666667,
      "grad_norm": 2.2695692223351216e-06,
      "learning_rate": 4.6509549795646704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1907232,
      "step": 6810
    },
    {
      "epoch": 75.72222222222223,
      "grad_norm": 8.485453690809663e-07,
      "learning_rate": 4.6504544662914306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1908672,
      "step": 6815
    },
    {
      "epoch": 75.77777777777777,
      "grad_norm": 1.1101401469204575e-06,
      "learning_rate": 4.6499536213910876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1910064,
      "step": 6820
    },
    {
      "epoch": 75.83333333333333,
      "grad_norm": 1.0595290405035485e-06,
      "learning_rate": 4.6494524449408786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1911488,
      "step": 6825
    },
    {
      "epoch": 75.88888888888889,
      "grad_norm": 2.3113434508559294e-06,
      "learning_rate": 4.6489509370180903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1912864,
      "step": 6830
    },
    {
      "epoch": 75.94444444444444,
      "grad_norm": 8.241846103373973e-07,
      "learning_rate": 4.648449097700063e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1914272,
      "step": 6835
    },
    {
      "epoch": 76.0,
      "grad_norm": 2.068567482638173e-06,
      "learning_rate": 4.647946927064185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1915600,
      "step": 6840
    },
    {
      "epoch": 76.05555555555556,
      "grad_norm": 1.618435931050044e-06,
      "learning_rate": 4.647444425187898e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1916992,
      "step": 6845
    },
    {
      "epoch": 76.11111111111111,
      "grad_norm": 8.34400395888224e-07,
      "learning_rate": 4.646941592148695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1918368,
      "step": 6850
    },
    {
      "epoch": 76.16666666666667,
      "grad_norm": 6.775530891900416e-07,
      "learning_rate": 4.646438428024117e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1919696,
      "step": 6855
    },
    {
      "epoch": 76.22222222222223,
      "grad_norm": 1.0374130852142116e-06,
      "learning_rate": 4.64593493289176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1921104,
      "step": 6860
    },
    {
      "epoch": 76.27777777777777,
      "grad_norm": 8.199927492569259e-07,
      "learning_rate": 4.64543110682927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1922496,
      "step": 6865
    },
    {
      "epoch": 76.33333333333333,
      "grad_norm": 8.089828611446137e-07,
      "learning_rate": 4.644926949914341e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1923968,
      "step": 6870
    },
    {
      "epoch": 76.38888888888889,
      "grad_norm": 6.882078196213115e-07,
      "learning_rate": 4.644422462224722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1925376,
      "step": 6875
    },
    {
      "epoch": 76.44444444444444,
      "grad_norm": 7.601881861774018e-07,
      "learning_rate": 4.643917643838211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1926800,
      "step": 6880
    },
    {
      "epoch": 76.5,
      "grad_norm": 7.530282459811133e-07,
      "learning_rate": 4.6434124948326564e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1928160,
      "step": 6885
    },
    {
      "epoch": 76.55555555555556,
      "grad_norm": 7.689449148529093e-07,
      "learning_rate": 4.6429070152859594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1929600,
      "step": 6890
    },
    {
      "epoch": 76.61111111111111,
      "grad_norm": 7.993682515916589e-07,
      "learning_rate": 4.6424012052760714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1930944,
      "step": 6895
    },
    {
      "epoch": 76.66666666666667,
      "grad_norm": 1.8175086324845324e-06,
      "learning_rate": 4.6418950648809945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1932368,
      "step": 6900
    },
    {
      "epoch": 76.72222222222223,
      "grad_norm": 8.415353249802138e-07,
      "learning_rate": 4.641388594178782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1933744,
      "step": 6905
    },
    {
      "epoch": 76.77777777777777,
      "grad_norm": 1.0155217751162127e-06,
      "learning_rate": 4.640881793247538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1935184,
      "step": 6910
    },
    {
      "epoch": 76.83333333333333,
      "grad_norm": 7.223626425911789e-07,
      "learning_rate": 4.6403746621654173e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1936544,
      "step": 6915
    },
    {
      "epoch": 76.88888888888889,
      "grad_norm": 1.0175078841712093e-06,
      "learning_rate": 4.639867201010626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1937936,
      "step": 6920
    },
    {
      "epoch": 76.94444444444444,
      "grad_norm": 2.5794461180339567e-06,
      "learning_rate": 4.6393594098614204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1939360,
      "step": 6925
    },
    {
      "epoch": 77.0,
      "grad_norm": 8.558571948924509e-07,
      "learning_rate": 4.63885128879611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1940800,
      "step": 6930
    },
    {
      "epoch": 77.05555555555556,
      "grad_norm": 6.699474965898844e-07,
      "learning_rate": 4.638342837893052e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1942240,
      "step": 6935
    },
    {
      "epoch": 77.11111111111111,
      "grad_norm": 1.0807316357386298e-06,
      "learning_rate": 4.6378340572306565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1943664,
      "step": 6940
    },
    {
      "epoch": 77.16666666666667,
      "grad_norm": 8.092758321254223e-07,
      "learning_rate": 4.6373249468873833e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1945040,
      "step": 6945
    },
    {
      "epoch": 77.22222222222223,
      "grad_norm": 9.005722176880226e-07,
      "learning_rate": 4.636815506941744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1946432,
      "step": 6950
    },
    {
      "epoch": 77.27777777777777,
      "grad_norm": 7.686172693865956e-07,
      "learning_rate": 4.6363057374723004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1947824,
      "step": 6955
    },
    {
      "epoch": 77.33333333333333,
      "grad_norm": 6.973558583922568e-07,
      "learning_rate": 4.635795638557666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1949232,
      "step": 6960
    },
    {
      "epoch": 77.38888888888889,
      "grad_norm": 7.094755574144074e-07,
      "learning_rate": 4.635285210276504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1950656,
      "step": 6965
    },
    {
      "epoch": 77.44444444444444,
      "grad_norm": 5.71371492696926e-06,
      "learning_rate": 4.6347744527075295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1952112,
      "step": 6970
    },
    {
      "epoch": 77.5,
      "grad_norm": 6.648843395851145e-07,
      "learning_rate": 4.634263365929506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1953552,
      "step": 6975
    },
    {
      "epoch": 77.55555555555556,
      "grad_norm": 8.369847250833118e-07,
      "learning_rate": 4.6337519500212515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1954912,
      "step": 6980
    },
    {
      "epoch": 77.61111111111111,
      "grad_norm": 8.822219115245389e-07,
      "learning_rate": 4.633240205061632e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1956320,
      "step": 6985
    },
    {
      "epoch": 77.66666666666667,
      "grad_norm": 1.1572260518732946e-06,
      "learning_rate": 4.632728131129565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1957696,
      "step": 6990
    },
    {
      "epoch": 77.72222222222223,
      "grad_norm": 8.185054412024328e-07,
      "learning_rate": 4.632215728304018e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1959104,
      "step": 6995
    },
    {
      "epoch": 77.77777777777777,
      "grad_norm": 7.97180518929963e-07,
      "learning_rate": 4.63170299666401e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1960496,
      "step": 7000
    },
    {
      "epoch": 77.77777777777777,
      "eval_loss": 0.268013060092926,
      "eval_runtime": 1.3206,
      "eval_samples_per_second": 30.29,
      "eval_steps_per_second": 15.145,
      "num_input_tokens_seen": 1960496,
      "step": 7000
    },
    {
      "epoch": 77.83333333333333,
      "grad_norm": 8.920191589822934e-07,
      "learning_rate": 4.631189936288612e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1961936,
      "step": 7005
    },
    {
      "epoch": 77.88888888888889,
      "grad_norm": 9.08937352050998e-07,
      "learning_rate": 4.630676547256944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1963296,
      "step": 7010
    },
    {
      "epoch": 77.94444444444444,
      "grad_norm": 8.97251936748944e-07,
      "learning_rate": 4.630162829648176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1964656,
      "step": 7015
    },
    {
      "epoch": 78.0,
      "grad_norm": 9.5564928415115e-07,
      "learning_rate": 4.629648783541531e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1966096,
      "step": 7020
    },
    {
      "epoch": 78.05555555555556,
      "grad_norm": 1.17611966743425e-06,
      "learning_rate": 4.6291344090162804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1967552,
      "step": 7025
    },
    {
      "epoch": 78.11111111111111,
      "grad_norm": 1.3789427839583368e-06,
      "learning_rate": 4.628619706151748e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1968928,
      "step": 7030
    },
    {
      "epoch": 78.16666666666667,
      "grad_norm": 1.7633356037549675e-06,
      "learning_rate": 4.628104675027306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1970336,
      "step": 7035
    },
    {
      "epoch": 78.22222222222223,
      "grad_norm": 8.906581570045091e-07,
      "learning_rate": 4.6275893157223805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1971744,
      "step": 7040
    },
    {
      "epoch": 78.27777777777777,
      "grad_norm": 1.339393406851741e-06,
      "learning_rate": 4.627073628316445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1973120,
      "step": 7045
    },
    {
      "epoch": 78.33333333333333,
      "grad_norm": 4.5401548049994744e-06,
      "learning_rate": 4.626557612889026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1974512,
      "step": 7050
    },
    {
      "epoch": 78.38888888888889,
      "grad_norm": 1.0141407074115705e-06,
      "learning_rate": 4.626041269519699e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1975888,
      "step": 7055
    },
    {
      "epoch": 78.44444444444444,
      "grad_norm": 7.68948723361973e-07,
      "learning_rate": 4.6255245982880905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1977264,
      "step": 7060
    },
    {
      "epoch": 78.5,
      "grad_norm": 9.563644880472566e-07,
      "learning_rate": 4.625007599273879e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1978640,
      "step": 7065
    },
    {
      "epoch": 78.55555555555556,
      "grad_norm": 9.333699608760071e-07,
      "learning_rate": 4.6244902725567895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1980016,
      "step": 7070
    },
    {
      "epoch": 78.61111111111111,
      "grad_norm": 9.669711289461702e-07,
      "learning_rate": 4.6239726182166024e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1981392,
      "step": 7075
    },
    {
      "epoch": 78.66666666666667,
      "grad_norm": 7.217993243102683e-07,
      "learning_rate": 4.623454636333147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1982800,
      "step": 7080
    },
    {
      "epoch": 78.72222222222223,
      "grad_norm": 5.517978024727199e-06,
      "learning_rate": 4.622936326986301e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1984224,
      "step": 7085
    },
    {
      "epoch": 78.77777777777777,
      "grad_norm": 7.8711474316151e-07,
      "learning_rate": 4.6224176902559946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1985632,
      "step": 7090
    },
    {
      "epoch": 78.83333333333333,
      "grad_norm": 7.965366535245266e-07,
      "learning_rate": 4.621898726222209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1987040,
      "step": 7095
    },
    {
      "epoch": 78.88888888888889,
      "grad_norm": 7.813162028469378e-07,
      "learning_rate": 4.6213794349649744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1988432,
      "step": 7100
    },
    {
      "epoch": 78.94444444444444,
      "grad_norm": 7.438674742843432e-07,
      "learning_rate": 4.6208598165643715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1989856,
      "step": 7105
    },
    {
      "epoch": 79.0,
      "grad_norm": 7.725735713393078e-07,
      "learning_rate": 4.620339871100533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1991248,
      "step": 7110
    },
    {
      "epoch": 79.05555555555556,
      "grad_norm": 3.119887423963519e-06,
      "learning_rate": 4.6198195986536394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1992656,
      "step": 7115
    },
    {
      "epoch": 79.11111111111111,
      "grad_norm": 8.088206868706038e-07,
      "learning_rate": 4.619298999303926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1994000,
      "step": 7120
    },
    {
      "epoch": 79.16666666666667,
      "grad_norm": 8.330766831932124e-07,
      "learning_rate": 4.618778073131673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1995376,
      "step": 7125
    },
    {
      "epoch": 79.22222222222223,
      "grad_norm": 8.155339514814841e-07,
      "learning_rate": 4.618256820217215e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1996768,
      "step": 7130
    },
    {
      "epoch": 79.27777777777777,
      "grad_norm": 8.04804187737318e-07,
      "learning_rate": 4.617735240640936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1998144,
      "step": 7135
    },
    {
      "epoch": 79.33333333333333,
      "grad_norm": 1.1947390703426208e-06,
      "learning_rate": 4.6172133344832705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 1999520,
      "step": 7140
    },
    {
      "epoch": 79.38888888888889,
      "grad_norm": 1.4525932101605576e-06,
      "learning_rate": 4.6166911018247004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2000880,
      "step": 7145
    },
    {
      "epoch": 79.44444444444444,
      "grad_norm": 7.256948606482183e-07,
      "learning_rate": 4.616168542745764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2002320,
      "step": 7150
    },
    {
      "epoch": 79.5,
      "grad_norm": 7.978651410667226e-07,
      "learning_rate": 4.6156456573270446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2003696,
      "step": 7155
    },
    {
      "epoch": 79.55555555555556,
      "grad_norm": 7.980716532074439e-07,
      "learning_rate": 4.615122445649177e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2005104,
      "step": 7160
    },
    {
      "epoch": 79.61111111111111,
      "grad_norm": 8.529268029633386e-07,
      "learning_rate": 4.6145989077928486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2006480,
      "step": 7165
    },
    {
      "epoch": 79.66666666666667,
      "grad_norm": 1.0658002338459482e-06,
      "learning_rate": 4.6140750438387953e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2007888,
      "step": 7170
    },
    {
      "epoch": 79.72222222222223,
      "grad_norm": 1.068891378963599e-06,
      "learning_rate": 4.613550853867803e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2009360,
      "step": 7175
    },
    {
      "epoch": 79.77777777777777,
      "grad_norm": 8.957183581514983e-07,
      "learning_rate": 4.613026337960708e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2010768,
      "step": 7180
    },
    {
      "epoch": 79.83333333333333,
      "grad_norm": 1.1680019724735757e-06,
      "learning_rate": 4.612501496198398e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2012112,
      "step": 7185
    },
    {
      "epoch": 79.88888888888889,
      "grad_norm": 4.318464561947621e-06,
      "learning_rate": 4.61197632866181e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2013520,
      "step": 7190
    },
    {
      "epoch": 79.94444444444444,
      "grad_norm": 5.629961492559232e-07,
      "learning_rate": 4.611450835431931e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2014944,
      "step": 7195
    },
    {
      "epoch": 80.0,
      "grad_norm": 8.493352652294561e-07,
      "learning_rate": 4.6109250165898e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2016368,
      "step": 7200
    },
    {
      "epoch": 80.0,
      "eval_loss": 0.28183484077453613,
      "eval_runtime": 1.2919,
      "eval_samples_per_second": 30.962,
      "eval_steps_per_second": 15.481,
      "num_input_tokens_seen": 2016368,
      "step": 7200
    },
    {
      "epoch": 80.05555555555556,
      "grad_norm": 1.4958760630179313e-06,
      "learning_rate": 4.610398872216503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2017760,
      "step": 7205
    },
    {
      "epoch": 80.11111111111111,
      "grad_norm": 8.032925506995525e-07,
      "learning_rate": 4.6098724023931796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2019152,
      "step": 7210
    },
    {
      "epoch": 80.16666666666667,
      "grad_norm": 1.733624799271638e-06,
      "learning_rate": 4.609345607201017e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2020592,
      "step": 7215
    },
    {
      "epoch": 80.22222222222223,
      "grad_norm": 5.985098141536582e-07,
      "learning_rate": 4.608818486721254e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2022000,
      "step": 7220
    },
    {
      "epoch": 80.27777777777777,
      "grad_norm": 8.168995577761962e-07,
      "learning_rate": 4.608291041035179e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2023376,
      "step": 7225
    },
    {
      "epoch": 80.33333333333333,
      "grad_norm": 8.690973913871858e-07,
      "learning_rate": 4.607763270224132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2024768,
      "step": 7230
    },
    {
      "epoch": 80.38888888888889,
      "grad_norm": 7.241580419758975e-07,
      "learning_rate": 4.6072351743695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2026144,
      "step": 7235
    },
    {
      "epoch": 80.44444444444444,
      "grad_norm": 6.914299319760175e-07,
      "learning_rate": 4.606706753552723e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2027536,
      "step": 7240
    },
    {
      "epoch": 80.5,
      "grad_norm": 6.191007173583785e-07,
      "learning_rate": 4.6061780078552906e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2028944,
      "step": 7245
    },
    {
      "epoch": 80.55555555555556,
      "grad_norm": 7.199864171525405e-07,
      "learning_rate": 4.605648937358742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2030336,
      "step": 7250
    },
    {
      "epoch": 80.61111111111111,
      "grad_norm": 6.150243621050322e-07,
      "learning_rate": 4.605119542144665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2031728,
      "step": 7255
    },
    {
      "epoch": 80.66666666666667,
      "grad_norm": 9.193282721753349e-07,
      "learning_rate": 4.604589822294701e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2033168,
      "step": 7260
    },
    {
      "epoch": 80.72222222222223,
      "grad_norm": 7.248423798955628e-07,
      "learning_rate": 4.604059777890537e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2034544,
      "step": 7265
    },
    {
      "epoch": 80.77777777777777,
      "grad_norm": 7.297008437490149e-07,
      "learning_rate": 4.6035294090139145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2035936,
      "step": 7270
    },
    {
      "epoch": 80.83333333333333,
      "grad_norm": 6.83553309954732e-07,
      "learning_rate": 4.6029987157466226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2037344,
      "step": 7275
    },
    {
      "epoch": 80.88888888888889,
      "grad_norm": 7.611111527694447e-07,
      "learning_rate": 4.602467698170502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2038720,
      "step": 7280
    },
    {
      "epoch": 80.94444444444444,
      "grad_norm": 6.349046657305735e-07,
      "learning_rate": 4.601936356367439e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2040128,
      "step": 7285
    },
    {
      "epoch": 81.0,
      "grad_norm": 1.1615885568971862e-06,
      "learning_rate": 4.601404690419377e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2041536,
      "step": 7290
    },
    {
      "epoch": 81.05555555555556,
      "grad_norm": 8.126111765704991e-07,
      "learning_rate": 4.600872700408303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2042912,
      "step": 7295
    },
    {
      "epoch": 81.11111111111111,
      "grad_norm": 6.105283887336554e-07,
      "learning_rate": 4.600340386416258e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2044336,
      "step": 7300
    },
    {
      "epoch": 81.16666666666667,
      "grad_norm": 7.43200246233755e-07,
      "learning_rate": 4.5998077485253296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2045728,
      "step": 7305
    },
    {
      "epoch": 81.22222222222223,
      "grad_norm": 6.212799803506641e-07,
      "learning_rate": 4.59927478681766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2047152,
      "step": 7310
    },
    {
      "epoch": 81.27777777777777,
      "grad_norm": 7.705656912548875e-07,
      "learning_rate": 4.5987415013754366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2048544,
      "step": 7315
    },
    {
      "epoch": 81.33333333333333,
      "grad_norm": 1.5454655795110739e-06,
      "learning_rate": 4.598207892280899e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2049968,
      "step": 7320
    },
    {
      "epoch": 81.38888888888889,
      "grad_norm": 7.27743440620543e-07,
      "learning_rate": 4.597673959616337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2051312,
      "step": 7325
    },
    {
      "epoch": 81.44444444444444,
      "grad_norm": 7.158855055422464e-07,
      "learning_rate": 4.597139703464089e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2052736,
      "step": 7330
    },
    {
      "epoch": 81.5,
      "grad_norm": 2.3056004465615842e-06,
      "learning_rate": 4.596605123906545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2054128,
      "step": 7335
    },
    {
      "epoch": 81.55555555555556,
      "grad_norm": 7.66185166867217e-07,
      "learning_rate": 4.596070221026143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2055520,
      "step": 7340
    },
    {
      "epoch": 81.61111111111111,
      "grad_norm": 6.961049621168058e-07,
      "learning_rate": 4.595534994905372e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2056928,
      "step": 7345
    },
    {
      "epoch": 81.66666666666667,
      "grad_norm": 6.722664807057299e-07,
      "learning_rate": 4.594999445626771e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2058368,
      "step": 7350
    },
    {
      "epoch": 81.72222222222223,
      "grad_norm": 7.479306987079326e-07,
      "learning_rate": 4.5944635732729276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2059760,
      "step": 7355
    },
    {
      "epoch": 81.77777777777777,
      "grad_norm": 1.3792246136290487e-06,
      "learning_rate": 4.5939273779264804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2061168,
      "step": 7360
    },
    {
      "epoch": 81.83333333333333,
      "grad_norm": 6.704499355691951e-07,
      "learning_rate": 4.593390859670118e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2062528,
      "step": 7365
    },
    {
      "epoch": 81.88888888888889,
      "grad_norm": 3.095299916822114e-06,
      "learning_rate": 4.5928540185865776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2063952,
      "step": 7370
    },
    {
      "epoch": 81.94444444444444,
      "grad_norm": 8.344364914592006e-07,
      "learning_rate": 4.592316854758648e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2065376,
      "step": 7375
    },
    {
      "epoch": 82.0,
      "grad_norm": 8.753564202379494e-07,
      "learning_rate": 4.5917793682691646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2066784,
      "step": 7380
    },
    {
      "epoch": 82.05555555555556,
      "grad_norm": 5.579771595876082e-07,
      "learning_rate": 4.5912415592010164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2068224,
      "step": 7385
    },
    {
      "epoch": 82.11111111111111,
      "grad_norm": 8.158048103723559e-07,
      "learning_rate": 4.5907034276371386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2069600,
      "step": 7390
    },
    {
      "epoch": 82.16666666666667,
      "grad_norm": 6.392140221578302e-07,
      "learning_rate": 4.5901649736605196e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2070992,
      "step": 7395
    },
    {
      "epoch": 82.22222222222223,
      "grad_norm": 7.531381243097712e-07,
      "learning_rate": 4.589626197354195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2072400,
      "step": 7400
    },
    {
      "epoch": 82.22222222222223,
      "eval_loss": 0.25661951303482056,
      "eval_runtime": 1.324,
      "eval_samples_per_second": 30.212,
      "eval_steps_per_second": 15.106,
      "num_input_tokens_seen": 2072400,
      "step": 7400
    },
    {
      "epoch": 82.27777777777777,
      "grad_norm": 1.0139131063624518e-06,
      "learning_rate": 4.5890870988012504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2073824,
      "step": 7405
    },
    {
      "epoch": 82.33333333333333,
      "grad_norm": 2.5952952000807272e-06,
      "learning_rate": 4.5885476780848226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2075200,
      "step": 7410
    },
    {
      "epoch": 82.38888888888889,
      "grad_norm": 8.84971484538255e-07,
      "learning_rate": 4.5880079352880964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2076592,
      "step": 7415
    },
    {
      "epoch": 82.44444444444444,
      "grad_norm": 1.1430352060415316e-06,
      "learning_rate": 4.5874678704943065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2078000,
      "step": 7420
    },
    {
      "epoch": 82.5,
      "grad_norm": 8.630738648207625e-07,
      "learning_rate": 4.5869274837867394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2079408,
      "step": 7425
    },
    {
      "epoch": 82.55555555555556,
      "grad_norm": 1.592999865351885e-06,
      "learning_rate": 4.5863867752487275e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2080800,
      "step": 7430
    },
    {
      "epoch": 82.61111111111111,
      "grad_norm": 8.791878940428433e-07,
      "learning_rate": 4.5858457449636554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2082176,
      "step": 7435
    },
    {
      "epoch": 82.66666666666667,
      "grad_norm": 7.718799110989494e-07,
      "learning_rate": 4.5853043930149574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2083600,
      "step": 7440
    },
    {
      "epoch": 82.72222222222223,
      "grad_norm": 8.322181201947387e-07,
      "learning_rate": 4.584762719486117e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2084976,
      "step": 7445
    },
    {
      "epoch": 82.77777777777777,
      "grad_norm": 6.03474177296448e-07,
      "learning_rate": 4.584220724460665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2086384,
      "step": 7450
    },
    {
      "epoch": 82.83333333333333,
      "grad_norm": 7.951866791700013e-07,
      "learning_rate": 4.5836784080221865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2087776,
      "step": 7455
    },
    {
      "epoch": 82.88888888888889,
      "grad_norm": 6.695313459204044e-07,
      "learning_rate": 4.583135770254312e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2089152,
      "step": 7460
    },
    {
      "epoch": 82.94444444444444,
      "grad_norm": 6.703781991745927e-07,
      "learning_rate": 4.5825928112407236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2090544,
      "step": 7465
    },
    {
      "epoch": 83.0,
      "grad_norm": 8.850835797602485e-07,
      "learning_rate": 4.582049531065152e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2092000,
      "step": 7470
    },
    {
      "epoch": 83.05555555555556,
      "grad_norm": 1.2889063327747863e-06,
      "learning_rate": 4.5815059298113783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2093392,
      "step": 7475
    },
    {
      "epoch": 83.11111111111111,
      "grad_norm": 1.7019481219904264e-06,
      "learning_rate": 4.580962007563232e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2094816,
      "step": 7480
    },
    {
      "epoch": 83.16666666666667,
      "grad_norm": 5.656596613334841e-07,
      "learning_rate": 4.5804177644045935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2096208,
      "step": 7485
    },
    {
      "epoch": 83.22222222222223,
      "grad_norm": 7.957077627906983e-07,
      "learning_rate": 4.579873200419391e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2097616,
      "step": 7490
    },
    {
      "epoch": 83.27777777777777,
      "grad_norm": 7.071827781146567e-07,
      "learning_rate": 4.5793283156916046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2098992,
      "step": 7495
    },
    {
      "epoch": 83.33333333333333,
      "grad_norm": 6.475431746366667e-07,
      "learning_rate": 4.578783110305261e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2100400,
      "step": 7500
    },
    {
      "epoch": 83.38888888888889,
      "grad_norm": 8.463193239549582e-07,
      "learning_rate": 4.578237584344438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2101808,
      "step": 7505
    },
    {
      "epoch": 83.44444444444444,
      "grad_norm": 8.786340117694635e-07,
      "learning_rate": 4.577691737893263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2103216,
      "step": 7510
    },
    {
      "epoch": 83.5,
      "grad_norm": 7.237622980937886e-07,
      "learning_rate": 4.577145571035912e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2104624,
      "step": 7515
    },
    {
      "epoch": 83.55555555555556,
      "grad_norm": 6.434216288653261e-07,
      "learning_rate": 4.576599083856611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2106048,
      "step": 7520
    },
    {
      "epoch": 83.61111111111111,
      "grad_norm": 9.807262131289463e-07,
      "learning_rate": 4.576052276439635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2107472,
      "step": 7525
    },
    {
      "epoch": 83.66666666666667,
      "grad_norm": 6.518693567159062e-07,
      "learning_rate": 4.575505148869308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2108832,
      "step": 7530
    },
    {
      "epoch": 83.72222222222223,
      "grad_norm": 5.797770086246601e-07,
      "learning_rate": 4.574957701230006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2110208,
      "step": 7535
    },
    {
      "epoch": 83.77777777777777,
      "grad_norm": 6.649752890552918e-07,
      "learning_rate": 4.57440993360615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2111584,
      "step": 7540
    },
    {
      "epoch": 83.83333333333333,
      "grad_norm": 7.270317610164057e-07,
      "learning_rate": 4.5738618460822134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2113008,
      "step": 7545
    },
    {
      "epoch": 83.88888888888889,
      "grad_norm": 1.5896608829280012e-06,
      "learning_rate": 4.573313438742719e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2114416,
      "step": 7550
    },
    {
      "epoch": 83.94444444444444,
      "grad_norm": 6.504247380689776e-07,
      "learning_rate": 4.5727647116722374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2115776,
      "step": 7555
    },
    {
      "epoch": 84.0,
      "grad_norm": 6.80924529206095e-07,
      "learning_rate": 4.5722156649553884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2117200,
      "step": 7560
    },
    {
      "epoch": 84.05555555555556,
      "grad_norm": 7.046454015835479e-07,
      "learning_rate": 4.571666298676843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2118592,
      "step": 7565
    },
    {
      "epoch": 84.11111111111111,
      "grad_norm": 6.950235729163978e-07,
      "learning_rate": 4.571116612921321e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2120000,
      "step": 7570
    },
    {
      "epoch": 84.16666666666667,
      "grad_norm": 1.4060278772376478e-06,
      "learning_rate": 4.57056660777359e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2121408,
      "step": 7575
    },
    {
      "epoch": 84.22222222222223,
      "grad_norm": 8.188093261196627e-07,
      "learning_rate": 4.5700162833184666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2122784,
      "step": 7580
    },
    {
      "epoch": 84.27777777777777,
      "grad_norm": 6.32677938483539e-07,
      "learning_rate": 4.5694656396408195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2124160,
      "step": 7585
    },
    {
      "epoch": 84.33333333333333,
      "grad_norm": 7.620571409461263e-07,
      "learning_rate": 4.5689146768255646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2125632,
      "step": 7590
    },
    {
      "epoch": 84.38888888888889,
      "grad_norm": 7.905818506515061e-07,
      "learning_rate": 4.568363394957667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2127024,
      "step": 7595
    },
    {
      "epoch": 84.44444444444444,
      "grad_norm": 3.0815422178420704e-06,
      "learning_rate": 4.567811794122141e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2128384,
      "step": 7600
    },
    {
      "epoch": 84.44444444444444,
      "eval_loss": 0.28496068716049194,
      "eval_runtime": 1.338,
      "eval_samples_per_second": 29.894,
      "eval_steps_per_second": 14.947,
      "num_input_tokens_seen": 2128384,
      "step": 7600
    },
    {
      "epoch": 84.5,
      "grad_norm": 8.788261425252131e-07,
      "learning_rate": 4.56725987440405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2129776,
      "step": 7605
    },
    {
      "epoch": 84.55555555555556,
      "grad_norm": 5.737135779781966e-07,
      "learning_rate": 4.566707635888508e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2131200,
      "step": 7610
    },
    {
      "epoch": 84.61111111111111,
      "grad_norm": 7.6547297567231e-07,
      "learning_rate": 4.566155078660677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2132608,
      "step": 7615
    },
    {
      "epoch": 84.66666666666667,
      "grad_norm": 6.525735329887539e-07,
      "learning_rate": 4.565602202805768e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2133968,
      "step": 7620
    },
    {
      "epoch": 84.72222222222223,
      "grad_norm": 7.420999850182852e-07,
      "learning_rate": 4.56504900840904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2135360,
      "step": 7625
    },
    {
      "epoch": 84.77777777777777,
      "grad_norm": 7.780713531246874e-07,
      "learning_rate": 4.564495495555805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2136800,
      "step": 7630
    },
    {
      "epoch": 84.83333333333333,
      "grad_norm": 7.138653472793521e-07,
      "learning_rate": 4.5639416643314204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2138192,
      "step": 7635
    },
    {
      "epoch": 84.88888888888889,
      "grad_norm": 7.128873562578519e-07,
      "learning_rate": 4.5633875148212946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2139632,
      "step": 7640
    },
    {
      "epoch": 84.94444444444444,
      "grad_norm": 7.600670528518094e-07,
      "learning_rate": 4.562833047110883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2141008,
      "step": 7645
    },
    {
      "epoch": 85.0,
      "grad_norm": 1.2287946447031572e-06,
      "learning_rate": 4.5622782612856923e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2142400,
      "step": 7650
    },
    {
      "epoch": 85.05555555555556,
      "grad_norm": 7.81141750394454e-07,
      "learning_rate": 4.561723157431278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2143808,
      "step": 7655
    },
    {
      "epoch": 85.11111111111111,
      "grad_norm": 6.315485165941936e-07,
      "learning_rate": 4.5611677356332435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2145200,
      "step": 7660
    },
    {
      "epoch": 85.16666666666667,
      "grad_norm": 5.829149927194521e-07,
      "learning_rate": 4.560611995977242e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2146592,
      "step": 7665
    },
    {
      "epoch": 85.22222222222223,
      "grad_norm": 7.746922960905067e-07,
      "learning_rate": 4.560055938548975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2148032,
      "step": 7670
    },
    {
      "epoch": 85.27777777777777,
      "grad_norm": 5.211109055380803e-06,
      "learning_rate": 4.5594995634341944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2149424,
      "step": 7675
    },
    {
      "epoch": 85.33333333333333,
      "grad_norm": 1.3590502021543216e-06,
      "learning_rate": 4.5589428707187e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2150832,
      "step": 7680
    },
    {
      "epoch": 85.38888888888889,
      "grad_norm": 5.600076065093162e-07,
      "learning_rate": 4.55838586048834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2152256,
      "step": 7685
    },
    {
      "epoch": 85.44444444444444,
      "grad_norm": 9.871764632407576e-07,
      "learning_rate": 4.557828532829013e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2153648,
      "step": 7690
    },
    {
      "epoch": 85.5,
      "grad_norm": 5.841210395374219e-07,
      "learning_rate": 4.557270887826667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2155056,
      "step": 7695
    },
    {
      "epoch": 85.55555555555556,
      "grad_norm": 6.012335802552116e-07,
      "learning_rate": 4.556712925567296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2156432,
      "step": 7700
    },
    {
      "epoch": 85.61111111111111,
      "grad_norm": 6.862717896183312e-07,
      "learning_rate": 4.5561546461369454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2157808,
      "step": 7705
    },
    {
      "epoch": 85.66666666666667,
      "grad_norm": 6.308248430286767e-07,
      "learning_rate": 4.55559604962171e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2159232,
      "step": 7710
    },
    {
      "epoch": 85.72222222222223,
      "grad_norm": 6.427671905839816e-07,
      "learning_rate": 4.55503713610773e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2160640,
      "step": 7715
    },
    {
      "epoch": 85.77777777777777,
      "grad_norm": 3.3377398267475655e-06,
      "learning_rate": 4.5544779056812e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2162064,
      "step": 7720
    },
    {
      "epoch": 85.83333333333333,
      "grad_norm": 6.141180506347155e-07,
      "learning_rate": 4.553918358428358e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2163456,
      "step": 7725
    },
    {
      "epoch": 85.88888888888889,
      "grad_norm": 9.224971790899872e-07,
      "learning_rate": 4.553358494435494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2164848,
      "step": 7730
    },
    {
      "epoch": 85.94444444444444,
      "grad_norm": 1.087551936507225e-06,
      "learning_rate": 4.5527983137889464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2166272,
      "step": 7735
    },
    {
      "epoch": 86.0,
      "grad_norm": 1.7777861103240866e-06,
      "learning_rate": 4.5522378165751015e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2167664,
      "step": 7740
    },
    {
      "epoch": 86.05555555555556,
      "grad_norm": 9.510586664873699e-07,
      "learning_rate": 4.5516770028803954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2169072,
      "step": 7745
    },
    {
      "epoch": 86.11111111111111,
      "grad_norm": 7.368751084868563e-07,
      "learning_rate": 4.5511158727913116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2170480,
      "step": 7750
    },
    {
      "epoch": 86.16666666666667,
      "grad_norm": 6.231066436157562e-07,
      "learning_rate": 4.5505544263943856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2171888,
      "step": 7755
    },
    {
      "epoch": 86.22222222222223,
      "grad_norm": 2.1623343400278827e-06,
      "learning_rate": 4.549992663776197e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2173248,
      "step": 7760
    },
    {
      "epoch": 86.27777777777777,
      "grad_norm": 5.790897148472141e-07,
      "learning_rate": 4.5494305850233786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2174656,
      "step": 7765
    },
    {
      "epoch": 86.33333333333333,
      "grad_norm": 6.187169105942303e-07,
      "learning_rate": 4.5488681902226094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2176064,
      "step": 7770
    },
    {
      "epoch": 86.38888888888889,
      "grad_norm": 5.00326848396071e-07,
      "learning_rate": 4.5483054794606174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2177456,
      "step": 7775
    },
    {
      "epoch": 86.44444444444444,
      "grad_norm": 6.018544809194282e-07,
      "learning_rate": 4.547742452824179e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2178864,
      "step": 7780
    },
    {
      "epoch": 86.5,
      "grad_norm": 6.799288598813291e-07,
      "learning_rate": 4.5471791104001215e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2180240,
      "step": 7785
    },
    {
      "epoch": 86.55555555555556,
      "grad_norm": 3.2747286695666844e-06,
      "learning_rate": 4.546615452275319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2181584,
      "step": 7790
    },
    {
      "epoch": 86.61111111111111,
      "grad_norm": 8.945211220634519e-07,
      "learning_rate": 4.5460514785366944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2182992,
      "step": 7795
    },
    {
      "epoch": 86.66666666666667,
      "grad_norm": 7.708330826972087e-07,
      "learning_rate": 4.545487189271219e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2184416,
      "step": 7800
    },
    {
      "epoch": 86.66666666666667,
      "eval_loss": 0.25023534893989563,
      "eval_runtime": 1.3186,
      "eval_samples_per_second": 30.335,
      "eval_steps_per_second": 15.167,
      "num_input_tokens_seen": 2184416,
      "step": 7800
    },
    {
      "epoch": 86.72222222222223,
      "grad_norm": 7.387046139228914e-07,
      "learning_rate": 4.544922584565914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2185808,
      "step": 7805
    },
    {
      "epoch": 86.77777777777777,
      "grad_norm": 6.402016197171179e-07,
      "learning_rate": 4.544357664507848e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2187184,
      "step": 7810
    },
    {
      "epoch": 86.83333333333333,
      "grad_norm": 6.191691568346869e-07,
      "learning_rate": 4.54379242918414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2188640,
      "step": 7815
    },
    {
      "epoch": 86.88888888888889,
      "grad_norm": 4.7382152956743084e-07,
      "learning_rate": 4.543226878681955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2190048,
      "step": 7820
    },
    {
      "epoch": 86.94444444444444,
      "grad_norm": 1.1398988135624677e-06,
      "learning_rate": 4.5426610130885087e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2191440,
      "step": 7825
    },
    {
      "epoch": 87.0,
      "grad_norm": 1.123337597164209e-06,
      "learning_rate": 4.542094832491064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2192864,
      "step": 7830
    },
    {
      "epoch": 87.05555555555556,
      "grad_norm": 3.4136476187995868e-06,
      "learning_rate": 4.541528336976934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2194288,
      "step": 7835
    },
    {
      "epoch": 87.11111111111111,
      "grad_norm": 6.399788503586024e-07,
      "learning_rate": 4.540961526633479e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2195728,
      "step": 7840
    },
    {
      "epoch": 87.16666666666667,
      "grad_norm": 7.833374411347904e-07,
      "learning_rate": 4.540394401548108e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2197120,
      "step": 7845
    },
    {
      "epoch": 87.22222222222223,
      "grad_norm": 5.079359652881976e-07,
      "learning_rate": 4.539826961808279e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2198512,
      "step": 7850
    },
    {
      "epoch": 87.27777777777777,
      "grad_norm": 1.1337682508383295e-06,
      "learning_rate": 4.5392592075014994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2199920,
      "step": 7855
    },
    {
      "epoch": 87.33333333333333,
      "grad_norm": 5.199044608161785e-07,
      "learning_rate": 4.538691138715322e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2201296,
      "step": 7860
    },
    {
      "epoch": 87.38888888888889,
      "grad_norm": 7.371322681137826e-07,
      "learning_rate": 4.5381227555373516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2202688,
      "step": 7865
    },
    {
      "epoch": 87.44444444444444,
      "grad_norm": 1.7215353409483214e-06,
      "learning_rate": 4.537554058055239e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2204112,
      "step": 7870
    },
    {
      "epoch": 87.5,
      "grad_norm": 5.590571845459635e-07,
      "learning_rate": 4.5369850463566865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2205472,
      "step": 7875
    },
    {
      "epoch": 87.55555555555556,
      "grad_norm": 1.047880573423754e-06,
      "learning_rate": 4.5364157205294404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2206864,
      "step": 7880
    },
    {
      "epoch": 87.61111111111111,
      "grad_norm": 8.534525477443822e-07,
      "learning_rate": 4.5358460806612996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2208336,
      "step": 7885
    },
    {
      "epoch": 87.66666666666667,
      "grad_norm": 7.985846650626627e-07,
      "learning_rate": 4.535276126840109e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2209744,
      "step": 7890
    },
    {
      "epoch": 87.72222222222223,
      "grad_norm": 6.681903528260591e-07,
      "learning_rate": 4.5347058591537626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2211120,
      "step": 7895
    },
    {
      "epoch": 87.77777777777777,
      "grad_norm": 5.756370455856086e-07,
      "learning_rate": 4.534135277690203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2212496,
      "step": 7900
    },
    {
      "epoch": 87.83333333333333,
      "grad_norm": 7.266486932167027e-07,
      "learning_rate": 4.533564382537421e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2213856,
      "step": 7905
    },
    {
      "epoch": 87.88888888888889,
      "grad_norm": 8.440014767074899e-07,
      "learning_rate": 4.532993173783456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2215296,
      "step": 7910
    },
    {
      "epoch": 87.94444444444444,
      "grad_norm": 5.844553925271612e-07,
      "learning_rate": 4.5324216515163954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2216704,
      "step": 7915
    },
    {
      "epoch": 88.0,
      "grad_norm": 4.796904704562621e-07,
      "learning_rate": 4.531849815824375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2218128,
      "step": 7920
    },
    {
      "epoch": 88.05555555555556,
      "grad_norm": 7.332409381888283e-07,
      "learning_rate": 4.5312776667955795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2219472,
      "step": 7925
    },
    {
      "epoch": 88.11111111111111,
      "grad_norm": 6.321553200905328e-07,
      "learning_rate": 4.5307052045182405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2220832,
      "step": 7930
    },
    {
      "epoch": 88.16666666666667,
      "grad_norm": 1.7442945363654871e-06,
      "learning_rate": 4.53013242908064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2222224,
      "step": 7935
    },
    {
      "epoch": 88.22222222222223,
      "grad_norm": 8.249169241025811e-07,
      "learning_rate": 4.529559340571107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2223584,
      "step": 7940
    },
    {
      "epoch": 88.27777777777777,
      "grad_norm": 6.487443897640333e-07,
      "learning_rate": 4.528985939078018e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2224944,
      "step": 7945
    },
    {
      "epoch": 88.33333333333333,
      "grad_norm": 6.065030220270273e-07,
      "learning_rate": 4.5284122246898e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2226336,
      "step": 7950
    },
    {
      "epoch": 88.38888888888889,
      "grad_norm": 1.0010190862885793e-06,
      "learning_rate": 4.527838197494926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2227728,
      "step": 7955
    },
    {
      "epoch": 88.44444444444444,
      "grad_norm": 8.976930985227227e-07,
      "learning_rate": 4.527263857581918e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2229168,
      "step": 7960
    },
    {
      "epoch": 88.5,
      "grad_norm": 5.318099738360615e-07,
      "learning_rate": 4.526689205039347e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2230592,
      "step": 7965
    },
    {
      "epoch": 88.55555555555556,
      "grad_norm": 9.201810371450847e-07,
      "learning_rate": 4.5261142399558324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2231984,
      "step": 7970
    },
    {
      "epoch": 88.61111111111111,
      "grad_norm": 6.261254270611971e-07,
      "learning_rate": 4.525538962420041e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2233424,
      "step": 7975
    },
    {
      "epoch": 88.66666666666667,
      "grad_norm": 1.1833952839879203e-06,
      "learning_rate": 4.524963372520685e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2234848,
      "step": 7980
    },
    {
      "epoch": 88.72222222222223,
      "grad_norm": 9.818439821174252e-07,
      "learning_rate": 4.524387470346531e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2236304,
      "step": 7985
    },
    {
      "epoch": 88.77777777777777,
      "grad_norm": 1.7834865957411239e-06,
      "learning_rate": 4.5238112559863885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2237680,
      "step": 7990
    },
    {
      "epoch": 88.83333333333333,
      "grad_norm": 6.01938268118829e-07,
      "learning_rate": 4.5232347295291175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2239104,
      "step": 7995
    },
    {
      "epoch": 88.88888888888889,
      "grad_norm": 6.200864959282626e-07,
      "learning_rate": 4.522657891063626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2240512,
      "step": 8000
    },
    {
      "epoch": 88.88888888888889,
      "eval_loss": 0.2656751573085785,
      "eval_runtime": 1.3139,
      "eval_samples_per_second": 30.443,
      "eval_steps_per_second": 15.222,
      "num_input_tokens_seen": 2240512,
      "step": 8000
    },
    {
      "epoch": 88.94444444444444,
      "grad_norm": 5.369681161937478e-07,
      "learning_rate": 4.52208074067887e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2241904,
      "step": 8005
    },
    {
      "epoch": 89.0,
      "grad_norm": 5.841750976287585e-07,
      "learning_rate": 4.5215032784638516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2243328,
      "step": 8010
    },
    {
      "epoch": 89.05555555555556,
      "grad_norm": 9.347168656859139e-07,
      "learning_rate": 4.5209255045076245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2244752,
      "step": 8015
    },
    {
      "epoch": 89.11111111111111,
      "grad_norm": 5.926717676629778e-07,
      "learning_rate": 4.5203474188992875e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2246160,
      "step": 8020
    },
    {
      "epoch": 89.16666666666667,
      "grad_norm": 6.088426403039193e-07,
      "learning_rate": 4.51976902172799e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2247568,
      "step": 8025
    },
    {
      "epoch": 89.22222222222223,
      "grad_norm": 5.542657390833483e-07,
      "learning_rate": 4.519190313082927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2248912,
      "step": 8030
    },
    {
      "epoch": 89.27777777777777,
      "grad_norm": 6.905735290274606e-07,
      "learning_rate": 4.518611293053343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2250304,
      "step": 8035
    },
    {
      "epoch": 89.33333333333333,
      "grad_norm": 9.064889354704064e-07,
      "learning_rate": 4.51803196172853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2251680,
      "step": 8040
    },
    {
      "epoch": 89.38888888888889,
      "grad_norm": 1.1660500831567333e-06,
      "learning_rate": 4.517452319197828e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2253056,
      "step": 8045
    },
    {
      "epoch": 89.44444444444444,
      "grad_norm": 9.94656602415489e-07,
      "learning_rate": 4.5168723655506265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2254448,
      "step": 8050
    },
    {
      "epoch": 89.5,
      "grad_norm": 4.7504605049653037e-07,
      "learning_rate": 4.51629210087636e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2255824,
      "step": 8055
    },
    {
      "epoch": 89.55555555555556,
      "grad_norm": 5.55484461983724e-07,
      "learning_rate": 4.515711525264513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2257248,
      "step": 8060
    },
    {
      "epoch": 89.61111111111111,
      "grad_norm": 5.36600111900043e-07,
      "learning_rate": 4.5151306388046175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2258624,
      "step": 8065
    },
    {
      "epoch": 89.66666666666667,
      "grad_norm": 5.009849814996414e-07,
      "learning_rate": 4.514549441586255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2260096,
      "step": 8070
    },
    {
      "epoch": 89.72222222222223,
      "grad_norm": 5.798630695608153e-07,
      "learning_rate": 4.513967933699051e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2261520,
      "step": 8075
    },
    {
      "epoch": 89.77777777777777,
      "grad_norm": 6.035652972968819e-07,
      "learning_rate": 4.513386115232684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2262928,
      "step": 8080
    },
    {
      "epoch": 89.83333333333333,
      "grad_norm": 8.952609960033442e-07,
      "learning_rate": 4.5128039862768745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2264304,
      "step": 8085
    },
    {
      "epoch": 89.88888888888889,
      "grad_norm": 5.930813813392888e-07,
      "learning_rate": 4.512221546921397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2265648,
      "step": 8090
    },
    {
      "epoch": 89.94444444444444,
      "grad_norm": 2.918595328083029e-06,
      "learning_rate": 4.5116387972560694e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2267056,
      "step": 8095
    },
    {
      "epoch": 90.0,
      "grad_norm": 5.749611773353536e-07,
      "learning_rate": 4.511055737370759e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2268464,
      "step": 8100
    },
    {
      "epoch": 90.05555555555556,
      "grad_norm": 1.1436515023888205e-06,
      "learning_rate": 4.510472367355383e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2269872,
      "step": 8105
    },
    {
      "epoch": 90.11111111111111,
      "grad_norm": 9.008958272715972e-07,
      "learning_rate": 4.509888687299901e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2271280,
      "step": 8110
    },
    {
      "epoch": 90.16666666666667,
      "grad_norm": 5.173270096747729e-07,
      "learning_rate": 4.5093046972943266e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2272720,
      "step": 8115
    },
    {
      "epoch": 90.22222222222223,
      "grad_norm": 8.445624644082272e-07,
      "learning_rate": 4.508720397428717e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2274112,
      "step": 8120
    },
    {
      "epoch": 90.27777777777777,
      "grad_norm": 4.797250312549295e-07,
      "learning_rate": 4.508135787793178e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2275520,
      "step": 8125
    },
    {
      "epoch": 90.33333333333333,
      "grad_norm": 5.139778522789129e-07,
      "learning_rate": 4.5075508684778664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2276896,
      "step": 8130
    },
    {
      "epoch": 90.38888888888889,
      "grad_norm": 4.698420354998234e-07,
      "learning_rate": 4.506965639572982e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2278304,
      "step": 8135
    },
    {
      "epoch": 90.44444444444444,
      "grad_norm": 5.063743060418346e-07,
      "learning_rate": 4.506380101168774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2279696,
      "step": 8140
    },
    {
      "epoch": 90.5,
      "grad_norm": 8.562361131225771e-07,
      "learning_rate": 4.505794253355542e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2281072,
      "step": 8145
    },
    {
      "epoch": 90.55555555555556,
      "grad_norm": 8.386151648664963e-07,
      "learning_rate": 4.5052080962236286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2282448,
      "step": 8150
    },
    {
      "epoch": 90.61111111111111,
      "grad_norm": 6.620639396714978e-07,
      "learning_rate": 4.504621629863428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2283888,
      "step": 8155
    },
    {
      "epoch": 90.66666666666667,
      "grad_norm": 7.057697075651959e-07,
      "learning_rate": 4.504034854365381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2285312,
      "step": 8160
    },
    {
      "epoch": 90.72222222222223,
      "grad_norm": 4.455176565443253e-07,
      "learning_rate": 4.503447769819974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2286704,
      "step": 8165
    },
    {
      "epoch": 90.77777777777777,
      "grad_norm": 5.020309572500992e-07,
      "learning_rate": 4.502860376317745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2288080,
      "step": 8170
    },
    {
      "epoch": 90.83333333333333,
      "grad_norm": 9.329165777671733e-07,
      "learning_rate": 4.502272673949276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2289488,
      "step": 8175
    },
    {
      "epoch": 90.88888888888889,
      "grad_norm": 5.874967996533087e-07,
      "learning_rate": 4.501684662805199e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2290896,
      "step": 8180
    },
    {
      "epoch": 90.94444444444444,
      "grad_norm": 5.81335029892216e-07,
      "learning_rate": 4.5010963429761924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2292240,
      "step": 8185
    },
    {
      "epoch": 91.0,
      "grad_norm": 5.11827295213152e-07,
      "learning_rate": 4.500507714552982e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2293664,
      "step": 8190
    },
    {
      "epoch": 91.05555555555556,
      "grad_norm": 4.346087223439099e-07,
      "learning_rate": 4.499918777626342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2295120,
      "step": 8195
    },
    {
      "epoch": 91.11111111111111,
      "grad_norm": 9.898197959046229e-07,
      "learning_rate": 4.499329532287093e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2296496,
      "step": 8200
    },
    {
      "epoch": 91.11111111111111,
      "eval_loss": 0.27814704179763794,
      "eval_runtime": 1.3294,
      "eval_samples_per_second": 30.089,
      "eval_steps_per_second": 15.044,
      "num_input_tokens_seen": 2296496,
      "step": 8200
    },
    {
      "epoch": 91.16666666666667,
      "grad_norm": 5.284065309751895e-07,
      "learning_rate": 4.4987399786261064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2297856,
      "step": 8205
    },
    {
      "epoch": 91.22222222222223,
      "grad_norm": 1.5194930256257067e-06,
      "learning_rate": 4.498150116734297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2299216,
      "step": 8210
    },
    {
      "epoch": 91.27777777777777,
      "grad_norm": 5.465885806188453e-07,
      "learning_rate": 4.4975599467026294e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2300592,
      "step": 8215
    },
    {
      "epoch": 91.33333333333333,
      "grad_norm": 5.16218619850406e-07,
      "learning_rate": 4.496969468622114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2301952,
      "step": 8220
    },
    {
      "epoch": 91.38888888888889,
      "grad_norm": 9.235603783963597e-07,
      "learning_rate": 4.496378682583813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2303328,
      "step": 8225
    },
    {
      "epoch": 91.44444444444444,
      "grad_norm": 1.8056109638564521e-06,
      "learning_rate": 4.495787588678829e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2304768,
      "step": 8230
    },
    {
      "epoch": 91.5,
      "grad_norm": 6.523941351588292e-07,
      "learning_rate": 4.4951961869983196e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2306192,
      "step": 8235
    },
    {
      "epoch": 91.55555555555556,
      "grad_norm": 5.390811566030607e-07,
      "learning_rate": 4.494604477633485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2307568,
      "step": 8240
    },
    {
      "epoch": 91.61111111111111,
      "grad_norm": 6.600650408472575e-07,
      "learning_rate": 4.4940124606755734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2308944,
      "step": 8245
    },
    {
      "epoch": 91.66666666666667,
      "grad_norm": 4.689181594130787e-07,
      "learning_rate": 4.493420136215882e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2310368,
      "step": 8250
    },
    {
      "epoch": 91.72222222222223,
      "grad_norm": 7.031098903098609e-07,
      "learning_rate": 4.492827504345756e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2311808,
      "step": 8255
    },
    {
      "epoch": 91.77777777777777,
      "grad_norm": 9.876511057882453e-07,
      "learning_rate": 4.492234565156584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2313216,
      "step": 8260
    },
    {
      "epoch": 91.83333333333333,
      "grad_norm": 4.637789174921636e-07,
      "learning_rate": 4.491641318739807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2314576,
      "step": 8265
    },
    {
      "epoch": 91.88888888888889,
      "grad_norm": 5.448627575788123e-07,
      "learning_rate": 4.4910477651869096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2316016,
      "step": 8270
    },
    {
      "epoch": 91.94444444444444,
      "grad_norm": 6.571682433786918e-07,
      "learning_rate": 4.4904539045894254e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2317472,
      "step": 8275
    },
    {
      "epoch": 92.0,
      "grad_norm": 6.122861577750882e-07,
      "learning_rate": 4.4898597370389364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2318864,
      "step": 8280
    },
    {
      "epoch": 92.05555555555556,
      "grad_norm": 5.891149044146005e-07,
      "learning_rate": 4.489265262627069e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2320240,
      "step": 8285
    },
    {
      "epoch": 92.11111111111111,
      "grad_norm": 5.023865696784924e-07,
      "learning_rate": 4.488670481445499e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2321664,
      "step": 8290
    },
    {
      "epoch": 92.16666666666667,
      "grad_norm": 3.8063231500018446e-07,
      "learning_rate": 4.488075393585951e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2323040,
      "step": 8295
    },
    {
      "epoch": 92.22222222222223,
      "grad_norm": 4.846392585022841e-07,
      "learning_rate": 4.487479999140193e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2324448,
      "step": 8300
    },
    {
      "epoch": 92.27777777777777,
      "grad_norm": 9.176544040201406e-07,
      "learning_rate": 4.4868842982000425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2325840,
      "step": 8305
    },
    {
      "epoch": 92.33333333333333,
      "grad_norm": 5.040355404162256e-07,
      "learning_rate": 4.486288290857365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2327216,
      "step": 8310
    },
    {
      "epoch": 92.38888888888889,
      "grad_norm": 1.1501598464747076e-06,
      "learning_rate": 4.4856919772040715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2328640,
      "step": 8315
    },
    {
      "epoch": 92.44444444444444,
      "grad_norm": 5.029584144722321e-07,
      "learning_rate": 4.485095357332122e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2330064,
      "step": 8320
    },
    {
      "epoch": 92.5,
      "grad_norm": 2.4665198452566983e-06,
      "learning_rate": 4.484498431333521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2331472,
      "step": 8325
    },
    {
      "epoch": 92.55555555555556,
      "grad_norm": 8.645067168799869e-07,
      "learning_rate": 4.4839011993003245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2332864,
      "step": 8330
    },
    {
      "epoch": 92.61111111111111,
      "grad_norm": 1.043781594489701e-06,
      "learning_rate": 4.4833036613246305e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2334224,
      "step": 8335
    },
    {
      "epoch": 92.66666666666667,
      "grad_norm": 1.0847377325262642e-06,
      "learning_rate": 4.482705817498589e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2335600,
      "step": 8340
    },
    {
      "epoch": 92.72222222222223,
      "grad_norm": 4.369956343452941e-07,
      "learning_rate": 4.4821076679143934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2336992,
      "step": 8345
    },
    {
      "epoch": 92.77777777777777,
      "grad_norm": 5.424559503808268e-07,
      "learning_rate": 4.481509212664288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2338432,
      "step": 8350
    },
    {
      "epoch": 92.83333333333333,
      "grad_norm": 4.2556669654914003e-07,
      "learning_rate": 4.480910451840559e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2339904,
      "step": 8355
    },
    {
      "epoch": 92.88888888888889,
      "grad_norm": 1.7776068261809996e-06,
      "learning_rate": 4.480311385535546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2341312,
      "step": 8360
    },
    {
      "epoch": 92.94444444444444,
      "grad_norm": 4.824310622097983e-07,
      "learning_rate": 4.47971201384163e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2342704,
      "step": 8365
    },
    {
      "epoch": 93.0,
      "grad_norm": 5.460764214149094e-07,
      "learning_rate": 4.4791123368512446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2344096,
      "step": 8370
    },
    {
      "epoch": 93.05555555555556,
      "grad_norm": 4.637176118649222e-07,
      "learning_rate": 4.478512354656864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2345520,
      "step": 8375
    },
    {
      "epoch": 93.11111111111111,
      "grad_norm": 4.257585260347696e-06,
      "learning_rate": 4.477912067351016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2346960,
      "step": 8380
    },
    {
      "epoch": 93.16666666666667,
      "grad_norm": 8.184376270037319e-07,
      "learning_rate": 4.477311475026271e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2348384,
      "step": 8385
    },
    {
      "epoch": 93.22222222222223,
      "grad_norm": 4.6555621224797505e-07,
      "learning_rate": 4.476710577775248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2349744,
      "step": 8390
    },
    {
      "epoch": 93.27777777777777,
      "grad_norm": 6.862326245027361e-07,
      "learning_rate": 4.476109375690612e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2351136,
      "step": 8395
    },
    {
      "epoch": 93.33333333333333,
      "grad_norm": 1.917506779136602e-06,
      "learning_rate": 4.4755078688650784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2352560,
      "step": 8400
    },
    {
      "epoch": 93.33333333333333,
      "eval_loss": 0.29218530654907227,
      "eval_runtime": 1.3192,
      "eval_samples_per_second": 30.321,
      "eval_steps_per_second": 15.161,
      "num_input_tokens_seen": 2352560,
      "step": 8400
    },
    {
      "epoch": 93.38888888888889,
      "grad_norm": 6.246800126064045e-07,
      "learning_rate": 4.474906057391406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2353952,
      "step": 8405
    },
    {
      "epoch": 93.44444444444444,
      "grad_norm": 4.5269345605447597e-07,
      "learning_rate": 4.4743039413624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2355360,
      "step": 8410
    },
    {
      "epoch": 93.5,
      "grad_norm": 5.190409524402639e-07,
      "learning_rate": 4.473701520870916e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2356752,
      "step": 8415
    },
    {
      "epoch": 93.55555555555556,
      "grad_norm": 4.893625487056852e-07,
      "learning_rate": 4.4730987960098544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2358128,
      "step": 8420
    },
    {
      "epoch": 93.61111111111111,
      "grad_norm": 1.6309252259816276e-06,
      "learning_rate": 4.4724957668721635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2359488,
      "step": 8425
    },
    {
      "epoch": 93.66666666666667,
      "grad_norm": 1.0133910564036341e-06,
      "learning_rate": 4.471892433550836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2360912,
      "step": 8430
    },
    {
      "epoch": 93.72222222222223,
      "grad_norm": 5.675429974871804e-07,
      "learning_rate": 4.471288796138916e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2362288,
      "step": 8435
    },
    {
      "epoch": 93.77777777777777,
      "grad_norm": 4.3294127749504696e-07,
      "learning_rate": 4.470684854729491e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2363712,
      "step": 8440
    },
    {
      "epoch": 93.83333333333333,
      "grad_norm": 5.977809678370249e-07,
      "learning_rate": 4.4700806094156955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2365104,
      "step": 8445
    },
    {
      "epoch": 93.88888888888889,
      "grad_norm": 6.472144491453946e-07,
      "learning_rate": 4.469476060290713e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2366496,
      "step": 8450
    },
    {
      "epoch": 93.94444444444444,
      "grad_norm": 8.642244324619242e-07,
      "learning_rate": 4.468871207447772e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2367888,
      "step": 8455
    },
    {
      "epoch": 94.0,
      "grad_norm": 9.255647910322296e-07,
      "learning_rate": 4.4682660509801486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2369312,
      "step": 8460
    },
    {
      "epoch": 94.05555555555556,
      "grad_norm": 4.0125587474904023e-07,
      "learning_rate": 4.467660590981165e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2370720,
      "step": 8465
    },
    {
      "epoch": 94.11111111111111,
      "grad_norm": 5.464859782478015e-07,
      "learning_rate": 4.467054827544191e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2372128,
      "step": 8470
    },
    {
      "epoch": 94.16666666666667,
      "grad_norm": 4.709953032033809e-07,
      "learning_rate": 4.4664487607626434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2373536,
      "step": 8475
    },
    {
      "epoch": 94.22222222222223,
      "grad_norm": 5.645957230626664e-07,
      "learning_rate": 4.4658423907299845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2374896,
      "step": 8480
    },
    {
      "epoch": 94.27777777777777,
      "grad_norm": 4.543903173725994e-07,
      "learning_rate": 4.465235717539725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2376256,
      "step": 8485
    },
    {
      "epoch": 94.33333333333333,
      "grad_norm": 4.231953312228143e-07,
      "learning_rate": 4.464628741285421e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2377680,
      "step": 8490
    },
    {
      "epoch": 94.38888888888889,
      "grad_norm": 5.149444746166409e-07,
      "learning_rate": 4.4640214620606754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2379104,
      "step": 8495
    },
    {
      "epoch": 94.44444444444444,
      "grad_norm": 1.5116015674720984e-06,
      "learning_rate": 4.46341387995914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2380512,
      "step": 8500
    },
    {
      "epoch": 94.5,
      "grad_norm": 5.363528430279985e-07,
      "learning_rate": 4.4628059950745106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2381936,
      "step": 8505
    },
    {
      "epoch": 94.55555555555556,
      "grad_norm": 5.082357006358507e-07,
      "learning_rate": 4.4621978075005297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2383296,
      "step": 8510
    },
    {
      "epoch": 94.61111111111111,
      "grad_norm": 3.5325929275131784e-06,
      "learning_rate": 4.461589317330989e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2384736,
      "step": 8515
    },
    {
      "epoch": 94.66666666666667,
      "grad_norm": 3.919978439625993e-07,
      "learning_rate": 4.460980524659724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2386192,
      "step": 8520
    },
    {
      "epoch": 94.72222222222223,
      "grad_norm": 5.462450189952506e-07,
      "learning_rate": 4.46037142958062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2387584,
      "step": 8525
    },
    {
      "epoch": 94.77777777777777,
      "grad_norm": 3.9192210010696726e-07,
      "learning_rate": 4.4597620321876046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2388976,
      "step": 8530
    },
    {
      "epoch": 94.83333333333333,
      "grad_norm": 4.5475195520339184e-07,
      "learning_rate": 4.459152332574656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2390368,
      "step": 8535
    },
    {
      "epoch": 94.88888888888889,
      "grad_norm": 4.818807042283879e-07,
      "learning_rate": 4.4585423308357985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2391792,
      "step": 8540
    },
    {
      "epoch": 94.94444444444444,
      "grad_norm": 4.759147032018518e-07,
      "learning_rate": 4.457932027065102e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2393200,
      "step": 8545
    },
    {
      "epoch": 95.0,
      "grad_norm": 1.2503320476753288e-06,
      "learning_rate": 4.45732142135668e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2394624,
      "step": 8550
    },
    {
      "epoch": 95.05555555555556,
      "grad_norm": 4.2940229150190135e-07,
      "learning_rate": 4.4567105138046986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2396048,
      "step": 8555
    },
    {
      "epoch": 95.11111111111111,
      "grad_norm": 6.675355734842014e-07,
      "learning_rate": 4.456099304503365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2397456,
      "step": 8560
    },
    {
      "epoch": 95.16666666666667,
      "grad_norm": 5.40218763944722e-07,
      "learning_rate": 4.455487793546939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2398864,
      "step": 8565
    },
    {
      "epoch": 95.22222222222223,
      "grad_norm": 9.79265109890548e-07,
      "learning_rate": 4.454875981029719e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2400240,
      "step": 8570
    },
    {
      "epoch": 95.27777777777777,
      "grad_norm": 4.3822785755764926e-07,
      "learning_rate": 4.454263867046057e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2401648,
      "step": 8575
    },
    {
      "epoch": 95.33333333333333,
      "grad_norm": 4.6168867129381397e-07,
      "learning_rate": 4.4536514516903484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2403056,
      "step": 8580
    },
    {
      "epoch": 95.38888888888889,
      "grad_norm": 3.8444125038950006e-07,
      "learning_rate": 4.453038735057034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2404400,
      "step": 8585
    },
    {
      "epoch": 95.44444444444444,
      "grad_norm": 4.978397214472352e-07,
      "learning_rate": 4.4524257172406034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2405824,
      "step": 8590
    },
    {
      "epoch": 95.5,
      "grad_norm": 4.4018952394253574e-07,
      "learning_rate": 4.451812398335592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2407232,
      "step": 8595
    },
    {
      "epoch": 95.55555555555556,
      "grad_norm": 2.1011230728618102e-06,
      "learning_rate": 4.4511987784365805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2408640,
      "step": 8600
    },
    {
      "epoch": 95.55555555555556,
      "eval_loss": 0.2896016240119934,
      "eval_runtime": 1.324,
      "eval_samples_per_second": 30.212,
      "eval_steps_per_second": 15.106,
      "num_input_tokens_seen": 2408640,
      "step": 8600
    },
    {
      "epoch": 95.61111111111111,
      "grad_norm": 9.075021694116003e-07,
      "learning_rate": 4.450584857638197e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2410048,
      "step": 8605
    },
    {
      "epoch": 95.66666666666667,
      "grad_norm": 4.460370632841659e-07,
      "learning_rate": 4.449970636035116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2411440,
      "step": 8610
    },
    {
      "epoch": 95.72222222222223,
      "grad_norm": 4.839851612814527e-07,
      "learning_rate": 4.4493561137220574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2412848,
      "step": 8615
    },
    {
      "epoch": 95.77777777777777,
      "grad_norm": 4.3159374740753265e-07,
      "learning_rate": 4.44874129079379e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2414272,
      "step": 8620
    },
    {
      "epoch": 95.83333333333333,
      "grad_norm": 3.6763753996638115e-07,
      "learning_rate": 4.4481261673451255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2415680,
      "step": 8625
    },
    {
      "epoch": 95.88888888888889,
      "grad_norm": 7.152511329877598e-07,
      "learning_rate": 4.4475107434709245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2417104,
      "step": 8630
    },
    {
      "epoch": 95.94444444444444,
      "grad_norm": 7.419649818984908e-07,
      "learning_rate": 4.446895019266093e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2418544,
      "step": 8635
    },
    {
      "epoch": 96.0,
      "grad_norm": 1.92830179912562e-06,
      "learning_rate": 4.446278994825583e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2419920,
      "step": 8640
    },
    {
      "epoch": 96.05555555555556,
      "grad_norm": 1.5036482636787696e-06,
      "learning_rate": 4.445662670244394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2421312,
      "step": 8645
    },
    {
      "epoch": 96.11111111111111,
      "grad_norm": 3.540989439443365e-07,
      "learning_rate": 4.44504604561757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2422656,
      "step": 8650
    },
    {
      "epoch": 96.16666666666667,
      "grad_norm": 1.0568455763859674e-06,
      "learning_rate": 4.4444291210402035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2424064,
      "step": 8655
    },
    {
      "epoch": 96.22222222222223,
      "grad_norm": 5.590638920693891e-07,
      "learning_rate": 4.443811896607431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2425424,
      "step": 8660
    },
    {
      "epoch": 96.27777777777777,
      "grad_norm": 9.111477083934005e-07,
      "learning_rate": 4.443194372414436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2426880,
      "step": 8665
    },
    {
      "epoch": 96.33333333333333,
      "grad_norm": 4.2672681388467026e-07,
      "learning_rate": 4.442576548556449e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2428272,
      "step": 8670
    },
    {
      "epoch": 96.38888888888889,
      "grad_norm": 4.1245752413487935e-07,
      "learning_rate": 4.441958425128747e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2429648,
      "step": 8675
    },
    {
      "epoch": 96.44444444444444,
      "grad_norm": 3.487873811991449e-07,
      "learning_rate": 4.4413400022266515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2431040,
      "step": 8680
    },
    {
      "epoch": 96.5,
      "grad_norm": 1.977222609639284e-06,
      "learning_rate": 4.4407212799455313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2432416,
      "step": 8685
    },
    {
      "epoch": 96.55555555555556,
      "grad_norm": 5.94450170865457e-07,
      "learning_rate": 4.4401022583808003e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2433824,
      "step": 8690
    },
    {
      "epoch": 96.61111111111111,
      "grad_norm": 4.830578177461575e-07,
      "learning_rate": 4.439482937627921e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2435248,
      "step": 8695
    },
    {
      "epoch": 96.66666666666667,
      "grad_norm": 5.075987701275153e-07,
      "learning_rate": 4.4388633177824004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2436704,
      "step": 8700
    },
    {
      "epoch": 96.72222222222223,
      "grad_norm": 3.9265853502001846e-07,
      "learning_rate": 4.4382433989397895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2438112,
      "step": 8705
    },
    {
      "epoch": 96.77777777777777,
      "grad_norm": 4.0766815345705254e-07,
      "learning_rate": 4.4376231811956895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2439520,
      "step": 8710
    },
    {
      "epoch": 96.83333333333333,
      "grad_norm": 3.844011757792032e-07,
      "learning_rate": 4.437002664645745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2440880,
      "step": 8715
    },
    {
      "epoch": 96.88888888888889,
      "grad_norm": 4.7295225158450194e-07,
      "learning_rate": 4.436381849385649e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2442272,
      "step": 8720
    },
    {
      "epoch": 96.94444444444444,
      "grad_norm": 5.596900223281409e-07,
      "learning_rate": 4.435760735511136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2443648,
      "step": 8725
    },
    {
      "epoch": 97.0,
      "grad_norm": 9.709187906992156e-07,
      "learning_rate": 4.435139323117992e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2445072,
      "step": 8730
    },
    {
      "epoch": 97.05555555555556,
      "grad_norm": 4.177464063559455e-07,
      "learning_rate": 4.434517612302046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2446512,
      "step": 8735
    },
    {
      "epoch": 97.11111111111111,
      "grad_norm": 9.86891677712265e-07,
      "learning_rate": 4.433895603159174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2447920,
      "step": 8740
    },
    {
      "epoch": 97.16666666666667,
      "grad_norm": 4.649019160751777e-07,
      "learning_rate": 4.433273295785296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2449328,
      "step": 8745
    },
    {
      "epoch": 97.22222222222223,
      "grad_norm": 3.9312163835347746e-07,
      "learning_rate": 4.432650690276382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2450752,
      "step": 8750
    },
    {
      "epoch": 97.27777777777777,
      "grad_norm": 9.298479426433914e-07,
      "learning_rate": 4.4320277867284435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2452176,
      "step": 8755
    },
    {
      "epoch": 97.33333333333333,
      "grad_norm": 9.654812629378284e-07,
      "learning_rate": 4.431404585237541e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2453552,
      "step": 8760
    },
    {
      "epoch": 97.38888888888889,
      "grad_norm": 5.331710895006836e-07,
      "learning_rate": 4.43078108589978e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2454928,
      "step": 8765
    },
    {
      "epoch": 97.44444444444444,
      "grad_norm": 3.75792780005213e-07,
      "learning_rate": 4.4301572888113116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2456368,
      "step": 8770
    },
    {
      "epoch": 97.5,
      "grad_norm": 4.605936680945888e-07,
      "learning_rate": 4.4295331940683337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2457744,
      "step": 8775
    },
    {
      "epoch": 97.55555555555556,
      "grad_norm": 6.97778034464136e-07,
      "learning_rate": 4.428908801767089e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2459152,
      "step": 8780
    },
    {
      "epoch": 97.61111111111111,
      "grad_norm": 4.789947638528247e-07,
      "learning_rate": 4.428284112003868e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2460496,
      "step": 8785
    },
    {
      "epoch": 97.66666666666667,
      "grad_norm": 6.144015856079932e-07,
      "learning_rate": 4.4276591248750033e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2461920,
      "step": 8790
    },
    {
      "epoch": 97.72222222222223,
      "grad_norm": 3.0419373615586665e-06,
      "learning_rate": 4.4270338404768774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2463312,
      "step": 8795
    },
    {
      "epoch": 97.77777777777777,
      "grad_norm": 5.98666304085782e-07,
      "learning_rate": 4.426408258905917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2464672,
      "step": 8800
    },
    {
      "epoch": 97.77777777777777,
      "eval_loss": 0.3003152906894684,
      "eval_runtime": 1.3277,
      "eval_samples_per_second": 30.128,
      "eval_steps_per_second": 15.064,
      "num_input_tokens_seen": 2464672,
      "step": 8800
    },
    {
      "epoch": 97.83333333333333,
      "grad_norm": 5.109272933623288e-07,
      "learning_rate": 4.425782380258594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2466080,
      "step": 8805
    },
    {
      "epoch": 97.88888888888889,
      "grad_norm": 4.7065415742508776e-07,
      "learning_rate": 4.425156204631427e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2467488,
      "step": 8810
    },
    {
      "epoch": 97.94444444444444,
      "grad_norm": 4.6103673412289936e-07,
      "learning_rate": 4.424529732120981e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2468896,
      "step": 8815
    },
    {
      "epoch": 98.0,
      "grad_norm": 4.002939135716588e-07,
      "learning_rate": 4.423902962823864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2470304,
      "step": 8820
    },
    {
      "epoch": 98.05555555555556,
      "grad_norm": 3.861628954382468e-07,
      "learning_rate": 4.423275896836733e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2471696,
      "step": 8825
    },
    {
      "epoch": 98.11111111111111,
      "grad_norm": 4.47130872771595e-07,
      "learning_rate": 4.42264853425629e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2473088,
      "step": 8830
    },
    {
      "epoch": 98.16666666666667,
      "grad_norm": 4.213072486436431e-07,
      "learning_rate": 4.4220208751792816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2474496,
      "step": 8835
    },
    {
      "epoch": 98.22222222222223,
      "grad_norm": 4.929428314426332e-07,
      "learning_rate": 4.421392919702499e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2475888,
      "step": 8840
    },
    {
      "epoch": 98.27777777777777,
      "grad_norm": 4.44088243511942e-07,
      "learning_rate": 4.4207646679227846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2477296,
      "step": 8845
    },
    {
      "epoch": 98.33333333333333,
      "grad_norm": 4.343128523487394e-07,
      "learning_rate": 4.42013611993702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2478736,
      "step": 8850
    },
    {
      "epoch": 98.38888888888889,
      "grad_norm": 4.4488305661616323e-07,
      "learning_rate": 4.419507275842135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2480112,
      "step": 8855
    },
    {
      "epoch": 98.44444444444444,
      "grad_norm": 1.5525421304118936e-06,
      "learning_rate": 4.418878135735106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2481584,
      "step": 8860
    },
    {
      "epoch": 98.5,
      "grad_norm": 4.6084105065347103e-07,
      "learning_rate": 4.418248699712955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2482960,
      "step": 8865
    },
    {
      "epoch": 98.55555555555556,
      "grad_norm": 1.789239831850864e-06,
      "learning_rate": 4.417618967872748e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2484352,
      "step": 8870
    },
    {
      "epoch": 98.61111111111111,
      "grad_norm": 4.97995415571495e-07,
      "learning_rate": 4.4169889403115985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2485776,
      "step": 8875
    },
    {
      "epoch": 98.66666666666667,
      "grad_norm": 3.5299873957228556e-07,
      "learning_rate": 4.4163586171266627e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2487136,
      "step": 8880
    },
    {
      "epoch": 98.72222222222223,
      "grad_norm": 3.5634252526506316e-07,
      "learning_rate": 4.415727998415147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2488560,
      "step": 8885
    },
    {
      "epoch": 98.77777777777777,
      "grad_norm": 4.394720178879652e-07,
      "learning_rate": 4.4150970842742985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2489984,
      "step": 8890
    },
    {
      "epoch": 98.83333333333333,
      "grad_norm": 3.726954389549064e-07,
      "learning_rate": 4.4144658748014134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2491376,
      "step": 8895
    },
    {
      "epoch": 98.88888888888889,
      "grad_norm": 4.3971118657282204e-07,
      "learning_rate": 4.413834370093831e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2492816,
      "step": 8900
    },
    {
      "epoch": 98.94444444444444,
      "grad_norm": 4.660954573409981e-07,
      "learning_rate": 4.413202570248939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2494176,
      "step": 8905
    },
    {
      "epoch": 99.0,
      "grad_norm": 4.903806711809011e-07,
      "learning_rate": 4.412570475364167e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2495488,
      "step": 8910
    },
    {
      "epoch": 99.05555555555556,
      "grad_norm": 1.0715411917772144e-06,
      "learning_rate": 4.411938085536994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2496880,
      "step": 8915
    },
    {
      "epoch": 99.11111111111111,
      "grad_norm": 5.65504933547345e-07,
      "learning_rate": 4.41130540086494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2498288,
      "step": 8920
    },
    {
      "epoch": 99.16666666666667,
      "grad_norm": 5.063664502813481e-06,
      "learning_rate": 4.4106724214455754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2499648,
      "step": 8925
    },
    {
      "epoch": 99.22222222222223,
      "grad_norm": 6.188037673382496e-07,
      "learning_rate": 4.4100391473765115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2501008,
      "step": 8930
    },
    {
      "epoch": 99.27777777777777,
      "grad_norm": 3.9481400904151087e-07,
      "learning_rate": 4.409405578755408e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2502416,
      "step": 8935
    },
    {
      "epoch": 99.33333333333333,
      "grad_norm": 4.088751097697241e-07,
      "learning_rate": 4.4087717156799705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2503808,
      "step": 8940
    },
    {
      "epoch": 99.38888888888889,
      "grad_norm": 1.8815127305060741e-06,
      "learning_rate": 4.408137558247946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2505200,
      "step": 8945
    },
    {
      "epoch": 99.44444444444444,
      "grad_norm": 3.458878552464739e-07,
      "learning_rate": 4.4075031065571306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2506608,
      "step": 8950
    },
    {
      "epoch": 99.5,
      "grad_norm": 1.0031079682448762e-06,
      "learning_rate": 4.406868360705366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2508000,
      "step": 8955
    },
    {
      "epoch": 99.55555555555556,
      "grad_norm": 4.1132659589493414e-07,
      "learning_rate": 4.406233320790536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2509440,
      "step": 8960
    },
    {
      "epoch": 99.61111111111111,
      "grad_norm": 3.60177295988251e-07,
      "learning_rate": 4.4055979869105734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2510864,
      "step": 8965
    },
    {
      "epoch": 99.66666666666667,
      "grad_norm": 5.137288781043026e-07,
      "learning_rate": 4.404962359163454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2512272,
      "step": 8970
    },
    {
      "epoch": 99.72222222222223,
      "grad_norm": 4.1030935449271055e-07,
      "learning_rate": 4.404326437647199e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2513680,
      "step": 8975
    },
    {
      "epoch": 99.77777777777777,
      "grad_norm": 3.782614896863379e-07,
      "learning_rate": 4.403690222459877e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2515056,
      "step": 8980
    },
    {
      "epoch": 99.83333333333333,
      "grad_norm": 4.236169672822143e-07,
      "learning_rate": 4.4030537136995984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2516464,
      "step": 8985
    },
    {
      "epoch": 99.88888888888889,
      "grad_norm": 9.240538929589093e-07,
      "learning_rate": 4.402416911464523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2517888,
      "step": 8990
    },
    {
      "epoch": 99.94444444444444,
      "grad_norm": 4.358386149760918e-07,
      "learning_rate": 4.4017798158528516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2519312,
      "step": 8995
    },
    {
      "epoch": 100.0,
      "grad_norm": 9.947624448614079e-07,
      "learning_rate": 4.401142426962834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2520688,
      "step": 9000
    },
    {
      "epoch": 100.0,
      "eval_loss": 0.2869197726249695,
      "eval_runtime": 1.2948,
      "eval_samples_per_second": 30.894,
      "eval_steps_per_second": 15.447,
      "num_input_tokens_seen": 2520688,
      "step": 9000
    },
    {
      "epoch": 100.05555555555556,
      "grad_norm": 1.055937104865734e-06,
      "learning_rate": 4.400504744892763e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2522112,
      "step": 9005
    },
    {
      "epoch": 100.11111111111111,
      "grad_norm": 4.756697080665617e-07,
      "learning_rate": 4.399866769740975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2523552,
      "step": 9010
    },
    {
      "epoch": 100.16666666666667,
      "grad_norm": 5.509933771463693e-07,
      "learning_rate": 4.399228501605859e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2524960,
      "step": 9015
    },
    {
      "epoch": 100.22222222222223,
      "grad_norm": 4.444694923222414e-07,
      "learning_rate": 4.398589940585839e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2526336,
      "step": 9020
    },
    {
      "epoch": 100.27777777777777,
      "grad_norm": 4.774832405018969e-07,
      "learning_rate": 4.3979510867793917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2527760,
      "step": 9025
    },
    {
      "epoch": 100.33333333333333,
      "grad_norm": 1.6072976904979441e-06,
      "learning_rate": 4.3973119402850346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2529152,
      "step": 9030
    },
    {
      "epoch": 100.38888888888889,
      "grad_norm": 3.794924623434781e-07,
      "learning_rate": 4.396672501201334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2530560,
      "step": 9035
    },
    {
      "epoch": 100.44444444444444,
      "grad_norm": 1.026552013172477e-06,
      "learning_rate": 4.396032769626899e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2531936,
      "step": 9040
    },
    {
      "epoch": 100.5,
      "grad_norm": 4.268837869858544e-07,
      "learning_rate": 4.395392745660384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2533328,
      "step": 9045
    },
    {
      "epoch": 100.55555555555556,
      "grad_norm": 1.0443110340929707e-06,
      "learning_rate": 4.394752429400488e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2534672,
      "step": 9050
    },
    {
      "epoch": 100.61111111111111,
      "grad_norm": 3.7524230265262304e-06,
      "learning_rate": 4.394111820945957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2536032,
      "step": 9055
    },
    {
      "epoch": 100.66666666666667,
      "grad_norm": 3.9667480677962885e-07,
      "learning_rate": 4.393470920395579e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2537408,
      "step": 9060
    },
    {
      "epoch": 100.72222222222223,
      "grad_norm": 2.1907410427957075e-06,
      "learning_rate": 4.392829727848192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2538800,
      "step": 9065
    },
    {
      "epoch": 100.77777777777777,
      "grad_norm": 7.319465566979488e-07,
      "learning_rate": 4.392188243402673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2540224,
      "step": 9070
    },
    {
      "epoch": 100.83333333333333,
      "grad_norm": 3.953530551825679e-07,
      "learning_rate": 4.391546467157949e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2541632,
      "step": 9075
    },
    {
      "epoch": 100.88888888888889,
      "grad_norm": 5.129942906023643e-07,
      "learning_rate": 4.390904399212988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2543008,
      "step": 9080
    },
    {
      "epoch": 100.94444444444444,
      "grad_norm": 3.6839611539107864e-07,
      "learning_rate": 4.390262039666807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2544416,
      "step": 9085
    },
    {
      "epoch": 101.0,
      "grad_norm": 4.58274996617547e-07,
      "learning_rate": 4.389619388618464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2545824,
      "step": 9090
    },
    {
      "epoch": 101.05555555555556,
      "grad_norm": 3.569305420114688e-07,
      "learning_rate": 4.3889764461670655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2547216,
      "step": 9095
    },
    {
      "epoch": 101.11111111111111,
      "grad_norm": 3.367049146163481e-07,
      "learning_rate": 4.38833321241176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2548608,
      "step": 9100
    },
    {
      "epoch": 101.16666666666667,
      "grad_norm": 3.6805155900765385e-07,
      "learning_rate": 4.3876896874517434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2550032,
      "step": 9105
    },
    {
      "epoch": 101.22222222222223,
      "grad_norm": 4.928216412736219e-07,
      "learning_rate": 4.3870458713862554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2551440,
      "step": 9110
    },
    {
      "epoch": 101.27777777777777,
      "grad_norm": 9.988879128286499e-07,
      "learning_rate": 4.386401764314579e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2552800,
      "step": 9115
    },
    {
      "epoch": 101.33333333333333,
      "grad_norm": 5.956799782325106e-07,
      "learning_rate": 4.385757366336045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2554240,
      "step": 9120
    },
    {
      "epoch": 101.38888888888889,
      "grad_norm": 3.9693119902040053e-07,
      "learning_rate": 4.385112677550027e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2555664,
      "step": 9125
    },
    {
      "epoch": 101.44444444444444,
      "grad_norm": 4.2995637272724707e-07,
      "learning_rate": 4.384467698055945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2557056,
      "step": 9130
    },
    {
      "epoch": 101.5,
      "grad_norm": 3.6117756962994463e-07,
      "learning_rate": 4.383822427953261e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2558464,
      "step": 9135
    },
    {
      "epoch": 101.55555555555556,
      "grad_norm": 3.519160145515343e-07,
      "learning_rate": 4.3831768673414864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2559856,
      "step": 9140
    },
    {
      "epoch": 101.61111111111111,
      "grad_norm": 3.628748856954189e-07,
      "learning_rate": 4.382531016320173e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2561232,
      "step": 9145
    },
    {
      "epoch": 101.66666666666667,
      "grad_norm": 5.418498858489329e-07,
      "learning_rate": 4.3818848749889184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2562672,
      "step": 9150
    },
    {
      "epoch": 101.72222222222223,
      "grad_norm": 3.560053016826714e-07,
      "learning_rate": 4.381238443447368e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2564048,
      "step": 9155
    },
    {
      "epoch": 101.77777777777777,
      "grad_norm": 1.956959977178485e-06,
      "learning_rate": 4.380591721795208e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2565424,
      "step": 9160
    },
    {
      "epoch": 101.83333333333333,
      "grad_norm": 4.061550669121061e-07,
      "learning_rate": 4.3799447101321723e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2566896,
      "step": 9165
    },
    {
      "epoch": 101.88888888888889,
      "grad_norm": 3.1148223911259265e-07,
      "learning_rate": 4.379297408558036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2568288,
      "step": 9170
    },
    {
      "epoch": 101.94444444444444,
      "grad_norm": 3.6931831459696696e-07,
      "learning_rate": 4.378649817172624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2569664,
      "step": 9175
    },
    {
      "epoch": 102.0,
      "grad_norm": 4.0323729422198085e-07,
      "learning_rate": 4.378001936075801e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2571056,
      "step": 9180
    },
    {
      "epoch": 102.05555555555556,
      "grad_norm": 3.7229227700663614e-07,
      "learning_rate": 4.377353765367479e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2572496,
      "step": 9185
    },
    {
      "epoch": 102.11111111111111,
      "grad_norm": 1.046477336785756e-06,
      "learning_rate": 4.376705305147614e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2573872,
      "step": 9190
    },
    {
      "epoch": 102.16666666666667,
      "grad_norm": 4.5188875219537294e-07,
      "learning_rate": 4.376056555516206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2575280,
      "step": 9195
    },
    {
      "epoch": 102.22222222222223,
      "grad_norm": 4.1512834059176384e-07,
      "learning_rate": 4.375407516573302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2576656,
      "step": 9200
    },
    {
      "epoch": 102.22222222222223,
      "eval_loss": 0.30222058296203613,
      "eval_runtime": 1.3146,
      "eval_samples_per_second": 30.428,
      "eval_steps_per_second": 15.214,
      "num_input_tokens_seen": 2576656,
      "step": 9200
    },
    {
      "epoch": 102.27777777777777,
      "grad_norm": 4.6965081423877564e-07,
      "learning_rate": 4.3747581884189913e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2578032,
      "step": 9205
    },
    {
      "epoch": 102.33333333333333,
      "grad_norm": 1.0800101790664485e-06,
      "learning_rate": 4.374108571153408e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2579456,
      "step": 9210
    },
    {
      "epoch": 102.38888888888889,
      "grad_norm": 5.291349793878908e-07,
      "learning_rate": 4.3734586648767316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2580880,
      "step": 9215
    },
    {
      "epoch": 102.44444444444444,
      "grad_norm": 1.9218582565372344e-06,
      "learning_rate": 4.372808469689186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2582304,
      "step": 9220
    },
    {
      "epoch": 102.5,
      "grad_norm": 3.8834215843053244e-07,
      "learning_rate": 4.372157985691039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2583664,
      "step": 9225
    },
    {
      "epoch": 102.55555555555556,
      "grad_norm": 3.643662580543605e-07,
      "learning_rate": 4.371507212982603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2585136,
      "step": 9230
    },
    {
      "epoch": 102.61111111111111,
      "grad_norm": 5.923278649788699e-07,
      "learning_rate": 4.370856151664236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2586544,
      "step": 9235
    },
    {
      "epoch": 102.66666666666667,
      "grad_norm": 3.5596437442109163e-07,
      "learning_rate": 4.3702048018363404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2588000,
      "step": 9240
    },
    {
      "epoch": 102.72222222222223,
      "grad_norm": 3.4945600191349513e-07,
      "learning_rate": 4.369553163599362e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2589344,
      "step": 9245
    },
    {
      "epoch": 102.77777777777777,
      "grad_norm": 3.9048006783559686e-07,
      "learning_rate": 4.3689012370537904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2590736,
      "step": 9250
    },
    {
      "epoch": 102.83333333333333,
      "grad_norm": 4.0215488184003334e-07,
      "learning_rate": 4.368249022300164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2592112,
      "step": 9255
    },
    {
      "epoch": 102.88888888888889,
      "grad_norm": 3.9494449310950586e-07,
      "learning_rate": 4.367596519439059e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2593520,
      "step": 9260
    },
    {
      "epoch": 102.94444444444444,
      "grad_norm": 3.915042725566309e-07,
      "learning_rate": 4.366943728571101e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2594880,
      "step": 9265
    },
    {
      "epoch": 103.0,
      "grad_norm": 3.9186048184092215e-07,
      "learning_rate": 4.366290649796959e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2596256,
      "step": 9270
    },
    {
      "epoch": 103.05555555555556,
      "grad_norm": 3.9425094655598514e-07,
      "learning_rate": 4.3656372832173456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2597648,
      "step": 9275
    },
    {
      "epoch": 103.11111111111111,
      "grad_norm": 1.7841413182395627e-06,
      "learning_rate": 4.364983628933017e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2599040,
      "step": 9280
    },
    {
      "epoch": 103.16666666666667,
      "grad_norm": 3.5923983432439854e-07,
      "learning_rate": 4.364329687044777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2600464,
      "step": 9285
    },
    {
      "epoch": 103.22222222222223,
      "grad_norm": 3.861503046209691e-07,
      "learning_rate": 4.36367545765347e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2601904,
      "step": 9290
    },
    {
      "epoch": 103.27777777777777,
      "grad_norm": 4.1534997308190214e-07,
      "learning_rate": 4.363020940859988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2603328,
      "step": 9295
    },
    {
      "epoch": 103.33333333333333,
      "grad_norm": 4.309986820771883e-07,
      "learning_rate": 4.362366136765263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2604768,
      "step": 9300
    },
    {
      "epoch": 103.38888888888889,
      "grad_norm": 5.707765353690775e-07,
      "learning_rate": 4.361711045470278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2606112,
      "step": 9305
    },
    {
      "epoch": 103.44444444444444,
      "grad_norm": 3.0383108651221846e-07,
      "learning_rate": 4.3610556670760524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2607520,
      "step": 9310
    },
    {
      "epoch": 103.5,
      "grad_norm": 4.6920968088670634e-07,
      "learning_rate": 4.360400001683657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2608912,
      "step": 9315
    },
    {
      "epoch": 103.55555555555556,
      "grad_norm": 4.33821526257816e-07,
      "learning_rate": 4.3597440493942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2610368,
      "step": 9320
    },
    {
      "epoch": 103.61111111111111,
      "grad_norm": 4.0856716054804565e-07,
      "learning_rate": 4.3590878103088405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2611792,
      "step": 9325
    },
    {
      "epoch": 103.66666666666667,
      "grad_norm": 3.3651227226982883e-07,
      "learning_rate": 4.358431284528779e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2613168,
      "step": 9330
    },
    {
      "epoch": 103.72222222222223,
      "grad_norm": 4.0663334743840096e-07,
      "learning_rate": 4.357774472155257e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2614528,
      "step": 9335
    },
    {
      "epoch": 103.77777777777777,
      "grad_norm": 7.164948101490154e-07,
      "learning_rate": 4.3571173732895664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2615920,
      "step": 9340
    },
    {
      "epoch": 103.83333333333333,
      "grad_norm": 1.5994648947526002e-06,
      "learning_rate": 4.356459988033039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2617232,
      "step": 9345
    },
    {
      "epoch": 103.88888888888889,
      "grad_norm": 4.310215899749892e-07,
      "learning_rate": 4.355802316487051e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2618608,
      "step": 9350
    },
    {
      "epoch": 103.94444444444444,
      "grad_norm": 3.6084358612242795e-07,
      "learning_rate": 4.355144358753025e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2620032,
      "step": 9355
    },
    {
      "epoch": 104.0,
      "grad_norm": 3.7005335684625607e-07,
      "learning_rate": 4.354486114932425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2621424,
      "step": 9360
    },
    {
      "epoch": 104.05555555555556,
      "grad_norm": 4.2917758946714457e-07,
      "learning_rate": 4.353827585126762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2622832,
      "step": 9365
    },
    {
      "epoch": 104.11111111111111,
      "grad_norm": 5.370021654016455e-07,
      "learning_rate": 4.353168769437588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2624320,
      "step": 9370
    },
    {
      "epoch": 104.16666666666667,
      "grad_norm": 3.450902852364379e-07,
      "learning_rate": 4.3525096679665014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2625680,
      "step": 9375
    },
    {
      "epoch": 104.22222222222223,
      "grad_norm": 4.32934939453844e-07,
      "learning_rate": 4.351850280815144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2627104,
      "step": 9380
    },
    {
      "epoch": 104.27777777777777,
      "grad_norm": 4.1286651253358286e-07,
      "learning_rate": 4.3511906080852014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2628528,
      "step": 9385
    },
    {
      "epoch": 104.33333333333333,
      "grad_norm": 4.229048329307261e-07,
      "learning_rate": 4.350530649878404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2629920,
      "step": 9390
    },
    {
      "epoch": 104.38888888888889,
      "grad_norm": 5.770240250058123e-07,
      "learning_rate": 4.3498704062965246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2631328,
      "step": 9395
    },
    {
      "epoch": 104.44444444444444,
      "grad_norm": 4.343271484685829e-07,
      "learning_rate": 4.3492098774413815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2632720,
      "step": 9400
    },
    {
      "epoch": 104.44444444444444,
      "eval_loss": 0.2932952344417572,
      "eval_runtime": 1.2995,
      "eval_samples_per_second": 30.781,
      "eval_steps_per_second": 15.391,
      "num_input_tokens_seen": 2632720,
      "step": 9400
    },
    {
      "epoch": 104.5,
      "grad_norm": 1.4403037766896887e-06,
      "learning_rate": 4.3485490634148375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2634144,
      "step": 9405
    },
    {
      "epoch": 104.55555555555556,
      "grad_norm": 5.336002573130827e-07,
      "learning_rate": 4.347887964318797e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2635568,
      "step": 9410
    },
    {
      "epoch": 104.61111111111111,
      "grad_norm": 4.0369113207816554e-07,
      "learning_rate": 4.34722658025521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2636896,
      "step": 9415
    },
    {
      "epoch": 104.66666666666667,
      "grad_norm": 4.5189042907622934e-07,
      "learning_rate": 4.346564911326071e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2638320,
      "step": 9420
    },
    {
      "epoch": 104.72222222222223,
      "grad_norm": 4.823880317417206e-07,
      "learning_rate": 4.345902957633418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2639712,
      "step": 9425
    },
    {
      "epoch": 104.77777777777777,
      "grad_norm": 4.901687020719692e-07,
      "learning_rate": 4.345240719279331e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2641136,
      "step": 9430
    },
    {
      "epoch": 104.83333333333333,
      "grad_norm": 5.101037459098734e-07,
      "learning_rate": 4.3445781963659374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2642544,
      "step": 9435
    },
    {
      "epoch": 104.88888888888889,
      "grad_norm": 4.0922640209828387e-07,
      "learning_rate": 4.3439153889954045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2643904,
      "step": 9440
    },
    {
      "epoch": 104.94444444444444,
      "grad_norm": 4.1860329247356276e-07,
      "learning_rate": 4.343252297269946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2645296,
      "step": 9445
    },
    {
      "epoch": 105.0,
      "grad_norm": 1.063192030414939e-06,
      "learning_rate": 4.342588921291821e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2646672,
      "step": 9450
    },
    {
      "epoch": 105.05555555555556,
      "grad_norm": 4.181083284038323e-07,
      "learning_rate": 4.341925261163328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2648112,
      "step": 9455
    },
    {
      "epoch": 105.11111111111111,
      "grad_norm": 3.61127803216732e-07,
      "learning_rate": 4.341261316986813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2649456,
      "step": 9460
    },
    {
      "epoch": 105.16666666666667,
      "grad_norm": 1.8321613879379584e-06,
      "learning_rate": 4.340597088864664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2650880,
      "step": 9465
    },
    {
      "epoch": 105.22222222222223,
      "grad_norm": 5.356536121325917e-07,
      "learning_rate": 4.339932576899313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2652320,
      "step": 9470
    },
    {
      "epoch": 105.27777777777777,
      "grad_norm": 6.404561645467766e-07,
      "learning_rate": 4.3392677811932375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2653680,
      "step": 9475
    },
    {
      "epoch": 105.33333333333333,
      "grad_norm": 1.087585019377002e-06,
      "learning_rate": 4.338602701848956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2655072,
      "step": 9480
    },
    {
      "epoch": 105.38888888888889,
      "grad_norm": 3.956540695071453e-07,
      "learning_rate": 4.337937338969033e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2656496,
      "step": 9485
    },
    {
      "epoch": 105.44444444444444,
      "grad_norm": 2.7677933758241124e-06,
      "learning_rate": 4.337271692656075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2657920,
      "step": 9490
    },
    {
      "epoch": 105.5,
      "grad_norm": 4.421305845880852e-07,
      "learning_rate": 4.336605763012733e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2659296,
      "step": 9495
    },
    {
      "epoch": 105.55555555555556,
      "grad_norm": 4.426275381774758e-07,
      "learning_rate": 4.3359395501417026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2660656,
      "step": 9500
    },
    {
      "epoch": 105.61111111111111,
      "grad_norm": 1.2391074051265605e-06,
      "learning_rate": 4.335273054145722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2662016,
      "step": 9505
    },
    {
      "epoch": 105.66666666666667,
      "grad_norm": 3.5520494634511124e-07,
      "learning_rate": 4.334606275127572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2663424,
      "step": 9510
    },
    {
      "epoch": 105.72222222222223,
      "grad_norm": 1.5348834949691081e-06,
      "learning_rate": 4.33393921319008e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2664832,
      "step": 9515
    },
    {
      "epoch": 105.77777777777777,
      "grad_norm": 1.2600129366546753e-06,
      "learning_rate": 4.3332718684361146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2666240,
      "step": 9520
    },
    {
      "epoch": 105.83333333333333,
      "grad_norm": 4.91947275804705e-07,
      "learning_rate": 4.332604240968588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2667664,
      "step": 9525
    },
    {
      "epoch": 105.88888888888889,
      "grad_norm": 4.622004041721084e-07,
      "learning_rate": 4.331936330890459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2669104,
      "step": 9530
    },
    {
      "epoch": 105.94444444444444,
      "grad_norm": 4.845518333240761e-07,
      "learning_rate": 4.331268138304725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2670512,
      "step": 9535
    },
    {
      "epoch": 106.0,
      "grad_norm": 1.3302371826284798e-06,
      "learning_rate": 4.330599663314431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2671904,
      "step": 9540
    },
    {
      "epoch": 106.05555555555556,
      "grad_norm": 4.475330115383258e-07,
      "learning_rate": 4.329930906022665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2673344,
      "step": 9545
    },
    {
      "epoch": 106.11111111111111,
      "grad_norm": 4.231959280787123e-07,
      "learning_rate": 4.3292618665325564e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2674800,
      "step": 9550
    },
    {
      "epoch": 106.16666666666667,
      "grad_norm": 1.748727981976117e-06,
      "learning_rate": 4.3285925449472796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2676176,
      "step": 9555
    },
    {
      "epoch": 106.22222222222223,
      "grad_norm": 3.4502272683312185e-07,
      "learning_rate": 4.327922941370054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2677520,
      "step": 9560
    },
    {
      "epoch": 106.27777777777777,
      "grad_norm": 4.473498620427563e-07,
      "learning_rate": 4.3272530559041384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2678944,
      "step": 9565
    },
    {
      "epoch": 106.33333333333333,
      "grad_norm": 4.1894469404724077e-07,
      "learning_rate": 4.32658288865284e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2680336,
      "step": 9570
    },
    {
      "epoch": 106.38888888888889,
      "grad_norm": 6.919864858900837e-07,
      "learning_rate": 4.325912439719505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2681696,
      "step": 9575
    },
    {
      "epoch": 106.44444444444444,
      "grad_norm": 1.2863986285083229e-06,
      "learning_rate": 4.3252417092075266e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2683104,
      "step": 9580
    },
    {
      "epoch": 106.5,
      "grad_norm": 4.678299774241168e-07,
      "learning_rate": 4.3245706972203385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2684544,
      "step": 9585
    },
    {
      "epoch": 106.55555555555556,
      "grad_norm": 2.232063252449734e-06,
      "learning_rate": 4.323899403861421e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2685920,
      "step": 9590
    },
    {
      "epoch": 106.61111111111111,
      "grad_norm": 4.791354513145052e-07,
      "learning_rate": 4.3232278292342935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2687264,
      "step": 9595
    },
    {
      "epoch": 106.66666666666667,
      "grad_norm": 4.4455345005189884e-07,
      "learning_rate": 4.322555973442524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2688704,
      "step": 9600
    },
    {
      "epoch": 106.66666666666667,
      "eval_loss": 0.3191697597503662,
      "eval_runtime": 1.3149,
      "eval_samples_per_second": 30.42,
      "eval_steps_per_second": 15.21,
      "num_input_tokens_seen": 2688704,
      "step": 9600
    },
    {
      "epoch": 106.72222222222223,
      "grad_norm": 5.321282969816821e-07,
      "learning_rate": 4.3218838365897184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2690128,
      "step": 9605
    },
    {
      "epoch": 106.77777777777777,
      "grad_norm": 4.352852442934818e-07,
      "learning_rate": 4.3212114187795306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2691568,
      "step": 9610
    },
    {
      "epoch": 106.83333333333333,
      "grad_norm": 1.0939057801806484e-06,
      "learning_rate": 4.320538720115656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2692960,
      "step": 9615
    },
    {
      "epoch": 106.88888888888889,
      "grad_norm": 1.0995811408065492e-06,
      "learning_rate": 4.319865740701831e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2694336,
      "step": 9620
    },
    {
      "epoch": 106.94444444444444,
      "grad_norm": 4.215841329369141e-07,
      "learning_rate": 4.3191924806418396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2695744,
      "step": 9625
    },
    {
      "epoch": 107.0,
      "grad_norm": 1.1082170203735586e-06,
      "learning_rate": 4.318518940039507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2697136,
      "step": 9630
    },
    {
      "epoch": 107.05555555555556,
      "grad_norm": 1.1849770089611411e-06,
      "learning_rate": 4.3178451189987e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2698560,
      "step": 9635
    },
    {
      "epoch": 107.11111111111111,
      "grad_norm": 4.117977709938714e-07,
      "learning_rate": 4.3171710176233315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2700000,
      "step": 9640
    },
    {
      "epoch": 107.16666666666667,
      "grad_norm": 4.206753203561675e-07,
      "learning_rate": 4.316496636017355e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2701424,
      "step": 9645
    },
    {
      "epoch": 107.22222222222223,
      "grad_norm": 1.6305169765473693e-06,
      "learning_rate": 4.315821974284771e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2702832,
      "step": 9650
    },
    {
      "epoch": 107.27777777777777,
      "grad_norm": 4.7310723516602593e-07,
      "learning_rate": 4.315147032529619e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2704224,
      "step": 9655
    },
    {
      "epoch": 107.33333333333333,
      "grad_norm": 4.047145409913355e-07,
      "learning_rate": 4.3144718108559845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2705648,
      "step": 9660
    },
    {
      "epoch": 107.38888888888889,
      "grad_norm": 5.127454869580106e-07,
      "learning_rate": 4.3137963093679945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2707024,
      "step": 9665
    },
    {
      "epoch": 107.44444444444444,
      "grad_norm": 1.3426405303107458e-06,
      "learning_rate": 4.31312052816982e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2708400,
      "step": 9670
    },
    {
      "epoch": 107.5,
      "grad_norm": 1.206018509947171e-06,
      "learning_rate": 4.312444467365675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2709792,
      "step": 9675
    },
    {
      "epoch": 107.55555555555556,
      "grad_norm": 4.455270925518562e-07,
      "learning_rate": 4.311768127059816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2711184,
      "step": 9680
    },
    {
      "epoch": 107.61111111111111,
      "grad_norm": 5.805540013170685e-07,
      "learning_rate": 4.3110915073565444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2712592,
      "step": 9685
    },
    {
      "epoch": 107.66666666666667,
      "grad_norm": 4.012685508314462e-07,
      "learning_rate": 4.310414608360203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2713968,
      "step": 9690
    },
    {
      "epoch": 107.72222222222223,
      "grad_norm": 4.1034348896573647e-07,
      "learning_rate": 4.309737430175177e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2715344,
      "step": 9695
    },
    {
      "epoch": 107.77777777777777,
      "grad_norm": 4.4536821519614023e-07,
      "learning_rate": 4.309059972905897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2716752,
      "step": 9700
    },
    {
      "epoch": 107.83333333333333,
      "grad_norm": 1.1440391745054512e-06,
      "learning_rate": 4.308382236656836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2718144,
      "step": 9705
    },
    {
      "epoch": 107.88888888888889,
      "grad_norm": 4.376564675112604e-07,
      "learning_rate": 4.307704221532507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2719552,
      "step": 9710
    },
    {
      "epoch": 107.94444444444444,
      "grad_norm": 6.441791242650652e-07,
      "learning_rate": 4.307025927637471e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2720960,
      "step": 9715
    },
    {
      "epoch": 108.0,
      "grad_norm": 1.2988281241632649e-06,
      "learning_rate": 4.306347355076328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2722336,
      "step": 9720
    },
    {
      "epoch": 108.05555555555556,
      "grad_norm": 1.1051889714508434e-06,
      "learning_rate": 4.305668503953724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2723760,
      "step": 9725
    },
    {
      "epoch": 108.11111111111111,
      "grad_norm": 1.2692188420260209e-06,
      "learning_rate": 4.3049893743743436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2725184,
      "step": 9730
    },
    {
      "epoch": 108.16666666666667,
      "grad_norm": 4.717195736247959e-07,
      "learning_rate": 4.304309966442919e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2726640,
      "step": 9735
    },
    {
      "epoch": 108.22222222222223,
      "grad_norm": 4.922892458125716e-07,
      "learning_rate": 4.303630280264224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2727984,
      "step": 9740
    },
    {
      "epoch": 108.27777777777777,
      "grad_norm": 3.7896901972089836e-07,
      "learning_rate": 4.302950315943074e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2729408,
      "step": 9745
    },
    {
      "epoch": 108.33333333333333,
      "grad_norm": 1.1199033451703144e-06,
      "learning_rate": 4.3022700735843275e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2730784,
      "step": 9750
    },
    {
      "epoch": 108.38888888888889,
      "grad_norm": 6.029670203133719e-07,
      "learning_rate": 4.301589553292887e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2732176,
      "step": 9755
    },
    {
      "epoch": 108.44444444444444,
      "grad_norm": 5.43213843684498e-07,
      "learning_rate": 4.300908755173697e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2733600,
      "step": 9760
    },
    {
      "epoch": 108.5,
      "grad_norm": 4.446748675945855e-07,
      "learning_rate": 4.300227679331745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2734992,
      "step": 9765
    },
    {
      "epoch": 108.55555555555556,
      "grad_norm": 4.972340548192733e-07,
      "learning_rate": 4.299546325872063e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2736352,
      "step": 9770
    },
    {
      "epoch": 108.61111111111111,
      "grad_norm": 7.378046689154871e-07,
      "learning_rate": 4.2988646948997225e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2737760,
      "step": 9775
    },
    {
      "epoch": 108.66666666666667,
      "grad_norm": 1.5719604107289342e-06,
      "learning_rate": 4.29818278651984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2739136,
      "step": 9780
    },
    {
      "epoch": 108.72222222222223,
      "grad_norm": 4.924033873976441e-07,
      "learning_rate": 4.297500600837574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2740496,
      "step": 9785
    },
    {
      "epoch": 108.77777777777777,
      "grad_norm": 4.043426713451481e-07,
      "learning_rate": 4.2968181379581276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2741936,
      "step": 9790
    },
    {
      "epoch": 108.83333333333333,
      "grad_norm": 9.708916195450001e-07,
      "learning_rate": 4.296135397986743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2743344,
      "step": 9795
    },
    {
      "epoch": 108.88888888888889,
      "grad_norm": 4.221638221224566e-07,
      "learning_rate": 4.295452381028709e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2744768,
      "step": 9800
    },
    {
      "epoch": 108.88888888888889,
      "eval_loss": 0.29875534772872925,
      "eval_runtime": 1.3297,
      "eval_samples_per_second": 30.082,
      "eval_steps_per_second": 15.041,
      "num_input_tokens_seen": 2744768,
      "step": 9800
    },
    {
      "epoch": 108.94444444444444,
      "grad_norm": 5.283362156660587e-07,
      "learning_rate": 4.294769087189354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2746144,
      "step": 9805
    },
    {
      "epoch": 109.0,
      "grad_norm": 2.0086281438125297e-06,
      "learning_rate": 4.294085516574052e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2747552,
      "step": 9810
    },
    {
      "epoch": 109.05555555555556,
      "grad_norm": 5.36753645974386e-07,
      "learning_rate": 4.2934016692882176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2748960,
      "step": 9815
    },
    {
      "epoch": 109.11111111111111,
      "grad_norm": 4.5290946104614704e-07,
      "learning_rate": 4.292717545437308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2750336,
      "step": 9820
    },
    {
      "epoch": 109.16666666666667,
      "grad_norm": 4.315671446875058e-07,
      "learning_rate": 4.292033145126825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2751728,
      "step": 9825
    },
    {
      "epoch": 109.22222222222223,
      "grad_norm": 1.5445878034370253e-06,
      "learning_rate": 4.29134846846231e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2753104,
      "step": 9830
    },
    {
      "epoch": 109.27777777777777,
      "grad_norm": 5.31307875917264e-07,
      "learning_rate": 4.29066351554935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2754496,
      "step": 9835
    },
    {
      "epoch": 109.33333333333333,
      "grad_norm": 5.279473498376319e-07,
      "learning_rate": 4.289978286493574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2755872,
      "step": 9840
    },
    {
      "epoch": 109.38888888888889,
      "grad_norm": 4.734381207072147e-07,
      "learning_rate": 4.28929278140065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2757312,
      "step": 9845
    },
    {
      "epoch": 109.44444444444444,
      "grad_norm": 5.735006993745628e-07,
      "learning_rate": 4.288607000376295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2758672,
      "step": 9850
    },
    {
      "epoch": 109.5,
      "grad_norm": 4.939888071930909e-07,
      "learning_rate": 4.2879209435262624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2760080,
      "step": 9855
    },
    {
      "epoch": 109.55555555555556,
      "grad_norm": 4.2514921005931683e-07,
      "learning_rate": 4.287234610956353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2761440,
      "step": 9860
    },
    {
      "epoch": 109.61111111111111,
      "grad_norm": 4.6094746153357846e-07,
      "learning_rate": 4.2865480027724056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2762832,
      "step": 9865
    },
    {
      "epoch": 109.66666666666667,
      "grad_norm": 4.946793978888309e-07,
      "learning_rate": 4.285861119080306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2764256,
      "step": 9870
    },
    {
      "epoch": 109.72222222222223,
      "grad_norm": 8.76948831773916e-07,
      "learning_rate": 4.2851739599859784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2765648,
      "step": 9875
    },
    {
      "epoch": 109.77777777777777,
      "grad_norm": 5.277369155010092e-07,
      "learning_rate": 4.2844865255953934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2767104,
      "step": 9880
    },
    {
      "epoch": 109.83333333333333,
      "grad_norm": 4.839133680434315e-07,
      "learning_rate": 4.2837988160145605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2768512,
      "step": 9885
    },
    {
      "epoch": 109.88888888888889,
      "grad_norm": 4.1041985809897596e-07,
      "learning_rate": 4.2831108313495336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2769904,
      "step": 9890
    },
    {
      "epoch": 109.94444444444444,
      "grad_norm": 4.972853844265046e-07,
      "learning_rate": 4.282422571706408e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2771312,
      "step": 9895
    },
    {
      "epoch": 110.0,
      "grad_norm": 4.946111857861979e-07,
      "learning_rate": 4.281734037191323e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2772736,
      "step": 9900
    },
    {
      "epoch": 110.05555555555556,
      "grad_norm": 5.03614330682467e-07,
      "learning_rate": 4.281045227910459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2774128,
      "step": 9905
    },
    {
      "epoch": 110.11111111111111,
      "grad_norm": 4.496091889905074e-07,
      "learning_rate": 4.280356143970038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2775520,
      "step": 9910
    },
    {
      "epoch": 110.16666666666667,
      "grad_norm": 5.538576601793466e-07,
      "learning_rate": 4.279666785476327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2776944,
      "step": 9915
    },
    {
      "epoch": 110.22222222222223,
      "grad_norm": 4.474087802464055e-07,
      "learning_rate": 4.2789771525356325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2778336,
      "step": 9920
    },
    {
      "epoch": 110.27777777777777,
      "grad_norm": 1.2274854270799551e-06,
      "learning_rate": 4.2782872452543056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2779760,
      "step": 9925
    },
    {
      "epoch": 110.33333333333333,
      "grad_norm": 5.276169758872129e-07,
      "learning_rate": 4.2775970637387376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2781152,
      "step": 9930
    },
    {
      "epoch": 110.38888888888889,
      "grad_norm": 1.0920762179011945e-06,
      "learning_rate": 4.276906608095363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2782544,
      "step": 9935
    },
    {
      "epoch": 110.44444444444444,
      "grad_norm": 2.3946356577653205e-06,
      "learning_rate": 4.276215878430661e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2783936,
      "step": 9940
    },
    {
      "epoch": 110.5,
      "grad_norm": 1.5087623523868388e-06,
      "learning_rate": 4.275524874851149e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2785328,
      "step": 9945
    },
    {
      "epoch": 110.55555555555556,
      "grad_norm": 3.812583031503891e-07,
      "learning_rate": 4.274833597463388e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2786736,
      "step": 9950
    },
    {
      "epoch": 110.61111111111111,
      "grad_norm": 1.2254585044502164e-06,
      "learning_rate": 4.2741420463739824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2788144,
      "step": 9955
    },
    {
      "epoch": 110.66666666666667,
      "grad_norm": 5.498023369909788e-07,
      "learning_rate": 4.273450221689578e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2789552,
      "step": 9960
    },
    {
      "epoch": 110.72222222222223,
      "grad_norm": 8.035258929339761e-07,
      "learning_rate": 4.272758123516863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2791008,
      "step": 9965
    },
    {
      "epoch": 110.77777777777777,
      "grad_norm": 4.4515499553199334e-07,
      "learning_rate": 4.272065751962567e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2792384,
      "step": 9970
    },
    {
      "epoch": 110.83333333333333,
      "grad_norm": 4.669058455419872e-07,
      "learning_rate": 4.271373107133464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2793760,
      "step": 9975
    },
    {
      "epoch": 110.88888888888889,
      "grad_norm": 1.1850412420244538e-06,
      "learning_rate": 4.270680189136366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2795184,
      "step": 9980
    },
    {
      "epoch": 110.94444444444444,
      "grad_norm": 1.1333381735312287e-06,
      "learning_rate": 4.269986998078132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2796560,
      "step": 9985
    },
    {
      "epoch": 111.0,
      "grad_norm": 7.785646403135615e-07,
      "learning_rate": 4.2692935340656595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2797952,
      "step": 9990
    },
    {
      "epoch": 111.05555555555556,
      "grad_norm": 5.446843829304271e-07,
      "learning_rate": 4.26859979720589e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2799344,
      "step": 9995
    },
    {
      "epoch": 111.11111111111111,
      "grad_norm": 4.695605468896247e-07,
      "learning_rate": 4.267905787605806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2800768,
      "step": 10000
    },
    {
      "epoch": 111.11111111111111,
      "eval_loss": 0.34467577934265137,
      "eval_runtime": 1.3085,
      "eval_samples_per_second": 30.569,
      "eval_steps_per_second": 15.285,
      "num_input_tokens_seen": 2800768,
      "step": 10000
    },
    {
      "epoch": 111.16666666666667,
      "grad_norm": 4.769856900566083e-07,
      "learning_rate": 4.267211505372433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2802160,
      "step": 10005
    },
    {
      "epoch": 111.22222222222223,
      "grad_norm": 1.1432942983446992e-06,
      "learning_rate": 4.266516950612837e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2803536,
      "step": 10010
    },
    {
      "epoch": 111.27777777777777,
      "grad_norm": 5.131090574650443e-07,
      "learning_rate": 4.265822123434128e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2804928,
      "step": 10015
    },
    {
      "epoch": 111.33333333333333,
      "grad_norm": 5.422446633929212e-07,
      "learning_rate": 4.265127023943457e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2806336,
      "step": 10020
    },
    {
      "epoch": 111.38888888888889,
      "grad_norm": 1.4769623248866992e-06,
      "learning_rate": 4.2644316522480176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2807744,
      "step": 10025
    },
    {
      "epoch": 111.44444444444444,
      "grad_norm": 4.753303528559627e-07,
      "learning_rate": 4.263736008455044e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2809120,
      "step": 10030
    },
    {
      "epoch": 111.5,
      "grad_norm": 8.407885161432205e-07,
      "learning_rate": 4.2630400926718125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2810512,
      "step": 10035
    },
    {
      "epoch": 111.55555555555556,
      "grad_norm": 5.613505322799028e-07,
      "learning_rate": 4.262343905005644e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2811920,
      "step": 10040
    },
    {
      "epoch": 111.61111111111111,
      "grad_norm": 4.917676506011048e-07,
      "learning_rate": 4.261647445563897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2813376,
      "step": 10045
    },
    {
      "epoch": 111.66666666666667,
      "grad_norm": 5.608927722278167e-07,
      "learning_rate": 4.260950714453976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2814784,
      "step": 10050
    },
    {
      "epoch": 111.72222222222223,
      "grad_norm": 9.997098686653771e-07,
      "learning_rate": 4.2602537117833266e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2816208,
      "step": 10055
    },
    {
      "epoch": 111.77777777777777,
      "grad_norm": 5.778010745416395e-07,
      "learning_rate": 4.259556437659433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2817584,
      "step": 10060
    },
    {
      "epoch": 111.83333333333333,
      "grad_norm": 9.869272616924718e-07,
      "learning_rate": 4.258858892189825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2819008,
      "step": 10065
    },
    {
      "epoch": 111.88888888888889,
      "grad_norm": 5.169713404029608e-07,
      "learning_rate": 4.2581610754820725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2820368,
      "step": 10070
    },
    {
      "epoch": 111.94444444444444,
      "grad_norm": 4.47121294655517e-07,
      "learning_rate": 4.2574629876437876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2821776,
      "step": 10075
    },
    {
      "epoch": 112.0,
      "grad_norm": 5.722410492126073e-07,
      "learning_rate": 4.256764628782625e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2823184,
      "step": 10080
    },
    {
      "epoch": 112.05555555555556,
      "grad_norm": 1.2312059425312327e-06,
      "learning_rate": 4.256065999006279e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2824528,
      "step": 10085
    },
    {
      "epoch": 112.11111111111111,
      "grad_norm": 5.604737225439749e-07,
      "learning_rate": 4.2553670984224885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2825952,
      "step": 10090
    },
    {
      "epoch": 112.16666666666667,
      "grad_norm": 9.963205229723826e-07,
      "learning_rate": 4.254667927139032e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2827376,
      "step": 10095
    },
    {
      "epoch": 112.22222222222223,
      "grad_norm": 4.900254566564399e-07,
      "learning_rate": 4.2539684852637295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2828752,
      "step": 10100
    },
    {
      "epoch": 112.27777777777777,
      "grad_norm": 4.005845539722941e-07,
      "learning_rate": 4.253268772904446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2830176,
      "step": 10105
    },
    {
      "epoch": 112.33333333333333,
      "grad_norm": 4.881588324678887e-07,
      "learning_rate": 4.252568790169085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2831584,
      "step": 10110
    },
    {
      "epoch": 112.38888888888889,
      "grad_norm": 5.139493168826448e-07,
      "learning_rate": 4.251868537165592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2832992,
      "step": 10115
    },
    {
      "epoch": 112.44444444444444,
      "grad_norm": 5.028510940974229e-07,
      "learning_rate": 4.251168014001955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2834400,
      "step": 10120
    },
    {
      "epoch": 112.5,
      "grad_norm": 6.425049150493578e-07,
      "learning_rate": 4.250467220786204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2835744,
      "step": 10125
    },
    {
      "epoch": 112.55555555555556,
      "grad_norm": 3.9404821450261807e-07,
      "learning_rate": 4.249766157626409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2837168,
      "step": 10130
    },
    {
      "epoch": 112.61111111111111,
      "grad_norm": 5.154988116373715e-07,
      "learning_rate": 4.249064824630684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2838528,
      "step": 10135
    },
    {
      "epoch": 112.66666666666667,
      "grad_norm": 5.409428922575898e-07,
      "learning_rate": 4.248363221907183e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2839888,
      "step": 10140
    },
    {
      "epoch": 112.72222222222223,
      "grad_norm": 1.2890834568679566e-06,
      "learning_rate": 4.2476613495641026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2841248,
      "step": 10145
    },
    {
      "epoch": 112.77777777777777,
      "grad_norm": 5.200110990699613e-07,
      "learning_rate": 4.246959207709679e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2842688,
      "step": 10150
    },
    {
      "epoch": 112.83333333333333,
      "grad_norm": 4.886297801931505e-07,
      "learning_rate": 4.246256796452192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2844064,
      "step": 10155
    },
    {
      "epoch": 112.88888888888889,
      "grad_norm": 3.9894496239867294e-07,
      "learning_rate": 4.245554115899962e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2845440,
      "step": 10160
    },
    {
      "epoch": 112.94444444444444,
      "grad_norm": 4.915106046610163e-07,
      "learning_rate": 4.2448511661613514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2846800,
      "step": 10165
    },
    {
      "epoch": 113.0,
      "grad_norm": 4.5393906589197286e-07,
      "learning_rate": 4.2441479473447635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2848256,
      "step": 10170
    },
    {
      "epoch": 113.05555555555556,
      "grad_norm": 4.6087285454632365e-07,
      "learning_rate": 4.243444459558644e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2849584,
      "step": 10175
    },
    {
      "epoch": 113.11111111111111,
      "grad_norm": 5.494917445503233e-07,
      "learning_rate": 4.24274070291148e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2850992,
      "step": 10180
    },
    {
      "epoch": 113.16666666666667,
      "grad_norm": 5.118502031109529e-07,
      "learning_rate": 4.242036677511798e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2852464,
      "step": 10185
    },
    {
      "epoch": 113.22222222222223,
      "grad_norm": 4.4442586499826575e-07,
      "learning_rate": 4.241332383468169e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2853904,
      "step": 10190
    },
    {
      "epoch": 113.27777777777777,
      "grad_norm": 4.493082883527677e-07,
      "learning_rate": 4.2406278208892034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2855344,
      "step": 10195
    },
    {
      "epoch": 113.33333333333333,
      "grad_norm": 5.255591872810328e-07,
      "learning_rate": 4.2399229898835536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2856768,
      "step": 10200
    },
    {
      "epoch": 113.33333333333333,
      "eval_loss": 0.32345396280288696,
      "eval_runtime": 1.3219,
      "eval_samples_per_second": 30.26,
      "eval_steps_per_second": 15.13,
      "num_input_tokens_seen": 2856768,
      "step": 10200
    },
    {
      "epoch": 113.38888888888889,
      "grad_norm": 4.853827704209834e-07,
      "learning_rate": 4.239217890559914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2858144,
      "step": 10205
    },
    {
      "epoch": 113.44444444444444,
      "grad_norm": 1.1978900147369131e-06,
      "learning_rate": 4.238512523027019e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2859504,
      "step": 10210
    },
    {
      "epoch": 113.5,
      "grad_norm": 5.749012643718743e-07,
      "learning_rate": 4.237806887393645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2860896,
      "step": 10215
    },
    {
      "epoch": 113.55555555555556,
      "grad_norm": 1.8509673509470304e-06,
      "learning_rate": 4.237100983768611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2862304,
      "step": 10220
    },
    {
      "epoch": 113.61111111111111,
      "grad_norm": 1.1358205256328802e-06,
      "learning_rate": 4.2363948122607756e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2863712,
      "step": 10225
    },
    {
      "epoch": 113.66666666666667,
      "grad_norm": 5.664863920173957e-07,
      "learning_rate": 4.235688372979039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2865072,
      "step": 10230
    },
    {
      "epoch": 113.72222222222223,
      "grad_norm": 1.540352172924031e-06,
      "learning_rate": 4.234981666032343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2866464,
      "step": 10235
    },
    {
      "epoch": 113.77777777777777,
      "grad_norm": 1.1929050742764957e-06,
      "learning_rate": 4.2342746915296704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2867824,
      "step": 10240
    },
    {
      "epoch": 113.83333333333333,
      "grad_norm": 1.5436942248925334e-06,
      "learning_rate": 4.233567449580047e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2869200,
      "step": 10245
    },
    {
      "epoch": 113.88888888888889,
      "grad_norm": 1.0344429028918967e-06,
      "learning_rate": 4.232859940292537e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2870592,
      "step": 10250
    },
    {
      "epoch": 113.94444444444444,
      "grad_norm": 4.3270674154882727e-07,
      "learning_rate": 4.232152163776248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2872032,
      "step": 10255
    },
    {
      "epoch": 114.0,
      "grad_norm": 4.6343197368514666e-07,
      "learning_rate": 4.231444120140328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2873424,
      "step": 10260
    },
    {
      "epoch": 114.05555555555556,
      "grad_norm": 1.1542441598066944e-06,
      "learning_rate": 4.230735809493967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2874784,
      "step": 10265
    },
    {
      "epoch": 114.11111111111111,
      "grad_norm": 4.7275662495849247e-07,
      "learning_rate": 4.2300272319463926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2876160,
      "step": 10270
    },
    {
      "epoch": 114.16666666666667,
      "grad_norm": 3.8183537753866403e-07,
      "learning_rate": 4.2293183876068786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2877600,
      "step": 10275
    },
    {
      "epoch": 114.22222222222223,
      "grad_norm": 4.445607828529319e-07,
      "learning_rate": 4.228609276584737e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2878976,
      "step": 10280
    },
    {
      "epoch": 114.27777777777777,
      "grad_norm": 4.6796219521638704e-07,
      "learning_rate": 4.227899898989323e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2880320,
      "step": 10285
    },
    {
      "epoch": 114.33333333333333,
      "grad_norm": 3.706715858697862e-07,
      "learning_rate": 4.2271902549300293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2881712,
      "step": 10290
    },
    {
      "epoch": 114.38888888888889,
      "grad_norm": 4.51076260787886e-07,
      "learning_rate": 4.226480344516294e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2883104,
      "step": 10295
    },
    {
      "epoch": 114.44444444444444,
      "grad_norm": 4.2071462758030975e-07,
      "learning_rate": 4.2257701678575925e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2884544,
      "step": 10300
    },
    {
      "epoch": 114.5,
      "grad_norm": 5.901736699343019e-07,
      "learning_rate": 4.225059725063444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2885952,
      "step": 10305
    },
    {
      "epoch": 114.55555555555556,
      "grad_norm": 4.201429533168266e-07,
      "learning_rate": 4.2243490162434074e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2887360,
      "step": 10310
    },
    {
      "epoch": 114.61111111111111,
      "grad_norm": 4.875963099948422e-07,
      "learning_rate": 4.223638041507083e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2888736,
      "step": 10315
    },
    {
      "epoch": 114.66666666666667,
      "grad_norm": 4.3352420675546455e-07,
      "learning_rate": 4.2229268009641124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2890176,
      "step": 10320
    },
    {
      "epoch": 114.72222222222223,
      "grad_norm": 4.2284037249373796e-07,
      "learning_rate": 4.222215294724177e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2891584,
      "step": 10325
    },
    {
      "epoch": 114.77777777777777,
      "grad_norm": 4.1151113805426576e-07,
      "learning_rate": 4.2215035228970005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2892992,
      "step": 10330
    },
    {
      "epoch": 114.83333333333333,
      "grad_norm": 5.382938184084196e-07,
      "learning_rate": 4.2207914855923464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2894400,
      "step": 10335
    },
    {
      "epoch": 114.88888888888889,
      "grad_norm": 5.864654326614982e-07,
      "learning_rate": 4.220079182920021e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2895840,
      "step": 10340
    },
    {
      "epoch": 114.94444444444444,
      "grad_norm": 1.462821387576696e-06,
      "learning_rate": 4.2193666149898705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2897264,
      "step": 10345
    },
    {
      "epoch": 115.0,
      "grad_norm": 5.616774956251902e-07,
      "learning_rate": 4.21865378191178e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2898624,
      "step": 10350
    },
    {
      "epoch": 115.05555555555556,
      "grad_norm": 2.254808578072698e-06,
      "learning_rate": 4.217940683795678e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2900032,
      "step": 10355
    },
    {
      "epoch": 115.11111111111111,
      "grad_norm": 7.852564181121124e-07,
      "learning_rate": 4.217227320751534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2901376,
      "step": 10360
    },
    {
      "epoch": 115.16666666666667,
      "grad_norm": 4.7612508069505566e-07,
      "learning_rate": 4.216513692889358e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2902784,
      "step": 10365
    },
    {
      "epoch": 115.22222222222223,
      "grad_norm": 4.3507736791070784e-07,
      "learning_rate": 4.215799800319199e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2904160,
      "step": 10370
    },
    {
      "epoch": 115.27777777777777,
      "grad_norm": 4.061270999500266e-07,
      "learning_rate": 4.2150856431511485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2905552,
      "step": 10375
    },
    {
      "epoch": 115.33333333333333,
      "grad_norm": 4.4118417008576216e-07,
      "learning_rate": 4.214371221495339e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2906960,
      "step": 10380
    },
    {
      "epoch": 115.38888888888889,
      "grad_norm": 9.215274303642218e-07,
      "learning_rate": 4.213656535461942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2908400,
      "step": 10385
    },
    {
      "epoch": 115.44444444444444,
      "grad_norm": 1.4709352171848877e-06,
      "learning_rate": 4.2129415851611734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2909840,
      "step": 10390
    },
    {
      "epoch": 115.5,
      "grad_norm": 4.422768142831046e-07,
      "learning_rate": 4.2122263707032855e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2911232,
      "step": 10395
    },
    {
      "epoch": 115.55555555555556,
      "grad_norm": 4.3281281136842154e-07,
      "learning_rate": 4.211510892198574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2912640,
      "step": 10400
    },
    {
      "epoch": 115.55555555555556,
      "eval_loss": 0.3244749903678894,
      "eval_runtime": 1.3135,
      "eval_samples_per_second": 30.454,
      "eval_steps_per_second": 15.227,
      "num_input_tokens_seen": 2912640,
      "step": 10400
    },
    {
      "epoch": 115.61111111111111,
      "grad_norm": 5.357044301490532e-07,
      "learning_rate": 4.210795149757375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2914080,
      "step": 10405
    },
    {
      "epoch": 115.66666666666667,
      "grad_norm": 1.0243813903798582e-06,
      "learning_rate": 4.210079143490065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2915472,
      "step": 10410
    },
    {
      "epoch": 115.72222222222223,
      "grad_norm": 1.0406866977064055e-06,
      "learning_rate": 4.2093628735070604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2916864,
      "step": 10415
    },
    {
      "epoch": 115.77777777777777,
      "grad_norm": 4.895285883321776e-07,
      "learning_rate": 4.208646339918819e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2918256,
      "step": 10420
    },
    {
      "epoch": 115.83333333333333,
      "grad_norm": 4.7657161417191674e-07,
      "learning_rate": 4.2079295428358414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2919664,
      "step": 10425
    },
    {
      "epoch": 115.88888888888889,
      "grad_norm": 1.2215077731525525e-06,
      "learning_rate": 4.207212482368664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2921056,
      "step": 10430
    },
    {
      "epoch": 115.94444444444444,
      "grad_norm": 5.042341513217252e-07,
      "learning_rate": 4.206495158627867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2922480,
      "step": 10435
    },
    {
      "epoch": 116.0,
      "grad_norm": 1.1144925338157918e-06,
      "learning_rate": 4.205777571724073e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2923856,
      "step": 10440
    },
    {
      "epoch": 116.05555555555556,
      "grad_norm": 4.90593492941116e-07,
      "learning_rate": 4.20505972176794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2925296,
      "step": 10445
    },
    {
      "epoch": 116.11111111111111,
      "grad_norm": 2.6988566332875052e-06,
      "learning_rate": 4.204341608870171e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2926704,
      "step": 10450
    },
    {
      "epoch": 116.16666666666667,
      "grad_norm": 9.844673058978515e-07,
      "learning_rate": 4.203623233141508e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2928160,
      "step": 10455
    },
    {
      "epoch": 116.22222222222223,
      "grad_norm": 4.268653128747246e-07,
      "learning_rate": 4.2029045946927334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2929600,
      "step": 10460
    },
    {
      "epoch": 116.27777777777777,
      "grad_norm": 4.90186323531816e-07,
      "learning_rate": 4.20218569363467e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2931024,
      "step": 10465
    },
    {
      "epoch": 116.33333333333333,
      "grad_norm": 9.803945886233123e-07,
      "learning_rate": 4.2014665300781834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2932368,
      "step": 10470
    },
    {
      "epoch": 116.38888888888889,
      "grad_norm": 4.7052046170392714e-07,
      "learning_rate": 4.200747104134174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2933728,
      "step": 10475
    },
    {
      "epoch": 116.44444444444444,
      "grad_norm": 4.670378928040009e-07,
      "learning_rate": 4.200027415913588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2935104,
      "step": 10480
    },
    {
      "epoch": 116.5,
      "grad_norm": 3.9290296172111994e-07,
      "learning_rate": 4.1993074655274126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2936528,
      "step": 10485
    },
    {
      "epoch": 116.55555555555556,
      "grad_norm": 1.3398946521192556e-06,
      "learning_rate": 4.198587253086669e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2937888,
      "step": 10490
    },
    {
      "epoch": 116.61111111111111,
      "grad_norm": 4.6162125499904505e-07,
      "learning_rate": 4.197866778702426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2939264,
      "step": 10495
    },
    {
      "epoch": 116.66666666666667,
      "grad_norm": 1.0794568652272574e-06,
      "learning_rate": 4.197146042485789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2940640,
      "step": 10500
    },
    {
      "epoch": 116.72222222222223,
      "grad_norm": 5.416708859229402e-07,
      "learning_rate": 4.1964250445479046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2942048,
      "step": 10505
    },
    {
      "epoch": 116.77777777777777,
      "grad_norm": 9.742487918629195e-07,
      "learning_rate": 4.19570378499996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2943456,
      "step": 10510
    },
    {
      "epoch": 116.83333333333333,
      "grad_norm": 4.919881462228659e-07,
      "learning_rate": 4.194982263953182e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2944896,
      "step": 10515
    },
    {
      "epoch": 116.88888888888889,
      "grad_norm": 1.3058795502729481e-06,
      "learning_rate": 4.194260481518838e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2946288,
      "step": 10520
    },
    {
      "epoch": 116.94444444444444,
      "grad_norm": 1.2270397746760864e-06,
      "learning_rate": 4.1935384378082366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2947680,
      "step": 10525
    },
    {
      "epoch": 117.0,
      "grad_norm": 1.1007747389157885e-06,
      "learning_rate": 4.1928161329327267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2949120,
      "step": 10530
    },
    {
      "epoch": 117.05555555555556,
      "grad_norm": 4.7136327907537634e-07,
      "learning_rate": 4.1920935670036945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2950512,
      "step": 10535
    },
    {
      "epoch": 117.11111111111111,
      "grad_norm": 4.2697834601312934e-07,
      "learning_rate": 4.1913707401325705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2951952,
      "step": 10540
    },
    {
      "epoch": 117.16666666666667,
      "grad_norm": 4.205316201932874e-07,
      "learning_rate": 4.1906476524308235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2953344,
      "step": 10545
    },
    {
      "epoch": 117.22222222222223,
      "grad_norm": 1.471515020057268e-06,
      "learning_rate": 4.189924304009962e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2954720,
      "step": 10550
    },
    {
      "epoch": 117.27777777777777,
      "grad_norm": 4.102518857962423e-07,
      "learning_rate": 4.189200694981537e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2956128,
      "step": 10555
    },
    {
      "epoch": 117.33333333333333,
      "grad_norm": 4.909260837848706e-07,
      "learning_rate": 4.188476825457136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2957488,
      "step": 10560
    },
    {
      "epoch": 117.38888888888889,
      "grad_norm": 4.0639974940859247e-07,
      "learning_rate": 4.18775269554839e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2958944,
      "step": 10565
    },
    {
      "epoch": 117.44444444444444,
      "grad_norm": 4.849412107432727e-07,
      "learning_rate": 4.187028305366969e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2960352,
      "step": 10570
    },
    {
      "epoch": 117.5,
      "grad_norm": 4.529562431798695e-07,
      "learning_rate": 4.1863036550245824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2961792,
      "step": 10575
    },
    {
      "epoch": 117.55555555555556,
      "grad_norm": 5.008870402889443e-07,
      "learning_rate": 4.1855787446329806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2963200,
      "step": 10580
    },
    {
      "epoch": 117.61111111111111,
      "grad_norm": 4.999845373276912e-07,
      "learning_rate": 4.184853574303955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2964624,
      "step": 10585
    },
    {
      "epoch": 117.66666666666667,
      "grad_norm": 1.0631689519868814e-06,
      "learning_rate": 4.184128144149334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2966048,
      "step": 10590
    },
    {
      "epoch": 117.72222222222223,
      "grad_norm": 5.284633743940503e-07,
      "learning_rate": 4.1834024542809896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2967456,
      "step": 10595
    },
    {
      "epoch": 117.77777777777777,
      "grad_norm": 4.844314958063478e-07,
      "learning_rate": 4.1826765048108315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2968832,
      "step": 10600
    },
    {
      "epoch": 117.77777777777777,
      "eval_loss": 0.3207324147224426,
      "eval_runtime": 1.3023,
      "eval_samples_per_second": 30.714,
      "eval_steps_per_second": 15.357,
      "num_input_tokens_seen": 2968832,
      "step": 10600
    },
    {
      "epoch": 117.83333333333333,
      "grad_norm": 4.437775089627394e-07,
      "learning_rate": 4.181950295850811e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2970240,
      "step": 10605
    },
    {
      "epoch": 117.88888888888889,
      "grad_norm": 2.479996965121245e-06,
      "learning_rate": 4.181223827512918e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2971616,
      "step": 10610
    },
    {
      "epoch": 117.94444444444444,
      "grad_norm": 3.7882225569774164e-06,
      "learning_rate": 4.180497099909183e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2973040,
      "step": 10615
    },
    {
      "epoch": 118.0,
      "grad_norm": 1.991079443541821e-06,
      "learning_rate": 4.179770113151677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2974416,
      "step": 10620
    },
    {
      "epoch": 118.05555555555556,
      "grad_norm": 3.95799389707463e-07,
      "learning_rate": 4.179042867352511e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2975872,
      "step": 10625
    },
    {
      "epoch": 118.11111111111111,
      "grad_norm": 4.910885422759748e-07,
      "learning_rate": 4.1783153626238334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2977232,
      "step": 10630
    },
    {
      "epoch": 118.16666666666667,
      "grad_norm": 4.4187498815517756e-07,
      "learning_rate": 4.177587599077836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2978624,
      "step": 10635
    },
    {
      "epoch": 118.22222222222223,
      "grad_norm": 5.4159255569175e-07,
      "learning_rate": 4.1768595768267494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2980048,
      "step": 10640
    },
    {
      "epoch": 118.27777777777777,
      "grad_norm": 1.357480641672737e-06,
      "learning_rate": 4.176131295982843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2981456,
      "step": 10645
    },
    {
      "epoch": 118.33333333333333,
      "grad_norm": 4.1029721842278377e-07,
      "learning_rate": 4.1754027566584276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2982816,
      "step": 10650
    },
    {
      "epoch": 118.38888888888889,
      "grad_norm": 4.915730755783443e-07,
      "learning_rate": 4.174673958965852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2984240,
      "step": 10655
    },
    {
      "epoch": 118.44444444444444,
      "grad_norm": 5.126885866957309e-07,
      "learning_rate": 4.173944903017507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2985664,
      "step": 10660
    },
    {
      "epoch": 118.5,
      "grad_norm": 9.73376245383406e-07,
      "learning_rate": 4.173215588925822e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2987072,
      "step": 10665
    },
    {
      "epoch": 118.55555555555556,
      "grad_norm": 4.994582809558779e-07,
      "learning_rate": 4.172486016803266e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2988480,
      "step": 10670
    },
    {
      "epoch": 118.61111111111111,
      "grad_norm": 4.6185672886167595e-07,
      "learning_rate": 4.171756186762349e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2989952,
      "step": 10675
    },
    {
      "epoch": 118.66666666666667,
      "grad_norm": 4.517594334174646e-07,
      "learning_rate": 4.171026098915619e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2991344,
      "step": 10680
    },
    {
      "epoch": 118.72222222222223,
      "grad_norm": 1.2842648402511259e-06,
      "learning_rate": 4.170295753375665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2992736,
      "step": 10685
    },
    {
      "epoch": 118.77777777777777,
      "grad_norm": 3.560726042906026e-07,
      "learning_rate": 4.169565150255117e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2994144,
      "step": 10690
    },
    {
      "epoch": 118.83333333333333,
      "grad_norm": 4.1164349795508315e-07,
      "learning_rate": 4.16883428966664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2995504,
      "step": 10695
    },
    {
      "epoch": 118.88888888888889,
      "grad_norm": 4.1045899479286163e-07,
      "learning_rate": 4.168103171722944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2996896,
      "step": 10700
    },
    {
      "epoch": 118.94444444444444,
      "grad_norm": 4.646163063171116e-07,
      "learning_rate": 4.167371796536777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2998288,
      "step": 10705
    },
    {
      "epoch": 119.0,
      "grad_norm": 4.0977630533234333e-07,
      "learning_rate": 4.166640164220924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 2999664,
      "step": 10710
    },
    {
      "epoch": 119.05555555555556,
      "grad_norm": 2.913630169132375e-06,
      "learning_rate": 4.1659082748882144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3001056,
      "step": 10715
    },
    {
      "epoch": 119.11111111111111,
      "grad_norm": 1.1410922979848692e-06,
      "learning_rate": 4.1651761286515135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3002464,
      "step": 10720
    },
    {
      "epoch": 119.16666666666667,
      "grad_norm": 5.08619052652648e-07,
      "learning_rate": 4.164443725623728e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3003856,
      "step": 10725
    },
    {
      "epoch": 119.22222222222223,
      "grad_norm": 1.3157953162590275e-06,
      "learning_rate": 4.163711065917802e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3005280,
      "step": 10730
    },
    {
      "epoch": 119.27777777777777,
      "grad_norm": 4.3842339891853044e-07,
      "learning_rate": 4.1629781496467234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3006672,
      "step": 10735
    },
    {
      "epoch": 119.33333333333333,
      "grad_norm": 4.081444728853967e-07,
      "learning_rate": 4.1622449769235164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3008096,
      "step": 10740
    },
    {
      "epoch": 119.38888888888889,
      "grad_norm": 4.770932378050929e-07,
      "learning_rate": 4.161511547861243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3009536,
      "step": 10745
    },
    {
      "epoch": 119.44444444444444,
      "grad_norm": 4.813355189980939e-07,
      "learning_rate": 4.1607778625730104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3010896,
      "step": 10750
    },
    {
      "epoch": 119.5,
      "grad_norm": 4.513946691986348e-07,
      "learning_rate": 4.160043921171961e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3012256,
      "step": 10755
    },
    {
      "epoch": 119.55555555555556,
      "grad_norm": 2.8632582598220324e-06,
      "learning_rate": 4.159309723771276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3013632,
      "step": 10760
    },
    {
      "epoch": 119.61111111111111,
      "grad_norm": 4.74134083106037e-07,
      "learning_rate": 4.158575270484181e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3015056,
      "step": 10765
    },
    {
      "epoch": 119.66666666666667,
      "grad_norm": 4.4873755200569576e-07,
      "learning_rate": 4.157840561423936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3016496,
      "step": 10770
    },
    {
      "epoch": 119.72222222222223,
      "grad_norm": 7.122798706404865e-07,
      "learning_rate": 4.1571055967038416e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3017904,
      "step": 10775
    },
    {
      "epoch": 119.77777777777777,
      "grad_norm": 1.4974226587582962e-06,
      "learning_rate": 4.156370376437241e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3019280,
      "step": 10780
    },
    {
      "epoch": 119.83333333333333,
      "grad_norm": 4.0401579326498904e-07,
      "learning_rate": 4.155634900737513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3020720,
      "step": 10785
    },
    {
      "epoch": 119.88888888888889,
      "grad_norm": 5.699571374861989e-07,
      "learning_rate": 4.1548991697180764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3022064,
      "step": 10790
    },
    {
      "epoch": 119.94444444444444,
      "grad_norm": 4.710798293672269e-07,
      "learning_rate": 4.1541631834923914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3023488,
      "step": 10795
    },
    {
      "epoch": 120.0,
      "grad_norm": 1.5061517615322373e-06,
      "learning_rate": 4.153426942173956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3024896,
      "step": 10800
    },
    {
      "epoch": 120.0,
      "eval_loss": 0.28891822695732117,
      "eval_runtime": 1.2918,
      "eval_samples_per_second": 30.966,
      "eval_steps_per_second": 15.483,
      "num_input_tokens_seen": 3024896,
      "step": 10800
    },
    {
      "epoch": 120.05555555555556,
      "grad_norm": 4.571966201183386e-07,
      "learning_rate": 4.152690445876308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3026320,
      "step": 10805
    },
    {
      "epoch": 120.11111111111111,
      "grad_norm": 4.5374648038887244e-07,
      "learning_rate": 4.1519536947130245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3027696,
      "step": 10810
    },
    {
      "epoch": 120.16666666666667,
      "grad_norm": 9.869810355667141e-07,
      "learning_rate": 4.151216688797722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3029136,
      "step": 10815
    },
    {
      "epoch": 120.22222222222223,
      "grad_norm": 1.0414687494630925e-06,
      "learning_rate": 4.150479428244054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3030608,
      "step": 10820
    },
    {
      "epoch": 120.27777777777777,
      "grad_norm": 5.154905693416367e-07,
      "learning_rate": 4.1497419131657176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3032016,
      "step": 10825
    },
    {
      "epoch": 120.33333333333333,
      "grad_norm": 1.0169297866013949e-06,
      "learning_rate": 4.149004143676447e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3033456,
      "step": 10830
    },
    {
      "epoch": 120.38888888888889,
      "grad_norm": 5.743987685491447e-07,
      "learning_rate": 4.148266119890015e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3034912,
      "step": 10835
    },
    {
      "epoch": 120.44444444444444,
      "grad_norm": 4.755759164254414e-07,
      "learning_rate": 4.1475278419202324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3036352,
      "step": 10840
    },
    {
      "epoch": 120.5,
      "grad_norm": 1.2930279353895457e-06,
      "learning_rate": 4.146789309880953e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3037712,
      "step": 10845
    },
    {
      "epoch": 120.55555555555556,
      "grad_norm": 1.1676611393340863e-06,
      "learning_rate": 4.146050523886068e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3039120,
      "step": 10850
    },
    {
      "epoch": 120.61111111111111,
      "grad_norm": 4.4599886450669146e-07,
      "learning_rate": 4.1453114840495055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3040512,
      "step": 10855
    },
    {
      "epoch": 120.66666666666667,
      "grad_norm": 3.896230680311419e-07,
      "learning_rate": 4.1445721904852364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3041984,
      "step": 10860
    },
    {
      "epoch": 120.72222222222223,
      "grad_norm": 4.0484422925146646e-07,
      "learning_rate": 4.143832643307269e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3043392,
      "step": 10865
    },
    {
      "epoch": 120.77777777777777,
      "grad_norm": 4.3677076178028074e-07,
      "learning_rate": 4.1430928426296503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3044752,
      "step": 10870
    },
    {
      "epoch": 120.83333333333333,
      "grad_norm": 3.8897286458450253e-07,
      "learning_rate": 4.142352788566466e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3046096,
      "step": 10875
    },
    {
      "epoch": 120.88888888888889,
      "grad_norm": 4.591079232341144e-07,
      "learning_rate": 4.1416124812318424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3047440,
      "step": 10880
    },
    {
      "epoch": 120.94444444444444,
      "grad_norm": 4.6111412643767835e-07,
      "learning_rate": 4.1408719207399453e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3048848,
      "step": 10885
    },
    {
      "epoch": 121.0,
      "grad_norm": 3.8983654349067365e-07,
      "learning_rate": 4.140131107204978e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3050240,
      "step": 10890
    },
    {
      "epoch": 121.05555555555556,
      "grad_norm": 4.281766337044246e-07,
      "learning_rate": 4.139390040741182e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3051616,
      "step": 10895
    },
    {
      "epoch": 121.11111111111111,
      "grad_norm": 4.266216819814872e-07,
      "learning_rate": 4.1386487214628396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3053008,
      "step": 10900
    },
    {
      "epoch": 121.16666666666667,
      "grad_norm": 2.7623068490356673e-06,
      "learning_rate": 4.137907149484272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3054384,
      "step": 10905
    },
    {
      "epoch": 121.22222222222223,
      "grad_norm": 6.102372367422504e-07,
      "learning_rate": 4.137165324919839e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3055776,
      "step": 10910
    },
    {
      "epoch": 121.27777777777777,
      "grad_norm": 4.7196107288982603e-07,
      "learning_rate": 4.136423247883939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3057168,
      "step": 10915
    },
    {
      "epoch": 121.33333333333333,
      "grad_norm": 4.5131383785701473e-07,
      "learning_rate": 4.135680918491009e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3058608,
      "step": 10920
    },
    {
      "epoch": 121.38888888888889,
      "grad_norm": 4.3033776364609366e-07,
      "learning_rate": 4.1349383368555265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3060000,
      "step": 10925
    },
    {
      "epoch": 121.44444444444444,
      "grad_norm": 5.431240310826979e-07,
      "learning_rate": 4.1341955030920065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3061408,
      "step": 10930
    },
    {
      "epoch": 121.5,
      "grad_norm": 1.3706678601010935e-06,
      "learning_rate": 4.1334524173150036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3062768,
      "step": 10935
    },
    {
      "epoch": 121.55555555555556,
      "grad_norm": 4.144145009377098e-07,
      "learning_rate": 4.13270907963911e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3064176,
      "step": 10940
    },
    {
      "epoch": 121.61111111111111,
      "grad_norm": 5.187557121644204e-07,
      "learning_rate": 4.131965490178959e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3065552,
      "step": 10945
    },
    {
      "epoch": 121.66666666666667,
      "grad_norm": 9.7905194706982e-07,
      "learning_rate": 4.131221649049222e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3066960,
      "step": 10950
    },
    {
      "epoch": 121.72222222222223,
      "grad_norm": 4.5308735252547194e-07,
      "learning_rate": 4.130477556364606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3068368,
      "step": 10955
    },
    {
      "epoch": 121.77777777777777,
      "grad_norm": 8.882668112164538e-07,
      "learning_rate": 4.129733212239861e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3069744,
      "step": 10960
    },
    {
      "epoch": 121.83333333333333,
      "grad_norm": 4.824948973691789e-07,
      "learning_rate": 4.128988616789774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3071168,
      "step": 10965
    },
    {
      "epoch": 121.88888888888889,
      "grad_norm": 5.77175228499982e-07,
      "learning_rate": 4.1282437701291724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3072576,
      "step": 10970
    },
    {
      "epoch": 121.94444444444444,
      "grad_norm": 9.597438292985316e-07,
      "learning_rate": 4.1274986723729184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3073968,
      "step": 10975
    },
    {
      "epoch": 122.0,
      "grad_norm": 5.312363100529183e-07,
      "learning_rate": 4.126753323635917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3075392,
      "step": 10980
    },
    {
      "epoch": 122.05555555555556,
      "grad_norm": 5.007853474126023e-07,
      "learning_rate": 4.12600772403311e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3076800,
      "step": 10985
    },
    {
      "epoch": 122.11111111111111,
      "grad_norm": 3.9835660459175415e-07,
      "learning_rate": 4.125261873679479e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3078256,
      "step": 10990
    },
    {
      "epoch": 122.16666666666667,
      "grad_norm": 4.524364101143874e-07,
      "learning_rate": 4.124515772690042e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3079680,
      "step": 10995
    },
    {
      "epoch": 122.22222222222223,
      "grad_norm": 4.6833977762616996e-07,
      "learning_rate": 4.123769421179858e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3081056,
      "step": 11000
    },
    {
      "epoch": 122.22222222222223,
      "eval_loss": 0.3320853114128113,
      "eval_runtime": 1.3295,
      "eval_samples_per_second": 30.087,
      "eval_steps_per_second": 15.043,
      "num_input_tokens_seen": 3081056,
      "step": 11000
    },
    {
      "epoch": 122.27777777777777,
      "grad_norm": 5.483240670400846e-07,
      "learning_rate": 4.1230228192640236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3082464,
      "step": 11005
    },
    {
      "epoch": 122.33333333333333,
      "grad_norm": 4.996410893909342e-07,
      "learning_rate": 4.122275967057675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3083904,
      "step": 11010
    },
    {
      "epoch": 122.38888888888889,
      "grad_norm": 4.0217284436039336e-07,
      "learning_rate": 4.1215288646759846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3085296,
      "step": 11015
    },
    {
      "epoch": 122.44444444444444,
      "grad_norm": 5.579066169048019e-07,
      "learning_rate": 4.120781512234166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3086688,
      "step": 11020
    },
    {
      "epoch": 122.5,
      "grad_norm": 1.687612893874757e-06,
      "learning_rate": 4.120033909847471e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3088096,
      "step": 11025
    },
    {
      "epoch": 122.55555555555556,
      "grad_norm": 5.985424991195032e-07,
      "learning_rate": 4.119286057631187e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3089504,
      "step": 11030
    },
    {
      "epoch": 122.61111111111111,
      "grad_norm": 1.3336689335119445e-06,
      "learning_rate": 4.118537955700646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3090864,
      "step": 11035
    },
    {
      "epoch": 122.66666666666667,
      "grad_norm": 5.92326216519723e-07,
      "learning_rate": 4.11778960417121e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3092272,
      "step": 11040
    },
    {
      "epoch": 122.72222222222223,
      "grad_norm": 5.778427976110834e-07,
      "learning_rate": 4.117041003158288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3093696,
      "step": 11045
    },
    {
      "epoch": 122.77777777777777,
      "grad_norm": 3.140034095849842e-06,
      "learning_rate": 4.1162921527773215e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3095072,
      "step": 11050
    },
    {
      "epoch": 122.83333333333333,
      "grad_norm": 1.2828730859837378e-06,
      "learning_rate": 4.115543053143794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3096464,
      "step": 11055
    },
    {
      "epoch": 122.88888888888889,
      "grad_norm": 5.037834966969967e-07,
      "learning_rate": 4.114793704373226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3097856,
      "step": 11060
    },
    {
      "epoch": 122.94444444444444,
      "grad_norm": 5.111023710924201e-07,
      "learning_rate": 4.114044106581175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3099232,
      "step": 11065
    },
    {
      "epoch": 123.0,
      "grad_norm": 3.8146978909026075e-07,
      "learning_rate": 4.11329425988324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3100640,
      "step": 11070
    },
    {
      "epoch": 123.05555555555556,
      "grad_norm": 1.1371239452273585e-06,
      "learning_rate": 4.112544164395056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3102048,
      "step": 11075
    },
    {
      "epoch": 123.11111111111111,
      "grad_norm": 4.799088060281065e-07,
      "learning_rate": 4.111793820232297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3103408,
      "step": 11080
    },
    {
      "epoch": 123.16666666666667,
      "grad_norm": 9.277042067878938e-07,
      "learning_rate": 4.1110432275106767e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3104784,
      "step": 11085
    },
    {
      "epoch": 123.22222222222223,
      "grad_norm": 1.6025525155782816e-06,
      "learning_rate": 4.110292386345944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3106176,
      "step": 11090
    },
    {
      "epoch": 123.27777777777777,
      "grad_norm": 5.292478704177483e-07,
      "learning_rate": 4.109541296853891e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3107584,
      "step": 11095
    },
    {
      "epoch": 123.33333333333333,
      "grad_norm": 5.567788434746035e-07,
      "learning_rate": 4.108789959150341e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3108976,
      "step": 11100
    },
    {
      "epoch": 123.38888888888889,
      "grad_norm": 5.589758416135737e-07,
      "learning_rate": 4.108038373351163e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3110416,
      "step": 11105
    },
    {
      "epoch": 123.44444444444444,
      "grad_norm": 5.297501957102213e-07,
      "learning_rate": 4.10728653957226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3111808,
      "step": 11110
    },
    {
      "epoch": 123.5,
      "grad_norm": 1.793650312720274e-06,
      "learning_rate": 4.106534457929575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3113248,
      "step": 11115
    },
    {
      "epoch": 123.55555555555556,
      "grad_norm": 5.327115673026128e-07,
      "learning_rate": 4.105782128539086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3114688,
      "step": 11120
    },
    {
      "epoch": 123.61111111111111,
      "grad_norm": 5.077645823803323e-07,
      "learning_rate": 4.1050295515168144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3116048,
      "step": 11125
    },
    {
      "epoch": 123.66666666666667,
      "grad_norm": 5.383300845096528e-07,
      "learning_rate": 4.1042767269788155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3117424,
      "step": 11130
    },
    {
      "epoch": 123.72222222222223,
      "grad_norm": 4.780098379342235e-07,
      "learning_rate": 4.103523655041185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3118832,
      "step": 11135
    },
    {
      "epoch": 123.77777777777777,
      "grad_norm": 5.602534542958892e-07,
      "learning_rate": 4.102770335820055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3120256,
      "step": 11140
    },
    {
      "epoch": 123.83333333333333,
      "grad_norm": 4.4663909193332074e-07,
      "learning_rate": 4.1020167694315984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3121648,
      "step": 11145
    },
    {
      "epoch": 123.88888888888889,
      "grad_norm": 5.667910727424896e-07,
      "learning_rate": 4.101262955992023e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3123056,
      "step": 11150
    },
    {
      "epoch": 123.94444444444444,
      "grad_norm": 4.946134595229523e-07,
      "learning_rate": 4.100508895617578e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3124432,
      "step": 11155
    },
    {
      "epoch": 124.0,
      "grad_norm": 1.0292370689057861e-06,
      "learning_rate": 4.099754588424547e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3125808,
      "step": 11160
    },
    {
      "epoch": 124.05555555555556,
      "grad_norm": 1.8439842506268178e-06,
      "learning_rate": 4.0990000345292546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3127184,
      "step": 11165
    },
    {
      "epoch": 124.11111111111111,
      "grad_norm": 4.547459298009926e-07,
      "learning_rate": 4.098245234048064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3128624,
      "step": 11170
    },
    {
      "epoch": 124.16666666666667,
      "grad_norm": 5.177480488782749e-07,
      "learning_rate": 4.0974901870973726e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3130016,
      "step": 11175
    },
    {
      "epoch": 124.22222222222223,
      "grad_norm": 1.9123704078083392e-06,
      "learning_rate": 4.096734893793619e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3131424,
      "step": 11180
    },
    {
      "epoch": 124.27777777777777,
      "grad_norm": 5.185858640288643e-07,
      "learning_rate": 4.095979354253279e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3132784,
      "step": 11185
    },
    {
      "epoch": 124.33333333333333,
      "grad_norm": 5.259332169771369e-07,
      "learning_rate": 4.0952235685928656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3134176,
      "step": 11190
    },
    {
      "epoch": 124.38888888888889,
      "grad_norm": 4.568778422253672e-07,
      "learning_rate": 4.094467536928932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3135568,
      "step": 11195
    },
    {
      "epoch": 124.44444444444444,
      "grad_norm": 5.498326345332316e-07,
      "learning_rate": 4.093711259378067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3136944,
      "step": 11200
    },
    {
      "epoch": 124.44444444444444,
      "eval_loss": 0.3126493990421295,
      "eval_runtime": 1.3046,
      "eval_samples_per_second": 30.66,
      "eval_steps_per_second": 15.33,
      "num_input_tokens_seen": 3136944,
      "step": 11200
    },
    {
      "epoch": 124.5,
      "grad_norm": 4.5232258116811863e-07,
      "learning_rate": 4.092954736056897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3138368,
      "step": 11205
    },
    {
      "epoch": 124.55555555555556,
      "grad_norm": 1.0005057902162662e-06,
      "learning_rate": 4.09219796708209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3139776,
      "step": 11210
    },
    {
      "epoch": 124.61111111111111,
      "grad_norm": 4.5295368522602075e-07,
      "learning_rate": 4.0914409525703464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3141184,
      "step": 11215
    },
    {
      "epoch": 124.66666666666667,
      "grad_norm": 1.4261549949878827e-06,
      "learning_rate": 4.090683692638408e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3142592,
      "step": 11220
    },
    {
      "epoch": 124.72222222222223,
      "grad_norm": 5.063497496848868e-07,
      "learning_rate": 4.089926187403056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3144032,
      "step": 11225
    },
    {
      "epoch": 124.77777777777777,
      "grad_norm": 4.5427435679812334e-07,
      "learning_rate": 4.0891684369811044e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3145440,
      "step": 11230
    },
    {
      "epoch": 124.83333333333333,
      "grad_norm": 7.20629827810626e-07,
      "learning_rate": 4.0884104414894107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3146816,
      "step": 11235
    },
    {
      "epoch": 124.88888888888889,
      "grad_norm": 3.5054176805715542e-06,
      "learning_rate": 4.087652201044864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3148208,
      "step": 11240
    },
    {
      "epoch": 124.94444444444444,
      "grad_norm": 1.5972971141309245e-06,
      "learning_rate": 4.086893715764397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3149600,
      "step": 11245
    },
    {
      "epoch": 125.0,
      "grad_norm": 6.024914682711824e-07,
      "learning_rate": 4.086134985764977e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3151008,
      "step": 11250
    },
    {
      "epoch": 125.05555555555556,
      "grad_norm": 5.901069357605593e-07,
      "learning_rate": 4.0853760111636085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3152400,
      "step": 11255
    },
    {
      "epoch": 125.11111111111111,
      "grad_norm": 1.5225389233819442e-06,
      "learning_rate": 4.084616792077337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3153792,
      "step": 11260
    },
    {
      "epoch": 125.16666666666667,
      "grad_norm": 1.476321699556138e-06,
      "learning_rate": 4.083857328623243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3155200,
      "step": 11265
    },
    {
      "epoch": 125.22222222222223,
      "grad_norm": 1.3546159607358277e-06,
      "learning_rate": 4.083097620918444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3156576,
      "step": 11270
    },
    {
      "epoch": 125.27777777777777,
      "grad_norm": 5.806724630019744e-07,
      "learning_rate": 4.082337669080097e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3157920,
      "step": 11275
    },
    {
      "epoch": 125.33333333333333,
      "grad_norm": 1.7899649265018525e-06,
      "learning_rate": 4.081577473225398e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3159328,
      "step": 11280
    },
    {
      "epoch": 125.38888888888889,
      "grad_norm": 6.016833253852383e-07,
      "learning_rate": 4.080817033471577e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3160768,
      "step": 11285
    },
    {
      "epoch": 125.44444444444444,
      "grad_norm": 5.567296739172889e-07,
      "learning_rate": 4.080056349935903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3162144,
      "step": 11290
    },
    {
      "epoch": 125.5,
      "grad_norm": 5.3606635219694e-07,
      "learning_rate": 4.079295422735684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3163536,
      "step": 11295
    },
    {
      "epoch": 125.55555555555556,
      "grad_norm": 7.241118851197825e-07,
      "learning_rate": 4.078534251988264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3164960,
      "step": 11300
    },
    {
      "epoch": 125.61111111111111,
      "grad_norm": 1.995287448153249e-06,
      "learning_rate": 4.077772837811025e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3166384,
      "step": 11305
    },
    {
      "epoch": 125.66666666666667,
      "grad_norm": 1.0450767149450257e-06,
      "learning_rate": 4.0770111803213874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3167824,
      "step": 11310
    },
    {
      "epoch": 125.72222222222223,
      "grad_norm": 4.471709758036013e-07,
      "learning_rate": 4.076249279636807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3169200,
      "step": 11315
    },
    {
      "epoch": 125.77777777777777,
      "grad_norm": 4.961633521816111e-07,
      "learning_rate": 4.075487135874781e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3170576,
      "step": 11320
    },
    {
      "epoch": 125.83333333333333,
      "grad_norm": 8.778919777796546e-07,
      "learning_rate": 4.074724749152837e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3172016,
      "step": 11325
    },
    {
      "epoch": 125.88888888888889,
      "grad_norm": 4.75744741379458e-07,
      "learning_rate": 4.07396211958855e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3173392,
      "step": 11330
    },
    {
      "epoch": 125.94444444444444,
      "grad_norm": 4.890814011559996e-07,
      "learning_rate": 4.073199247299523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3174832,
      "step": 11335
    },
    {
      "epoch": 126.0,
      "grad_norm": 9.057899887920939e-07,
      "learning_rate": 4.072436132403403e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3176192,
      "step": 11340
    },
    {
      "epoch": 126.05555555555556,
      "grad_norm": 7.530420589318965e-07,
      "learning_rate": 4.0716727750178704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3177552,
      "step": 11345
    },
    {
      "epoch": 126.11111111111111,
      "grad_norm": 5.605948558695673e-07,
      "learning_rate": 4.0709091752606455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3178992,
      "step": 11350
    },
    {
      "epoch": 126.16666666666667,
      "grad_norm": 5.178524702387222e-07,
      "learning_rate": 4.070145333249484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3180400,
      "step": 11355
    },
    {
      "epoch": 126.22222222222223,
      "grad_norm": 5.624781351798447e-07,
      "learning_rate": 4.069381249102181e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3181824,
      "step": 11360
    },
    {
      "epoch": 126.27777777777777,
      "grad_norm": 1.3629402246806421e-06,
      "learning_rate": 4.0686169229365665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3183232,
      "step": 11365
    },
    {
      "epoch": 126.33333333333333,
      "grad_norm": 4.786075464835449e-07,
      "learning_rate": 4.067852354870511e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3184624,
      "step": 11370
    },
    {
      "epoch": 126.38888888888889,
      "grad_norm": 5.414705128714559e-07,
      "learning_rate": 4.067087545021919e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3186048,
      "step": 11375
    },
    {
      "epoch": 126.44444444444444,
      "grad_norm": 4.5695423978031613e-07,
      "learning_rate": 4.066322493508734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3187424,
      "step": 11380
    },
    {
      "epoch": 126.5,
      "grad_norm": 6.395504215106484e-07,
      "learning_rate": 4.065557200448937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3188816,
      "step": 11385
    },
    {
      "epoch": 126.55555555555556,
      "grad_norm": 5.465777235258429e-07,
      "learning_rate": 4.064791665960546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3190224,
      "step": 11390
    },
    {
      "epoch": 126.61111111111111,
      "grad_norm": 5.266301172923704e-07,
      "learning_rate": 4.064025890161615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3191584,
      "step": 11395
    },
    {
      "epoch": 126.66666666666667,
      "grad_norm": 1.405950229127484e-06,
      "learning_rate": 4.0632598731702373e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3192960,
      "step": 11400
    },
    {
      "epoch": 126.66666666666667,
      "eval_loss": 0.3366057872772217,
      "eval_runtime": 1.306,
      "eval_samples_per_second": 30.629,
      "eval_steps_per_second": 15.314,
      "num_input_tokens_seen": 3192960,
      "step": 11400
    },
    {
      "epoch": 126.72222222222223,
      "grad_norm": 2.6838363282877253e-06,
      "learning_rate": 4.0624936151045426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3194352,
      "step": 11405
    },
    {
      "epoch": 126.77777777777777,
      "grad_norm": 4.987739430362126e-07,
      "learning_rate": 4.061727116082696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3195760,
      "step": 11410
    },
    {
      "epoch": 126.83333333333333,
      "grad_norm": 5.297079610500077e-07,
      "learning_rate": 4.060960376222903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3197184,
      "step": 11415
    },
    {
      "epoch": 126.88888888888889,
      "grad_norm": 4.5885957433711155e-07,
      "learning_rate": 4.0601933956434034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3198560,
      "step": 11420
    },
    {
      "epoch": 126.94444444444444,
      "grad_norm": 7.071893719512445e-07,
      "learning_rate": 4.059426174462476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3199952,
      "step": 11425
    },
    {
      "epoch": 127.0,
      "grad_norm": 4.873322723142337e-07,
      "learning_rate": 4.058658712798435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3201328,
      "step": 11430
    },
    {
      "epoch": 127.05555555555556,
      "grad_norm": 5.737854849030555e-07,
      "learning_rate": 4.0578910107696336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3202736,
      "step": 11435
    },
    {
      "epoch": 127.11111111111111,
      "grad_norm": 5.122674338053912e-07,
      "learning_rate": 4.05712306849446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3204144,
      "step": 11440
    },
    {
      "epoch": 127.16666666666667,
      "grad_norm": 5.261976525616774e-07,
      "learning_rate": 4.0563548860913415e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3205536,
      "step": 11445
    },
    {
      "epoch": 127.22222222222223,
      "grad_norm": 1.7991235381487058e-06,
      "learning_rate": 4.0555864636787414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3206928,
      "step": 11450
    },
    {
      "epoch": 127.27777777777777,
      "grad_norm": 5.658146164932987e-07,
      "learning_rate": 4.054817801375159e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3208336,
      "step": 11455
    },
    {
      "epoch": 127.33333333333333,
      "grad_norm": 2.368670948271756e-06,
      "learning_rate": 4.054048899299134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3209696,
      "step": 11460
    },
    {
      "epoch": 127.38888888888889,
      "grad_norm": 1.1839558737847256e-06,
      "learning_rate": 4.0532797575692385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3211088,
      "step": 11465
    },
    {
      "epoch": 127.44444444444444,
      "grad_norm": 7.546564688709623e-07,
      "learning_rate": 4.052510376304085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3212496,
      "step": 11470
    },
    {
      "epoch": 127.5,
      "grad_norm": 5.275492185319308e-07,
      "learning_rate": 4.051740755622321e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3213888,
      "step": 11475
    },
    {
      "epoch": 127.55555555555556,
      "grad_norm": 6.328757535811746e-07,
      "learning_rate": 4.050970895642632e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3215232,
      "step": 11480
    },
    {
      "epoch": 127.61111111111111,
      "grad_norm": 5.583939355346956e-07,
      "learning_rate": 4.050200796483741e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3216592,
      "step": 11485
    },
    {
      "epoch": 127.66666666666667,
      "grad_norm": 1.051000140250835e-06,
      "learning_rate": 4.049430458264405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3218000,
      "step": 11490
    },
    {
      "epoch": 127.72222222222223,
      "grad_norm": 5.782414973509731e-07,
      "learning_rate": 4.048659881103422e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3219392,
      "step": 11495
    },
    {
      "epoch": 127.77777777777777,
      "grad_norm": 6.662333476015192e-07,
      "learning_rate": 4.0478890651196235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3220832,
      "step": 11500
    },
    {
      "epoch": 127.83333333333333,
      "grad_norm": 1.510562810835836e-06,
      "learning_rate": 4.047118010431879e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3222272,
      "step": 11505
    },
    {
      "epoch": 127.88888888888889,
      "grad_norm": 5.627429686683172e-07,
      "learning_rate": 4.046346717159094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3223680,
      "step": 11510
    },
    {
      "epoch": 127.94444444444444,
      "grad_norm": 4.981418442184804e-07,
      "learning_rate": 4.045575185420214e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3225088,
      "step": 11515
    },
    {
      "epoch": 128.0,
      "grad_norm": 1.4814797850704053e-06,
      "learning_rate": 4.0448034153342165e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3226512,
      "step": 11520
    },
    {
      "epoch": 128.05555555555554,
      "grad_norm": 1.6859955849213293e-06,
      "learning_rate": 4.0440314070201194e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3227888,
      "step": 11525
    },
    {
      "epoch": 128.11111111111111,
      "grad_norm": 4.6140016252138594e-07,
      "learning_rate": 4.043259160596976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3229296,
      "step": 11530
    },
    {
      "epoch": 128.16666666666666,
      "grad_norm": 5.884011784473842e-07,
      "learning_rate": 4.0424866761838767e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3230720,
      "step": 11535
    },
    {
      "epoch": 128.22222222222223,
      "grad_norm": 8.123922157210473e-07,
      "learning_rate": 4.041713953899948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3232160,
      "step": 11540
    },
    {
      "epoch": 128.27777777777777,
      "grad_norm": 1.013576138575445e-06,
      "learning_rate": 4.0409409938643515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3233616,
      "step": 11545
    },
    {
      "epoch": 128.33333333333334,
      "grad_norm": 5.34865705503762e-07,
      "learning_rate": 4.0401677961962904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3235008,
      "step": 11550
    },
    {
      "epoch": 128.38888888888889,
      "grad_norm": 6.494713602478441e-07,
      "learning_rate": 4.039394361015001e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3236416,
      "step": 11555
    },
    {
      "epoch": 128.44444444444446,
      "grad_norm": 1.4894465039105853e-06,
      "learning_rate": 4.038620688439755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3237808,
      "step": 11560
    },
    {
      "epoch": 128.5,
      "grad_norm": 5.153633537702262e-07,
      "learning_rate": 4.037846778589862e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3239200,
      "step": 11565
    },
    {
      "epoch": 128.55555555555554,
      "grad_norm": 4.6116591079226055e-07,
      "learning_rate": 4.0370726315846715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3240592,
      "step": 11570
    },
    {
      "epoch": 128.61111111111111,
      "grad_norm": 5.291445859256783e-07,
      "learning_rate": 4.036298247543565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3242016,
      "step": 11575
    },
    {
      "epoch": 128.66666666666666,
      "grad_norm": 5.405453293860774e-07,
      "learning_rate": 4.035523626585962e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3243392,
      "step": 11580
    },
    {
      "epoch": 128.72222222222223,
      "grad_norm": 6.082602226342715e-07,
      "learning_rate": 4.0347487688313194e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3244800,
      "step": 11585
    },
    {
      "epoch": 128.77777777777777,
      "grad_norm": 2.54179440162261e-06,
      "learning_rate": 4.0339736743991296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3246176,
      "step": 11590
    },
    {
      "epoch": 128.83333333333334,
      "grad_norm": 6.160646535136038e-07,
      "learning_rate": 4.0331983434089227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3247568,
      "step": 11595
    },
    {
      "epoch": 128.88888888888889,
      "grad_norm": 6.55628184631496e-07,
      "learning_rate": 4.032422775980264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3248976,
      "step": 11600
    },
    {
      "epoch": 128.88888888888889,
      "eval_loss": 0.34557223320007324,
      "eval_runtime": 1.3189,
      "eval_samples_per_second": 30.329,
      "eval_steps_per_second": 15.164,
      "num_input_tokens_seen": 3248976,
      "step": 11600
    },
    {
      "epoch": 128.94444444444446,
      "grad_norm": 2.106757619912969e-06,
      "learning_rate": 4.031646972232754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3250352,
      "step": 11605
    },
    {
      "epoch": 129.0,
      "grad_norm": 5.154150812813896e-07,
      "learning_rate": 4.0308709322860344e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3251776,
      "step": 11610
    },
    {
      "epoch": 129.05555555555554,
      "grad_norm": 8.926787131713354e-07,
      "learning_rate": 4.0300946562597784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3253200,
      "step": 11615
    },
    {
      "epoch": 129.11111111111111,
      "grad_norm": 4.483375732888817e-07,
      "learning_rate": 4.029318144273698e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3254560,
      "step": 11620
    },
    {
      "epoch": 129.16666666666666,
      "grad_norm": 4.2208804984511517e-07,
      "learning_rate": 4.0285413964475415e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3255968,
      "step": 11625
    },
    {
      "epoch": 129.22222222222223,
      "grad_norm": 5.622176217912056e-07,
      "learning_rate": 4.0277644129010927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3257392,
      "step": 11630
    },
    {
      "epoch": 129.27777777777777,
      "grad_norm": 5.910752634008531e-07,
      "learning_rate": 4.0269871937541724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3258768,
      "step": 11635
    },
    {
      "epoch": 129.33333333333334,
      "grad_norm": 5.347236538000288e-07,
      "learning_rate": 4.026209739126637e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3260192,
      "step": 11640
    },
    {
      "epoch": 129.38888888888889,
      "grad_norm": 5.118833996675676e-07,
      "learning_rate": 4.025432049138381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3261600,
      "step": 11645
    },
    {
      "epoch": 129.44444444444446,
      "grad_norm": 1.8608343452797271e-06,
      "learning_rate": 4.0246541239093325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3263008,
      "step": 11650
    },
    {
      "epoch": 129.5,
      "grad_norm": 7.960750849633769e-07,
      "learning_rate": 4.023875963559459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3264432,
      "step": 11655
    },
    {
      "epoch": 129.55555555555554,
      "grad_norm": 5.87286763220618e-07,
      "learning_rate": 4.023097568208761e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3265840,
      "step": 11660
    },
    {
      "epoch": 129.61111111111111,
      "grad_norm": 5.297899861034239e-07,
      "learning_rate": 4.022318937977277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3267264,
      "step": 11665
    },
    {
      "epoch": 129.66666666666666,
      "grad_norm": 3.7563233945547836e-06,
      "learning_rate": 4.021540072985084e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3268688,
      "step": 11670
    },
    {
      "epoch": 129.72222222222223,
      "grad_norm": 4.839073426410323e-07,
      "learning_rate": 4.020760973352289e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3270080,
      "step": 11675
    },
    {
      "epoch": 129.77777777777777,
      "grad_norm": 4.7679372983111534e-07,
      "learning_rate": 4.019981639199042e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3271440,
      "step": 11680
    },
    {
      "epoch": 129.83333333333334,
      "grad_norm": 5.51905031898059e-07,
      "learning_rate": 4.0192020706455245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3272816,
      "step": 11685
    },
    {
      "epoch": 129.88888888888889,
      "grad_norm": 6.829392873441975e-07,
      "learning_rate": 4.018422267811956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3274224,
      "step": 11690
    },
    {
      "epoch": 129.94444444444446,
      "grad_norm": 9.889924967865227e-07,
      "learning_rate": 4.017642230818592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3275584,
      "step": 11695
    },
    {
      "epoch": 130.0,
      "grad_norm": 7.062297413540364e-07,
      "learning_rate": 4.0168619597857246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3276976,
      "step": 11700
    },
    {
      "epoch": 130.05555555555554,
      "grad_norm": 1.9430858628766146e-06,
      "learning_rate": 4.016081454833681e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3278400,
      "step": 11705
    },
    {
      "epoch": 130.11111111111111,
      "grad_norm": 5.140730650055048e-07,
      "learning_rate": 4.0153007160828245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3279808,
      "step": 11710
    },
    {
      "epoch": 130.16666666666666,
      "grad_norm": 6.20066316514567e-07,
      "learning_rate": 4.0145197436535555e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3281232,
      "step": 11715
    },
    {
      "epoch": 130.22222222222223,
      "grad_norm": 3.844857474177843e-06,
      "learning_rate": 4.0137385376663095e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3282576,
      "step": 11720
    },
    {
      "epoch": 130.27777777777777,
      "grad_norm": 1.9172316569893155e-06,
      "learning_rate": 4.012957098241558e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3284016,
      "step": 11725
    },
    {
      "epoch": 130.33333333333334,
      "grad_norm": 4.528307329110248e-07,
      "learning_rate": 4.0121754254998076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3285440,
      "step": 11730
    },
    {
      "epoch": 130.38888888888889,
      "grad_norm": 5.773861744273745e-07,
      "learning_rate": 4.011393519561606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3286816,
      "step": 11735
    },
    {
      "epoch": 130.44444444444446,
      "grad_norm": 6.369970719788398e-07,
      "learning_rate": 4.010611380547529e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3288208,
      "step": 11740
    },
    {
      "epoch": 130.5,
      "grad_norm": 6.551636033691466e-07,
      "learning_rate": 4.009829008578192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3289600,
      "step": 11745
    },
    {
      "epoch": 130.55555555555554,
      "grad_norm": 6.466308377639507e-07,
      "learning_rate": 4.00904640377425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3291024,
      "step": 11750
    },
    {
      "epoch": 130.61111111111111,
      "grad_norm": 5.921339720771357e-07,
      "learning_rate": 4.0082635662563886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3292448,
      "step": 11755
    },
    {
      "epoch": 130.66666666666666,
      "grad_norm": 5.864810077582661e-07,
      "learning_rate": 4.007480496145331e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3293840,
      "step": 11760
    },
    {
      "epoch": 130.72222222222223,
      "grad_norm": 5.17650391884672e-07,
      "learning_rate": 4.006697193561837e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3295264,
      "step": 11765
    },
    {
      "epoch": 130.77777777777777,
      "grad_norm": 1.4466875200014329e-06,
      "learning_rate": 4.005913658626701e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3296672,
      "step": 11770
    },
    {
      "epoch": 130.83333333333334,
      "grad_norm": 5.983742994430941e-07,
      "learning_rate": 4.005129891460754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3298064,
      "step": 11775
    },
    {
      "epoch": 130.88888888888889,
      "grad_norm": 1.2281941508263117e-06,
      "learning_rate": 4.004345892184864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3299440,
      "step": 11780
    },
    {
      "epoch": 130.94444444444446,
      "grad_norm": 1.0758985808934085e-06,
      "learning_rate": 4.003561660919932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3300816,
      "step": 11785
    },
    {
      "epoch": 131.0,
      "grad_norm": 6.111684456300281e-07,
      "learning_rate": 4.002777197786897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3302176,
      "step": 11790
    },
    {
      "epoch": 131.05555555555554,
      "grad_norm": 5.080217420072586e-07,
      "learning_rate": 4.0019925029067326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3303552,
      "step": 11795
    },
    {
      "epoch": 131.11111111111111,
      "grad_norm": 1.5213341839626082e-06,
      "learning_rate": 4.0012075764004495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3305024,
      "step": 11800
    },
    {
      "epoch": 131.11111111111111,
      "eval_loss": 0.3281330466270447,
      "eval_runtime": 1.3361,
      "eval_samples_per_second": 29.937,
      "eval_steps_per_second": 14.969,
      "num_input_tokens_seen": 3305024,
      "step": 11800
    },
    {
      "epoch": 131.16666666666666,
      "grad_norm": 5.4024980045142e-07,
      "learning_rate": 4.000422418389094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3306464,
      "step": 11805
    },
    {
      "epoch": 131.22222222222223,
      "grad_norm": 5.867114509783278e-07,
      "learning_rate": 3.999637028993744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3307888,
      "step": 11810
    },
    {
      "epoch": 131.27777777777777,
      "grad_norm": 5.41701581369125e-07,
      "learning_rate": 3.99885140833552e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3309328,
      "step": 11815
    },
    {
      "epoch": 131.33333333333334,
      "grad_norm": 5.548142212319362e-07,
      "learning_rate": 3.998065556535572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3310688,
      "step": 11820
    },
    {
      "epoch": 131.38888888888889,
      "grad_norm": 6.706898716402065e-07,
      "learning_rate": 3.9972794737150895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3312064,
      "step": 11825
    },
    {
      "epoch": 131.44444444444446,
      "grad_norm": 4.772306283484795e-07,
      "learning_rate": 3.996493159995297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3313392,
      "step": 11830
    },
    {
      "epoch": 131.5,
      "grad_norm": 5.527415396500146e-07,
      "learning_rate": 3.995706615497453e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3314832,
      "step": 11835
    },
    {
      "epoch": 131.55555555555554,
      "grad_norm": 9.674572538642678e-07,
      "learning_rate": 3.994919840342852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3316224,
      "step": 11840
    },
    {
      "epoch": 131.61111111111111,
      "grad_norm": 5.623502374874079e-07,
      "learning_rate": 3.994132834652825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3317616,
      "step": 11845
    },
    {
      "epoch": 131.66666666666666,
      "grad_norm": 1.055066832122975e-06,
      "learning_rate": 3.99334559854874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3319008,
      "step": 11850
    },
    {
      "epoch": 131.72222222222223,
      "grad_norm": 5.445180022434215e-07,
      "learning_rate": 3.9925581321519955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3320400,
      "step": 11855
    },
    {
      "epoch": 131.77777777777777,
      "grad_norm": 7.027951482996286e-07,
      "learning_rate": 3.991770435584031e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3321808,
      "step": 11860
    },
    {
      "epoch": 131.83333333333334,
      "grad_norm": 8.327041882694175e-07,
      "learning_rate": 3.990982508966319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3323168,
      "step": 11865
    },
    {
      "epoch": 131.88888888888889,
      "grad_norm": 2.589742052805377e-06,
      "learning_rate": 3.990194352420367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3324544,
      "step": 11870
    },
    {
      "epoch": 131.94444444444446,
      "grad_norm": 5.338135906640673e-07,
      "learning_rate": 3.9894059660677184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3326000,
      "step": 11875
    },
    {
      "epoch": 132.0,
      "grad_norm": 2.5570468551450176e-06,
      "learning_rate": 3.9886173500299526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3327424,
      "step": 11880
    },
    {
      "epoch": 132.05555555555554,
      "grad_norm": 4.0302509773937345e-07,
      "learning_rate": 3.987828504428685e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3328784,
      "step": 11885
    },
    {
      "epoch": 132.11111111111111,
      "grad_norm": 5.662152489094296e-07,
      "learning_rate": 3.987039429385565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3330256,
      "step": 11890
    },
    {
      "epoch": 132.16666666666666,
      "grad_norm": 5.682724122380023e-07,
      "learning_rate": 3.986250125022277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3331664,
      "step": 11895
    },
    {
      "epoch": 132.22222222222223,
      "grad_norm": 6.205134468473261e-07,
      "learning_rate": 3.985460591460544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3333056,
      "step": 11900
    },
    {
      "epoch": 132.27777777777777,
      "grad_norm": 5.950161607870541e-07,
      "learning_rate": 3.984670828822118e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3334432,
      "step": 11905
    },
    {
      "epoch": 132.33333333333334,
      "grad_norm": 4.972598617314361e-07,
      "learning_rate": 3.983880837228794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3335872,
      "step": 11910
    },
    {
      "epoch": 132.38888888888889,
      "grad_norm": 6.544157145071949e-07,
      "learning_rate": 3.983090616802396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3337264,
      "step": 11915
    },
    {
      "epoch": 132.44444444444446,
      "grad_norm": 4.4509286567517847e-07,
      "learning_rate": 3.982300167664788e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3338656,
      "step": 11920
    },
    {
      "epoch": 132.5,
      "grad_norm": 1.941593382071005e-06,
      "learning_rate": 3.981509489937868e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3340048,
      "step": 11925
    },
    {
      "epoch": 132.55555555555554,
      "grad_norm": 6.248807835618209e-07,
      "learning_rate": 3.9807185837435643e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3341488,
      "step": 11930
    },
    {
      "epoch": 132.61111111111111,
      "grad_norm": 6.480218530668935e-07,
      "learning_rate": 3.9799274492038484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3342896,
      "step": 11935
    },
    {
      "epoch": 132.66666666666666,
      "grad_norm": 6.176856004458386e-07,
      "learning_rate": 3.979136086440722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3344240,
      "step": 11940
    },
    {
      "epoch": 132.72222222222223,
      "grad_norm": 5.271274972074025e-07,
      "learning_rate": 3.9783444955762226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3345600,
      "step": 11945
    },
    {
      "epoch": 132.77777777777777,
      "grad_norm": 1.3265970437714714e-06,
      "learning_rate": 3.977552676732424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3346992,
      "step": 11950
    },
    {
      "epoch": 132.83333333333334,
      "grad_norm": 4.924420977658883e-07,
      "learning_rate": 3.976760630031435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3348384,
      "step": 11955
    },
    {
      "epoch": 132.88888888888889,
      "grad_norm": 6.628456503676716e-07,
      "learning_rate": 3.975968355595398e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3349840,
      "step": 11960
    },
    {
      "epoch": 132.94444444444446,
      "grad_norm": 6.198932851475547e-07,
      "learning_rate": 3.9751758535464935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3351264,
      "step": 11965
    },
    {
      "epoch": 133.0,
      "grad_norm": 7.371784249698976e-07,
      "learning_rate": 3.9743831240069326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3352624,
      "step": 11970
    },
    {
      "epoch": 133.05555555555554,
      "grad_norm": 1.4306586990642245e-06,
      "learning_rate": 3.9735901670989675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3353984,
      "step": 11975
    },
    {
      "epoch": 133.11111111111111,
      "grad_norm": 1.5284043684005155e-06,
      "learning_rate": 3.97279698294488e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3355392,
      "step": 11980
    },
    {
      "epoch": 133.16666666666666,
      "grad_norm": 5.104814135847846e-07,
      "learning_rate": 3.9720035716669876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3356784,
      "step": 11985
    },
    {
      "epoch": 133.22222222222223,
      "grad_norm": 4.7580712703165773e-07,
      "learning_rate": 3.9712099333876474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3358208,
      "step": 11990
    },
    {
      "epoch": 133.27777777777777,
      "grad_norm": 4.0245075183520385e-07,
      "learning_rate": 3.9704160682292475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3359632,
      "step": 11995
    },
    {
      "epoch": 133.33333333333334,
      "grad_norm": 1.5327854043789557e-06,
      "learning_rate": 3.9696219763142106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3361008,
      "step": 12000
    },
    {
      "epoch": 133.33333333333334,
      "eval_loss": 0.34895405173301697,
      "eval_runtime": 1.3007,
      "eval_samples_per_second": 30.751,
      "eval_steps_per_second": 15.376,
      "num_input_tokens_seen": 3361008,
      "step": 12000
    },
    {
      "epoch": 133.38888888888889,
      "grad_norm": 5.845846544616506e-07,
      "learning_rate": 3.968827657764997e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3362432,
      "step": 12005
    },
    {
      "epoch": 133.44444444444446,
      "grad_norm": 5.064935635346046e-07,
      "learning_rate": 3.9680331127041e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3363872,
      "step": 12010
    },
    {
      "epoch": 133.5,
      "grad_norm": 1.7912079783855006e-06,
      "learning_rate": 3.9672383412540495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3365264,
      "step": 12015
    },
    {
      "epoch": 133.55555555555554,
      "grad_norm": 1.1302097391308052e-06,
      "learning_rate": 3.966443343537407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3366640,
      "step": 12020
    },
    {
      "epoch": 133.61111111111111,
      "grad_norm": 6.268968490985571e-07,
      "learning_rate": 3.965648119676772e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3368032,
      "step": 12025
    },
    {
      "epoch": 133.66666666666666,
      "grad_norm": 1.016676151266438e-06,
      "learning_rate": 3.96485266979478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3369456,
      "step": 12030
    },
    {
      "epoch": 133.72222222222223,
      "grad_norm": 2.105595740431454e-06,
      "learning_rate": 3.9640569940140974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3370848,
      "step": 12035
    },
    {
      "epoch": 133.77777777777777,
      "grad_norm": 3.4485267406125786e-06,
      "learning_rate": 3.963261092457428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3372256,
      "step": 12040
    },
    {
      "epoch": 133.83333333333334,
      "grad_norm": 6.126708171905193e-07,
      "learning_rate": 3.962464965247509e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3373664,
      "step": 12045
    },
    {
      "epoch": 133.88888888888889,
      "grad_norm": 4.908662276648101e-07,
      "learning_rate": 3.9616686125071135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3375072,
      "step": 12050
    },
    {
      "epoch": 133.94444444444446,
      "grad_norm": 5.709886181648471e-07,
      "learning_rate": 3.9608720343590506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3376480,
      "step": 12055
    },
    {
      "epoch": 134.0,
      "grad_norm": 5.776984721705958e-07,
      "learning_rate": 3.960075230926161e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3377840,
      "step": 12060
    },
    {
      "epoch": 134.05555555555554,
      "grad_norm": 6.063053774596483e-07,
      "learning_rate": 3.959278202331322e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3379264,
      "step": 12065
    },
    {
      "epoch": 134.11111111111111,
      "grad_norm": 1.0470396318851272e-06,
      "learning_rate": 3.958480948697446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3380608,
      "step": 12070
    },
    {
      "epoch": 134.16666666666666,
      "grad_norm": 4.972694114258047e-07,
      "learning_rate": 3.95768347014748e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3382000,
      "step": 12075
    },
    {
      "epoch": 134.22222222222223,
      "grad_norm": 5.516022838492063e-07,
      "learning_rate": 3.956885766804404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3383392,
      "step": 12080
    },
    {
      "epoch": 134.27777777777777,
      "grad_norm": 6.765740181435831e-07,
      "learning_rate": 3.956087838791235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3384784,
      "step": 12085
    },
    {
      "epoch": 134.33333333333334,
      "grad_norm": 1.4088316220295383e-06,
      "learning_rate": 3.955289686231022e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3386240,
      "step": 12090
    },
    {
      "epoch": 134.38888888888889,
      "grad_norm": 6.001171755087853e-07,
      "learning_rate": 3.9544913092468504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3387616,
      "step": 12095
    },
    {
      "epoch": 134.44444444444446,
      "grad_norm": 7.196760520855605e-07,
      "learning_rate": 3.9536927079618425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3389008,
      "step": 12100
    },
    {
      "epoch": 134.5,
      "grad_norm": 5.989039095766202e-07,
      "learning_rate": 3.9528938824991494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3390416,
      "step": 12105
    },
    {
      "epoch": 134.55555555555554,
      "grad_norm": 1.5356475842054351e-06,
      "learning_rate": 3.952094832981962e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3391856,
      "step": 12110
    },
    {
      "epoch": 134.61111111111111,
      "grad_norm": 6.056594656911329e-07,
      "learning_rate": 3.951295559533503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3393216,
      "step": 12115
    },
    {
      "epoch": 134.66666666666666,
      "grad_norm": 6.847028544143541e-07,
      "learning_rate": 3.95049606227703e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3394592,
      "step": 12120
    },
    {
      "epoch": 134.72222222222223,
      "grad_norm": 6.490539590231492e-07,
      "learning_rate": 3.949696341335838e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3396016,
      "step": 12125
    },
    {
      "epoch": 134.77777777777777,
      "grad_norm": 8.235402901846101e-07,
      "learning_rate": 3.9488963968332503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3397424,
      "step": 12130
    },
    {
      "epoch": 134.83333333333334,
      "grad_norm": 1.077896627066366e-06,
      "learning_rate": 3.948096228892631e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3398848,
      "step": 12135
    },
    {
      "epoch": 134.88888888888889,
      "grad_norm": 2.8091512831451837e-06,
      "learning_rate": 3.947295837637375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3400272,
      "step": 12140
    },
    {
      "epoch": 134.94444444444446,
      "grad_norm": 1.274958208341559e-06,
      "learning_rate": 3.9464952231909135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3401648,
      "step": 12145
    },
    {
      "epoch": 135.0,
      "grad_norm": 1.125433414017607e-06,
      "learning_rate": 3.945694385676711e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3403056,
      "step": 12150
    },
    {
      "epoch": 135.05555555555554,
      "grad_norm": 5.750545710725419e-07,
      "learning_rate": 3.944893325218265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3404464,
      "step": 12155
    },
    {
      "epoch": 135.11111111111111,
      "grad_norm": 6.637254728047992e-07,
      "learning_rate": 3.944092041939112e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3405872,
      "step": 12160
    },
    {
      "epoch": 135.16666666666666,
      "grad_norm": 2.2076937966630794e-06,
      "learning_rate": 3.943290535962818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3407312,
      "step": 12165
    },
    {
      "epoch": 135.22222222222223,
      "grad_norm": 1.1823839258795488e-06,
      "learning_rate": 3.942488807412985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3408736,
      "step": 12170
    },
    {
      "epoch": 135.27777777777777,
      "grad_norm": 2.7064741061622044e-06,
      "learning_rate": 3.941686856413251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3410144,
      "step": 12175
    },
    {
      "epoch": 135.33333333333334,
      "grad_norm": 4.5295266204448126e-07,
      "learning_rate": 3.9408846830872874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3411600,
      "step": 12180
    },
    {
      "epoch": 135.38888888888889,
      "grad_norm": 1.2118813401684747e-06,
      "learning_rate": 3.940082287558798e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3412976,
      "step": 12185
    },
    {
      "epoch": 135.44444444444446,
      "grad_norm": 2.685305844352115e-06,
      "learning_rate": 3.939279669951522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3414384,
      "step": 12190
    },
    {
      "epoch": 135.5,
      "grad_norm": 5.293994718158501e-07,
      "learning_rate": 3.938476830389234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3415792,
      "step": 12195
    },
    {
      "epoch": 135.55555555555554,
      "grad_norm": 5.720730769098736e-07,
      "learning_rate": 3.937673768995742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3417152,
      "step": 12200
    },
    {
      "epoch": 135.55555555555554,
      "eval_loss": 0.3237461447715759,
      "eval_runtime": 1.3257,
      "eval_samples_per_second": 30.174,
      "eval_steps_per_second": 15.087,
      "num_input_tokens_seen": 3417152,
      "step": 12200
    },
    {
      "epoch": 135.61111111111111,
      "grad_norm": 6.045351028660662e-07,
      "learning_rate": 3.936870485894888e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3418480,
      "step": 12205
    },
    {
      "epoch": 135.66666666666666,
      "grad_norm": 5.003118417334917e-07,
      "learning_rate": 3.9360669812105475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3419888,
      "step": 12210
    },
    {
      "epoch": 135.72222222222223,
      "grad_norm": 1.052509560395265e-06,
      "learning_rate": 3.9352632550666325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3421296,
      "step": 12215
    },
    {
      "epoch": 135.77777777777777,
      "grad_norm": 6.08472760177392e-07,
      "learning_rate": 3.9344593075870866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3422688,
      "step": 12220
    },
    {
      "epoch": 135.83333333333334,
      "grad_norm": 5.772854478891531e-07,
      "learning_rate": 3.933655138895889e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3424048,
      "step": 12225
    },
    {
      "epoch": 135.88888888888889,
      "grad_norm": 5.382909762374766e-07,
      "learning_rate": 3.932850749117053e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3425440,
      "step": 12230
    },
    {
      "epoch": 135.94444444444446,
      "grad_norm": 5.478782441059593e-07,
      "learning_rate": 3.932046138374624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3426784,
      "step": 12235
    },
    {
      "epoch": 136.0,
      "grad_norm": 1.0286622682542657e-06,
      "learning_rate": 3.9312413067926854e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3428192,
      "step": 12240
    },
    {
      "epoch": 136.05555555555554,
      "grad_norm": 7.418485665766639e-07,
      "learning_rate": 3.9304362544953506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3429600,
      "step": 12245
    },
    {
      "epoch": 136.11111111111111,
      "grad_norm": 6.709120157211146e-07,
      "learning_rate": 3.929630981606769e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3431008,
      "step": 12250
    },
    {
      "epoch": 136.16666666666666,
      "grad_norm": 5.714152280233975e-07,
      "learning_rate": 3.928825488251124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3432416,
      "step": 12255
    },
    {
      "epoch": 136.22222222222223,
      "grad_norm": 1.2942356306666625e-06,
      "learning_rate": 3.9280197745526344e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3433760,
      "step": 12260
    },
    {
      "epoch": 136.27777777777777,
      "grad_norm": 1.421960405423306e-06,
      "learning_rate": 3.9272138406355495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3435136,
      "step": 12265
    },
    {
      "epoch": 136.33333333333334,
      "grad_norm": 2.8078891318727983e-06,
      "learning_rate": 3.926407686624154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3436512,
      "step": 12270
    },
    {
      "epoch": 136.38888888888889,
      "grad_norm": 5.4493273182743e-07,
      "learning_rate": 3.9256013126427684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3437888,
      "step": 12275
    },
    {
      "epoch": 136.44444444444446,
      "grad_norm": 6.736074169566564e-07,
      "learning_rate": 3.9247947188157455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3439296,
      "step": 12280
    },
    {
      "epoch": 136.5,
      "grad_norm": 6.56802683351998e-07,
      "learning_rate": 3.9239879052674715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3440704,
      "step": 12285
    },
    {
      "epoch": 136.55555555555554,
      "grad_norm": 6.313124458756647e-07,
      "learning_rate": 3.9231808721223673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3442144,
      "step": 12290
    },
    {
      "epoch": 136.61111111111111,
      "grad_norm": 1.075703607966716e-06,
      "learning_rate": 3.9223736195048886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3443504,
      "step": 12295
    },
    {
      "epoch": 136.66666666666666,
      "grad_norm": 1.9824212813546183e-06,
      "learning_rate": 3.921566147539523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3444928,
      "step": 12300
    },
    {
      "epoch": 136.72222222222223,
      "grad_norm": 2.3744228201394435e-06,
      "learning_rate": 3.920758456350792e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3446368,
      "step": 12305
    },
    {
      "epoch": 136.77777777777777,
      "grad_norm": 6.577081990144507e-07,
      "learning_rate": 3.919950546063253e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3447712,
      "step": 12310
    },
    {
      "epoch": 136.83333333333334,
      "grad_norm": 5.704602017431171e-07,
      "learning_rate": 3.919142416801496e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3449168,
      "step": 12315
    },
    {
      "epoch": 136.88888888888889,
      "grad_norm": 5.626827714877436e-07,
      "learning_rate": 3.918334068690144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3450528,
      "step": 12320
    },
    {
      "epoch": 136.94444444444446,
      "grad_norm": 6.141106041468447e-07,
      "learning_rate": 3.917525501853855e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3451952,
      "step": 12325
    },
    {
      "epoch": 137.0,
      "grad_norm": 6.813373261138622e-07,
      "learning_rate": 3.916716716417319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3453328,
      "step": 12330
    },
    {
      "epoch": 137.05555555555554,
      "grad_norm": 5.069376811661641e-07,
      "learning_rate": 3.915907712505263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3454672,
      "step": 12335
    },
    {
      "epoch": 137.11111111111111,
      "grad_norm": 5.679788159795862e-07,
      "learning_rate": 3.915098490242444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3456096,
      "step": 12340
    },
    {
      "epoch": 137.16666666666666,
      "grad_norm": 7.652956810488831e-07,
      "learning_rate": 3.914289049753654e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3457536,
      "step": 12345
    },
    {
      "epoch": 137.22222222222223,
      "grad_norm": 6.505508736154297e-07,
      "learning_rate": 3.913479391163719e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3458928,
      "step": 12350
    },
    {
      "epoch": 137.27777777777777,
      "grad_norm": 8.441662657787674e-07,
      "learning_rate": 3.9126695145975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3460368,
      "step": 12355
    },
    {
      "epoch": 137.33333333333334,
      "grad_norm": 1.2225940508869826e-06,
      "learning_rate": 3.911859420179889e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3461760,
      "step": 12360
    },
    {
      "epoch": 137.38888888888889,
      "grad_norm": 1.60664274062583e-06,
      "learning_rate": 3.911049108035813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3463184,
      "step": 12365
    },
    {
      "epoch": 137.44444444444446,
      "grad_norm": 6.556309699590201e-07,
      "learning_rate": 3.910238578290232e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3464624,
      "step": 12370
    },
    {
      "epoch": 137.5,
      "grad_norm": 5.110363190397038e-07,
      "learning_rate": 3.90942783106814e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3466000,
      "step": 12375
    },
    {
      "epoch": 137.55555555555554,
      "grad_norm": 7.384832656498475e-07,
      "learning_rate": 3.908616866494564e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3467344,
      "step": 12380
    },
    {
      "epoch": 137.61111111111111,
      "grad_norm": 1.956307869477314e-06,
      "learning_rate": 3.907805684694566e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3468720,
      "step": 12385
    },
    {
      "epoch": 137.66666666666666,
      "grad_norm": 8.284472983177693e-07,
      "learning_rate": 3.90699428579324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3470064,
      "step": 12390
    },
    {
      "epoch": 137.72222222222223,
      "grad_norm": 6.189928853927995e-07,
      "learning_rate": 3.906182669915713e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3471456,
      "step": 12395
    },
    {
      "epoch": 137.77777777777777,
      "grad_norm": 5.287690214572649e-07,
      "learning_rate": 3.9053708371871476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3472832,
      "step": 12400
    },
    {
      "epoch": 137.77777777777777,
      "eval_loss": 0.3754573464393616,
      "eval_runtime": 1.316,
      "eval_samples_per_second": 30.396,
      "eval_steps_per_second": 15.198,
      "num_input_tokens_seen": 3472832,
      "step": 12400
    },
    {
      "epoch": 137.83333333333334,
      "grad_norm": 7.177836778282654e-07,
      "learning_rate": 3.904558787732738e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3474272,
      "step": 12405
    },
    {
      "epoch": 137.88888888888889,
      "grad_norm": 8.10665255812637e-07,
      "learning_rate": 3.9037465216777135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3475680,
      "step": 12410
    },
    {
      "epoch": 137.94444444444446,
      "grad_norm": 2.4456858227495104e-06,
      "learning_rate": 3.902934039147334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3477088,
      "step": 12415
    },
    {
      "epoch": 138.0,
      "grad_norm": 6.732638553330617e-07,
      "learning_rate": 3.902121340266894e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3478464,
      "step": 12420
    },
    {
      "epoch": 138.05555555555554,
      "grad_norm": 7.334386395996262e-07,
      "learning_rate": 3.9013084251617246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3479888,
      "step": 12425
    },
    {
      "epoch": 138.11111111111111,
      "grad_norm": 5.408567176345969e-07,
      "learning_rate": 3.9004952939571865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3481248,
      "step": 12430
    },
    {
      "epoch": 138.16666666666666,
      "grad_norm": 6.147425324343203e-07,
      "learning_rate": 3.899681946778673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3482624,
      "step": 12435
    },
    {
      "epoch": 138.22222222222223,
      "grad_norm": 6.151388447506179e-07,
      "learning_rate": 3.898868383751615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3484032,
      "step": 12440
    },
    {
      "epoch": 138.27777777777777,
      "grad_norm": 1.3798032796330517e-06,
      "learning_rate": 3.8980546050014724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3485424,
      "step": 12445
    },
    {
      "epoch": 138.33333333333334,
      "grad_norm": 5.380993570724968e-07,
      "learning_rate": 3.897240610653741e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3486832,
      "step": 12450
    },
    {
      "epoch": 138.38888888888889,
      "grad_norm": 1.5895491287665209e-06,
      "learning_rate": 3.896426400833948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3488256,
      "step": 12455
    },
    {
      "epoch": 138.44444444444446,
      "grad_norm": 1.525833454252279e-06,
      "learning_rate": 3.895611975667656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3489632,
      "step": 12460
    },
    {
      "epoch": 138.5,
      "grad_norm": 4.6941281084400543e-07,
      "learning_rate": 3.8947973352804584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3491024,
      "step": 12465
    },
    {
      "epoch": 138.55555555555554,
      "grad_norm": 1.0604525186863611e-06,
      "learning_rate": 3.893982479797984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3492432,
      "step": 12470
    },
    {
      "epoch": 138.61111111111111,
      "grad_norm": 8.011076602087996e-07,
      "learning_rate": 3.8931674093458926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3493872,
      "step": 12475
    },
    {
      "epoch": 138.66666666666666,
      "grad_norm": 6.946843313926365e-07,
      "learning_rate": 3.89235212404988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3495280,
      "step": 12480
    },
    {
      "epoch": 138.72222222222223,
      "grad_norm": 5.62199886644521e-07,
      "learning_rate": 3.891536624035672e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3496688,
      "step": 12485
    },
    {
      "epoch": 138.77777777777777,
      "grad_norm": 1.2170177114967373e-06,
      "learning_rate": 3.8907209094290295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3498096,
      "step": 12490
    },
    {
      "epoch": 138.83333333333334,
      "grad_norm": 6.186311907185882e-07,
      "learning_rate": 3.8899049803557466e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3499488,
      "step": 12495
    },
    {
      "epoch": 138.88888888888889,
      "grad_norm": 6.743177891621599e-07,
      "learning_rate": 3.889088836941648e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3500896,
      "step": 12500
    },
    {
      "epoch": 138.94444444444446,
      "grad_norm": 5.936369120718155e-07,
      "learning_rate": 3.8882724793125946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3502304,
      "step": 12505
    },
    {
      "epoch": 139.0,
      "grad_norm": 1.5764218233016436e-06,
      "learning_rate": 3.8874559075944794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3503728,
      "step": 12510
    },
    {
      "epoch": 139.05555555555554,
      "grad_norm": 6.595529384867405e-07,
      "learning_rate": 3.886639121913227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3505120,
      "step": 12515
    },
    {
      "epoch": 139.11111111111111,
      "grad_norm": 1.191847672998847e-06,
      "learning_rate": 3.885822122394797e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3506512,
      "step": 12520
    },
    {
      "epoch": 139.16666666666666,
      "grad_norm": 6.775793508495553e-07,
      "learning_rate": 3.8850049091651794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3507872,
      "step": 12525
    },
    {
      "epoch": 139.22222222222223,
      "grad_norm": 4.933506829729595e-07,
      "learning_rate": 3.8841874823504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3509248,
      "step": 12530
    },
    {
      "epoch": 139.27777777777777,
      "grad_norm": 6.095615958656708e-07,
      "learning_rate": 3.8833698420765157e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3510640,
      "step": 12535
    },
    {
      "epoch": 139.33333333333334,
      "grad_norm": 7.818484846211504e-07,
      "learning_rate": 3.882551988469618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3512064,
      "step": 12540
    },
    {
      "epoch": 139.38888888888889,
      "grad_norm": 6.36306026535749e-07,
      "learning_rate": 3.881733921655829e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3513472,
      "step": 12545
    },
    {
      "epoch": 139.44444444444446,
      "grad_norm": 4.191212156001711e-06,
      "learning_rate": 3.8809156417613054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3514928,
      "step": 12550
    },
    {
      "epoch": 139.5,
      "grad_norm": 1.1641310493359924e-06,
      "learning_rate": 3.8800971489122364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3516336,
      "step": 12555
    },
    {
      "epoch": 139.55555555555554,
      "grad_norm": 6.293475394159032e-07,
      "learning_rate": 3.8792784432348434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3517728,
      "step": 12560
    },
    {
      "epoch": 139.61111111111111,
      "grad_norm": 5.696815605915617e-07,
      "learning_rate": 3.878459524855381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3519120,
      "step": 12565
    },
    {
      "epoch": 139.66666666666666,
      "grad_norm": 5.868867560820945e-07,
      "learning_rate": 3.8776403939001384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3520512,
      "step": 12570
    },
    {
      "epoch": 139.72222222222223,
      "grad_norm": 5.542293024518585e-07,
      "learning_rate": 3.876821050495433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3521920,
      "step": 12575
    },
    {
      "epoch": 139.77777777777777,
      "grad_norm": 1.1663106533887913e-06,
      "learning_rate": 3.87600149476762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3523360,
      "step": 12580
    },
    {
      "epoch": 139.83333333333334,
      "grad_norm": 7.130690846679499e-07,
      "learning_rate": 3.8751817268430843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3524768,
      "step": 12585
    },
    {
      "epoch": 139.88888888888889,
      "grad_norm": 3.0929879812902072e-06,
      "learning_rate": 3.8743617468482464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3526176,
      "step": 12590
    },
    {
      "epoch": 139.94444444444446,
      "grad_norm": 2.0158518054813612e-06,
      "learning_rate": 3.8735415549095535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3527600,
      "step": 12595
    },
    {
      "epoch": 140.0,
      "grad_norm": 1.1680265288305236e-06,
      "learning_rate": 3.8727211511534934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3529008,
      "step": 12600
    },
    {
      "epoch": 140.0,
      "eval_loss": 0.3278871774673462,
      "eval_runtime": 1.2888,
      "eval_samples_per_second": 31.037,
      "eval_steps_per_second": 15.519,
      "num_input_tokens_seen": 3529008,
      "step": 12600
    },
    {
      "epoch": 140.05555555555554,
      "grad_norm": 7.070514129736694e-07,
      "learning_rate": 3.8719005357065804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3530384,
      "step": 12605
    },
    {
      "epoch": 140.11111111111111,
      "grad_norm": 5.19017248734599e-07,
      "learning_rate": 3.8710797086953645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3531760,
      "step": 12610
    },
    {
      "epoch": 140.16666666666666,
      "grad_norm": 5.601897328233463e-07,
      "learning_rate": 3.870258670246427e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3533152,
      "step": 12615
    },
    {
      "epoch": 140.22222222222223,
      "grad_norm": 8.01972078079416e-07,
      "learning_rate": 3.869437420486384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3534608,
      "step": 12620
    },
    {
      "epoch": 140.27777777777777,
      "grad_norm": 2.033225200648303e-06,
      "learning_rate": 3.8686159595418805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3536016,
      "step": 12625
    },
    {
      "epoch": 140.33333333333334,
      "grad_norm": 1.9401591089263093e-06,
      "learning_rate": 3.867794287539597e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3537408,
      "step": 12630
    },
    {
      "epoch": 140.38888888888889,
      "grad_norm": 5.307039145918679e-07,
      "learning_rate": 3.866972404606245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3538784,
      "step": 12635
    },
    {
      "epoch": 140.44444444444446,
      "grad_norm": 8.022450970202044e-07,
      "learning_rate": 3.866150310868571e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3540192,
      "step": 12640
    },
    {
      "epoch": 140.5,
      "grad_norm": 6.403076326932933e-07,
      "learning_rate": 3.8653280064533506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3541648,
      "step": 12645
    },
    {
      "epoch": 140.55555555555554,
      "grad_norm": 5.946538408352353e-07,
      "learning_rate": 3.864505491487394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3543008,
      "step": 12650
    },
    {
      "epoch": 140.61111111111111,
      "grad_norm": 5.527964503926341e-07,
      "learning_rate": 3.8636827660975414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3544496,
      "step": 12655
    },
    {
      "epoch": 140.66666666666666,
      "grad_norm": 7.568768296550843e-07,
      "learning_rate": 3.862859830410671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3545936,
      "step": 12660
    },
    {
      "epoch": 140.72222222222223,
      "grad_norm": 1.5311923107219627e-06,
      "learning_rate": 3.862036684553688e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3547312,
      "step": 12665
    },
    {
      "epoch": 140.77777777777777,
      "grad_norm": 6.983672165006283e-07,
      "learning_rate": 3.8612133286535314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3548736,
      "step": 12670
    },
    {
      "epoch": 140.83333333333334,
      "grad_norm": 6.482575827249093e-07,
      "learning_rate": 3.860389762837173e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3550112,
      "step": 12675
    },
    {
      "epoch": 140.88888888888889,
      "grad_norm": 5.805524097013404e-07,
      "learning_rate": 3.859565987231618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3551456,
      "step": 12680
    },
    {
      "epoch": 140.94444444444446,
      "grad_norm": 6.111209245318605e-07,
      "learning_rate": 3.858742001963902e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3552912,
      "step": 12685
    },
    {
      "epoch": 141.0,
      "grad_norm": 1.5001405699877068e-06,
      "learning_rate": 3.857917807161094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3554304,
      "step": 12690
    },
    {
      "epoch": 141.05555555555554,
      "grad_norm": 1.4460659940596088e-06,
      "learning_rate": 3.857093402950296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3555744,
      "step": 12695
    },
    {
      "epoch": 141.11111111111111,
      "grad_norm": 3.120380597465555e-06,
      "learning_rate": 3.8562687894586414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3557184,
      "step": 12700
    },
    {
      "epoch": 141.16666666666666,
      "grad_norm": 1.38732150389842e-06,
      "learning_rate": 3.8554439668132946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3558592,
      "step": 12705
    },
    {
      "epoch": 141.22222222222223,
      "grad_norm": 6.384246376001101e-07,
      "learning_rate": 3.854618935141455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3559984,
      "step": 12710
    },
    {
      "epoch": 141.27777777777777,
      "grad_norm": 8.361814138879708e-07,
      "learning_rate": 3.8537936945703525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3561360,
      "step": 12715
    },
    {
      "epoch": 141.33333333333334,
      "grad_norm": 1.9563337900763145e-06,
      "learning_rate": 3.852968245227249e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3562768,
      "step": 12720
    },
    {
      "epoch": 141.38888888888889,
      "grad_norm": 6.957631626391958e-07,
      "learning_rate": 3.85214258723944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3564176,
      "step": 12725
    },
    {
      "epoch": 141.44444444444446,
      "grad_norm": 6.33976185326901e-07,
      "learning_rate": 3.8513167207342524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3565552,
      "step": 12730
    },
    {
      "epoch": 141.5,
      "grad_norm": 1.5429221775775659e-06,
      "learning_rate": 3.850490645839044e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3566928,
      "step": 12735
    },
    {
      "epoch": 141.55555555555554,
      "grad_norm": 6.296699552876817e-07,
      "learning_rate": 3.849664362681207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3568352,
      "step": 12740
    },
    {
      "epoch": 141.61111111111111,
      "grad_norm": 6.871713935652224e-07,
      "learning_rate": 3.848837871388165e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3569744,
      "step": 12745
    },
    {
      "epoch": 141.66666666666666,
      "grad_norm": 7.172241680564184e-07,
      "learning_rate": 3.848011172087371e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3571088,
      "step": 12750
    },
    {
      "epoch": 141.72222222222223,
      "grad_norm": 1.5119215959202847e-06,
      "learning_rate": 3.847184264906315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3572496,
      "step": 12755
    },
    {
      "epoch": 141.77777777777777,
      "grad_norm": 1.0622361514833756e-06,
      "learning_rate": 3.846357149972516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3573920,
      "step": 12760
    },
    {
      "epoch": 141.83333333333334,
      "grad_norm": 6.801881227147533e-07,
      "learning_rate": 3.8455298274135246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3575264,
      "step": 12765
    },
    {
      "epoch": 141.88888888888889,
      "grad_norm": 6.936230647625052e-07,
      "learning_rate": 3.8447022973569254e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3576672,
      "step": 12770
    },
    {
      "epoch": 141.94444444444446,
      "grad_norm": 6.571565904778254e-07,
      "learning_rate": 3.843874559930332e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3578112,
      "step": 12775
    },
    {
      "epoch": 142.0,
      "grad_norm": 5.224597430242284e-07,
      "learning_rate": 3.843046615261394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3579568,
      "step": 12780
    },
    {
      "epoch": 142.05555555555554,
      "grad_norm": 1.3925960047345143e-06,
      "learning_rate": 3.842218463477791e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3581008,
      "step": 12785
    },
    {
      "epoch": 142.11111111111111,
      "grad_norm": 5.555187385652971e-07,
      "learning_rate": 3.841390104707233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3582416,
      "step": 12790
    },
    {
      "epoch": 142.16666666666666,
      "grad_norm": 7.107871624612017e-07,
      "learning_rate": 3.8405615390774643e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3583840,
      "step": 12795
    },
    {
      "epoch": 142.22222222222223,
      "grad_norm": 6.569005677192763e-07,
      "learning_rate": 3.839732766716259e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3585200,
      "step": 12800
    },
    {
      "epoch": 142.22222222222223,
      "eval_loss": 0.30285048484802246,
      "eval_runtime": 1.3452,
      "eval_samples_per_second": 29.735,
      "eval_steps_per_second": 14.867,
      "num_input_tokens_seen": 3585200,
      "step": 12800
    },
    {
      "epoch": 142.27777777777777,
      "grad_norm": 6.41763620023994e-07,
      "learning_rate": 3.838903787751425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3586640,
      "step": 12805
    },
    {
      "epoch": 142.33333333333334,
      "grad_norm": 3.382428076292854e-06,
      "learning_rate": 3.838074602310802e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3588032,
      "step": 12810
    },
    {
      "epoch": 142.38888888888889,
      "grad_norm": 6.122628519733553e-07,
      "learning_rate": 3.837245210522258e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3589424,
      "step": 12815
    },
    {
      "epoch": 142.44444444444446,
      "grad_norm": 1.5851876469241688e-06,
      "learning_rate": 3.8364156125136996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3590832,
      "step": 12820
    },
    {
      "epoch": 142.5,
      "grad_norm": 1.4800502867728937e-06,
      "learning_rate": 3.835585808413059e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3592256,
      "step": 12825
    },
    {
      "epoch": 142.55555555555554,
      "grad_norm": 5.251675361250818e-07,
      "learning_rate": 3.8347557983483024e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3593632,
      "step": 12830
    },
    {
      "epoch": 142.61111111111111,
      "grad_norm": 1.5154965922192787e-06,
      "learning_rate": 3.833925582447428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3594976,
      "step": 12835
    },
    {
      "epoch": 142.66666666666666,
      "grad_norm": 7.099833965185098e-07,
      "learning_rate": 3.8330951608384656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3596400,
      "step": 12840
    },
    {
      "epoch": 142.72222222222223,
      "grad_norm": 7.062961344672658e-07,
      "learning_rate": 3.832264533649477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3597824,
      "step": 12845
    },
    {
      "epoch": 142.77777777777777,
      "grad_norm": 7.398648449452594e-07,
      "learning_rate": 3.8314337010085555e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3599200,
      "step": 12850
    },
    {
      "epoch": 142.83333333333334,
      "grad_norm": 1.5502906762776547e-06,
      "learning_rate": 3.830602663043824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3600624,
      "step": 12855
    },
    {
      "epoch": 142.88888888888889,
      "grad_norm": 1.2725573697025538e-06,
      "learning_rate": 3.8297714198834414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3602032,
      "step": 12860
    },
    {
      "epoch": 142.94444444444446,
      "grad_norm": 6.34857485692919e-07,
      "learning_rate": 3.828939971655595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3603408,
      "step": 12865
    },
    {
      "epoch": 143.0,
      "grad_norm": 6.69119060603407e-07,
      "learning_rate": 3.828108318488505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3604848,
      "step": 12870
    },
    {
      "epoch": 143.05555555555554,
      "grad_norm": 1.104342118196655e-06,
      "learning_rate": 3.8272764605104216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3606256,
      "step": 12875
    },
    {
      "epoch": 143.11111111111111,
      "grad_norm": 4.032664037367795e-06,
      "learning_rate": 3.826444397849628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3607632,
      "step": 12880
    },
    {
      "epoch": 143.16666666666666,
      "grad_norm": 6.793546276639972e-07,
      "learning_rate": 3.825612130634439e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3608992,
      "step": 12885
    },
    {
      "epoch": 143.22222222222223,
      "grad_norm": 1.6128757351907552e-06,
      "learning_rate": 3.824779658993202e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3610400,
      "step": 12890
    },
    {
      "epoch": 143.27777777777777,
      "grad_norm": 7.015474920990528e-07,
      "learning_rate": 3.823946983054292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3611840,
      "step": 12895
    },
    {
      "epoch": 143.33333333333334,
      "grad_norm": 1.8499546285966062e-06,
      "learning_rate": 3.82311410294612e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3613216,
      "step": 12900
    },
    {
      "epoch": 143.38888888888889,
      "grad_norm": 2.1041842046543024e-06,
      "learning_rate": 3.822281018797127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3614608,
      "step": 12905
    },
    {
      "epoch": 143.44444444444446,
      "grad_norm": 2.1078660665807547e-06,
      "learning_rate": 3.821447730735783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3616048,
      "step": 12910
    },
    {
      "epoch": 143.5,
      "grad_norm": 2.1647238099831156e-06,
      "learning_rate": 3.820614238890592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3617440,
      "step": 12915
    },
    {
      "epoch": 143.55555555555554,
      "grad_norm": 6.038015953890863e-07,
      "learning_rate": 3.819780543390091e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3618832,
      "step": 12920
    },
    {
      "epoch": 143.61111111111111,
      "grad_norm": 6.537762828884297e-07,
      "learning_rate": 3.818946644362844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3620240,
      "step": 12925
    },
    {
      "epoch": 143.66666666666666,
      "grad_norm": 7.273783921846189e-07,
      "learning_rate": 3.81811254193745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3621664,
      "step": 12930
    },
    {
      "epoch": 143.72222222222223,
      "grad_norm": 6.934453153917275e-07,
      "learning_rate": 3.8172782362425366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3623056,
      "step": 12935
    },
    {
      "epoch": 143.77777777777777,
      "grad_norm": 5.955799906587345e-07,
      "learning_rate": 3.816443727406765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3624496,
      "step": 12940
    },
    {
      "epoch": 143.83333333333334,
      "grad_norm": 6.529610914185469e-07,
      "learning_rate": 3.815609015558829e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3625888,
      "step": 12945
    },
    {
      "epoch": 143.88888888888889,
      "grad_norm": 2.4249825401057024e-06,
      "learning_rate": 3.814774100827448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3627264,
      "step": 12950
    },
    {
      "epoch": 143.94444444444446,
      "grad_norm": 1.4760722706341767e-06,
      "learning_rate": 3.813938983341379e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3628640,
      "step": 12955
    },
    {
      "epoch": 144.0,
      "grad_norm": 1.4677914350613719e-06,
      "learning_rate": 3.813103663229407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3630016,
      "step": 12960
    },
    {
      "epoch": 144.05555555555554,
      "grad_norm": 6.877629630253068e-07,
      "learning_rate": 3.812268140620349e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3631424,
      "step": 12965
    },
    {
      "epoch": 144.11111111111111,
      "grad_norm": 5.35778838184342e-07,
      "learning_rate": 3.811432415643051e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3632800,
      "step": 12970
    },
    {
      "epoch": 144.16666666666666,
      "grad_norm": 1.4294545280790771e-06,
      "learning_rate": 3.8105964884263954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3634192,
      "step": 12975
    },
    {
      "epoch": 144.22222222222223,
      "grad_norm": 5.627869654745155e-07,
      "learning_rate": 3.809760359099291e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3635632,
      "step": 12980
    },
    {
      "epoch": 144.27777777777777,
      "grad_norm": 6.924610147507337e-07,
      "learning_rate": 3.8089240277906804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3636976,
      "step": 12985
    },
    {
      "epoch": 144.33333333333334,
      "grad_norm": 1.4836102764093084e-06,
      "learning_rate": 3.808087494629535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3638368,
      "step": 12990
    },
    {
      "epoch": 144.38888888888889,
      "grad_norm": 6.722243028889352e-07,
      "learning_rate": 3.8072507597448595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3639744,
      "step": 12995
    },
    {
      "epoch": 144.44444444444446,
      "grad_norm": 2.7085061446996406e-06,
      "learning_rate": 3.806413823265689e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3641200,
      "step": 13000
    },
    {
      "epoch": 144.44444444444446,
      "eval_loss": 0.3639534115791321,
      "eval_runtime": 1.3234,
      "eval_samples_per_second": 30.225,
      "eval_steps_per_second": 15.112,
      "num_input_tokens_seen": 3641200,
      "step": 13000
    },
    {
      "epoch": 144.5,
      "grad_norm": 2.1356527213356458e-06,
      "learning_rate": 3.805576685321089e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3642592,
      "step": 13005
    },
    {
      "epoch": 144.55555555555554,
      "grad_norm": 5.231850650488923e-07,
      "learning_rate": 3.804739346040158e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3643984,
      "step": 13010
    },
    {
      "epoch": 144.61111111111111,
      "grad_norm": 8.487873515150568e-07,
      "learning_rate": 3.8039018055520234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3645360,
      "step": 13015
    },
    {
      "epoch": 144.66666666666666,
      "grad_norm": 5.954084372206125e-07,
      "learning_rate": 3.803064063985844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3646784,
      "step": 13020
    },
    {
      "epoch": 144.72222222222223,
      "grad_norm": 6.418089810722449e-07,
      "learning_rate": 3.802226121470811e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3648192,
      "step": 13025
    },
    {
      "epoch": 144.77777777777777,
      "grad_norm": 5.272313501336612e-07,
      "learning_rate": 3.801387978136145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3649584,
      "step": 13030
    },
    {
      "epoch": 144.83333333333334,
      "grad_norm": 7.668246553294011e-07,
      "learning_rate": 3.800549634111099e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3650976,
      "step": 13035
    },
    {
      "epoch": 144.88888888888889,
      "grad_norm": 6.893287718412466e-07,
      "learning_rate": 3.799711089524955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3652384,
      "step": 13040
    },
    {
      "epoch": 144.94444444444446,
      "grad_norm": 1.1711794059010572e-06,
      "learning_rate": 3.7988723445070285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3653792,
      "step": 13045
    },
    {
      "epoch": 145.0,
      "grad_norm": 1.3220660548540764e-06,
      "learning_rate": 3.798033399186663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3655216,
      "step": 13050
    },
    {
      "epoch": 145.05555555555554,
      "grad_norm": 7.266029342645197e-07,
      "learning_rate": 3.797194253693237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3656640,
      "step": 13055
    },
    {
      "epoch": 145.11111111111111,
      "grad_norm": 5.815659278596286e-07,
      "learning_rate": 3.796354908156153e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3658032,
      "step": 13060
    },
    {
      "epoch": 145.16666666666666,
      "grad_norm": 5.038505719312525e-07,
      "learning_rate": 3.795515362704853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3659392,
      "step": 13065
    },
    {
      "epoch": 145.22222222222223,
      "grad_norm": 6.849801366115571e-07,
      "learning_rate": 3.794675617468803e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3660768,
      "step": 13070
    },
    {
      "epoch": 145.27777777777777,
      "grad_norm": 8.723037012714485e-07,
      "learning_rate": 3.793835672577503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3662192,
      "step": 13075
    },
    {
      "epoch": 145.33333333333334,
      "grad_norm": 8.32216358048754e-07,
      "learning_rate": 3.7929955281604826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3663600,
      "step": 13080
    },
    {
      "epoch": 145.38888888888889,
      "grad_norm": 3.776317498704884e-06,
      "learning_rate": 3.7921551843473036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3664992,
      "step": 13085
    },
    {
      "epoch": 145.44444444444446,
      "grad_norm": 6.303778832261742e-07,
      "learning_rate": 3.791314641267557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3666384,
      "step": 13090
    },
    {
      "epoch": 145.5,
      "grad_norm": 4.537644997526513e-07,
      "learning_rate": 3.790473899050864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3667792,
      "step": 13095
    },
    {
      "epoch": 145.55555555555554,
      "grad_norm": 5.936349793955742e-07,
      "learning_rate": 3.7896329578268794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3669200,
      "step": 13100
    },
    {
      "epoch": 145.61111111111111,
      "grad_norm": 5.355722692002018e-07,
      "learning_rate": 3.7887918177252855e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3670560,
      "step": 13105
    },
    {
      "epoch": 145.66666666666666,
      "grad_norm": 4.133619029289548e-07,
      "learning_rate": 3.787950478875798e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3671952,
      "step": 13110
    },
    {
      "epoch": 145.72222222222223,
      "grad_norm": 1.5145224097068422e-06,
      "learning_rate": 3.787108941408162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3673360,
      "step": 13115
    },
    {
      "epoch": 145.77777777777777,
      "grad_norm": 6.816474638071668e-07,
      "learning_rate": 3.786267205452151e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3674736,
      "step": 13120
    },
    {
      "epoch": 145.83333333333334,
      "grad_norm": 1.4275636885940912e-06,
      "learning_rate": 3.785425271137573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3676144,
      "step": 13125
    },
    {
      "epoch": 145.88888888888889,
      "grad_norm": 6.915034305166046e-07,
      "learning_rate": 3.7845831385942655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3677584,
      "step": 13130
    },
    {
      "epoch": 145.94444444444446,
      "grad_norm": 5.133519493938365e-07,
      "learning_rate": 3.7837408079520944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3679008,
      "step": 13135
    },
    {
      "epoch": 146.0,
      "grad_norm": 6.811860089328547e-07,
      "learning_rate": 3.782898279340957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3680432,
      "step": 13140
    },
    {
      "epoch": 146.05555555555554,
      "grad_norm": 1.4280144569056574e-06,
      "learning_rate": 3.782055552890784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3681808,
      "step": 13145
    },
    {
      "epoch": 146.11111111111111,
      "grad_norm": 6.372029019985348e-07,
      "learning_rate": 3.781212628731534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3683200,
      "step": 13150
    },
    {
      "epoch": 146.16666666666666,
      "grad_norm": 1.11910719624575e-06,
      "learning_rate": 3.7803695069931946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3684608,
      "step": 13155
    },
    {
      "epoch": 146.22222222222223,
      "grad_norm": 7.529035883635515e-07,
      "learning_rate": 3.779526187805789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3686064,
      "step": 13160
    },
    {
      "epoch": 146.27777777777777,
      "grad_norm": 6.119097974988108e-07,
      "learning_rate": 3.778682671299364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3687456,
      "step": 13165
    },
    {
      "epoch": 146.33333333333334,
      "grad_norm": 7.156582455536409e-07,
      "learning_rate": 3.777838957604003e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3688800,
      "step": 13170
    },
    {
      "epoch": 146.38888888888889,
      "grad_norm": 7.500234460167121e-07,
      "learning_rate": 3.776995046849816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3690208,
      "step": 13175
    },
    {
      "epoch": 146.44444444444446,
      "grad_norm": 1.6315946140821325e-06,
      "learning_rate": 3.776150939166945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3691616,
      "step": 13180
    },
    {
      "epoch": 146.5,
      "grad_norm": 6.494549893432122e-07,
      "learning_rate": 3.775306634685562e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3693008,
      "step": 13185
    },
    {
      "epoch": 146.55555555555554,
      "grad_norm": 6.045777354302118e-07,
      "learning_rate": 3.7744621335358696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3694448,
      "step": 13190
    },
    {
      "epoch": 146.61111111111111,
      "grad_norm": 5.515825023394427e-07,
      "learning_rate": 3.7736174358481e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3695840,
      "step": 13195
    },
    {
      "epoch": 146.66666666666666,
      "grad_norm": 3.3640624224062776e-06,
      "learning_rate": 3.7727725417525175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3697232,
      "step": 13200
    },
    {
      "epoch": 146.66666666666666,
      "eval_loss": 0.3433644771575928,
      "eval_runtime": 1.3302,
      "eval_samples_per_second": 30.07,
      "eval_steps_per_second": 15.035,
      "num_input_tokens_seen": 3697232,
      "step": 13200
    },
    {
      "epoch": 146.72222222222223,
      "grad_norm": 1.586185248925176e-06,
      "learning_rate": 3.771927451379414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3698624,
      "step": 13205
    },
    {
      "epoch": 146.77777777777777,
      "grad_norm": 7.555447041340813e-07,
      "learning_rate": 3.7710821648591135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3700064,
      "step": 13210
    },
    {
      "epoch": 146.83333333333334,
      "grad_norm": 8.934412676353531e-07,
      "learning_rate": 3.7702366823219694e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3701440,
      "step": 13215
    },
    {
      "epoch": 146.88888888888889,
      "grad_norm": 1.447053818992572e-06,
      "learning_rate": 3.769391003898366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3702832,
      "step": 13220
    },
    {
      "epoch": 146.94444444444446,
      "grad_norm": 1.6119918200274697e-06,
      "learning_rate": 3.768545129718718e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3704192,
      "step": 13225
    },
    {
      "epoch": 147.0,
      "grad_norm": 5.725685241486644e-07,
      "learning_rate": 3.7676990599134686e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3705584,
      "step": 13230
    },
    {
      "epoch": 147.05555555555554,
      "grad_norm": 1.6359762184947613e-06,
      "learning_rate": 3.766852794613095e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3706960,
      "step": 13235
    },
    {
      "epoch": 147.11111111111111,
      "grad_norm": 6.436872581616626e-07,
      "learning_rate": 3.766006333948099e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3708336,
      "step": 13240
    },
    {
      "epoch": 147.16666666666666,
      "grad_norm": 7.292339887499111e-07,
      "learning_rate": 3.765159678049017e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3709712,
      "step": 13245
    },
    {
      "epoch": 147.22222222222223,
      "grad_norm": 1.3710791790799703e-06,
      "learning_rate": 3.7643128270464134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3711152,
      "step": 13250
    },
    {
      "epoch": 147.27777777777777,
      "grad_norm": 7.729234425823961e-07,
      "learning_rate": 3.763465781070884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3712544,
      "step": 13255
    },
    {
      "epoch": 147.33333333333334,
      "grad_norm": 5.138556389283622e-07,
      "learning_rate": 3.762618540253052e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3713968,
      "step": 13260
    },
    {
      "epoch": 147.38888888888889,
      "grad_norm": 5.879937248209899e-07,
      "learning_rate": 3.761771104723576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3715376,
      "step": 13265
    },
    {
      "epoch": 147.44444444444446,
      "grad_norm": 7.094526495166065e-07,
      "learning_rate": 3.7609234746131386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3716816,
      "step": 13270
    },
    {
      "epoch": 147.5,
      "grad_norm": 3.3042138056771364e-06,
      "learning_rate": 3.7600756500524556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3718160,
      "step": 13275
    },
    {
      "epoch": 147.55555555555554,
      "grad_norm": 7.66357516113203e-07,
      "learning_rate": 3.759227631172271e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3719552,
      "step": 13280
    },
    {
      "epoch": 147.61111111111111,
      "grad_norm": 1.577832222210418e-06,
      "learning_rate": 3.758379418103363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3720944,
      "step": 13285
    },
    {
      "epoch": 147.66666666666666,
      "grad_norm": 5.701832037630084e-07,
      "learning_rate": 3.757531010976534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3722352,
      "step": 13290
    },
    {
      "epoch": 147.72222222222223,
      "grad_norm": 5.189527882976108e-07,
      "learning_rate": 3.75668240992262e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3723728,
      "step": 13295
    },
    {
      "epoch": 147.77777777777777,
      "grad_norm": 1.5319033082050737e-06,
      "learning_rate": 3.7558336150724865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3725152,
      "step": 13300
    },
    {
      "epoch": 147.83333333333334,
      "grad_norm": 6.548425517394207e-07,
      "learning_rate": 3.754984626557028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3726528,
      "step": 13305
    },
    {
      "epoch": 147.88888888888889,
      "grad_norm": 5.517434829016565e-07,
      "learning_rate": 3.754135444507168e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3727920,
      "step": 13310
    },
    {
      "epoch": 147.94444444444446,
      "grad_norm": 1.5631308087904472e-06,
      "learning_rate": 3.753286069053863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3729360,
      "step": 13315
    },
    {
      "epoch": 148.0,
      "grad_norm": 4.418190201249672e-06,
      "learning_rate": 3.7524365003280945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3730784,
      "step": 13320
    },
    {
      "epoch": 148.05555555555554,
      "grad_norm": 6.876143174849858e-07,
      "learning_rate": 3.75158673846088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3732144,
      "step": 13325
    },
    {
      "epoch": 148.11111111111111,
      "grad_norm": 4.515158877893555e-07,
      "learning_rate": 3.750736783583262e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3733584,
      "step": 13330
    },
    {
      "epoch": 148.16666666666666,
      "grad_norm": 7.331220785999903e-07,
      "learning_rate": 3.7498866358263144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3735008,
      "step": 13335
    },
    {
      "epoch": 148.22222222222223,
      "grad_norm": 1.5139156630539219e-06,
      "learning_rate": 3.74903629532114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3736416,
      "step": 13340
    },
    {
      "epoch": 148.27777777777777,
      "grad_norm": 5.67352856251091e-07,
      "learning_rate": 3.748185762198873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3737888,
      "step": 13345
    },
    {
      "epoch": 148.33333333333334,
      "grad_norm": 7.505076951019873e-07,
      "learning_rate": 3.747335036590676e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3739296,
      "step": 13350
    },
    {
      "epoch": 148.38888888888889,
      "grad_norm": 3.399838533368893e-06,
      "learning_rate": 3.7464841186277405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3740672,
      "step": 13355
    },
    {
      "epoch": 148.44444444444446,
      "grad_norm": 1.8894287450166303e-06,
      "learning_rate": 3.7456330084412896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3742128,
      "step": 13360
    },
    {
      "epoch": 148.5,
      "grad_norm": 8.015961157070706e-07,
      "learning_rate": 3.744781706162576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3743472,
      "step": 13365
    },
    {
      "epoch": 148.55555555555554,
      "grad_norm": 6.983401021898317e-07,
      "learning_rate": 3.743930211922879e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3744816,
      "step": 13370
    },
    {
      "epoch": 148.61111111111111,
      "grad_norm": 5.125164079800015e-07,
      "learning_rate": 3.743078525853513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3746192,
      "step": 13375
    },
    {
      "epoch": 148.66666666666666,
      "grad_norm": 1.5696173250034917e-06,
      "learning_rate": 3.7422266480858154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3747584,
      "step": 13380
    },
    {
      "epoch": 148.72222222222223,
      "grad_norm": 9.625441634852905e-07,
      "learning_rate": 3.741374578751158e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3748960,
      "step": 13385
    },
    {
      "epoch": 148.77777777777777,
      "grad_norm": 5.790355430690397e-07,
      "learning_rate": 3.740522317980941e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3750384,
      "step": 13390
    },
    {
      "epoch": 148.83333333333334,
      "grad_norm": 1.5334546787926229e-06,
      "learning_rate": 3.739669865906593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3751728,
      "step": 13395
    },
    {
      "epoch": 148.88888888888889,
      "grad_norm": 7.084812523316941e-07,
      "learning_rate": 3.738817222659573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3753168,
      "step": 13400
    },
    {
      "epoch": 148.88888888888889,
      "eval_loss": 0.37274837493896484,
      "eval_runtime": 1.3216,
      "eval_samples_per_second": 30.266,
      "eval_steps_per_second": 15.133,
      "num_input_tokens_seen": 3753168,
      "step": 13400
    },
    {
      "epoch": 148.94444444444446,
      "grad_norm": 7.843246976335649e-07,
      "learning_rate": 3.73796438837137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3754576,
      "step": 13405
    },
    {
      "epoch": 149.0,
      "grad_norm": 6.948108648430207e-07,
      "learning_rate": 3.7371113631735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3755984,
      "step": 13410
    },
    {
      "epoch": 149.05555555555554,
      "grad_norm": 1.3359582453631447e-06,
      "learning_rate": 3.736258147197512e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3757344,
      "step": 13415
    },
    {
      "epoch": 149.11111111111111,
      "grad_norm": 5.955783990430064e-07,
      "learning_rate": 3.735404740574981e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3758704,
      "step": 13420
    },
    {
      "epoch": 149.16666666666666,
      "grad_norm": 8.151707788783824e-07,
      "learning_rate": 3.7345511434375145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3760112,
      "step": 13425
    },
    {
      "epoch": 149.22222222222223,
      "grad_norm": 2.7621299523161724e-06,
      "learning_rate": 3.733697355916748e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3761520,
      "step": 13430
    },
    {
      "epoch": 149.27777777777777,
      "grad_norm": 7.664463623768825e-07,
      "learning_rate": 3.732843378144345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3762896,
      "step": 13435
    },
    {
      "epoch": 149.33333333333334,
      "grad_norm": 7.627746754224063e-07,
      "learning_rate": 3.7319892102519995e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3764320,
      "step": 13440
    },
    {
      "epoch": 149.38888888888889,
      "grad_norm": 6.32300213965209e-07,
      "learning_rate": 3.731134852371436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3765744,
      "step": 13445
    },
    {
      "epoch": 149.44444444444446,
      "grad_norm": 7.299067874555476e-07,
      "learning_rate": 3.730280304634408e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3767152,
      "step": 13450
    },
    {
      "epoch": 149.5,
      "grad_norm": 1.1472451433292008e-06,
      "learning_rate": 3.729425567172696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3768544,
      "step": 13455
    },
    {
      "epoch": 149.55555555555554,
      "grad_norm": 7.753884005978762e-07,
      "learning_rate": 3.728570640118111e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3769952,
      "step": 13460
    },
    {
      "epoch": 149.61111111111111,
      "grad_norm": 1.4365377865033224e-06,
      "learning_rate": 3.727715523602494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3771360,
      "step": 13465
    },
    {
      "epoch": 149.66666666666666,
      "grad_norm": 1.460506268813333e-06,
      "learning_rate": 3.726860217757715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3772768,
      "step": 13470
    },
    {
      "epoch": 149.72222222222223,
      "grad_norm": 6.348146825985168e-07,
      "learning_rate": 3.726004722715673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3774176,
      "step": 13475
    },
    {
      "epoch": 149.77777777777777,
      "grad_norm": 8.5167778252071e-07,
      "learning_rate": 3.725149038608296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3775600,
      "step": 13480
    },
    {
      "epoch": 149.83333333333334,
      "grad_norm": 6.244199539651163e-07,
      "learning_rate": 3.7242931655675404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3776976,
      "step": 13485
    },
    {
      "epoch": 149.88888888888889,
      "grad_norm": 7.751240787001734e-07,
      "learning_rate": 3.7234371037253937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3778336,
      "step": 13490
    },
    {
      "epoch": 149.94444444444446,
      "grad_norm": 1.6483406852785265e-06,
      "learning_rate": 3.7225808532138705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3779744,
      "step": 13495
    },
    {
      "epoch": 150.0,
      "grad_norm": 7.821052463441447e-07,
      "learning_rate": 3.721724414165016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3781120,
      "step": 13500
    },
    {
      "epoch": 150.05555555555554,
      "grad_norm": 1.117832198360702e-06,
      "learning_rate": 3.720867786710904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3782480,
      "step": 13505
    },
    {
      "epoch": 150.11111111111111,
      "grad_norm": 6.56807173982088e-07,
      "learning_rate": 3.7200109709836366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3783888,
      "step": 13510
    },
    {
      "epoch": 150.16666666666666,
      "grad_norm": 8.028030151763232e-07,
      "learning_rate": 3.7191539671153465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3785296,
      "step": 13515
    },
    {
      "epoch": 150.22222222222223,
      "grad_norm": 1.3642808198710554e-06,
      "learning_rate": 3.718296775238193e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3786656,
      "step": 13520
    },
    {
      "epoch": 150.27777777777777,
      "grad_norm": 1.5266292621163302e-06,
      "learning_rate": 3.7174393954843675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3788096,
      "step": 13525
    },
    {
      "epoch": 150.33333333333334,
      "grad_norm": 6.153050549073669e-07,
      "learning_rate": 3.716581827986087e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3789472,
      "step": 13530
    },
    {
      "epoch": 150.38888888888889,
      "grad_norm": 1.5755127833472216e-06,
      "learning_rate": 3.7157240728756004e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3790896,
      "step": 13535
    },
    {
      "epoch": 150.44444444444446,
      "grad_norm": 6.897904540892341e-07,
      "learning_rate": 3.714866130285184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3792272,
      "step": 13540
    },
    {
      "epoch": 150.5,
      "grad_norm": 7.960027801345859e-07,
      "learning_rate": 3.714008000347143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3793664,
      "step": 13545
    },
    {
      "epoch": 150.55555555555554,
      "grad_norm": 2.0387840322655393e-06,
      "learning_rate": 3.7131496831938126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3795104,
      "step": 13550
    },
    {
      "epoch": 150.61111111111111,
      "grad_norm": 2.560178927524248e-06,
      "learning_rate": 3.7122911789575565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3796528,
      "step": 13555
    },
    {
      "epoch": 150.66666666666666,
      "grad_norm": 6.492533657365129e-07,
      "learning_rate": 3.711432487770765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3797888,
      "step": 13560
    },
    {
      "epoch": 150.72222222222223,
      "grad_norm": 5.322158926901466e-07,
      "learning_rate": 3.710573609765861e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3799328,
      "step": 13565
    },
    {
      "epoch": 150.77777777777777,
      "grad_norm": 5.862950160917535e-07,
      "learning_rate": 3.709714545075292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3800736,
      "step": 13570
    },
    {
      "epoch": 150.83333333333334,
      "grad_norm": 8.487098739351495e-07,
      "learning_rate": 3.708855293831538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3802096,
      "step": 13575
    },
    {
      "epoch": 150.88888888888889,
      "grad_norm": 7.395794341391593e-07,
      "learning_rate": 3.707995856167107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3803520,
      "step": 13580
    },
    {
      "epoch": 150.94444444444446,
      "grad_norm": 1.510749029876024e-06,
      "learning_rate": 3.707136232214534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3804880,
      "step": 13585
    },
    {
      "epoch": 151.0,
      "grad_norm": 1.099586938835273e-06,
      "learning_rate": 3.7062764221063844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3806304,
      "step": 13590
    },
    {
      "epoch": 151.05555555555554,
      "grad_norm": 6.459734436248254e-07,
      "learning_rate": 3.705416425975252e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3807712,
      "step": 13595
    },
    {
      "epoch": 151.11111111111111,
      "grad_norm": 6.401184577953245e-07,
      "learning_rate": 3.704556243953758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3809136,
      "step": 13600
    },
    {
      "epoch": 151.11111111111111,
      "eval_loss": 0.35036537051200867,
      "eval_runtime": 1.3417,
      "eval_samples_per_second": 29.814,
      "eval_steps_per_second": 14.907,
      "num_input_tokens_seen": 3809136,
      "step": 13600
    },
    {
      "epoch": 151.16666666666666,
      "grad_norm": 5.37437699676957e-07,
      "learning_rate": 3.7036958761745535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3810512,
      "step": 13605
    },
    {
      "epoch": 151.22222222222223,
      "grad_norm": 3.1579834285366815e-06,
      "learning_rate": 3.702835322770318e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3811936,
      "step": 13610
    },
    {
      "epoch": 151.27777777777777,
      "grad_norm": 1.1844579148601042e-06,
      "learning_rate": 3.701974583873761e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3813392,
      "step": 13615
    },
    {
      "epoch": 151.33333333333334,
      "grad_norm": 4.205248842481524e-06,
      "learning_rate": 3.701113659617618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3814784,
      "step": 13620
    },
    {
      "epoch": 151.38888888888889,
      "grad_norm": 5.516355940926587e-07,
      "learning_rate": 3.7002525501346535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3816208,
      "step": 13625
    },
    {
      "epoch": 151.44444444444446,
      "grad_norm": 5.769109066022793e-07,
      "learning_rate": 3.699391255557664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3817568,
      "step": 13630
    },
    {
      "epoch": 151.5,
      "grad_norm": 1.612310597920441e-06,
      "learning_rate": 3.69852977601947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3818896,
      "step": 13635
    },
    {
      "epoch": 151.55555555555554,
      "grad_norm": 6.956424272175354e-07,
      "learning_rate": 3.697668111652922e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3820288,
      "step": 13640
    },
    {
      "epoch": 151.61111111111111,
      "grad_norm": 5.743312385675381e-07,
      "learning_rate": 3.6968062625909005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3821696,
      "step": 13645
    },
    {
      "epoch": 151.66666666666666,
      "grad_norm": 8.456945579382591e-07,
      "learning_rate": 3.6959442289663135e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3823104,
      "step": 13650
    },
    {
      "epoch": 151.72222222222223,
      "grad_norm": 1.433191300748149e-06,
      "learning_rate": 3.695082010912098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3824496,
      "step": 13655
    },
    {
      "epoch": 151.77777777777777,
      "grad_norm": 7.81710639330413e-07,
      "learning_rate": 3.694219608561217e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3825888,
      "step": 13660
    },
    {
      "epoch": 151.83333333333334,
      "grad_norm": 1.4620453612224082e-06,
      "learning_rate": 3.693357022046665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3827296,
      "step": 13665
    },
    {
      "epoch": 151.88888888888889,
      "grad_norm": 1.6139809986270848e-06,
      "learning_rate": 3.6924942515014644e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3828688,
      "step": 13670
    },
    {
      "epoch": 151.94444444444446,
      "grad_norm": 6.332688258225971e-07,
      "learning_rate": 3.691631297058664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3830176,
      "step": 13675
    },
    {
      "epoch": 152.0,
      "grad_norm": 6.828394703006779e-07,
      "learning_rate": 3.6907681588513424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3831584,
      "step": 13680
    },
    {
      "epoch": 152.05555555555554,
      "grad_norm": 6.476768703578273e-07,
      "learning_rate": 3.689904837012606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3832960,
      "step": 13685
    },
    {
      "epoch": 152.11111111111111,
      "grad_norm": 6.24493566192541e-07,
      "learning_rate": 3.689041331675591e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3834304,
      "step": 13690
    },
    {
      "epoch": 152.16666666666666,
      "grad_norm": 8.799146939963975e-07,
      "learning_rate": 3.688177642973461e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3835680,
      "step": 13695
    },
    {
      "epoch": 152.22222222222223,
      "grad_norm": 6.063510227249935e-07,
      "learning_rate": 3.687313771039406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3837120,
      "step": 13700
    },
    {
      "epoch": 152.27777777777777,
      "grad_norm": 6.759894972674374e-07,
      "learning_rate": 3.686449716006647e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3838528,
      "step": 13705
    },
    {
      "epoch": 152.33333333333334,
      "grad_norm": 5.901772510696901e-07,
      "learning_rate": 3.685585478008432e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3839936,
      "step": 13710
    },
    {
      "epoch": 152.38888888888889,
      "grad_norm": 6.090450028750638e-07,
      "learning_rate": 3.6847210571780364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3841312,
      "step": 13715
    },
    {
      "epoch": 152.44444444444446,
      "grad_norm": 7.968595809870749e-07,
      "learning_rate": 3.683856453648767e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3842688,
      "step": 13720
    },
    {
      "epoch": 152.5,
      "grad_norm": 1.4960728549340274e-06,
      "learning_rate": 3.682991667553954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3844064,
      "step": 13725
    },
    {
      "epoch": 152.55555555555554,
      "grad_norm": 6.999724178058386e-07,
      "learning_rate": 3.6821266990269606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3845456,
      "step": 13730
    },
    {
      "epoch": 152.61111111111111,
      "grad_norm": 7.705983193773136e-07,
      "learning_rate": 3.681261548201174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3846880,
      "step": 13735
    },
    {
      "epoch": 152.66666666666666,
      "grad_norm": 8.082914746410097e-07,
      "learning_rate": 3.6803962152100125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3848336,
      "step": 13740
    },
    {
      "epoch": 152.72222222222223,
      "grad_norm": 1.0823480351973558e-06,
      "learning_rate": 3.67953070018692e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3849728,
      "step": 13745
    },
    {
      "epoch": 152.77777777777777,
      "grad_norm": 6.366693696691073e-07,
      "learning_rate": 3.678665003265371e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3851120,
      "step": 13750
    },
    {
      "epoch": 152.83333333333334,
      "grad_norm": 6.654008188888838e-07,
      "learning_rate": 3.677799124578867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3852576,
      "step": 13755
    },
    {
      "epoch": 152.88888888888889,
      "grad_norm": 6.90423064497736e-07,
      "learning_rate": 3.676933064260937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3853968,
      "step": 13760
    },
    {
      "epoch": 152.94444444444446,
      "grad_norm": 7.676950986024167e-07,
      "learning_rate": 3.6760668224451365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3855424,
      "step": 13765
    },
    {
      "epoch": 153.0,
      "grad_norm": 7.629008109688584e-07,
      "learning_rate": 3.675200399265054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3856816,
      "step": 13770
    },
    {
      "epoch": 153.05555555555554,
      "grad_norm": 7.517514291066618e-07,
      "learning_rate": 3.6743337948543014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3858192,
      "step": 13775
    },
    {
      "epoch": 153.11111111111111,
      "grad_norm": 4.955649615112634e-07,
      "learning_rate": 3.6734670093465204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3859600,
      "step": 13780
    },
    {
      "epoch": 153.16666666666666,
      "grad_norm": 5.19628599704447e-07,
      "learning_rate": 3.672600042875379e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3861008,
      "step": 13785
    },
    {
      "epoch": 153.22222222222223,
      "grad_norm": 8.983682846519514e-07,
      "learning_rate": 3.671732895574575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3862400,
      "step": 13790
    },
    {
      "epoch": 153.27777777777777,
      "grad_norm": 1.5002786994955386e-06,
      "learning_rate": 3.670865567577834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3863824,
      "step": 13795
    },
    {
      "epoch": 153.33333333333334,
      "grad_norm": 1.545780833112076e-06,
      "learning_rate": 3.669998059018909e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3865216,
      "step": 13800
    },
    {
      "epoch": 153.33333333333334,
      "eval_loss": 0.3873576521873474,
      "eval_runtime": 1.3262,
      "eval_samples_per_second": 30.162,
      "eval_steps_per_second": 15.081,
      "num_input_tokens_seen": 3865216,
      "step": 13800
    },
    {
      "epoch": 153.38888888888889,
      "grad_norm": 5.897169899071741e-07,
      "learning_rate": 3.6691303700315796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3866576,
      "step": 13805
    },
    {
      "epoch": 153.44444444444446,
      "grad_norm": 7.03002854152146e-07,
      "learning_rate": 3.668262500749655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3868000,
      "step": 13810
    },
    {
      "epoch": 153.5,
      "grad_norm": 7.798846013429284e-07,
      "learning_rate": 3.667394451306971e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3869440,
      "step": 13815
    },
    {
      "epoch": 153.55555555555554,
      "grad_norm": 8.719156312508858e-07,
      "learning_rate": 3.666526221837393e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3870800,
      "step": 13820
    },
    {
      "epoch": 153.61111111111111,
      "grad_norm": 1.4576016837963834e-06,
      "learning_rate": 3.665657812474812e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3872208,
      "step": 13825
    },
    {
      "epoch": 153.66666666666666,
      "grad_norm": 8.234148936026031e-07,
      "learning_rate": 3.664789223353147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3873584,
      "step": 13830
    },
    {
      "epoch": 153.72222222222223,
      "grad_norm": 6.746259941792232e-07,
      "learning_rate": 3.663920454606347e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3874992,
      "step": 13835
    },
    {
      "epoch": 153.77777777777777,
      "grad_norm": 7.436992177645152e-07,
      "learning_rate": 3.6630515063683856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3876400,
      "step": 13840
    },
    {
      "epoch": 153.83333333333334,
      "grad_norm": 6.060087685000326e-07,
      "learning_rate": 3.662182378773267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3877776,
      "step": 13845
    },
    {
      "epoch": 153.88888888888889,
      "grad_norm": 1.054375047715439e-06,
      "learning_rate": 3.66131307195502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3879168,
      "step": 13850
    },
    {
      "epoch": 153.94444444444446,
      "grad_norm": 6.157618486213323e-07,
      "learning_rate": 3.6604435860477034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3880528,
      "step": 13855
    },
    {
      "epoch": 154.0,
      "grad_norm": 5.750999889642117e-07,
      "learning_rate": 3.6595739211854025e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3881968,
      "step": 13860
    },
    {
      "epoch": 154.05555555555554,
      "grad_norm": 1.5541104403382633e-06,
      "learning_rate": 3.658704077502231e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3883392,
      "step": 13865
    },
    {
      "epoch": 154.11111111111111,
      "grad_norm": 1.6392020825151121e-06,
      "learning_rate": 3.65783405513233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3884832,
      "step": 13870
    },
    {
      "epoch": 154.16666666666666,
      "grad_norm": 1.5514995084231487e-06,
      "learning_rate": 3.656963854209867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3886208,
      "step": 13875
    },
    {
      "epoch": 154.22222222222223,
      "grad_norm": 7.556665764241188e-07,
      "learning_rate": 3.656093474869038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3887568,
      "step": 13880
    },
    {
      "epoch": 154.27777777777777,
      "grad_norm": 3.056689592995099e-06,
      "learning_rate": 3.655222917244068e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3888976,
      "step": 13885
    },
    {
      "epoch": 154.33333333333334,
      "grad_norm": 6.734758812854125e-07,
      "learning_rate": 3.6543521814692054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3890368,
      "step": 13890
    },
    {
      "epoch": 154.38888888888889,
      "grad_norm": 1.1228385119466111e-06,
      "learning_rate": 3.653481267678731e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3891792,
      "step": 13895
    },
    {
      "epoch": 154.44444444444446,
      "grad_norm": 1.7335402162643732e-06,
      "learning_rate": 3.652610176006949e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3893168,
      "step": 13900
    },
    {
      "epoch": 154.5,
      "grad_norm": 1.3037802091275807e-06,
      "learning_rate": 3.6517389065881925e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3894560,
      "step": 13905
    },
    {
      "epoch": 154.55555555555554,
      "grad_norm": 5.122857373862644e-07,
      "learning_rate": 3.650867459556824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3895968,
      "step": 13910
    },
    {
      "epoch": 154.61111111111111,
      "grad_norm": 5.417564352683257e-07,
      "learning_rate": 3.64999583504723e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3897360,
      "step": 13915
    },
    {
      "epoch": 154.66666666666666,
      "grad_norm": 6.682096227450529e-07,
      "learning_rate": 3.649124033193827e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3898768,
      "step": 13920
    },
    {
      "epoch": 154.72222222222223,
      "grad_norm": 7.728363584647013e-07,
      "learning_rate": 3.648252054131057e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3900192,
      "step": 13925
    },
    {
      "epoch": 154.77777777777777,
      "grad_norm": 1.5857521020734566e-06,
      "learning_rate": 3.647379897993391e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3901584,
      "step": 13930
    },
    {
      "epoch": 154.83333333333334,
      "grad_norm": 7.296727631000977e-07,
      "learning_rate": 3.646507564915325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3902992,
      "step": 13935
    },
    {
      "epoch": 154.88888888888889,
      "grad_norm": 6.689926408398605e-07,
      "learning_rate": 3.645635055031385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3904432,
      "step": 13940
    },
    {
      "epoch": 154.94444444444446,
      "grad_norm": 1.108306719288521e-06,
      "learning_rate": 3.6447623684761224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3905824,
      "step": 13945
    },
    {
      "epoch": 155.0,
      "grad_norm": 6.275627697505115e-07,
      "learning_rate": 3.643889505384117e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3907280,
      "step": 13950
    },
    {
      "epoch": 155.05555555555554,
      "grad_norm": 7.343978722929023e-07,
      "learning_rate": 3.6430164658899744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3908656,
      "step": 13955
    },
    {
      "epoch": 155.11111111111111,
      "grad_norm": 1.113957864617987e-06,
      "learning_rate": 3.642143250128329e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3909968,
      "step": 13960
    },
    {
      "epoch": 155.16666666666666,
      "grad_norm": 1.4920331068424275e-06,
      "learning_rate": 3.641269858233841e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3911344,
      "step": 13965
    },
    {
      "epoch": 155.22222222222223,
      "grad_norm": 6.911236027917766e-07,
      "learning_rate": 3.640396290341199e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3912752,
      "step": 13970
    },
    {
      "epoch": 155.27777777777777,
      "grad_norm": 3.0901965146767907e-06,
      "learning_rate": 3.639522546585118e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3914176,
      "step": 13975
    },
    {
      "epoch": 155.33333333333334,
      "grad_norm": 6.37179937257315e-07,
      "learning_rate": 3.6386486271003404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3915584,
      "step": 13980
    },
    {
      "epoch": 155.38888888888889,
      "grad_norm": 6.616103860324074e-07,
      "learning_rate": 3.6377745320216346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3917040,
      "step": 13985
    },
    {
      "epoch": 155.44444444444446,
      "grad_norm": 3.404460130695952e-06,
      "learning_rate": 3.636900261483798e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3918432,
      "step": 13990
    },
    {
      "epoch": 155.5,
      "grad_norm": 7.357760978266015e-07,
      "learning_rate": 3.636025815621654e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3919808,
      "step": 13995
    },
    {
      "epoch": 155.55555555555554,
      "grad_norm": 6.631497058151581e-07,
      "learning_rate": 3.635151194570054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3921216,
      "step": 14000
    },
    {
      "epoch": 155.55555555555554,
      "eval_loss": 0.3806132376194,
      "eval_runtime": 1.3347,
      "eval_samples_per_second": 29.97,
      "eval_steps_per_second": 14.985,
      "num_input_tokens_seen": 3921216,
      "step": 14000
    },
    {
      "epoch": 155.61111111111111,
      "grad_norm": 7.176285521381942e-07,
      "learning_rate": 3.634276398463873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3922640,
      "step": 14005
    },
    {
      "epoch": 155.66666666666666,
      "grad_norm": 7.134207749004418e-07,
      "learning_rate": 3.633401427438018e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3924032,
      "step": 14010
    },
    {
      "epoch": 155.72222222222223,
      "grad_norm": 7.432352617797733e-07,
      "learning_rate": 3.63252628162742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3925424,
      "step": 14015
    },
    {
      "epoch": 155.77777777777777,
      "grad_norm": 8.294974804812227e-07,
      "learning_rate": 3.6316509611670364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3926816,
      "step": 14020
    },
    {
      "epoch": 155.83333333333334,
      "grad_norm": 3.3682474622764857e-06,
      "learning_rate": 3.630775466191854e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3928224,
      "step": 14025
    },
    {
      "epoch": 155.88888888888889,
      "grad_norm": 1.496005666012934e-06,
      "learning_rate": 3.629899796836884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3929584,
      "step": 14030
    },
    {
      "epoch": 155.94444444444446,
      "grad_norm": 7.338285854530113e-07,
      "learning_rate": 3.6290239532371666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3931024,
      "step": 14035
    },
    {
      "epoch": 156.0,
      "grad_norm": 8.369574402422586e-07,
      "learning_rate": 3.628147935527767e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3932464,
      "step": 14040
    },
    {
      "epoch": 156.05555555555554,
      "grad_norm": 1.2140850458308705e-06,
      "learning_rate": 3.627271743843779e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3933920,
      "step": 14045
    },
    {
      "epoch": 156.11111111111111,
      "grad_norm": 1.967557864190894e-06,
      "learning_rate": 3.626395378320321e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3935312,
      "step": 14050
    },
    {
      "epoch": 156.16666666666666,
      "grad_norm": 5.790870432065276e-07,
      "learning_rate": 3.625518839092541e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3936688,
      "step": 14055
    },
    {
      "epoch": 156.22222222222223,
      "grad_norm": 1.6152863508978044e-06,
      "learning_rate": 3.624642126295612e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3938080,
      "step": 14060
    },
    {
      "epoch": 156.27777777777777,
      "grad_norm": 7.077260875121283e-07,
      "learning_rate": 3.6237652400647345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3939504,
      "step": 14065
    },
    {
      "epoch": 156.33333333333334,
      "grad_norm": 2.810626710925135e-06,
      "learning_rate": 3.622888180535134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3940928,
      "step": 14070
    },
    {
      "epoch": 156.38888888888889,
      "grad_norm": 6.440780566663307e-07,
      "learning_rate": 3.6220109478420655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3942288,
      "step": 14075
    },
    {
      "epoch": 156.44444444444446,
      "grad_norm": 7.610915986333566e-07,
      "learning_rate": 3.6211335421208084e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3943696,
      "step": 14080
    },
    {
      "epoch": 156.5,
      "grad_norm": 3.3946514577110065e-06,
      "learning_rate": 3.62025596350667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3945088,
      "step": 14085
    },
    {
      "epoch": 156.55555555555554,
      "grad_norm": 6.740161211382656e-07,
      "learning_rate": 3.619378212134984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3946464,
      "step": 14090
    },
    {
      "epoch": 156.61111111111111,
      "grad_norm": 6.841756317044201e-07,
      "learning_rate": 3.618500288141111e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3947856,
      "step": 14095
    },
    {
      "epoch": 156.66666666666666,
      "grad_norm": 2.6037992029159795e-06,
      "learning_rate": 3.617622191660438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3949248,
      "step": 14100
    },
    {
      "epoch": 156.72222222222223,
      "grad_norm": 8.606243113717937e-07,
      "learning_rate": 3.616743922828377e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3950704,
      "step": 14105
    },
    {
      "epoch": 156.77777777777777,
      "grad_norm": 4.541581347439205e-06,
      "learning_rate": 3.615865481780371e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3952080,
      "step": 14110
    },
    {
      "epoch": 156.83333333333334,
      "grad_norm": 7.237083536892897e-07,
      "learning_rate": 3.614986868651883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3953536,
      "step": 14115
    },
    {
      "epoch": 156.88888888888889,
      "grad_norm": 6.93054289513384e-07,
      "learning_rate": 3.614108083578409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3954880,
      "step": 14120
    },
    {
      "epoch": 156.94444444444446,
      "grad_norm": 6.896945023981971e-07,
      "learning_rate": 3.613229126695467e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3956288,
      "step": 14125
    },
    {
      "epoch": 157.0,
      "grad_norm": 5.823339961352758e-07,
      "learning_rate": 3.612349998138605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3957712,
      "step": 14130
    },
    {
      "epoch": 157.05555555555554,
      "grad_norm": 7.668309081054758e-07,
      "learning_rate": 3.6114706980433946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3959136,
      "step": 14135
    },
    {
      "epoch": 157.11111111111111,
      "grad_norm": 6.994859518272278e-07,
      "learning_rate": 3.610591226545435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3960528,
      "step": 14140
    },
    {
      "epoch": 157.16666666666666,
      "grad_norm": 6.101023473092937e-07,
      "learning_rate": 3.6097115837803505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3961936,
      "step": 14145
    },
    {
      "epoch": 157.22222222222223,
      "grad_norm": 6.765701527911006e-07,
      "learning_rate": 3.608831769883795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3963360,
      "step": 14150
    },
    {
      "epoch": 157.27777777777777,
      "grad_norm": 1.5343406403189874e-06,
      "learning_rate": 3.607951784991446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3964736,
      "step": 14155
    },
    {
      "epoch": 157.33333333333334,
      "grad_norm": 6.204745091054065e-07,
      "learning_rate": 3.6070716292390085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3966144,
      "step": 14160
    },
    {
      "epoch": 157.38888888888889,
      "grad_norm": 1.6213907656492665e-06,
      "learning_rate": 3.606191302762213e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3967504,
      "step": 14165
    },
    {
      "epoch": 157.44444444444446,
      "grad_norm": 8.340172712451022e-07,
      "learning_rate": 3.605310805696818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3968944,
      "step": 14170
    },
    {
      "epoch": 157.5,
      "grad_norm": 1.1632557743723737e-06,
      "learning_rate": 3.6044301381786067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3970256,
      "step": 14175
    },
    {
      "epoch": 157.55555555555554,
      "grad_norm": 1.4970504480515956e-06,
      "learning_rate": 3.6035493003433883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3971696,
      "step": 14180
    },
    {
      "epoch": 157.61111111111111,
      "grad_norm": 6.3189099819283e-07,
      "learning_rate": 3.6026682923269994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3973056,
      "step": 14185
    },
    {
      "epoch": 157.66666666666666,
      "grad_norm": 1.1407770443838672e-06,
      "learning_rate": 3.6017871142653034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3974448,
      "step": 14190
    },
    {
      "epoch": 157.72222222222223,
      "grad_norm": 1.2760862091454328e-06,
      "learning_rate": 3.600905766294189e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3975872,
      "step": 14195
    },
    {
      "epoch": 157.77777777777777,
      "grad_norm": 8.276697940345912e-07,
      "learning_rate": 3.60002424854957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3977312,
      "step": 14200
    },
    {
      "epoch": 157.77777777777777,
      "eval_loss": 0.3885982632637024,
      "eval_runtime": 1.3044,
      "eval_samples_per_second": 30.665,
      "eval_steps_per_second": 15.332,
      "num_input_tokens_seen": 3977312,
      "step": 14200
    },
    {
      "epoch": 157.83333333333334,
      "grad_norm": 7.993427857400093e-07,
      "learning_rate": 3.5991425611673876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3978752,
      "step": 14205
    },
    {
      "epoch": 157.88888888888889,
      "grad_norm": 5.390976980379492e-07,
      "learning_rate": 3.5982607042836105e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3980160,
      "step": 14210
    },
    {
      "epoch": 157.94444444444446,
      "grad_norm": 1.1459870847829734e-06,
      "learning_rate": 3.597378678034231e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3981568,
      "step": 14215
    },
    {
      "epoch": 158.0,
      "grad_norm": 5.822723778692307e-07,
      "learning_rate": 3.596496482555269e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3982960,
      "step": 14220
    },
    {
      "epoch": 158.05555555555554,
      "grad_norm": 7.236956776068837e-07,
      "learning_rate": 3.595614117982769e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3984400,
      "step": 14225
    },
    {
      "epoch": 158.11111111111111,
      "grad_norm": 7.04391368344659e-07,
      "learning_rate": 3.594731584452805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3985776,
      "step": 14230
    },
    {
      "epoch": 158.16666666666666,
      "grad_norm": 1.3367682640819112e-06,
      "learning_rate": 3.593848882101472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3987136,
      "step": 14235
    },
    {
      "epoch": 158.22222222222223,
      "grad_norm": 6.396244316420052e-07,
      "learning_rate": 3.592966011064896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3988544,
      "step": 14240
    },
    {
      "epoch": 158.27777777777777,
      "grad_norm": 7.219515509859775e-07,
      "learning_rate": 3.592082971479226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3989968,
      "step": 14245
    },
    {
      "epoch": 158.33333333333334,
      "grad_norm": 3.4940555906359805e-06,
      "learning_rate": 3.5911997634806385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3991376,
      "step": 14250
    },
    {
      "epoch": 158.38888888888889,
      "grad_norm": 6.707747957079846e-07,
      "learning_rate": 3.5903163872053336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3992800,
      "step": 14255
    },
    {
      "epoch": 158.44444444444446,
      "grad_norm": 8.276921903416223e-07,
      "learning_rate": 3.58943284278954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3994240,
      "step": 14260
    },
    {
      "epoch": 158.5,
      "grad_norm": 5.60934324767004e-07,
      "learning_rate": 3.588549130369512e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3995616,
      "step": 14265
    },
    {
      "epoch": 158.55555555555554,
      "grad_norm": 8.190945095520874e-07,
      "learning_rate": 3.5876652500815274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3996976,
      "step": 14270
    },
    {
      "epoch": 158.61111111111111,
      "grad_norm": 1.5429839095304487e-06,
      "learning_rate": 3.586781202061894e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3998384,
      "step": 14275
    },
    {
      "epoch": 158.66666666666666,
      "grad_norm": 7.149182579269109e-07,
      "learning_rate": 3.585896986446942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 3999808,
      "step": 14280
    },
    {
      "epoch": 158.72222222222223,
      "grad_norm": 6.969356718400377e-07,
      "learning_rate": 3.585012603373028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4001184,
      "step": 14285
    },
    {
      "epoch": 158.77777777777777,
      "grad_norm": 8.255864827333426e-07,
      "learning_rate": 3.584128052976535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4002624,
      "step": 14290
    },
    {
      "epoch": 158.83333333333334,
      "grad_norm": 7.672321657992143e-07,
      "learning_rate": 3.5832433353938724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4004016,
      "step": 14295
    },
    {
      "epoch": 158.88888888888889,
      "grad_norm": 3.417044808884384e-06,
      "learning_rate": 3.5823584507614746e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4005440,
      "step": 14300
    },
    {
      "epoch": 158.94444444444446,
      "grad_norm": 1.9908363810827723e-06,
      "learning_rate": 3.581473399215802e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4006848,
      "step": 14305
    },
    {
      "epoch": 159.0,
      "grad_norm": 6.473982239185716e-07,
      "learning_rate": 3.580588180893341e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4008256,
      "step": 14310
    },
    {
      "epoch": 159.05555555555554,
      "grad_norm": 1.1296402817606577e-06,
      "learning_rate": 3.579702795930602e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4009648,
      "step": 14315
    },
    {
      "epoch": 159.11111111111111,
      "grad_norm": 6.425158289857791e-07,
      "learning_rate": 3.578817244464125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4011040,
      "step": 14320
    },
    {
      "epoch": 159.16666666666666,
      "grad_norm": 7.679484497202793e-07,
      "learning_rate": 3.577931526630471e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4012448,
      "step": 14325
    },
    {
      "epoch": 159.22222222222223,
      "grad_norm": 7.035910698505177e-07,
      "learning_rate": 3.577045642566229e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4013856,
      "step": 14330
    },
    {
      "epoch": 159.27777777777777,
      "grad_norm": 1.5612879451509798e-06,
      "learning_rate": 3.576159592408014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4015280,
      "step": 14335
    },
    {
      "epoch": 159.33333333333334,
      "grad_norm": 6.299130177467305e-07,
      "learning_rate": 3.575273376292466e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4016640,
      "step": 14340
    },
    {
      "epoch": 159.38888888888889,
      "grad_norm": 6.676864927612769e-07,
      "learning_rate": 3.574386994356251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4018064,
      "step": 14345
    },
    {
      "epoch": 159.44444444444446,
      "grad_norm": 1.1982571095359162e-06,
      "learning_rate": 3.573500446736059e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4019472,
      "step": 14350
    },
    {
      "epoch": 159.5,
      "grad_norm": 6.414970243895368e-07,
      "learning_rate": 3.5726137335686094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4020848,
      "step": 14355
    },
    {
      "epoch": 159.55555555555554,
      "grad_norm": 8.252530392383051e-07,
      "learning_rate": 3.571726854990642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4022240,
      "step": 14360
    },
    {
      "epoch": 159.61111111111111,
      "grad_norm": 1.5232030818879139e-06,
      "learning_rate": 3.570839811138925e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4023616,
      "step": 14365
    },
    {
      "epoch": 159.66666666666666,
      "grad_norm": 3.4540496471890947e-06,
      "learning_rate": 3.569952602150252e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4024992,
      "step": 14370
    },
    {
      "epoch": 159.72222222222223,
      "grad_norm": 7.139888111851178e-07,
      "learning_rate": 3.569065228161442e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4026400,
      "step": 14375
    },
    {
      "epoch": 159.77777777777777,
      "grad_norm": 6.147389512989321e-07,
      "learning_rate": 3.5681776893093395e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4027824,
      "step": 14380
    },
    {
      "epoch": 159.83333333333334,
      "grad_norm": 1.3598362329503288e-06,
      "learning_rate": 3.5672899857308134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4029216,
      "step": 14385
    },
    {
      "epoch": 159.88888888888889,
      "grad_norm": 7.200155209829973e-07,
      "learning_rate": 3.566402117562759e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4030640,
      "step": 14390
    },
    {
      "epoch": 159.94444444444446,
      "grad_norm": 7.562192081422836e-07,
      "learning_rate": 3.565514084942097e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4032048,
      "step": 14395
    },
    {
      "epoch": 160.0,
      "grad_norm": 2.795204864014522e-06,
      "learning_rate": 3.564625888005773e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4033488,
      "step": 14400
    },
    {
      "epoch": 160.0,
      "eval_loss": 0.36411207914352417,
      "eval_runtime": 1.2907,
      "eval_samples_per_second": 30.991,
      "eval_steps_per_second": 15.496,
      "num_input_tokens_seen": 4033488,
      "step": 14400
    },
    {
      "epoch": 160.05555555555554,
      "grad_norm": 1.9528597476892173e-06,
      "learning_rate": 3.563737526890759e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4034848,
      "step": 14405
    },
    {
      "epoch": 160.11111111111111,
      "grad_norm": 8.293004043480323e-07,
      "learning_rate": 3.562849001734049e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4036272,
      "step": 14410
    },
    {
      "epoch": 160.16666666666666,
      "grad_norm": 6.242041195037018e-07,
      "learning_rate": 3.561960312672667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4037696,
      "step": 14415
    },
    {
      "epoch": 160.22222222222223,
      "grad_norm": 3.525262172843213e-06,
      "learning_rate": 3.5610714598436596e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4039056,
      "step": 14420
    },
    {
      "epoch": 160.27777777777777,
      "grad_norm": 1.1794015790655976e-06,
      "learning_rate": 3.5601824433840986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4040496,
      "step": 14425
    },
    {
      "epoch": 160.33333333333334,
      "grad_norm": 5.260345687929657e-07,
      "learning_rate": 3.559293263431082e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4041904,
      "step": 14430
    },
    {
      "epoch": 160.38888888888889,
      "grad_norm": 6.343436780298362e-07,
      "learning_rate": 3.558403920121732e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4043296,
      "step": 14435
    },
    {
      "epoch": 160.44444444444446,
      "grad_norm": 5.71924260839296e-07,
      "learning_rate": 3.557514413593197e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4044672,
      "step": 14440
    },
    {
      "epoch": 160.5,
      "grad_norm": 7.697606179135619e-07,
      "learning_rate": 3.55662474398265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4046032,
      "step": 14445
    },
    {
      "epoch": 160.55555555555554,
      "grad_norm": 7.778322697049589e-07,
      "learning_rate": 3.555734911427288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4047408,
      "step": 14450
    },
    {
      "epoch": 160.61111111111111,
      "grad_norm": 1.1795626733146491e-06,
      "learning_rate": 3.5548449160643363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4048848,
      "step": 14455
    },
    {
      "epoch": 160.66666666666666,
      "grad_norm": 7.31333898329467e-07,
      "learning_rate": 3.553954758031043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4050208,
      "step": 14460
    },
    {
      "epoch": 160.72222222222223,
      "grad_norm": 7.638196279913245e-07,
      "learning_rate": 3.5530644374646815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4051632,
      "step": 14465
    },
    {
      "epoch": 160.77777777777777,
      "grad_norm": 5.566301979342825e-07,
      "learning_rate": 3.552173954502549e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4053024,
      "step": 14470
    },
    {
      "epoch": 160.83333333333334,
      "grad_norm": 7.511926582992601e-07,
      "learning_rate": 3.55128330928197e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4054432,
      "step": 14475
    },
    {
      "epoch": 160.88888888888889,
      "grad_norm": 7.76154195136769e-07,
      "learning_rate": 3.550392501940294e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4055888,
      "step": 14480
    },
    {
      "epoch": 160.94444444444446,
      "grad_norm": 7.828703019185923e-07,
      "learning_rate": 3.5495015326148945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4057344,
      "step": 14485
    },
    {
      "epoch": 161.0,
      "grad_norm": 3.848080723400926e-06,
      "learning_rate": 3.548610401443169e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4058704,
      "step": 14490
    },
    {
      "epoch": 161.05555555555554,
      "grad_norm": 8.884565545486112e-07,
      "learning_rate": 3.547719108562543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4060112,
      "step": 14495
    },
    {
      "epoch": 161.11111111111111,
      "grad_norm": 8.609072779108828e-07,
      "learning_rate": 3.546827654110464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4061504,
      "step": 14500
    },
    {
      "epoch": 161.16666666666666,
      "grad_norm": 6.331067083920061e-07,
      "learning_rate": 3.545936038224405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4062928,
      "step": 14505
    },
    {
      "epoch": 161.22222222222223,
      "grad_norm": 3.677793984024902e-06,
      "learning_rate": 3.545044261041864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4064400,
      "step": 14510
    },
    {
      "epoch": 161.27777777777777,
      "grad_norm": 2.5024394290085183e-06,
      "learning_rate": 3.5441523227003657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4065808,
      "step": 14515
    },
    {
      "epoch": 161.33333333333334,
      "grad_norm": 6.659832365585316e-07,
      "learning_rate": 3.543260223337459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4067248,
      "step": 14520
    },
    {
      "epoch": 161.38888888888889,
      "grad_norm": 5.644303087137814e-07,
      "learning_rate": 3.542367963090714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4068624,
      "step": 14525
    },
    {
      "epoch": 161.44444444444446,
      "grad_norm": 6.247097985578876e-07,
      "learning_rate": 3.5414755420977295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4070016,
      "step": 14530
    },
    {
      "epoch": 161.5,
      "grad_norm": 6.455201742028294e-07,
      "learning_rate": 3.54058296049613e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4071440,
      "step": 14535
    },
    {
      "epoch": 161.55555555555554,
      "grad_norm": 8.738355177229096e-07,
      "learning_rate": 3.53969021842356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4072800,
      "step": 14540
    },
    {
      "epoch": 161.61111111111111,
      "grad_norm": 1.5639277535228757e-06,
      "learning_rate": 3.5387973160176926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4074192,
      "step": 14545
    },
    {
      "epoch": 161.66666666666666,
      "grad_norm": 2.1507714791368926e-06,
      "learning_rate": 3.537904253416224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4075584,
      "step": 14550
    },
    {
      "epoch": 161.72222222222223,
      "grad_norm": 9.303445267505595e-07,
      "learning_rate": 3.537011030756878e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4076960,
      "step": 14555
    },
    {
      "epoch": 161.77777777777777,
      "grad_norm": 1.4923994058335666e-06,
      "learning_rate": 3.536117648177399e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4078336,
      "step": 14560
    },
    {
      "epoch": 161.83333333333334,
      "grad_norm": 3.5133189157932065e-06,
      "learning_rate": 3.535224105815558e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4079792,
      "step": 14565
    },
    {
      "epoch": 161.88888888888889,
      "grad_norm": 6.93185768341209e-07,
      "learning_rate": 3.5343304038091494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4081168,
      "step": 14570
    },
    {
      "epoch": 161.94444444444446,
      "grad_norm": 1.4653949165222002e-06,
      "learning_rate": 3.5334365422959955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4082560,
      "step": 14575
    },
    {
      "epoch": 162.0,
      "grad_norm": 7.475759957742412e-07,
      "learning_rate": 3.5325425214139396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4083904,
      "step": 14580
    },
    {
      "epoch": 162.05555555555554,
      "grad_norm": 7.538445174759545e-07,
      "learning_rate": 3.531648341300851e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4085280,
      "step": 14585
    },
    {
      "epoch": 162.11111111111111,
      "grad_norm": 6.897818138895673e-07,
      "learning_rate": 3.530754002094623e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4086688,
      "step": 14590
    },
    {
      "epoch": 162.16666666666666,
      "grad_norm": 1.2468224213080248e-06,
      "learning_rate": 3.529859503933175e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4088064,
      "step": 14595
    },
    {
      "epoch": 162.22222222222223,
      "grad_norm": 6.821061901973735e-07,
      "learning_rate": 3.52896484695445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4089504,
      "step": 14600
    },
    {
      "epoch": 162.22222222222223,
      "eval_loss": 0.39667797088623047,
      "eval_runtime": 1.3338,
      "eval_samples_per_second": 29.99,
      "eval_steps_per_second": 14.995,
      "num_input_tokens_seen": 4089504,
      "step": 14600
    },
    {
      "epoch": 162.27777777777777,
      "grad_norm": 1.156304961114074e-06,
      "learning_rate": 3.528070031296414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4090896,
      "step": 14605
    },
    {
      "epoch": 162.33333333333334,
      "grad_norm": 7.170813773882401e-07,
      "learning_rate": 3.5271750570970605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4092288,
      "step": 14610
    },
    {
      "epoch": 162.38888888888889,
      "grad_norm": 7.076430961205915e-07,
      "learning_rate": 3.526279924494405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4093712,
      "step": 14615
    },
    {
      "epoch": 162.44444444444446,
      "grad_norm": 2.450945885357214e-06,
      "learning_rate": 3.5253846336264874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4095104,
      "step": 14620
    },
    {
      "epoch": 162.5,
      "grad_norm": 6.859860945951368e-07,
      "learning_rate": 3.5244891846313736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4096528,
      "step": 14625
    },
    {
      "epoch": 162.55555555555554,
      "grad_norm": 7.743324204056989e-07,
      "learning_rate": 3.5235935776471527e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4097952,
      "step": 14630
    },
    {
      "epoch": 162.61111111111111,
      "grad_norm": 2.0175889403617475e-06,
      "learning_rate": 3.522697812811939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4099328,
      "step": 14635
    },
    {
      "epoch": 162.66666666666666,
      "grad_norm": 9.882958238449646e-07,
      "learning_rate": 3.521801890263871e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4100752,
      "step": 14640
    },
    {
      "epoch": 162.72222222222223,
      "grad_norm": 7.274480822161422e-07,
      "learning_rate": 3.5209058101411114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4102176,
      "step": 14645
    },
    {
      "epoch": 162.77777777777777,
      "grad_norm": 5.688260671377066e-07,
      "learning_rate": 3.520009572581845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4103584,
      "step": 14650
    },
    {
      "epoch": 162.83333333333334,
      "grad_norm": 1.555000835651299e-06,
      "learning_rate": 3.519113177724285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4105008,
      "step": 14655
    },
    {
      "epoch": 162.88888888888889,
      "grad_norm": 1.9443004930508323e-06,
      "learning_rate": 3.5182166257066656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4106384,
      "step": 14660
    },
    {
      "epoch": 162.94444444444446,
      "grad_norm": 2.50907328336325e-06,
      "learning_rate": 3.517319916667247e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4107808,
      "step": 14665
    },
    {
      "epoch": 163.0,
      "grad_norm": 5.441914368020662e-07,
      "learning_rate": 3.516423050744313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4109200,
      "step": 14670
    },
    {
      "epoch": 163.05555555555554,
      "grad_norm": 6.494223043773673e-07,
      "learning_rate": 3.5155260280761704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4110608,
      "step": 14675
    },
    {
      "epoch": 163.11111111111111,
      "grad_norm": 6.201595397214987e-07,
      "learning_rate": 3.514628848801154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4112000,
      "step": 14680
    },
    {
      "epoch": 163.16666666666666,
      "grad_norm": 7.374095503109857e-07,
      "learning_rate": 3.5137315130576174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4113392,
      "step": 14685
    },
    {
      "epoch": 163.22222222222223,
      "grad_norm": 3.39138296112651e-06,
      "learning_rate": 3.512834020983942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4114832,
      "step": 14690
    },
    {
      "epoch": 163.27777777777777,
      "grad_norm": 1.5160383100010222e-06,
      "learning_rate": 3.5119363727185334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4116256,
      "step": 14695
    },
    {
      "epoch": 163.33333333333334,
      "grad_norm": 6.41202518636419e-07,
      "learning_rate": 3.511038568399819e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4117664,
      "step": 14700
    },
    {
      "epoch": 163.38888888888889,
      "grad_norm": 6.836634725004842e-07,
      "learning_rate": 3.510140608166251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4119040,
      "step": 14705
    },
    {
      "epoch": 163.44444444444446,
      "grad_norm": 1.3260049627206172e-06,
      "learning_rate": 3.509242492156308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4120464,
      "step": 14710
    },
    {
      "epoch": 163.5,
      "grad_norm": 6.554363949362596e-07,
      "learning_rate": 3.5083442205084896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4121872,
      "step": 14715
    },
    {
      "epoch": 163.55555555555554,
      "grad_norm": 6.157239340609522e-07,
      "learning_rate": 3.507445793361321e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4123216,
      "step": 14720
    },
    {
      "epoch": 163.61111111111111,
      "grad_norm": 7.293410817510448e-07,
      "learning_rate": 3.5065472108533505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4124592,
      "step": 14725
    },
    {
      "epoch": 163.66666666666666,
      "grad_norm": 7.038804028525192e-07,
      "learning_rate": 3.5056484731231504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4125952,
      "step": 14730
    },
    {
      "epoch": 163.72222222222223,
      "grad_norm": 1.5598844811393064e-06,
      "learning_rate": 3.504749580309319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4127344,
      "step": 14735
    },
    {
      "epoch": 163.77777777777777,
      "grad_norm": 2.6476573111722246e-06,
      "learning_rate": 3.5038505325504753e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4128784,
      "step": 14740
    },
    {
      "epoch": 163.83333333333334,
      "grad_norm": 9.055005421032547e-07,
      "learning_rate": 3.502951329985264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4130176,
      "step": 14745
    },
    {
      "epoch": 163.88888888888889,
      "grad_norm": 5.719705313822487e-07,
      "learning_rate": 3.502051972752354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4131568,
      "step": 14750
    },
    {
      "epoch": 163.94444444444446,
      "grad_norm": 1.0859689609787893e-06,
      "learning_rate": 3.5011524609904374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4132960,
      "step": 14755
    },
    {
      "epoch": 164.0,
      "grad_norm": 2.114876224368345e-06,
      "learning_rate": 3.50025279483823e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4134368,
      "step": 14760
    },
    {
      "epoch": 164.05555555555554,
      "grad_norm": 6.255222615436651e-07,
      "learning_rate": 3.499352974434472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4135712,
      "step": 14765
    },
    {
      "epoch": 164.11111111111111,
      "grad_norm": 6.019750458108319e-07,
      "learning_rate": 3.498452999917926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4137104,
      "step": 14770
    },
    {
      "epoch": 164.16666666666666,
      "grad_norm": 8.97203335625818e-07,
      "learning_rate": 3.4975528714273795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4138480,
      "step": 14775
    },
    {
      "epoch": 164.22222222222223,
      "grad_norm": 6.758975246157206e-07,
      "learning_rate": 3.4966525891016454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4139936,
      "step": 14780
    },
    {
      "epoch": 164.27777777777777,
      "grad_norm": 2.890570613089949e-06,
      "learning_rate": 3.495752153079557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4141328,
      "step": 14785
    },
    {
      "epoch": 164.33333333333334,
      "grad_norm": 6.143309860817681e-07,
      "learning_rate": 3.494851563499974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4142720,
      "step": 14790
    },
    {
      "epoch": 164.38888888888889,
      "grad_norm": 8.671622140354884e-07,
      "learning_rate": 3.493950820501777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4144144,
      "step": 14795
    },
    {
      "epoch": 164.44444444444446,
      "grad_norm": 6.592201202693104e-07,
      "learning_rate": 3.493049924223872e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4145504,
      "step": 14800
    },
    {
      "epoch": 164.44444444444446,
      "eval_loss": 0.4044431746006012,
      "eval_runtime": 1.3072,
      "eval_samples_per_second": 30.599,
      "eval_steps_per_second": 15.299,
      "num_input_tokens_seen": 4145504,
      "step": 14800
    },
    {
      "epoch": 164.5,
      "grad_norm": 3.4517843232606538e-06,
      "learning_rate": 3.49214887480519e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4146816,
      "step": 14805
    },
    {
      "epoch": 164.55555555555554,
      "grad_norm": 5.606203785646358e-07,
      "learning_rate": 3.4912476723846834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4148192,
      "step": 14810
    },
    {
      "epoch": 164.61111111111111,
      "grad_norm": 6.669130243608379e-07,
      "learning_rate": 3.490346317101328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4149648,
      "step": 14815
    },
    {
      "epoch": 164.66666666666666,
      "grad_norm": 6.29914438832202e-07,
      "learning_rate": 3.4894448090941266e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4150992,
      "step": 14820
    },
    {
      "epoch": 164.72222222222223,
      "grad_norm": 6.248202453207341e-07,
      "learning_rate": 3.488543148502101e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4152416,
      "step": 14825
    },
    {
      "epoch": 164.77777777777777,
      "grad_norm": 8.779068139119772e-07,
      "learning_rate": 3.487641335464299e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4153840,
      "step": 14830
    },
    {
      "epoch": 164.83333333333334,
      "grad_norm": 1.4448078218265437e-06,
      "learning_rate": 3.4867393701197914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4155232,
      "step": 14835
    },
    {
      "epoch": 164.88888888888889,
      "grad_norm": 1.1242767641306273e-06,
      "learning_rate": 3.485837252607673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4156672,
      "step": 14840
    },
    {
      "epoch": 164.94444444444446,
      "grad_norm": 2.2013480247551342e-06,
      "learning_rate": 3.4849349830670615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4158064,
      "step": 14845
    },
    {
      "epoch": 165.0,
      "grad_norm": 7.284219805114844e-07,
      "learning_rate": 3.4840325616370976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4159472,
      "step": 14850
    },
    {
      "epoch": 165.05555555555554,
      "grad_norm": 1.1402005384297809e-06,
      "learning_rate": 3.483129988456947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4160848,
      "step": 14855
    },
    {
      "epoch": 165.11111111111111,
      "grad_norm": 1.0780287311717984e-06,
      "learning_rate": 3.482227263665797e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4162256,
      "step": 14860
    },
    {
      "epoch": 165.16666666666666,
      "grad_norm": 7.208543024717073e-07,
      "learning_rate": 3.48132438740286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4163680,
      "step": 14865
    },
    {
      "epoch": 165.22222222222223,
      "grad_norm": 6.943695893824042e-07,
      "learning_rate": 3.48042135980737e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4165056,
      "step": 14870
    },
    {
      "epoch": 165.27777777777777,
      "grad_norm": 6.630472739743709e-07,
      "learning_rate": 3.479518181018586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4166448,
      "step": 14875
    },
    {
      "epoch": 165.33333333333334,
      "grad_norm": 3.418522737774765e-06,
      "learning_rate": 3.4786148511757886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4167808,
      "step": 14880
    },
    {
      "epoch": 165.38888888888889,
      "grad_norm": 1.3494942550096312e-06,
      "learning_rate": 3.477711370418284e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4169248,
      "step": 14885
    },
    {
      "epoch": 165.44444444444446,
      "grad_norm": 1.5132927728700452e-06,
      "learning_rate": 3.476807738885399e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4170640,
      "step": 14890
    },
    {
      "epoch": 165.5,
      "grad_norm": 7.844525953260018e-07,
      "learning_rate": 3.475903956716485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4172064,
      "step": 14895
    },
    {
      "epoch": 165.55555555555554,
      "grad_norm": 9.025288250086305e-07,
      "learning_rate": 3.475000024050917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4173472,
      "step": 14900
    },
    {
      "epoch": 165.61111111111111,
      "grad_norm": 1.5307465446312563e-06,
      "learning_rate": 3.4740959410280926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4174848,
      "step": 14905
    },
    {
      "epoch": 165.66666666666666,
      "grad_norm": 6.4854845049922e-07,
      "learning_rate": 3.4731917077874324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4176256,
      "step": 14910
    },
    {
      "epoch": 165.72222222222223,
      "grad_norm": 1.5253416449922952e-06,
      "learning_rate": 3.4722873244683816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4177664,
      "step": 14915
    },
    {
      "epoch": 165.77777777777777,
      "grad_norm": 5.663593469762418e-07,
      "learning_rate": 3.4713827912104065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4179056,
      "step": 14920
    },
    {
      "epoch": 165.83333333333334,
      "grad_norm": 5.624079676636029e-06,
      "learning_rate": 3.470478108152998e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4180416,
      "step": 14925
    },
    {
      "epoch": 165.88888888888889,
      "grad_norm": 1.5240550510497997e-06,
      "learning_rate": 3.4695732754356695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4181856,
      "step": 14930
    },
    {
      "epoch": 165.94444444444446,
      "grad_norm": 6.529522806886234e-07,
      "learning_rate": 3.4686682931979576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4183232,
      "step": 14935
    },
    {
      "epoch": 166.0,
      "grad_norm": 1.2303217999942717e-06,
      "learning_rate": 3.467763161579422e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4184672,
      "step": 14940
    },
    {
      "epoch": 166.05555555555554,
      "grad_norm": 3.913080490747234e-06,
      "learning_rate": 3.466857880719645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4186096,
      "step": 14945
    },
    {
      "epoch": 166.11111111111111,
      "grad_norm": 6.945314794393198e-07,
      "learning_rate": 3.465952450758233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4187472,
      "step": 14950
    },
    {
      "epoch": 166.16666666666666,
      "grad_norm": 1.2011034868919523e-06,
      "learning_rate": 3.4650468718348126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4188880,
      "step": 14955
    },
    {
      "epoch": 166.22222222222223,
      "grad_norm": 5.238934477347357e-07,
      "learning_rate": 3.464141144089038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4190288,
      "step": 14960
    },
    {
      "epoch": 166.27777777777777,
      "grad_norm": 6.381802677424275e-07,
      "learning_rate": 3.463235267660583e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4191632,
      "step": 14965
    },
    {
      "epoch": 166.33333333333334,
      "grad_norm": 6.410223818420491e-07,
      "learning_rate": 3.462329242689145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4192976,
      "step": 14970
    },
    {
      "epoch": 166.38888888888889,
      "grad_norm": 3.7809813875355758e-06,
      "learning_rate": 3.461423069314444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4194416,
      "step": 14975
    },
    {
      "epoch": 166.44444444444446,
      "grad_norm": 7.146507527977519e-07,
      "learning_rate": 3.460516747676224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4195824,
      "step": 14980
    },
    {
      "epoch": 166.5,
      "grad_norm": 5.929336452936695e-07,
      "learning_rate": 3.459610277914251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4197232,
      "step": 14985
    },
    {
      "epoch": 166.55555555555554,
      "grad_norm": 6.298276957750204e-07,
      "learning_rate": 3.458703660168314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4198640,
      "step": 14990
    },
    {
      "epoch": 166.61111111111111,
      "grad_norm": 6.69473536163423e-07,
      "learning_rate": 3.457796894578224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4200048,
      "step": 14995
    },
    {
      "epoch": 166.66666666666666,
      "grad_norm": 1.540600464977615e-06,
      "learning_rate": 3.456889981283817e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4201440,
      "step": 15000
    },
    {
      "epoch": 166.66666666666666,
      "eval_loss": 0.4140651226043701,
      "eval_runtime": 1.3291,
      "eval_samples_per_second": 30.096,
      "eval_steps_per_second": 15.048,
      "num_input_tokens_seen": 4201440,
      "step": 15000
    },
    {
      "epoch": 166.72222222222223,
      "grad_norm": 1.5081832316354848e-06,
      "learning_rate": 3.45598292042495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4202864,
      "step": 15005
    },
    {
      "epoch": 166.77777777777777,
      "grad_norm": 5.995987635287747e-07,
      "learning_rate": 3.4550757121415035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4204304,
      "step": 15010
    },
    {
      "epoch": 166.83333333333334,
      "grad_norm": 7.15382952876098e-07,
      "learning_rate": 3.454168356573378e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4205664,
      "step": 15015
    },
    {
      "epoch": 166.88888888888889,
      "grad_norm": 3.3454552976763807e-06,
      "learning_rate": 3.453260853860503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4207056,
      "step": 15020
    },
    {
      "epoch": 166.94444444444446,
      "grad_norm": 6.506853083010355e-07,
      "learning_rate": 3.452353204142824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4208432,
      "step": 15025
    },
    {
      "epoch": 167.0,
      "grad_norm": 6.238552145987342e-07,
      "learning_rate": 3.4514454075603136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4209840,
      "step": 15030
    },
    {
      "epoch": 167.05555555555554,
      "grad_norm": 7.159752613006276e-07,
      "learning_rate": 3.450537464252964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4211216,
      "step": 15035
    },
    {
      "epoch": 167.11111111111111,
      "grad_norm": 2.536623924243031e-06,
      "learning_rate": 3.4496293743607925e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4212656,
      "step": 15040
    },
    {
      "epoch": 167.16666666666666,
      "grad_norm": 6.754280548193492e-07,
      "learning_rate": 3.448721138023838e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4214032,
      "step": 15045
    },
    {
      "epoch": 167.22222222222223,
      "grad_norm": 1.557558903186873e-06,
      "learning_rate": 3.447812755382162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4215440,
      "step": 15050
    },
    {
      "epoch": 167.27777777777777,
      "grad_norm": 6.824333809163363e-07,
      "learning_rate": 3.446904226575847e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4216848,
      "step": 15055
    },
    {
      "epoch": 167.33333333333334,
      "grad_norm": 7.590302288917883e-07,
      "learning_rate": 3.445995551745002e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4218256,
      "step": 15060
    },
    {
      "epoch": 167.38888888888889,
      "grad_norm": 1.5249514717652346e-06,
      "learning_rate": 3.445086731029753e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4219648,
      "step": 15065
    },
    {
      "epoch": 167.44444444444446,
      "grad_norm": 5.845818691341265e-07,
      "learning_rate": 3.444177764570255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4221024,
      "step": 15070
    },
    {
      "epoch": 167.5,
      "grad_norm": 5.932828344157315e-07,
      "learning_rate": 3.44326865250668e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4222480,
      "step": 15075
    },
    {
      "epoch": 167.55555555555554,
      "grad_norm": 6.824960792073398e-07,
      "learning_rate": 3.442359394979225e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4223840,
      "step": 15080
    },
    {
      "epoch": 167.61111111111111,
      "grad_norm": 1.5332068414863897e-06,
      "learning_rate": 3.441449992128108e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4225248,
      "step": 15085
    },
    {
      "epoch": 167.66666666666666,
      "grad_norm": 6.84701262798626e-07,
      "learning_rate": 3.440540444093573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4226656,
      "step": 15090
    },
    {
      "epoch": 167.72222222222223,
      "grad_norm": 6.670826451227185e-07,
      "learning_rate": 3.43963075101588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4228032,
      "step": 15095
    },
    {
      "epoch": 167.77777777777777,
      "grad_norm": 1.5010072047516587e-06,
      "learning_rate": 3.438720913035318e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4229456,
      "step": 15100
    },
    {
      "epoch": 167.83333333333334,
      "grad_norm": 6.22131494765199e-07,
      "learning_rate": 3.437810930292195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4230848,
      "step": 15105
    },
    {
      "epoch": 167.88888888888889,
      "grad_norm": 6.631929636569112e-07,
      "learning_rate": 3.43690080292684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4232256,
      "step": 15110
    },
    {
      "epoch": 167.94444444444446,
      "grad_norm": 8.238968803198077e-06,
      "learning_rate": 3.435990531079608e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4233648,
      "step": 15115
    },
    {
      "epoch": 168.0,
      "grad_norm": 5.968135496914329e-07,
      "learning_rate": 3.435080114890874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4235040,
      "step": 15120
    },
    {
      "epoch": 168.05555555555554,
      "grad_norm": 5.250473122941912e-07,
      "learning_rate": 3.434169554501035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4236464,
      "step": 15125
    },
    {
      "epoch": 168.11111111111111,
      "grad_norm": 5.761637567047728e-07,
      "learning_rate": 3.433258850050511e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4237824,
      "step": 15130
    },
    {
      "epoch": 168.16666666666666,
      "grad_norm": 7.336158205362153e-07,
      "learning_rate": 3.4323480016797446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4239216,
      "step": 15135
    },
    {
      "epoch": 168.22222222222223,
      "grad_norm": 7.303146389858739e-07,
      "learning_rate": 3.4314370095291995e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4240624,
      "step": 15140
    },
    {
      "epoch": 168.27777777777777,
      "grad_norm": 6.127696906332858e-06,
      "learning_rate": 3.430525873739363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4242032,
      "step": 15145
    },
    {
      "epoch": 168.33333333333334,
      "grad_norm": 1.2411584293658962e-06,
      "learning_rate": 3.429614594450743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4243440,
      "step": 15150
    },
    {
      "epoch": 168.38888888888889,
      "grad_norm": 1.6197850527532864e-06,
      "learning_rate": 3.428703171803869e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4244864,
      "step": 15155
    },
    {
      "epoch": 168.44444444444446,
      "grad_norm": 4.666727875246579e-07,
      "learning_rate": 3.4277916059392964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4246320,
      "step": 15160
    },
    {
      "epoch": 168.5,
      "grad_norm": 1.5936296904328628e-06,
      "learning_rate": 3.426879896997598e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4247680,
      "step": 15165
    },
    {
      "epoch": 168.55555555555554,
      "grad_norm": 8.322287499140657e-07,
      "learning_rate": 3.425968045119372e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4249104,
      "step": 15170
    },
    {
      "epoch": 168.61111111111111,
      "grad_norm": 6.981111368986603e-07,
      "learning_rate": 3.425056050445237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4250480,
      "step": 15175
    },
    {
      "epoch": 168.66666666666666,
      "grad_norm": 8.214169042730646e-07,
      "learning_rate": 3.4241439131158336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4251872,
      "step": 15180
    },
    {
      "epoch": 168.72222222222223,
      "grad_norm": 6.213930419107783e-07,
      "learning_rate": 3.423231633271825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4253312,
      "step": 15185
    },
    {
      "epoch": 168.77777777777777,
      "grad_norm": 6.613387313336716e-07,
      "learning_rate": 3.4223192110538985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4254656,
      "step": 15190
    },
    {
      "epoch": 168.83333333333334,
      "grad_norm": 6.811590651523147e-07,
      "learning_rate": 3.4214066466027575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4256064,
      "step": 15195
    },
    {
      "epoch": 168.88888888888889,
      "grad_norm": 7.476476753254246e-07,
      "learning_rate": 3.4204939400591325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4257504,
      "step": 15200
    },
    {
      "epoch": 168.88888888888889,
      "eval_loss": 0.35443609952926636,
      "eval_runtime": 1.3324,
      "eval_samples_per_second": 30.02,
      "eval_steps_per_second": 15.01,
      "num_input_tokens_seen": 4257504,
      "step": 15200
    },
    {
      "epoch": 168.94444444444446,
      "grad_norm": 1.605454713171639e-06,
      "learning_rate": 3.419581091563775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4258928,
      "step": 15205
    },
    {
      "epoch": 169.0,
      "grad_norm": 1.2368220723146806e-06,
      "learning_rate": 3.418668101257456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4260272,
      "step": 15210
    },
    {
      "epoch": 169.05555555555554,
      "grad_norm": 1.549208377582545e-06,
      "learning_rate": 3.417754969280971e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4261680,
      "step": 15215
    },
    {
      "epoch": 169.11111111111111,
      "grad_norm": 7.190931228251429e-07,
      "learning_rate": 3.416841695775137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4263120,
      "step": 15220
    },
    {
      "epoch": 169.16666666666666,
      "grad_norm": 6.756120569662016e-07,
      "learning_rate": 3.415928280880792e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4264512,
      "step": 15225
    },
    {
      "epoch": 169.22222222222223,
      "grad_norm": 1.1144104519189568e-06,
      "learning_rate": 3.4150147247387965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4265952,
      "step": 15230
    },
    {
      "epoch": 169.27777777777777,
      "grad_norm": 1.1020505326087005e-06,
      "learning_rate": 3.4141010274900306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4267344,
      "step": 15235
    },
    {
      "epoch": 169.33333333333334,
      "grad_norm": 3.487229605525499e-06,
      "learning_rate": 3.413187189275399e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4268752,
      "step": 15240
    },
    {
      "epoch": 169.38888888888889,
      "grad_norm": 1.6146365169333876e-06,
      "learning_rate": 3.4122732102358265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4270080,
      "step": 15245
    },
    {
      "epoch": 169.44444444444446,
      "grad_norm": 1.1217308610866894e-06,
      "learning_rate": 3.411359090512261e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4271440,
      "step": 15250
    },
    {
      "epoch": 169.5,
      "grad_norm": 1.17275055799837e-06,
      "learning_rate": 3.410444830245672e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4272832,
      "step": 15255
    },
    {
      "epoch": 169.55555555555554,
      "grad_norm": 5.723994149775535e-07,
      "learning_rate": 3.409530429577048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4274240,
      "step": 15260
    },
    {
      "epoch": 169.61111111111111,
      "grad_norm": 7.253592571032641e-07,
      "learning_rate": 3.408615888647402e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4275664,
      "step": 15265
    },
    {
      "epoch": 169.66666666666666,
      "grad_norm": 1.8174700926465448e-06,
      "learning_rate": 3.4077012075977675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4277056,
      "step": 15270
    },
    {
      "epoch": 169.72222222222223,
      "grad_norm": 1.0903377187787555e-06,
      "learning_rate": 3.4067863865692e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4278432,
      "step": 15275
    },
    {
      "epoch": 169.77777777777777,
      "grad_norm": 6.168358481772884e-07,
      "learning_rate": 3.4058714257027755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4279792,
      "step": 15280
    },
    {
      "epoch": 169.83333333333334,
      "grad_norm": 6.029901555848483e-07,
      "learning_rate": 3.404956325139594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4281232,
      "step": 15285
    },
    {
      "epoch": 169.88888888888889,
      "grad_norm": 6.511405672426918e-07,
      "learning_rate": 3.404041085020775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4282624,
      "step": 15290
    },
    {
      "epoch": 169.94444444444446,
      "grad_norm": 7.092793907759187e-07,
      "learning_rate": 3.403125705487459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4284064,
      "step": 15295
    },
    {
      "epoch": 170.0,
      "grad_norm": 2.075661768685677e-06,
      "learning_rate": 3.402210186680811e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4285504,
      "step": 15300
    },
    {
      "epoch": 170.05555555555554,
      "grad_norm": 5.460708507598611e-07,
      "learning_rate": 3.4012945287420137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4286848,
      "step": 15305
    },
    {
      "epoch": 170.11111111111111,
      "grad_norm": 7.076527595017978e-07,
      "learning_rate": 3.400378731812274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4288208,
      "step": 15310
    },
    {
      "epoch": 170.16666666666666,
      "grad_norm": 1.5781665752001572e-06,
      "learning_rate": 3.399462796032817e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4289600,
      "step": 15315
    },
    {
      "epoch": 170.22222222222223,
      "grad_norm": 7.551488465651346e-07,
      "learning_rate": 3.3985467215448954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4290992,
      "step": 15320
    },
    {
      "epoch": 170.27777777777777,
      "grad_norm": 6.841590334261127e-07,
      "learning_rate": 3.3976305084897776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4292384,
      "step": 15325
    },
    {
      "epoch": 170.33333333333334,
      "grad_norm": 5.74121122554061e-06,
      "learning_rate": 3.3967141570087544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4293760,
      "step": 15330
    },
    {
      "epoch": 170.38888888888889,
      "grad_norm": 1.216618443322659e-06,
      "learning_rate": 3.39579766724314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4295152,
      "step": 15335
    },
    {
      "epoch": 170.44444444444446,
      "grad_norm": 5.409025902736175e-07,
      "learning_rate": 3.3948810393342677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4296560,
      "step": 15340
    },
    {
      "epoch": 170.5,
      "grad_norm": 4.769822794514766e-07,
      "learning_rate": 3.3939642734234936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4297968,
      "step": 15345
    },
    {
      "epoch": 170.55555555555554,
      "grad_norm": 7.339343142120924e-07,
      "learning_rate": 3.393047369652194e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4299376,
      "step": 15350
    },
    {
      "epoch": 170.61111111111111,
      "grad_norm": 4.261535195837496e-06,
      "learning_rate": 3.3921303281617664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4300832,
      "step": 15355
    },
    {
      "epoch": 170.66666666666666,
      "grad_norm": 6.389603299794544e-07,
      "learning_rate": 3.391213149093632e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4302240,
      "step": 15360
    },
    {
      "epoch": 170.72222222222223,
      "grad_norm": 1.6285606534438557e-06,
      "learning_rate": 3.3902958325892303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4303600,
      "step": 15365
    },
    {
      "epoch": 170.77777777777777,
      "grad_norm": 3.7548377349594375e-06,
      "learning_rate": 3.389378378790023e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4305040,
      "step": 15370
    },
    {
      "epoch": 170.83333333333334,
      "grad_norm": 4.860310127696721e-07,
      "learning_rate": 3.388460787837493e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4306432,
      "step": 15375
    },
    {
      "epoch": 170.88888888888889,
      "grad_norm": 6.098551921240869e-07,
      "learning_rate": 3.387543059873145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4307840,
      "step": 15380
    },
    {
      "epoch": 170.94444444444446,
      "grad_norm": 6.628052346968616e-07,
      "learning_rate": 3.386625195038503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4309248,
      "step": 15385
    },
    {
      "epoch": 171.0,
      "grad_norm": 3.5258456136944005e-06,
      "learning_rate": 3.3857071934751136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4310656,
      "step": 15390
    },
    {
      "epoch": 171.05555555555554,
      "grad_norm": 6.69169708089612e-07,
      "learning_rate": 3.384789055324544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4312048,
      "step": 15395
    },
    {
      "epoch": 171.11111111111111,
      "grad_norm": 6.751619139322429e-07,
      "learning_rate": 3.3838707807283843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4313408,
      "step": 15400
    },
    {
      "epoch": 171.11111111111111,
      "eval_loss": 0.36459964513778687,
      "eval_runtime": 1.3252,
      "eval_samples_per_second": 30.184,
      "eval_steps_per_second": 15.092,
      "num_input_tokens_seen": 4313408,
      "step": 15400
    },
    {
      "epoch": 171.16666666666666,
      "grad_norm": 1.2645043625525432e-06,
      "learning_rate": 3.382952369828243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4314832,
      "step": 15405
    },
    {
      "epoch": 171.22222222222223,
      "grad_norm": 1.5665594901292934e-06,
      "learning_rate": 3.38203382276575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4316208,
      "step": 15410
    },
    {
      "epoch": 171.27777777777777,
      "grad_norm": 7.007853923823859e-07,
      "learning_rate": 3.381115139682557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4317584,
      "step": 15415
    },
    {
      "epoch": 171.33333333333334,
      "grad_norm": 2.1871317130717216e-06,
      "learning_rate": 3.3801963207203366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4318944,
      "step": 15420
    },
    {
      "epoch": 171.38888888888889,
      "grad_norm": 5.812242989122751e-07,
      "learning_rate": 3.379277366020782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4320384,
      "step": 15425
    },
    {
      "epoch": 171.44444444444446,
      "grad_norm": 7.462084568032878e-07,
      "learning_rate": 3.3783582757256085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4321808,
      "step": 15430
    },
    {
      "epoch": 171.5,
      "grad_norm": 1.5886712390056346e-06,
      "learning_rate": 3.3774390499765504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4323232,
      "step": 15435
    },
    {
      "epoch": 171.55555555555554,
      "grad_norm": 8.353100042768347e-07,
      "learning_rate": 3.376519688915364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4324656,
      "step": 15440
    },
    {
      "epoch": 171.61111111111111,
      "grad_norm": 7.801975243637571e-07,
      "learning_rate": 3.3756001926838273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4326064,
      "step": 15445
    },
    {
      "epoch": 171.66666666666666,
      "grad_norm": 7.190495807662955e-07,
      "learning_rate": 3.374680561423737e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4327424,
      "step": 15450
    },
    {
      "epoch": 171.72222222222223,
      "grad_norm": 6.861824886073009e-07,
      "learning_rate": 3.373760795276912e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4328832,
      "step": 15455
    },
    {
      "epoch": 171.77777777777777,
      "grad_norm": 6.196785875545174e-07,
      "learning_rate": 3.372840894385192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4330240,
      "step": 15460
    },
    {
      "epoch": 171.83333333333334,
      "grad_norm": 2.349337819396169e-06,
      "learning_rate": 3.3719208588904375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4331632,
      "step": 15465
    },
    {
      "epoch": 171.88888888888889,
      "grad_norm": 6.171773634378042e-07,
      "learning_rate": 3.371000688934529e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4333024,
      "step": 15470
    },
    {
      "epoch": 171.94444444444446,
      "grad_norm": 6.740307867403317e-07,
      "learning_rate": 3.370080384659369e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4334416,
      "step": 15475
    },
    {
      "epoch": 172.0,
      "grad_norm": 1.4959331338104676e-06,
      "learning_rate": 3.36915994620688e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4335808,
      "step": 15480
    },
    {
      "epoch": 172.05555555555554,
      "grad_norm": 5.438927246359526e-07,
      "learning_rate": 3.3682393737190035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4337264,
      "step": 15485
    },
    {
      "epoch": 172.11111111111111,
      "grad_norm": 6.964216368032794e-07,
      "learning_rate": 3.3673186673377054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4338688,
      "step": 15490
    },
    {
      "epoch": 172.16666666666666,
      "grad_norm": 3.1185379611997632e-06,
      "learning_rate": 3.366397827204969e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4340048,
      "step": 15495
    },
    {
      "epoch": 172.22222222222223,
      "grad_norm": 5.140936991665512e-06,
      "learning_rate": 3.3654768534628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4341472,
      "step": 15500
    },
    {
      "epoch": 172.27777777777777,
      "grad_norm": 6.624684942835302e-07,
      "learning_rate": 3.3645557462532245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4342944,
      "step": 15505
    },
    {
      "epoch": 172.33333333333334,
      "grad_norm": 5.89355238389544e-07,
      "learning_rate": 3.363634505718288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4344336,
      "step": 15510
    },
    {
      "epoch": 172.38888888888889,
      "grad_norm": 7.665720431759837e-07,
      "learning_rate": 3.362713132000057e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4345744,
      "step": 15515
    },
    {
      "epoch": 172.44444444444446,
      "grad_norm": 5.824452387059864e-07,
      "learning_rate": 3.36179162524062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4347136,
      "step": 15520
    },
    {
      "epoch": 172.5,
      "grad_norm": 2.3719358068774454e-06,
      "learning_rate": 3.3608699855820846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4348544,
      "step": 15525
    },
    {
      "epoch": 172.55555555555554,
      "grad_norm": 5.95752908338909e-07,
      "learning_rate": 3.359948213166578e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4349920,
      "step": 15530
    },
    {
      "epoch": 172.61111111111111,
      "grad_norm": 1.581874812472961e-06,
      "learning_rate": 3.359026308136252e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4351312,
      "step": 15535
    },
    {
      "epoch": 172.66666666666666,
      "grad_norm": 6.897820981066616e-07,
      "learning_rate": 3.358104270633272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4352704,
      "step": 15540
    },
    {
      "epoch": 172.72222222222223,
      "grad_norm": 5.744659574702382e-07,
      "learning_rate": 3.357182100799831e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4354096,
      "step": 15545
    },
    {
      "epoch": 172.77777777777777,
      "grad_norm": 1.525804805169173e-06,
      "learning_rate": 3.3562597987781384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4355504,
      "step": 15550
    },
    {
      "epoch": 172.83333333333334,
      "grad_norm": 6.471531719398627e-07,
      "learning_rate": 3.355337364710424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4356816,
      "step": 15555
    },
    {
      "epoch": 172.88888888888889,
      "grad_norm": 5.616968223876029e-07,
      "learning_rate": 3.354414798738939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4358192,
      "step": 15560
    },
    {
      "epoch": 172.94444444444446,
      "grad_norm": 8.770644512878789e-07,
      "learning_rate": 3.353492101005955e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4359648,
      "step": 15565
    },
    {
      "epoch": 173.0,
      "grad_norm": 7.077009627209918e-07,
      "learning_rate": 3.352569271653763e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4361024,
      "step": 15570
    },
    {
      "epoch": 173.05555555555554,
      "grad_norm": 7.139450985960138e-07,
      "learning_rate": 3.351646310824675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4362464,
      "step": 15575
    },
    {
      "epoch": 173.11111111111111,
      "grad_norm": 1.647856947784021e-06,
      "learning_rate": 3.350723218661023e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4363872,
      "step": 15580
    },
    {
      "epoch": 173.16666666666666,
      "grad_norm": 1.4864082231724751e-06,
      "learning_rate": 3.349799995305162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4365264,
      "step": 15585
    },
    {
      "epoch": 173.22222222222223,
      "grad_norm": 7.925232807792781e-07,
      "learning_rate": 3.348876640899461e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4366640,
      "step": 15590
    },
    {
      "epoch": 173.27777777777777,
      "grad_norm": 1.6074591258075088e-06,
      "learning_rate": 3.3479531555863144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4368080,
      "step": 15595
    },
    {
      "epoch": 173.33333333333334,
      "grad_norm": 1.6507149211975047e-06,
      "learning_rate": 3.3470295395081344e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4369488,
      "step": 15600
    },
    {
      "epoch": 173.33333333333334,
      "eval_loss": 0.3906360864639282,
      "eval_runtime": 1.3263,
      "eval_samples_per_second": 30.16,
      "eval_steps_per_second": 15.08,
      "num_input_tokens_seen": 4369488,
      "step": 15600
    },
    {
      "epoch": 173.38888888888889,
      "grad_norm": 1.5504048178627272e-06,
      "learning_rate": 3.3461057928073556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4370896,
      "step": 15605
    },
    {
      "epoch": 173.44444444444446,
      "grad_norm": 1.5239978665704257e-06,
      "learning_rate": 3.345181915626431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4372272,
      "step": 15610
    },
    {
      "epoch": 173.5,
      "grad_norm": 6.149406885924691e-07,
      "learning_rate": 3.344257908107834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4373696,
      "step": 15615
    },
    {
      "epoch": 173.55555555555554,
      "grad_norm": 5.17405942446203e-06,
      "learning_rate": 3.343333770394058e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4375088,
      "step": 15620
    },
    {
      "epoch": 173.61111111111111,
      "grad_norm": 1.6781498288764851e-06,
      "learning_rate": 3.342409502627616e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4376512,
      "step": 15625
    },
    {
      "epoch": 173.66666666666666,
      "grad_norm": 6.783134836041427e-07,
      "learning_rate": 3.341485104951043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4377920,
      "step": 15630
    },
    {
      "epoch": 173.72222222222223,
      "grad_norm": 6.34307411928603e-07,
      "learning_rate": 3.340560577506892e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4379296,
      "step": 15635
    },
    {
      "epoch": 173.77777777777777,
      "grad_norm": 2.187980953749502e-06,
      "learning_rate": 3.339635920437735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4380672,
      "step": 15640
    },
    {
      "epoch": 173.83333333333334,
      "grad_norm": 3.267875854362501e-06,
      "learning_rate": 3.338711133886169e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4382048,
      "step": 15645
    },
    {
      "epoch": 173.88888888888889,
      "grad_norm": 6.692775400551909e-07,
      "learning_rate": 3.3377862179948064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4383440,
      "step": 15650
    },
    {
      "epoch": 173.94444444444446,
      "grad_norm": 6.75011165185424e-07,
      "learning_rate": 3.336861172906281e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4384848,
      "step": 15655
    },
    {
      "epoch": 174.0,
      "grad_norm": 6.576267423952231e-07,
      "learning_rate": 3.335935998763245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4386256,
      "step": 15660
    },
    {
      "epoch": 174.05555555555554,
      "grad_norm": 6.273744020290906e-06,
      "learning_rate": 3.3350106957083744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4387600,
      "step": 15665
    },
    {
      "epoch": 174.11111111111111,
      "grad_norm": 6.36067113646277e-07,
      "learning_rate": 3.33408526388436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4388992,
      "step": 15670
    },
    {
      "epoch": 174.16666666666666,
      "grad_norm": 8.598889849054103e-07,
      "learning_rate": 3.3331597034339166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4390416,
      "step": 15675
    },
    {
      "epoch": 174.22222222222223,
      "grad_norm": 1.003442548608291e-06,
      "learning_rate": 3.3322340144997764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4391808,
      "step": 15680
    },
    {
      "epoch": 174.27777777777777,
      "grad_norm": 3.0063076792430365e-06,
      "learning_rate": 3.331308197224693e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4393200,
      "step": 15685
    },
    {
      "epoch": 174.33333333333334,
      "grad_norm": 5.740583901570062e-07,
      "learning_rate": 3.330382251751438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4394608,
      "step": 15690
    },
    {
      "epoch": 174.38888888888889,
      "grad_norm": 5.330933845471009e-07,
      "learning_rate": 3.3294561782228054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4395952,
      "step": 15695
    },
    {
      "epoch": 174.44444444444446,
      "grad_norm": 6.876448424009141e-07,
      "learning_rate": 3.328529976781607e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4397360,
      "step": 15700
    },
    {
      "epoch": 174.5,
      "grad_norm": 6.00254509208753e-07,
      "learning_rate": 3.327603647570673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4398816,
      "step": 15705
    },
    {
      "epoch": 174.55555555555554,
      "grad_norm": 2.5214944798790384e-06,
      "learning_rate": 3.326677190732857e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4400208,
      "step": 15710
    },
    {
      "epoch": 174.61111111111111,
      "grad_norm": 1.6708831935829949e-06,
      "learning_rate": 3.325750606411029e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4401616,
      "step": 15715
    },
    {
      "epoch": 174.66666666666666,
      "grad_norm": 6.298419634731545e-07,
      "learning_rate": 3.3248238947480804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4403008,
      "step": 15720
    },
    {
      "epoch": 174.72222222222223,
      "grad_norm": 1.6016940662666457e-06,
      "learning_rate": 3.323897055886922e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4404432,
      "step": 15725
    },
    {
      "epoch": 174.77777777777777,
      "grad_norm": 6.975357678129512e-07,
      "learning_rate": 3.322970089970484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4405840,
      "step": 15730
    },
    {
      "epoch": 174.83333333333334,
      "grad_norm": 5.930149313826405e-07,
      "learning_rate": 3.3220429971417165e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4407280,
      "step": 15735
    },
    {
      "epoch": 174.88888888888889,
      "grad_norm": 6.044734277566022e-07,
      "learning_rate": 3.321115777543588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4408672,
      "step": 15740
    },
    {
      "epoch": 174.94444444444446,
      "grad_norm": 1.5118274632186512e-06,
      "learning_rate": 3.320188431319088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4410144,
      "step": 15745
    },
    {
      "epoch": 175.0,
      "grad_norm": 5.938924232395948e-07,
      "learning_rate": 3.319260958611224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4411504,
      "step": 15750
    },
    {
      "epoch": 175.05555555555554,
      "grad_norm": 6.736444220223348e-07,
      "learning_rate": 3.3183333595630256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4412928,
      "step": 15755
    },
    {
      "epoch": 175.11111111111111,
      "grad_norm": 5.846729322911415e-07,
      "learning_rate": 3.317405634317538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4414352,
      "step": 15760
    },
    {
      "epoch": 175.16666666666666,
      "grad_norm": 1.5399815538330586e-06,
      "learning_rate": 3.3164777830178315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4415712,
      "step": 15765
    },
    {
      "epoch": 175.22222222222223,
      "grad_norm": 1.20100480671681e-06,
      "learning_rate": 3.315549805806989e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4417072,
      "step": 15770
    },
    {
      "epoch": 175.27777777777777,
      "grad_norm": 7.050462613733544e-07,
      "learning_rate": 3.314621702828118e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4418512,
      "step": 15775
    },
    {
      "epoch": 175.33333333333334,
      "grad_norm": 6.991143095547159e-07,
      "learning_rate": 3.313693474224342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4419888,
      "step": 15780
    },
    {
      "epoch": 175.38888888888889,
      "grad_norm": 6.036713102730573e-07,
      "learning_rate": 3.312765120138809e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4421296,
      "step": 15785
    },
    {
      "epoch": 175.44444444444446,
      "grad_norm": 5.444258590614481e-07,
      "learning_rate": 3.311836640714679e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4422736,
      "step": 15790
    },
    {
      "epoch": 175.5,
      "grad_norm": 5.3926341934129596e-06,
      "learning_rate": 3.310908036095137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4424144,
      "step": 15795
    },
    {
      "epoch": 175.55555555555554,
      "grad_norm": 1.2396633337630192e-06,
      "learning_rate": 3.309979306423386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4425536,
      "step": 15800
    },
    {
      "epoch": 175.55555555555554,
      "eval_loss": 0.36695390939712524,
      "eval_runtime": 1.3199,
      "eval_samples_per_second": 30.306,
      "eval_steps_per_second": 15.153,
      "num_input_tokens_seen": 4425536,
      "step": 15800
    },
    {
      "epoch": 175.61111111111111,
      "grad_norm": 6.025393304298632e-07,
      "learning_rate": 3.309050451842647e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4426992,
      "step": 15805
    },
    {
      "epoch": 175.66666666666666,
      "grad_norm": 5.349156140255218e-07,
      "learning_rate": 3.3081214724961604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4428384,
      "step": 15810
    },
    {
      "epoch": 175.72222222222223,
      "grad_norm": 4.4644596641774115e-07,
      "learning_rate": 3.307192368527188e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4429760,
      "step": 15815
    },
    {
      "epoch": 175.77777777777777,
      "grad_norm": 5.911294920224464e-07,
      "learning_rate": 3.306263140079008e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4431152,
      "step": 15820
    },
    {
      "epoch": 175.83333333333334,
      "grad_norm": 6.419876967811433e-07,
      "learning_rate": 3.30533378729492e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4432544,
      "step": 15825
    },
    {
      "epoch": 175.88888888888889,
      "grad_norm": 1.6092184296212508e-06,
      "learning_rate": 3.304404310318242e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4433968,
      "step": 15830
    },
    {
      "epoch": 175.94444444444446,
      "grad_norm": 5.688078772436711e-07,
      "learning_rate": 3.3034747092923105e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4435344,
      "step": 15835
    },
    {
      "epoch": 176.0,
      "grad_norm": 1.073796056516585e-06,
      "learning_rate": 3.3025449843604806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4436752,
      "step": 15840
    },
    {
      "epoch": 176.05555555555554,
      "grad_norm": 6.571426638402045e-07,
      "learning_rate": 3.30161513566613e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4438176,
      "step": 15845
    },
    {
      "epoch": 176.11111111111111,
      "grad_norm": 6.306481168394384e-07,
      "learning_rate": 3.3006851633526506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4439552,
      "step": 15850
    },
    {
      "epoch": 176.16666666666666,
      "grad_norm": 6.831111249994137e-07,
      "learning_rate": 3.2997550675634584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4440944,
      "step": 15855
    },
    {
      "epoch": 176.22222222222223,
      "grad_norm": 3.1555482564726844e-06,
      "learning_rate": 3.2988248484419825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4442352,
      "step": 15860
    },
    {
      "epoch": 176.27777777777777,
      "grad_norm": 1.2244693152752006e-06,
      "learning_rate": 3.2978945061316776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4443744,
      "step": 15865
    },
    {
      "epoch": 176.33333333333334,
      "grad_norm": 3.16075283990358e-06,
      "learning_rate": 3.296964040776013e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4445200,
      "step": 15870
    },
    {
      "epoch": 176.38888888888889,
      "grad_norm": 7.253981948451838e-07,
      "learning_rate": 3.296033452518478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4446608,
      "step": 15875
    },
    {
      "epoch": 176.44444444444446,
      "grad_norm": 6.14956661593169e-07,
      "learning_rate": 3.2951027415025806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4448032,
      "step": 15880
    },
    {
      "epoch": 176.5,
      "grad_norm": 6.073319127608556e-07,
      "learning_rate": 3.294171907871849e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4449472,
      "step": 15885
    },
    {
      "epoch": 176.55555555555554,
      "grad_norm": 1.1983655667791027e-06,
      "learning_rate": 3.293240951769828e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4450864,
      "step": 15890
    },
    {
      "epoch": 176.61111111111111,
      "grad_norm": 2.025818048423389e-06,
      "learning_rate": 3.2923098733400846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4452272,
      "step": 15895
    },
    {
      "epoch": 176.66666666666666,
      "grad_norm": 7.104197266016854e-07,
      "learning_rate": 3.291378672726202e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4453728,
      "step": 15900
    },
    {
      "epoch": 176.72222222222223,
      "grad_norm": 6.192494197421183e-07,
      "learning_rate": 3.2904473500717824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4455120,
      "step": 15905
    },
    {
      "epoch": 176.77777777777777,
      "grad_norm": 1.7047544815795845e-06,
      "learning_rate": 3.289515905520449e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4456512,
      "step": 15910
    },
    {
      "epoch": 176.83333333333334,
      "grad_norm": 7.68949121265905e-07,
      "learning_rate": 3.288584339215841e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4457840,
      "step": 15915
    },
    {
      "epoch": 176.88888888888889,
      "grad_norm": 7.853595889173448e-07,
      "learning_rate": 3.287652651301617e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4459216,
      "step": 15920
    },
    {
      "epoch": 176.94444444444446,
      "grad_norm": 3.0394135137612466e-06,
      "learning_rate": 3.286720841921457e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4460576,
      "step": 15925
    },
    {
      "epoch": 177.0,
      "grad_norm": 4.982438213119167e-07,
      "learning_rate": 3.285788911219056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4462000,
      "step": 15930
    },
    {
      "epoch": 177.05555555555554,
      "grad_norm": 5.221154424361885e-07,
      "learning_rate": 3.284856859338131e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4463392,
      "step": 15935
    },
    {
      "epoch": 177.11111111111111,
      "grad_norm": 1.5853111108299345e-06,
      "learning_rate": 3.283924686422414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4464784,
      "step": 15940
    },
    {
      "epoch": 177.16666666666666,
      "grad_norm": 5.435459229374828e-07,
      "learning_rate": 3.282992392615659e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4466160,
      "step": 15945
    },
    {
      "epoch": 177.22222222222223,
      "grad_norm": 1.0939459116343642e-06,
      "learning_rate": 3.282059978061638e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4467568,
      "step": 15950
    },
    {
      "epoch": 177.27777777777777,
      "grad_norm": 6.707612669742957e-07,
      "learning_rate": 3.28112744290414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4468944,
      "step": 15955
    },
    {
      "epoch": 177.33333333333334,
      "grad_norm": 6.272608743529418e-07,
      "learning_rate": 3.280194787286974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4470400,
      "step": 15960
    },
    {
      "epoch": 177.38888888888889,
      "grad_norm": 1.548698264741688e-06,
      "learning_rate": 3.2792620113539674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4471824,
      "step": 15965
    },
    {
      "epoch": 177.44444444444446,
      "grad_norm": 1.5699156392656732e-06,
      "learning_rate": 3.278329115248966e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4473216,
      "step": 15970
    },
    {
      "epoch": 177.5,
      "grad_norm": 7.274920221789216e-07,
      "learning_rate": 3.277396099115834e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4474592,
      "step": 15975
    },
    {
      "epoch": 177.55555555555554,
      "grad_norm": 1.53656196744123e-06,
      "learning_rate": 3.276462963098454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4476016,
      "step": 15980
    },
    {
      "epoch": 177.61111111111111,
      "grad_norm": 7.945906190798269e-07,
      "learning_rate": 3.275529707340728e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4477408,
      "step": 15985
    },
    {
      "epoch": 177.66666666666666,
      "grad_norm": 6.255825724110764e-07,
      "learning_rate": 3.274596331986574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4478752,
      "step": 15990
    },
    {
      "epoch": 177.72222222222223,
      "grad_norm": 5.720266926800832e-07,
      "learning_rate": 3.273662837179932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4480160,
      "step": 15995
    },
    {
      "epoch": 177.77777777777777,
      "grad_norm": 1.5960315522534074e-06,
      "learning_rate": 3.272729223064758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4481568,
      "step": 16000
    },
    {
      "epoch": 177.77777777777777,
      "eval_loss": 0.34323424100875854,
      "eval_runtime": 1.3173,
      "eval_samples_per_second": 30.366,
      "eval_steps_per_second": 15.183,
      "num_input_tokens_seen": 4481568,
      "step": 16000
    },
    {
      "epoch": 177.83333333333334,
      "grad_norm": 6.590007046725077e-07,
      "learning_rate": 3.2717954897850264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4482960,
      "step": 16005
    },
    {
      "epoch": 177.88888888888889,
      "grad_norm": 5.181581741453556e-07,
      "learning_rate": 3.270861637484733e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4484352,
      "step": 16010
    },
    {
      "epoch": 177.94444444444446,
      "grad_norm": 1.160653482656926e-06,
      "learning_rate": 3.2699276663078867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4485776,
      "step": 16015
    },
    {
      "epoch": 178.0,
      "grad_norm": 1.2340217381279217e-06,
      "learning_rate": 3.268993576398519e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4487184,
      "step": 16020
    },
    {
      "epoch": 178.05555555555554,
      "grad_norm": 2.4090618353511672e-06,
      "learning_rate": 3.268059367900678e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4488608,
      "step": 16025
    },
    {
      "epoch": 178.11111111111111,
      "grad_norm": 1.6652865042487974e-06,
      "learning_rate": 3.26712504095843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4490032,
      "step": 16030
    },
    {
      "epoch": 178.16666666666666,
      "grad_norm": 6.889573000989913e-07,
      "learning_rate": 3.2661905957158615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4491472,
      "step": 16035
    },
    {
      "epoch": 178.22222222222223,
      "grad_norm": 1.282850121242518e-06,
      "learning_rate": 3.2652560323170734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4492880,
      "step": 16040
    },
    {
      "epoch": 178.27777777777777,
      "grad_norm": 5.095017172607186e-07,
      "learning_rate": 3.264321350906189e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4494272,
      "step": 16045
    },
    {
      "epoch": 178.33333333333334,
      "grad_norm": 7.05667957845435e-07,
      "learning_rate": 3.263386551627346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4495632,
      "step": 16050
    },
    {
      "epoch": 178.38888888888889,
      "grad_norm": 7.39190340937057e-07,
      "learning_rate": 3.2624516346247055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4497040,
      "step": 16055
    },
    {
      "epoch": 178.44444444444446,
      "grad_norm": 2.0656104879890336e-06,
      "learning_rate": 3.2615166000424404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4498448,
      "step": 16060
    },
    {
      "epoch": 178.5,
      "grad_norm": 6.219240731297759e-07,
      "learning_rate": 3.260581448024745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4499888,
      "step": 16065
    },
    {
      "epoch": 178.55555555555554,
      "grad_norm": 8.986834245661157e-07,
      "learning_rate": 3.2596461787158335e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4501296,
      "step": 16070
    },
    {
      "epoch": 178.61111111111111,
      "grad_norm": 7.065132194838952e-07,
      "learning_rate": 3.258710792259934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4502672,
      "step": 16075
    },
    {
      "epoch": 178.66666666666666,
      "grad_norm": 1.5826944945729338e-06,
      "learning_rate": 3.257775288801296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4504032,
      "step": 16080
    },
    {
      "epoch": 178.72222222222223,
      "grad_norm": 6.578650300070876e-07,
      "learning_rate": 3.256839668484186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4505424,
      "step": 16085
    },
    {
      "epoch": 178.77777777777777,
      "grad_norm": 1.172291945295001e-06,
      "learning_rate": 3.255903931452888e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4506800,
      "step": 16090
    },
    {
      "epoch": 178.83333333333334,
      "grad_norm": 5.184135716262972e-07,
      "learning_rate": 3.2549680778517045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4508144,
      "step": 16095
    },
    {
      "epoch": 178.88888888888889,
      "grad_norm": 5.180776270208298e-07,
      "learning_rate": 3.2540321078249556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4509584,
      "step": 16100
    },
    {
      "epoch": 178.94444444444446,
      "grad_norm": 5.455036102830491e-07,
      "learning_rate": 3.2530960215169795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4510976,
      "step": 16105
    },
    {
      "epoch": 179.0,
      "grad_norm": 1.4888814803271089e-06,
      "learning_rate": 3.2521598190721345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4512384,
      "step": 16110
    },
    {
      "epoch": 179.05555555555554,
      "grad_norm": 6.267649723668001e-07,
      "learning_rate": 3.251223500634792e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4513744,
      "step": 16115
    },
    {
      "epoch": 179.11111111111111,
      "grad_norm": 1.6041916524045519e-06,
      "learning_rate": 3.2502870663493445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4515152,
      "step": 16120
    },
    {
      "epoch": 179.16666666666666,
      "grad_norm": 1.0610727940729703e-06,
      "learning_rate": 3.249350516360203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4516544,
      "step": 16125
    },
    {
      "epoch": 179.22222222222223,
      "grad_norm": 6.716443294862984e-07,
      "learning_rate": 3.248413850811797e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4517968,
      "step": 16130
    },
    {
      "epoch": 179.27777777777777,
      "grad_norm": 5.653819812323491e-07,
      "learning_rate": 3.2474770698485677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4519344,
      "step": 16135
    },
    {
      "epoch": 179.33333333333334,
      "grad_norm": 6.507482339657145e-07,
      "learning_rate": 3.246540173614983e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4520736,
      "step": 16140
    },
    {
      "epoch": 179.38888888888889,
      "grad_norm": 7.276104270204087e-07,
      "learning_rate": 3.2456031622555197e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4522128,
      "step": 16145
    },
    {
      "epoch": 179.44444444444446,
      "grad_norm": 2.0451645923458273e-06,
      "learning_rate": 3.2446660359146794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4523552,
      "step": 16150
    },
    {
      "epoch": 179.5,
      "grad_norm": 6.769998890376883e-07,
      "learning_rate": 3.2437287947369786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4524944,
      "step": 16155
    },
    {
      "epoch": 179.55555555555554,
      "grad_norm": 3.717420440807473e-06,
      "learning_rate": 3.2427914388669525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4526384,
      "step": 16160
    },
    {
      "epoch": 179.61111111111111,
      "grad_norm": 5.226610824138334e-07,
      "learning_rate": 3.241853968449151e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4527808,
      "step": 16165
    },
    {
      "epoch": 179.66666666666666,
      "grad_norm": 5.803317435493227e-07,
      "learning_rate": 3.240916383628144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4529200,
      "step": 16170
    },
    {
      "epoch": 179.72222222222223,
      "grad_norm": 4.2522810872469563e-07,
      "learning_rate": 3.239978684548521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4530624,
      "step": 16175
    },
    {
      "epoch": 179.77777777777777,
      "grad_norm": 1.5607172372256173e-06,
      "learning_rate": 3.239040871354885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4532016,
      "step": 16180
    },
    {
      "epoch": 179.83333333333334,
      "grad_norm": 9.858516705207876e-07,
      "learning_rate": 3.2381029441918596e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4533392,
      "step": 16185
    },
    {
      "epoch": 179.88888888888889,
      "grad_norm": 1.674602231105382e-06,
      "learning_rate": 3.2371649032040845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4534832,
      "step": 16190
    },
    {
      "epoch": 179.94444444444446,
      "grad_norm": 5.620759679914045e-07,
      "learning_rate": 3.2362267485362174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4536240,
      "step": 16195
    },
    {
      "epoch": 180.0,
      "grad_norm": 7.263777774824121e-07,
      "learning_rate": 3.235288480332934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4537616,
      "step": 16200
    },
    {
      "epoch": 180.0,
      "eval_loss": 0.3773461580276489,
      "eval_runtime": 1.2909,
      "eval_samples_per_second": 30.986,
      "eval_steps_per_second": 15.493,
      "num_input_tokens_seen": 4537616,
      "step": 16200
    },
    {
      "epoch": 180.05555555555554,
      "grad_norm": 4.706062100012787e-06,
      "learning_rate": 3.234350098738927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4539008,
      "step": 16205
    },
    {
      "epoch": 180.11111111111111,
      "grad_norm": 1.616664349057828e-06,
      "learning_rate": 3.233411603898906e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4540384,
      "step": 16210
    },
    {
      "epoch": 180.16666666666666,
      "grad_norm": 1.5576514442727785e-06,
      "learning_rate": 3.232472995957599e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4541776,
      "step": 16215
    },
    {
      "epoch": 180.22222222222223,
      "grad_norm": 1.1461783060440212e-06,
      "learning_rate": 3.231534275059751e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4543152,
      "step": 16220
    },
    {
      "epoch": 180.27777777777777,
      "grad_norm": 1.5375846942333737e-06,
      "learning_rate": 3.230595441350125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4544576,
      "step": 16225
    },
    {
      "epoch": 180.33333333333334,
      "grad_norm": 4.665664050662599e-07,
      "learning_rate": 3.2296564949735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4545984,
      "step": 16230
    },
    {
      "epoch": 180.38888888888889,
      "grad_norm": 5.21066908731882e-07,
      "learning_rate": 3.228717436074675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4547424,
      "step": 16235
    },
    {
      "epoch": 180.44444444444446,
      "grad_norm": 6.049625653758994e-07,
      "learning_rate": 3.227778264798463e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4548800,
      "step": 16240
    },
    {
      "epoch": 180.5,
      "grad_norm": 1.4931125633665943e-06,
      "learning_rate": 3.226838981289698e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4550176,
      "step": 16245
    },
    {
      "epoch": 180.55555555555554,
      "grad_norm": 1.5400014490296599e-06,
      "learning_rate": 3.225899585693227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4551584,
      "step": 16250
    },
    {
      "epoch": 180.61111111111111,
      "grad_norm": 6.927062372596993e-07,
      "learning_rate": 3.224960078153918e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4552992,
      "step": 16255
    },
    {
      "epoch": 180.66666666666666,
      "grad_norm": 1.035218247125158e-06,
      "learning_rate": 3.224020458816655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4554416,
      "step": 16260
    },
    {
      "epoch": 180.72222222222223,
      "grad_norm": 1.059389546753664e-06,
      "learning_rate": 3.223080727826337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4555840,
      "step": 16265
    },
    {
      "epoch": 180.77777777777777,
      "grad_norm": 6.984757874306524e-07,
      "learning_rate": 3.222140885327885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4557248,
      "step": 16270
    },
    {
      "epoch": 180.83333333333334,
      "grad_norm": 1.5840272453715443e-06,
      "learning_rate": 3.221200931466234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4558624,
      "step": 16275
    },
    {
      "epoch": 180.88888888888889,
      "grad_norm": 3.1754718747833977e-06,
      "learning_rate": 3.220260866386336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4560032,
      "step": 16280
    },
    {
      "epoch": 180.94444444444446,
      "grad_norm": 7.127756020963716e-07,
      "learning_rate": 3.21932069023316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4561440,
      "step": 16285
    },
    {
      "epoch": 181.0,
      "grad_norm": 1.6175871451196144e-06,
      "learning_rate": 3.218380403151695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4562880,
      "step": 16290
    },
    {
      "epoch": 181.05555555555554,
      "grad_norm": 1.1964475561399013e-06,
      "learning_rate": 3.217440005286943e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4564208,
      "step": 16295
    },
    {
      "epoch": 181.11111111111111,
      "grad_norm": 6.225855599950592e-07,
      "learning_rate": 3.216499496783928e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4565632,
      "step": 16300
    },
    {
      "epoch": 181.16666666666666,
      "grad_norm": 5.81685412726074e-07,
      "learning_rate": 3.2155588777876856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4567056,
      "step": 16305
    },
    {
      "epoch": 181.22222222222223,
      "grad_norm": 7.193271471805929e-07,
      "learning_rate": 3.214618148443273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4568480,
      "step": 16310
    },
    {
      "epoch": 181.27777777777777,
      "grad_norm": 3.9139313230407424e-06,
      "learning_rate": 3.2136773088957595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4569856,
      "step": 16315
    },
    {
      "epoch": 181.33333333333334,
      "grad_norm": 1.1881173804795253e-06,
      "learning_rate": 3.2127363592902374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4571216,
      "step": 16320
    },
    {
      "epoch": 181.38888888888889,
      "grad_norm": 5.613183589048276e-07,
      "learning_rate": 3.211795299771812e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4572640,
      "step": 16325
    },
    {
      "epoch": 181.44444444444446,
      "grad_norm": 1.5487469227082329e-06,
      "learning_rate": 3.210854130485605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4574032,
      "step": 16330
    },
    {
      "epoch": 181.5,
      "grad_norm": 6.479177159235405e-07,
      "learning_rate": 3.209912851576759e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4575408,
      "step": 16335
    },
    {
      "epoch": 181.55555555555554,
      "grad_norm": 1.565018010296626e-06,
      "learning_rate": 3.208971463190431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4576784,
      "step": 16340
    },
    {
      "epoch": 181.61111111111111,
      "grad_norm": 2.478131136740558e-06,
      "learning_rate": 3.208029965471793e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4578176,
      "step": 16345
    },
    {
      "epoch": 181.66666666666666,
      "grad_norm": 1.513222969151684e-06,
      "learning_rate": 3.2070883585660364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4579568,
      "step": 16350
    },
    {
      "epoch": 181.72222222222223,
      "grad_norm": 7.599528544233181e-07,
      "learning_rate": 3.20614664261837e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4581008,
      "step": 16355
    },
    {
      "epoch": 181.77777777777777,
      "grad_norm": 1.1758020264096558e-06,
      "learning_rate": 3.205204817774016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4582416,
      "step": 16360
    },
    {
      "epoch": 181.83333333333334,
      "grad_norm": 8.373026503250003e-07,
      "learning_rate": 3.204262884178218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4583808,
      "step": 16365
    },
    {
      "epoch": 181.88888888888889,
      "grad_norm": 6.896817126289534e-07,
      "learning_rate": 3.2033208419762314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4585200,
      "step": 16370
    },
    {
      "epoch": 181.94444444444446,
      "grad_norm": 5.07225649926113e-07,
      "learning_rate": 3.2023786913133344e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4586608,
      "step": 16375
    },
    {
      "epoch": 182.0,
      "grad_norm": 5.568541041611752e-07,
      "learning_rate": 3.201436432334816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4588032,
      "step": 16380
    },
    {
      "epoch": 182.05555555555554,
      "grad_norm": 5.569280006056943e-07,
      "learning_rate": 3.2004940651859844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4589408,
      "step": 16385
    },
    {
      "epoch": 182.11111111111111,
      "grad_norm": 5.352276843950676e-07,
      "learning_rate": 3.1995515900121655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4590816,
      "step": 16390
    },
    {
      "epoch": 182.16666666666666,
      "grad_norm": 6.275407145039935e-07,
      "learning_rate": 3.1986090069587e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4592192,
      "step": 16395
    },
    {
      "epoch": 182.22222222222223,
      "grad_norm": 1.7118646837843698e-06,
      "learning_rate": 3.1976663161709466e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4593600,
      "step": 16400
    },
    {
      "epoch": 182.22222222222223,
      "eval_loss": 0.39895930886268616,
      "eval_runtime": 1.2932,
      "eval_samples_per_second": 30.93,
      "eval_steps_per_second": 15.465,
      "num_input_tokens_seen": 4593600,
      "step": 16400
    },
    {
      "epoch": 182.27777777777777,
      "grad_norm": 4.5969864004291594e-07,
      "learning_rate": 3.196723517794279e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4594992,
      "step": 16405
    },
    {
      "epoch": 182.33333333333334,
      "grad_norm": 9.853555411609705e-07,
      "learning_rate": 3.19578061197409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4596384,
      "step": 16410
    },
    {
      "epoch": 182.38888888888889,
      "grad_norm": 1.0170200539505458e-06,
      "learning_rate": 3.194837598855787e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4597840,
      "step": 16415
    },
    {
      "epoch": 182.44444444444446,
      "grad_norm": 6.250991191336652e-07,
      "learning_rate": 3.193894478584794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4599248,
      "step": 16420
    },
    {
      "epoch": 182.5,
      "grad_norm": 1.6514322851435281e-06,
      "learning_rate": 3.192951251306553e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4600640,
      "step": 16425
    },
    {
      "epoch": 182.55555555555554,
      "grad_norm": 4.350684434939467e-07,
      "learning_rate": 3.192007917166521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4602048,
      "step": 16430
    },
    {
      "epoch": 182.61111111111111,
      "grad_norm": 1.4807592378929257e-06,
      "learning_rate": 3.191064476310171e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4603424,
      "step": 16435
    },
    {
      "epoch": 182.66666666666666,
      "grad_norm": 6.428135179703531e-07,
      "learning_rate": 3.1901209288829944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4604784,
      "step": 16440
    },
    {
      "epoch": 182.72222222222223,
      "grad_norm": 5.85339194003609e-07,
      "learning_rate": 3.1891772750304985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4606160,
      "step": 16445
    },
    {
      "epoch": 182.77777777777777,
      "grad_norm": 1.035792024595139e-06,
      "learning_rate": 3.188233514898206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4607520,
      "step": 16450
    },
    {
      "epoch": 182.83333333333334,
      "grad_norm": 1.6280057479889365e-06,
      "learning_rate": 3.187289648631657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4608944,
      "step": 16455
    },
    {
      "epoch": 182.88888888888889,
      "grad_norm": 5.388337172007596e-07,
      "learning_rate": 3.186345676376406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4610304,
      "step": 16460
    },
    {
      "epoch": 182.94444444444446,
      "grad_norm": 5.375564455789572e-07,
      "learning_rate": 3.1854015982780275e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4611696,
      "step": 16465
    },
    {
      "epoch": 183.0,
      "grad_norm": 3.906607616954716e-06,
      "learning_rate": 3.1844574144821084e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4613136,
      "step": 16470
    },
    {
      "epoch": 183.05555555555554,
      "grad_norm": 5.38199344646273e-07,
      "learning_rate": 3.1835131251342554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4614592,
      "step": 16475
    },
    {
      "epoch": 183.11111111111111,
      "grad_norm": 6.187332246554433e-07,
      "learning_rate": 3.182568730380089e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4616016,
      "step": 16480
    },
    {
      "epoch": 183.16666666666666,
      "grad_norm": 1.1145041298732394e-06,
      "learning_rate": 3.181624230365245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4617456,
      "step": 16485
    },
    {
      "epoch": 183.22222222222223,
      "grad_norm": 6.812044262005656e-07,
      "learning_rate": 3.180679625235381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4618848,
      "step": 16490
    },
    {
      "epoch": 183.27777777777777,
      "grad_norm": 5.516750434253481e-07,
      "learning_rate": 3.1797349151361646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4620272,
      "step": 16495
    },
    {
      "epoch": 183.33333333333334,
      "grad_norm": 6.848926545899303e-07,
      "learning_rate": 3.178790100213281e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4621680,
      "step": 16500
    },
    {
      "epoch": 183.38888888888889,
      "grad_norm": 5.156940460437909e-06,
      "learning_rate": 3.1778451806124346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4623056,
      "step": 16505
    },
    {
      "epoch": 183.44444444444446,
      "grad_norm": 5.041986241849372e-07,
      "learning_rate": 3.176900156479342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4624432,
      "step": 16510
    },
    {
      "epoch": 183.5,
      "grad_norm": 5.374616875997162e-07,
      "learning_rate": 3.17595502795974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4625840,
      "step": 16515
    },
    {
      "epoch": 183.55555555555554,
      "grad_norm": 5.175986075300898e-07,
      "learning_rate": 3.175009795199377e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4627280,
      "step": 16520
    },
    {
      "epoch": 183.61111111111111,
      "grad_norm": 6.197429343046679e-07,
      "learning_rate": 3.1740644583440224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4628656,
      "step": 16525
    },
    {
      "epoch": 183.66666666666666,
      "grad_norm": 7.637510748281784e-07,
      "learning_rate": 3.173119017539457e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4630096,
      "step": 16530
    },
    {
      "epoch": 183.72222222222223,
      "grad_norm": 5.833003342559095e-07,
      "learning_rate": 3.172173472931479e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4631520,
      "step": 16535
    },
    {
      "epoch": 183.77777777777777,
      "grad_norm": 6.043264306754281e-07,
      "learning_rate": 3.1712278246659055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4632848,
      "step": 16540
    },
    {
      "epoch": 183.83333333333334,
      "grad_norm": 5.568749656958971e-07,
      "learning_rate": 3.170282072888566e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4634256,
      "step": 16545
    },
    {
      "epoch": 183.88888888888889,
      "grad_norm": 4.7319551299551676e-07,
      "learning_rate": 3.169336217745307e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4635664,
      "step": 16550
    },
    {
      "epoch": 183.94444444444446,
      "grad_norm": 1.5838676290513831e-06,
      "learning_rate": 3.1683902593819924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4637072,
      "step": 16555
    },
    {
      "epoch": 184.0,
      "grad_norm": 7.105122108441719e-07,
      "learning_rate": 3.1674441979445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4638448,
      "step": 16560
    },
    {
      "epoch": 184.05555555555554,
      "grad_norm": 6.160867656035407e-07,
      "learning_rate": 3.166498033578725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4639856,
      "step": 16565
    },
    {
      "epoch": 184.11111111111111,
      "grad_norm": 4.506053983277525e-07,
      "learning_rate": 3.165551766430578e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4641232,
      "step": 16570
    },
    {
      "epoch": 184.16666666666666,
      "grad_norm": 1.2582893305079779e-06,
      "learning_rate": 3.164605396645984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4642640,
      "step": 16575
    },
    {
      "epoch": 184.22222222222223,
      "grad_norm": 7.282770866368082e-07,
      "learning_rate": 3.163658924370886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4644016,
      "step": 16580
    },
    {
      "epoch": 184.27777777777777,
      "grad_norm": 6.20528624040162e-07,
      "learning_rate": 3.1627123497512415e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4645424,
      "step": 16585
    },
    {
      "epoch": 184.33333333333334,
      "grad_norm": 5.20813728144276e-07,
      "learning_rate": 3.1617656729330245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4646800,
      "step": 16590
    },
    {
      "epoch": 184.38888888888889,
      "grad_norm": 6.544702841893013e-07,
      "learning_rate": 3.1608188940622255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4648224,
      "step": 16595
    },
    {
      "epoch": 184.44444444444446,
      "grad_norm": 2.348109319427749e-06,
      "learning_rate": 3.159872013284847e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4649664,
      "step": 16600
    },
    {
      "epoch": 184.44444444444446,
      "eval_loss": 0.3898445963859558,
      "eval_runtime": 1.2959,
      "eval_samples_per_second": 30.867,
      "eval_steps_per_second": 15.433,
      "num_input_tokens_seen": 4649664,
      "step": 16600
    },
    {
      "epoch": 184.5,
      "grad_norm": 6.911832883815805e-07,
      "learning_rate": 3.1589250307469134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4651088,
      "step": 16605
    },
    {
      "epoch": 184.55555555555554,
      "grad_norm": 6.924182116563316e-07,
      "learning_rate": 3.1579779465944586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4652464,
      "step": 16610
    },
    {
      "epoch": 184.61111111111111,
      "grad_norm": 5.364896651371964e-07,
      "learning_rate": 3.1570307609735363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4653872,
      "step": 16615
    },
    {
      "epoch": 184.66666666666666,
      "grad_norm": 5.924154606873344e-07,
      "learning_rate": 3.156083474030213e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4655328,
      "step": 16620
    },
    {
      "epoch": 184.72222222222223,
      "grad_norm": 9.858805469775689e-07,
      "learning_rate": 3.155136085910573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4656720,
      "step": 16625
    },
    {
      "epoch": 184.77777777777777,
      "grad_norm": 6.553236175932398e-07,
      "learning_rate": 3.154188596760717e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4658112,
      "step": 16630
    },
    {
      "epoch": 184.83333333333334,
      "grad_norm": 7.119391511878348e-07,
      "learning_rate": 3.153241006726757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4659536,
      "step": 16635
    },
    {
      "epoch": 184.88888888888889,
      "grad_norm": 6.219723900358076e-07,
      "learning_rate": 3.152293315954825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4660896,
      "step": 16640
    },
    {
      "epoch": 184.94444444444446,
      "grad_norm": 9.692447520137648e-07,
      "learning_rate": 3.1513455245910666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4662288,
      "step": 16645
    },
    {
      "epoch": 185.0,
      "grad_norm": 5.705538228539808e-07,
      "learning_rate": 3.150397632781643e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4663648,
      "step": 16650
    },
    {
      "epoch": 185.05555555555554,
      "grad_norm": 7.206615464383503e-07,
      "learning_rate": 3.149449640672731e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4665040,
      "step": 16655
    },
    {
      "epoch": 185.11111111111111,
      "grad_norm": 6.718080953760364e-07,
      "learning_rate": 3.148501548410523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4666432,
      "step": 16660
    },
    {
      "epoch": 185.16666666666666,
      "grad_norm": 7.760297648928827e-07,
      "learning_rate": 3.1475533561412256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4667872,
      "step": 16665
    },
    {
      "epoch": 185.22222222222223,
      "grad_norm": 6.068985953788797e-07,
      "learning_rate": 3.146605064011065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4669248,
      "step": 16670
    },
    {
      "epoch": 185.27777777777777,
      "grad_norm": 6.136154411251482e-07,
      "learning_rate": 3.145656672166277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4670656,
      "step": 16675
    },
    {
      "epoch": 185.33333333333334,
      "grad_norm": 5.567231937675388e-07,
      "learning_rate": 3.144708180753116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4672064,
      "step": 16680
    },
    {
      "epoch": 185.38888888888889,
      "grad_norm": 4.5536248194366635e-07,
      "learning_rate": 3.143759589917851e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4673472,
      "step": 16685
    },
    {
      "epoch": 185.44444444444446,
      "grad_norm": 2.094719775413978e-06,
      "learning_rate": 3.142810899806768e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4674848,
      "step": 16690
    },
    {
      "epoch": 185.5,
      "grad_norm": 5.664801960847399e-07,
      "learning_rate": 3.141862110566166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4676256,
      "step": 16695
    },
    {
      "epoch": 185.55555555555554,
      "grad_norm": 5.876995032849663e-07,
      "learning_rate": 3.1409132223423606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4677664,
      "step": 16700
    },
    {
      "epoch": 185.61111111111111,
      "grad_norm": 3.00828196486691e-06,
      "learning_rate": 3.139964235281682e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4679024,
      "step": 16705
    },
    {
      "epoch": 185.66666666666666,
      "grad_norm": 6.968679144847556e-07,
      "learning_rate": 3.139015149530476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4680416,
      "step": 16710
    },
    {
      "epoch": 185.72222222222223,
      "grad_norm": 6.919975703567616e-07,
      "learning_rate": 3.1380659652351034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4681840,
      "step": 16715
    },
    {
      "epoch": 185.77777777777777,
      "grad_norm": 5.874756539014925e-07,
      "learning_rate": 3.137116682541941e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4683280,
      "step": 16720
    },
    {
      "epoch": 185.83333333333334,
      "grad_norm": 6.226990763025242e-07,
      "learning_rate": 3.136167301597379e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4684704,
      "step": 16725
    },
    {
      "epoch": 185.88888888888889,
      "grad_norm": 1.6494951751155895e-06,
      "learning_rate": 3.1352178225478254e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4686080,
      "step": 16730
    },
    {
      "epoch": 185.94444444444446,
      "grad_norm": 1.1624488251982257e-06,
      "learning_rate": 3.1342682455396996e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4687440,
      "step": 16735
    },
    {
      "epoch": 186.0,
      "grad_norm": 6.768225944142614e-07,
      "learning_rate": 3.133318570719441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4688864,
      "step": 16740
    },
    {
      "epoch": 186.05555555555554,
      "grad_norm": 4.886005626758561e-07,
      "learning_rate": 3.132368798233499e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4690208,
      "step": 16745
    },
    {
      "epoch": 186.11111111111111,
      "grad_norm": 5.209589062360465e-07,
      "learning_rate": 3.131418928228342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4691584,
      "step": 16750
    },
    {
      "epoch": 186.16666666666666,
      "grad_norm": 1.0945866506517632e-06,
      "learning_rate": 3.1304689608504514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4693024,
      "step": 16755
    },
    {
      "epoch": 186.22222222222223,
      "grad_norm": 6.9050270212756e-07,
      "learning_rate": 3.129518896246324e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4694416,
      "step": 16760
    },
    {
      "epoch": 186.27777777777777,
      "grad_norm": 7.143782113416819e-06,
      "learning_rate": 3.128568734562472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4695808,
      "step": 16765
    },
    {
      "epoch": 186.33333333333334,
      "grad_norm": 1.058405359799508e-06,
      "learning_rate": 3.127618475945421e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4697232,
      "step": 16770
    },
    {
      "epoch": 186.38888888888889,
      "grad_norm": 5.657726660501794e-07,
      "learning_rate": 3.126668120541715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4698624,
      "step": 16775
    },
    {
      "epoch": 186.44444444444446,
      "grad_norm": 5.974836199129641e-07,
      "learning_rate": 3.1257176684979096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4700000,
      "step": 16780
    },
    {
      "epoch": 186.5,
      "grad_norm": 4.430458488968725e-07,
      "learning_rate": 3.124767119960576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4701376,
      "step": 16785
    },
    {
      "epoch": 186.55555555555554,
      "grad_norm": 5.009679853174021e-07,
      "learning_rate": 3.123816475076301e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4702752,
      "step": 16790
    },
    {
      "epoch": 186.61111111111111,
      "grad_norm": 7.826288310752716e-07,
      "learning_rate": 3.122865733991687e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4704208,
      "step": 16795
    },
    {
      "epoch": 186.66666666666666,
      "grad_norm": 4.0825005953593063e-07,
      "learning_rate": 3.1219148968533486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4705600,
      "step": 16800
    },
    {
      "epoch": 186.66666666666666,
      "eval_loss": 0.40677133202552795,
      "eval_runtime": 1.3002,
      "eval_samples_per_second": 30.766,
      "eval_steps_per_second": 15.383,
      "num_input_tokens_seen": 4705600,
      "step": 16800
    },
    {
      "epoch": 186.72222222222223,
      "grad_norm": 4.918234708384261e-07,
      "learning_rate": 3.120963963807918e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4707072,
      "step": 16805
    },
    {
      "epoch": 186.77777777777777,
      "grad_norm": 4.953601546731079e-07,
      "learning_rate": 3.12001293500204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4708464,
      "step": 16810
    },
    {
      "epoch": 186.83333333333334,
      "grad_norm": 4.3032147800659004e-07,
      "learning_rate": 3.1190618105823765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4709888,
      "step": 16815
    },
    {
      "epoch": 186.88888888888889,
      "grad_norm": 6.11849259257724e-07,
      "learning_rate": 3.118110590695603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4711344,
      "step": 16820
    },
    {
      "epoch": 186.94444444444446,
      "grad_norm": 1.5057639757287689e-06,
      "learning_rate": 3.117159275488407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4712736,
      "step": 16825
    },
    {
      "epoch": 187.0,
      "grad_norm": 1.483203732277616e-06,
      "learning_rate": 3.1162078651074956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4714096,
      "step": 16830
    },
    {
      "epoch": 187.05555555555554,
      "grad_norm": 7.080547561599815e-07,
      "learning_rate": 3.1152563596995885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4715456,
      "step": 16835
    },
    {
      "epoch": 187.11111111111111,
      "grad_norm": 6.354634933813941e-07,
      "learning_rate": 3.1143047594114186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4716864,
      "step": 16840
    },
    {
      "epoch": 187.16666666666666,
      "grad_norm": 6.744054985574621e-07,
      "learning_rate": 3.113353064389734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4718240,
      "step": 16845
    },
    {
      "epoch": 187.22222222222223,
      "grad_norm": 6.114470920692838e-07,
      "learning_rate": 3.1124012747812993e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4719600,
      "step": 16850
    },
    {
      "epoch": 187.27777777777777,
      "grad_norm": 1.9263006834080443e-06,
      "learning_rate": 3.1114493907328936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4720992,
      "step": 16855
    },
    {
      "epoch": 187.33333333333334,
      "grad_norm": 5.995671585878881e-07,
      "learning_rate": 3.110497412391306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4722432,
      "step": 16860
    },
    {
      "epoch": 187.38888888888889,
      "grad_norm": 6.451468266277516e-07,
      "learning_rate": 3.1095453399033466e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4723888,
      "step": 16865
    },
    {
      "epoch": 187.44444444444446,
      "grad_norm": 5.370762323764211e-07,
      "learning_rate": 3.108593173415835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4725296,
      "step": 16870
    },
    {
      "epoch": 187.5,
      "grad_norm": 9.62931949288759e-07,
      "learning_rate": 3.107640913075609e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4726736,
      "step": 16875
    },
    {
      "epoch": 187.55555555555554,
      "grad_norm": 5.714571784665168e-07,
      "learning_rate": 3.106688559029517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4728176,
      "step": 16880
    },
    {
      "epoch": 187.61111111111111,
      "grad_norm": 3.5425312034931267e-06,
      "learning_rate": 3.105736111424425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4729568,
      "step": 16885
    },
    {
      "epoch": 187.66666666666666,
      "grad_norm": 5.427649512057542e-07,
      "learning_rate": 3.1047835704072136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4730976,
      "step": 16890
    },
    {
      "epoch": 187.72222222222223,
      "grad_norm": 5.955689630354755e-07,
      "learning_rate": 3.103830936124775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4732384,
      "step": 16895
    },
    {
      "epoch": 187.77777777777777,
      "grad_norm": 2.883689376176335e-06,
      "learning_rate": 3.102878208724018e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4733744,
      "step": 16900
    },
    {
      "epoch": 187.83333333333334,
      "grad_norm": 5.249611376711982e-07,
      "learning_rate": 3.101925388351865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4735168,
      "step": 16905
    },
    {
      "epoch": 187.88888888888889,
      "grad_norm": 5.79378877318959e-07,
      "learning_rate": 3.1009724751552515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4736576,
      "step": 16910
    },
    {
      "epoch": 187.94444444444446,
      "grad_norm": 1.1402880772948265e-06,
      "learning_rate": 3.100019469281131e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4737952,
      "step": 16915
    },
    {
      "epoch": 188.0,
      "grad_norm": 1.0892530326600536e-06,
      "learning_rate": 3.0990663708764685e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4739328,
      "step": 16920
    },
    {
      "epoch": 188.05555555555554,
      "grad_norm": 7.767462761876232e-07,
      "learning_rate": 3.098113180088243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4740736,
      "step": 16925
    },
    {
      "epoch": 188.11111111111111,
      "grad_norm": 7.362173164437991e-07,
      "learning_rate": 3.097159897063448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4742176,
      "step": 16930
    },
    {
      "epoch": 188.16666666666666,
      "grad_norm": 5.003822138860414e-07,
      "learning_rate": 3.096206521949094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4743568,
      "step": 16935
    },
    {
      "epoch": 188.22222222222223,
      "grad_norm": 5.431120371213183e-07,
      "learning_rate": 3.0952530548922006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4744992,
      "step": 16940
    },
    {
      "epoch": 188.27777777777777,
      "grad_norm": 6.098382527852664e-07,
      "learning_rate": 3.0942994960398064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4746384,
      "step": 16945
    },
    {
      "epoch": 188.33333333333334,
      "grad_norm": 4.883095812147076e-07,
      "learning_rate": 3.093345845538961e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4747856,
      "step": 16950
    },
    {
      "epoch": 188.38888888888889,
      "grad_norm": 5.878692377336847e-07,
      "learning_rate": 3.09239210353673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4749216,
      "step": 16955
    },
    {
      "epoch": 188.44444444444446,
      "grad_norm": 2.016349299083231e-06,
      "learning_rate": 3.0914382701801926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4750608,
      "step": 16960
    },
    {
      "epoch": 188.5,
      "grad_norm": 4.7348081011477916e-07,
      "learning_rate": 3.090484345616441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4751984,
      "step": 16965
    },
    {
      "epoch": 188.55555555555554,
      "grad_norm": 5.400977443059674e-07,
      "learning_rate": 3.0895303299925825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4753376,
      "step": 16970
    },
    {
      "epoch": 188.61111111111111,
      "grad_norm": 6.080741741243401e-07,
      "learning_rate": 3.0885762234557393e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4754784,
      "step": 16975
    },
    {
      "epoch": 188.66666666666666,
      "grad_norm": 1.245757289325411e-06,
      "learning_rate": 3.087622026153045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4756208,
      "step": 16980
    },
    {
      "epoch": 188.72222222222223,
      "grad_norm": 6.487400696641998e-07,
      "learning_rate": 3.086667738231651e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4757584,
      "step": 16985
    },
    {
      "epoch": 188.77777777777777,
      "grad_norm": 6.576361215593352e-07,
      "learning_rate": 3.085713359838718e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4758992,
      "step": 16990
    },
    {
      "epoch": 188.83333333333334,
      "grad_norm": 1.6270114429062232e-06,
      "learning_rate": 3.084758891121425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4760368,
      "step": 16995
    },
    {
      "epoch": 188.88888888888889,
      "grad_norm": 5.672384304489242e-07,
      "learning_rate": 3.083804332226963e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4761760,
      "step": 17000
    },
    {
      "epoch": 188.88888888888889,
      "eval_loss": 0.3945319652557373,
      "eval_runtime": 1.2879,
      "eval_samples_per_second": 31.059,
      "eval_steps_per_second": 15.529,
      "num_input_tokens_seen": 4761760,
      "step": 17000
    },
    {
      "epoch": 188.94444444444446,
      "grad_norm": 6.899880986566131e-07,
      "learning_rate": 3.082849683302536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4763104,
      "step": 17005
    },
    {
      "epoch": 189.0,
      "grad_norm": 5.517606496141525e-07,
      "learning_rate": 3.081894944495363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4764544,
      "step": 17010
    },
    {
      "epoch": 189.05555555555554,
      "grad_norm": 5.824815048072196e-07,
      "learning_rate": 3.080940115952677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4765968,
      "step": 17015
    },
    {
      "epoch": 189.11111111111111,
      "grad_norm": 4.532870661932975e-06,
      "learning_rate": 3.0799851978217245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4767440,
      "step": 17020
    },
    {
      "epoch": 189.16666666666666,
      "grad_norm": 1.4908794128132286e-06,
      "learning_rate": 3.0790301902497666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4768848,
      "step": 17025
    },
    {
      "epoch": 189.22222222222223,
      "grad_norm": 5.499910002981778e-07,
      "learning_rate": 3.078075093384076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4770224,
      "step": 17030
    },
    {
      "epoch": 189.27777777777777,
      "grad_norm": 6.094742275308818e-07,
      "learning_rate": 3.077119907371942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4771648,
      "step": 17035
    },
    {
      "epoch": 189.33333333333334,
      "grad_norm": 5.720429498978774e-07,
      "learning_rate": 3.076164632360666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4773024,
      "step": 17040
    },
    {
      "epoch": 189.38888888888889,
      "grad_norm": 1.6018784663174301e-06,
      "learning_rate": 3.075209268497563e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4774432,
      "step": 17045
    },
    {
      "epoch": 189.44444444444446,
      "grad_norm": 3.7818685996171553e-06,
      "learning_rate": 3.074253815929961e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4775776,
      "step": 17050
    },
    {
      "epoch": 189.5,
      "grad_norm": 6.034729267412331e-07,
      "learning_rate": 3.0732982748052054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4777184,
      "step": 17055
    },
    {
      "epoch": 189.55555555555554,
      "grad_norm": 1.0174327371714753e-06,
      "learning_rate": 3.072342645270651e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4778640,
      "step": 17060
    },
    {
      "epoch": 189.61111111111111,
      "grad_norm": 6.003280645927589e-07,
      "learning_rate": 3.071386927473668e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4780080,
      "step": 17065
    },
    {
      "epoch": 189.66666666666666,
      "grad_norm": 5.947926524640934e-07,
      "learning_rate": 3.0704311215616404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4781488,
      "step": 17070
    },
    {
      "epoch": 189.72222222222223,
      "grad_norm": 1.577109401296184e-06,
      "learning_rate": 3.0694752276819656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4782912,
      "step": 17075
    },
    {
      "epoch": 189.77777777777777,
      "grad_norm": 6.785813866372337e-07,
      "learning_rate": 3.068519245982054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4784272,
      "step": 17080
    },
    {
      "epoch": 189.83333333333334,
      "grad_norm": 3.794754320551874e-06,
      "learning_rate": 3.0675631766093304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4785600,
      "step": 17085
    },
    {
      "epoch": 189.88888888888889,
      "grad_norm": 1.5365980061687878e-06,
      "learning_rate": 3.066607019711232e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4787008,
      "step": 17090
    },
    {
      "epoch": 189.94444444444446,
      "grad_norm": 5.42861812391493e-07,
      "learning_rate": 3.065650775435211e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4788432,
      "step": 17095
    },
    {
      "epoch": 190.0,
      "grad_norm": 4.957460646437539e-07,
      "learning_rate": 3.0646944439287326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4789856,
      "step": 17100
    },
    {
      "epoch": 190.05555555555554,
      "grad_norm": 4.883978590441984e-07,
      "learning_rate": 3.0637380253392736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4791216,
      "step": 17105
    },
    {
      "epoch": 190.11111111111111,
      "grad_norm": 1.5632965641998453e-06,
      "learning_rate": 3.062781519814327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4792640,
      "step": 17110
    },
    {
      "epoch": 190.16666666666666,
      "grad_norm": 2.0076738564966945e-06,
      "learning_rate": 3.0618249275013985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4794016,
      "step": 17115
    },
    {
      "epoch": 190.22222222222223,
      "grad_norm": 5.796237587674113e-07,
      "learning_rate": 3.060868248548005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4795408,
      "step": 17120
    },
    {
      "epoch": 190.27777777777777,
      "grad_norm": 5.794526600766403e-07,
      "learning_rate": 3.0599114831016796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4796848,
      "step": 17125
    },
    {
      "epoch": 190.33333333333334,
      "grad_norm": 3.114955688943155e-06,
      "learning_rate": 3.0589546313099666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4798256,
      "step": 17130
    },
    {
      "epoch": 190.38888888888889,
      "grad_norm": 6.380636250469252e-07,
      "learning_rate": 3.0579976933204255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4799648,
      "step": 17135
    },
    {
      "epoch": 190.44444444444446,
      "grad_norm": 5.313214614943718e-07,
      "learning_rate": 3.0570406692806284e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4801040,
      "step": 17140
    },
    {
      "epoch": 190.5,
      "grad_norm": 5.225837185207638e-07,
      "learning_rate": 3.05608355933816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4802448,
      "step": 17145
    },
    {
      "epoch": 190.55555555555554,
      "grad_norm": 5.059594627709885e-07,
      "learning_rate": 3.055126363640618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4803808,
      "step": 17150
    },
    {
      "epoch": 190.61111111111111,
      "grad_norm": 7.21617311683076e-07,
      "learning_rate": 3.0541690823356146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4805248,
      "step": 17155
    },
    {
      "epoch": 190.66666666666666,
      "grad_norm": 5.588210569840157e-07,
      "learning_rate": 3.053211715570775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4806656,
      "step": 17160
    },
    {
      "epoch": 190.72222222222223,
      "grad_norm": 4.837505684918142e-07,
      "learning_rate": 3.052254263493736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4808080,
      "step": 17165
    },
    {
      "epoch": 190.77777777777777,
      "grad_norm": 6.111649781814776e-07,
      "learning_rate": 3.0512967262521498e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4809472,
      "step": 17170
    },
    {
      "epoch": 190.83333333333334,
      "grad_norm": 6.348951728796237e-07,
      "learning_rate": 3.0503391039936803e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4810832,
      "step": 17175
    },
    {
      "epoch": 190.88888888888889,
      "grad_norm": 1.5884138520050328e-06,
      "learning_rate": 3.0493813968660056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4812208,
      "step": 17180
    },
    {
      "epoch": 190.94444444444446,
      "grad_norm": 3.95571305489284e-06,
      "learning_rate": 3.0484236050168153e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4813632,
      "step": 17185
    },
    {
      "epoch": 191.0,
      "grad_norm": 2.1693560938729206e-06,
      "learning_rate": 3.0474657285938123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4815008,
      "step": 17190
    },
    {
      "epoch": 191.05555555555554,
      "grad_norm": 1.6599112768744817e-06,
      "learning_rate": 3.046507767744715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4816384,
      "step": 17195
    },
    {
      "epoch": 191.11111111111111,
      "grad_norm": 3.5053335523116402e-06,
      "learning_rate": 3.045549722617252e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4817728,
      "step": 17200
    },
    {
      "epoch": 191.11111111111111,
      "eval_loss": 0.3966147005558014,
      "eval_runtime": 1.2892,
      "eval_samples_per_second": 31.028,
      "eval_steps_per_second": 15.514,
      "num_input_tokens_seen": 4817728,
      "step": 17200
    },
    {
      "epoch": 191.16666666666666,
      "grad_norm": 5.043333430876373e-07,
      "learning_rate": 3.0445915933591658e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4819104,
      "step": 17205
    },
    {
      "epoch": 191.22222222222223,
      "grad_norm": 5.50421759726305e-07,
      "learning_rate": 3.0436333801182114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4820512,
      "step": 17210
    },
    {
      "epoch": 191.27777777777777,
      "grad_norm": 5.103203761791519e-07,
      "learning_rate": 3.0426750830421596e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4821936,
      "step": 17215
    },
    {
      "epoch": 191.33333333333334,
      "grad_norm": 5.906061915084138e-07,
      "learning_rate": 3.0417167022787897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4823344,
      "step": 17220
    },
    {
      "epoch": 191.38888888888889,
      "grad_norm": 6.362207045640389e-07,
      "learning_rate": 3.0407582379758966e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4824736,
      "step": 17225
    },
    {
      "epoch": 191.44444444444446,
      "grad_norm": 6.096298648117227e-07,
      "learning_rate": 3.039799690281287e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4826128,
      "step": 17230
    },
    {
      "epoch": 191.5,
      "grad_norm": 1.5792851399965002e-06,
      "learning_rate": 3.0388410593427823e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4827536,
      "step": 17235
    },
    {
      "epoch": 191.55555555555554,
      "grad_norm": 3.2109203402796993e-06,
      "learning_rate": 3.0378823453082146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4828944,
      "step": 17240
    },
    {
      "epoch": 191.61111111111111,
      "grad_norm": 4.6715499024685414e-07,
      "learning_rate": 3.03692354832543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4830288,
      "step": 17245
    },
    {
      "epoch": 191.66666666666666,
      "grad_norm": 4.3297649199303123e-07,
      "learning_rate": 3.0359646685422865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4831712,
      "step": 17250
    },
    {
      "epoch": 191.72222222222223,
      "grad_norm": 5.570382768382842e-07,
      "learning_rate": 3.035005706106656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4833088,
      "step": 17255
    },
    {
      "epoch": 191.77777777777777,
      "grad_norm": 5.654393930853985e-07,
      "learning_rate": 3.034046661166422e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4834496,
      "step": 17260
    },
    {
      "epoch": 191.83333333333334,
      "grad_norm": 1.0966089121211553e-06,
      "learning_rate": 3.033087533869482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4835920,
      "step": 17265
    },
    {
      "epoch": 191.88888888888889,
      "grad_norm": 2.890475798267289e-06,
      "learning_rate": 3.0321283243637444e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4837392,
      "step": 17270
    },
    {
      "epoch": 191.94444444444446,
      "grad_norm": 5.680793151441321e-07,
      "learning_rate": 3.0311690327971326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4838784,
      "step": 17275
    },
    {
      "epoch": 192.0,
      "grad_norm": 4.908726509711414e-07,
      "learning_rate": 3.030209659317581e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4840208,
      "step": 17280
    },
    {
      "epoch": 192.05555555555554,
      "grad_norm": 6.0769195897592e-07,
      "learning_rate": 3.0292502040730362e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4841600,
      "step": 17285
    },
    {
      "epoch": 192.11111111111111,
      "grad_norm": 1.6059404970292235e-06,
      "learning_rate": 3.0282906672114597e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4842944,
      "step": 17290
    },
    {
      "epoch": 192.16666666666666,
      "grad_norm": 5.996371896799246e-07,
      "learning_rate": 3.027331048880823e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4844320,
      "step": 17295
    },
    {
      "epoch": 192.22222222222223,
      "grad_norm": 2.6685027023631847e-06,
      "learning_rate": 3.0263713492291123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4845744,
      "step": 17300
    },
    {
      "epoch": 192.27777777777777,
      "grad_norm": 6.214636414370034e-07,
      "learning_rate": 3.0254115684043242e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4847152,
      "step": 17305
    },
    {
      "epoch": 192.33333333333334,
      "grad_norm": 7.258414598254603e-07,
      "learning_rate": 3.024451706554469e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4848560,
      "step": 17310
    },
    {
      "epoch": 192.38888888888889,
      "grad_norm": 6.269262371461082e-07,
      "learning_rate": 3.0234917638275705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4849952,
      "step": 17315
    },
    {
      "epoch": 192.44444444444446,
      "grad_norm": 1.1719102985807694e-06,
      "learning_rate": 3.0225317403716635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4851328,
      "step": 17320
    },
    {
      "epoch": 192.5,
      "grad_norm": 6.285204108280595e-07,
      "learning_rate": 3.0215716363347956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4852752,
      "step": 17325
    },
    {
      "epoch": 192.55555555555554,
      "grad_norm": 5.976493184789433e-07,
      "learning_rate": 3.0206114518650275e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4854128,
      "step": 17330
    },
    {
      "epoch": 192.61111111111111,
      "grad_norm": 5.571052042796509e-06,
      "learning_rate": 3.0196511871104304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4855568,
      "step": 17335
    },
    {
      "epoch": 192.66666666666666,
      "grad_norm": 1.933065959747182e-06,
      "learning_rate": 3.01869084221909e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4856992,
      "step": 17340
    },
    {
      "epoch": 192.72222222222223,
      "grad_norm": 1.146595309364784e-06,
      "learning_rate": 3.0177304173391037e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4858384,
      "step": 17345
    },
    {
      "epoch": 192.77777777777777,
      "grad_norm": 5.433145133793005e-07,
      "learning_rate": 3.01676991261858e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4859760,
      "step": 17350
    },
    {
      "epoch": 192.83333333333334,
      "grad_norm": 1.2040095498377923e-06,
      "learning_rate": 3.015809328205642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4861200,
      "step": 17355
    },
    {
      "epoch": 192.88888888888889,
      "grad_norm": 2.074647454719525e-06,
      "learning_rate": 3.0148486642484248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4862608,
      "step": 17360
    },
    {
      "epoch": 192.94444444444446,
      "grad_norm": 6.029105179550243e-07,
      "learning_rate": 3.0138879208950722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4863984,
      "step": 17365
    },
    {
      "epoch": 193.0,
      "grad_norm": 1.0360239457440912e-06,
      "learning_rate": 3.012927098293744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4865376,
      "step": 17370
    },
    {
      "epoch": 193.05555555555554,
      "grad_norm": 5.755844085797435e-07,
      "learning_rate": 3.0119661965926123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4866768,
      "step": 17375
    },
    {
      "epoch": 193.11111111111111,
      "grad_norm": 5.247546255304769e-07,
      "learning_rate": 3.0110052159398587e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4868160,
      "step": 17380
    },
    {
      "epoch": 193.16666666666666,
      "grad_norm": 1.2011001899736584e-06,
      "learning_rate": 3.0100441564836802e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4869600,
      "step": 17385
    },
    {
      "epoch": 193.22222222222223,
      "grad_norm": 1.0240534038530313e-06,
      "learning_rate": 3.0090830183722817e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4871024,
      "step": 17390
    },
    {
      "epoch": 193.27777777777777,
      "grad_norm": 6.183116170177527e-07,
      "learning_rate": 3.0081218017538852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4872448,
      "step": 17395
    },
    {
      "epoch": 193.33333333333334,
      "grad_norm": 6.521552222693572e-07,
      "learning_rate": 3.0071605067767212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4873856,
      "step": 17400
    },
    {
      "epoch": 193.33333333333334,
      "eval_loss": 0.39010462164878845,
      "eval_runtime": 1.2876,
      "eval_samples_per_second": 31.066,
      "eval_steps_per_second": 15.533,
      "num_input_tokens_seen": 4873856,
      "step": 17400
    },
    {
      "epoch": 193.38888888888889,
      "grad_norm": 7.237552495098498e-07,
      "learning_rate": 3.006199133589034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4875264,
      "step": 17405
    },
    {
      "epoch": 193.44444444444446,
      "grad_norm": 7.068334980431246e-06,
      "learning_rate": 3.005237682339079e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4876640,
      "step": 17410
    },
    {
      "epoch": 193.5,
      "grad_norm": 5.386453381106548e-07,
      "learning_rate": 3.0042761531751228e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4878016,
      "step": 17415
    },
    {
      "epoch": 193.55555555555554,
      "grad_norm": 4.415436478666379e-07,
      "learning_rate": 3.0033145462454482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4879408,
      "step": 17420
    },
    {
      "epoch": 193.61111111111111,
      "grad_norm": 3.911026169589604e-07,
      "learning_rate": 3.002352861698345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4880832,
      "step": 17425
    },
    {
      "epoch": 193.66666666666666,
      "grad_norm": 5.902547854930162e-07,
      "learning_rate": 3.0013910996821178e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4882240,
      "step": 17430
    },
    {
      "epoch": 193.72222222222223,
      "grad_norm": 4.4610749228013447e-07,
      "learning_rate": 3.0004292603450817e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4883600,
      "step": 17435
    },
    {
      "epoch": 193.77777777777777,
      "grad_norm": 6.202025701895764e-07,
      "learning_rate": 2.9994673438355653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4885024,
      "step": 17440
    },
    {
      "epoch": 193.83333333333334,
      "grad_norm": 5.155364988240763e-07,
      "learning_rate": 2.9985053503019078e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4886432,
      "step": 17445
    },
    {
      "epoch": 193.88888888888889,
      "grad_norm": 6.138726007520745e-07,
      "learning_rate": 2.99754327989246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4887856,
      "step": 17450
    },
    {
      "epoch": 193.94444444444446,
      "grad_norm": 6.273384087762679e-07,
      "learning_rate": 2.9965811327555864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4889232,
      "step": 17455
    },
    {
      "epoch": 194.0,
      "grad_norm": 4.881309905613307e-06,
      "learning_rate": 2.995618909039662e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4890624,
      "step": 17460
    },
    {
      "epoch": 194.05555555555554,
      "grad_norm": 2.3095014967111638e-06,
      "learning_rate": 2.9946566088930727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4892048,
      "step": 17465
    },
    {
      "epoch": 194.11111111111111,
      "grad_norm": 6.452209504459461e-07,
      "learning_rate": 2.9936942324642192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4893424,
      "step": 17470
    },
    {
      "epoch": 194.16666666666666,
      "grad_norm": 5.892475769542216e-07,
      "learning_rate": 2.9927317799015097e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4894848,
      "step": 17475
    },
    {
      "epoch": 194.22222222222223,
      "grad_norm": 1.6055658988989308e-06,
      "learning_rate": 2.9917692513533685e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4896256,
      "step": 17480
    },
    {
      "epoch": 194.27777777777777,
      "grad_norm": 1.5395725085909362e-06,
      "learning_rate": 2.990806646968229e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4897680,
      "step": 17485
    },
    {
      "epoch": 194.33333333333334,
      "grad_norm": 6.58170336009789e-07,
      "learning_rate": 2.989843966894536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4899088,
      "step": 17490
    },
    {
      "epoch": 194.38888888888889,
      "grad_norm": 4.919294269711827e-07,
      "learning_rate": 2.9888812112807472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4900464,
      "step": 17495
    },
    {
      "epoch": 194.44444444444446,
      "grad_norm": 1.0418240208309726e-06,
      "learning_rate": 2.987918380275333e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4901904,
      "step": 17500
    },
    {
      "epoch": 194.5,
      "grad_norm": 1.0997562185366405e-06,
      "learning_rate": 2.9869554740267724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4903280,
      "step": 17505
    },
    {
      "epoch": 194.55555555555554,
      "grad_norm": 1.0571678785709082e-06,
      "learning_rate": 2.9859924926835585e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4904704,
      "step": 17510
    },
    {
      "epoch": 194.61111111111111,
      "grad_norm": 6.923620503584971e-07,
      "learning_rate": 2.9850294363941944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4906144,
      "step": 17515
    },
    {
      "epoch": 194.66666666666666,
      "grad_norm": 7.229560878840857e-07,
      "learning_rate": 2.9840663053071967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4907504,
      "step": 17520
    },
    {
      "epoch": 194.72222222222223,
      "grad_norm": 5.76358252146747e-06,
      "learning_rate": 2.983103099571091e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4908928,
      "step": 17525
    },
    {
      "epoch": 194.77777777777777,
      "grad_norm": 4.658519401345984e-07,
      "learning_rate": 2.9821398193344164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4910352,
      "step": 17530
    },
    {
      "epoch": 194.83333333333334,
      "grad_norm": 4.576473600081954e-07,
      "learning_rate": 2.9811764647457226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4911728,
      "step": 17535
    },
    {
      "epoch": 194.88888888888889,
      "grad_norm": 5.978500325909408e-07,
      "learning_rate": 2.9802130359535714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4913120,
      "step": 17540
    },
    {
      "epoch": 194.94444444444446,
      "grad_norm": 4.317571892897831e-06,
      "learning_rate": 2.979249533106535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4914496,
      "step": 17545
    },
    {
      "epoch": 195.0,
      "grad_norm": 7.214221682261268e-07,
      "learning_rate": 2.9782859563531986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4915904,
      "step": 17550
    },
    {
      "epoch": 195.05555555555554,
      "grad_norm": 6.370031542246579e-07,
      "learning_rate": 2.977322305842156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4917344,
      "step": 17555
    },
    {
      "epoch": 195.11111111111111,
      "grad_norm": 6.763034434698056e-07,
      "learning_rate": 2.9763585817220162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4918800,
      "step": 17560
    },
    {
      "epoch": 195.16666666666666,
      "grad_norm": 6.180384843901265e-07,
      "learning_rate": 2.975394784141397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4920192,
      "step": 17565
    },
    {
      "epoch": 195.22222222222223,
      "grad_norm": 6.435934665205423e-07,
      "learning_rate": 2.974430913248928e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4921632,
      "step": 17570
    },
    {
      "epoch": 195.27777777777777,
      "grad_norm": 5.789138413092587e-07,
      "learning_rate": 2.9734669691932497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4922976,
      "step": 17575
    },
    {
      "epoch": 195.33333333333334,
      "grad_norm": 5.73740749132412e-07,
      "learning_rate": 2.9725029521230147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4924400,
      "step": 17580
    },
    {
      "epoch": 195.38888888888889,
      "grad_norm": 4.6955267407611245e-07,
      "learning_rate": 2.9715388621868873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4925792,
      "step": 17585
    },
    {
      "epoch": 195.44444444444446,
      "grad_norm": 1.0847862768059713e-06,
      "learning_rate": 2.970574699533541e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4927200,
      "step": 17590
    },
    {
      "epoch": 195.5,
      "grad_norm": 5.68653149457532e-07,
      "learning_rate": 2.969610464311662e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4928544,
      "step": 17595
    },
    {
      "epoch": 195.55555555555554,
      "grad_norm": 2.0331910945969867e-06,
      "learning_rate": 2.9686461566699487e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4929936,
      "step": 17600
    },
    {
      "epoch": 195.55555555555554,
      "eval_loss": 0.40182334184646606,
      "eval_runtime": 1.2892,
      "eval_samples_per_second": 31.028,
      "eval_steps_per_second": 15.514,
      "num_input_tokens_seen": 4929936,
      "step": 17600
    },
    {
      "epoch": 195.61111111111111,
      "grad_norm": 6.044111842129496e-07,
      "learning_rate": 2.9676817767571086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4931296,
      "step": 17605
    },
    {
      "epoch": 195.66666666666666,
      "grad_norm": 7.239920591928239e-07,
      "learning_rate": 2.966717324721861e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4932720,
      "step": 17610
    },
    {
      "epoch": 195.72222222222223,
      "grad_norm": 2.1091027520014904e-06,
      "learning_rate": 2.9657528007129366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4934144,
      "step": 17615
    },
    {
      "epoch": 195.77777777777777,
      "grad_norm": 5.086640157969669e-07,
      "learning_rate": 2.9647882048790777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4935552,
      "step": 17620
    },
    {
      "epoch": 195.83333333333334,
      "grad_norm": 5.518962211681355e-07,
      "learning_rate": 2.963823537369037e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4936912,
      "step": 17625
    },
    {
      "epoch": 195.88888888888889,
      "grad_norm": 6.558044560733833e-07,
      "learning_rate": 2.9628587983315775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4938352,
      "step": 17630
    },
    {
      "epoch": 195.94444444444446,
      "grad_norm": 6.471695428444946e-07,
      "learning_rate": 2.9618939879154746e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4939760,
      "step": 17635
    },
    {
      "epoch": 196.0,
      "grad_norm": 5.00655175983411e-07,
      "learning_rate": 2.9609291062695143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4941168,
      "step": 17640
    },
    {
      "epoch": 196.05555555555554,
      "grad_norm": 5.294653533383098e-07,
      "learning_rate": 2.9599641535424938e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4942544,
      "step": 17645
    },
    {
      "epoch": 196.11111111111111,
      "grad_norm": 6.431802148654242e-07,
      "learning_rate": 2.9589991298832202e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4943920,
      "step": 17650
    },
    {
      "epoch": 196.16666666666666,
      "grad_norm": 5.742725193158549e-07,
      "learning_rate": 2.958034035440513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4945296,
      "step": 17655
    },
    {
      "epoch": 196.22222222222223,
      "grad_norm": 1.5060953728607274e-06,
      "learning_rate": 2.957068870363201e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4946768,
      "step": 17660
    },
    {
      "epoch": 196.27777777777777,
      "grad_norm": 4.864211291533138e-07,
      "learning_rate": 2.956103634800126e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4948176,
      "step": 17665
    },
    {
      "epoch": 196.33333333333334,
      "grad_norm": 5.816211228193424e-07,
      "learning_rate": 2.9551383289001384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4949584,
      "step": 17670
    },
    {
      "epoch": 196.38888888888889,
      "grad_norm": 1.6637086446280591e-06,
      "learning_rate": 2.9541729528121005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4950992,
      "step": 17675
    },
    {
      "epoch": 196.44444444444446,
      "grad_norm": 1.626924131414853e-06,
      "learning_rate": 2.9532075066848856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4952352,
      "step": 17680
    },
    {
      "epoch": 196.5,
      "grad_norm": 7.090284270816483e-07,
      "learning_rate": 2.9522419906673786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4953712,
      "step": 17685
    },
    {
      "epoch": 196.55555555555554,
      "grad_norm": 5.578769446401566e-07,
      "learning_rate": 2.951276404908474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4955120,
      "step": 17690
    },
    {
      "epoch": 196.61111111111111,
      "grad_norm": 5.770910433966492e-07,
      "learning_rate": 2.9503107495570752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4956576,
      "step": 17695
    },
    {
      "epoch": 196.66666666666666,
      "grad_norm": 5.824059599035536e-07,
      "learning_rate": 2.9493450247621003e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4957984,
      "step": 17700
    },
    {
      "epoch": 196.72222222222223,
      "grad_norm": 5.400598297455872e-07,
      "learning_rate": 2.948379230672476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4959360,
      "step": 17705
    },
    {
      "epoch": 196.77777777777777,
      "grad_norm": 6.466238460234308e-07,
      "learning_rate": 2.9474133674371396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4960720,
      "step": 17710
    },
    {
      "epoch": 196.83333333333334,
      "grad_norm": 6.248197337299644e-07,
      "learning_rate": 2.9464474352050387e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4962048,
      "step": 17715
    },
    {
      "epoch": 196.88888888888889,
      "grad_norm": 4.6689015107403975e-06,
      "learning_rate": 2.9454814341251336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4963440,
      "step": 17720
    },
    {
      "epoch": 196.94444444444446,
      "grad_norm": 5.992858973513648e-07,
      "learning_rate": 2.9445153643463942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4964848,
      "step": 17725
    },
    {
      "epoch": 197.0,
      "grad_norm": 5.329394525688258e-07,
      "learning_rate": 2.943549226017798e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4966272,
      "step": 17730
    },
    {
      "epoch": 197.05555555555554,
      "grad_norm": 4.821237666874367e-07,
      "learning_rate": 2.942583019288337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4967648,
      "step": 17735
    },
    {
      "epoch": 197.11111111111111,
      "grad_norm": 1.5580776562273968e-06,
      "learning_rate": 2.9416167443070132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4969040,
      "step": 17740
    },
    {
      "epoch": 197.16666666666666,
      "grad_norm": 4.560334673442412e-06,
      "learning_rate": 2.9406504012228375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4970432,
      "step": 17745
    },
    {
      "epoch": 197.22222222222223,
      "grad_norm": 5.704850991605781e-07,
      "learning_rate": 2.939683990184832e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4971792,
      "step": 17750
    },
    {
      "epoch": 197.27777777777777,
      "grad_norm": 6.474967335634574e-07,
      "learning_rate": 2.93871751134203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4973200,
      "step": 17755
    },
    {
      "epoch": 197.33333333333334,
      "grad_norm": 5.119265438224829e-07,
      "learning_rate": 2.9377509648434752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4974592,
      "step": 17760
    },
    {
      "epoch": 197.38888888888889,
      "grad_norm": 1.1551818488442223e-06,
      "learning_rate": 2.9367843508382203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4976016,
      "step": 17765
    },
    {
      "epoch": 197.44444444444446,
      "grad_norm": 6.459151222770743e-07,
      "learning_rate": 2.9358176694753293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4977424,
      "step": 17770
    },
    {
      "epoch": 197.5,
      "grad_norm": 1.7351075030092034e-06,
      "learning_rate": 2.9348509209038766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4978800,
      "step": 17775
    },
    {
      "epoch": 197.55555555555554,
      "grad_norm": 5.326592713572609e-07,
      "learning_rate": 2.933884105272947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4980240,
      "step": 17780
    },
    {
      "epoch": 197.61111111111111,
      "grad_norm": 4.867601433033997e-07,
      "learning_rate": 2.9329172227316366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4981648,
      "step": 17785
    },
    {
      "epoch": 197.66666666666666,
      "grad_norm": 6.568288881680928e-07,
      "learning_rate": 2.93195027342905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4983040,
      "step": 17790
    },
    {
      "epoch": 197.72222222222223,
      "grad_norm": 1.686387349764118e-06,
      "learning_rate": 2.9309832575143024e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4984448,
      "step": 17795
    },
    {
      "epoch": 197.77777777777777,
      "grad_norm": 5.818676527269417e-07,
      "learning_rate": 2.930016175136521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4985840,
      "step": 17800
    },
    {
      "epoch": 197.77777777777777,
      "eval_loss": 0.366407573223114,
      "eval_runtime": 1.2893,
      "eval_samples_per_second": 31.025,
      "eval_steps_per_second": 15.512,
      "num_input_tokens_seen": 4985840,
      "step": 17800
    },
    {
      "epoch": 197.83333333333334,
      "grad_norm": 5.238130142970476e-06,
      "learning_rate": 2.9290490264448412e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4987280,
      "step": 17805
    },
    {
      "epoch": 197.88888888888889,
      "grad_norm": 6.508148544526193e-07,
      "learning_rate": 2.9280818115884094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4988704,
      "step": 17810
    },
    {
      "epoch": 197.94444444444446,
      "grad_norm": 4.6009190555196255e-06,
      "learning_rate": 2.9271145307163828e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4990112,
      "step": 17815
    },
    {
      "epoch": 198.0,
      "grad_norm": 4.844299041906197e-07,
      "learning_rate": 2.9261471839779287e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4991520,
      "step": 17820
    },
    {
      "epoch": 198.05555555555554,
      "grad_norm": 4.1595413335926423e-07,
      "learning_rate": 2.925179771522223e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4992928,
      "step": 17825
    },
    {
      "epoch": 198.11111111111111,
      "grad_norm": 4.3275142047605186e-07,
      "learning_rate": 2.9242122934984535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4994336,
      "step": 17830
    },
    {
      "epoch": 198.16666666666666,
      "grad_norm": 5.000802616450528e-07,
      "learning_rate": 2.9232447500558176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4995744,
      "step": 17835
    },
    {
      "epoch": 198.22222222222223,
      "grad_norm": 5.967789320493466e-07,
      "learning_rate": 2.9222771413435225e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4997136,
      "step": 17840
    },
    {
      "epoch": 198.27777777777777,
      "grad_norm": 1.1348398629706935e-06,
      "learning_rate": 2.9213094675107848e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 4998592,
      "step": 17845
    },
    {
      "epoch": 198.33333333333334,
      "grad_norm": 8.14430961781909e-07,
      "learning_rate": 2.9203417287068335e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5000016,
      "step": 17850
    },
    {
      "epoch": 198.38888888888889,
      "grad_norm": 4.614004183167708e-07,
      "learning_rate": 2.9193739250809042e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5001424,
      "step": 17855
    },
    {
      "epoch": 198.44444444444446,
      "grad_norm": 4.593516109707707e-07,
      "learning_rate": 2.9184060567822463e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5002768,
      "step": 17860
    },
    {
      "epoch": 198.5,
      "grad_norm": 4.963298465554544e-07,
      "learning_rate": 2.9174381239601166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5004192,
      "step": 17865
    },
    {
      "epoch": 198.55555555555554,
      "grad_norm": 1.5039363461255562e-06,
      "learning_rate": 2.916470126763783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5005584,
      "step": 17870
    },
    {
      "epoch": 198.61111111111111,
      "grad_norm": 1.6426404272351647e-06,
      "learning_rate": 2.9155020653425203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5006976,
      "step": 17875
    },
    {
      "epoch": 198.66666666666666,
      "grad_norm": 6.272553036978934e-07,
      "learning_rate": 2.9145339398456184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5008400,
      "step": 17880
    },
    {
      "epoch": 198.72222222222223,
      "grad_norm": 6.165426498228044e-07,
      "learning_rate": 2.913565750422374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5009824,
      "step": 17885
    },
    {
      "epoch": 198.77777777777777,
      "grad_norm": 1.6775512676758808e-06,
      "learning_rate": 2.9125974972220938e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5011200,
      "step": 17890
    },
    {
      "epoch": 198.83333333333334,
      "grad_norm": 5.922507284594758e-07,
      "learning_rate": 2.9116291803940932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5012592,
      "step": 17895
    },
    {
      "epoch": 198.88888888888889,
      "grad_norm": 5.621845957648475e-07,
      "learning_rate": 2.910660800087701e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5013968,
      "step": 17900
    },
    {
      "epoch": 198.94444444444446,
      "grad_norm": 2.2360641196428332e-06,
      "learning_rate": 2.909692356452254e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5015408,
      "step": 17905
    },
    {
      "epoch": 199.0,
      "grad_norm": 6.824605520705518e-07,
      "learning_rate": 2.9087238496370962e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5016768,
      "step": 17910
    },
    {
      "epoch": 199.05555555555554,
      "grad_norm": 5.870506356586702e-07,
      "learning_rate": 2.907755279791583e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5018160,
      "step": 17915
    },
    {
      "epoch": 199.11111111111111,
      "grad_norm": 2.375225903961109e-06,
      "learning_rate": 2.906786647065083e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5019632,
      "step": 17920
    },
    {
      "epoch": 199.16666666666666,
      "grad_norm": 1.0579640274954727e-06,
      "learning_rate": 2.9058179516069695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5021056,
      "step": 17925
    },
    {
      "epoch": 199.22222222222223,
      "grad_norm": 3.5653463328344515e-06,
      "learning_rate": 2.9048491935666282e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5022448,
      "step": 17930
    },
    {
      "epoch": 199.27777777777777,
      "grad_norm": 1.6948525853877072e-06,
      "learning_rate": 2.9038803730934534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5023840,
      "step": 17935
    },
    {
      "epoch": 199.33333333333334,
      "grad_norm": 1.4799455811953521e-06,
      "learning_rate": 2.9029114903368503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5025200,
      "step": 17940
    },
    {
      "epoch": 199.38888888888889,
      "grad_norm": 1.6308026715705637e-06,
      "learning_rate": 2.9019425454462318e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5026576,
      "step": 17945
    },
    {
      "epoch": 199.44444444444446,
      "grad_norm": 5.072012640994217e-07,
      "learning_rate": 2.9009735385710212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5027936,
      "step": 17950
    },
    {
      "epoch": 199.5,
      "grad_norm": 1.1133827229059534e-06,
      "learning_rate": 2.900004469860652e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5029344,
      "step": 17955
    },
    {
      "epoch": 199.55555555555554,
      "grad_norm": 1.1655721436909516e-06,
      "learning_rate": 2.8990353394645668e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5030800,
      "step": 17960
    },
    {
      "epoch": 199.61111111111111,
      "grad_norm": 1.6854259001775063e-06,
      "learning_rate": 2.8980661475322186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5032224,
      "step": 17965
    },
    {
      "epoch": 199.66666666666666,
      "grad_norm": 5.476667865877971e-07,
      "learning_rate": 2.897096894213067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5033600,
      "step": 17970
    },
    {
      "epoch": 199.72222222222223,
      "grad_norm": 4.536390463272255e-07,
      "learning_rate": 2.8961275796565845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5034976,
      "step": 17975
    },
    {
      "epoch": 199.77777777777777,
      "grad_norm": 1.0519204352021916e-06,
      "learning_rate": 2.8951582040122517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5036336,
      "step": 17980
    },
    {
      "epoch": 199.83333333333334,
      "grad_norm": 1.6990338735922705e-06,
      "learning_rate": 2.894188767429557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5037712,
      "step": 17985
    },
    {
      "epoch": 199.88888888888889,
      "grad_norm": 4.70168487254341e-07,
      "learning_rate": 2.8932192700580014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5039104,
      "step": 17990
    },
    {
      "epoch": 199.94444444444446,
      "grad_norm": 1.0988003396050772e-06,
      "learning_rate": 2.8922497120470916e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5040480,
      "step": 17995
    },
    {
      "epoch": 200.0,
      "grad_norm": 6.906886937940726e-07,
      "learning_rate": 2.891280093546348e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5041920,
      "step": 18000
    },
    {
      "epoch": 200.0,
      "eval_loss": 0.3877609968185425,
      "eval_runtime": 1.2845,
      "eval_samples_per_second": 31.14,
      "eval_steps_per_second": 15.57,
      "num_input_tokens_seen": 5041920,
      "step": 18000
    },
    {
      "epoch": 200.05555555555554,
      "grad_norm": 4.932023216497328e-07,
      "learning_rate": 2.890310414705297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5043344,
      "step": 18005
    },
    {
      "epoch": 200.11111111111111,
      "grad_norm": 4.973229010829527e-07,
      "learning_rate": 2.8893406756734742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5044704,
      "step": 18010
    },
    {
      "epoch": 200.16666666666666,
      "grad_norm": 4.885945372734568e-07,
      "learning_rate": 2.888370876600427e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5046112,
      "step": 18015
    },
    {
      "epoch": 200.22222222222223,
      "grad_norm": 6.533879286507727e-07,
      "learning_rate": 2.8874010176357104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5047520,
      "step": 18020
    },
    {
      "epoch": 200.27777777777777,
      "grad_norm": 1.533123054286989e-06,
      "learning_rate": 2.886431098928888e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5048928,
      "step": 18025
    },
    {
      "epoch": 200.33333333333334,
      "grad_norm": 6.40363282400358e-07,
      "learning_rate": 2.885461120629534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5050352,
      "step": 18030
    },
    {
      "epoch": 200.38888888888889,
      "grad_norm": 6.22357333668333e-07,
      "learning_rate": 2.8844910828872317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5051760,
      "step": 18035
    },
    {
      "epoch": 200.44444444444446,
      "grad_norm": 6.213252845554962e-07,
      "learning_rate": 2.8835209858515715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5053152,
      "step": 18040
    },
    {
      "epoch": 200.5,
      "grad_norm": 4.6651823026877537e-07,
      "learning_rate": 2.8825508296721566e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5054528,
      "step": 18045
    },
    {
      "epoch": 200.55555555555554,
      "grad_norm": 5.14182431743393e-07,
      "learning_rate": 2.881580614498596e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5055952,
      "step": 18050
    },
    {
      "epoch": 200.61111111111111,
      "grad_norm": 3.7940681067993864e-06,
      "learning_rate": 2.8806103404805103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5057312,
      "step": 18055
    },
    {
      "epoch": 200.66666666666666,
      "grad_norm": 5.727825396206754e-07,
      "learning_rate": 2.8796400077675257e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5058672,
      "step": 18060
    },
    {
      "epoch": 200.72222222222223,
      "grad_norm": 1.7477080973549164e-06,
      "learning_rate": 2.8786696165092812e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5060032,
      "step": 18065
    },
    {
      "epoch": 200.77777777777777,
      "grad_norm": 5.148961008671904e-07,
      "learning_rate": 2.8776991668554236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5061440,
      "step": 18070
    },
    {
      "epoch": 200.83333333333334,
      "grad_norm": 3.875237837291934e-07,
      "learning_rate": 2.876728658955608e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5062832,
      "step": 18075
    },
    {
      "epoch": 200.88888888888889,
      "grad_norm": 5.226372081779118e-07,
      "learning_rate": 2.8757580929594986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5064272,
      "step": 18080
    },
    {
      "epoch": 200.94444444444446,
      "grad_norm": 1.551266223032144e-06,
      "learning_rate": 2.87478746901677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5065680,
      "step": 18085
    },
    {
      "epoch": 201.0,
      "grad_norm": 5.879354603166576e-07,
      "learning_rate": 2.873816787277103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5067088,
      "step": 18090
    },
    {
      "epoch": 201.05555555555554,
      "grad_norm": 4.3513298919606314e-07,
      "learning_rate": 2.8728460478901903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5068496,
      "step": 18095
    },
    {
      "epoch": 201.11111111111111,
      "grad_norm": 5.107000333737233e-07,
      "learning_rate": 2.8718752510057307e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5069872,
      "step": 18100
    },
    {
      "epoch": 201.16666666666666,
      "grad_norm": 5.789401029687724e-07,
      "learning_rate": 2.870904396773435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5071312,
      "step": 18105
    },
    {
      "epoch": 201.22222222222223,
      "grad_norm": 2.0559050426527392e-06,
      "learning_rate": 2.86993348534302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5072688,
      "step": 18110
    },
    {
      "epoch": 201.27777777777777,
      "grad_norm": 6.073542522244679e-07,
      "learning_rate": 2.868962516864212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5074112,
      "step": 18115
    },
    {
      "epoch": 201.33333333333334,
      "grad_norm": 4.166945473116357e-06,
      "learning_rate": 2.8679914914867477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5075504,
      "step": 18120
    },
    {
      "epoch": 201.38888888888889,
      "grad_norm": 6.835307431174442e-07,
      "learning_rate": 2.8670204093603713e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5076912,
      "step": 18125
    },
    {
      "epoch": 201.44444444444446,
      "grad_norm": 6.188736847434484e-07,
      "learning_rate": 2.8660492706348357e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5078304,
      "step": 18130
    },
    {
      "epoch": 201.5,
      "grad_norm": 1.1241756965318928e-06,
      "learning_rate": 2.8650780754599022e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5079760,
      "step": 18135
    },
    {
      "epoch": 201.55555555555554,
      "grad_norm": 9.165054279947071e-07,
      "learning_rate": 2.8641068239853407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5081136,
      "step": 18140
    },
    {
      "epoch": 201.61111111111111,
      "grad_norm": 4.878608592662204e-07,
      "learning_rate": 2.863135516360932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5082544,
      "step": 18145
    },
    {
      "epoch": 201.66666666666666,
      "grad_norm": 6.781343699913123e-07,
      "learning_rate": 2.8621641527364633e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5083984,
      "step": 18150
    },
    {
      "epoch": 201.72222222222223,
      "grad_norm": 5.236556717136409e-07,
      "learning_rate": 2.8611927332617313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5085376,
      "step": 18155
    },
    {
      "epoch": 201.77777777777777,
      "grad_norm": 7.206088525890664e-07,
      "learning_rate": 2.8602212580865405e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5086784,
      "step": 18160
    },
    {
      "epoch": 201.83333333333334,
      "grad_norm": 6.188509473759041e-07,
      "learning_rate": 2.859249727360705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5088144,
      "step": 18165
    },
    {
      "epoch": 201.88888888888889,
      "grad_norm": 7.024714818726352e-07,
      "learning_rate": 2.8582781412340465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5089536,
      "step": 18170
    },
    {
      "epoch": 201.94444444444446,
      "grad_norm": 1.6667225963828969e-06,
      "learning_rate": 2.857306499856397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5090960,
      "step": 18175
    },
    {
      "epoch": 202.0,
      "grad_norm": 1.7392198969901074e-06,
      "learning_rate": 2.856334803377594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5092304,
      "step": 18180
    },
    {
      "epoch": 202.05555555555554,
      "grad_norm": 7.6053606790083e-07,
      "learning_rate": 2.8553630519474867e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5093664,
      "step": 18185
    },
    {
      "epoch": 202.11111111111111,
      "grad_norm": 5.4082429414847866e-06,
      "learning_rate": 2.8543912457159317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5095056,
      "step": 18190
    },
    {
      "epoch": 202.16666666666666,
      "grad_norm": 1.6859003153513186e-06,
      "learning_rate": 2.853419384832792e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5096464,
      "step": 18195
    },
    {
      "epoch": 202.22222222222223,
      "grad_norm": 5.502889734998462e-07,
      "learning_rate": 2.8524474694479423e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5097872,
      "step": 18200
    },
    {
      "epoch": 202.22222222222223,
      "eval_loss": 0.3578169345855713,
      "eval_runtime": 1.2891,
      "eval_samples_per_second": 31.028,
      "eval_steps_per_second": 15.514,
      "num_input_tokens_seen": 5097872,
      "step": 18200
    },
    {
      "epoch": 202.27777777777777,
      "grad_norm": 2.0478541955526453e-06,
      "learning_rate": 2.851475499711264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5099280,
      "step": 18205
    },
    {
      "epoch": 202.33333333333334,
      "grad_norm": 1.650910007811035e-06,
      "learning_rate": 2.8505034757726468e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5100672,
      "step": 18210
    },
    {
      "epoch": 202.38888888888889,
      "grad_norm": 1.0754389450085e-06,
      "learning_rate": 2.8495313977819886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5102096,
      "step": 18215
    },
    {
      "epoch": 202.44444444444446,
      "grad_norm": 5.860165401827544e-07,
      "learning_rate": 2.8485592658891956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5103520,
      "step": 18220
    },
    {
      "epoch": 202.5,
      "grad_norm": 5.930237421125639e-07,
      "learning_rate": 2.8475870802441844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5104992,
      "step": 18225
    },
    {
      "epoch": 202.55555555555554,
      "grad_norm": 1.0181526022279286e-06,
      "learning_rate": 2.8466148409968774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5106416,
      "step": 18230
    },
    {
      "epoch": 202.61111111111111,
      "grad_norm": 6.600798201361613e-07,
      "learning_rate": 2.8456425482972067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5107824,
      "step": 18235
    },
    {
      "epoch": 202.66666666666666,
      "grad_norm": 5.85394332119904e-07,
      "learning_rate": 2.84467020229511e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5109168,
      "step": 18240
    },
    {
      "epoch": 202.72222222222223,
      "grad_norm": 9.921583341565565e-07,
      "learning_rate": 2.8436978031405375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5110528,
      "step": 18245
    },
    {
      "epoch": 202.77777777777777,
      "grad_norm": 1.4907720924384193e-06,
      "learning_rate": 2.842725350983445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5111936,
      "step": 18250
    },
    {
      "epoch": 202.83333333333334,
      "grad_norm": 5.975837211735779e-07,
      "learning_rate": 2.8417528459737957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5113360,
      "step": 18255
    },
    {
      "epoch": 202.88888888888889,
      "grad_norm": 4.7219481302818167e-07,
      "learning_rate": 2.8407802882615624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5114704,
      "step": 18260
    },
    {
      "epoch": 202.94444444444446,
      "grad_norm": 5.318578359947423e-07,
      "learning_rate": 2.8398076779967277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5116080,
      "step": 18265
    },
    {
      "epoch": 203.0,
      "grad_norm": 5.389237230701838e-06,
      "learning_rate": 2.8388350153292774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5117488,
      "step": 18270
    },
    {
      "epoch": 203.05555555555554,
      "grad_norm": 5.677882199961459e-07,
      "learning_rate": 2.8378623004092103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5118848,
      "step": 18275
    },
    {
      "epoch": 203.11111111111111,
      "grad_norm": 5.154360565029492e-07,
      "learning_rate": 2.8368895333865302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5120288,
      "step": 18280
    },
    {
      "epoch": 203.16666666666666,
      "grad_norm": 5.107486913402681e-07,
      "learning_rate": 2.835916714411251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5121776,
      "step": 18285
    },
    {
      "epoch": 203.22222222222223,
      "grad_norm": 5.685530481969181e-07,
      "learning_rate": 2.8349438436333926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5123200,
      "step": 18290
    },
    {
      "epoch": 203.27777777777777,
      "grad_norm": 1.0035099649030599e-06,
      "learning_rate": 2.833970921202984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5124608,
      "step": 18295
    },
    {
      "epoch": 203.33333333333334,
      "grad_norm": 1.0644860140018864e-06,
      "learning_rate": 2.8329979472700628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5126016,
      "step": 18300
    },
    {
      "epoch": 203.38888888888889,
      "grad_norm": 3.6108342555962736e-06,
      "learning_rate": 2.832024921984674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5127440,
      "step": 18305
    },
    {
      "epoch": 203.44444444444446,
      "grad_norm": 4.528307044893154e-07,
      "learning_rate": 2.8310518454968693e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5128864,
      "step": 18310
    },
    {
      "epoch": 203.5,
      "grad_norm": 6.808650709899666e-07,
      "learning_rate": 2.8300787179567095e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5130272,
      "step": 18315
    },
    {
      "epoch": 203.55555555555554,
      "grad_norm": 6.563634542544605e-07,
      "learning_rate": 2.8291055395142636e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5131680,
      "step": 18320
    },
    {
      "epoch": 203.61111111111111,
      "grad_norm": 2.3745315047563054e-06,
      "learning_rate": 2.8281323103196073e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5133072,
      "step": 18325
    },
    {
      "epoch": 203.66666666666666,
      "grad_norm": 5.025945029046852e-07,
      "learning_rate": 2.8271590305228256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5134496,
      "step": 18330
    },
    {
      "epoch": 203.72222222222223,
      "grad_norm": 5.506336719918181e-07,
      "learning_rate": 2.82618570027401e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5135872,
      "step": 18335
    },
    {
      "epoch": 203.77777777777777,
      "grad_norm": 4.884778945779544e-07,
      "learning_rate": 2.8252123197232604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5137264,
      "step": 18340
    },
    {
      "epoch": 203.83333333333334,
      "grad_norm": 1.7535968481752207e-06,
      "learning_rate": 2.8242388890206843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5138672,
      "step": 18345
    },
    {
      "epoch": 203.88888888888889,
      "grad_norm": 1.6941451121965656e-06,
      "learning_rate": 2.8232654083163967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5140048,
      "step": 18350
    },
    {
      "epoch": 203.94444444444446,
      "grad_norm": 4.917452542940737e-07,
      "learning_rate": 2.822291877760521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5141424,
      "step": 18355
    },
    {
      "epoch": 204.0,
      "grad_norm": 4.4107949292993e-07,
      "learning_rate": 2.8213182975031864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5142816,
      "step": 18360
    },
    {
      "epoch": 204.05555555555554,
      "grad_norm": 1.0422360219308757e-06,
      "learning_rate": 2.8203446676945337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5144192,
      "step": 18365
    },
    {
      "epoch": 204.11111111111111,
      "grad_norm": 6.13949669059366e-06,
      "learning_rate": 2.8193709884847075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5145600,
      "step": 18370
    },
    {
      "epoch": 204.16666666666666,
      "grad_norm": 6.762647331015614e-07,
      "learning_rate": 2.8183972600238605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5146992,
      "step": 18375
    },
    {
      "epoch": 204.22222222222223,
      "grad_norm": 5.369191740101087e-07,
      "learning_rate": 2.817423482462156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5148416,
      "step": 18380
    },
    {
      "epoch": 204.27777777777777,
      "grad_norm": 1.6225307035711012e-06,
      "learning_rate": 2.8164496559497605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5149808,
      "step": 18385
    },
    {
      "epoch": 204.33333333333334,
      "grad_norm": 5.02618263453769e-07,
      "learning_rate": 2.815475780636852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5151232,
      "step": 18390
    },
    {
      "epoch": 204.38888888888889,
      "grad_norm": 3.567579085483885e-07,
      "learning_rate": 2.814501856673613e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5152656,
      "step": 18395
    },
    {
      "epoch": 204.44444444444446,
      "grad_norm": 2.9461102712957654e-07,
      "learning_rate": 2.8135278842102353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5154064,
      "step": 18400
    },
    {
      "epoch": 204.44444444444446,
      "eval_loss": 0.38750022649765015,
      "eval_runtime": 1.2883,
      "eval_samples_per_second": 31.049,
      "eval_steps_per_second": 15.525,
      "num_input_tokens_seen": 5154064,
      "step": 18400
    },
    {
      "epoch": 204.5,
      "grad_norm": 4.833268008042069e-07,
      "learning_rate": 2.8125538633969183e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5155488,
      "step": 18405
    },
    {
      "epoch": 204.55555555555554,
      "grad_norm": 4.907694233224902e-07,
      "learning_rate": 2.8115797943838677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5156880,
      "step": 18410
    },
    {
      "epoch": 204.61111111111111,
      "grad_norm": 5.473916075970919e-07,
      "learning_rate": 2.810605677321298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5158272,
      "step": 18415
    },
    {
      "epoch": 204.66666666666666,
      "grad_norm": 5.808626610814827e-07,
      "learning_rate": 2.809631512359428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5159664,
      "step": 18420
    },
    {
      "epoch": 204.72222222222223,
      "grad_norm": 5.396336746343877e-07,
      "learning_rate": 2.8086572996484884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5161072,
      "step": 18425
    },
    {
      "epoch": 204.77777777777777,
      "grad_norm": 6.064584567866405e-07,
      "learning_rate": 2.8076830393387143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5162480,
      "step": 18430
    },
    {
      "epoch": 204.83333333333334,
      "grad_norm": 5.226515327194647e-07,
      "learning_rate": 2.8067087315803497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5163888,
      "step": 18435
    },
    {
      "epoch": 204.88888888888889,
      "grad_norm": 3.168374405504437e-06,
      "learning_rate": 2.8057343765236433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5165280,
      "step": 18440
    },
    {
      "epoch": 204.94444444444446,
      "grad_norm": 1.0762145166154369e-06,
      "learning_rate": 2.804759974318854e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5166704,
      "step": 18445
    },
    {
      "epoch": 205.0,
      "grad_norm": 4.960725163982715e-07,
      "learning_rate": 2.8037855251162482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5168096,
      "step": 18450
    },
    {
      "epoch": 205.05555555555554,
      "grad_norm": 4.482860731513938e-07,
      "learning_rate": 2.802811029066096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5169520,
      "step": 18455
    },
    {
      "epoch": 205.11111111111111,
      "grad_norm": 4.5754504185424594e-07,
      "learning_rate": 2.8018364863186764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5170896,
      "step": 18460
    },
    {
      "epoch": 205.16666666666666,
      "grad_norm": 4.843480496674601e-07,
      "learning_rate": 2.800861897024279e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5172320,
      "step": 18465
    },
    {
      "epoch": 205.22222222222223,
      "grad_norm": 4.5748561205982696e-07,
      "learning_rate": 2.799887261333196e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5173792,
      "step": 18470
    },
    {
      "epoch": 205.27777777777777,
      "grad_norm": 1.511237087470363e-06,
      "learning_rate": 2.798912579395728e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5175184,
      "step": 18475
    },
    {
      "epoch": 205.33333333333334,
      "grad_norm": 1.4921472484275e-06,
      "learning_rate": 2.797937851362185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5176560,
      "step": 18480
    },
    {
      "epoch": 205.38888888888889,
      "grad_norm": 5.101759938952455e-07,
      "learning_rate": 2.7969630773828802e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5177984,
      "step": 18485
    },
    {
      "epoch": 205.44444444444446,
      "grad_norm": 5.411858978732198e-07,
      "learning_rate": 2.7959882576081382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5179424,
      "step": 18490
    },
    {
      "epoch": 205.5,
      "grad_norm": 5.480956701831019e-07,
      "learning_rate": 2.795013392188286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5180784,
      "step": 18495
    },
    {
      "epoch": 205.55555555555554,
      "grad_norm": 3.925050350517267e-06,
      "learning_rate": 2.7940384812736614e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5182160,
      "step": 18500
    },
    {
      "epoch": 205.61111111111111,
      "grad_norm": 5.42776035672432e-07,
      "learning_rate": 2.7930635250146087e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5183552,
      "step": 18505
    },
    {
      "epoch": 205.66666666666666,
      "grad_norm": 1.7026236491801683e-06,
      "learning_rate": 2.792088523561477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5184944,
      "step": 18510
    },
    {
      "epoch": 205.72222222222223,
      "grad_norm": 4.562554352105508e-07,
      "learning_rate": 2.7911134770646246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5186368,
      "step": 18515
    },
    {
      "epoch": 205.77777777777777,
      "grad_norm": 4.398858663989813e-07,
      "learning_rate": 2.7901383856744157e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5187760,
      "step": 18520
    },
    {
      "epoch": 205.83333333333334,
      "grad_norm": 5.110737788527331e-07,
      "learning_rate": 2.7891632495412217e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5189120,
      "step": 18525
    },
    {
      "epoch": 205.88888888888889,
      "grad_norm": 1.5044104202388553e-06,
      "learning_rate": 2.7881880688154205e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5190528,
      "step": 18530
    },
    {
      "epoch": 205.94444444444446,
      "grad_norm": 1.1728806157407234e-06,
      "learning_rate": 2.7872128436473977e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5191936,
      "step": 18535
    },
    {
      "epoch": 206.0,
      "grad_norm": 6.089252337915241e-07,
      "learning_rate": 2.7862375741875448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5193328,
      "step": 18540
    },
    {
      "epoch": 206.05555555555554,
      "grad_norm": 6.004830765959923e-07,
      "learning_rate": 2.785262260586261e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5194672,
      "step": 18545
    },
    {
      "epoch": 206.11111111111111,
      "grad_norm": 5.545966246245371e-07,
      "learning_rate": 2.7842869029939517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5196064,
      "step": 18550
    },
    {
      "epoch": 206.16666666666666,
      "grad_norm": 5.008666335015732e-07,
      "learning_rate": 2.7833115015610296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5197440,
      "step": 18555
    },
    {
      "epoch": 206.22222222222223,
      "grad_norm": 1.761007638378942e-06,
      "learning_rate": 2.7823360564379136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5198816,
      "step": 18560
    },
    {
      "epoch": 206.27777777777777,
      "grad_norm": 5.963522653473774e-07,
      "learning_rate": 2.7813605677750297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5200224,
      "step": 18565
    },
    {
      "epoch": 206.33333333333334,
      "grad_norm": 6.030038548487937e-07,
      "learning_rate": 2.7803850357228102e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5201600,
      "step": 18570
    },
    {
      "epoch": 206.38888888888889,
      "grad_norm": 5.145906243342324e-07,
      "learning_rate": 2.779409460431695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5203008,
      "step": 18575
    },
    {
      "epoch": 206.44444444444446,
      "grad_norm": 5.481210223479138e-07,
      "learning_rate": 2.778433842052129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5204432,
      "step": 18580
    },
    {
      "epoch": 206.5,
      "grad_norm": 4.393498613808333e-07,
      "learning_rate": 2.7774581807345664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5205824,
      "step": 18585
    },
    {
      "epoch": 206.55555555555554,
      "grad_norm": 5.765840001004108e-07,
      "learning_rate": 2.776482476629465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5207248,
      "step": 18590
    },
    {
      "epoch": 206.61111111111111,
      "grad_norm": 1.1920053566427669e-06,
      "learning_rate": 2.7755067298872924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5208656,
      "step": 18595
    },
    {
      "epoch": 206.66666666666666,
      "grad_norm": 6.769756737412536e-07,
      "learning_rate": 2.774530940658518e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5210112,
      "step": 18600
    },
    {
      "epoch": 206.66666666666666,
      "eval_loss": 0.3622409701347351,
      "eval_runtime": 1.3022,
      "eval_samples_per_second": 30.716,
      "eval_steps_per_second": 15.358,
      "num_input_tokens_seen": 5210112,
      "step": 18600
    },
    {
      "epoch": 206.72222222222223,
      "grad_norm": 1.7166938732771087e-06,
      "learning_rate": 2.7735551090936236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5211456,
      "step": 18605
    },
    {
      "epoch": 206.77777777777777,
      "grad_norm": 4.928194812237052e-07,
      "learning_rate": 2.7725792353430934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5212896,
      "step": 18610
    },
    {
      "epoch": 206.83333333333334,
      "grad_norm": 5.668891844834434e-07,
      "learning_rate": 2.77160331955742e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5214304,
      "step": 18615
    },
    {
      "epoch": 206.88888888888889,
      "grad_norm": 1.1019699286407558e-06,
      "learning_rate": 2.7706273618871008e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5215696,
      "step": 18620
    },
    {
      "epoch": 206.94444444444446,
      "grad_norm": 3.774126980715664e-06,
      "learning_rate": 2.769651362482642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5217056,
      "step": 18625
    },
    {
      "epoch": 207.0,
      "grad_norm": 4.81713641420356e-07,
      "learning_rate": 2.768675321494555e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5218448,
      "step": 18630
    },
    {
      "epoch": 207.05555555555554,
      "grad_norm": 5.025287350690633e-07,
      "learning_rate": 2.7676992390733565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5219840,
      "step": 18635
    },
    {
      "epoch": 207.11111111111111,
      "grad_norm": 4.927113081976131e-07,
      "learning_rate": 2.766723115369571e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5221264,
      "step": 18640
    },
    {
      "epoch": 207.16666666666666,
      "grad_norm": 4.904783850179228e-07,
      "learning_rate": 2.765746950533729e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5222640,
      "step": 18645
    },
    {
      "epoch": 207.22222222222223,
      "grad_norm": 4.2566310298752796e-07,
      "learning_rate": 2.7647707447163684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5224000,
      "step": 18650
    },
    {
      "epoch": 207.27777777777777,
      "grad_norm": 4.4026535306329606e-07,
      "learning_rate": 2.7637944980680315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5225472,
      "step": 18655
    },
    {
      "epoch": 207.33333333333334,
      "grad_norm": 1.5095247363206e-06,
      "learning_rate": 2.762818210739268e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5226880,
      "step": 18660
    },
    {
      "epoch": 207.38888888888889,
      "grad_norm": 6.104806971052312e-07,
      "learning_rate": 2.7618418828806332e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5228288,
      "step": 18665
    },
    {
      "epoch": 207.44444444444446,
      "grad_norm": 1.0735172963904915e-06,
      "learning_rate": 2.76086551464269e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5229680,
      "step": 18670
    },
    {
      "epoch": 207.5,
      "grad_norm": 1.736284616526973e-06,
      "learning_rate": 2.759889106176006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5231104,
      "step": 18675
    },
    {
      "epoch": 207.55555555555554,
      "grad_norm": 5.029505132370105e-07,
      "learning_rate": 2.758912657631156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5232480,
      "step": 18680
    },
    {
      "epoch": 207.61111111111111,
      "grad_norm": 1.0773275107567315e-06,
      "learning_rate": 2.7579361691587198e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5233904,
      "step": 18685
    },
    {
      "epoch": 207.66666666666666,
      "grad_norm": 5.590379146269697e-07,
      "learning_rate": 2.756959640909285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5235280,
      "step": 18690
    },
    {
      "epoch": 207.72222222222223,
      "grad_norm": 4.584892394632334e-06,
      "learning_rate": 2.7559830730334452e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5236672,
      "step": 18695
    },
    {
      "epoch": 207.77777777777777,
      "grad_norm": 1.7629182593736914e-06,
      "learning_rate": 2.7550064656817988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5238096,
      "step": 18700
    },
    {
      "epoch": 207.83333333333334,
      "grad_norm": 5.67401457374217e-07,
      "learning_rate": 2.7540298190049503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5239488,
      "step": 18705
    },
    {
      "epoch": 207.88888888888889,
      "grad_norm": 5.415808459474647e-07,
      "learning_rate": 2.7530531331535107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5240848,
      "step": 18710
    },
    {
      "epoch": 207.94444444444446,
      "grad_norm": 3.924594238924328e-06,
      "learning_rate": 2.752076408278099e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5242256,
      "step": 18715
    },
    {
      "epoch": 208.0,
      "grad_norm": 5.622140974992362e-07,
      "learning_rate": 2.751099644529337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5243696,
      "step": 18720
    },
    {
      "epoch": 208.05555555555554,
      "grad_norm": 2.3447826151823392e-06,
      "learning_rate": 2.7501228420578533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5245072,
      "step": 18725
    },
    {
      "epoch": 208.11111111111111,
      "grad_norm": 2.0414122445799876e-06,
      "learning_rate": 2.7491460010142857e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5246448,
      "step": 18730
    },
    {
      "epoch": 208.16666666666666,
      "grad_norm": 7.295466275536455e-07,
      "learning_rate": 2.7481691215492727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5247824,
      "step": 18735
    },
    {
      "epoch": 208.22222222222223,
      "grad_norm": 6.313965741355787e-07,
      "learning_rate": 2.747192203813463e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5249200,
      "step": 18740
    },
    {
      "epoch": 208.27777777777777,
      "grad_norm": 3.546272637322545e-06,
      "learning_rate": 2.7462152479575087e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5250624,
      "step": 18745
    },
    {
      "epoch": 208.33333333333334,
      "grad_norm": 5.40508324320399e-07,
      "learning_rate": 2.7452382541320697e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5252000,
      "step": 18750
    },
    {
      "epoch": 208.38888888888889,
      "grad_norm": 5.953698973826249e-07,
      "learning_rate": 2.7442612224878096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5253456,
      "step": 18755
    },
    {
      "epoch": 208.44444444444446,
      "grad_norm": 1.699919494058122e-06,
      "learning_rate": 2.7432841531753994e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5254896,
      "step": 18760
    },
    {
      "epoch": 208.5,
      "grad_norm": 5.274196155369282e-07,
      "learning_rate": 2.7423070463455147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5256288,
      "step": 18765
    },
    {
      "epoch": 208.55555555555554,
      "grad_norm": 5.990805789224396e-07,
      "learning_rate": 2.7413299021488397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5257680,
      "step": 18770
    },
    {
      "epoch": 208.61111111111111,
      "grad_norm": 6.160199745863792e-07,
      "learning_rate": 2.7403527207360615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5259056,
      "step": 18775
    },
    {
      "epoch": 208.66666666666666,
      "grad_norm": 6.885182983751292e-07,
      "learning_rate": 2.7393755022578722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5260480,
      "step": 18780
    },
    {
      "epoch": 208.72222222222223,
      "grad_norm": 1.6847425285959616e-06,
      "learning_rate": 2.7383982468649714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5261872,
      "step": 18785
    },
    {
      "epoch": 208.77777777777777,
      "grad_norm": 1.0725041192927165e-06,
      "learning_rate": 2.7374209547080665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5263248,
      "step": 18790
    },
    {
      "epoch": 208.83333333333334,
      "grad_norm": 5.579563548963051e-07,
      "learning_rate": 2.7364436259378663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5264624,
      "step": 18795
    },
    {
      "epoch": 208.88888888888889,
      "grad_norm": 4.575012440000137e-07,
      "learning_rate": 2.735466260705088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5266064,
      "step": 18800
    },
    {
      "epoch": 208.88888888888889,
      "eval_loss": 0.36705824732780457,
      "eval_runtime": 1.2918,
      "eval_samples_per_second": 30.965,
      "eval_steps_per_second": 15.483,
      "num_input_tokens_seen": 5266064,
      "step": 18800
    },
    {
      "epoch": 208.94444444444446,
      "grad_norm": 3.9402360130225134e-07,
      "learning_rate": 2.7344888591604524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5267504,
      "step": 18805
    },
    {
      "epoch": 209.0,
      "grad_norm": 3.7065203741804e-06,
      "learning_rate": 2.7335114214546893e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5268928,
      "step": 18810
    },
    {
      "epoch": 209.05555555555554,
      "grad_norm": 5.190129854781844e-07,
      "learning_rate": 2.7325339477385293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5270368,
      "step": 18815
    },
    {
      "epoch": 209.11111111111111,
      "grad_norm": 4.063657286224043e-07,
      "learning_rate": 2.7315564381627128e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5271792,
      "step": 18820
    },
    {
      "epoch": 209.16666666666666,
      "grad_norm": 4.4962038714402297e-07,
      "learning_rate": 2.7305788928779835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5273184,
      "step": 18825
    },
    {
      "epoch": 209.22222222222223,
      "grad_norm": 5.666241236212954e-07,
      "learning_rate": 2.729601312035091e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5274560,
      "step": 18830
    },
    {
      "epoch": 209.27777777777777,
      "grad_norm": 1.6958208561845822e-06,
      "learning_rate": 2.7286236957847915e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5275984,
      "step": 18835
    },
    {
      "epoch": 209.33333333333334,
      "grad_norm": 2.1116134121257346e-06,
      "learning_rate": 2.7276460442778446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5277344,
      "step": 18840
    },
    {
      "epoch": 209.38888888888889,
      "grad_norm": 3.58724264515331e-06,
      "learning_rate": 2.726668357665017e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5278720,
      "step": 18845
    },
    {
      "epoch": 209.44444444444446,
      "grad_norm": 8.805054676486179e-07,
      "learning_rate": 2.7256906360970808e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5280160,
      "step": 18850
    },
    {
      "epoch": 209.5,
      "grad_norm": 4.566950622120203e-07,
      "learning_rate": 2.7247128797248117e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5281600,
      "step": 18855
    },
    {
      "epoch": 209.55555555555554,
      "grad_norm": 6.083602102080476e-07,
      "learning_rate": 2.7237350886989925e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5282960,
      "step": 18860
    },
    {
      "epoch": 209.61111111111111,
      "grad_norm": 3.903119250026066e-06,
      "learning_rate": 2.7227572631704107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5284368,
      "step": 18865
    },
    {
      "epoch": 209.66666666666666,
      "grad_norm": 6.236883223209588e-07,
      "learning_rate": 2.7217794032898596e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5285792,
      "step": 18870
    },
    {
      "epoch": 209.72222222222223,
      "grad_norm": 1.736065314617008e-06,
      "learning_rate": 2.7208015092081384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5287200,
      "step": 18875
    },
    {
      "epoch": 209.77777777777777,
      "grad_norm": 5.631616772916459e-07,
      "learning_rate": 2.719823581076049e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5288560,
      "step": 18880
    },
    {
      "epoch": 209.83333333333334,
      "grad_norm": 3.408975146612647e-07,
      "learning_rate": 2.718845619044401e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5289968,
      "step": 18885
    },
    {
      "epoch": 209.88888888888889,
      "grad_norm": 4.631128831533715e-07,
      "learning_rate": 2.7178676232640088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5291312,
      "step": 18890
    },
    {
      "epoch": 209.94444444444446,
      "grad_norm": 4.909202289127279e-07,
      "learning_rate": 2.716889593885691e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5292720,
      "step": 18895
    },
    {
      "epoch": 210.0,
      "grad_norm": 5.864004606337403e-07,
      "learning_rate": 2.7159115310602716e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5294128,
      "step": 18900
    },
    {
      "epoch": 210.05555555555554,
      "grad_norm": 4.7448580176023825e-07,
      "learning_rate": 2.7149334349385814e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5295536,
      "step": 18905
    },
    {
      "epoch": 210.11111111111111,
      "grad_norm": 5.5316750149358995e-06,
      "learning_rate": 2.713955305671454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5296944,
      "step": 18910
    },
    {
      "epoch": 210.16666666666666,
      "grad_norm": 4.83829069253261e-07,
      "learning_rate": 2.71297714340973e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5298352,
      "step": 18915
    },
    {
      "epoch": 210.22222222222223,
      "grad_norm": 4.492507059694617e-07,
      "learning_rate": 2.7119989483042545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5299856,
      "step": 18920
    },
    {
      "epoch": 210.27777777777777,
      "grad_norm": 1.107947355194483e-06,
      "learning_rate": 2.7110207205058768e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5301248,
      "step": 18925
    },
    {
      "epoch": 210.33333333333334,
      "grad_norm": 4.90687398269074e-07,
      "learning_rate": 2.7100424601654517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5302624,
      "step": 18930
    },
    {
      "epoch": 210.38888888888889,
      "grad_norm": 4.997384053240239e-07,
      "learning_rate": 2.7090641674338403e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5304016,
      "step": 18935
    },
    {
      "epoch": 210.44444444444446,
      "grad_norm": 5.13310112637555e-07,
      "learning_rate": 2.7080858424619072e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5305376,
      "step": 18940
    },
    {
      "epoch": 210.5,
      "grad_norm": 3.1173449315247126e-06,
      "learning_rate": 2.707107485400521e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5306736,
      "step": 18945
    },
    {
      "epoch": 210.55555555555554,
      "grad_norm": 1.727858034428209e-06,
      "learning_rate": 2.7061290964005586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5308176,
      "step": 18950
    },
    {
      "epoch": 210.61111111111111,
      "grad_norm": 1.7059442143363412e-06,
      "learning_rate": 2.7051506756129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5309536,
      "step": 18955
    },
    {
      "epoch": 210.66666666666666,
      "grad_norm": 5.238908897808869e-07,
      "learning_rate": 2.704172223188428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5310928,
      "step": 18960
    },
    {
      "epoch": 210.72222222222223,
      "grad_norm": 5.905770308345382e-07,
      "learning_rate": 2.7031937392780334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5312320,
      "step": 18965
    },
    {
      "epoch": 210.77777777777777,
      "grad_norm": 4.5793316871822753e-07,
      "learning_rate": 2.702215224032611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5313712,
      "step": 18970
    },
    {
      "epoch": 210.83333333333334,
      "grad_norm": 8.938521887102979e-07,
      "learning_rate": 2.70123667760306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5315168,
      "step": 18975
    },
    {
      "epoch": 210.88888888888889,
      "grad_norm": 4.6200759129533253e-07,
      "learning_rate": 2.7002581001402845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5316592,
      "step": 18980
    },
    {
      "epoch": 210.94444444444446,
      "grad_norm": 6.917157975294685e-07,
      "learning_rate": 2.6992794917951923e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5317952,
      "step": 18985
    },
    {
      "epoch": 211.0,
      "grad_norm": 1.5392553223136929e-06,
      "learning_rate": 2.6983008527187e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5319376,
      "step": 18990
    },
    {
      "epoch": 211.05555555555554,
      "grad_norm": 5.880695539417502e-07,
      "learning_rate": 2.697322183061723e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5320784,
      "step": 18995
    },
    {
      "epoch": 211.11111111111111,
      "grad_norm": 4.948482796862663e-07,
      "learning_rate": 2.696343482975186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5322160,
      "step": 19000
    },
    {
      "epoch": 211.11111111111111,
      "eval_loss": 0.3800784647464752,
      "eval_runtime": 1.2891,
      "eval_samples_per_second": 31.03,
      "eval_steps_per_second": 15.515,
      "num_input_tokens_seen": 5322160,
      "step": 19000
    },
    {
      "epoch": 211.16666666666666,
      "grad_norm": 5.12626058934984e-07,
      "learning_rate": 2.695364752610016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5323552,
      "step": 19005
    },
    {
      "epoch": 211.22222222222223,
      "grad_norm": 5.385526833379117e-07,
      "learning_rate": 2.6943859921171467e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5324976,
      "step": 19010
    },
    {
      "epoch": 211.27777777777777,
      "grad_norm": 2.0996242255932884e-06,
      "learning_rate": 2.6934072016475143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5326368,
      "step": 19015
    },
    {
      "epoch": 211.33333333333334,
      "grad_norm": 6.091159434618021e-07,
      "learning_rate": 2.6924283813520606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5327824,
      "step": 19020
    },
    {
      "epoch": 211.38888888888889,
      "grad_norm": 4.951269829689409e-07,
      "learning_rate": 2.691449531381733e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5329248,
      "step": 19025
    },
    {
      "epoch": 211.44444444444446,
      "grad_norm": 1.1223896763112862e-06,
      "learning_rate": 2.6904706518874816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5330608,
      "step": 19030
    },
    {
      "epoch": 211.5,
      "grad_norm": 1.6998724277073052e-06,
      "learning_rate": 2.6894917430202615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5332016,
      "step": 19035
    },
    {
      "epoch": 211.55555555555554,
      "grad_norm": 2.4007977117435075e-06,
      "learning_rate": 2.6885128049310343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5333424,
      "step": 19040
    },
    {
      "epoch": 211.61111111111111,
      "grad_norm": 5.106680305289046e-07,
      "learning_rate": 2.687533837770762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5334832,
      "step": 19045
    },
    {
      "epoch": 211.66666666666666,
      "grad_norm": 5.760058456871775e-07,
      "learning_rate": 2.6865548416904162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5336272,
      "step": 19050
    },
    {
      "epoch": 211.72222222222223,
      "grad_norm": 3.6516478303383337e-06,
      "learning_rate": 2.68557581684097e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5337680,
      "step": 19055
    },
    {
      "epoch": 211.77777777777777,
      "grad_norm": 5.829906513099559e-07,
      "learning_rate": 2.6845967633733998e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5339056,
      "step": 19060
    },
    {
      "epoch": 211.83333333333334,
      "grad_norm": 5.563165927924274e-07,
      "learning_rate": 2.683617681438689e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5340416,
      "step": 19065
    },
    {
      "epoch": 211.88888888888889,
      "grad_norm": 1.0402040970802773e-06,
      "learning_rate": 2.682638571187825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5341760,
      "step": 19070
    },
    {
      "epoch": 211.94444444444446,
      "grad_norm": 1.1115233746750164e-06,
      "learning_rate": 2.6816594327717976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5343184,
      "step": 19075
    },
    {
      "epoch": 212.0,
      "grad_norm": 5.567895868807682e-07,
      "learning_rate": 2.680680266341603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5344608,
      "step": 19080
    },
    {
      "epoch": 212.05555555555554,
      "grad_norm": 6.122917852735554e-07,
      "learning_rate": 2.67970107204824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5345952,
      "step": 19085
    },
    {
      "epoch": 212.11111111111111,
      "grad_norm": 2.160131089112838e-06,
      "learning_rate": 2.6787218500427142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5347328,
      "step": 19090
    },
    {
      "epoch": 212.16666666666666,
      "grad_norm": 4.513345572831895e-07,
      "learning_rate": 2.6777426004760332e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5348720,
      "step": 19095
    },
    {
      "epoch": 212.22222222222223,
      "grad_norm": 2.0762504391313996e-06,
      "learning_rate": 2.6767633234992094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5350112,
      "step": 19100
    },
    {
      "epoch": 212.27777777777777,
      "grad_norm": 2.302333086845465e-06,
      "learning_rate": 2.6757840192632598e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5351568,
      "step": 19105
    },
    {
      "epoch": 212.33333333333334,
      "grad_norm": 6.82150925968017e-07,
      "learning_rate": 2.6748046879192052e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5352960,
      "step": 19110
    },
    {
      "epoch": 212.38888888888889,
      "grad_norm": 2.2171050204633502e-06,
      "learning_rate": 2.673825329618071e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5354352,
      "step": 19115
    },
    {
      "epoch": 212.44444444444446,
      "grad_norm": 6.161654937386629e-07,
      "learning_rate": 2.6728459445108866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5355776,
      "step": 19120
    },
    {
      "epoch": 212.5,
      "grad_norm": 9.665008064985159e-07,
      "learning_rate": 2.6718665327486854e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5357168,
      "step": 19125
    },
    {
      "epoch": 212.55555555555554,
      "grad_norm": 4.536817641564994e-07,
      "learning_rate": 2.6708870944825048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5358544,
      "step": 19130
    },
    {
      "epoch": 212.61111111111111,
      "grad_norm": 5.992838509882858e-07,
      "learning_rate": 2.6699076298633874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5360000,
      "step": 19135
    },
    {
      "epoch": 212.66666666666666,
      "grad_norm": 5.538879577215994e-07,
      "learning_rate": 2.6689281390423788e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5361424,
      "step": 19140
    },
    {
      "epoch": 212.72222222222223,
      "grad_norm": 6.043172220415727e-07,
      "learning_rate": 2.667948622170527e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5362816,
      "step": 19145
    },
    {
      "epoch": 212.77777777777777,
      "grad_norm": 2.491737859600107e-06,
      "learning_rate": 2.6669690793988873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5364208,
      "step": 19150
    },
    {
      "epoch": 212.83333333333334,
      "grad_norm": 3.6174978959024884e-06,
      "learning_rate": 2.665989510878518e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5365632,
      "step": 19155
    },
    {
      "epoch": 212.88888888888889,
      "grad_norm": 5.501540272234706e-07,
      "learning_rate": 2.6650099167604793e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5367024,
      "step": 19160
    },
    {
      "epoch": 212.94444444444446,
      "grad_norm": 5.172440751266549e-07,
      "learning_rate": 2.6640302971958376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5368416,
      "step": 19165
    },
    {
      "epoch": 213.0,
      "grad_norm": 5.069065878160472e-07,
      "learning_rate": 2.6630506523356635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5369792,
      "step": 19170
    },
    {
      "epoch": 213.05555555555554,
      "grad_norm": 3.7724410617556714e-07,
      "learning_rate": 2.6620709823310297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5371152,
      "step": 19175
    },
    {
      "epoch": 213.11111111111111,
      "grad_norm": 1.6893974361664732e-06,
      "learning_rate": 2.661091287333014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5372560,
      "step": 19180
    },
    {
      "epoch": 213.16666666666666,
      "grad_norm": 5.216807608121599e-07,
      "learning_rate": 2.660111567492696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5373968,
      "step": 19185
    },
    {
      "epoch": 213.22222222222223,
      "grad_norm": 3.9392824646711233e-07,
      "learning_rate": 2.6591318229611635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5375408,
      "step": 19190
    },
    {
      "epoch": 213.27777777777777,
      "grad_norm": 6.517451538456953e-07,
      "learning_rate": 2.6581520538895037e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5376784,
      "step": 19195
    },
    {
      "epoch": 213.33333333333334,
      "grad_norm": 9.063415973287192e-07,
      "learning_rate": 2.6571722604288102e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5378224,
      "step": 19200
    },
    {
      "epoch": 213.33333333333334,
      "eval_loss": 0.35208946466445923,
      "eval_runtime": 1.2891,
      "eval_samples_per_second": 31.03,
      "eval_steps_per_second": 15.515,
      "num_input_tokens_seen": 5378224,
      "step": 19200
    },
    {
      "epoch": 213.38888888888889,
      "grad_norm": 8.080184557002212e-07,
      "learning_rate": 2.656192442730179e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5379648,
      "step": 19205
    },
    {
      "epoch": 213.44444444444446,
      "grad_norm": 9.459006378165213e-07,
      "learning_rate": 2.6552126009447098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5381056,
      "step": 19210
    },
    {
      "epoch": 213.5,
      "grad_norm": 6.017792770762753e-07,
      "learning_rate": 2.654232735223507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5382480,
      "step": 19215
    },
    {
      "epoch": 213.55555555555554,
      "grad_norm": 6.591732812921691e-07,
      "learning_rate": 2.6532528457176787e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5383840,
      "step": 19220
    },
    {
      "epoch": 213.61111111111111,
      "grad_norm": 5.419033186626621e-07,
      "learning_rate": 2.6522729325783348e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5385248,
      "step": 19225
    },
    {
      "epoch": 213.66666666666666,
      "grad_norm": 6.248887984838802e-07,
      "learning_rate": 2.6512929959565914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5386608,
      "step": 19230
    },
    {
      "epoch": 213.72222222222223,
      "grad_norm": 1.0212108918494778e-06,
      "learning_rate": 2.6503130360035673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5388032,
      "step": 19235
    },
    {
      "epoch": 213.77777777777777,
      "grad_norm": 2.2369163161783945e-06,
      "learning_rate": 2.6493330528703835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5389456,
      "step": 19240
    },
    {
      "epoch": 213.83333333333334,
      "grad_norm": 4.4870839133182017e-07,
      "learning_rate": 2.648353046708167e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5390896,
      "step": 19245
    },
    {
      "epoch": 213.88888888888889,
      "grad_norm": 6.258860025809554e-07,
      "learning_rate": 2.647373017668046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5392304,
      "step": 19250
    },
    {
      "epoch": 213.94444444444446,
      "grad_norm": 6.519876478705555e-07,
      "learning_rate": 2.6463929659011537e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5393728,
      "step": 19255
    },
    {
      "epoch": 214.0,
      "grad_norm": 2.4113348899845732e-06,
      "learning_rate": 2.6454128915586262e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5395104,
      "step": 19260
    },
    {
      "epoch": 214.05555555555554,
      "grad_norm": 3.576421477191616e-06,
      "learning_rate": 2.6444327947916036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5396496,
      "step": 19265
    },
    {
      "epoch": 214.11111111111111,
      "grad_norm": 5.960031330687343e-07,
      "learning_rate": 2.6434526757512292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5397952,
      "step": 19270
    },
    {
      "epoch": 214.16666666666666,
      "grad_norm": 5.615115128421166e-07,
      "learning_rate": 2.6424725345886486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5399296,
      "step": 19275
    },
    {
      "epoch": 214.22222222222223,
      "grad_norm": 5.8318255469203e-07,
      "learning_rate": 2.641492371455014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5400672,
      "step": 19280
    },
    {
      "epoch": 214.27777777777777,
      "grad_norm": 8.384545822082146e-07,
      "learning_rate": 2.640512186501477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5402112,
      "step": 19285
    },
    {
      "epoch": 214.33333333333334,
      "grad_norm": 5.902123234591272e-07,
      "learning_rate": 2.639531979879195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5403520,
      "step": 19290
    },
    {
      "epoch": 214.38888888888889,
      "grad_norm": 5.579553317147656e-07,
      "learning_rate": 2.638551751739328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5404928,
      "step": 19295
    },
    {
      "epoch": 214.44444444444446,
      "grad_norm": 5.453778157971101e-07,
      "learning_rate": 2.6375715022330404e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5406336,
      "step": 19300
    },
    {
      "epoch": 214.5,
      "grad_norm": 5.687618340743938e-07,
      "learning_rate": 2.6365912315114976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5407744,
      "step": 19305
    },
    {
      "epoch": 214.55555555555554,
      "grad_norm": 5.201712838243111e-07,
      "learning_rate": 2.6356109397258704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5409136,
      "step": 19310
    },
    {
      "epoch": 214.61111111111111,
      "grad_norm": 1.0427237384647015e-06,
      "learning_rate": 2.6346306270273325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5410512,
      "step": 19315
    },
    {
      "epoch": 214.66666666666666,
      "grad_norm": 5.530824864763417e-07,
      "learning_rate": 2.6336502935670608e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5411936,
      "step": 19320
    },
    {
      "epoch": 214.72222222222223,
      "grad_norm": 2.0545289771689568e-06,
      "learning_rate": 2.6326699394962333e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5413328,
      "step": 19325
    },
    {
      "epoch": 214.77777777777777,
      "grad_norm": 5.520869308384135e-07,
      "learning_rate": 2.6316895649660334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5414704,
      "step": 19330
    },
    {
      "epoch": 214.83333333333334,
      "grad_norm": 5.631629846902797e-07,
      "learning_rate": 2.6307091701276486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5416112,
      "step": 19335
    },
    {
      "epoch": 214.88888888888889,
      "grad_norm": 5.112921144245774e-07,
      "learning_rate": 2.629728755132267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5417520,
      "step": 19340
    },
    {
      "epoch": 214.94444444444446,
      "grad_norm": 1.0468205573488376e-06,
      "learning_rate": 2.628748320131081e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5418960,
      "step": 19345
    },
    {
      "epoch": 215.0,
      "grad_norm": 2.2529984562424943e-06,
      "learning_rate": 2.6277678652752856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5420384,
      "step": 19350
    },
    {
      "epoch": 215.05555555555554,
      "grad_norm": 5.930589281888388e-07,
      "learning_rate": 2.6267873907160807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5421792,
      "step": 19355
    },
    {
      "epoch": 215.11111111111111,
      "grad_norm": 5.028994110034546e-07,
      "learning_rate": 2.6258068966046668e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5423152,
      "step": 19360
    },
    {
      "epoch": 215.16666666666666,
      "grad_norm": 4.734467040634627e-07,
      "learning_rate": 2.6248263830922475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5424528,
      "step": 19365
    },
    {
      "epoch": 215.22222222222223,
      "grad_norm": 5.421716764431039e-07,
      "learning_rate": 2.6238458503300318e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5425952,
      "step": 19370
    },
    {
      "epoch": 215.27777777777777,
      "grad_norm": 6.241612595658808e-07,
      "learning_rate": 2.6228652984692292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5427376,
      "step": 19375
    },
    {
      "epoch": 215.33333333333334,
      "grad_norm": 6.629828135373828e-07,
      "learning_rate": 2.621884727661054e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5428800,
      "step": 19380
    },
    {
      "epoch": 215.38888888888889,
      "grad_norm": 5.906017008783238e-07,
      "learning_rate": 2.6209041380567222e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5430208,
      "step": 19385
    },
    {
      "epoch": 215.44444444444446,
      "grad_norm": 5.845020609740459e-07,
      "learning_rate": 2.6199235298074527e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5431616,
      "step": 19390
    },
    {
      "epoch": 215.5,
      "grad_norm": 2.332939629923203e-06,
      "learning_rate": 2.618942903064468e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5433024,
      "step": 19395
    },
    {
      "epoch": 215.55555555555554,
      "grad_norm": 5.078269964542415e-07,
      "learning_rate": 2.6179622579789932e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5434432,
      "step": 19400
    },
    {
      "epoch": 215.55555555555554,
      "eval_loss": 0.3748704493045807,
      "eval_runtime": 1.2977,
      "eval_samples_per_second": 30.823,
      "eval_steps_per_second": 15.411,
      "num_input_tokens_seen": 5434432,
      "step": 19400
    },
    {
      "epoch": 215.61111111111111,
      "grad_norm": 5.115633143759624e-07,
      "learning_rate": 2.6169815947022553e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5435824,
      "step": 19405
    },
    {
      "epoch": 215.66666666666666,
      "grad_norm": 5.55519193312648e-07,
      "learning_rate": 2.6160009133854853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5437216,
      "step": 19410
    },
    {
      "epoch": 215.72222222222223,
      "grad_norm": 9.588890179657028e-07,
      "learning_rate": 2.6150202141799168e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5438640,
      "step": 19415
    },
    {
      "epoch": 215.77777777777777,
      "grad_norm": 5.969944822936668e-07,
      "learning_rate": 2.614039497236786e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5440048,
      "step": 19420
    },
    {
      "epoch": 215.83333333333334,
      "grad_norm": 5.820210731144471e-07,
      "learning_rate": 2.6130587627073315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5441440,
      "step": 19425
    },
    {
      "epoch": 215.88888888888889,
      "grad_norm": 5.031355954088212e-07,
      "learning_rate": 2.6120780107427956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5442816,
      "step": 19430
    },
    {
      "epoch": 215.94444444444446,
      "grad_norm": 1.604702106305922e-06,
      "learning_rate": 2.6110972414944214e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5444272,
      "step": 19435
    },
    {
      "epoch": 216.0,
      "grad_norm": 5.928573045821395e-07,
      "learning_rate": 2.6101164551134565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5445680,
      "step": 19440
    },
    {
      "epoch": 216.05555555555554,
      "grad_norm": 1.692774048933643e-06,
      "learning_rate": 2.6091356517511505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5447136,
      "step": 19445
    },
    {
      "epoch": 216.11111111111111,
      "grad_norm": 4.644793705210759e-07,
      "learning_rate": 2.608154831558755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5448512,
      "step": 19450
    },
    {
      "epoch": 216.16666666666666,
      "grad_norm": 4.262110167019273e-07,
      "learning_rate": 2.607173994687526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5449872,
      "step": 19455
    },
    {
      "epoch": 216.22222222222223,
      "grad_norm": 3.966909503105853e-07,
      "learning_rate": 2.6061931412887196e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5451280,
      "step": 19460
    },
    {
      "epoch": 216.27777777777777,
      "grad_norm": 1.1256630614298047e-06,
      "learning_rate": 2.6052122715135973e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5452688,
      "step": 19465
    },
    {
      "epoch": 216.33333333333334,
      "grad_norm": 9.967387768483604e-07,
      "learning_rate": 2.60423138551342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5454112,
      "step": 19470
    },
    {
      "epoch": 216.38888888888889,
      "grad_norm": 6.483767265308416e-07,
      "learning_rate": 2.6032504834394527e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5455488,
      "step": 19475
    },
    {
      "epoch": 216.44444444444446,
      "grad_norm": 7.308457838917093e-07,
      "learning_rate": 2.602269565442964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5456896,
      "step": 19480
    },
    {
      "epoch": 216.5,
      "grad_norm": 4.953532766194257e-07,
      "learning_rate": 2.6012886316752227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5458304,
      "step": 19485
    },
    {
      "epoch": 216.55555555555554,
      "grad_norm": 6.357269626278139e-07,
      "learning_rate": 2.6003076822875018e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5459712,
      "step": 19490
    },
    {
      "epoch": 216.61111111111111,
      "grad_norm": 1.0124822438228875e-06,
      "learning_rate": 2.5993267174310755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5461104,
      "step": 19495
    },
    {
      "epoch": 216.66666666666666,
      "grad_norm": 1.0517265991438762e-06,
      "learning_rate": 2.5983457372572218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5462448,
      "step": 19500
    },
    {
      "epoch": 216.72222222222223,
      "grad_norm": 4.0443495663566864e-07,
      "learning_rate": 2.597364741917219e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5463856,
      "step": 19505
    },
    {
      "epoch": 216.77777777777777,
      "grad_norm": 5.192025014366664e-07,
      "learning_rate": 2.5963837315623492e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5465232,
      "step": 19510
    },
    {
      "epoch": 216.83333333333334,
      "grad_norm": 4.1219831814487407e-07,
      "learning_rate": 2.595402706343897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5466672,
      "step": 19515
    },
    {
      "epoch": 216.88888888888889,
      "grad_norm": 6.42213251467183e-07,
      "learning_rate": 2.594421666413148e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5468112,
      "step": 19520
    },
    {
      "epoch": 216.94444444444446,
      "grad_norm": 3.7862357658013934e-06,
      "learning_rate": 2.5934406119213928e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5469504,
      "step": 19525
    },
    {
      "epoch": 217.0,
      "grad_norm": 4.021800066311698e-07,
      "learning_rate": 2.5924595430199193e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5470848,
      "step": 19530
    },
    {
      "epoch": 217.05555555555554,
      "grad_norm": 3.0512287594319787e-06,
      "learning_rate": 2.5914784598600238e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5472240,
      "step": 19535
    },
    {
      "epoch": 217.11111111111111,
      "grad_norm": 6.077823968553275e-07,
      "learning_rate": 2.5904973625930002e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5473616,
      "step": 19540
    },
    {
      "epoch": 217.16666666666666,
      "grad_norm": 5.434070544652059e-07,
      "learning_rate": 2.5895162513701456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5475008,
      "step": 19545
    },
    {
      "epoch": 217.22222222222223,
      "grad_norm": 5.712664687962388e-07,
      "learning_rate": 2.5885351263427593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5476384,
      "step": 19550
    },
    {
      "epoch": 217.27777777777777,
      "grad_norm": 5.876202067156555e-07,
      "learning_rate": 2.5875539876621448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5477776,
      "step": 19555
    },
    {
      "epoch": 217.33333333333334,
      "grad_norm": 5.817598776047817e-07,
      "learning_rate": 2.586572835479605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5479168,
      "step": 19560
    },
    {
      "epoch": 217.38888888888889,
      "grad_norm": 1.706661009848176e-06,
      "learning_rate": 2.585591669946446e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5480528,
      "step": 19565
    },
    {
      "epoch": 217.44444444444446,
      "grad_norm": 5.278770345285011e-07,
      "learning_rate": 2.5846104912139756e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5481936,
      "step": 19570
    },
    {
      "epoch": 217.5,
      "grad_norm": 4.768833719026588e-07,
      "learning_rate": 2.583629299433505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5483328,
      "step": 19575
    },
    {
      "epoch": 217.55555555555554,
      "grad_norm": 6.070371796340623e-07,
      "learning_rate": 2.582648094756345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5484752,
      "step": 19580
    },
    {
      "epoch": 217.61111111111111,
      "grad_norm": 5.187351348467928e-07,
      "learning_rate": 2.5816668773338098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5486112,
      "step": 19585
    },
    {
      "epoch": 217.66666666666666,
      "grad_norm": 6.024214940225647e-07,
      "learning_rate": 2.580685647317216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5487536,
      "step": 19590
    },
    {
      "epoch": 217.72222222222223,
      "grad_norm": 5.844115662512195e-07,
      "learning_rate": 2.5797044048578818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5488928,
      "step": 19595
    },
    {
      "epoch": 217.77777777777777,
      "grad_norm": 6.428187475648883e-07,
      "learning_rate": 2.5787231501071262e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5490352,
      "step": 19600
    },
    {
      "epoch": 217.77777777777777,
      "eval_loss": 0.371354877948761,
      "eval_runtime": 1.3026,
      "eval_samples_per_second": 30.709,
      "eval_steps_per_second": 15.354,
      "num_input_tokens_seen": 5490352,
      "step": 19600
    },
    {
      "epoch": 217.83333333333334,
      "grad_norm": 5.281992230266042e-07,
      "learning_rate": 2.577741883216272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5491744,
      "step": 19605
    },
    {
      "epoch": 217.88888888888889,
      "grad_norm": 1.0119149465026567e-06,
      "learning_rate": 2.576760604336642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5493200,
      "step": 19610
    },
    {
      "epoch": 217.94444444444446,
      "grad_norm": 1.6889489415916614e-06,
      "learning_rate": 2.575779313619563e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5494624,
      "step": 19615
    },
    {
      "epoch": 218.0,
      "grad_norm": 2.311486468897783e-06,
      "learning_rate": 2.5747980112163605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5496016,
      "step": 19620
    },
    {
      "epoch": 218.05555555555554,
      "grad_norm": 5.70345491723856e-07,
      "learning_rate": 2.5738166972783656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5497424,
      "step": 19625
    },
    {
      "epoch": 218.11111111111111,
      "grad_norm": 5.543537326957448e-07,
      "learning_rate": 2.5728353719569075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5498784,
      "step": 19630
    },
    {
      "epoch": 218.16666666666666,
      "grad_norm": 1.0134441481568501e-06,
      "learning_rate": 2.57185403540332e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5500176,
      "step": 19635
    },
    {
      "epoch": 218.22222222222223,
      "grad_norm": 1.0241876680083806e-06,
      "learning_rate": 2.5708726877689375e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5501584,
      "step": 19640
    },
    {
      "epoch": 218.27777777777777,
      "grad_norm": 4.715832062629488e-07,
      "learning_rate": 2.5698913292050964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5502992,
      "step": 19645
    },
    {
      "epoch": 218.33333333333334,
      "grad_norm": 1.1062160183428205e-06,
      "learning_rate": 2.568909959863133e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5504416,
      "step": 19650
    },
    {
      "epoch": 218.38888888888889,
      "grad_norm": 6.373712153617817e-07,
      "learning_rate": 2.5679285798943887e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5505824,
      "step": 19655
    },
    {
      "epoch": 218.44444444444446,
      "grad_norm": 4.3182831177546177e-07,
      "learning_rate": 2.5669471894502035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5507200,
      "step": 19660
    },
    {
      "epoch": 218.5,
      "grad_norm": 6.302609563135775e-07,
      "learning_rate": 2.56596578868192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5508544,
      "step": 19665
    },
    {
      "epoch": 218.55555555555554,
      "grad_norm": 1.0295055972164846e-06,
      "learning_rate": 2.564984377740883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5509936,
      "step": 19670
    },
    {
      "epoch": 218.61111111111111,
      "grad_norm": 4.769266297444119e-07,
      "learning_rate": 2.564002956778438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5511360,
      "step": 19675
    },
    {
      "epoch": 218.66666666666666,
      "grad_norm": 1.7525576367916074e-06,
      "learning_rate": 2.563021525945934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5512800,
      "step": 19680
    },
    {
      "epoch": 218.72222222222223,
      "grad_norm": 5.753271352659795e-07,
      "learning_rate": 2.562040085394718e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5514192,
      "step": 19685
    },
    {
      "epoch": 218.77777777777777,
      "grad_norm": 5.439883352664765e-07,
      "learning_rate": 2.56105863527614e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5515600,
      "step": 19690
    },
    {
      "epoch": 218.83333333333334,
      "grad_norm": 5.440979293780401e-07,
      "learning_rate": 2.5600771757415548e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5516992,
      "step": 19695
    },
    {
      "epoch": 218.88888888888889,
      "grad_norm": 2.3860841338319005e-06,
      "learning_rate": 2.5590957069423134e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5518448,
      "step": 19700
    },
    {
      "epoch": 218.94444444444446,
      "grad_norm": 5.464478931571648e-07,
      "learning_rate": 2.5581142290297716e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5519856,
      "step": 19705
    },
    {
      "epoch": 219.0,
      "grad_norm": 5.358979819902743e-07,
      "learning_rate": 2.557132742155285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5521264,
      "step": 19710
    },
    {
      "epoch": 219.05555555555554,
      "grad_norm": 5.214847078605089e-07,
      "learning_rate": 2.556151246470212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5522688,
      "step": 19715
    },
    {
      "epoch": 219.11111111111111,
      "grad_norm": 4.939776090395753e-07,
      "learning_rate": 2.5551697421259114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5524144,
      "step": 19720
    },
    {
      "epoch": 219.16666666666666,
      "grad_norm": 2.859328105841996e-06,
      "learning_rate": 2.554188229273743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5525520,
      "step": 19725
    },
    {
      "epoch": 219.22222222222223,
      "grad_norm": 1.1012102731911e-06,
      "learning_rate": 2.5532067080650678e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5526928,
      "step": 19730
    },
    {
      "epoch": 219.27777777777777,
      "grad_norm": 3.769551426557882e-07,
      "learning_rate": 2.55222517865125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5528352,
      "step": 19735
    },
    {
      "epoch": 219.33333333333334,
      "grad_norm": 5.387488499764004e-07,
      "learning_rate": 2.5512436411836538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5529712,
      "step": 19740
    },
    {
      "epoch": 219.38888888888889,
      "grad_norm": 5.316790634424251e-07,
      "learning_rate": 2.5502620958136443e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5531120,
      "step": 19745
    },
    {
      "epoch": 219.44444444444446,
      "grad_norm": 1.0035929562945967e-06,
      "learning_rate": 2.5492805426925874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5532528,
      "step": 19750
    },
    {
      "epoch": 219.5,
      "grad_norm": 5.008486709812132e-07,
      "learning_rate": 2.5482989819718523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5533888,
      "step": 19755
    },
    {
      "epoch": 219.55555555555554,
      "grad_norm": 5.26550650192803e-07,
      "learning_rate": 2.5473174138028065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5535248,
      "step": 19760
    },
    {
      "epoch": 219.61111111111111,
      "grad_norm": 4.842926841774897e-07,
      "learning_rate": 2.5463358383368212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5536624,
      "step": 19765
    },
    {
      "epoch": 219.66666666666666,
      "grad_norm": 6.310509093054861e-07,
      "learning_rate": 2.545354255725267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5538064,
      "step": 19770
    },
    {
      "epoch": 219.72222222222223,
      "grad_norm": 5.461288878905179e-07,
      "learning_rate": 2.5443726661195165e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5539488,
      "step": 19775
    },
    {
      "epoch": 219.77777777777777,
      "grad_norm": 2.298979097759002e-06,
      "learning_rate": 2.543391069670944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5540864,
      "step": 19780
    },
    {
      "epoch": 219.83333333333334,
      "grad_norm": 5.584204814113036e-07,
      "learning_rate": 2.5424094665309228e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5542272,
      "step": 19785
    },
    {
      "epoch": 219.88888888888889,
      "grad_norm": 1.7122118833867717e-06,
      "learning_rate": 2.5414278568508292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5543696,
      "step": 19790
    },
    {
      "epoch": 219.94444444444446,
      "grad_norm": 4.900757630821317e-07,
      "learning_rate": 2.540446240782039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5545072,
      "step": 19795
    },
    {
      "epoch": 220.0,
      "grad_norm": 5.920857120145229e-07,
      "learning_rate": 2.5394646184759307e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5546432,
      "step": 19800
    },
    {
      "epoch": 220.0,
      "eval_loss": 0.360029011964798,
      "eval_runtime": 1.2805,
      "eval_samples_per_second": 31.237,
      "eval_steps_per_second": 15.619,
      "num_input_tokens_seen": 5546432,
      "step": 19800
    },
    {
      "epoch": 220.05555555555554,
      "grad_norm": 5.290335138852242e-07,
      "learning_rate": 2.538482990083882e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5547824,
      "step": 19805
    },
    {
      "epoch": 220.11111111111111,
      "grad_norm": 2.4425903575320262e-06,
      "learning_rate": 2.5375013557572725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5549216,
      "step": 19810
    },
    {
      "epoch": 220.16666666666666,
      "grad_norm": 4.723395647943107e-07,
      "learning_rate": 2.536519715647483e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5550608,
      "step": 19815
    },
    {
      "epoch": 220.22222222222223,
      "grad_norm": 5.688248734259105e-07,
      "learning_rate": 2.535538069905894e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5552032,
      "step": 19820
    },
    {
      "epoch": 220.27777777777777,
      "grad_norm": 4.831359774470911e-07,
      "learning_rate": 2.534556418683888e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5553472,
      "step": 19825
    },
    {
      "epoch": 220.33333333333334,
      "grad_norm": 2.442603090457851e-06,
      "learning_rate": 2.5335747621328486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5554864,
      "step": 19830
    },
    {
      "epoch": 220.38888888888889,
      "grad_norm": 3.141565457553952e-06,
      "learning_rate": 2.5325931004041586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5556288,
      "step": 19835
    },
    {
      "epoch": 220.44444444444446,
      "grad_norm": 5.491162937687477e-07,
      "learning_rate": 2.5316114336492032e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5557648,
      "step": 19840
    },
    {
      "epoch": 220.5,
      "grad_norm": 5.738312438552384e-07,
      "learning_rate": 2.530629762019367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5559024,
      "step": 19845
    },
    {
      "epoch": 220.55555555555554,
      "grad_norm": 4.3693856355275784e-07,
      "learning_rate": 2.5296480856660364e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5560432,
      "step": 19850
    },
    {
      "epoch": 220.61111111111111,
      "grad_norm": 1.1213909374419018e-06,
      "learning_rate": 2.528666404740599e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5561856,
      "step": 19855
    },
    {
      "epoch": 220.66666666666666,
      "grad_norm": 4.768897952089901e-07,
      "learning_rate": 2.527684719394442e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5563280,
      "step": 19860
    },
    {
      "epoch": 220.72222222222223,
      "grad_norm": 5.890727834412246e-07,
      "learning_rate": 2.526703029778953e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5564688,
      "step": 19865
    },
    {
      "epoch": 220.77777777777777,
      "grad_norm": 4.934540811518673e-07,
      "learning_rate": 2.5257213360455208e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5566048,
      "step": 19870
    },
    {
      "epoch": 220.83333333333334,
      "grad_norm": 2.1272160211083246e-06,
      "learning_rate": 2.5247396383455353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5567440,
      "step": 19875
    },
    {
      "epoch": 220.88888888888889,
      "grad_norm": 6.310788762675656e-07,
      "learning_rate": 2.523757936830387e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5568800,
      "step": 19880
    },
    {
      "epoch": 220.94444444444446,
      "grad_norm": 5.109313292450679e-07,
      "learning_rate": 2.5227762316514662e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5570240,
      "step": 19885
    },
    {
      "epoch": 221.0,
      "grad_norm": 9.65960452958825e-07,
      "learning_rate": 2.5217945229601648e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5571632,
      "step": 19890
    },
    {
      "epoch": 221.05555555555554,
      "grad_norm": 5.418909267973504e-07,
      "learning_rate": 2.5208128109078738e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5573056,
      "step": 19895
    },
    {
      "epoch": 221.11111111111111,
      "grad_norm": 5.97791142809001e-07,
      "learning_rate": 2.5198310956459853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5574448,
      "step": 19900
    },
    {
      "epoch": 221.16666666666666,
      "grad_norm": 4.781996949532186e-07,
      "learning_rate": 2.518849377325893e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5575824,
      "step": 19905
    },
    {
      "epoch": 221.22222222222223,
      "grad_norm": 4.850081722906907e-07,
      "learning_rate": 2.51786765609899e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5577232,
      "step": 19910
    },
    {
      "epoch": 221.27777777777777,
      "grad_norm": 4.749795152747538e-07,
      "learning_rate": 2.5168859321166694e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5578592,
      "step": 19915
    },
    {
      "epoch": 221.33333333333334,
      "grad_norm": 5.139966674505558e-07,
      "learning_rate": 2.515904205530326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5580016,
      "step": 19920
    },
    {
      "epoch": 221.38888888888889,
      "grad_norm": 1.1167466027472983e-06,
      "learning_rate": 2.514922476491355e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5581376,
      "step": 19925
    },
    {
      "epoch": 221.44444444444446,
      "grad_norm": 5.213963163441804e-07,
      "learning_rate": 2.51394074515115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5582768,
      "step": 19930
    },
    {
      "epoch": 221.5,
      "grad_norm": 5.048426032772113e-07,
      "learning_rate": 2.5129590116611067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5584128,
      "step": 19935
    },
    {
      "epoch": 221.55555555555554,
      "grad_norm": 8.978684604699083e-07,
      "learning_rate": 2.5119772761726212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5585568,
      "step": 19940
    },
    {
      "epoch": 221.61111111111111,
      "grad_norm": 6.45727766368509e-07,
      "learning_rate": 2.5109955388370893e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5586928,
      "step": 19945
    },
    {
      "epoch": 221.66666666666666,
      "grad_norm": 2.0265949842723785e-06,
      "learning_rate": 2.510013799805907e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5588304,
      "step": 19950
    },
    {
      "epoch": 221.72222222222223,
      "grad_norm": 9.431008152205322e-07,
      "learning_rate": 2.5090320592304706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5589776,
      "step": 19955
    },
    {
      "epoch": 221.77777777777777,
      "grad_norm": 5.133676381774421e-07,
      "learning_rate": 2.5080503172621777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5591168,
      "step": 19960
    },
    {
      "epoch": 221.83333333333334,
      "grad_norm": 4.1863114574880456e-07,
      "learning_rate": 2.5070685740524246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5592608,
      "step": 19965
    },
    {
      "epoch": 221.88888888888889,
      "grad_norm": 5.125064603817009e-07,
      "learning_rate": 2.5060868297526084e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5594000,
      "step": 19970
    },
    {
      "epoch": 221.94444444444446,
      "grad_norm": 4.591834112943616e-07,
      "learning_rate": 2.5051050845141267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5595424,
      "step": 19975
    },
    {
      "epoch": 222.0,
      "grad_norm": 2.3185693862615153e-06,
      "learning_rate": 2.5041233384883765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5596832,
      "step": 19980
    },
    {
      "epoch": 222.05555555555554,
      "grad_norm": 6.08024379289418e-07,
      "learning_rate": 2.5031415918267564e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5598256,
      "step": 19985
    },
    {
      "epoch": 222.11111111111111,
      "grad_norm": 9.22231379263394e-07,
      "learning_rate": 2.5021598446806626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5599648,
      "step": 19990
    },
    {
      "epoch": 222.16666666666666,
      "grad_norm": 5.752280003434862e-07,
      "learning_rate": 2.5011780972014937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5601040,
      "step": 19995
    },
    {
      "epoch": 222.22222222222223,
      "grad_norm": 3.5962837046099594e-06,
      "learning_rate": 2.5001963495406478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5602400,
      "step": 20000
    },
    {
      "epoch": 222.22222222222223,
      "eval_loss": 0.40143242478370667,
      "eval_runtime": 1.2884,
      "eval_samples_per_second": 31.045,
      "eval_steps_per_second": 15.523,
      "num_input_tokens_seen": 5602400,
      "step": 20000
    },
    {
      "epoch": 222.27777777777777,
      "grad_norm": 6.088624218136829e-07,
      "learning_rate": 2.499214601849522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5603824,
      "step": 20005
    },
    {
      "epoch": 222.33333333333334,
      "grad_norm": 4.6428382916019473e-07,
      "learning_rate": 2.4982328542795148e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5605232,
      "step": 20010
    },
    {
      "epoch": 222.38888888888889,
      "grad_norm": 3.778107156904298e-06,
      "learning_rate": 2.497251106982024e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5606608,
      "step": 20015
    },
    {
      "epoch": 222.44444444444446,
      "grad_norm": 3.300753803614498e-07,
      "learning_rate": 2.4962693601084458e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5607984,
      "step": 20020
    },
    {
      "epoch": 222.5,
      "grad_norm": 5.018493993702577e-07,
      "learning_rate": 2.4952876138101794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5609392,
      "step": 20025
    },
    {
      "epoch": 222.55555555555554,
      "grad_norm": 1.1131311339340755e-06,
      "learning_rate": 2.4943058682386233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5610800,
      "step": 20030
    },
    {
      "epoch": 222.61111111111111,
      "grad_norm": 3.612372552197485e-07,
      "learning_rate": 2.493324123545173e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5612224,
      "step": 20035
    },
    {
      "epoch": 222.66666666666666,
      "grad_norm": 6.563456622643571e-07,
      "learning_rate": 2.4923423798812272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5613664,
      "step": 20040
    },
    {
      "epoch": 222.72222222222223,
      "grad_norm": 6.375759085130994e-07,
      "learning_rate": 2.4913606373981825e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5615056,
      "step": 20045
    },
    {
      "epoch": 222.77777777777777,
      "grad_norm": 8.983145676211279e-07,
      "learning_rate": 2.4903788962474357e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5616480,
      "step": 20050
    },
    {
      "epoch": 222.83333333333334,
      "grad_norm": 4.4657963371719234e-07,
      "learning_rate": 2.489397156580385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5617856,
      "step": 20055
    },
    {
      "epoch": 222.88888888888889,
      "grad_norm": 4.2969722358066065e-07,
      "learning_rate": 2.4884154185484246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5619264,
      "step": 20060
    },
    {
      "epoch": 222.94444444444446,
      "grad_norm": 1.0672516737031401e-06,
      "learning_rate": 2.4874336823029526e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5620640,
      "step": 20065
    },
    {
      "epoch": 223.0,
      "grad_norm": 5.577585966420884e-07,
      "learning_rate": 2.4864519479953656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5622016,
      "step": 20070
    },
    {
      "epoch": 223.05555555555554,
      "grad_norm": 6.412968787117279e-07,
      "learning_rate": 2.485470215777058e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5623440,
      "step": 20075
    },
    {
      "epoch": 223.11111111111111,
      "grad_norm": 2.240837375211413e-06,
      "learning_rate": 2.4844884857994258e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5624848,
      "step": 20080
    },
    {
      "epoch": 223.16666666666666,
      "grad_norm": 6.04971717166336e-07,
      "learning_rate": 2.4835067582138638e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5626272,
      "step": 20085
    },
    {
      "epoch": 223.22222222222223,
      "grad_norm": 5.08123662257276e-07,
      "learning_rate": 2.4825250331717666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5627680,
      "step": 20090
    },
    {
      "epoch": 223.27777777777777,
      "grad_norm": 4.751894948640256e-07,
      "learning_rate": 2.4815433108245298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5629136,
      "step": 20095
    },
    {
      "epoch": 223.33333333333334,
      "grad_norm": 9.444991064810893e-07,
      "learning_rate": 2.4805615913235456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5630560,
      "step": 20100
    },
    {
      "epoch": 223.38888888888889,
      "grad_norm": 6.032045121173724e-07,
      "learning_rate": 2.479579874820208e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5632016,
      "step": 20105
    },
    {
      "epoch": 223.44444444444446,
      "grad_norm": 1.7531750700072735e-06,
      "learning_rate": 2.4785981614659115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5633392,
      "step": 20110
    },
    {
      "epoch": 223.5,
      "grad_norm": 6.196261210789089e-07,
      "learning_rate": 2.477616451412047e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5634752,
      "step": 20115
    },
    {
      "epoch": 223.55555555555554,
      "grad_norm": 4.4964599510421976e-07,
      "learning_rate": 2.476634744810007e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5636128,
      "step": 20120
    },
    {
      "epoch": 223.61111111111111,
      "grad_norm": 3.634979975686292e-06,
      "learning_rate": 2.475653041811183e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5637520,
      "step": 20125
    },
    {
      "epoch": 223.66666666666666,
      "grad_norm": 5.749721481151937e-07,
      "learning_rate": 2.4746713425669652e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5638912,
      "step": 20130
    },
    {
      "epoch": 223.72222222222223,
      "grad_norm": 9.932515467880876e-07,
      "learning_rate": 2.4736896472287458e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5640336,
      "step": 20135
    },
    {
      "epoch": 223.77777777777777,
      "grad_norm": 4.7260303404073056e-07,
      "learning_rate": 2.4727079559479124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5641728,
      "step": 20140
    },
    {
      "epoch": 223.83333333333334,
      "grad_norm": 1.0127312179974979e-06,
      "learning_rate": 2.4717262688758557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5643136,
      "step": 20145
    },
    {
      "epoch": 223.88888888888889,
      "grad_norm": 4.558215209726768e-07,
      "learning_rate": 2.4707445861639637e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5644512,
      "step": 20150
    },
    {
      "epoch": 223.94444444444446,
      "grad_norm": 5.802363034490554e-07,
      "learning_rate": 2.4697629079636244e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5645872,
      "step": 20155
    },
    {
      "epoch": 224.0,
      "grad_norm": 2.223530600531376e-06,
      "learning_rate": 2.4687812344262244e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5647264,
      "step": 20160
    },
    {
      "epoch": 224.05555555555554,
      "grad_norm": 4.712917132110306e-07,
      "learning_rate": 2.46779956570315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5648640,
      "step": 20165
    },
    {
      "epoch": 224.11111111111111,
      "grad_norm": 5.007754566577205e-07,
      "learning_rate": 2.466817901945787e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5650064,
      "step": 20170
    },
    {
      "epoch": 224.16666666666666,
      "grad_norm": 3.0485286970360903e-06,
      "learning_rate": 2.4658362433055217e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5651456,
      "step": 20175
    },
    {
      "epoch": 224.22222222222223,
      "grad_norm": 5.699322969121567e-07,
      "learning_rate": 2.4648545899337356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5652880,
      "step": 20180
    },
    {
      "epoch": 224.27777777777777,
      "grad_norm": 6.036722197677591e-07,
      "learning_rate": 2.4638729419818143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5654224,
      "step": 20185
    },
    {
      "epoch": 224.33333333333334,
      "grad_norm": 2.0149659576418344e-06,
      "learning_rate": 2.46289129960114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5655664,
      "step": 20190
    },
    {
      "epoch": 224.38888888888889,
      "grad_norm": 4.4460909975896357e-07,
      "learning_rate": 2.4619096629430924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5657072,
      "step": 20195
    },
    {
      "epoch": 224.44444444444446,
      "grad_norm": 5.099016107124044e-07,
      "learning_rate": 2.4609280321590543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5658464,
      "step": 20200
    },
    {
      "epoch": 224.44444444444446,
      "eval_loss": 0.3992190957069397,
      "eval_runtime": 1.2962,
      "eval_samples_per_second": 30.859,
      "eval_steps_per_second": 15.43,
      "num_input_tokens_seen": 5658464,
      "step": 20200
    },
    {
      "epoch": 224.5,
      "grad_norm": 4.4186140257806983e-07,
      "learning_rate": 2.4599464074004037e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5659888,
      "step": 20205
    },
    {
      "epoch": 224.55555555555554,
      "grad_norm": 5.775763156634639e-07,
      "learning_rate": 2.4589647888185204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5661280,
      "step": 20210
    },
    {
      "epoch": 224.61111111111111,
      "grad_norm": 5.2007517297170125e-06,
      "learning_rate": 2.4579831765647836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5662624,
      "step": 20215
    },
    {
      "epoch": 224.66666666666666,
      "grad_norm": 5.323399818735197e-07,
      "learning_rate": 2.4570015707905676e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5664064,
      "step": 20220
    },
    {
      "epoch": 224.72222222222223,
      "grad_norm": 5.954137805019855e-07,
      "learning_rate": 2.4560199716472508e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5665472,
      "step": 20225
    },
    {
      "epoch": 224.77777777777777,
      "grad_norm": 1.7102414631153806e-06,
      "learning_rate": 2.455038379286207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5666880,
      "step": 20230
    },
    {
      "epoch": 224.83333333333334,
      "grad_norm": 6.721548970745062e-07,
      "learning_rate": 2.4540567938588095e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5668272,
      "step": 20235
    },
    {
      "epoch": 224.88888888888889,
      "grad_norm": 4.414271472796827e-07,
      "learning_rate": 2.4530752155164328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5669648,
      "step": 20240
    },
    {
      "epoch": 224.94444444444446,
      "grad_norm": 1.120529191211972e-06,
      "learning_rate": 2.4520936444104463e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5671056,
      "step": 20245
    },
    {
      "epoch": 225.0,
      "grad_norm": 6.511739911729819e-07,
      "learning_rate": 2.4511120806922218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5672432,
      "step": 20250
    },
    {
      "epoch": 225.05555555555554,
      "grad_norm": 5.409847290138714e-07,
      "learning_rate": 2.45013052451313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5673776,
      "step": 20255
    },
    {
      "epoch": 225.11111111111111,
      "grad_norm": 5.068902737548342e-07,
      "learning_rate": 2.4491489760245376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5675120,
      "step": 20260
    },
    {
      "epoch": 225.16666666666666,
      "grad_norm": 1.077134925253631e-06,
      "learning_rate": 2.4481674353778115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5676496,
      "step": 20265
    },
    {
      "epoch": 225.22222222222223,
      "grad_norm": 1.0051376193587203e-06,
      "learning_rate": 2.447185902724319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5677888,
      "step": 20270
    },
    {
      "epoch": 225.27777777777777,
      "grad_norm": 5.225107884143654e-07,
      "learning_rate": 2.4462043782154233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5679280,
      "step": 20275
    },
    {
      "epoch": 225.33333333333334,
      "grad_norm": 5.589668035099749e-07,
      "learning_rate": 2.4452228620024895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5680688,
      "step": 20280
    },
    {
      "epoch": 225.38888888888889,
      "grad_norm": 5.505454510057461e-07,
      "learning_rate": 2.4442413542368776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5682144,
      "step": 20285
    },
    {
      "epoch": 225.44444444444446,
      "grad_norm": 6.353217258947552e-07,
      "learning_rate": 2.4432598550699502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5683584,
      "step": 20290
    },
    {
      "epoch": 225.5,
      "grad_norm": 6.601011364182341e-07,
      "learning_rate": 2.4422783646530663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5684992,
      "step": 20295
    },
    {
      "epoch": 225.55555555555554,
      "grad_norm": 6.214552854544309e-07,
      "learning_rate": 2.441296883137584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5686416,
      "step": 20300
    },
    {
      "epoch": 225.61111111111111,
      "grad_norm": 4.7593746899110556e-07,
      "learning_rate": 2.4403154106748592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5687808,
      "step": 20305
    },
    {
      "epoch": 225.66666666666666,
      "grad_norm": 5.042170414526481e-07,
      "learning_rate": 2.4393339474162494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5689216,
      "step": 20310
    },
    {
      "epoch": 225.72222222222223,
      "grad_norm": 5.473344799611368e-07,
      "learning_rate": 2.4383524935131062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5690592,
      "step": 20315
    },
    {
      "epoch": 225.77777777777777,
      "grad_norm": 5.193619472265709e-06,
      "learning_rate": 2.437371049116784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5692016,
      "step": 20320
    },
    {
      "epoch": 225.83333333333334,
      "grad_norm": 5.355569783205283e-07,
      "learning_rate": 2.436389614378632e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5693440,
      "step": 20325
    },
    {
      "epoch": 225.88888888888889,
      "grad_norm": 5.360313934943406e-07,
      "learning_rate": 2.435408189450002e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5694800,
      "step": 20330
    },
    {
      "epoch": 225.94444444444446,
      "grad_norm": 6.004369765832962e-07,
      "learning_rate": 2.4344267744822406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5696208,
      "step": 20335
    },
    {
      "epoch": 226.0,
      "grad_norm": 2.325195055163931e-06,
      "learning_rate": 2.4334453696266944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5697600,
      "step": 20340
    },
    {
      "epoch": 226.05555555555554,
      "grad_norm": 5.935461899753136e-07,
      "learning_rate": 2.432463975034708e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5698928,
      "step": 20345
    },
    {
      "epoch": 226.11111111111111,
      "grad_norm": 2.2738922780263238e-06,
      "learning_rate": 2.4314825908576265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5700288,
      "step": 20350
    },
    {
      "epoch": 226.16666666666666,
      "grad_norm": 4.986722501598706e-07,
      "learning_rate": 2.4305012172467897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5701648,
      "step": 20355
    },
    {
      "epoch": 226.22222222222223,
      "grad_norm": 4.84601287098485e-07,
      "learning_rate": 2.4295198543535393e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5703040,
      "step": 20360
    },
    {
      "epoch": 226.27777777777777,
      "grad_norm": 5.720079343518591e-07,
      "learning_rate": 2.4285385023292124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5704464,
      "step": 20365
    },
    {
      "epoch": 226.33333333333334,
      "grad_norm": 3.5822724839817965e-06,
      "learning_rate": 2.427557161325147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5705824,
      "step": 20370
    },
    {
      "epoch": 226.38888888888889,
      "grad_norm": 5.254329380477429e-07,
      "learning_rate": 2.4265758314926778e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5707280,
      "step": 20375
    },
    {
      "epoch": 226.44444444444446,
      "grad_norm": 2.067205514322268e-06,
      "learning_rate": 2.4255945129831373e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5708752,
      "step": 20380
    },
    {
      "epoch": 226.5,
      "grad_norm": 5.096897552903101e-07,
      "learning_rate": 2.4246132059478578e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5710144,
      "step": 20385
    },
    {
      "epoch": 226.55555555555554,
      "grad_norm": 5.32758463123173e-07,
      "learning_rate": 2.4236319105381706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5711536,
      "step": 20390
    },
    {
      "epoch": 226.61111111111111,
      "grad_norm": 7.054863999655936e-07,
      "learning_rate": 2.422650626905401e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5712928,
      "step": 20395
    },
    {
      "epoch": 226.66666666666666,
      "grad_norm": 2.039801756836823e-06,
      "learning_rate": 2.4216693552008785e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5714352,
      "step": 20400
    },
    {
      "epoch": 226.66666666666666,
      "eval_loss": 0.38984403014183044,
      "eval_runtime": 1.2889,
      "eval_samples_per_second": 31.033,
      "eval_steps_per_second": 15.517,
      "num_input_tokens_seen": 5714352,
      "step": 20400
    },
    {
      "epoch": 226.72222222222223,
      "grad_norm": 5.954615858172474e-07,
      "learning_rate": 2.4206880955759247e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5715696,
      "step": 20405
    },
    {
      "epoch": 226.77777777777777,
      "grad_norm": 4.923340952700528e-07,
      "learning_rate": 2.419706848181863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5717120,
      "step": 20410
    },
    {
      "epoch": 226.83333333333334,
      "grad_norm": 6.074964176150388e-07,
      "learning_rate": 2.4187256131700153e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5718512,
      "step": 20415
    },
    {
      "epoch": 226.88888888888889,
      "grad_norm": 4.778087827617128e-07,
      "learning_rate": 2.4177443906916985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5719968,
      "step": 20420
    },
    {
      "epoch": 226.94444444444446,
      "grad_norm": 5.01481338233134e-07,
      "learning_rate": 2.4167631808982303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5721376,
      "step": 20425
    },
    {
      "epoch": 227.0,
      "grad_norm": 5.40193866527261e-07,
      "learning_rate": 2.4157819839409264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5722784,
      "step": 20430
    },
    {
      "epoch": 227.05555555555554,
      "grad_norm": 9.698233043309301e-07,
      "learning_rate": 2.414800799971098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5724144,
      "step": 20435
    },
    {
      "epoch": 227.11111111111111,
      "grad_norm": 1.6144218761837692e-06,
      "learning_rate": 2.4138196291400582e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5725584,
      "step": 20440
    },
    {
      "epoch": 227.16666666666666,
      "grad_norm": 4.264219057859009e-07,
      "learning_rate": 2.412838471599114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5726976,
      "step": 20445
    },
    {
      "epoch": 227.22222222222223,
      "grad_norm": 5.130775093675766e-07,
      "learning_rate": 2.411857327499572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5728416,
      "step": 20450
    },
    {
      "epoch": 227.27777777777777,
      "grad_norm": 5.600118129223119e-07,
      "learning_rate": 2.410876196992739e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5729856,
      "step": 20455
    },
    {
      "epoch": 227.33333333333334,
      "grad_norm": 1.152946083493589e-06,
      "learning_rate": 2.4098950802299156e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5731232,
      "step": 20460
    },
    {
      "epoch": 227.38888888888889,
      "grad_norm": 6.061216595298902e-07,
      "learning_rate": 2.4089139773624027e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5732640,
      "step": 20465
    },
    {
      "epoch": 227.44444444444446,
      "grad_norm": 6.613136065425351e-07,
      "learning_rate": 2.4079328885415007e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5734032,
      "step": 20470
    },
    {
      "epoch": 227.5,
      "grad_norm": 4.6632328576379223e-07,
      "learning_rate": 2.4069518139185036e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5735456,
      "step": 20475
    },
    {
      "epoch": 227.55555555555554,
      "grad_norm": 2.087573420794797e-06,
      "learning_rate": 2.405970753644706e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5736800,
      "step": 20480
    },
    {
      "epoch": 227.61111111111111,
      "grad_norm": 1.7068375655071577e-06,
      "learning_rate": 2.4049897078714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5738256,
      "step": 20485
    },
    {
      "epoch": 227.66666666666666,
      "grad_norm": 5.829331257700687e-07,
      "learning_rate": 2.404008676749874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5739632,
      "step": 20490
    },
    {
      "epoch": 227.72222222222223,
      "grad_norm": 4.78005119930458e-07,
      "learning_rate": 2.403027660431418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5741024,
      "step": 20495
    },
    {
      "epoch": 227.77777777777777,
      "grad_norm": 9.384825716551859e-07,
      "learning_rate": 2.402046659067314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5742416,
      "step": 20500
    },
    {
      "epoch": 227.83333333333334,
      "grad_norm": 1.5519913176831324e-06,
      "learning_rate": 2.401065672808847e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5743776,
      "step": 20505
    },
    {
      "epoch": 227.88888888888889,
      "grad_norm": 5.44860426998639e-07,
      "learning_rate": 2.400084701807296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5745184,
      "step": 20510
    },
    {
      "epoch": 227.94444444444446,
      "grad_norm": 1.4924466995580588e-06,
      "learning_rate": 2.39910374621394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5746592,
      "step": 20515
    },
    {
      "epoch": 228.0,
      "grad_norm": 5.588955218627234e-07,
      "learning_rate": 2.3981228061800544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5748000,
      "step": 20520
    },
    {
      "epoch": 228.05555555555554,
      "grad_norm": 9.999987469200278e-07,
      "learning_rate": 2.3971418818569115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5749424,
      "step": 20525
    },
    {
      "epoch": 228.11111111111111,
      "grad_norm": 1.0447975000715815e-06,
      "learning_rate": 2.3961609733957832e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5750864,
      "step": 20530
    },
    {
      "epoch": 228.16666666666666,
      "grad_norm": 5.124262543176883e-07,
      "learning_rate": 2.395180080947939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5752288,
      "step": 20535
    },
    {
      "epoch": 228.22222222222223,
      "grad_norm": 1.0692682508306461e-06,
      "learning_rate": 2.394199204664642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5753680,
      "step": 20540
    },
    {
      "epoch": 228.27777777777777,
      "grad_norm": 9.269267593481345e-07,
      "learning_rate": 2.3932183446971583e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5755072,
      "step": 20545
    },
    {
      "epoch": 228.33333333333334,
      "grad_norm": 5.58111992177146e-07,
      "learning_rate": 2.3922375011967473e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5756464,
      "step": 20550
    },
    {
      "epoch": 228.38888888888889,
      "grad_norm": 2.3781251456966856e-06,
      "learning_rate": 2.3912566743146676e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5757856,
      "step": 20555
    },
    {
      "epoch": 228.44444444444446,
      "grad_norm": 1.7068473425752018e-06,
      "learning_rate": 2.390275864202176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5759264,
      "step": 20560
    },
    {
      "epoch": 228.5,
      "grad_norm": 4.6707236833753996e-07,
      "learning_rate": 2.3892950710105243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5760640,
      "step": 20565
    },
    {
      "epoch": 228.55555555555554,
      "grad_norm": 3.0326875730679603e-06,
      "learning_rate": 2.3883142948909635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5761984,
      "step": 20570
    },
    {
      "epoch": 228.61111111111111,
      "grad_norm": 5.11068492414779e-07,
      "learning_rate": 2.3873335359947433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5763408,
      "step": 20575
    },
    {
      "epoch": 228.66666666666666,
      "grad_norm": 1.519058400845097e-06,
      "learning_rate": 2.3863527944731066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5764816,
      "step": 20580
    },
    {
      "epoch": 228.72222222222223,
      "grad_norm": 1.701887413219083e-06,
      "learning_rate": 2.385372070477298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5766240,
      "step": 20585
    },
    {
      "epoch": 228.77777777777777,
      "grad_norm": 4.7319110763055505e-07,
      "learning_rate": 2.384391364158556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5767600,
      "step": 20590
    },
    {
      "epoch": 228.83333333333334,
      "grad_norm": 5.636853188661917e-07,
      "learning_rate": 2.3834106756681185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5768992,
      "step": 20595
    },
    {
      "epoch": 228.88888888888889,
      "grad_norm": 5.197459245209757e-07,
      "learning_rate": 2.3824300051572206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5770416,
      "step": 20600
    },
    {
      "epoch": 228.88888888888889,
      "eval_loss": 0.3507901728153229,
      "eval_runtime": 1.2944,
      "eval_samples_per_second": 30.903,
      "eval_steps_per_second": 15.451,
      "num_input_tokens_seen": 5770416,
      "step": 20600
    },
    {
      "epoch": 228.94444444444446,
      "grad_norm": 1.064251364368829e-06,
      "learning_rate": 2.3814493527770923e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5771888,
      "step": 20605
    },
    {
      "epoch": 229.0,
      "grad_norm": 5.34818752839783e-07,
      "learning_rate": 2.3804687186789637e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5773312,
      "step": 20610
    },
    {
      "epoch": 229.05555555555554,
      "grad_norm": 1.5566807860523113e-06,
      "learning_rate": 2.379488103014062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5774688,
      "step": 20615
    },
    {
      "epoch": 229.11111111111111,
      "grad_norm": 5.912060601076519e-07,
      "learning_rate": 2.3785075059336086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5776096,
      "step": 20620
    },
    {
      "epoch": 229.16666666666666,
      "grad_norm": 1.760918962645519e-06,
      "learning_rate": 2.3775269275888248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5777536,
      "step": 20625
    },
    {
      "epoch": 229.22222222222223,
      "grad_norm": 4.727686189198721e-07,
      "learning_rate": 2.3765463681309274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5778912,
      "step": 20630
    },
    {
      "epoch": 229.27777777777777,
      "grad_norm": 5.423684683592e-07,
      "learning_rate": 2.3755658277111313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5780320,
      "step": 20635
    },
    {
      "epoch": 229.33333333333334,
      "grad_norm": 4.803784463547345e-07,
      "learning_rate": 2.374585306480649e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5781680,
      "step": 20640
    },
    {
      "epoch": 229.38888888888889,
      "grad_norm": 5.302680392560433e-07,
      "learning_rate": 2.3736048045906877e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5783056,
      "step": 20645
    },
    {
      "epoch": 229.44444444444446,
      "grad_norm": 5.612582185676729e-07,
      "learning_rate": 2.372624322192454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5784448,
      "step": 20650
    },
    {
      "epoch": 229.5,
      "grad_norm": 9.845674640018842e-07,
      "learning_rate": 2.3716438594371516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5785872,
      "step": 20655
    },
    {
      "epoch": 229.55555555555554,
      "grad_norm": 4.3010871308979404e-07,
      "learning_rate": 2.3706634164759784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5787264,
      "step": 20660
    },
    {
      "epoch": 229.61111111111111,
      "grad_norm": 5.478231628330832e-07,
      "learning_rate": 2.3696829934601323e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5788640,
      "step": 20665
    },
    {
      "epoch": 229.66666666666666,
      "grad_norm": 1.6465216958749807e-06,
      "learning_rate": 2.3687025905408053e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5790064,
      "step": 20670
    },
    {
      "epoch": 229.72222222222223,
      "grad_norm": 5.511681138159474e-07,
      "learning_rate": 2.3677222078691886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5791456,
      "step": 20675
    },
    {
      "epoch": 229.77777777777777,
      "grad_norm": 2.133388079528231e-06,
      "learning_rate": 2.366741845596471e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5792816,
      "step": 20680
    },
    {
      "epoch": 229.83333333333334,
      "grad_norm": 5.995597121000174e-07,
      "learning_rate": 2.3657615038738343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5794192,
      "step": 20685
    },
    {
      "epoch": 229.88888888888889,
      "grad_norm": 1.4917745829734486e-06,
      "learning_rate": 2.3647811828524614e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5795648,
      "step": 20690
    },
    {
      "epoch": 229.94444444444446,
      "grad_norm": 1.511280743216048e-06,
      "learning_rate": 2.363800882683529e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5797056,
      "step": 20695
    },
    {
      "epoch": 230.0,
      "grad_norm": 5.583609095083375e-07,
      "learning_rate": 2.3628206035182125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5798464,
      "step": 20700
    },
    {
      "epoch": 230.05555555555554,
      "grad_norm": 2.15754675991775e-06,
      "learning_rate": 2.361840345507683e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5799856,
      "step": 20705
    },
    {
      "epoch": 230.11111111111111,
      "grad_norm": 5.535378022614168e-07,
      "learning_rate": 2.3608601088031073e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5801232,
      "step": 20710
    },
    {
      "epoch": 230.16666666666666,
      "grad_norm": 6.211118375176738e-07,
      "learning_rate": 2.3598798935556516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5802608,
      "step": 20715
    },
    {
      "epoch": 230.22222222222223,
      "grad_norm": 9.743815780893783e-07,
      "learning_rate": 2.3588996999164784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5803984,
      "step": 20720
    },
    {
      "epoch": 230.27777777777777,
      "grad_norm": 4.960523938279948e-07,
      "learning_rate": 2.3579195280367434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5805312,
      "step": 20725
    },
    {
      "epoch": 230.33333333333334,
      "grad_norm": 4.5058004616294056e-07,
      "learning_rate": 2.356939378067603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5806672,
      "step": 20730
    },
    {
      "epoch": 230.38888888888889,
      "grad_norm": 5.457671932163066e-07,
      "learning_rate": 2.3559592501602092e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5808080,
      "step": 20735
    },
    {
      "epoch": 230.44444444444446,
      "grad_norm": 2.09362042369321e-06,
      "learning_rate": 2.3549791444657076e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5809504,
      "step": 20740
    },
    {
      "epoch": 230.5,
      "grad_norm": 3.131505309283966e-06,
      "learning_rate": 2.353999061135246e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5810896,
      "step": 20745
    },
    {
      "epoch": 230.55555555555554,
      "grad_norm": 5.056806458014762e-07,
      "learning_rate": 2.3530190003199626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5812272,
      "step": 20750
    },
    {
      "epoch": 230.61111111111111,
      "grad_norm": 1.540687435408472e-06,
      "learning_rate": 2.3520389621709965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5813664,
      "step": 20755
    },
    {
      "epoch": 230.66666666666666,
      "grad_norm": 6.607342584175058e-07,
      "learning_rate": 2.351058946839483e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5815072,
      "step": 20760
    },
    {
      "epoch": 230.72222222222223,
      "grad_norm": 6.141053745523095e-07,
      "learning_rate": 2.350078954476551e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5816464,
      "step": 20765
    },
    {
      "epoch": 230.77777777777777,
      "grad_norm": 1.678228272794513e-06,
      "learning_rate": 2.3490989852333272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5817888,
      "step": 20770
    },
    {
      "epoch": 230.83333333333334,
      "grad_norm": 4.6028662836761214e-07,
      "learning_rate": 2.3481190392609377e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5819344,
      "step": 20775
    },
    {
      "epoch": 230.88888888888889,
      "grad_norm": 6.013476649968652e-07,
      "learning_rate": 2.3471391167105e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5820784,
      "step": 20780
    },
    {
      "epoch": 230.94444444444446,
      "grad_norm": 1.0044552709587151e-06,
      "learning_rate": 2.3461592177331325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5822192,
      "step": 20785
    },
    {
      "epoch": 231.0,
      "grad_norm": 5.04281615576474e-07,
      "learning_rate": 2.345179342479946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5823648,
      "step": 20790
    },
    {
      "epoch": 231.05555555555554,
      "grad_norm": 4.422725794483995e-07,
      "learning_rate": 2.3441994911020503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5825072,
      "step": 20795
    },
    {
      "epoch": 231.11111111111111,
      "grad_norm": 4.978483048034832e-07,
      "learning_rate": 2.3432196637505522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5826496,
      "step": 20800
    },
    {
      "epoch": 231.11111111111111,
      "eval_loss": 0.37461018562316895,
      "eval_runtime": 1.2908,
      "eval_samples_per_second": 30.988,
      "eval_steps_per_second": 15.494,
      "num_input_tokens_seen": 5826496,
      "step": 20800
    },
    {
      "epoch": 231.16666666666666,
      "grad_norm": 9.623921641832567e-07,
      "learning_rate": 2.3422398605765515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5827840,
      "step": 20805
    },
    {
      "epoch": 231.22222222222223,
      "grad_norm": 2.030489895332721e-06,
      "learning_rate": 2.3412600817311462e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5829232,
      "step": 20810
    },
    {
      "epoch": 231.27777777777777,
      "grad_norm": 1.5221056628433871e-06,
      "learning_rate": 2.3402803273654326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5830656,
      "step": 20815
    },
    {
      "epoch": 231.33333333333334,
      "grad_norm": 5.527311373043631e-07,
      "learning_rate": 2.3393005976304983e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5832016,
      "step": 20820
    },
    {
      "epoch": 231.38888888888889,
      "grad_norm": 2.2923684355191654e-06,
      "learning_rate": 2.338320892677432e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5833424,
      "step": 20825
    },
    {
      "epoch": 231.44444444444446,
      "grad_norm": 1.0650858257577056e-06,
      "learning_rate": 2.3373412126573155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5834864,
      "step": 20830
    },
    {
      "epoch": 231.5,
      "grad_norm": 6.386116524481622e-07,
      "learning_rate": 2.3363615577212285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5836224,
      "step": 20835
    },
    {
      "epoch": 231.55555555555554,
      "grad_norm": 1.0093169748870423e-06,
      "learning_rate": 2.3353819280202455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5837632,
      "step": 20840
    },
    {
      "epoch": 231.61111111111111,
      "grad_norm": 5.701426175619417e-07,
      "learning_rate": 2.334402323705438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5839040,
      "step": 20845
    },
    {
      "epoch": 231.66666666666666,
      "grad_norm": 5.467106234391395e-07,
      "learning_rate": 2.3334227449278725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5840464,
      "step": 20850
    },
    {
      "epoch": 231.72222222222223,
      "grad_norm": 1.6942875618042308e-06,
      "learning_rate": 2.3324431918386143e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5841856,
      "step": 20855
    },
    {
      "epoch": 231.77777777777777,
      "grad_norm": 5.628968438031734e-07,
      "learning_rate": 2.3314636645887207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5843232,
      "step": 20860
    },
    {
      "epoch": 231.83333333333334,
      "grad_norm": 6.16664522112842e-07,
      "learning_rate": 2.3304841633292487e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5844640,
      "step": 20865
    },
    {
      "epoch": 231.88888888888889,
      "grad_norm": 6.156428185022378e-07,
      "learning_rate": 2.329504688211248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5846016,
      "step": 20870
    },
    {
      "epoch": 231.94444444444446,
      "grad_norm": 6.186750738379487e-07,
      "learning_rate": 2.3285252393857677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5847440,
      "step": 20875
    },
    {
      "epoch": 232.0,
      "grad_norm": 5.636558739752218e-07,
      "learning_rate": 2.327545817003851e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5848816,
      "step": 20880
    },
    {
      "epoch": 232.05555555555554,
      "grad_norm": 5.216382987782708e-07,
      "learning_rate": 2.326566421216535e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5850240,
      "step": 20885
    },
    {
      "epoch": 232.11111111111111,
      "grad_norm": 1.4919811519575887e-06,
      "learning_rate": 2.3255870521748565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5851632,
      "step": 20890
    },
    {
      "epoch": 232.16666666666666,
      "grad_norm": 5.887320639885729e-07,
      "learning_rate": 2.3246077100298474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5853008,
      "step": 20895
    },
    {
      "epoch": 232.22222222222223,
      "grad_norm": 4.866090534960676e-07,
      "learning_rate": 2.3236283949325328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5854400,
      "step": 20900
    },
    {
      "epoch": 232.27777777777777,
      "grad_norm": 6.508403771476878e-07,
      "learning_rate": 2.3226491070339368e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5855792,
      "step": 20905
    },
    {
      "epoch": 232.33333333333334,
      "grad_norm": 5.835648266838689e-07,
      "learning_rate": 2.3216698464850762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5857200,
      "step": 20910
    },
    {
      "epoch": 232.38888888888889,
      "grad_norm": 6.149153364276572e-07,
      "learning_rate": 2.320690613436967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5858608,
      "step": 20915
    },
    {
      "epoch": 232.44444444444446,
      "grad_norm": 5.456003577819502e-07,
      "learning_rate": 2.3197114080406192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5860016,
      "step": 20920
    },
    {
      "epoch": 232.5,
      "grad_norm": 5.357998702493205e-07,
      "learning_rate": 2.3187322304470365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5861392,
      "step": 20925
    },
    {
      "epoch": 232.55555555555554,
      "grad_norm": 5.252146593193174e-07,
      "learning_rate": 2.3177530808072222e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5862832,
      "step": 20930
    },
    {
      "epoch": 232.61111111111111,
      "grad_norm": 9.386228043695155e-07,
      "learning_rate": 2.316773959272174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5864192,
      "step": 20935
    },
    {
      "epoch": 232.66666666666666,
      "grad_norm": 5.098771111988754e-07,
      "learning_rate": 2.3157948659928823e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5865616,
      "step": 20940
    },
    {
      "epoch": 232.72222222222223,
      "grad_norm": 1.1503698260639794e-06,
      "learning_rate": 2.3148158011203388e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5867008,
      "step": 20945
    },
    {
      "epoch": 232.77777777777777,
      "grad_norm": 4.80532605706685e-07,
      "learning_rate": 2.3138367648055253e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5868464,
      "step": 20950
    },
    {
      "epoch": 232.83333333333334,
      "grad_norm": 2.4506957743142266e-06,
      "learning_rate": 2.312857757199422e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5869856,
      "step": 20955
    },
    {
      "epoch": 232.88888888888889,
      "grad_norm": 1.0841112043635803e-06,
      "learning_rate": 2.3118787784530048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5871280,
      "step": 20960
    },
    {
      "epoch": 232.94444444444446,
      "grad_norm": 5.93100082824094e-07,
      "learning_rate": 2.310899828717243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5872688,
      "step": 20965
    },
    {
      "epoch": 233.0,
      "grad_norm": 1.6857103446454857e-06,
      "learning_rate": 2.309920908143104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5874080,
      "step": 20970
    },
    {
      "epoch": 233.05555555555554,
      "grad_norm": 1.6966934026640956e-06,
      "learning_rate": 2.308942016881551e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5875488,
      "step": 20975
    },
    {
      "epoch": 233.11111111111111,
      "grad_norm": 8.930462627176894e-07,
      "learning_rate": 2.307963155083539e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5876848,
      "step": 20980
    },
    {
      "epoch": 233.16666666666666,
      "grad_norm": 4.904249522041937e-07,
      "learning_rate": 2.306984322900022e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5878256,
      "step": 20985
    },
    {
      "epoch": 233.22222222222223,
      "grad_norm": 6.603603424082394e-07,
      "learning_rate": 2.3060055204819482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5879616,
      "step": 20990
    },
    {
      "epoch": 233.27777777777777,
      "grad_norm": 3.63695903615735e-06,
      "learning_rate": 2.3050267479802604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5881056,
      "step": 20995
    },
    {
      "epoch": 233.33333333333334,
      "grad_norm": 5.479437845679058e-07,
      "learning_rate": 2.304048005545899e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5882496,
      "step": 21000
    },
    {
      "epoch": 233.33333333333334,
      "eval_loss": 0.35755854845046997,
      "eval_runtime": 1.285,
      "eval_samples_per_second": 31.129,
      "eval_steps_per_second": 15.565,
      "num_input_tokens_seen": 5882496,
      "step": 21000
    },
    {
      "epoch": 233.38888888888889,
      "grad_norm": 5.405847787187668e-07,
      "learning_rate": 2.3030692933297972e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5883920,
      "step": 21005
    },
    {
      "epoch": 233.44444444444446,
      "grad_norm": 5.059972636445309e-07,
      "learning_rate": 2.3020906114828843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5885280,
      "step": 21010
    },
    {
      "epoch": 233.5,
      "grad_norm": 1.0206805427515064e-06,
      "learning_rate": 2.301111960156088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5886672,
      "step": 21015
    },
    {
      "epoch": 233.55555555555554,
      "grad_norm": 5.339722974895267e-07,
      "learning_rate": 2.300133339500326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5888096,
      "step": 21020
    },
    {
      "epoch": 233.61111111111111,
      "grad_norm": 5.145440127307666e-07,
      "learning_rate": 2.2991547496665148e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5889488,
      "step": 21025
    },
    {
      "epoch": 233.66666666666666,
      "grad_norm": 1.5097120922291651e-06,
      "learning_rate": 2.298176190805565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5890880,
      "step": 21030
    },
    {
      "epoch": 233.72222222222223,
      "grad_norm": 1.6580966075707693e-06,
      "learning_rate": 2.2971976630683826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5892288,
      "step": 21035
    },
    {
      "epoch": 233.77777777777777,
      "grad_norm": 5.361125658964738e-07,
      "learning_rate": 2.29621916660587e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5893728,
      "step": 21040
    },
    {
      "epoch": 233.83333333333334,
      "grad_norm": 5.423516427072173e-07,
      "learning_rate": 2.295240701568922e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5895088,
      "step": 21045
    },
    {
      "epoch": 233.88888888888889,
      "grad_norm": 9.09769653389958e-07,
      "learning_rate": 2.2942622681084312e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5896496,
      "step": 21050
    },
    {
      "epoch": 233.94444444444446,
      "grad_norm": 4.073443164998025e-07,
      "learning_rate": 2.293283866375284e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5897904,
      "step": 21055
    },
    {
      "epoch": 234.0,
      "grad_norm": 1.019001047097845e-06,
      "learning_rate": 2.2923054965203627e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5899296,
      "step": 21060
    },
    {
      "epoch": 234.05555555555554,
      "grad_norm": 1.0717089935496915e-06,
      "learning_rate": 2.2913271586945443e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5900672,
      "step": 21065
    },
    {
      "epoch": 234.11111111111111,
      "grad_norm": 5.234495574768516e-07,
      "learning_rate": 2.290348853048699e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5902064,
      "step": 21070
    },
    {
      "epoch": 234.16666666666666,
      "grad_norm": 4.981802703696303e-07,
      "learning_rate": 2.2893705797336956e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5903456,
      "step": 21075
    },
    {
      "epoch": 234.22222222222223,
      "grad_norm": 5.500801876223704e-07,
      "learning_rate": 2.288392338900397e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5904816,
      "step": 21080
    },
    {
      "epoch": 234.27777777777777,
      "grad_norm": 1.6382390413127723e-06,
      "learning_rate": 2.2874141306996576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5906176,
      "step": 21085
    },
    {
      "epoch": 234.33333333333334,
      "grad_norm": 4.93032359827339e-07,
      "learning_rate": 2.2864359552823312e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5907600,
      "step": 21090
    },
    {
      "epoch": 234.38888888888889,
      "grad_norm": 4.083710791746853e-07,
      "learning_rate": 2.2854578127992648e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5908976,
      "step": 21095
    },
    {
      "epoch": 234.44444444444446,
      "grad_norm": 5.523128834283852e-07,
      "learning_rate": 2.2844797034012988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5910400,
      "step": 21100
    },
    {
      "epoch": 234.5,
      "grad_norm": 5.581845812230313e-07,
      "learning_rate": 2.2835016272392722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5911776,
      "step": 21105
    },
    {
      "epoch": 234.55555555555554,
      "grad_norm": 4.506361506173562e-07,
      "learning_rate": 2.2825235844640142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5913184,
      "step": 21110
    },
    {
      "epoch": 234.61111111111111,
      "grad_norm": 5.73100805922877e-07,
      "learning_rate": 2.2815455752263522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5914512,
      "step": 21115
    },
    {
      "epoch": 234.66666666666666,
      "grad_norm": 1.0079419325847994e-06,
      "learning_rate": 2.2805675996771092e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5915920,
      "step": 21120
    },
    {
      "epoch": 234.72222222222223,
      "grad_norm": 6.335978923743824e-07,
      "learning_rate": 2.2795896579670987e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5917312,
      "step": 21125
    },
    {
      "epoch": 234.77777777777777,
      "grad_norm": 1.0521862350287847e-06,
      "learning_rate": 2.2786117502471337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5918720,
      "step": 21130
    },
    {
      "epoch": 234.83333333333334,
      "grad_norm": 2.2268739030550933e-06,
      "learning_rate": 2.2776338766680185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5920096,
      "step": 21135
    },
    {
      "epoch": 234.88888888888889,
      "grad_norm": 5.876188993170217e-07,
      "learning_rate": 2.2766560373805533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5921552,
      "step": 21140
    },
    {
      "epoch": 234.94444444444446,
      "grad_norm": 4.758294380735606e-07,
      "learning_rate": 2.2756782325355353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5923024,
      "step": 21145
    },
    {
      "epoch": 235.0,
      "grad_norm": 4.813744567400136e-07,
      "learning_rate": 2.2747004622837514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5924416,
      "step": 21150
    },
    {
      "epoch": 235.05555555555554,
      "grad_norm": 4.5092872369423276e-07,
      "learning_rate": 2.2737227267759878e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5925824,
      "step": 21155
    },
    {
      "epoch": 235.11111111111111,
      "grad_norm": 4.0409105395156075e-07,
      "learning_rate": 2.272745026163024e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5927232,
      "step": 21160
    },
    {
      "epoch": 235.16666666666666,
      "grad_norm": 3.6977705804019934e-06,
      "learning_rate": 2.271767360595633e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5928624,
      "step": 21165
    },
    {
      "epoch": 235.22222222222223,
      "grad_norm": 5.368643769543269e-07,
      "learning_rate": 2.270789730224583e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5930048,
      "step": 21170
    },
    {
      "epoch": 235.27777777777777,
      "grad_norm": 5.847689408255974e-07,
      "learning_rate": 2.2698121352006367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5931472,
      "step": 21175
    },
    {
      "epoch": 235.33333333333334,
      "grad_norm": 9.998725545301568e-07,
      "learning_rate": 2.2688345756745517e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5932864,
      "step": 21180
    },
    {
      "epoch": 235.38888888888889,
      "grad_norm": 5.675142347172368e-07,
      "learning_rate": 2.267857051797081e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5934272,
      "step": 21185
    },
    {
      "epoch": 235.44444444444446,
      "grad_norm": 4.3491183987498516e-07,
      "learning_rate": 2.2668795637189695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5935648,
      "step": 21190
    },
    {
      "epoch": 235.5,
      "grad_norm": 5.6689384564379e-07,
      "learning_rate": 2.2659021115909586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5937024,
      "step": 21195
    },
    {
      "epoch": 235.55555555555554,
      "grad_norm": 1.0620210559864063e-06,
      "learning_rate": 2.2649246955637847e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5938432,
      "step": 21200
    },
    {
      "epoch": 235.55555555555554,
      "eval_loss": 0.3687517046928406,
      "eval_runtime": 1.2869,
      "eval_samples_per_second": 31.082,
      "eval_steps_per_second": 15.541,
      "num_input_tokens_seen": 5938432,
      "step": 21200
    },
    {
      "epoch": 235.61111111111111,
      "grad_norm": 4.6419805244113377e-07,
      "learning_rate": 2.2639473157881766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5939824,
      "step": 21205
    },
    {
      "epoch": 235.66666666666666,
      "grad_norm": 5.830656277794333e-07,
      "learning_rate": 2.2629699724148594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5941184,
      "step": 21210
    },
    {
      "epoch": 235.72222222222223,
      "grad_norm": 4.337098005180451e-07,
      "learning_rate": 2.26199266559455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5942624,
      "step": 21215
    },
    {
      "epoch": 235.77777777777777,
      "grad_norm": 9.234609592567722e-07,
      "learning_rate": 2.2610153954779625e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5944016,
      "step": 21220
    },
    {
      "epoch": 235.83333333333334,
      "grad_norm": 1.0565621550995274e-06,
      "learning_rate": 2.2600381622158056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5945392,
      "step": 21225
    },
    {
      "epoch": 235.88888888888889,
      "grad_norm": 6.011520667925652e-07,
      "learning_rate": 2.2590609659587783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5946832,
      "step": 21230
    },
    {
      "epoch": 235.94444444444446,
      "grad_norm": 5.903544320062792e-07,
      "learning_rate": 2.2580838068575787e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5948224,
      "step": 21235
    },
    {
      "epoch": 236.0,
      "grad_norm": 4.996792881684087e-07,
      "learning_rate": 2.257106685062896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5949648,
      "step": 21240
    },
    {
      "epoch": 236.05555555555554,
      "grad_norm": 3.612945874920115e-06,
      "learning_rate": 2.256129600725415e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5951040,
      "step": 21245
    },
    {
      "epoch": 236.11111111111111,
      "grad_norm": 1.5323615798479295e-06,
      "learning_rate": 2.2551525539958145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5952464,
      "step": 21250
    },
    {
      "epoch": 236.16666666666666,
      "grad_norm": 4.754243718707585e-07,
      "learning_rate": 2.2541755450247663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5953904,
      "step": 21255
    },
    {
      "epoch": 236.22222222222223,
      "grad_norm": 4.842053726861195e-07,
      "learning_rate": 2.2531985739629382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5955344,
      "step": 21260
    },
    {
      "epoch": 236.27777777777777,
      "grad_norm": 1.0202469411524362e-06,
      "learning_rate": 2.2522216409609924e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5956720,
      "step": 21265
    },
    {
      "epoch": 236.33333333333334,
      "grad_norm": 6.480166234723583e-07,
      "learning_rate": 2.2512447461695826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5958144,
      "step": 21270
    },
    {
      "epoch": 236.38888888888889,
      "grad_norm": 5.29321539488592e-07,
      "learning_rate": 2.2502678897393593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5959536,
      "step": 21275
    },
    {
      "epoch": 236.44444444444446,
      "grad_norm": 6.309119839897903e-07,
      "learning_rate": 2.2492910718209665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5960896,
      "step": 21280
    },
    {
      "epoch": 236.5,
      "grad_norm": 8.364460768461868e-07,
      "learning_rate": 2.2483142925650398e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5962288,
      "step": 21285
    },
    {
      "epoch": 236.55555555555554,
      "grad_norm": 5.515225893759634e-07,
      "learning_rate": 2.247337552122213e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5963696,
      "step": 21290
    },
    {
      "epoch": 236.61111111111111,
      "grad_norm": 4.982611585546692e-07,
      "learning_rate": 2.24636085064311e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5965120,
      "step": 21295
    },
    {
      "epoch": 236.66666666666666,
      "grad_norm": 1.9703861653397325e-06,
      "learning_rate": 2.245384188278351e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5966480,
      "step": 21300
    },
    {
      "epoch": 236.72222222222223,
      "grad_norm": 1.0525444622544455e-06,
      "learning_rate": 2.2444075651785513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5967920,
      "step": 21305
    },
    {
      "epoch": 236.77777777777777,
      "grad_norm": 2.0851800854870817e-06,
      "learning_rate": 2.243430981494316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5969344,
      "step": 21310
    },
    {
      "epoch": 236.83333333333334,
      "grad_norm": 4.404588764828077e-07,
      "learning_rate": 2.2424544373762475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5970752,
      "step": 21315
    },
    {
      "epoch": 236.88888888888889,
      "grad_norm": 5.15525982791587e-07,
      "learning_rate": 2.2414779329749418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5972128,
      "step": 21320
    },
    {
      "epoch": 236.94444444444446,
      "grad_norm": 5.442214501272247e-07,
      "learning_rate": 2.2405014684409873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5973520,
      "step": 21325
    },
    {
      "epoch": 237.0,
      "grad_norm": 4.554160000225238e-07,
      "learning_rate": 2.239525043924968e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5974880,
      "step": 21330
    },
    {
      "epoch": 237.05555555555554,
      "grad_norm": 1.709224420665123e-06,
      "learning_rate": 2.2385486595774592e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5976208,
      "step": 21335
    },
    {
      "epoch": 237.11111111111111,
      "grad_norm": 1.50450898672716e-06,
      "learning_rate": 2.237572315549033e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5977568,
      "step": 21340
    },
    {
      "epoch": 237.16666666666666,
      "grad_norm": 5.27025179053453e-07,
      "learning_rate": 2.2365960119902545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5978928,
      "step": 21345
    },
    {
      "epoch": 237.22222222222223,
      "grad_norm": 4.846880869990855e-07,
      "learning_rate": 2.2356197490516806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5980384,
      "step": 21350
    },
    {
      "epoch": 237.27777777777777,
      "grad_norm": 5.508702543011168e-07,
      "learning_rate": 2.234643526883863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5981824,
      "step": 21355
    },
    {
      "epoch": 237.33333333333334,
      "grad_norm": 6.172855364638963e-07,
      "learning_rate": 2.2336673456373497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5983248,
      "step": 21360
    },
    {
      "epoch": 237.38888888888889,
      "grad_norm": 5.686347321898211e-07,
      "learning_rate": 2.2326912054626772e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5984656,
      "step": 21365
    },
    {
      "epoch": 237.44444444444446,
      "grad_norm": 9.82980168373615e-07,
      "learning_rate": 2.2317151065103813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5986064,
      "step": 21370
    },
    {
      "epoch": 237.5,
      "grad_norm": 5.442977908387547e-07,
      "learning_rate": 2.2307390489309865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5987424,
      "step": 21375
    },
    {
      "epoch": 237.55555555555554,
      "grad_norm": 6.448047429330472e-07,
      "learning_rate": 2.2297630328750146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5988848,
      "step": 21380
    },
    {
      "epoch": 237.61111111111111,
      "grad_norm": 1.5200050711428048e-06,
      "learning_rate": 2.228787058492979e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5990256,
      "step": 21385
    },
    {
      "epoch": 237.66666666666666,
      "grad_norm": 4.374653030936315e-07,
      "learning_rate": 2.2278111259353875e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5991680,
      "step": 21390
    },
    {
      "epoch": 237.72222222222223,
      "grad_norm": 3.5807900644613255e-07,
      "learning_rate": 2.2268352353527395e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5993088,
      "step": 21395
    },
    {
      "epoch": 237.77777777777777,
      "grad_norm": 4.960841124557192e-07,
      "learning_rate": 2.225859386895533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5994480,
      "step": 21400
    },
    {
      "epoch": 237.77777777777777,
      "eval_loss": 0.37031468749046326,
      "eval_runtime": 1.2896,
      "eval_samples_per_second": 31.018,
      "eval_steps_per_second": 15.509,
      "num_input_tokens_seen": 5994480,
      "step": 21400
    },
    {
      "epoch": 237.83333333333334,
      "grad_norm": 5.026377607464383e-07,
      "learning_rate": 2.2248835807142525e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5995888,
      "step": 21405
    },
    {
      "epoch": 237.88888888888889,
      "grad_norm": 4.114595526516496e-07,
      "learning_rate": 2.2239078169593826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5997296,
      "step": 21410
    },
    {
      "epoch": 237.94444444444446,
      "grad_norm": 4.846929186896887e-07,
      "learning_rate": 2.222932095781396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 5998720,
      "step": 21415
    },
    {
      "epoch": 238.0,
      "grad_norm": 5.072739668321447e-07,
      "learning_rate": 2.221956417330762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6000176,
      "step": 21420
    },
    {
      "epoch": 238.05555555555554,
      "grad_norm": 5.078322828921955e-07,
      "learning_rate": 2.2209807817579438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6001568,
      "step": 21425
    },
    {
      "epoch": 238.11111111111111,
      "grad_norm": 5.839048071720754e-07,
      "learning_rate": 2.220005189213394e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6002944,
      "step": 21430
    },
    {
      "epoch": 238.16666666666666,
      "grad_norm": 1.6678957308613462e-06,
      "learning_rate": 2.2190296398475624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6004368,
      "step": 21435
    },
    {
      "epoch": 238.22222222222223,
      "grad_norm": 5.306395678417175e-07,
      "learning_rate": 2.2180541338108926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6005728,
      "step": 21440
    },
    {
      "epoch": 238.27777777777777,
      "grad_norm": 1.1116366067653871e-06,
      "learning_rate": 2.2170786712538176e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6007104,
      "step": 21445
    },
    {
      "epoch": 238.33333333333334,
      "grad_norm": 9.975119610317051e-07,
      "learning_rate": 2.216103252326768e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6008496,
      "step": 21450
    },
    {
      "epoch": 238.38888888888889,
      "grad_norm": 1.5445742747033364e-06,
      "learning_rate": 2.2151278771801635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6009920,
      "step": 21455
    },
    {
      "epoch": 238.44444444444446,
      "grad_norm": 5.099847726341977e-07,
      "learning_rate": 2.21415254596442e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6011328,
      "step": 21460
    },
    {
      "epoch": 238.5,
      "grad_norm": 4.72432958531499e-07,
      "learning_rate": 2.213177258829947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6012800,
      "step": 21465
    },
    {
      "epoch": 238.55555555555554,
      "grad_norm": 1.469307676416065e-06,
      "learning_rate": 2.2122020159271445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6014192,
      "step": 21470
    },
    {
      "epoch": 238.61111111111111,
      "grad_norm": 5.380267111831927e-07,
      "learning_rate": 2.2112268174064075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6015584,
      "step": 21475
    },
    {
      "epoch": 238.66666666666666,
      "grad_norm": 1.7296335954597453e-06,
      "learning_rate": 2.2102516634181253e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6016992,
      "step": 21480
    },
    {
      "epoch": 238.72222222222223,
      "grad_norm": 1.086360725821578e-06,
      "learning_rate": 2.209276554112677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6018384,
      "step": 21485
    },
    {
      "epoch": 238.77777777777777,
      "grad_norm": 4.935817514706287e-07,
      "learning_rate": 2.2083014896404384e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6019840,
      "step": 21490
    },
    {
      "epoch": 238.83333333333334,
      "grad_norm": 5.272671046441246e-07,
      "learning_rate": 2.207326470151775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6021248,
      "step": 21495
    },
    {
      "epoch": 238.88888888888889,
      "grad_norm": 9.309389383815869e-07,
      "learning_rate": 2.2063514957970477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6022672,
      "step": 21500
    },
    {
      "epoch": 238.94444444444446,
      "grad_norm": 1.5160786688284134e-06,
      "learning_rate": 2.205376566726611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6024048,
      "step": 21505
    },
    {
      "epoch": 239.0,
      "grad_norm": 6.284201390371891e-07,
      "learning_rate": 2.204401683090809e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6025408,
      "step": 21510
    },
    {
      "epoch": 239.05555555555554,
      "grad_norm": 2.29242209570657e-06,
      "learning_rate": 2.203426845039982e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6026832,
      "step": 21515
    },
    {
      "epoch": 239.11111111111111,
      "grad_norm": 5.049261631029367e-07,
      "learning_rate": 2.202452052724464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6028272,
      "step": 21520
    },
    {
      "epoch": 239.16666666666666,
      "grad_norm": 4.74800970096112e-07,
      "learning_rate": 2.2014773062945777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6029632,
      "step": 21525
    },
    {
      "epoch": 239.22222222222223,
      "grad_norm": 9.850442665992887e-07,
      "learning_rate": 2.2005026059006427e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6031024,
      "step": 21530
    },
    {
      "epoch": 239.27777777777777,
      "grad_norm": 1.0377776789027848e-06,
      "learning_rate": 2.1995279516929695e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6032400,
      "step": 21535
    },
    {
      "epoch": 239.33333333333334,
      "grad_norm": 6.308507636276772e-07,
      "learning_rate": 2.1985533438218613e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6033840,
      "step": 21540
    },
    {
      "epoch": 239.38888888888889,
      "grad_norm": 5.54290352283715e-07,
      "learning_rate": 2.197578782437617e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6035264,
      "step": 21545
    },
    {
      "epoch": 239.44444444444446,
      "grad_norm": 6.509063723569852e-07,
      "learning_rate": 2.196604267690524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6036672,
      "step": 21550
    },
    {
      "epoch": 239.5,
      "grad_norm": 3.2031214232119964e-06,
      "learning_rate": 2.195629799730865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6038064,
      "step": 21555
    },
    {
      "epoch": 239.55555555555554,
      "grad_norm": 6.191764896357199e-07,
      "learning_rate": 2.1946553787089173e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6039504,
      "step": 21560
    },
    {
      "epoch": 239.61111111111111,
      "grad_norm": 4.819296464120271e-07,
      "learning_rate": 2.193681004774947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6040928,
      "step": 21565
    },
    {
      "epoch": 239.66666666666666,
      "grad_norm": 2.1833900518686278e-06,
      "learning_rate": 2.1927066780792154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6042336,
      "step": 21570
    },
    {
      "epoch": 239.72222222222223,
      "grad_norm": 1.0354946198276593e-06,
      "learning_rate": 2.191732398771975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6043712,
      "step": 21575
    },
    {
      "epoch": 239.77777777777777,
      "grad_norm": 5.512472398550017e-07,
      "learning_rate": 2.1907581670034725e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6045072,
      "step": 21580
    },
    {
      "epoch": 239.83333333333334,
      "grad_norm": 9.705081538413651e-07,
      "learning_rate": 2.189783982923948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6046464,
      "step": 21585
    },
    {
      "epoch": 239.88888888888889,
      "grad_norm": 5.509417064786248e-07,
      "learning_rate": 2.1888098466836303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6047888,
      "step": 21590
    },
    {
      "epoch": 239.94444444444446,
      "grad_norm": 9.120677759710816e-07,
      "learning_rate": 2.1878357584327457e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6049264,
      "step": 21595
    },
    {
      "epoch": 240.0,
      "grad_norm": 6.298661787695892e-07,
      "learning_rate": 2.1868617183215103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6050656,
      "step": 21600
    },
    {
      "epoch": 240.0,
      "eval_loss": 0.3402942717075348,
      "eval_runtime": 1.2828,
      "eval_samples_per_second": 31.181,
      "eval_steps_per_second": 15.591,
      "num_input_tokens_seen": 6050656,
      "step": 21600
    },
    {
      "epoch": 240.05555555555554,
      "grad_norm": 9.81268613031716e-07,
      "learning_rate": 2.1858877265001327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6052064,
      "step": 21605
    },
    {
      "epoch": 240.11111111111111,
      "grad_norm": 5.320363811733841e-07,
      "learning_rate": 2.184913783118816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6053472,
      "step": 21610
    },
    {
      "epoch": 240.16666666666666,
      "grad_norm": 1.0152953109354712e-06,
      "learning_rate": 2.1839398883277522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6054864,
      "step": 21615
    },
    {
      "epoch": 240.22222222222223,
      "grad_norm": 4.914002147415886e-07,
      "learning_rate": 2.182966042277129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6056240,
      "step": 21620
    },
    {
      "epoch": 240.27777777777777,
      "grad_norm": 4.7601824348930677e-07,
      "learning_rate": 2.181992245117128e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6057616,
      "step": 21625
    },
    {
      "epoch": 240.33333333333334,
      "grad_norm": 4.3667344584719103e-07,
      "learning_rate": 2.181018496997918e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6058992,
      "step": 21630
    },
    {
      "epoch": 240.38888888888889,
      "grad_norm": 1.0196566790909856e-06,
      "learning_rate": 2.1800447980696648e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6060432,
      "step": 21635
    },
    {
      "epoch": 240.44444444444446,
      "grad_norm": 1.072223767550895e-06,
      "learning_rate": 2.1790711484825248e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6061840,
      "step": 21640
    },
    {
      "epoch": 240.5,
      "grad_norm": 1.0121671039087232e-06,
      "learning_rate": 2.178097548386646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6063232,
      "step": 21645
    },
    {
      "epoch": 240.55555555555554,
      "grad_norm": 9.867349035630468e-07,
      "learning_rate": 2.1771239979321712e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6064672,
      "step": 21650
    },
    {
      "epoch": 240.61111111111111,
      "grad_norm": 1.7181066596094752e-06,
      "learning_rate": 2.1761504972692327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6066032,
      "step": 21655
    },
    {
      "epoch": 240.66666666666666,
      "grad_norm": 2.0527322703856044e-06,
      "learning_rate": 2.1751770465479572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6067424,
      "step": 21660
    },
    {
      "epoch": 240.72222222222223,
      "grad_norm": 2.0656145807151916e-06,
      "learning_rate": 2.174203645918464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6068864,
      "step": 21665
    },
    {
      "epoch": 240.77777777777777,
      "grad_norm": 6.262740157580993e-07,
      "learning_rate": 2.1732302955308624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6070304,
      "step": 21670
    },
    {
      "epoch": 240.83333333333334,
      "grad_norm": 2.3436491574102547e-06,
      "learning_rate": 2.172256995535255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6071712,
      "step": 21675
    },
    {
      "epoch": 240.88888888888889,
      "grad_norm": 5.671026315212657e-07,
      "learning_rate": 2.171283746081739e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6073088,
      "step": 21680
    },
    {
      "epoch": 240.94444444444446,
      "grad_norm": 5.966990670458472e-07,
      "learning_rate": 2.1703105473203988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6074448,
      "step": 21685
    },
    {
      "epoch": 241.0,
      "grad_norm": 4.871440637543856e-07,
      "learning_rate": 2.1693373994013168e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6075856,
      "step": 21690
    },
    {
      "epoch": 241.05555555555554,
      "grad_norm": 8.930785497796023e-07,
      "learning_rate": 2.168364302474562e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6077248,
      "step": 21695
    },
    {
      "epoch": 241.11111111111111,
      "grad_norm": 1.1193096725037321e-06,
      "learning_rate": 2.167391256690199e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6078656,
      "step": 21700
    },
    {
      "epoch": 241.16666666666666,
      "grad_norm": 5.588211138274346e-07,
      "learning_rate": 2.1664182621982855e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6080096,
      "step": 21705
    },
    {
      "epoch": 241.22222222222223,
      "grad_norm": 1.4903415603839676e-06,
      "learning_rate": 2.1654453191488673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6081488,
      "step": 21710
    },
    {
      "epoch": 241.27777777777777,
      "grad_norm": 9.203864124174288e-07,
      "learning_rate": 2.1644724276919846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6082928,
      "step": 21715
    },
    {
      "epoch": 241.33333333333334,
      "grad_norm": 4.991791229258524e-07,
      "learning_rate": 2.1634995879776715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6084304,
      "step": 21720
    },
    {
      "epoch": 241.38888888888889,
      "grad_norm": 3.9036245880197384e-07,
      "learning_rate": 2.162526800155949e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6085680,
      "step": 21725
    },
    {
      "epoch": 241.44444444444446,
      "grad_norm": 5.147445563125075e-07,
      "learning_rate": 2.1615540643768363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6087056,
      "step": 21730
    },
    {
      "epoch": 241.5,
      "grad_norm": 5.42764212241309e-07,
      "learning_rate": 2.160581380790339e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6088464,
      "step": 21735
    },
    {
      "epoch": 241.55555555555554,
      "grad_norm": 3.6029809962201398e-06,
      "learning_rate": 2.1596087495464586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6089856,
      "step": 21740
    },
    {
      "epoch": 241.61111111111111,
      "grad_norm": 4.777255071530817e-07,
      "learning_rate": 2.1586361707951866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6091248,
      "step": 21745
    },
    {
      "epoch": 241.66666666666666,
      "grad_norm": 5.231789259596553e-07,
      "learning_rate": 2.157663644686507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6092688,
      "step": 21750
    },
    {
      "epoch": 241.72222222222223,
      "grad_norm": 4.180691064448183e-07,
      "learning_rate": 2.156691171370396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6094064,
      "step": 21755
    },
    {
      "epoch": 241.77777777777777,
      "grad_norm": 4.553183146072115e-07,
      "learning_rate": 2.1557187509968195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6095456,
      "step": 21760
    },
    {
      "epoch": 241.83333333333334,
      "grad_norm": 5.240666496320046e-07,
      "learning_rate": 2.1547463837157382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6096880,
      "step": 21765
    },
    {
      "epoch": 241.88888888888889,
      "grad_norm": 5.244684757599316e-07,
      "learning_rate": 2.1537740696771045e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6098304,
      "step": 21770
    },
    {
      "epoch": 241.94444444444446,
      "grad_norm": 3.530037474774872e-06,
      "learning_rate": 2.1528018090308587e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6099760,
      "step": 21775
    },
    {
      "epoch": 242.0,
      "grad_norm": 5.691214255421073e-07,
      "learning_rate": 2.151829601926938e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6101152,
      "step": 21780
    },
    {
      "epoch": 242.05555555555554,
      "grad_norm": 5.338807227417419e-07,
      "learning_rate": 2.1508574485152684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6102528,
      "step": 21785
    },
    {
      "epoch": 242.11111111111111,
      "grad_norm": 6.522062676594942e-07,
      "learning_rate": 2.1498853489457667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6103936,
      "step": 21790
    },
    {
      "epoch": 242.16666666666666,
      "grad_norm": 6.392109526132117e-07,
      "learning_rate": 2.1489133033683455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6105344,
      "step": 21795
    },
    {
      "epoch": 242.22222222222223,
      "grad_norm": 5.292920945976221e-07,
      "learning_rate": 2.1479413119329038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6106736,
      "step": 21800
    },
    {
      "epoch": 242.22222222222223,
      "eval_loss": 0.3380020260810852,
      "eval_runtime": 1.2918,
      "eval_samples_per_second": 30.965,
      "eval_steps_per_second": 15.483,
      "num_input_tokens_seen": 6106736,
      "step": 21800
    },
    {
      "epoch": 242.27777777777777,
      "grad_norm": 6.277688271438819e-07,
      "learning_rate": 2.1469693747893355e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6108144,
      "step": 21805
    },
    {
      "epoch": 242.33333333333334,
      "grad_norm": 1.0034273145720363e-06,
      "learning_rate": 2.1459974920875274e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6109584,
      "step": 21810
    },
    {
      "epoch": 242.38888888888889,
      "grad_norm": 4.964833806297975e-07,
      "learning_rate": 2.145025663977354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6110976,
      "step": 21815
    },
    {
      "epoch": 242.44444444444446,
      "grad_norm": 4.543431373349449e-07,
      "learning_rate": 2.1440538906086844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6112320,
      "step": 21820
    },
    {
      "epoch": 242.5,
      "grad_norm": 6.280081947807048e-07,
      "learning_rate": 2.1430821721313782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6113744,
      "step": 21825
    },
    {
      "epoch": 242.55555555555554,
      "grad_norm": 5.73690101646207e-07,
      "learning_rate": 2.142110508695286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6115168,
      "step": 21830
    },
    {
      "epoch": 242.61111111111111,
      "grad_norm": 2.2851666017231764e-06,
      "learning_rate": 2.1411389004502515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6116528,
      "step": 21835
    },
    {
      "epoch": 242.66666666666666,
      "grad_norm": 1.7606181472729077e-06,
      "learning_rate": 2.140167347546107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6117936,
      "step": 21840
    },
    {
      "epoch": 242.72222222222223,
      "grad_norm": 4.568577196550905e-07,
      "learning_rate": 2.1391958501326793e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6119312,
      "step": 21845
    },
    {
      "epoch": 242.77777777777777,
      "grad_norm": 1.945878238984733e-06,
      "learning_rate": 2.1382244083597873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6120720,
      "step": 21850
    },
    {
      "epoch": 242.83333333333334,
      "grad_norm": 5.052990559306636e-07,
      "learning_rate": 2.137253022377237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6122144,
      "step": 21855
    },
    {
      "epoch": 242.88888888888889,
      "grad_norm": 6.317502538877307e-07,
      "learning_rate": 2.136281692334829e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6123568,
      "step": 21860
    },
    {
      "epoch": 242.94444444444446,
      "grad_norm": 5.411238817032427e-07,
      "learning_rate": 2.135310418382356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6124976,
      "step": 21865
    },
    {
      "epoch": 243.0,
      "grad_norm": 5.379224035095831e-07,
      "learning_rate": 2.134339200669598e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6126368,
      "step": 21870
    },
    {
      "epoch": 243.05555555555554,
      "grad_norm": 3.0486057767120656e-07,
      "learning_rate": 2.133368039346331e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6127760,
      "step": 21875
    },
    {
      "epoch": 243.11111111111111,
      "grad_norm": 2.0714251149911433e-06,
      "learning_rate": 2.1323969345623195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6129232,
      "step": 21880
    },
    {
      "epoch": 243.16666666666666,
      "grad_norm": 4.6213315840759606e-07,
      "learning_rate": 2.1314258864673207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6130640,
      "step": 21885
    },
    {
      "epoch": 243.22222222222223,
      "grad_norm": 5.149667572368344e-07,
      "learning_rate": 2.130454895211082e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6132048,
      "step": 21890
    },
    {
      "epoch": 243.27777777777777,
      "grad_norm": 9.046258924172434e-07,
      "learning_rate": 2.129483960943342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6133440,
      "step": 21895
    },
    {
      "epoch": 243.33333333333334,
      "grad_norm": 3.6050059293302184e-07,
      "learning_rate": 2.128513083813831e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6134864,
      "step": 21900
    },
    {
      "epoch": 243.38888888888889,
      "grad_norm": 4.786376166521222e-07,
      "learning_rate": 2.1275422639722724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6136272,
      "step": 21905
    },
    {
      "epoch": 243.44444444444446,
      "grad_norm": 5.168739107830334e-07,
      "learning_rate": 2.126571501568376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6137664,
      "step": 21910
    },
    {
      "epoch": 243.5,
      "grad_norm": 4.707662810687907e-07,
      "learning_rate": 2.1256007967518478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6139072,
      "step": 21915
    },
    {
      "epoch": 243.55555555555554,
      "grad_norm": 6.254435902519617e-07,
      "learning_rate": 2.124630149672381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6140464,
      "step": 21920
    },
    {
      "epoch": 243.61111111111111,
      "grad_norm": 4.969455176251358e-07,
      "learning_rate": 2.1236595604796624e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6141840,
      "step": 21925
    },
    {
      "epoch": 243.66666666666666,
      "grad_norm": 9.151568747256533e-07,
      "learning_rate": 2.1226890293233693e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6143248,
      "step": 21930
    },
    {
      "epoch": 243.72222222222223,
      "grad_norm": 5.499439339473611e-07,
      "learning_rate": 2.1217185563531694e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6144640,
      "step": 21935
    },
    {
      "epoch": 243.77777777777777,
      "grad_norm": 1.7121989230872714e-06,
      "learning_rate": 2.120748141718721e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6146048,
      "step": 21940
    },
    {
      "epoch": 243.83333333333334,
      "grad_norm": 6.524237505800556e-07,
      "learning_rate": 2.1197777855696765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6147472,
      "step": 21945
    },
    {
      "epoch": 243.88888888888889,
      "grad_norm": 1.7048969311872497e-06,
      "learning_rate": 2.1188074880556746e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6148848,
      "step": 21950
    },
    {
      "epoch": 243.94444444444446,
      "grad_norm": 4.4721548420056934e-07,
      "learning_rate": 2.1178372493263495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6150288,
      "step": 21955
    },
    {
      "epoch": 244.0,
      "grad_norm": 1.7201078890138888e-06,
      "learning_rate": 2.116867069531322e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6151680,
      "step": 21960
    },
    {
      "epoch": 244.05555555555554,
      "grad_norm": 4.707163725470309e-07,
      "learning_rate": 2.1158969488202073e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6153136,
      "step": 21965
    },
    {
      "epoch": 244.11111111111111,
      "grad_norm": 1.02175067695498e-06,
      "learning_rate": 2.114926887342611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6154528,
      "step": 21970
    },
    {
      "epoch": 244.16666666666666,
      "grad_norm": 5.933003990321595e-07,
      "learning_rate": 2.113956885248127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6155904,
      "step": 21975
    },
    {
      "epoch": 244.22222222222223,
      "grad_norm": 5.045092734690115e-07,
      "learning_rate": 2.112986942686342e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6157328,
      "step": 21980
    },
    {
      "epoch": 244.27777777777777,
      "grad_norm": 4.7233987743311445e-07,
      "learning_rate": 2.112017059806835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6158720,
      "step": 21985
    },
    {
      "epoch": 244.33333333333334,
      "grad_norm": 9.88777969723742e-07,
      "learning_rate": 2.1110472367591724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6160096,
      "step": 21990
    },
    {
      "epoch": 244.38888888888889,
      "grad_norm": 1.690607518867182e-06,
      "learning_rate": 2.1100774736929145e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6161488,
      "step": 21995
    },
    {
      "epoch": 244.44444444444446,
      "grad_norm": 6.095164053476765e-07,
      "learning_rate": 2.10910777075761e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6162896,
      "step": 22000
    },
    {
      "epoch": 244.44444444444446,
      "eval_loss": 0.36523765325546265,
      "eval_runtime": 1.2972,
      "eval_samples_per_second": 30.836,
      "eval_steps_per_second": 15.418,
      "num_input_tokens_seen": 6162896,
      "step": 22000
    },
    {
      "epoch": 244.5,
      "grad_norm": 1.5290733017536695e-06,
      "learning_rate": 2.108138128102799e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6164320,
      "step": 22005
    },
    {
      "epoch": 244.55555555555554,
      "grad_norm": 5.498517339219688e-07,
      "learning_rate": 2.107168545878014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6165712,
      "step": 22010
    },
    {
      "epoch": 244.61111111111111,
      "grad_norm": 5.465124672809907e-07,
      "learning_rate": 2.106199024232775e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6167120,
      "step": 22015
    },
    {
      "epoch": 244.66666666666666,
      "grad_norm": 4.33205883609844e-07,
      "learning_rate": 2.105229563316595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6168544,
      "step": 22020
    },
    {
      "epoch": 244.72222222222223,
      "grad_norm": 1.723591253721679e-06,
      "learning_rate": 2.1042601632789784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6169936,
      "step": 22025
    },
    {
      "epoch": 244.77777777777777,
      "grad_norm": 5.980623427603859e-07,
      "learning_rate": 2.103290824269417e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6171296,
      "step": 22030
    },
    {
      "epoch": 244.83333333333334,
      "grad_norm": 3.948965741074062e-07,
      "learning_rate": 2.1023215464373965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6172656,
      "step": 22035
    },
    {
      "epoch": 244.88888888888889,
      "grad_norm": 5.824466029480391e-07,
      "learning_rate": 2.1013523299323908e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6174096,
      "step": 22040
    },
    {
      "epoch": 244.94444444444446,
      "grad_norm": 1.6739866168791195e-06,
      "learning_rate": 2.1003831749038654e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6175504,
      "step": 22045
    },
    {
      "epoch": 245.0,
      "grad_norm": 1.001987470772292e-06,
      "learning_rate": 2.099414081501277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6176896,
      "step": 22050
    },
    {
      "epoch": 245.05555555555554,
      "grad_norm": 1.7502890159448725e-06,
      "learning_rate": 2.09844504987407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6178272,
      "step": 22055
    },
    {
      "epoch": 245.11111111111111,
      "grad_norm": 5.475682769429113e-07,
      "learning_rate": 2.097476080171683e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6179648,
      "step": 22060
    },
    {
      "epoch": 245.16666666666666,
      "grad_norm": 5.093685331303277e-07,
      "learning_rate": 2.0965071725435436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6181040,
      "step": 22065
    },
    {
      "epoch": 245.22222222222223,
      "grad_norm": 4.87532247461786e-07,
      "learning_rate": 2.0955383271390684e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6182496,
      "step": 22070
    },
    {
      "epoch": 245.27777777777777,
      "grad_norm": 3.871930402965518e-06,
      "learning_rate": 2.094569544107666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6183904,
      "step": 22075
    },
    {
      "epoch": 245.33333333333334,
      "grad_norm": 1.7070838111976627e-06,
      "learning_rate": 2.093600823598735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6185280,
      "step": 22080
    },
    {
      "epoch": 245.38888888888889,
      "grad_norm": 6.058743906578457e-07,
      "learning_rate": 2.092632165761663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6186640,
      "step": 22085
    },
    {
      "epoch": 245.44444444444446,
      "grad_norm": 6.010270681144902e-07,
      "learning_rate": 2.091663570745832e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6188032,
      "step": 22090
    },
    {
      "epoch": 245.5,
      "grad_norm": 9.851701179286465e-07,
      "learning_rate": 2.0906950387006086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6189408,
      "step": 22095
    },
    {
      "epoch": 245.55555555555554,
      "grad_norm": 5.892528065487568e-07,
      "learning_rate": 2.0897265697753543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6190832,
      "step": 22100
    },
    {
      "epoch": 245.61111111111111,
      "grad_norm": 4.705041476427141e-07,
      "learning_rate": 2.088758164119419e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6192208,
      "step": 22105
    },
    {
      "epoch": 245.66666666666666,
      "grad_norm": 1.7493529185230727e-06,
      "learning_rate": 2.0877898218821428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6193616,
      "step": 22110
    },
    {
      "epoch": 245.72222222222223,
      "grad_norm": 4.6609429205091146e-07,
      "learning_rate": 2.0868215432128565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6195040,
      "step": 22115
    },
    {
      "epoch": 245.77777777777777,
      "grad_norm": 9.896937172015896e-07,
      "learning_rate": 2.0858533282608796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6196448,
      "step": 22120
    },
    {
      "epoch": 245.83333333333334,
      "grad_norm": 5.865190928489028e-07,
      "learning_rate": 2.084885177175524e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6197872,
      "step": 22125
    },
    {
      "epoch": 245.88888888888889,
      "grad_norm": 4.6753368110330484e-07,
      "learning_rate": 2.0839170901060917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6199312,
      "step": 22130
    },
    {
      "epoch": 245.94444444444446,
      "grad_norm": 9.164470498035371e-07,
      "learning_rate": 2.082949067201872e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6200736,
      "step": 22135
    },
    {
      "epoch": 246.0,
      "grad_norm": 5.95919118495658e-07,
      "learning_rate": 2.0819811086121475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6202112,
      "step": 22140
    },
    {
      "epoch": 246.05555555555554,
      "grad_norm": 6.033829436091764e-07,
      "learning_rate": 2.08101321448619e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6203488,
      "step": 22145
    },
    {
      "epoch": 246.11111111111111,
      "grad_norm": 6.327492201307905e-07,
      "learning_rate": 2.080045384973259e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6204896,
      "step": 22150
    },
    {
      "epoch": 246.16666666666666,
      "grad_norm": 5.984458653074398e-07,
      "learning_rate": 2.0790776202226082e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6206304,
      "step": 22155
    },
    {
      "epoch": 246.22222222222223,
      "grad_norm": 3.6289616218709853e-06,
      "learning_rate": 2.078109920383477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6207664,
      "step": 22160
    },
    {
      "epoch": 246.27777777777777,
      "grad_norm": 5.092163632980373e-07,
      "learning_rate": 2.0771422856050978e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6209040,
      "step": 22165
    },
    {
      "epoch": 246.33333333333334,
      "grad_norm": 5.309642006068316e-07,
      "learning_rate": 2.076174716036693e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6210496,
      "step": 22170
    },
    {
      "epoch": 246.38888888888889,
      "grad_norm": 4.839793632527289e-07,
      "learning_rate": 2.075207211827472e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6211888,
      "step": 22175
    },
    {
      "epoch": 246.44444444444446,
      "grad_norm": 4.1789394344959874e-07,
      "learning_rate": 2.074239773126638e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6213328,
      "step": 22180
    },
    {
      "epoch": 246.5,
      "grad_norm": 4.4093746964790625e-07,
      "learning_rate": 2.073272400083382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6214752,
      "step": 22185
    },
    {
      "epoch": 246.55555555555554,
      "grad_norm": 5.447816988635168e-07,
      "learning_rate": 2.072305092846883e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6216128,
      "step": 22190
    },
    {
      "epoch": 246.61111111111111,
      "grad_norm": 1.0185393648498575e-06,
      "learning_rate": 2.0713378515663152e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6217552,
      "step": 22195
    },
    {
      "epoch": 246.66666666666666,
      "grad_norm": 5.199361794439028e-07,
      "learning_rate": 2.070370676390836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6218976,
      "step": 22200
    },
    {
      "epoch": 246.66666666666666,
      "eval_loss": 0.35795336961746216,
      "eval_runtime": 1.2883,
      "eval_samples_per_second": 31.048,
      "eval_steps_per_second": 15.524,
      "num_input_tokens_seen": 6218976,
      "step": 22200
    },
    {
      "epoch": 246.72222222222223,
      "grad_norm": 5.217504508436832e-07,
      "learning_rate": 2.0694035674695974e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6220352,
      "step": 22205
    },
    {
      "epoch": 246.77777777777777,
      "grad_norm": 1.6800471485112212e-06,
      "learning_rate": 2.0684365249517416e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6221760,
      "step": 22210
    },
    {
      "epoch": 246.83333333333334,
      "grad_norm": 2.774465656329994e-06,
      "learning_rate": 2.067469548986396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6223200,
      "step": 22215
    },
    {
      "epoch": 246.88888888888889,
      "grad_norm": 9.53254073010612e-07,
      "learning_rate": 2.066502639722681e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6224592,
      "step": 22220
    },
    {
      "epoch": 246.94444444444446,
      "grad_norm": 3.233493771404028e-06,
      "learning_rate": 2.065535797309708e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6225968,
      "step": 22225
    },
    {
      "epoch": 247.0,
      "grad_norm": 4.007204097433714e-07,
      "learning_rate": 2.0645690218965736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6227344,
      "step": 22230
    },
    {
      "epoch": 247.05555555555554,
      "grad_norm": 4.637578854271851e-07,
      "learning_rate": 2.063602313632369e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6228688,
      "step": 22235
    },
    {
      "epoch": 247.11111111111111,
      "grad_norm": 5.593032028627931e-07,
      "learning_rate": 2.0626356726661704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6230048,
      "step": 22240
    },
    {
      "epoch": 247.16666666666666,
      "grad_norm": 5.880128242097271e-07,
      "learning_rate": 2.0616690991470477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6231424,
      "step": 22245
    },
    {
      "epoch": 247.22222222222223,
      "grad_norm": 1.0349640433560126e-06,
      "learning_rate": 2.0607025932240595e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6232816,
      "step": 22250
    },
    {
      "epoch": 247.27777777777777,
      "grad_norm": 1.0076188345919945e-06,
      "learning_rate": 2.059736155046251e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6234192,
      "step": 22255
    },
    {
      "epoch": 247.33333333333334,
      "grad_norm": 1.6839954923852929e-06,
      "learning_rate": 2.0587697847626603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6235616,
      "step": 22260
    },
    {
      "epoch": 247.38888888888889,
      "grad_norm": 5.108443588142109e-07,
      "learning_rate": 2.057803482522314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6237008,
      "step": 22265
    },
    {
      "epoch": 247.44444444444446,
      "grad_norm": 5.804632223771478e-07,
      "learning_rate": 2.056837248474227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6238384,
      "step": 22270
    },
    {
      "epoch": 247.5,
      "grad_norm": 4.151516463934968e-07,
      "learning_rate": 2.0558710827674064e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6239824,
      "step": 22275
    },
    {
      "epoch": 247.55555555555554,
      "grad_norm": 5.369334985516616e-07,
      "learning_rate": 2.054904985550845e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6241248,
      "step": 22280
    },
    {
      "epoch": 247.61111111111111,
      "grad_norm": 4.264293238520622e-07,
      "learning_rate": 2.0539389569735287e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6242704,
      "step": 22285
    },
    {
      "epoch": 247.66666666666666,
      "grad_norm": 1.6934003497226513e-06,
      "learning_rate": 2.052972997184431e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6244128,
      "step": 22290
    },
    {
      "epoch": 247.72222222222223,
      "grad_norm": 1.043187012328417e-06,
      "learning_rate": 2.0520071063325146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6245504,
      "step": 22295
    },
    {
      "epoch": 247.77777777777777,
      "grad_norm": 4.873331818089355e-07,
      "learning_rate": 2.051041284566732e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6246896,
      "step": 22300
    },
    {
      "epoch": 247.83333333333334,
      "grad_norm": 5.553370101551991e-07,
      "learning_rate": 2.050075532036026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6248352,
      "step": 22305
    },
    {
      "epoch": 247.88888888888889,
      "grad_norm": 6.230390567907307e-07,
      "learning_rate": 2.0491098488893264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6249808,
      "step": 22310
    },
    {
      "epoch": 247.94444444444446,
      "grad_norm": 5.918273586758005e-07,
      "learning_rate": 2.0481442352755546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6251200,
      "step": 22315
    },
    {
      "epoch": 248.0,
      "grad_norm": 8.985510930870078e-07,
      "learning_rate": 2.0471786913436198e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6252608,
      "step": 22320
    },
    {
      "epoch": 248.05555555555554,
      "grad_norm": 2.3545542262581876e-06,
      "learning_rate": 2.0462132172424218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6254032,
      "step": 22325
    },
    {
      "epoch": 248.11111111111111,
      "grad_norm": 5.909176366003521e-07,
      "learning_rate": 2.0452478131208484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6255440,
      "step": 22330
    },
    {
      "epoch": 248.16666666666666,
      "grad_norm": 9.795512596610934e-07,
      "learning_rate": 2.0442824791277765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6256832,
      "step": 22335
    },
    {
      "epoch": 248.22222222222223,
      "grad_norm": 5.102882596474956e-07,
      "learning_rate": 2.0433172154120727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6258224,
      "step": 22340
    },
    {
      "epoch": 248.27777777777777,
      "grad_norm": 8.923771588342788e-07,
      "learning_rate": 2.0423520221225947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6259616,
      "step": 22345
    },
    {
      "epoch": 248.33333333333334,
      "grad_norm": 3.871706439895206e-07,
      "learning_rate": 2.0413868994081848e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6260992,
      "step": 22350
    },
    {
      "epoch": 248.38888888888889,
      "grad_norm": 4.963157493875769e-07,
      "learning_rate": 2.0404218474176795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6262368,
      "step": 22355
    },
    {
      "epoch": 248.44444444444446,
      "grad_norm": 2.2972849365032744e-06,
      "learning_rate": 2.0394568662999002e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6263776,
      "step": 22360
    },
    {
      "epoch": 248.5,
      "grad_norm": 9.63406023402058e-07,
      "learning_rate": 2.0384919562036593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6265216,
      "step": 22365
    },
    {
      "epoch": 248.55555555555554,
      "grad_norm": 4.310630288273387e-07,
      "learning_rate": 2.0375271172777593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6266640,
      "step": 22370
    },
    {
      "epoch": 248.61111111111111,
      "grad_norm": 5.270954943625838e-07,
      "learning_rate": 2.0365623496709885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6268000,
      "step": 22375
    },
    {
      "epoch": 248.66666666666666,
      "grad_norm": 5.089355568088649e-07,
      "learning_rate": 2.0355976535321283e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6269392,
      "step": 22380
    },
    {
      "epoch": 248.72222222222223,
      "grad_norm": 2.030600171565311e-06,
      "learning_rate": 2.034633029009945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6270768,
      "step": 22385
    },
    {
      "epoch": 248.77777777777777,
      "grad_norm": 2.3668096673645778e-06,
      "learning_rate": 2.0336684762531972e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6272144,
      "step": 22390
    },
    {
      "epoch": 248.83333333333334,
      "grad_norm": 5.174836132937344e-07,
      "learning_rate": 2.032703995410631e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6273536,
      "step": 22395
    },
    {
      "epoch": 248.88888888888889,
      "grad_norm": 4.497483132581692e-07,
      "learning_rate": 2.031739586630981e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6274960,
      "step": 22400
    },
    {
      "epoch": 248.88888888888889,
      "eval_loss": 0.3397849500179291,
      "eval_runtime": 1.2895,
      "eval_samples_per_second": 31.019,
      "eval_steps_per_second": 15.51,
      "num_input_tokens_seen": 6274960,
      "step": 22400
    },
    {
      "epoch": 248.94444444444446,
      "grad_norm": 5.152911057848542e-07,
      "learning_rate": 2.0307752500629707e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6276400,
      "step": 22405
    },
    {
      "epoch": 249.0,
      "grad_norm": 4.481607447814895e-06,
      "learning_rate": 2.0298109858553144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6277792,
      "step": 22410
    },
    {
      "epoch": 249.05555555555554,
      "grad_norm": 5.952789479124476e-07,
      "learning_rate": 2.028846794156712e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6279200,
      "step": 22415
    },
    {
      "epoch": 249.11111111111111,
      "grad_norm": 1.7005462495944812e-06,
      "learning_rate": 2.027882675115856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6280576,
      "step": 22420
    },
    {
      "epoch": 249.16666666666666,
      "grad_norm": 5.807656293654873e-07,
      "learning_rate": 2.026918628881423e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6281984,
      "step": 22425
    },
    {
      "epoch": 249.22222222222223,
      "grad_norm": 3.2712002848711563e-06,
      "learning_rate": 2.0259546556020833e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6283392,
      "step": 22430
    },
    {
      "epoch": 249.27777777777777,
      "grad_norm": 4.6924841967666e-07,
      "learning_rate": 2.024990755426493e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6284784,
      "step": 22435
    },
    {
      "epoch": 249.33333333333334,
      "grad_norm": 5.040987502979988e-07,
      "learning_rate": 2.0240269285032975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6286176,
      "step": 22440
    },
    {
      "epoch": 249.38888888888889,
      "grad_norm": 9.267738505513989e-07,
      "learning_rate": 2.0230631749811306e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6287568,
      "step": 22445
    },
    {
      "epoch": 249.44444444444446,
      "grad_norm": 3.6036128676641965e-06,
      "learning_rate": 2.0220994950086162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6288944,
      "step": 22450
    },
    {
      "epoch": 249.5,
      "grad_norm": 4.996115308131266e-07,
      "learning_rate": 2.021135888734365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6290320,
      "step": 22455
    },
    {
      "epoch": 249.55555555555554,
      "grad_norm": 5.963074158898962e-07,
      "learning_rate": 2.0201723563069783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6291728,
      "step": 22460
    },
    {
      "epoch": 249.61111111111111,
      "grad_norm": 5.637954814119439e-07,
      "learning_rate": 2.0192088978750433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6293120,
      "step": 22465
    },
    {
      "epoch": 249.66666666666666,
      "grad_norm": 1.4966740309318993e-06,
      "learning_rate": 2.0182455135871385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6294544,
      "step": 22470
    },
    {
      "epoch": 249.72222222222223,
      "grad_norm": 5.847226702826447e-07,
      "learning_rate": 2.0172822035918305e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6295952,
      "step": 22475
    },
    {
      "epoch": 249.77777777777777,
      "grad_norm": 3.4767822398862336e-07,
      "learning_rate": 2.016318968037671e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6297344,
      "step": 22480
    },
    {
      "epoch": 249.83333333333334,
      "grad_norm": 1.1613636843321729e-06,
      "learning_rate": 2.015355807073206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6298768,
      "step": 22485
    },
    {
      "epoch": 249.88888888888889,
      "grad_norm": 4.42477983142453e-07,
      "learning_rate": 2.0143927208469664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6300192,
      "step": 22490
    },
    {
      "epoch": 249.94444444444446,
      "grad_norm": 5.89500587011571e-07,
      "learning_rate": 2.0134297095074708e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6301600,
      "step": 22495
    },
    {
      "epoch": 250.0,
      "grad_norm": 5.354698373594147e-07,
      "learning_rate": 2.0124667732032297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6303008,
      "step": 22500
    },
    {
      "epoch": 250.05555555555554,
      "grad_norm": 4.3331377241884184e-07,
      "learning_rate": 2.011503912082738e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6304448,
      "step": 22505
    },
    {
      "epoch": 250.11111111111111,
      "grad_norm": 4.902660748484777e-07,
      "learning_rate": 2.0105411262944823e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6305904,
      "step": 22510
    },
    {
      "epoch": 250.16666666666666,
      "grad_norm": 4.19329694523185e-07,
      "learning_rate": 2.0095784159869366e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6307296,
      "step": 22515
    },
    {
      "epoch": 250.22222222222223,
      "grad_norm": 5.273375336400932e-07,
      "learning_rate": 2.0086157813085608e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6308688,
      "step": 22520
    },
    {
      "epoch": 250.27777777777777,
      "grad_norm": 6.240020979930705e-07,
      "learning_rate": 2.0076532224078068e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6310080,
      "step": 22525
    },
    {
      "epoch": 250.33333333333334,
      "grad_norm": 1.5098604535523918e-06,
      "learning_rate": 2.0066907394331142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6311472,
      "step": 22530
    },
    {
      "epoch": 250.38888888888889,
      "grad_norm": 5.631316071230685e-07,
      "learning_rate": 2.0057283325329077e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6312864,
      "step": 22535
    },
    {
      "epoch": 250.44444444444446,
      "grad_norm": 1.7655335113886395e-06,
      "learning_rate": 2.0047660018556047e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6314272,
      "step": 22540
    },
    {
      "epoch": 250.5,
      "grad_norm": 9.684905535323196e-07,
      "learning_rate": 2.0038037475496075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6315616,
      "step": 22545
    },
    {
      "epoch": 250.55555555555554,
      "grad_norm": 5.615116265289544e-07,
      "learning_rate": 2.0028415697633073e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6317072,
      "step": 22550
    },
    {
      "epoch": 250.61111111111111,
      "grad_norm": 6.109376045060344e-07,
      "learning_rate": 2.0018794686450858e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6318464,
      "step": 22555
    },
    {
      "epoch": 250.66666666666666,
      "grad_norm": 5.235027060734865e-07,
      "learning_rate": 2.0009174443433088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6319888,
      "step": 22560
    },
    {
      "epoch": 250.72222222222223,
      "grad_norm": 4.919008347314957e-07,
      "learning_rate": 1.999955497006334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6321232,
      "step": 22565
    },
    {
      "epoch": 250.77777777777777,
      "grad_norm": 5.497075790117378e-07,
      "learning_rate": 1.9989936267825067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6322624,
      "step": 22570
    },
    {
      "epoch": 250.83333333333334,
      "grad_norm": 4.990717457076244e-07,
      "learning_rate": 1.9980318338201572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6324064,
      "step": 22575
    },
    {
      "epoch": 250.88888888888889,
      "grad_norm": 9.58494865699322e-07,
      "learning_rate": 1.997070118267607e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6325472,
      "step": 22580
    },
    {
      "epoch": 250.94444444444446,
      "grad_norm": 1.614816483197501e-06,
      "learning_rate": 1.9961084802731654e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6326848,
      "step": 22585
    },
    {
      "epoch": 251.0,
      "grad_norm": 5.753784080297919e-07,
      "learning_rate": 1.9951469199851273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6328224,
      "step": 22590
    },
    {
      "epoch": 251.05555555555554,
      "grad_norm": 4.668559938636463e-07,
      "learning_rate": 1.99418543755178e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6329664,
      "step": 22595
    },
    {
      "epoch": 251.11111111111111,
      "grad_norm": 4.902049681732024e-07,
      "learning_rate": 1.9932240331213936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6331008,
      "step": 22600
    },
    {
      "epoch": 251.11111111111111,
      "eval_loss": 0.3739665448665619,
      "eval_runtime": 1.2926,
      "eval_samples_per_second": 30.945,
      "eval_steps_per_second": 15.473,
      "num_input_tokens_seen": 6331008,
      "step": 22600
    },
    {
      "epoch": 251.16666666666666,
      "grad_norm": 1.515328222012613e-06,
      "learning_rate": 1.9922627068422297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6332400,
      "step": 22605
    },
    {
      "epoch": 251.22222222222223,
      "grad_norm": 5.766429467257694e-07,
      "learning_rate": 1.991301458862538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6333792,
      "step": 22610
    },
    {
      "epoch": 251.27777777777777,
      "grad_norm": 2.1092321276228176e-06,
      "learning_rate": 1.9903402893305536e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6335216,
      "step": 22615
    },
    {
      "epoch": 251.33333333333334,
      "grad_norm": 1.118417799261806e-06,
      "learning_rate": 1.9893791983945016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6336672,
      "step": 22620
    },
    {
      "epoch": 251.38888888888889,
      "grad_norm": 5.588717044702207e-07,
      "learning_rate": 1.988418186202594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6338080,
      "step": 22625
    },
    {
      "epoch": 251.44444444444446,
      "grad_norm": 4.4259812170821533e-07,
      "learning_rate": 1.98745725290303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6339456,
      "step": 22630
    },
    {
      "epoch": 251.5,
      "grad_norm": 4.309446808292705e-07,
      "learning_rate": 1.986496398644e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6340880,
      "step": 22635
    },
    {
      "epoch": 251.55555555555554,
      "grad_norm": 4.952148628944997e-07,
      "learning_rate": 1.9855356235736777e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6342272,
      "step": 22640
    },
    {
      "epoch": 251.61111111111111,
      "grad_norm": 8.415989896093379e-07,
      "learning_rate": 1.9845749278402277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6343664,
      "step": 22645
    },
    {
      "epoch": 251.66666666666666,
      "grad_norm": 5.216260774432158e-07,
      "learning_rate": 1.9836143115918006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6345056,
      "step": 22650
    },
    {
      "epoch": 251.72222222222223,
      "grad_norm": 5.41051861091546e-07,
      "learning_rate": 1.9826537749765367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6346464,
      "step": 22655
    },
    {
      "epoch": 251.77777777777777,
      "grad_norm": 6.763755209249211e-07,
      "learning_rate": 1.9816933181425625e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6347904,
      "step": 22660
    },
    {
      "epoch": 251.83333333333334,
      "grad_norm": 2.3010309178062016e-06,
      "learning_rate": 1.9807329412379903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6349328,
      "step": 22665
    },
    {
      "epoch": 251.88888888888889,
      "grad_norm": 3.555925104592461e-06,
      "learning_rate": 1.9797726444109247e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6350736,
      "step": 22670
    },
    {
      "epoch": 251.94444444444446,
      "grad_norm": 1.440463734070363e-06,
      "learning_rate": 1.9788124278094557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6352112,
      "step": 22675
    },
    {
      "epoch": 252.0,
      "grad_norm": 1.5162358977249824e-06,
      "learning_rate": 1.9778522915816594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6353520,
      "step": 22680
    },
    {
      "epoch": 252.05555555555554,
      "grad_norm": 3.9234478776961623e-07,
      "learning_rate": 1.9768922358756014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6354928,
      "step": 22685
    },
    {
      "epoch": 252.11111111111111,
      "grad_norm": 4.433363756106701e-07,
      "learning_rate": 1.9759322608393353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6356336,
      "step": 22690
    },
    {
      "epoch": 252.16666666666666,
      "grad_norm": 5.983441724310978e-07,
      "learning_rate": 1.9749723666208992e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6357728,
      "step": 22695
    },
    {
      "epoch": 252.22222222222223,
      "grad_norm": 1.0103512977366336e-06,
      "learning_rate": 1.9740125533683235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6359184,
      "step": 22700
    },
    {
      "epoch": 252.27777777777777,
      "grad_norm": 5.445034503281931e-07,
      "learning_rate": 1.9730528212296208e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6360608,
      "step": 22705
    },
    {
      "epoch": 252.33333333333334,
      "grad_norm": 5.83991948133189e-07,
      "learning_rate": 1.9720931703527945e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6362000,
      "step": 22710
    },
    {
      "epoch": 252.38888888888889,
      "grad_norm": 1.5511271840296104e-06,
      "learning_rate": 1.9711336008858373e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6363440,
      "step": 22715
    },
    {
      "epoch": 252.44444444444446,
      "grad_norm": 1.0090042223964701e-06,
      "learning_rate": 1.9701741129767233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6364800,
      "step": 22720
    },
    {
      "epoch": 252.5,
      "grad_norm": 6.678972113149939e-07,
      "learning_rate": 1.9692147067734202e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6366192,
      "step": 22725
    },
    {
      "epoch": 252.55555555555554,
      "grad_norm": 4.946875833411468e-07,
      "learning_rate": 1.96825538242388e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6367568,
      "step": 22730
    },
    {
      "epoch": 252.61111111111111,
      "grad_norm": 1.0254397011522087e-06,
      "learning_rate": 1.967296140076041e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6368976,
      "step": 22735
    },
    {
      "epoch": 252.66666666666666,
      "grad_norm": 5.066429480393708e-07,
      "learning_rate": 1.966336979877833e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6370384,
      "step": 22740
    },
    {
      "epoch": 252.72222222222223,
      "grad_norm": 3.7013521136941563e-07,
      "learning_rate": 1.9653779019771678e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6371824,
      "step": 22745
    },
    {
      "epoch": 252.77777777777777,
      "grad_norm": 5.312164716997358e-07,
      "learning_rate": 1.9644189065219488e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6373248,
      "step": 22750
    },
    {
      "epoch": 252.83333333333334,
      "grad_norm": 9.951505717253895e-07,
      "learning_rate": 1.9634599936600655e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6374624,
      "step": 22755
    },
    {
      "epoch": 252.88888888888889,
      "grad_norm": 5.38509709713253e-07,
      "learning_rate": 1.9625011635393935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6375984,
      "step": 22760
    },
    {
      "epoch": 252.94444444444446,
      "grad_norm": 4.2644356312848686e-07,
      "learning_rate": 1.9615424163077963e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6377344,
      "step": 22765
    },
    {
      "epoch": 253.0,
      "grad_norm": 5.4294429219226e-07,
      "learning_rate": 1.9605837521131263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6378784,
      "step": 22770
    },
    {
      "epoch": 253.05555555555554,
      "grad_norm": 4.871914711657155e-07,
      "learning_rate": 1.9596251711032192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6380192,
      "step": 22775
    },
    {
      "epoch": 253.11111111111111,
      "grad_norm": 4.872687782153662e-07,
      "learning_rate": 1.958666673425903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6381616,
      "step": 22780
    },
    {
      "epoch": 253.16666666666666,
      "grad_norm": 5.853960374224698e-07,
      "learning_rate": 1.957708259228987e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6382992,
      "step": 22785
    },
    {
      "epoch": 253.22222222222223,
      "grad_norm": 4.897327698927256e-07,
      "learning_rate": 1.956749928660273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6384384,
      "step": 22790
    },
    {
      "epoch": 253.27777777777777,
      "grad_norm": 1.7041564888131688e-06,
      "learning_rate": 1.955791681867547e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6385712,
      "step": 22795
    },
    {
      "epoch": 253.33333333333334,
      "grad_norm": 1.5174920235949685e-06,
      "learning_rate": 1.9548335189985824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6387152,
      "step": 22800
    },
    {
      "epoch": 253.33333333333334,
      "eval_loss": 0.3142276108264923,
      "eval_runtime": 1.2946,
      "eval_samples_per_second": 30.898,
      "eval_steps_per_second": 15.449,
      "num_input_tokens_seen": 6387152,
      "step": 22800
    },
    {
      "epoch": 253.38888888888889,
      "grad_norm": 5.650753678310139e-07,
      "learning_rate": 1.9538754402011396e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6388544,
      "step": 22805
    },
    {
      "epoch": 253.44444444444446,
      "grad_norm": 9.20928641789942e-07,
      "learning_rate": 1.952917445622968e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6389920,
      "step": 22810
    },
    {
      "epoch": 253.5,
      "grad_norm": 4.769374299939955e-07,
      "learning_rate": 1.9519595354118005e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6391296,
      "step": 22815
    },
    {
      "epoch": 253.55555555555554,
      "grad_norm": 2.3848344881116645e-06,
      "learning_rate": 1.951001709715361e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6392752,
      "step": 22820
    },
    {
      "epoch": 253.61111111111111,
      "grad_norm": 6.383670552168041e-07,
      "learning_rate": 1.9500439686813556e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6394112,
      "step": 22825
    },
    {
      "epoch": 253.66666666666666,
      "grad_norm": 9.132041896009468e-07,
      "learning_rate": 1.949086312457482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6395488,
      "step": 22830
    },
    {
      "epoch": 253.72222222222223,
      "grad_norm": 4.932064712193096e-07,
      "learning_rate": 1.9481287411914223e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6396912,
      "step": 22835
    },
    {
      "epoch": 253.77777777777777,
      "grad_norm": 5.310291157911706e-07,
      "learning_rate": 1.9471712550308457e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6398336,
      "step": 22840
    },
    {
      "epoch": 253.83333333333334,
      "grad_norm": 1.0833773558260873e-06,
      "learning_rate": 1.946213854123409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6399792,
      "step": 22845
    },
    {
      "epoch": 253.88888888888889,
      "grad_norm": 4.406780078625161e-07,
      "learning_rate": 1.9452565386167554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6401168,
      "step": 22850
    },
    {
      "epoch": 253.94444444444446,
      "grad_norm": 4.895109668723308e-07,
      "learning_rate": 1.9442993086585142e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6402576,
      "step": 22855
    },
    {
      "epoch": 254.0,
      "grad_norm": 5.404072567216645e-07,
      "learning_rate": 1.9433421643963043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6403984,
      "step": 22860
    },
    {
      "epoch": 254.05555555555554,
      "grad_norm": 2.2334243112709373e-06,
      "learning_rate": 1.942385105977727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6405424,
      "step": 22865
    },
    {
      "epoch": 254.11111111111111,
      "grad_norm": 1.7514055343781365e-06,
      "learning_rate": 1.9414281335503743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6406816,
      "step": 22870
    },
    {
      "epoch": 254.16666666666666,
      "grad_norm": 5.404654075391591e-07,
      "learning_rate": 1.9404712472618232e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6408192,
      "step": 22875
    },
    {
      "epoch": 254.22222222222223,
      "grad_norm": 1.0068132496598992e-06,
      "learning_rate": 1.939514447259636e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6409584,
      "step": 22880
    },
    {
      "epoch": 254.27777777777777,
      "grad_norm": 1.0140904578292975e-06,
      "learning_rate": 1.938557733691365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6410944,
      "step": 22885
    },
    {
      "epoch": 254.33333333333334,
      "grad_norm": 5.393745254878013e-07,
      "learning_rate": 1.9376011067045476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6412336,
      "step": 22890
    },
    {
      "epoch": 254.38888888888889,
      "grad_norm": 5.64964636851073e-07,
      "learning_rate": 1.9366445664467065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6413760,
      "step": 22895
    },
    {
      "epoch": 254.44444444444446,
      "grad_norm": 1.4939481616238481e-06,
      "learning_rate": 1.9356881130653533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6415184,
      "step": 22900
    },
    {
      "epoch": 254.5,
      "grad_norm": 4.939222435496049e-07,
      "learning_rate": 1.9347317467079846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6416576,
      "step": 22905
    },
    {
      "epoch": 254.55555555555554,
      "grad_norm": 9.696136658021715e-07,
      "learning_rate": 1.9337754675220836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6418000,
      "step": 22910
    },
    {
      "epoch": 254.61111111111111,
      "grad_norm": 5.021847755415365e-07,
      "learning_rate": 1.9328192756551218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6419392,
      "step": 22915
    },
    {
      "epoch": 254.66666666666666,
      "grad_norm": 3.5828425097861327e-06,
      "learning_rate": 1.931863171254555e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6420784,
      "step": 22920
    },
    {
      "epoch": 254.72222222222223,
      "grad_norm": 5.734357273468049e-07,
      "learning_rate": 1.930907154467826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6422224,
      "step": 22925
    },
    {
      "epoch": 254.77777777777777,
      "grad_norm": 2.290772272317554e-06,
      "learning_rate": 1.9299512254423673e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6423632,
      "step": 22930
    },
    {
      "epoch": 254.83333333333334,
      "grad_norm": 1.0946354223051458e-06,
      "learning_rate": 1.9289953843255914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6425056,
      "step": 22935
    },
    {
      "epoch": 254.88888888888889,
      "grad_norm": 9.563339062879095e-07,
      "learning_rate": 1.9280396312649048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6426464,
      "step": 22940
    },
    {
      "epoch": 254.94444444444446,
      "grad_norm": 4.897036660622689e-07,
      "learning_rate": 1.9270839664076936e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6427824,
      "step": 22945
    },
    {
      "epoch": 255.0,
      "grad_norm": 1.0285812095389701e-06,
      "learning_rate": 1.9261283899013345e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6429216,
      "step": 22950
    },
    {
      "epoch": 255.05555555555554,
      "grad_norm": 6.135066996648675e-07,
      "learning_rate": 1.92517290189319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6430656,
      "step": 22955
    },
    {
      "epoch": 255.11111111111111,
      "grad_norm": 1.5261973658198258e-06,
      "learning_rate": 1.924217502530607e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6432048,
      "step": 22960
    },
    {
      "epoch": 255.16666666666666,
      "grad_norm": 5.810487664348329e-07,
      "learning_rate": 1.9232621919609207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6433440,
      "step": 22965
    },
    {
      "epoch": 255.22222222222223,
      "grad_norm": 4.1407801631976326e-07,
      "learning_rate": 1.9223069703314534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6434816,
      "step": 22970
    },
    {
      "epoch": 255.27777777777777,
      "grad_norm": 1.026126938086236e-06,
      "learning_rate": 1.92135183778951e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6436192,
      "step": 22975
    },
    {
      "epoch": 255.33333333333334,
      "grad_norm": 5.187573037801485e-07,
      "learning_rate": 1.9203967944823857e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6437568,
      "step": 22980
    },
    {
      "epoch": 255.38888888888889,
      "grad_norm": 1.6948710026554181e-06,
      "learning_rate": 1.9194418405573588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6438992,
      "step": 22985
    },
    {
      "epoch": 255.44444444444446,
      "grad_norm": 5.558130169447395e-07,
      "learning_rate": 1.9184869761616954e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6440400,
      "step": 22990
    },
    {
      "epoch": 255.5,
      "grad_norm": 1.6843519006215502e-06,
      "learning_rate": 1.9175322014426495e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6441808,
      "step": 22995
    },
    {
      "epoch": 255.55555555555554,
      "grad_norm": 1.0388990858700708e-06,
      "learning_rate": 1.9165775165474565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6443200,
      "step": 23000
    },
    {
      "epoch": 255.55555555555554,
      "eval_loss": 0.36029791831970215,
      "eval_runtime": 1.289,
      "eval_samples_per_second": 31.031,
      "eval_steps_per_second": 15.515,
      "num_input_tokens_seen": 6443200,
      "step": 23000
    },
    {
      "epoch": 255.61111111111111,
      "grad_norm": 4.2058019289470394e-07,
      "learning_rate": 1.9156229216233434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6444592,
      "step": 23005
    },
    {
      "epoch": 255.66666666666666,
      "grad_norm": 4.057166052007233e-07,
      "learning_rate": 1.9146684168175184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6445936,
      "step": 23010
    },
    {
      "epoch": 255.72222222222223,
      "grad_norm": 5.692679110325116e-07,
      "learning_rate": 1.9137140022771796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6447392,
      "step": 23015
    },
    {
      "epoch": 255.77777777777777,
      "grad_norm": 7.072217158565763e-07,
      "learning_rate": 1.9127596781495103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6448784,
      "step": 23020
    },
    {
      "epoch": 255.83333333333334,
      "grad_norm": 2.3655377390241483e-06,
      "learning_rate": 1.9118054445816767e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6450176,
      "step": 23025
    },
    {
      "epoch": 255.88888888888889,
      "grad_norm": 5.353821279641124e-07,
      "learning_rate": 1.9108513017208356e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6451600,
      "step": 23030
    },
    {
      "epoch": 255.94444444444446,
      "grad_norm": 1.7175140101244324e-06,
      "learning_rate": 1.9098972497141287e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6453008,
      "step": 23035
    },
    {
      "epoch": 256.0,
      "grad_norm": 4.514612328421208e-07,
      "learning_rate": 1.9089432887086806e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6454416,
      "step": 23040
    },
    {
      "epoch": 256.05555555555554,
      "grad_norm": 4.829901172342943e-07,
      "learning_rate": 1.9079894188516056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6455824,
      "step": 23045
    },
    {
      "epoch": 256.1111111111111,
      "grad_norm": 6.011650839354843e-07,
      "learning_rate": 1.907035640290002e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6457216,
      "step": 23050
    },
    {
      "epoch": 256.1666666666667,
      "grad_norm": 5.166168079995259e-07,
      "learning_rate": 1.9060819531709534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6458624,
      "step": 23055
    },
    {
      "epoch": 256.22222222222223,
      "grad_norm": 1.003172997116053e-06,
      "learning_rate": 1.9051283576415325e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6460048,
      "step": 23060
    },
    {
      "epoch": 256.27777777777777,
      "grad_norm": 5.147849151398987e-07,
      "learning_rate": 1.904174853848793e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6461536,
      "step": 23065
    },
    {
      "epoch": 256.3333333333333,
      "grad_norm": 5.81182291625737e-07,
      "learning_rate": 1.903221441939779e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6462928,
      "step": 23070
    },
    {
      "epoch": 256.3888888888889,
      "grad_norm": 9.773407327884343e-07,
      "learning_rate": 1.9022681220615194e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6464336,
      "step": 23075
    },
    {
      "epoch": 256.44444444444446,
      "grad_norm": 9.307423738391662e-07,
      "learning_rate": 1.9013148943610255e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6465712,
      "step": 23080
    },
    {
      "epoch": 256.5,
      "grad_norm": 4.651834331070859e-07,
      "learning_rate": 1.9003617589852998e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6467120,
      "step": 23085
    },
    {
      "epoch": 256.55555555555554,
      "grad_norm": 5.679980290551612e-07,
      "learning_rate": 1.899408716081326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6468464,
      "step": 23090
    },
    {
      "epoch": 256.6111111111111,
      "grad_norm": 5.370977191887505e-07,
      "learning_rate": 1.898455765796075e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6469856,
      "step": 23095
    },
    {
      "epoch": 256.6666666666667,
      "grad_norm": 9.238769393959956e-07,
      "learning_rate": 1.8975029082765053e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6471232,
      "step": 23100
    },
    {
      "epoch": 256.72222222222223,
      "grad_norm": 6.024836238793796e-07,
      "learning_rate": 1.8965501436695577e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6472624,
      "step": 23105
    },
    {
      "epoch": 256.77777777777777,
      "grad_norm": 6.691145131298981e-07,
      "learning_rate": 1.895597472122161e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6474016,
      "step": 23110
    },
    {
      "epoch": 256.8333333333333,
      "grad_norm": 4.939763016409415e-07,
      "learning_rate": 1.894644893781231e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6475424,
      "step": 23115
    },
    {
      "epoch": 256.8888888888889,
      "grad_norm": 2.2274866751104128e-06,
      "learning_rate": 1.893692408793665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6476848,
      "step": 23120
    },
    {
      "epoch": 256.94444444444446,
      "grad_norm": 6.180447940096201e-07,
      "learning_rate": 1.8927400173063493e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6478272,
      "step": 23125
    },
    {
      "epoch": 257.0,
      "grad_norm": 5.817142891828553e-07,
      "learning_rate": 1.891787719466154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6479632,
      "step": 23130
    },
    {
      "epoch": 257.05555555555554,
      "grad_norm": 5.525058668354177e-07,
      "learning_rate": 1.8908355154199346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6481008,
      "step": 23135
    },
    {
      "epoch": 257.1111111111111,
      "grad_norm": 9.968563290385646e-07,
      "learning_rate": 1.8898834053145357e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6482416,
      "step": 23140
    },
    {
      "epoch": 257.1666666666667,
      "grad_norm": 5.477970148604072e-07,
      "learning_rate": 1.8889313892967813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6483808,
      "step": 23145
    },
    {
      "epoch": 257.22222222222223,
      "grad_norm": 1.7261016864722478e-06,
      "learning_rate": 1.8879794675134863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6485184,
      "step": 23150
    },
    {
      "epoch": 257.27777777777777,
      "grad_norm": 5.92214689731918e-07,
      "learning_rate": 1.8870276401114494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6486592,
      "step": 23155
    },
    {
      "epoch": 257.3333333333333,
      "grad_norm": 2.3774139208398992e-06,
      "learning_rate": 1.886075907237453e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6487984,
      "step": 23160
    },
    {
      "epoch": 257.3888888888889,
      "grad_norm": 6.503925078504835e-07,
      "learning_rate": 1.8851242690382672e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6489392,
      "step": 23165
    },
    {
      "epoch": 257.44444444444446,
      "grad_norm": 1.0324932873118087e-06,
      "learning_rate": 1.884172725660645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6490816,
      "step": 23170
    },
    {
      "epoch": 257.5,
      "grad_norm": 1.5036260947454139e-06,
      "learning_rate": 1.8832212772513277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6492192,
      "step": 23175
    },
    {
      "epoch": 257.55555555555554,
      "grad_norm": 5.677704848494614e-07,
      "learning_rate": 1.8822699239570414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6493568,
      "step": 23180
    },
    {
      "epoch": 257.6111111111111,
      "grad_norm": 6.760042765563412e-07,
      "learning_rate": 1.8813186659244943e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6494960,
      "step": 23185
    },
    {
      "epoch": 257.6666666666667,
      "grad_norm": 8.913945634958509e-07,
      "learning_rate": 1.880367503300385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6496304,
      "step": 23190
    },
    {
      "epoch": 257.72222222222223,
      "grad_norm": 1.1509534942888422e-06,
      "learning_rate": 1.8794164362313927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6497664,
      "step": 23195
    },
    {
      "epoch": 257.77777777777777,
      "grad_norm": 4.868895757681457e-07,
      "learning_rate": 1.878465464864185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6499088,
      "step": 23200
    },
    {
      "epoch": 257.77777777777777,
      "eval_loss": 0.3026605546474457,
      "eval_runtime": 1.2927,
      "eval_samples_per_second": 30.942,
      "eval_steps_per_second": 15.471,
      "num_input_tokens_seen": 6499088,
      "step": 23200
    },
    {
      "epoch": 257.8333333333333,
      "grad_norm": 5.76857928535901e-07,
      "learning_rate": 1.877514589345414e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6500544,
      "step": 23205
    },
    {
      "epoch": 257.8888888888889,
      "grad_norm": 4.967249651599559e-07,
      "learning_rate": 1.876563809821715e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6501968,
      "step": 23210
    },
    {
      "epoch": 257.94444444444446,
      "grad_norm": 1.4989699366196874e-06,
      "learning_rate": 1.8756131264397106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6503296,
      "step": 23215
    },
    {
      "epoch": 258.0,
      "grad_norm": 5.61618378469575e-07,
      "learning_rate": 1.87466253934601e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6504704,
      "step": 23220
    },
    {
      "epoch": 258.05555555555554,
      "grad_norm": 1.5297455320251174e-06,
      "learning_rate": 1.8737120486872033e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6506064,
      "step": 23225
    },
    {
      "epoch": 258.1111111111111,
      "grad_norm": 6.020291607455874e-07,
      "learning_rate": 1.8727616546098696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6507456,
      "step": 23230
    },
    {
      "epoch": 258.1666666666667,
      "grad_norm": 5.169062546883652e-07,
      "learning_rate": 1.8718113572605716e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6508848,
      "step": 23235
    },
    {
      "epoch": 258.22222222222223,
      "grad_norm": 1.6680728549545165e-06,
      "learning_rate": 1.8708611567858554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6510272,
      "step": 23240
    },
    {
      "epoch": 258.27777777777777,
      "grad_norm": 6.116109716458595e-07,
      "learning_rate": 1.8699110533322565e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6511728,
      "step": 23245
    },
    {
      "epoch": 258.3333333333333,
      "grad_norm": 1.1181011814187514e-06,
      "learning_rate": 1.8689610470462897e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6513152,
      "step": 23250
    },
    {
      "epoch": 258.3888888888889,
      "grad_norm": 5.457937390929146e-07,
      "learning_rate": 1.8680111380744604e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6514544,
      "step": 23255
    },
    {
      "epoch": 258.44444444444446,
      "grad_norm": 4.255453518453578e-07,
      "learning_rate": 1.8670613265632564e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6515920,
      "step": 23260
    },
    {
      "epoch": 258.5,
      "grad_norm": 2.009157242355286e-06,
      "learning_rate": 1.866111612659149e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6517280,
      "step": 23265
    },
    {
      "epoch": 258.55555555555554,
      "grad_norm": 1.6814340142445872e-06,
      "learning_rate": 1.8651619965085967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6518720,
      "step": 23270
    },
    {
      "epoch": 258.6111111111111,
      "grad_norm": 5.409524987953773e-07,
      "learning_rate": 1.8642124782580433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6520144,
      "step": 23275
    },
    {
      "epoch": 258.6666666666667,
      "grad_norm": 9.819987099035643e-07,
      "learning_rate": 1.8632630580539144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6521552,
      "step": 23280
    },
    {
      "epoch": 258.72222222222223,
      "grad_norm": 1.5009453591119382e-06,
      "learning_rate": 1.862313736042625e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6522928,
      "step": 23285
    },
    {
      "epoch": 258.77777777777777,
      "grad_norm": 1.0024205039371736e-06,
      "learning_rate": 1.8613645123705703e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6524336,
      "step": 23290
    },
    {
      "epoch": 258.8333333333333,
      "grad_norm": 6.116530926192354e-07,
      "learning_rate": 1.8604153871841328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6525728,
      "step": 23295
    },
    {
      "epoch": 258.8888888888889,
      "grad_norm": 5.979926527288626e-07,
      "learning_rate": 1.859466360629682e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6527120,
      "step": 23300
    },
    {
      "epoch": 258.94444444444446,
      "grad_norm": 3.5485527405398898e-06,
      "learning_rate": 1.8585174328535666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6528496,
      "step": 23305
    },
    {
      "epoch": 259.0,
      "grad_norm": 5.692477884622349e-07,
      "learning_rate": 1.857568604002124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6529920,
      "step": 23310
    },
    {
      "epoch": 259.05555555555554,
      "grad_norm": 2.1299060790624935e-06,
      "learning_rate": 1.8566198742216774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6531264,
      "step": 23315
    },
    {
      "epoch": 259.1111111111111,
      "grad_norm": 5.431895715446444e-07,
      "learning_rate": 1.85567124365853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6532688,
      "step": 23320
    },
    {
      "epoch": 259.1666666666667,
      "grad_norm": 4.797506107934169e-07,
      "learning_rate": 1.854722712458975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6534112,
      "step": 23325
    },
    {
      "epoch": 259.22222222222223,
      "grad_norm": 3.5949963148596e-06,
      "learning_rate": 1.853774280769286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6535536,
      "step": 23330
    },
    {
      "epoch": 259.27777777777777,
      "grad_norm": 5.580068318522535e-07,
      "learning_rate": 1.852825948735724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6536944,
      "step": 23335
    },
    {
      "epoch": 259.3333333333333,
      "grad_norm": 2.2157651073939633e-06,
      "learning_rate": 1.851877716504534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6538320,
      "step": 23340
    },
    {
      "epoch": 259.3888888888889,
      "grad_norm": 8.383285035051813e-07,
      "learning_rate": 1.8509295842219448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6539728,
      "step": 23345
    },
    {
      "epoch": 259.44444444444446,
      "grad_norm": 3.8544166613974085e-07,
      "learning_rate": 1.8499815520341697e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6541136,
      "step": 23350
    },
    {
      "epoch": 259.5,
      "grad_norm": 4.998112785870035e-07,
      "learning_rate": 1.8490336200874094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6542560,
      "step": 23355
    },
    {
      "epoch": 259.55555555555554,
      "grad_norm": 6.153927074592502e-07,
      "learning_rate": 1.848085788527844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6543968,
      "step": 23360
    },
    {
      "epoch": 259.6111111111111,
      "grad_norm": 1.5381974662886932e-06,
      "learning_rate": 1.847138057501644e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6545376,
      "step": 23365
    },
    {
      "epoch": 259.6666666666667,
      "grad_norm": 5.211140887695365e-07,
      "learning_rate": 1.8461904271549582e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6546784,
      "step": 23370
    },
    {
      "epoch": 259.72222222222223,
      "grad_norm": 5.791609964944655e-07,
      "learning_rate": 1.845242897633926e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6548208,
      "step": 23375
    },
    {
      "epoch": 259.77777777777777,
      "grad_norm": 6.179226375024882e-07,
      "learning_rate": 1.844295469084667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6549584,
      "step": 23380
    },
    {
      "epoch": 259.8333333333333,
      "grad_norm": 4.457034208371624e-07,
      "learning_rate": 1.843348141653286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6550944,
      "step": 23385
    },
    {
      "epoch": 259.8888888888889,
      "grad_norm": 1.6887474885152187e-06,
      "learning_rate": 1.842400915485874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6552336,
      "step": 23390
    },
    {
      "epoch": 259.94444444444446,
      "grad_norm": 4.987965098735003e-07,
      "learning_rate": 1.8414537907285053e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6553744,
      "step": 23395
    },
    {
      "epoch": 260.0,
      "grad_norm": 2.000904260057723e-06,
      "learning_rate": 1.840506767527237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6555184,
      "step": 23400
    },
    {
      "epoch": 260.0,
      "eval_loss": 0.34345296025276184,
      "eval_runtime": 1.2809,
      "eval_samples_per_second": 31.228,
      "eval_steps_per_second": 15.614,
      "num_input_tokens_seen": 6555184,
      "step": 23400
    },
    {
      "epoch": 260.05555555555554,
      "grad_norm": 4.493645633374399e-07,
      "learning_rate": 1.8395598460281137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6556624,
      "step": 23405
    },
    {
      "epoch": 260.1111111111111,
      "grad_norm": 6.141270887383143e-07,
      "learning_rate": 1.838613026377161e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6558080,
      "step": 23410
    },
    {
      "epoch": 260.1666666666667,
      "grad_norm": 5.909567448725284e-07,
      "learning_rate": 1.8376663087203917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6559472,
      "step": 23415
    },
    {
      "epoch": 260.22222222222223,
      "grad_norm": 5.196338292989822e-07,
      "learning_rate": 1.8367196932038014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6560912,
      "step": 23420
    },
    {
      "epoch": 260.27777777777777,
      "grad_norm": 5.319927822711179e-07,
      "learning_rate": 1.8357731799733686e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6562272,
      "step": 23425
    },
    {
      "epoch": 260.3333333333333,
      "grad_norm": 5.522599622054258e-07,
      "learning_rate": 1.8348267691750586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6563696,
      "step": 23430
    },
    {
      "epoch": 260.3888888888889,
      "grad_norm": 1.7683109945210163e-06,
      "learning_rate": 1.833880460954821e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6565088,
      "step": 23435
    },
    {
      "epoch": 260.44444444444446,
      "grad_norm": 1.0545284112595255e-06,
      "learning_rate": 1.8329342554585866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6566464,
      "step": 23440
    },
    {
      "epoch": 260.5,
      "grad_norm": 6.679750299554144e-07,
      "learning_rate": 1.8319881528322735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6567840,
      "step": 23445
    },
    {
      "epoch": 260.55555555555554,
      "grad_norm": 5.53803147340659e-07,
      "learning_rate": 1.8310421532217815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6569248,
      "step": 23450
    },
    {
      "epoch": 260.6111111111111,
      "grad_norm": 5.437756840365182e-07,
      "learning_rate": 1.8300962567729958e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6570672,
      "step": 23455
    },
    {
      "epoch": 260.6666666666667,
      "grad_norm": 5.851594551131711e-07,
      "learning_rate": 1.8291504636317866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6572048,
      "step": 23460
    },
    {
      "epoch": 260.72222222222223,
      "grad_norm": 1.9296173832117347e-06,
      "learning_rate": 1.8282047739440055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6573472,
      "step": 23465
    },
    {
      "epoch": 260.77777777777777,
      "grad_norm": 5.179718414183299e-07,
      "learning_rate": 1.8272591878554903e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6574864,
      "step": 23470
    },
    {
      "epoch": 260.8333333333333,
      "grad_norm": 5.09050266828126e-07,
      "learning_rate": 1.8263137055120638e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6576272,
      "step": 23475
    },
    {
      "epoch": 260.8888888888889,
      "grad_norm": 4.367639974134363e-07,
      "learning_rate": 1.8253683270595295e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6577680,
      "step": 23480
    },
    {
      "epoch": 260.94444444444446,
      "grad_norm": 2.0124216462136246e-06,
      "learning_rate": 1.824423052643677e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6579040,
      "step": 23485
    },
    {
      "epoch": 261.0,
      "grad_norm": 5.150841957402008e-07,
      "learning_rate": 1.82347788241028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6580432,
      "step": 23490
    },
    {
      "epoch": 261.05555555555554,
      "grad_norm": 4.989468607163872e-07,
      "learning_rate": 1.8225328165050942e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6581808,
      "step": 23495
    },
    {
      "epoch": 261.1111111111111,
      "grad_norm": 4.898728889202175e-07,
      "learning_rate": 1.821587855073863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6583232,
      "step": 23500
    },
    {
      "epoch": 261.1666666666667,
      "grad_norm": 1.5130881365621462e-06,
      "learning_rate": 1.8206429982623086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6584608,
      "step": 23505
    },
    {
      "epoch": 261.22222222222223,
      "grad_norm": 6.150658578008006e-07,
      "learning_rate": 1.8196982462161416e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6586000,
      "step": 23510
    },
    {
      "epoch": 261.27777777777777,
      "grad_norm": 6.196501090016682e-07,
      "learning_rate": 1.818753599081055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6587408,
      "step": 23515
    },
    {
      "epoch": 261.3333333333333,
      "grad_norm": 1.017476165543485e-06,
      "learning_rate": 1.817809057002724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6588864,
      "step": 23520
    },
    {
      "epoch": 261.3888888888889,
      "grad_norm": 5.919992531744356e-07,
      "learning_rate": 1.8168646201268096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6590272,
      "step": 23525
    },
    {
      "epoch": 261.44444444444446,
      "grad_norm": 3.6868125334876822e-06,
      "learning_rate": 1.8159202885989557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6591632,
      "step": 23530
    },
    {
      "epoch": 261.5,
      "grad_norm": 1.5264690773619805e-06,
      "learning_rate": 1.814976062564789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6593008,
      "step": 23535
    },
    {
      "epoch": 261.55555555555554,
      "grad_norm": 1.136348259933584e-06,
      "learning_rate": 1.8140319421699234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6594384,
      "step": 23540
    },
    {
      "epoch": 261.6111111111111,
      "grad_norm": 1.0724014600782539e-06,
      "learning_rate": 1.8130879275599515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6595808,
      "step": 23545
    },
    {
      "epoch": 261.6666666666667,
      "grad_norm": 4.978027732249757e-07,
      "learning_rate": 1.8121440188804544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6597264,
      "step": 23550
    },
    {
      "epoch": 261.72222222222223,
      "grad_norm": 4.58432623418048e-07,
      "learning_rate": 1.811200216276993e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6598640,
      "step": 23555
    },
    {
      "epoch": 261.77777777777777,
      "grad_norm": 1.0063833997264737e-06,
      "learning_rate": 1.810256519895115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6600064,
      "step": 23560
    },
    {
      "epoch": 261.8333333333333,
      "grad_norm": 5.535467835215968e-07,
      "learning_rate": 1.8093129298803494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6601440,
      "step": 23565
    },
    {
      "epoch": 261.8888888888889,
      "grad_norm": 5.643464646709617e-07,
      "learning_rate": 1.808369446378209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6602848,
      "step": 23570
    },
    {
      "epoch": 261.94444444444446,
      "grad_norm": 5.514760346159164e-07,
      "learning_rate": 1.8074260695341914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6604240,
      "step": 23575
    },
    {
      "epoch": 262.0,
      "grad_norm": 9.690713795862393e-07,
      "learning_rate": 1.8064827994937782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6605632,
      "step": 23580
    },
    {
      "epoch": 262.05555555555554,
      "grad_norm": 5.881614697500481e-07,
      "learning_rate": 1.8055396364024317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6606992,
      "step": 23585
    },
    {
      "epoch": 262.1111111111111,
      "grad_norm": 5.265059144221595e-07,
      "learning_rate": 1.804596580405601e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6608416,
      "step": 23590
    },
    {
      "epoch": 262.1666666666667,
      "grad_norm": 9.281317261411459e-07,
      "learning_rate": 1.8036536316487174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6609872,
      "step": 23595
    },
    {
      "epoch": 262.22222222222223,
      "grad_norm": 5.062686909695913e-07,
      "learning_rate": 1.802710790277193e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6611312,
      "step": 23600
    },
    {
      "epoch": 262.22222222222223,
      "eval_loss": 0.3032988905906677,
      "eval_runtime": 1.3009,
      "eval_samples_per_second": 30.747,
      "eval_steps_per_second": 15.374,
      "num_input_tokens_seen": 6611312,
      "step": 23600
    },
    {
      "epoch": 262.27777777777777,
      "grad_norm": 5.047069748798094e-07,
      "learning_rate": 1.801768056436429e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6612640,
      "step": 23605
    },
    {
      "epoch": 262.3333333333333,
      "grad_norm": 2.224696117991698e-06,
      "learning_rate": 1.8008254302718035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6614064,
      "step": 23610
    },
    {
      "epoch": 262.3888888888889,
      "grad_norm": 4.6121806462906534e-07,
      "learning_rate": 1.7998829119286837e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6615440,
      "step": 23615
    },
    {
      "epoch": 262.44444444444446,
      "grad_norm": 5.327522103470983e-07,
      "learning_rate": 1.798940501552418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6616816,
      "step": 23620
    },
    {
      "epoch": 262.5,
      "grad_norm": 1.4653478501713835e-06,
      "learning_rate": 1.797998199288336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6618160,
      "step": 23625
    },
    {
      "epoch": 262.55555555555554,
      "grad_norm": 4.775141633217572e-07,
      "learning_rate": 1.7970560052817543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6619600,
      "step": 23630
    },
    {
      "epoch": 262.6111111111111,
      "grad_norm": 2.169558001696714e-06,
      "learning_rate": 1.7961139196779702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6621024,
      "step": 23635
    },
    {
      "epoch": 262.6666666666667,
      "grad_norm": 6.531349754368421e-07,
      "learning_rate": 1.7951719426222647e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6622448,
      "step": 23640
    },
    {
      "epoch": 262.72222222222223,
      "grad_norm": 4.82554071368213e-07,
      "learning_rate": 1.794230074259904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6623872,
      "step": 23645
    },
    {
      "epoch": 262.77777777777777,
      "grad_norm": 5.910857225899235e-07,
      "learning_rate": 1.7932883147361336e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6625264,
      "step": 23650
    },
    {
      "epoch": 262.8333333333333,
      "grad_norm": 1.7116007029471803e-06,
      "learning_rate": 1.7923466641961865e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6626640,
      "step": 23655
    },
    {
      "epoch": 262.8888888888889,
      "grad_norm": 6.036040076651261e-07,
      "learning_rate": 1.791405122785278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6628096,
      "step": 23660
    },
    {
      "epoch": 262.94444444444446,
      "grad_norm": 5.222150889494515e-07,
      "learning_rate": 1.7904636906486037e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6629440,
      "step": 23665
    },
    {
      "epoch": 263.0,
      "grad_norm": 4.1504597447783453e-07,
      "learning_rate": 1.7895223679313448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6630800,
      "step": 23670
    },
    {
      "epoch": 263.05555555555554,
      "grad_norm": 1.035978698382678e-06,
      "learning_rate": 1.7885811547786653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6632192,
      "step": 23675
    },
    {
      "epoch": 263.1111111111111,
      "grad_norm": 5.487462431119638e-07,
      "learning_rate": 1.7876400513357115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6633536,
      "step": 23680
    },
    {
      "epoch": 263.1666666666667,
      "grad_norm": 6.186957079989952e-07,
      "learning_rate": 1.7866990577476146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6634928,
      "step": 23685
    },
    {
      "epoch": 263.22222222222223,
      "grad_norm": 9.835163155003102e-07,
      "learning_rate": 1.7857581741594863e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6636336,
      "step": 23690
    },
    {
      "epoch": 263.27777777777777,
      "grad_norm": 5.461344585455663e-07,
      "learning_rate": 1.7848174007164237e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6637680,
      "step": 23695
    },
    {
      "epoch": 263.3333333333333,
      "grad_norm": 5.145207637724525e-07,
      "learning_rate": 1.7838767375635052e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6639152,
      "step": 23700
    },
    {
      "epoch": 263.3888888888889,
      "grad_norm": 4.5333555931392766e-07,
      "learning_rate": 1.782936184845793e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6640560,
      "step": 23705
    },
    {
      "epoch": 263.44444444444446,
      "grad_norm": 4.4180458758091845e-07,
      "learning_rate": 1.7819957427083334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6641904,
      "step": 23710
    },
    {
      "epoch": 263.5,
      "grad_norm": 5.004058039048687e-07,
      "learning_rate": 1.7810554112961516e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6643328,
      "step": 23715
    },
    {
      "epoch": 263.55555555555554,
      "grad_norm": 1.037689798977226e-06,
      "learning_rate": 1.7801151907542607e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6644720,
      "step": 23720
    },
    {
      "epoch": 263.6111111111111,
      "grad_norm": 1.7076384892789065e-06,
      "learning_rate": 1.7791750812276547e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6646128,
      "step": 23725
    },
    {
      "epoch": 263.6666666666667,
      "grad_norm": 9.086635941457644e-07,
      "learning_rate": 1.778235082861309e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6647520,
      "step": 23730
    },
    {
      "epoch": 263.72222222222223,
      "grad_norm": 3.587561650419957e-06,
      "learning_rate": 1.777295195800184e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6648896,
      "step": 23735
    },
    {
      "epoch": 263.77777777777777,
      "grad_norm": 5.717995463783154e-07,
      "learning_rate": 1.7763554201892215e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6650304,
      "step": 23740
    },
    {
      "epoch": 263.8333333333333,
      "grad_norm": 6.767302238586126e-07,
      "learning_rate": 1.7754157561733476e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6651680,
      "step": 23745
    },
    {
      "epoch": 263.8888888888889,
      "grad_norm": 5.182059794606175e-07,
      "learning_rate": 1.7744762038974702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6653056,
      "step": 23750
    },
    {
      "epoch": 263.94444444444446,
      "grad_norm": 5.814397923131764e-07,
      "learning_rate": 1.7735367635064788e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6654544,
      "step": 23755
    },
    {
      "epoch": 264.0,
      "grad_norm": 1.7097687532441341e-06,
      "learning_rate": 1.7725974351452474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6655968,
      "step": 23760
    },
    {
      "epoch": 264.05555555555554,
      "grad_norm": 2.399698587396415e-06,
      "learning_rate": 1.771658218958634e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6657376,
      "step": 23765
    },
    {
      "epoch": 264.1111111111111,
      "grad_norm": 9.320447134086862e-07,
      "learning_rate": 1.770719115091475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6658800,
      "step": 23770
    },
    {
      "epoch": 264.1666666666667,
      "grad_norm": 5.601340831162815e-07,
      "learning_rate": 1.7697801236885935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6660192,
      "step": 23775
    },
    {
      "epoch": 264.22222222222223,
      "grad_norm": 1.0400824521639151e-06,
      "learning_rate": 1.7688412448947944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6661552,
      "step": 23780
    },
    {
      "epoch": 264.27777777777777,
      "grad_norm": 8.952415555540938e-07,
      "learning_rate": 1.767902478854862e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6662928,
      "step": 23785
    },
    {
      "epoch": 264.3333333333333,
      "grad_norm": 9.65592562351958e-07,
      "learning_rate": 1.766963825713569e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6664304,
      "step": 23790
    },
    {
      "epoch": 264.3888888888889,
      "grad_norm": 6.620517751798616e-07,
      "learning_rate": 1.766025285615665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6665712,
      "step": 23795
    },
    {
      "epoch": 264.44444444444446,
      "grad_norm": 6.307554940576665e-07,
      "learning_rate": 1.7650868587058854e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6667104,
      "step": 23800
    },
    {
      "epoch": 264.44444444444446,
      "eval_loss": 0.307365745306015,
      "eval_runtime": 1.2901,
      "eval_samples_per_second": 31.005,
      "eval_steps_per_second": 15.503,
      "num_input_tokens_seen": 6667104,
      "step": 23800
    },
    {
      "epoch": 264.5,
      "grad_norm": 9.42806082093739e-07,
      "learning_rate": 1.7641485451289484e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6668528,
      "step": 23805
    },
    {
      "epoch": 264.55555555555554,
      "grad_norm": 5.166744472262508e-07,
      "learning_rate": 1.7632103450295534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6669904,
      "step": 23810
    },
    {
      "epoch": 264.6111111111111,
      "grad_norm": 6.568170647369698e-07,
      "learning_rate": 1.762272258552381e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6671328,
      "step": 23815
    },
    {
      "epoch": 264.6666666666667,
      "grad_norm": 5.075133344689675e-07,
      "learning_rate": 1.7613342858420988e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6672704,
      "step": 23820
    },
    {
      "epoch": 264.72222222222223,
      "grad_norm": 1.4844576980976854e-06,
      "learning_rate": 1.760396427043351e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6674112,
      "step": 23825
    },
    {
      "epoch": 264.77777777777777,
      "grad_norm": 1.0063304216600955e-06,
      "learning_rate": 1.7594586823007696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6675504,
      "step": 23830
    },
    {
      "epoch": 264.8333333333333,
      "grad_norm": 4.794746359948476e-07,
      "learning_rate": 1.7585210517589646e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6676944,
      "step": 23835
    },
    {
      "epoch": 264.8888888888889,
      "grad_norm": 5.359524948289618e-07,
      "learning_rate": 1.7575835355625314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6678416,
      "step": 23840
    },
    {
      "epoch": 264.94444444444446,
      "grad_norm": 4.24175141233718e-07,
      "learning_rate": 1.756646133856048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6679760,
      "step": 23845
    },
    {
      "epoch": 265.0,
      "grad_norm": 8.422088626502955e-07,
      "learning_rate": 1.7557088467840714e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6681136,
      "step": 23850
    },
    {
      "epoch": 265.05555555555554,
      "grad_norm": 2.2286258172243834e-06,
      "learning_rate": 1.7547716744911438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6682496,
      "step": 23855
    },
    {
      "epoch": 265.1111111111111,
      "grad_norm": 5.114479790790938e-07,
      "learning_rate": 1.7538346171217902e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6683872,
      "step": 23860
    },
    {
      "epoch": 265.1666666666667,
      "grad_norm": 1.7100916238632635e-06,
      "learning_rate": 1.7528976748205146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6685280,
      "step": 23865
    },
    {
      "epoch": 265.22222222222223,
      "grad_norm": 5.054211555943766e-07,
      "learning_rate": 1.751960847731807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6686672,
      "step": 23870
    },
    {
      "epoch": 265.27777777777777,
      "grad_norm": 4.1714014287208556e-07,
      "learning_rate": 1.7510241360001362e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6688112,
      "step": 23875
    },
    {
      "epoch": 265.3333333333333,
      "grad_norm": 5.39121060683101e-07,
      "learning_rate": 1.7500875397699562e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6689552,
      "step": 23880
    },
    {
      "epoch": 265.3888888888889,
      "grad_norm": 5.034546006754681e-07,
      "learning_rate": 1.7491510591857015e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6690960,
      "step": 23885
    },
    {
      "epoch": 265.44444444444446,
      "grad_norm": 2.3391773993353127e-06,
      "learning_rate": 1.7482146943917896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6692368,
      "step": 23890
    },
    {
      "epoch": 265.5,
      "grad_norm": 5.513043674909568e-07,
      "learning_rate": 1.7472784455326185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6693744,
      "step": 23895
    },
    {
      "epoch": 265.55555555555554,
      "grad_norm": 1.685097231529653e-06,
      "learning_rate": 1.746342312752572e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6695152,
      "step": 23900
    },
    {
      "epoch": 265.6111111111111,
      "grad_norm": 9.243427712135599e-07,
      "learning_rate": 1.74540629619601e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6696496,
      "step": 23905
    },
    {
      "epoch": 265.6666666666667,
      "grad_norm": 9.811876680032583e-07,
      "learning_rate": 1.7444703960072815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6697888,
      "step": 23910
    },
    {
      "epoch": 265.72222222222223,
      "grad_norm": 1.49434924878733e-06,
      "learning_rate": 1.7435346123307118e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6699312,
      "step": 23915
    },
    {
      "epoch": 265.77777777777777,
      "grad_norm": 4.3501393065525917e-07,
      "learning_rate": 1.742598945310611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6700672,
      "step": 23920
    },
    {
      "epoch": 265.8333333333333,
      "grad_norm": 5.481178959598765e-07,
      "learning_rate": 1.741663395091272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6702112,
      "step": 23925
    },
    {
      "epoch": 265.8888888888889,
      "grad_norm": 1.7298768852924695e-06,
      "learning_rate": 1.7407279618169657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6703504,
      "step": 23930
    },
    {
      "epoch": 265.94444444444446,
      "grad_norm": 2.1567241219599964e-06,
      "learning_rate": 1.73979264563195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6704928,
      "step": 23935
    },
    {
      "epoch": 266.0,
      "grad_norm": 4.229212891004863e-07,
      "learning_rate": 1.7388574466804625e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6706368,
      "step": 23940
    },
    {
      "epoch": 266.05555555555554,
      "grad_norm": 6.780498438274662e-07,
      "learning_rate": 1.7379223651067207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6707760,
      "step": 23945
    },
    {
      "epoch": 266.1111111111111,
      "grad_norm": 5.7310165857416e-07,
      "learning_rate": 1.736987401054928e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6709168,
      "step": 23950
    },
    {
      "epoch": 266.1666666666667,
      "grad_norm": 4.94246478410787e-07,
      "learning_rate": 1.736052554669266e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6710576,
      "step": 23955
    },
    {
      "epoch": 266.22222222222223,
      "grad_norm": 1.0120814977199188e-06,
      "learning_rate": 1.7351178260939007e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6711984,
      "step": 23960
    },
    {
      "epoch": 266.27777777777777,
      "grad_norm": 2.285687514813617e-06,
      "learning_rate": 1.7341832154729794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6713360,
      "step": 23965
    },
    {
      "epoch": 266.3333333333333,
      "grad_norm": 4.870885277341586e-07,
      "learning_rate": 1.7332487229506286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6714704,
      "step": 23970
    },
    {
      "epoch": 266.3888888888889,
      "grad_norm": 1.6954654711298645e-06,
      "learning_rate": 1.732314348670961e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6716080,
      "step": 23975
    },
    {
      "epoch": 266.44444444444446,
      "grad_norm": 4.881212021246029e-07,
      "learning_rate": 1.7313800927780686e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6717440,
      "step": 23980
    },
    {
      "epoch": 266.5,
      "grad_norm": 4.577835568397859e-07,
      "learning_rate": 1.7304459554160245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6718864,
      "step": 23985
    },
    {
      "epoch": 266.55555555555554,
      "grad_norm": 6.03529315412743e-07,
      "learning_rate": 1.7295119367288853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6720272,
      "step": 23990
    },
    {
      "epoch": 266.6111111111111,
      "grad_norm": 5.383852794693667e-07,
      "learning_rate": 1.728578036860688e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6721616,
      "step": 23995
    },
    {
      "epoch": 266.6666666666667,
      "grad_norm": 6.068227662581194e-07,
      "learning_rate": 1.7276442559554513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6723024,
      "step": 24000
    },
    {
      "epoch": 266.6666666666667,
      "eval_loss": 0.31588953733444214,
      "eval_runtime": 1.2887,
      "eval_samples_per_second": 31.039,
      "eval_steps_per_second": 15.52,
      "num_input_tokens_seen": 6723024,
      "step": 24000
    },
    {
      "epoch": 266.72222222222223,
      "grad_norm": 5.102222075947793e-07,
      "learning_rate": 1.726710594157177e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6724384,
      "step": 24005
    },
    {
      "epoch": 266.77777777777777,
      "grad_norm": 5.461739647216746e-07,
      "learning_rate": 1.725777051609846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6725808,
      "step": 24010
    },
    {
      "epoch": 266.8333333333333,
      "grad_norm": 1.0296195114278817e-06,
      "learning_rate": 1.7248436284574228e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6727232,
      "step": 24015
    },
    {
      "epoch": 266.8888888888889,
      "grad_norm": 2.1022749479016056e-06,
      "learning_rate": 1.723910324843855e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6728656,
      "step": 24020
    },
    {
      "epoch": 266.94444444444446,
      "grad_norm": 6.483841161752935e-07,
      "learning_rate": 1.722977140913067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6730096,
      "step": 24025
    },
    {
      "epoch": 267.0,
      "grad_norm": 5.823280844197143e-07,
      "learning_rate": 1.7220440768089688e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6731536,
      "step": 24030
    },
    {
      "epoch": 267.05555555555554,
      "grad_norm": 2.213011157436995e-06,
      "learning_rate": 1.7211111326754505e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6732928,
      "step": 24035
    },
    {
      "epoch": 267.1111111111111,
      "grad_norm": 5.763880039921787e-07,
      "learning_rate": 1.720178308656383e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6734352,
      "step": 24040
    },
    {
      "epoch": 267.1666666666667,
      "grad_norm": 6.296785386439296e-07,
      "learning_rate": 1.719245604895621e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6735776,
      "step": 24045
    },
    {
      "epoch": 267.22222222222223,
      "grad_norm": 1.5122100194275845e-06,
      "learning_rate": 1.7183130215369972e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6737168,
      "step": 24050
    },
    {
      "epoch": 267.27777777777777,
      "grad_norm": 1.0185731298406608e-06,
      "learning_rate": 1.7173805587243292e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6738576,
      "step": 24055
    },
    {
      "epoch": 267.3333333333333,
      "grad_norm": 1.6860784626260283e-06,
      "learning_rate": 1.7164482166014147e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6740000,
      "step": 24060
    },
    {
      "epoch": 267.3888888888889,
      "grad_norm": 2.3298725864151493e-06,
      "learning_rate": 1.7155159953120313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6741376,
      "step": 24065
    },
    {
      "epoch": 267.44444444444446,
      "grad_norm": 4.833897833123046e-07,
      "learning_rate": 1.714583894999941e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6742768,
      "step": 24070
    },
    {
      "epoch": 267.5,
      "grad_norm": 5.69390692817251e-07,
      "learning_rate": 1.7136519158088826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6744176,
      "step": 24075
    },
    {
      "epoch": 267.55555555555554,
      "grad_norm": 9.660965361035778e-07,
      "learning_rate": 1.712720057882581e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6745584,
      "step": 24080
    },
    {
      "epoch": 267.6111111111111,
      "grad_norm": 3.5518717140803346e-06,
      "learning_rate": 1.7117883213647413e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6746976,
      "step": 24085
    },
    {
      "epoch": 267.6666666666667,
      "grad_norm": 9.369512667944946e-07,
      "learning_rate": 1.710856706399046e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6748416,
      "step": 24090
    },
    {
      "epoch": 267.72222222222223,
      "grad_norm": 1.0040561164714745e-06,
      "learning_rate": 1.7099252131291648e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6749856,
      "step": 24095
    },
    {
      "epoch": 267.77777777777777,
      "grad_norm": 4.493582252962369e-07,
      "learning_rate": 1.708993841698744e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6751216,
      "step": 24100
    },
    {
      "epoch": 267.8333333333333,
      "grad_norm": 6.107031822466524e-07,
      "learning_rate": 1.7080625922514132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6752640,
      "step": 24105
    },
    {
      "epoch": 267.8888888888889,
      "grad_norm": 5.200809027883224e-07,
      "learning_rate": 1.7071314649307836e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6754064,
      "step": 24110
    },
    {
      "epoch": 267.94444444444446,
      "grad_norm": 2.2357785383064765e-06,
      "learning_rate": 1.7062004598804448e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6755472,
      "step": 24115
    },
    {
      "epoch": 268.0,
      "grad_norm": 4.947406523569953e-06,
      "learning_rate": 1.7052695772439702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6756896,
      "step": 24120
    },
    {
      "epoch": 268.05555555555554,
      "grad_norm": 4.7430913241441885e-07,
      "learning_rate": 1.7043388171649154e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6758304,
      "step": 24125
    },
    {
      "epoch": 268.1111111111111,
      "grad_norm": 4.1238433823309606e-07,
      "learning_rate": 1.7034081797868127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6759696,
      "step": 24130
    },
    {
      "epoch": 268.1666666666667,
      "grad_norm": 4.352397127149743e-07,
      "learning_rate": 1.70247766525318e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6761120,
      "step": 24135
    },
    {
      "epoch": 268.22222222222223,
      "grad_norm": 2.9278473334670707e-07,
      "learning_rate": 1.701547273707514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6762544,
      "step": 24140
    },
    {
      "epoch": 268.27777777777777,
      "grad_norm": 1.666346861384227e-06,
      "learning_rate": 1.7006170052932916e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6764000,
      "step": 24145
    },
    {
      "epoch": 268.3333333333333,
      "grad_norm": 4.2261555677214346e-07,
      "learning_rate": 1.6996868601539735e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6765360,
      "step": 24150
    },
    {
      "epoch": 268.3888888888889,
      "grad_norm": 5.061786509941157e-07,
      "learning_rate": 1.6987568384329977e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6766752,
      "step": 24155
    },
    {
      "epoch": 268.44444444444446,
      "grad_norm": 4.671276769840915e-07,
      "learning_rate": 1.6978269402737866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6768144,
      "step": 24160
    },
    {
      "epoch": 268.5,
      "grad_norm": 1.0665194167813752e-06,
      "learning_rate": 1.696897165819743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6769568,
      "step": 24165
    },
    {
      "epoch": 268.55555555555554,
      "grad_norm": 1.0534113243920729e-06,
      "learning_rate": 1.6959675152142487e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6770976,
      "step": 24170
    },
    {
      "epoch": 268.6111111111111,
      "grad_norm": 5.2377896508915e-07,
      "learning_rate": 1.6950379886006667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6772352,
      "step": 24175
    },
    {
      "epoch": 268.6666666666667,
      "grad_norm": 4.519459082530375e-07,
      "learning_rate": 1.6941085861223438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6773760,
      "step": 24180
    },
    {
      "epoch": 268.72222222222223,
      "grad_norm": 4.977550815965515e-07,
      "learning_rate": 1.6931793079226034e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6775184,
      "step": 24185
    },
    {
      "epoch": 268.77777777777777,
      "grad_norm": 3.021754537257948e-06,
      "learning_rate": 1.692250154144754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6776560,
      "step": 24190
    },
    {
      "epoch": 268.8333333333333,
      "grad_norm": 5.135972287462209e-07,
      "learning_rate": 1.6913211249320807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6777968,
      "step": 24195
    },
    {
      "epoch": 268.8888888888889,
      "grad_norm": 5.541108407669526e-07,
      "learning_rate": 1.6903922204278522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6779376,
      "step": 24200
    },
    {
      "epoch": 268.8888888888889,
      "eval_loss": 0.31484660506248474,
      "eval_runtime": 1.2906,
      "eval_samples_per_second": 30.994,
      "eval_steps_per_second": 15.497,
      "num_input_tokens_seen": 6779376,
      "step": 24200
    },
    {
      "epoch": 268.94444444444446,
      "grad_norm": 5.208584070715006e-07,
      "learning_rate": 1.6894634407753186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6780752,
      "step": 24205
    },
    {
      "epoch": 269.0,
      "grad_norm": 1.6457183846796397e-06,
      "learning_rate": 1.6885347861177077e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6782096,
      "step": 24210
    },
    {
      "epoch": 269.05555555555554,
      "grad_norm": 5.417687702902185e-07,
      "learning_rate": 1.6876062565982298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6783504,
      "step": 24215
    },
    {
      "epoch": 269.1111111111111,
      "grad_norm": 1.1240189223826746e-06,
      "learning_rate": 1.6866778523600774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6784912,
      "step": 24220
    },
    {
      "epoch": 269.1666666666667,
      "grad_norm": 1.0888633141803439e-06,
      "learning_rate": 1.6857495735464195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6786272,
      "step": 24225
    },
    {
      "epoch": 269.22222222222223,
      "grad_norm": 4.956586963089649e-07,
      "learning_rate": 1.6848214203004115e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6787616,
      "step": 24230
    },
    {
      "epoch": 269.27777777777777,
      "grad_norm": 5.334713932825252e-07,
      "learning_rate": 1.6838933927651835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6789024,
      "step": 24235
    },
    {
      "epoch": 269.3333333333333,
      "grad_norm": 1.7181481553052436e-06,
      "learning_rate": 1.6829654910838506e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6790432,
      "step": 24240
    },
    {
      "epoch": 269.3888888888889,
      "grad_norm": 5.155317808203108e-07,
      "learning_rate": 1.6820377153995065e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6791856,
      "step": 24245
    },
    {
      "epoch": 269.44444444444446,
      "grad_norm": 5.103238436277024e-07,
      "learning_rate": 1.681110065855226e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6793216,
      "step": 24250
    },
    {
      "epoch": 269.5,
      "grad_norm": 9.819647175390855e-07,
      "learning_rate": 1.6801825425940642e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6794608,
      "step": 24255
    },
    {
      "epoch": 269.55555555555554,
      "grad_norm": 6.316016083474096e-07,
      "learning_rate": 1.679255145759056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6796016,
      "step": 24260
    },
    {
      "epoch": 269.6111111111111,
      "grad_norm": 5.755995857725793e-07,
      "learning_rate": 1.6783278754932187e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6797440,
      "step": 24265
    },
    {
      "epoch": 269.6666666666667,
      "grad_norm": 1.9948918179579778e-06,
      "learning_rate": 1.6774007319395496e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6798848,
      "step": 24270
    },
    {
      "epoch": 269.72222222222223,
      "grad_norm": 2.0872159893770004e-06,
      "learning_rate": 1.6764737152410243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6800240,
      "step": 24275
    },
    {
      "epoch": 269.77777777777777,
      "grad_norm": 5.173822614779056e-07,
      "learning_rate": 1.6755468255406016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6801600,
      "step": 24280
    },
    {
      "epoch": 269.8333333333333,
      "grad_norm": 5.023028961659293e-07,
      "learning_rate": 1.674620062981219e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6803024,
      "step": 24285
    },
    {
      "epoch": 269.8888888888889,
      "grad_norm": 4.929125339003804e-07,
      "learning_rate": 1.6736934277057947e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6804384,
      "step": 24290
    },
    {
      "epoch": 269.94444444444446,
      "grad_norm": 5.482370397658087e-07,
      "learning_rate": 1.6727669198572286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6805776,
      "step": 24295
    },
    {
      "epoch": 270.0,
      "grad_norm": 2.1108758119225968e-06,
      "learning_rate": 1.6718405395783984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6807248,
      "step": 24300
    },
    {
      "epoch": 270.05555555555554,
      "grad_norm": 2.0481211322476156e-06,
      "learning_rate": 1.6709142870121643e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6808672,
      "step": 24305
    },
    {
      "epoch": 270.1111111111111,
      "grad_norm": 6.152958462735114e-07,
      "learning_rate": 1.669988162301367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6810032,
      "step": 24310
    },
    {
      "epoch": 270.1666666666667,
      "grad_norm": 4.178035339919006e-07,
      "learning_rate": 1.6690621655888243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6811376,
      "step": 24315
    },
    {
      "epoch": 270.22222222222223,
      "grad_norm": 6.376586156875419e-07,
      "learning_rate": 1.6681362970173386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6812800,
      "step": 24320
    },
    {
      "epoch": 270.27777777777777,
      "grad_norm": 4.6753845595048915e-07,
      "learning_rate": 1.6672105567296904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6814208,
      "step": 24325
    },
    {
      "epoch": 270.3333333333333,
      "grad_norm": 3.5277380447951145e-06,
      "learning_rate": 1.666284944868639e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6815648,
      "step": 24330
    },
    {
      "epoch": 270.3888888888889,
      "grad_norm": 1.1117009535155375e-06,
      "learning_rate": 1.665359461576927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6817040,
      "step": 24335
    },
    {
      "epoch": 270.44444444444446,
      "grad_norm": 5.824631443829276e-07,
      "learning_rate": 1.6644341069972736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6818416,
      "step": 24340
    },
    {
      "epoch": 270.5,
      "grad_norm": 4.15017609611823e-07,
      "learning_rate": 1.6635088812723813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6819792,
      "step": 24345
    },
    {
      "epoch": 270.55555555555554,
      "grad_norm": 5.421445621323073e-07,
      "learning_rate": 1.6625837845449328e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6821216,
      "step": 24350
    },
    {
      "epoch": 270.6111111111111,
      "grad_norm": 5.273132615002396e-07,
      "learning_rate": 1.6616588169575874e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6822576,
      "step": 24355
    },
    {
      "epoch": 270.6666666666667,
      "grad_norm": 2.902914275182411e-06,
      "learning_rate": 1.6607339786529878e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6824016,
      "step": 24360
    },
    {
      "epoch": 270.72222222222223,
      "grad_norm": 2.319564373465255e-06,
      "learning_rate": 1.659809269773756e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6825408,
      "step": 24365
    },
    {
      "epoch": 270.77777777777777,
      "grad_norm": 1.0174979934163275e-06,
      "learning_rate": 1.658884690462493e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6826784,
      "step": 24370
    },
    {
      "epoch": 270.8333333333333,
      "grad_norm": 5.729442591473344e-07,
      "learning_rate": 1.6579602408617813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6828192,
      "step": 24375
    },
    {
      "epoch": 270.8888888888889,
      "grad_norm": 5.501344730873825e-07,
      "learning_rate": 1.657035921114181e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6829616,
      "step": 24380
    },
    {
      "epoch": 270.94444444444446,
      "grad_norm": 5.295799496707332e-07,
      "learning_rate": 1.656111731362236e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6831024,
      "step": 24385
    },
    {
      "epoch": 271.0,
      "grad_norm": 5.761908141721506e-07,
      "learning_rate": 1.6551876717484666e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6832448,
      "step": 24390
    },
    {
      "epoch": 271.05555555555554,
      "grad_norm": 5.831561225022597e-07,
      "learning_rate": 1.6542637424153752e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6833792,
      "step": 24395
    },
    {
      "epoch": 271.1111111111111,
      "grad_norm": 5.459243084260379e-07,
      "learning_rate": 1.6533399435054418e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6835232,
      "step": 24400
    },
    {
      "epoch": 271.1111111111111,
      "eval_loss": 0.31009092926979065,
      "eval_runtime": 1.3027,
      "eval_samples_per_second": 30.706,
      "eval_steps_per_second": 15.353,
      "num_input_tokens_seen": 6835232,
      "step": 24400
    },
    {
      "epoch": 271.1666666666667,
      "grad_norm": 2.018355189647991e-06,
      "learning_rate": 1.6524162751611304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6836608,
      "step": 24405
    },
    {
      "epoch": 271.22222222222223,
      "grad_norm": 5.0776469606717e-07,
      "learning_rate": 1.6514927375248796e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6838000,
      "step": 24410
    },
    {
      "epoch": 271.27777777777777,
      "grad_norm": 4.42517801957365e-07,
      "learning_rate": 1.6505693307391127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6839392,
      "step": 24415
    },
    {
      "epoch": 271.3333333333333,
      "grad_norm": 4.2696376567619154e-07,
      "learning_rate": 1.6496460549462288e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6840800,
      "step": 24420
    },
    {
      "epoch": 271.3888888888889,
      "grad_norm": 1.0304831903340528e-06,
      "learning_rate": 1.6487229102886097e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6842176,
      "step": 24425
    },
    {
      "epoch": 271.44444444444446,
      "grad_norm": 4.948246328240202e-07,
      "learning_rate": 1.6477998969086155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6843520,
      "step": 24430
    },
    {
      "epoch": 271.5,
      "grad_norm": 9.858738394541433e-07,
      "learning_rate": 1.646877014948587e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6844944,
      "step": 24435
    },
    {
      "epoch": 271.55555555555554,
      "grad_norm": 4.186765067970555e-07,
      "learning_rate": 1.6459542645508433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6846400,
      "step": 24440
    },
    {
      "epoch": 271.6111111111111,
      "grad_norm": 4.481220230445615e-07,
      "learning_rate": 1.6450316458576852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6847776,
      "step": 24445
    },
    {
      "epoch": 271.6666666666667,
      "grad_norm": 6.17020589288586e-07,
      "learning_rate": 1.6441091590113912e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6849200,
      "step": 24450
    },
    {
      "epoch": 271.72222222222223,
      "grad_norm": 5.271036798148998e-07,
      "learning_rate": 1.6431868041542213e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6850624,
      "step": 24455
    },
    {
      "epoch": 271.77777777777777,
      "grad_norm": 6.398886398528703e-07,
      "learning_rate": 1.6422645814284123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6852048,
      "step": 24460
    },
    {
      "epoch": 271.8333333333333,
      "grad_norm": 2.0671329821198015e-06,
      "learning_rate": 1.6413424909761846e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6853440,
      "step": 24465
    },
    {
      "epoch": 271.8888888888889,
      "grad_norm": 5.963623834759346e-07,
      "learning_rate": 1.640420532939736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6854880,
      "step": 24470
    },
    {
      "epoch": 271.94444444444446,
      "grad_norm": 5.501060513779521e-07,
      "learning_rate": 1.639498707461242e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6856240,
      "step": 24475
    },
    {
      "epoch": 272.0,
      "grad_norm": 4.92674587349029e-07,
      "learning_rate": 1.6385770146828614e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6857680,
      "step": 24480
    },
    {
      "epoch": 272.05555555555554,
      "grad_norm": 9.879270237433957e-07,
      "learning_rate": 1.637655454746731e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6859072,
      "step": 24485
    },
    {
      "epoch": 272.1111111111111,
      "grad_norm": 9.63785396379535e-07,
      "learning_rate": 1.6367340277949658e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6860448,
      "step": 24490
    },
    {
      "epoch": 272.1666666666667,
      "grad_norm": 5.058892043052765e-07,
      "learning_rate": 1.635812733969663e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6861824,
      "step": 24495
    },
    {
      "epoch": 272.22222222222223,
      "grad_norm": 5.976426109555177e-07,
      "learning_rate": 1.634891573412896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6863216,
      "step": 24500
    },
    {
      "epoch": 272.27777777777777,
      "grad_norm": 1.4602438795918715e-06,
      "learning_rate": 1.6339705462667196e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6864592,
      "step": 24505
    },
    {
      "epoch": 272.3333333333333,
      "grad_norm": 1.6516172536285012e-06,
      "learning_rate": 1.633049652673169e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6865984,
      "step": 24510
    },
    {
      "epoch": 272.3888888888889,
      "grad_norm": 4.997541509510484e-07,
      "learning_rate": 1.632128892774256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6867456,
      "step": 24515
    },
    {
      "epoch": 272.44444444444446,
      "grad_norm": 5.284580879560963e-07,
      "learning_rate": 1.6312082667119737e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6868864,
      "step": 24520
    },
    {
      "epoch": 272.5,
      "grad_norm": 5.569481800193898e-07,
      "learning_rate": 1.630287774628296e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6870240,
      "step": 24525
    },
    {
      "epoch": 272.55555555555554,
      "grad_norm": 2.4071305233519524e-06,
      "learning_rate": 1.6293674166651718e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6871616,
      "step": 24530
    },
    {
      "epoch": 272.6111111111111,
      "grad_norm": 6.288825034062029e-07,
      "learning_rate": 1.6284471929645338e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6873040,
      "step": 24535
    },
    {
      "epoch": 272.6666666666667,
      "grad_norm": 6.060625992176938e-07,
      "learning_rate": 1.627527103668291e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6874448,
      "step": 24540
    },
    {
      "epoch": 272.72222222222223,
      "grad_norm": 5.195225867282716e-07,
      "learning_rate": 1.6266071489183327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6875872,
      "step": 24545
    },
    {
      "epoch": 272.77777777777777,
      "grad_norm": 4.130582738071098e-07,
      "learning_rate": 1.6256873288565283e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6877232,
      "step": 24550
    },
    {
      "epoch": 272.8333333333333,
      "grad_norm": 5.254759116724017e-07,
      "learning_rate": 1.6247676436247245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6878624,
      "step": 24555
    },
    {
      "epoch": 272.8888888888889,
      "grad_norm": 5.084392569187912e-07,
      "learning_rate": 1.6238480933647486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6880048,
      "step": 24560
    },
    {
      "epoch": 272.94444444444446,
      "grad_norm": 2.297761739100679e-06,
      "learning_rate": 1.6229286782184083e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6881408,
      "step": 24565
    },
    {
      "epoch": 273.0,
      "grad_norm": 2.127220795955509e-06,
      "learning_rate": 1.622009398327487e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6882832,
      "step": 24570
    },
    {
      "epoch": 273.05555555555554,
      "grad_norm": 5.870971335752984e-07,
      "learning_rate": 1.6210902538337502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6884224,
      "step": 24575
    },
    {
      "epoch": 273.1111111111111,
      "grad_norm": 5.414555062088766e-07,
      "learning_rate": 1.6201712448789413e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6885600,
      "step": 24580
    },
    {
      "epoch": 273.1666666666667,
      "grad_norm": 4.490906633236591e-07,
      "learning_rate": 1.6192523716047827e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6886992,
      "step": 24585
    },
    {
      "epoch": 273.22222222222223,
      "grad_norm": 4.494556833378738e-06,
      "learning_rate": 1.6183336341529776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6888352,
      "step": 24590
    },
    {
      "epoch": 273.27777777777777,
      "grad_norm": 1.7440102055843454e-06,
      "learning_rate": 1.6174150326652047e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6889728,
      "step": 24595
    },
    {
      "epoch": 273.3333333333333,
      "grad_norm": 5.97611858665914e-07,
      "learning_rate": 1.6164965672831256e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6891104,
      "step": 24600
    },
    {
      "epoch": 273.3333333333333,
      "eval_loss": 0.3030507564544678,
      "eval_runtime": 1.2906,
      "eval_samples_per_second": 30.992,
      "eval_steps_per_second": 15.496,
      "num_input_tokens_seen": 6891104,
      "step": 24600
    },
    {
      "epoch": 273.3888888888889,
      "grad_norm": 4.854845769841631e-07,
      "learning_rate": 1.6155782381483784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6892512,
      "step": 24605
    },
    {
      "epoch": 273.44444444444446,
      "grad_norm": 3.688223557674064e-07,
      "learning_rate": 1.6146600454025813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6893936,
      "step": 24610
    },
    {
      "epoch": 273.5,
      "grad_norm": 5.391650006458804e-07,
      "learning_rate": 1.6137419891873317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6895360,
      "step": 24615
    },
    {
      "epoch": 273.55555555555554,
      "grad_norm": 5.050772529102687e-07,
      "learning_rate": 1.6128240696442038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6896768,
      "step": 24620
    },
    {
      "epoch": 273.6111111111111,
      "grad_norm": 1.6494670944666723e-06,
      "learning_rate": 1.611906286914753e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6898160,
      "step": 24625
    },
    {
      "epoch": 273.6666666666667,
      "grad_norm": 5.465770414048166e-07,
      "learning_rate": 1.6109886411405144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6899600,
      "step": 24630
    },
    {
      "epoch": 273.72222222222223,
      "grad_norm": 9.57426550485252e-07,
      "learning_rate": 1.6100711324629985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6901008,
      "step": 24635
    },
    {
      "epoch": 273.77777777777777,
      "grad_norm": 5.909122933189792e-07,
      "learning_rate": 1.609153761023698e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6902448,
      "step": 24640
    },
    {
      "epoch": 273.8333333333333,
      "grad_norm": 9.9315013812884e-07,
      "learning_rate": 1.608236526964083e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6903840,
      "step": 24645
    },
    {
      "epoch": 273.8888888888889,
      "grad_norm": 6.37564255612233e-07,
      "learning_rate": 1.607319430425601e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6905248,
      "step": 24650
    },
    {
      "epoch": 273.94444444444446,
      "grad_norm": 1.0911506933553028e-06,
      "learning_rate": 1.606402471549682e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6906640,
      "step": 24655
    },
    {
      "epoch": 274.0,
      "grad_norm": 6.191313559611444e-07,
      "learning_rate": 1.6054856504777312e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6908000,
      "step": 24660
    },
    {
      "epoch": 274.05555555555554,
      "grad_norm": 1.715559278636647e-06,
      "learning_rate": 1.6045689673511334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6909408,
      "step": 24665
    },
    {
      "epoch": 274.1111111111111,
      "grad_norm": 5.464243031383376e-07,
      "learning_rate": 1.6036524223112548e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6910848,
      "step": 24670
    },
    {
      "epoch": 274.1666666666667,
      "grad_norm": 4.774495891979313e-07,
      "learning_rate": 1.602736015499436e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6912304,
      "step": 24675
    },
    {
      "epoch": 274.22222222222223,
      "grad_norm": 3.1887209388514748e-06,
      "learning_rate": 1.601819747057e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6913680,
      "step": 24680
    },
    {
      "epoch": 274.27777777777777,
      "grad_norm": 4.39766125737151e-07,
      "learning_rate": 1.6009036171252465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6915072,
      "step": 24685
    },
    {
      "epoch": 274.3333333333333,
      "grad_norm": 4.802520834346069e-07,
      "learning_rate": 1.599987625845453e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6916496,
      "step": 24690
    },
    {
      "epoch": 274.3888888888889,
      "grad_norm": 9.832431260292651e-07,
      "learning_rate": 1.599071773358879e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6917936,
      "step": 24695
    },
    {
      "epoch": 274.44444444444446,
      "grad_norm": 4.220063090087933e-07,
      "learning_rate": 1.598156059806758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6919312,
      "step": 24700
    },
    {
      "epoch": 274.5,
      "grad_norm": 5.761564807471586e-07,
      "learning_rate": 1.5972404853303062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6920720,
      "step": 24705
    },
    {
      "epoch": 274.55555555555554,
      "grad_norm": 5.554125550588651e-07,
      "learning_rate": 1.5963250500707172e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6922112,
      "step": 24710
    },
    {
      "epoch": 274.6111111111111,
      "grad_norm": 9.496000075159827e-07,
      "learning_rate": 1.5954097541691612e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6923552,
      "step": 24715
    },
    {
      "epoch": 274.6666666666667,
      "grad_norm": 4.3309687498549465e-06,
      "learning_rate": 1.5944945977667884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6924976,
      "step": 24720
    },
    {
      "epoch": 274.72222222222223,
      "grad_norm": 5.903354463043797e-07,
      "learning_rate": 1.593579581004729e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6926336,
      "step": 24725
    },
    {
      "epoch": 274.77777777777777,
      "grad_norm": 4.640604629457812e-07,
      "learning_rate": 1.592664704024088e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6927664,
      "step": 24730
    },
    {
      "epoch": 274.8333333333333,
      "grad_norm": 6.318643954728032e-07,
      "learning_rate": 1.591749966965953e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6929072,
      "step": 24735
    },
    {
      "epoch": 274.8888888888889,
      "grad_norm": 2.228082848887425e-06,
      "learning_rate": 1.5908353699713856e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6930448,
      "step": 24740
    },
    {
      "epoch": 274.94444444444446,
      "grad_norm": 2.271404355269624e-06,
      "learning_rate": 1.5899209131814298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6931856,
      "step": 24745
    },
    {
      "epoch": 275.0,
      "grad_norm": 5.69311850995291e-07,
      "learning_rate": 1.5890065967371067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6933280,
      "step": 24750
    },
    {
      "epoch": 275.05555555555554,
      "grad_norm": 6.262931719902554e-07,
      "learning_rate": 1.5880924207794144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6934736,
      "step": 24755
    },
    {
      "epoch": 275.1111111111111,
      "grad_norm": 4.2995262106160226e-07,
      "learning_rate": 1.5871783854493298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6936192,
      "step": 24760
    },
    {
      "epoch": 275.1666666666667,
      "grad_norm": 8.985091426438885e-07,
      "learning_rate": 1.5862644908878106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6937584,
      "step": 24765
    },
    {
      "epoch": 275.22222222222223,
      "grad_norm": 6.450695195781009e-07,
      "learning_rate": 1.5853507372357885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6939056,
      "step": 24770
    },
    {
      "epoch": 275.27777777777777,
      "grad_norm": 5.454129450299661e-07,
      "learning_rate": 1.5844371246341776e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6940432,
      "step": 24775
    },
    {
      "epoch": 275.3333333333333,
      "grad_norm": 4.886890110356035e-07,
      "learning_rate": 1.5835236532238674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6941840,
      "step": 24780
    },
    {
      "epoch": 275.3888888888889,
      "grad_norm": 3.0674636946059763e-06,
      "learning_rate": 1.582610323145727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6943232,
      "step": 24785
    },
    {
      "epoch": 275.44444444444446,
      "grad_norm": 4.832231184082048e-07,
      "learning_rate": 1.5816971345406035e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6944608,
      "step": 24790
    },
    {
      "epoch": 275.5,
      "grad_norm": 5.802378950647835e-07,
      "learning_rate": 1.5807840875493225e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6946032,
      "step": 24795
    },
    {
      "epoch": 275.55555555555554,
      "grad_norm": 5.398812277235265e-07,
      "learning_rate": 1.5798711823126854e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6947456,
      "step": 24800
    },
    {
      "epoch": 275.55555555555554,
      "eval_loss": 0.33908694982528687,
      "eval_runtime": 1.2906,
      "eval_samples_per_second": 30.993,
      "eval_steps_per_second": 15.496,
      "num_input_tokens_seen": 6947456,
      "step": 24800
    },
    {
      "epoch": 275.6111111111111,
      "grad_norm": 6.694330068057752e-07,
      "learning_rate": 1.578958418971477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6948880,
      "step": 24805
    },
    {
      "epoch": 275.6666666666667,
      "grad_norm": 6.4721018588898e-07,
      "learning_rate": 1.578045797666453e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6950256,
      "step": 24810
    },
    {
      "epoch": 275.72222222222223,
      "grad_norm": 5.277987042973109e-07,
      "learning_rate": 1.5771333185383548e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6951632,
      "step": 24815
    },
    {
      "epoch": 275.77777777777777,
      "grad_norm": 4.956097541253257e-07,
      "learning_rate": 1.576220981727895e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6953008,
      "step": 24820
    },
    {
      "epoch": 275.8333333333333,
      "grad_norm": 1.0316658745068708e-06,
      "learning_rate": 1.575308787375769e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6954432,
      "step": 24825
    },
    {
      "epoch": 275.8888888888889,
      "grad_norm": 4.561021285098832e-07,
      "learning_rate": 1.5743967356226492e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6955792,
      "step": 24830
    },
    {
      "epoch": 275.94444444444446,
      "grad_norm": 4.699999180957093e-07,
      "learning_rate": 1.5734848266091835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6957184,
      "step": 24835
    },
    {
      "epoch": 276.0,
      "grad_norm": 1.4820225260336883e-06,
      "learning_rate": 1.572573060476001e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6958576,
      "step": 24840
    },
    {
      "epoch": 276.05555555555554,
      "grad_norm": 1.4685961104987655e-06,
      "learning_rate": 1.5716614373637085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6959984,
      "step": 24845
    },
    {
      "epoch": 276.1111111111111,
      "grad_norm": 2.0185102584946435e-06,
      "learning_rate": 1.570749957412887e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6961360,
      "step": 24850
    },
    {
      "epoch": 276.1666666666667,
      "grad_norm": 6.073718168408959e-07,
      "learning_rate": 1.5698386207641013e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6962736,
      "step": 24855
    },
    {
      "epoch": 276.22222222222223,
      "grad_norm": 5.640877134283073e-07,
      "learning_rate": 1.5689274275578884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6964096,
      "step": 24860
    },
    {
      "epoch": 276.27777777777777,
      "grad_norm": 4.64332515548449e-07,
      "learning_rate": 1.5680163779347667e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6965440,
      "step": 24865
    },
    {
      "epoch": 276.3333333333333,
      "grad_norm": 9.604814295016695e-07,
      "learning_rate": 1.5671054720352327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6966880,
      "step": 24870
    },
    {
      "epoch": 276.3888888888889,
      "grad_norm": 5.379234835345414e-07,
      "learning_rate": 1.566194709999757e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6968272,
      "step": 24875
    },
    {
      "epoch": 276.44444444444446,
      "grad_norm": 5.082709435555444e-07,
      "learning_rate": 1.5652840919687933e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6969680,
      "step": 24880
    },
    {
      "epoch": 276.5,
      "grad_norm": 5.731911301154469e-07,
      "learning_rate": 1.5643736180827676e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6971072,
      "step": 24885
    },
    {
      "epoch": 276.55555555555554,
      "grad_norm": 1.977809461095603e-06,
      "learning_rate": 1.5634632884820878e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6972496,
      "step": 24890
    },
    {
      "epoch": 276.6111111111111,
      "grad_norm": 6.551114211106324e-07,
      "learning_rate": 1.5625531033071395e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6973840,
      "step": 24895
    },
    {
      "epoch": 276.6666666666667,
      "grad_norm": 1.6424677369286655e-06,
      "learning_rate": 1.5616430626982828e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6975312,
      "step": 24900
    },
    {
      "epoch": 276.72222222222223,
      "grad_norm": 9.407577863385086e-07,
      "learning_rate": 1.5607331667958575e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6976752,
      "step": 24905
    },
    {
      "epoch": 276.77777777777777,
      "grad_norm": 1.097202812161413e-06,
      "learning_rate": 1.5598234157401824e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6978160,
      "step": 24910
    },
    {
      "epoch": 276.8333333333333,
      "grad_norm": 5.714496182918083e-07,
      "learning_rate": 1.5589138096715503e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6979584,
      "step": 24915
    },
    {
      "epoch": 276.8888888888889,
      "grad_norm": 4.7460602559112886e-07,
      "learning_rate": 1.5580043487302365e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6980992,
      "step": 24920
    },
    {
      "epoch": 276.94444444444446,
      "grad_norm": 5.214297971178894e-07,
      "learning_rate": 1.5570950330564888e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6982416,
      "step": 24925
    },
    {
      "epoch": 277.0,
      "grad_norm": 1.695226387710136e-06,
      "learning_rate": 1.5561858627905367e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6983808,
      "step": 24930
    },
    {
      "epoch": 277.05555555555554,
      "grad_norm": 6.519124440274027e-07,
      "learning_rate": 1.5552768380725857e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6985200,
      "step": 24935
    },
    {
      "epoch": 277.1111111111111,
      "grad_norm": 5.200654982218111e-07,
      "learning_rate": 1.5543679590428183e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6986576,
      "step": 24940
    },
    {
      "epoch": 277.1666666666667,
      "grad_norm": 1.0363003184465924e-06,
      "learning_rate": 1.5534592258413943e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6987968,
      "step": 24945
    },
    {
      "epoch": 277.22222222222223,
      "grad_norm": 1.7132814491560566e-06,
      "learning_rate": 1.5525506386084538e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6989376,
      "step": 24950
    },
    {
      "epoch": 277.27777777777777,
      "grad_norm": 4.768048142977932e-07,
      "learning_rate": 1.55164219748411e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6990816,
      "step": 24955
    },
    {
      "epoch": 277.3333333333333,
      "grad_norm": 2.204013981099706e-06,
      "learning_rate": 1.550733902608459e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6992240,
      "step": 24960
    },
    {
      "epoch": 277.3888888888889,
      "grad_norm": 4.907646484753059e-07,
      "learning_rate": 1.549825754121568e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6993616,
      "step": 24965
    },
    {
      "epoch": 277.44444444444446,
      "grad_norm": 4.96085817758285e-07,
      "learning_rate": 1.5489177521634864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6995056,
      "step": 24970
    },
    {
      "epoch": 277.5,
      "grad_norm": 1.7125322528954712e-06,
      "learning_rate": 1.5480098968742402e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6996432,
      "step": 24975
    },
    {
      "epoch": 277.55555555555554,
      "grad_norm": 3.886985666667897e-07,
      "learning_rate": 1.5471021883938304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6997856,
      "step": 24980
    },
    {
      "epoch": 277.6111111111111,
      "grad_norm": 2.0820677946176147e-06,
      "learning_rate": 1.546194626862238e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 6999232,
      "step": 24985
    },
    {
      "epoch": 277.6666666666667,
      "grad_norm": 4.576828018798551e-07,
      "learning_rate": 1.5452872124194216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7000672,
      "step": 24990
    },
    {
      "epoch": 277.72222222222223,
      "grad_norm": 5.141240535522229e-07,
      "learning_rate": 1.5443799452053136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7002064,
      "step": 24995
    },
    {
      "epoch": 277.77777777777777,
      "grad_norm": 5.357715622267278e-07,
      "learning_rate": 1.543472825359828e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7003408,
      "step": 25000
    },
    {
      "epoch": 277.77777777777777,
      "eval_loss": 0.34609031677246094,
      "eval_runtime": 1.2923,
      "eval_samples_per_second": 30.952,
      "eval_steps_per_second": 15.476,
      "num_input_tokens_seen": 7003408,
      "step": 25000
    },
    {
      "epoch": 277.8333333333333,
      "grad_norm": 5.958769406788633e-07,
      "learning_rate": 1.5425658530228522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7004832,
      "step": 25005
    },
    {
      "epoch": 277.8888888888889,
      "grad_norm": 9.601747024134966e-07,
      "learning_rate": 1.5416590283342546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7006240,
      "step": 25010
    },
    {
      "epoch": 277.94444444444446,
      "grad_norm": 5.437758545667748e-07,
      "learning_rate": 1.5407523514338783e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7007648,
      "step": 25015
    },
    {
      "epoch": 278.0,
      "grad_norm": 5.97102200572408e-07,
      "learning_rate": 1.539845822461543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7009024,
      "step": 25020
    },
    {
      "epoch": 278.05555555555554,
      "grad_norm": 1.0607910780890961e-06,
      "learning_rate": 1.538939441557048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7010432,
      "step": 25025
    },
    {
      "epoch": 278.1111111111111,
      "grad_norm": 1.0185834753428935e-06,
      "learning_rate": 1.5380332088601696e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7011840,
      "step": 25030
    },
    {
      "epoch": 278.1666666666667,
      "grad_norm": 5.463307957143115e-07,
      "learning_rate": 1.537127124510658e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7013264,
      "step": 25035
    },
    {
      "epoch": 278.22222222222223,
      "grad_norm": 3.107832299065194e-06,
      "learning_rate": 1.5362211886482457e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7014640,
      "step": 25040
    },
    {
      "epoch": 278.27777777777777,
      "grad_norm": 3.910024020115088e-07,
      "learning_rate": 1.5353154014126363e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7016048,
      "step": 25045
    },
    {
      "epoch": 278.3333333333333,
      "grad_norm": 4.880037067778176e-07,
      "learning_rate": 1.534409762943515e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7017408,
      "step": 25050
    },
    {
      "epoch": 278.3888888888889,
      "grad_norm": 5.397082531999331e-07,
      "learning_rate": 1.5335042733805438e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7018784,
      "step": 25055
    },
    {
      "epoch": 278.44444444444446,
      "grad_norm": 8.953192605076765e-07,
      "learning_rate": 1.532598932863358e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7020176,
      "step": 25060
    },
    {
      "epoch": 278.5,
      "grad_norm": 1.7411828139302088e-06,
      "learning_rate": 1.531693741531574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7021616,
      "step": 25065
    },
    {
      "epoch": 278.55555555555554,
      "grad_norm": 5.346331022337836e-07,
      "learning_rate": 1.5307886995247844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7022976,
      "step": 25070
    },
    {
      "epoch": 278.6111111111111,
      "grad_norm": 5.632052193504933e-07,
      "learning_rate": 1.529883806982557e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7024416,
      "step": 25075
    },
    {
      "epoch": 278.6666666666667,
      "grad_norm": 5.025115115131484e-07,
      "learning_rate": 1.5289790640444376e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7025824,
      "step": 25080
    },
    {
      "epoch": 278.72222222222223,
      "grad_norm": 1.089119336938893e-06,
      "learning_rate": 1.5280744708499494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7027200,
      "step": 25085
    },
    {
      "epoch": 278.77777777777777,
      "grad_norm": 5.513290375347424e-07,
      "learning_rate": 1.527170027538591e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7028608,
      "step": 25090
    },
    {
      "epoch": 278.8333333333333,
      "grad_norm": 5.058131478108407e-07,
      "learning_rate": 1.5262657342498407e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7030000,
      "step": 25095
    },
    {
      "epoch": 278.8888888888889,
      "grad_norm": 3.1665283586335136e-06,
      "learning_rate": 1.52536159112315e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7031392,
      "step": 25100
    },
    {
      "epoch": 278.94444444444446,
      "grad_norm": 6.485808512479707e-07,
      "learning_rate": 1.5244575982979497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7032816,
      "step": 25105
    },
    {
      "epoch": 279.0,
      "grad_norm": 9.380451047036331e-07,
      "learning_rate": 1.5235537559136487e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7034240,
      "step": 25110
    },
    {
      "epoch": 279.05555555555554,
      "grad_norm": 1.6623166629869957e-06,
      "learning_rate": 1.5226500641096286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7035648,
      "step": 25115
    },
    {
      "epoch": 279.1111111111111,
      "grad_norm": 4.399421413836535e-07,
      "learning_rate": 1.5217465230252509e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7036992,
      "step": 25120
    },
    {
      "epoch": 279.1666666666667,
      "grad_norm": 4.606118011452054e-07,
      "learning_rate": 1.5208431327998523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7038416,
      "step": 25125
    },
    {
      "epoch": 279.22222222222223,
      "grad_norm": 4.977495109415031e-07,
      "learning_rate": 1.5199398935727477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7039856,
      "step": 25130
    },
    {
      "epoch": 279.27777777777777,
      "grad_norm": 1.6761678125476465e-06,
      "learning_rate": 1.5190368054832282e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7041232,
      "step": 25135
    },
    {
      "epoch": 279.3333333333333,
      "grad_norm": 1.018769125948893e-06,
      "learning_rate": 1.5181338686705601e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7042640,
      "step": 25140
    },
    {
      "epoch": 279.3888888888889,
      "grad_norm": 9.289522040489828e-07,
      "learning_rate": 1.5172310832739889e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7044032,
      "step": 25145
    },
    {
      "epoch": 279.44444444444446,
      "grad_norm": 5.068326345281093e-07,
      "learning_rate": 1.5163284494327346e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7045408,
      "step": 25150
    },
    {
      "epoch": 279.5,
      "grad_norm": 9.735151706991019e-07,
      "learning_rate": 1.5154259672859952e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7046816,
      "step": 25155
    },
    {
      "epoch": 279.55555555555554,
      "grad_norm": 5.11904886479897e-07,
      "learning_rate": 1.5145236369729452e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7048240,
      "step": 25160
    },
    {
      "epoch": 279.6111111111111,
      "grad_norm": 5.803722160635516e-07,
      "learning_rate": 1.5136214586327335e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7049680,
      "step": 25165
    },
    {
      "epoch": 279.6666666666667,
      "grad_norm": 3.0912440251995577e-06,
      "learning_rate": 1.5127194324044885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7051072,
      "step": 25170
    },
    {
      "epoch": 279.72222222222223,
      "grad_norm": 5.554188646783587e-07,
      "learning_rate": 1.5118175584273148e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7052464,
      "step": 25175
    },
    {
      "epoch": 279.77777777777777,
      "grad_norm": 5.522550168279849e-07,
      "learning_rate": 1.5109158368402909e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7053888,
      "step": 25180
    },
    {
      "epoch": 279.8333333333333,
      "grad_norm": 8.563099527236773e-07,
      "learning_rate": 1.5100142677824753e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7055264,
      "step": 25185
    },
    {
      "epoch": 279.8888888888889,
      "grad_norm": 2.0003731151518878e-06,
      "learning_rate": 1.509112851392901e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7056704,
      "step": 25190
    },
    {
      "epoch": 279.94444444444446,
      "grad_norm": 6.484461323452706e-07,
      "learning_rate": 1.5082115878105763e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7058128,
      "step": 25195
    },
    {
      "epoch": 280.0,
      "grad_norm": 9.910459084494505e-07,
      "learning_rate": 1.5073104771744892e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7059536,
      "step": 25200
    },
    {
      "epoch": 280.0,
      "eval_loss": 0.33790481090545654,
      "eval_runtime": 1.2924,
      "eval_samples_per_second": 30.95,
      "eval_steps_per_second": 15.475,
      "num_input_tokens_seen": 7059536,
      "step": 25200
    },
    {
      "epoch": 280.05555555555554,
      "grad_norm": 5.359546548788785e-07,
      "learning_rate": 1.5064095196236006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7060928,
      "step": 25205
    },
    {
      "epoch": 280.1111111111111,
      "grad_norm": 9.71755412138009e-07,
      "learning_rate": 1.50550871529685e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7062384,
      "step": 25210
    },
    {
      "epoch": 280.1666666666667,
      "grad_norm": 5.473041255754652e-07,
      "learning_rate": 1.5046080643331546e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7063792,
      "step": 25215
    },
    {
      "epoch": 280.22222222222223,
      "grad_norm": 5.575869295171287e-07,
      "learning_rate": 1.5037075668714028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7065200,
      "step": 25220
    },
    {
      "epoch": 280.27777777777777,
      "grad_norm": 9.95441496343119e-07,
      "learning_rate": 1.5028072230504656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7066560,
      "step": 25225
    },
    {
      "epoch": 280.3333333333333,
      "grad_norm": 6.151944944576826e-07,
      "learning_rate": 1.5019070330091861e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7067984,
      "step": 25230
    },
    {
      "epoch": 280.3888888888889,
      "grad_norm": 6.1085648894732e-07,
      "learning_rate": 1.5010069968863843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7069360,
      "step": 25235
    },
    {
      "epoch": 280.44444444444446,
      "grad_norm": 5.473252713272814e-07,
      "learning_rate": 1.5001071148208584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7070720,
      "step": 25240
    },
    {
      "epoch": 280.5,
      "grad_norm": 1.6926194348343415e-06,
      "learning_rate": 1.49920738695138e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7072128,
      "step": 25245
    },
    {
      "epoch": 280.55555555555554,
      "grad_norm": 1.4860848978059948e-06,
      "learning_rate": 1.4983078134166995e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7073488,
      "step": 25250
    },
    {
      "epoch": 280.6111111111111,
      "grad_norm": 1.0092879847434233e-06,
      "learning_rate": 1.4974083943555428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7074880,
      "step": 25255
    },
    {
      "epoch": 280.6666666666667,
      "grad_norm": 9.638146138968295e-07,
      "learning_rate": 1.496509129906611e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7076336,
      "step": 25260
    },
    {
      "epoch": 280.72222222222223,
      "grad_norm": 4.94488233471202e-07,
      "learning_rate": 1.4956100202085809e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7077744,
      "step": 25265
    },
    {
      "epoch": 280.77777777777777,
      "grad_norm": 6.273200483519759e-07,
      "learning_rate": 1.4947110654001093e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7079136,
      "step": 25270
    },
    {
      "epoch": 280.8333333333333,
      "grad_norm": 5.400524401011353e-07,
      "learning_rate": 1.4938122656198234e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7080528,
      "step": 25275
    },
    {
      "epoch": 280.8888888888889,
      "grad_norm": 1.7063373434211826e-06,
      "learning_rate": 1.4929136210063316e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7081904,
      "step": 25280
    },
    {
      "epoch": 280.94444444444446,
      "grad_norm": 1.4885151813359698e-06,
      "learning_rate": 1.4920151316982146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7083344,
      "step": 25285
    },
    {
      "epoch": 281.0,
      "grad_norm": 1.4908830507920356e-06,
      "learning_rate": 1.4911167978340312e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7084736,
      "step": 25290
    },
    {
      "epoch": 281.05555555555554,
      "grad_norm": 9.829079772316618e-07,
      "learning_rate": 1.4902186195523166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7086096,
      "step": 25295
    },
    {
      "epoch": 281.1111111111111,
      "grad_norm": 5.851106266163697e-07,
      "learning_rate": 1.4893205969915805e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7087520,
      "step": 25300
    },
    {
      "epoch": 281.1666666666667,
      "grad_norm": 9.197370900437818e-07,
      "learning_rate": 1.4884227302903086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7088976,
      "step": 25305
    },
    {
      "epoch": 281.22222222222223,
      "grad_norm": 6.095871754041582e-07,
      "learning_rate": 1.4875250195869653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7090384,
      "step": 25310
    },
    {
      "epoch": 281.27777777777777,
      "grad_norm": 5.354232825993677e-07,
      "learning_rate": 1.4866274650199862e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7091792,
      "step": 25315
    },
    {
      "epoch": 281.3333333333333,
      "grad_norm": 9.376740308653098e-07,
      "learning_rate": 1.485730066727788e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7093168,
      "step": 25320
    },
    {
      "epoch": 281.3888888888889,
      "grad_norm": 5.120397759128537e-07,
      "learning_rate": 1.4848328248487586e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7094512,
      "step": 25325
    },
    {
      "epoch": 281.44444444444446,
      "grad_norm": 5.71074451727327e-07,
      "learning_rate": 1.4839357395212656e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7095968,
      "step": 25330
    },
    {
      "epoch": 281.5,
      "grad_norm": 5.092293235975376e-07,
      "learning_rate": 1.4830388108836502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7097344,
      "step": 25335
    },
    {
      "epoch": 281.55555555555554,
      "grad_norm": 4.995621907255554e-07,
      "learning_rate": 1.4821420390742299e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7098688,
      "step": 25340
    },
    {
      "epoch": 281.6111111111111,
      "grad_norm": 6.846159976703348e-07,
      "learning_rate": 1.4812454242312979e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7100112,
      "step": 25345
    },
    {
      "epoch": 281.6666666666667,
      "grad_norm": 5.417311399469327e-07,
      "learning_rate": 1.4803489664931253e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7101504,
      "step": 25350
    },
    {
      "epoch": 281.72222222222223,
      "grad_norm": 5.732419481319084e-07,
      "learning_rate": 1.4794526659979544e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7102960,
      "step": 25355
    },
    {
      "epoch": 281.77777777777777,
      "grad_norm": 6.651180797234701e-07,
      "learning_rate": 1.4785565228840086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7104368,
      "step": 25360
    },
    {
      "epoch": 281.8333333333333,
      "grad_norm": 1.6771780337876407e-06,
      "learning_rate": 1.4776605372894819e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7105808,
      "step": 25365
    },
    {
      "epoch": 281.8888888888889,
      "grad_norm": 4.266036626177083e-07,
      "learning_rate": 1.4767647093525488e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7107200,
      "step": 25370
    },
    {
      "epoch": 281.94444444444446,
      "grad_norm": 4.237236908011255e-07,
      "learning_rate": 1.4758690392113566e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7108560,
      "step": 25375
    },
    {
      "epoch": 282.0,
      "grad_norm": 2.254451601402252e-06,
      "learning_rate": 1.4749735270040276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7109968,
      "step": 25380
    },
    {
      "epoch": 282.05555555555554,
      "grad_norm": 6.343088330140745e-07,
      "learning_rate": 1.4740781728686623e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7111360,
      "step": 25385
    },
    {
      "epoch": 282.1111111111111,
      "grad_norm": 6.673762982245535e-07,
      "learning_rate": 1.4731829769433358e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7112672,
      "step": 25390
    },
    {
      "epoch": 282.1666666666667,
      "grad_norm": 6.463031354542181e-07,
      "learning_rate": 1.4722879393660976e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7114128,
      "step": 25395
    },
    {
      "epoch": 282.22222222222223,
      "grad_norm": 2.1601156277029077e-06,
      "learning_rate": 1.4713930602749748e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7115504,
      "step": 25400
    },
    {
      "epoch": 282.22222222222223,
      "eval_loss": 0.34881898760795593,
      "eval_runtime": 1.2918,
      "eval_samples_per_second": 30.965,
      "eval_steps_per_second": 15.483,
      "num_input_tokens_seen": 7115504,
      "step": 25400
    },
    {
      "epoch": 282.27777777777777,
      "grad_norm": 5.615087843580113e-07,
      "learning_rate": 1.470498339807968e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7116928,
      "step": 25405
    },
    {
      "epoch": 282.3333333333333,
      "grad_norm": 5.102745035401313e-07,
      "learning_rate": 1.4696037781030542e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7118320,
      "step": 25410
    },
    {
      "epoch": 282.3888888888889,
      "grad_norm": 5.795122319796064e-07,
      "learning_rate": 1.4687093752981876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7119696,
      "step": 25415
    },
    {
      "epoch": 282.44444444444446,
      "grad_norm": 8.895338510228612e-07,
      "learning_rate": 1.4678151315312943e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7121136,
      "step": 25420
    },
    {
      "epoch": 282.5,
      "grad_norm": 2.289036274305545e-06,
      "learning_rate": 1.4669210469402789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7122544,
      "step": 25425
    },
    {
      "epoch": 282.55555555555554,
      "grad_norm": 5.933372904110001e-07,
      "learning_rate": 1.4660271216630218e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7123952,
      "step": 25430
    },
    {
      "epoch": 282.6111111111111,
      "grad_norm": 4.820107051273226e-07,
      "learning_rate": 1.4651333558373748e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7125344,
      "step": 25435
    },
    {
      "epoch": 282.6666666666667,
      "grad_norm": 6.077797252146411e-07,
      "learning_rate": 1.4642397496011707e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7126784,
      "step": 25440
    },
    {
      "epoch": 282.72222222222223,
      "grad_norm": 5.792639967694413e-07,
      "learning_rate": 1.4633463030922129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7128192,
      "step": 25445
    },
    {
      "epoch": 282.77777777777777,
      "grad_norm": 6.114037773841119e-07,
      "learning_rate": 1.462453016448282e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7129600,
      "step": 25450
    },
    {
      "epoch": 282.8333333333333,
      "grad_norm": 2.2778785933041945e-06,
      "learning_rate": 1.4615598898071354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7131024,
      "step": 25455
    },
    {
      "epoch": 282.8888888888889,
      "grad_norm": 1.9565568436519243e-06,
      "learning_rate": 1.4606669233065026e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7132416,
      "step": 25460
    },
    {
      "epoch": 282.94444444444446,
      "grad_norm": 1.7524661188872415e-06,
      "learning_rate": 1.4597741170840914e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7133808,
      "step": 25465
    },
    {
      "epoch": 283.0,
      "grad_norm": 5.732621843890229e-07,
      "learning_rate": 1.4588814712775853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7135216,
      "step": 25470
    },
    {
      "epoch": 283.05555555555554,
      "grad_norm": 5.590516138909152e-07,
      "learning_rate": 1.4579889860246382e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7136592,
      "step": 25475
    },
    {
      "epoch": 283.1111111111111,
      "grad_norm": 4.4995221060162294e-07,
      "learning_rate": 1.457096661462885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7137984,
      "step": 25480
    },
    {
      "epoch": 283.1666666666667,
      "grad_norm": 8.719620723240951e-07,
      "learning_rate": 1.4562044977299322e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7139392,
      "step": 25485
    },
    {
      "epoch": 283.22222222222223,
      "grad_norm": 3.5947016385762254e-06,
      "learning_rate": 1.4553124949633623e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7140816,
      "step": 25490
    },
    {
      "epoch": 283.27777777777777,
      "grad_norm": 4.979684149475361e-07,
      "learning_rate": 1.4544206533007354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7142256,
      "step": 25495
    },
    {
      "epoch": 283.3333333333333,
      "grad_norm": 5.458956024995132e-07,
      "learning_rate": 1.4535289728795821e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7143680,
      "step": 25500
    },
    {
      "epoch": 283.3888888888889,
      "grad_norm": 4.5756797817375627e-07,
      "learning_rate": 1.4526374538374132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7145056,
      "step": 25505
    },
    {
      "epoch": 283.44444444444446,
      "grad_norm": 5.006219794267963e-07,
      "learning_rate": 1.4517460963117097e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7146480,
      "step": 25510
    },
    {
      "epoch": 283.5,
      "grad_norm": 4.6350433535735647e-07,
      "learning_rate": 1.4508549004399314e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7147888,
      "step": 25515
    },
    {
      "epoch": 283.55555555555554,
      "grad_norm": 5.268596510177304e-07,
      "learning_rate": 1.449963866359513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7149232,
      "step": 25520
    },
    {
      "epoch": 283.6111111111111,
      "grad_norm": 1.6602718915237347e-06,
      "learning_rate": 1.4490729942078607e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7150624,
      "step": 25525
    },
    {
      "epoch": 283.6666666666667,
      "grad_norm": 5.417709871835541e-07,
      "learning_rate": 1.4481822841223608e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7152048,
      "step": 25530
    },
    {
      "epoch": 283.72222222222223,
      "grad_norm": 3.6877709135296755e-06,
      "learning_rate": 1.4472917362403704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7153456,
      "step": 25535
    },
    {
      "epoch": 283.77777777777777,
      "grad_norm": 5.395652920014982e-07,
      "learning_rate": 1.4464013506992224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7154832,
      "step": 25540
    },
    {
      "epoch": 283.8333333333333,
      "grad_norm": 4.631257866094529e-07,
      "learning_rate": 1.4455111276362277e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7156272,
      "step": 25545
    },
    {
      "epoch": 283.8888888888889,
      "grad_norm": 6.355526238621678e-07,
      "learning_rate": 1.4446210671886676e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7157664,
      "step": 25550
    },
    {
      "epoch": 283.94444444444446,
      "grad_norm": 9.4646105708307e-07,
      "learning_rate": 1.4437311694938015e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7159072,
      "step": 25555
    },
    {
      "epoch": 284.0,
      "grad_norm": 9.394934750162065e-07,
      "learning_rate": 1.442841434688864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7160464,
      "step": 25560
    },
    {
      "epoch": 284.05555555555554,
      "grad_norm": 5.124229573993944e-07,
      "learning_rate": 1.4419518629110615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7161904,
      "step": 25565
    },
    {
      "epoch": 284.1111111111111,
      "grad_norm": 5.136350296197634e-07,
      "learning_rate": 1.4410624542975778e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7163344,
      "step": 25570
    },
    {
      "epoch": 284.1666666666667,
      "grad_norm": 5.004098397876078e-07,
      "learning_rate": 1.4401732089855724e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7164688,
      "step": 25575
    },
    {
      "epoch": 284.22222222222223,
      "grad_norm": 3.5183779800718185e-07,
      "learning_rate": 1.4392841271121754e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7166128,
      "step": 25580
    },
    {
      "epoch": 284.27777777777777,
      "grad_norm": 4.912785698252264e-07,
      "learning_rate": 1.438395208814497e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7167552,
      "step": 25585
    },
    {
      "epoch": 284.3333333333333,
      "grad_norm": 5.040577661930001e-07,
      "learning_rate": 1.4375064542296174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7168960,
      "step": 25590
    },
    {
      "epoch": 284.3888888888889,
      "grad_norm": 1.0025528354162816e-06,
      "learning_rate": 1.4366178634945946e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7170304,
      "step": 25595
    },
    {
      "epoch": 284.44444444444446,
      "grad_norm": 4.2708998648777197e-07,
      "learning_rate": 1.4357294367464616e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7171744,
      "step": 25600
    },
    {
      "epoch": 284.44444444444446,
      "eval_loss": 0.36703360080718994,
      "eval_runtime": 1.2947,
      "eval_samples_per_second": 30.894,
      "eval_steps_per_second": 15.447,
      "num_input_tokens_seen": 7171744,
      "step": 25600
    },
    {
      "epoch": 284.5,
      "grad_norm": 5.901964641452651e-07,
      "learning_rate": 1.434841174122224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7173152,
      "step": 25605
    },
    {
      "epoch": 284.55555555555554,
      "grad_norm": 3.810995679032203e-07,
      "learning_rate": 1.4339530757588615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7174496,
      "step": 25610
    },
    {
      "epoch": 284.6111111111111,
      "grad_norm": 8.482853104396781e-07,
      "learning_rate": 1.433065141793333e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7175904,
      "step": 25615
    },
    {
      "epoch": 284.6666666666667,
      "grad_norm": 9.814068562263856e-07,
      "learning_rate": 1.4321773723625665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7177296,
      "step": 25620
    },
    {
      "epoch": 284.72222222222223,
      "grad_norm": 5.262697300167929e-07,
      "learning_rate": 1.4312897676034693e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7178720,
      "step": 25625
    },
    {
      "epoch": 284.77777777777777,
      "grad_norm": 6.189417263158248e-07,
      "learning_rate": 1.4304023276529188e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7180112,
      "step": 25630
    },
    {
      "epoch": 284.8333333333333,
      "grad_norm": 2.343816959182732e-06,
      "learning_rate": 1.4295150526477712e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7181488,
      "step": 25635
    },
    {
      "epoch": 284.8888888888889,
      "grad_norm": 5.498164910022751e-07,
      "learning_rate": 1.4286279427248562e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7182880,
      "step": 25640
    },
    {
      "epoch": 284.94444444444446,
      "grad_norm": 5.530574185286241e-07,
      "learning_rate": 1.4277409980209747e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7184304,
      "step": 25645
    },
    {
      "epoch": 285.0,
      "grad_norm": 5.596018581854878e-07,
      "learning_rate": 1.4268542186729061e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7185696,
      "step": 25650
    },
    {
      "epoch": 285.05555555555554,
      "grad_norm": 1.009818220154557e-06,
      "learning_rate": 1.4259676048174043e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7187088,
      "step": 25655
    },
    {
      "epoch": 285.1111111111111,
      "grad_norm": 4.656678527226177e-07,
      "learning_rate": 1.4250811565911937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7188464,
      "step": 25660
    },
    {
      "epoch": 285.1666666666667,
      "grad_norm": 5.145318482391303e-07,
      "learning_rate": 1.4241948741309782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7189856,
      "step": 25665
    },
    {
      "epoch": 285.22222222222223,
      "grad_norm": 9.649994581195642e-07,
      "learning_rate": 1.4233087575734317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7191280,
      "step": 25670
    },
    {
      "epoch": 285.27777777777777,
      "grad_norm": 5.495358550433593e-07,
      "learning_rate": 1.422422807055206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7192704,
      "step": 25675
    },
    {
      "epoch": 285.3333333333333,
      "grad_norm": 5.529143436433515e-07,
      "learning_rate": 1.4215370227129243e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7194160,
      "step": 25680
    },
    {
      "epoch": 285.3888888888889,
      "grad_norm": 1.0177144531553495e-06,
      "learning_rate": 1.4206514046831876e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7195536,
      "step": 25685
    },
    {
      "epoch": 285.44444444444446,
      "grad_norm": 9.865260608421522e-07,
      "learning_rate": 1.419765953102567e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7196912,
      "step": 25690
    },
    {
      "epoch": 285.5,
      "grad_norm": 5.028390432926244e-07,
      "learning_rate": 1.4188806681076125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7198272,
      "step": 25695
    },
    {
      "epoch": 285.55555555555554,
      "grad_norm": 4.987645638721006e-07,
      "learning_rate": 1.4179955498348443e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7199728,
      "step": 25700
    },
    {
      "epoch": 285.6111111111111,
      "grad_norm": 9.495107065049524e-07,
      "learning_rate": 1.4171105984207605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7201088,
      "step": 25705
    },
    {
      "epoch": 285.6666666666667,
      "grad_norm": 6.086286248319084e-07,
      "learning_rate": 1.4162258140018304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7202512,
      "step": 25710
    },
    {
      "epoch": 285.72222222222223,
      "grad_norm": 5.538766458812461e-07,
      "learning_rate": 1.4153411967144986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7203920,
      "step": 25715
    },
    {
      "epoch": 285.77777777777777,
      "grad_norm": 9.153148425866675e-07,
      "learning_rate": 1.4144567466951864e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7205376,
      "step": 25720
    },
    {
      "epoch": 285.8333333333333,
      "grad_norm": 4.3975867924928025e-07,
      "learning_rate": 1.4135724640802844e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7206736,
      "step": 25725
    },
    {
      "epoch": 285.8888888888889,
      "grad_norm": 9.067081236935337e-07,
      "learning_rate": 1.4126883490061615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7208128,
      "step": 25730
    },
    {
      "epoch": 285.94444444444446,
      "grad_norm": 8.972529030870646e-07,
      "learning_rate": 1.4118044016091603e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7209520,
      "step": 25735
    },
    {
      "epoch": 286.0,
      "grad_norm": 5.85980785672291e-07,
      "learning_rate": 1.410920622025594e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7210944,
      "step": 25740
    },
    {
      "epoch": 286.05555555555554,
      "grad_norm": 1.0813340622917167e-06,
      "learning_rate": 1.4100370103917554e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7212304,
      "step": 25745
    },
    {
      "epoch": 286.1111111111111,
      "grad_norm": 5.872544193152862e-07,
      "learning_rate": 1.409153566843907e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7213680,
      "step": 25750
    },
    {
      "epoch": 286.1666666666667,
      "grad_norm": 5.489289378601825e-07,
      "learning_rate": 1.408270291518286e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7215104,
      "step": 25755
    },
    {
      "epoch": 286.22222222222223,
      "grad_norm": 5.135761398378236e-07,
      "learning_rate": 1.407387184551107e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7216512,
      "step": 25760
    },
    {
      "epoch": 286.27777777777777,
      "grad_norm": 5.233497972767509e-07,
      "learning_rate": 1.4065042460785532e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7217920,
      "step": 25765
    },
    {
      "epoch": 286.3333333333333,
      "grad_norm": 1.5293617252609693e-06,
      "learning_rate": 1.405621476236787e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7219344,
      "step": 25770
    },
    {
      "epoch": 286.3888888888889,
      "grad_norm": 5.855840186086425e-07,
      "learning_rate": 1.4047388751619423e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7220720,
      "step": 25775
    },
    {
      "epoch": 286.44444444444446,
      "grad_norm": 3.963661754369241e-07,
      "learning_rate": 1.4038564429901264e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7222112,
      "step": 25780
    },
    {
      "epoch": 286.5,
      "grad_norm": 1.0186288363911444e-06,
      "learning_rate": 1.4029741798574227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7223520,
      "step": 25785
    },
    {
      "epoch": 286.55555555555554,
      "grad_norm": 5.227517476669163e-07,
      "learning_rate": 1.402092085899886e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7224928,
      "step": 25790
    },
    {
      "epoch": 286.6111111111111,
      "grad_norm": 1.6709338979126187e-06,
      "learning_rate": 1.4012101612535464e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7226304,
      "step": 25795
    },
    {
      "epoch": 286.6666666666667,
      "grad_norm": 4.714876524758438e-07,
      "learning_rate": 1.4003284060544092e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7227712,
      "step": 25800
    },
    {
      "epoch": 286.6666666666667,
      "eval_loss": 0.3276625871658325,
      "eval_runtime": 1.2929,
      "eval_samples_per_second": 30.937,
      "eval_steps_per_second": 15.469,
      "num_input_tokens_seen": 7227712,
      "step": 25800
    },
    {
      "epoch": 286.72222222222223,
      "grad_norm": 9.99711573967943e-07,
      "learning_rate": 1.3994468204384504e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7229136,
      "step": 25805
    },
    {
      "epoch": 286.77777777777777,
      "grad_norm": 5.469257189361088e-07,
      "learning_rate": 1.398565404541622e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7230480,
      "step": 25810
    },
    {
      "epoch": 286.8333333333333,
      "grad_norm": 6.250830324461276e-07,
      "learning_rate": 1.3976841584998513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7231904,
      "step": 25815
    },
    {
      "epoch": 286.8888888888889,
      "grad_norm": 4.562401159091678e-07,
      "learning_rate": 1.3968030824490352e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7233328,
      "step": 25820
    },
    {
      "epoch": 286.94444444444446,
      "grad_norm": 5.734511887567351e-07,
      "learning_rate": 1.3959221765250469e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7234736,
      "step": 25825
    },
    {
      "epoch": 287.0,
      "grad_norm": 5.16951217832684e-07,
      "learning_rate": 1.3950414408637343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7236144,
      "step": 25830
    },
    {
      "epoch": 287.05555555555554,
      "grad_norm": 1.6770761703810422e-06,
      "learning_rate": 1.3941608756009166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7237584,
      "step": 25835
    },
    {
      "epoch": 287.1111111111111,
      "grad_norm": 5.650703087667353e-07,
      "learning_rate": 1.3932804808723898e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7238976,
      "step": 25840
    },
    {
      "epoch": 287.1666666666667,
      "grad_norm": 2.2274182356341043e-06,
      "learning_rate": 1.3924002568139194e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7240368,
      "step": 25845
    },
    {
      "epoch": 287.22222222222223,
      "grad_norm": 5.103817670715216e-07,
      "learning_rate": 1.3915202035612485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7241760,
      "step": 25850
    },
    {
      "epoch": 287.27777777777777,
      "grad_norm": 6.16134002484614e-07,
      "learning_rate": 1.3906403212500935e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7243168,
      "step": 25855
    },
    {
      "epoch": 287.3333333333333,
      "grad_norm": 4.4400837850844255e-07,
      "learning_rate": 1.3897606100161409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7244560,
      "step": 25860
    },
    {
      "epoch": 287.3888888888889,
      "grad_norm": 9.290642992709763e-07,
      "learning_rate": 1.388881069995055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7245952,
      "step": 25865
    },
    {
      "epoch": 287.44444444444446,
      "grad_norm": 1.7097449926950503e-06,
      "learning_rate": 1.3880017013224708e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7247328,
      "step": 25870
    },
    {
      "epoch": 287.5,
      "grad_norm": 5.816410748593626e-07,
      "learning_rate": 1.3871225041339984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7248720,
      "step": 25875
    },
    {
      "epoch": 287.55555555555554,
      "grad_norm": 4.3597387957561295e-06,
      "learning_rate": 1.386243478565222e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7250112,
      "step": 25880
    },
    {
      "epoch": 287.6111111111111,
      "grad_norm": 1.7723310747896903e-06,
      "learning_rate": 1.3853646247516966e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7251488,
      "step": 25885
    },
    {
      "epoch": 287.6666666666667,
      "grad_norm": 4.971896032657241e-07,
      "learning_rate": 1.3844859428289545e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7252880,
      "step": 25890
    },
    {
      "epoch": 287.72222222222223,
      "grad_norm": 1.0115106761077186e-06,
      "learning_rate": 1.3836074329324984e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7254320,
      "step": 25895
    },
    {
      "epoch": 287.77777777777777,
      "grad_norm": 9.743313285071054e-07,
      "learning_rate": 1.3827290951978044e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7255744,
      "step": 25900
    },
    {
      "epoch": 287.8333333333333,
      "grad_norm": 6.448408953474427e-07,
      "learning_rate": 1.381850929760326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7257136,
      "step": 25905
    },
    {
      "epoch": 287.8888888888889,
      "grad_norm": 5.622580943054345e-07,
      "learning_rate": 1.3809729367554842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7258512,
      "step": 25910
    },
    {
      "epoch": 287.94444444444446,
      "grad_norm": 4.3430645746411756e-07,
      "learning_rate": 1.3800951163186784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7259936,
      "step": 25915
    },
    {
      "epoch": 288.0,
      "grad_norm": 3.677252834677347e-06,
      "learning_rate": 1.3792174685852801e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7261328,
      "step": 25920
    },
    {
      "epoch": 288.05555555555554,
      "grad_norm": 4.805562525689311e-07,
      "learning_rate": 1.378339993690632e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7262688,
      "step": 25925
    },
    {
      "epoch": 288.1111111111111,
      "grad_norm": 6.113215818004392e-07,
      "learning_rate": 1.3774626917700523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7264096,
      "step": 25930
    },
    {
      "epoch": 288.1666666666667,
      "grad_norm": 5.319960791894118e-07,
      "learning_rate": 1.3765855629588334e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7265520,
      "step": 25935
    },
    {
      "epoch": 288.22222222222223,
      "grad_norm": 9.262681714972132e-07,
      "learning_rate": 1.3757086073922374e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7266960,
      "step": 25940
    },
    {
      "epoch": 288.27777777777777,
      "grad_norm": 5.763367312283663e-07,
      "learning_rate": 1.3748318252055038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7268336,
      "step": 25945
    },
    {
      "epoch": 288.3333333333333,
      "grad_norm": 2.2481522137240972e-06,
      "learning_rate": 1.3739552165338416e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7269760,
      "step": 25950
    },
    {
      "epoch": 288.3888888888889,
      "grad_norm": 9.536101401863561e-07,
      "learning_rate": 1.3730787815124354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7271168,
      "step": 25955
    },
    {
      "epoch": 288.44444444444446,
      "grad_norm": 3.5864800338458735e-06,
      "learning_rate": 1.3722025202764443e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7272576,
      "step": 25960
    },
    {
      "epoch": 288.5,
      "grad_norm": 5.569435757024621e-07,
      "learning_rate": 1.371326432960997e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7273952,
      "step": 25965
    },
    {
      "epoch": 288.55555555555554,
      "grad_norm": 5.709994752578496e-07,
      "learning_rate": 1.3704505197011969e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7275344,
      "step": 25970
    },
    {
      "epoch": 288.6111111111111,
      "grad_norm": 5.45573072940897e-07,
      "learning_rate": 1.3695747806321224e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7276736,
      "step": 25975
    },
    {
      "epoch": 288.6666666666667,
      "grad_norm": 5.031070600125531e-07,
      "learning_rate": 1.3686992158888212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7278176,
      "step": 25980
    },
    {
      "epoch": 288.72222222222223,
      "grad_norm": 5.452776008496585e-07,
      "learning_rate": 1.367823825606319e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7279616,
      "step": 25985
    },
    {
      "epoch": 288.77777777777777,
      "grad_norm": 1.111170718104404e-06,
      "learning_rate": 1.36694860991961e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7281056,
      "step": 25990
    },
    {
      "epoch": 288.8333333333333,
      "grad_norm": 1.6693170437065419e-06,
      "learning_rate": 1.3660735689636636e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7282432,
      "step": 25995
    },
    {
      "epoch": 288.8888888888889,
      "grad_norm": 5.799561222374905e-07,
      "learning_rate": 1.365198702873424e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7283856,
      "step": 26000
    },
    {
      "epoch": 288.8888888888889,
      "eval_loss": 0.3057142198085785,
      "eval_runtime": 1.2904,
      "eval_samples_per_second": 30.999,
      "eval_steps_per_second": 15.5,
      "num_input_tokens_seen": 7283856,
      "step": 26000
    },
    {
      "epoch": 288.94444444444446,
      "grad_norm": 9.430877980776131e-07,
      "learning_rate": 1.364324011783804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7285296,
      "step": 26005
    },
    {
      "epoch": 289.0,
      "grad_norm": 3.129964170511812e-06,
      "learning_rate": 1.3634494958296934e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7286672,
      "step": 26010
    },
    {
      "epoch": 289.05555555555554,
      "grad_norm": 9.381997756463534e-07,
      "learning_rate": 1.3625751551459542e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7288048,
      "step": 26015
    },
    {
      "epoch": 289.1111111111111,
      "grad_norm": 5.863465730726602e-07,
      "learning_rate": 1.3617009898674188e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7289472,
      "step": 26020
    },
    {
      "epoch": 289.1666666666667,
      "grad_norm": 5.632148827316996e-07,
      "learning_rate": 1.3608270001288967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7290896,
      "step": 26025
    },
    {
      "epoch": 289.22222222222223,
      "grad_norm": 1.4996437585068634e-06,
      "learning_rate": 1.359953186065166e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7292304,
      "step": 26030
    },
    {
      "epoch": 289.27777777777777,
      "grad_norm": 3.6381175050337333e-06,
      "learning_rate": 1.3590795478109814e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7293696,
      "step": 26035
    },
    {
      "epoch": 289.3333333333333,
      "grad_norm": 4.978224978913204e-07,
      "learning_rate": 1.3582060855010675e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7295072,
      "step": 26040
    },
    {
      "epoch": 289.3888888888889,
      "grad_norm": 5.692405125046207e-07,
      "learning_rate": 1.3573327992701245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7296480,
      "step": 26045
    },
    {
      "epoch": 289.44444444444446,
      "grad_norm": 4.797345241058792e-07,
      "learning_rate": 1.356459689252823e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7297904,
      "step": 26050
    },
    {
      "epoch": 289.5,
      "grad_norm": 5.642032760988513e-07,
      "learning_rate": 1.3555867555838087e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7299296,
      "step": 26055
    },
    {
      "epoch": 289.55555555555554,
      "grad_norm": 5.413147619037773e-07,
      "learning_rate": 1.3547139983976975e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7300704,
      "step": 26060
    },
    {
      "epoch": 289.6111111111111,
      "grad_norm": 8.314550541399512e-07,
      "learning_rate": 1.3538414178290815e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7302080,
      "step": 26065
    },
    {
      "epoch": 289.6666666666667,
      "grad_norm": 1.4949289379728725e-06,
      "learning_rate": 1.3529690140125209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7303472,
      "step": 26070
    },
    {
      "epoch": 289.72222222222223,
      "grad_norm": 5.207016329222824e-07,
      "learning_rate": 1.352096787082553e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7304864,
      "step": 26075
    },
    {
      "epoch": 289.77777777777777,
      "grad_norm": 4.974231160304043e-07,
      "learning_rate": 1.3512247371736871e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7306272,
      "step": 26080
    },
    {
      "epoch": 289.8333333333333,
      "grad_norm": 4.331800766976812e-07,
      "learning_rate": 1.3503528644204022e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7307712,
      "step": 26085
    },
    {
      "epoch": 289.8888888888889,
      "grad_norm": 6.153463232294598e-07,
      "learning_rate": 1.349481168957153e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7309072,
      "step": 26090
    },
    {
      "epoch": 289.94444444444446,
      "grad_norm": 6.771420544282591e-07,
      "learning_rate": 1.3486096509183665e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7310464,
      "step": 26095
    },
    {
      "epoch": 290.0,
      "grad_norm": 3.2442740121041425e-06,
      "learning_rate": 1.3477383104384406e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7311840,
      "step": 26100
    },
    {
      "epoch": 290.05555555555554,
      "grad_norm": 1.6656283605698263e-06,
      "learning_rate": 1.3468671476517481e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7313248,
      "step": 26105
    },
    {
      "epoch": 290.1111111111111,
      "grad_norm": 4.7648299528191274e-07,
      "learning_rate": 1.3459961626926326e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7314688,
      "step": 26110
    },
    {
      "epoch": 290.1666666666667,
      "grad_norm": 8.755477551858348e-07,
      "learning_rate": 1.3451253556954101e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7316128,
      "step": 26115
    },
    {
      "epoch": 290.22222222222223,
      "grad_norm": 9.892651178233791e-07,
      "learning_rate": 1.3442547267943717e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7317568,
      "step": 26120
    },
    {
      "epoch": 290.27777777777777,
      "grad_norm": 9.943590839611716e-07,
      "learning_rate": 1.3433842761237774e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7318944,
      "step": 26125
    },
    {
      "epoch": 290.3333333333333,
      "grad_norm": 5.690698685612006e-07,
      "learning_rate": 1.3425140038178639e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7320320,
      "step": 26130
    },
    {
      "epoch": 290.3888888888889,
      "grad_norm": 5.420482125373383e-07,
      "learning_rate": 1.3416439100108358e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7321696,
      "step": 26135
    },
    {
      "epoch": 290.44444444444446,
      "grad_norm": 5.775210638603312e-07,
      "learning_rate": 1.3407739948368734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7323072,
      "step": 26140
    },
    {
      "epoch": 290.5,
      "grad_norm": 5.499802568920131e-07,
      "learning_rate": 1.3399042584301298e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7324528,
      "step": 26145
    },
    {
      "epoch": 290.55555555555554,
      "grad_norm": 5.175917863198265e-07,
      "learning_rate": 1.3390347009247272e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7325936,
      "step": 26150
    },
    {
      "epoch": 290.6111111111111,
      "grad_norm": 4.5279551841304055e-07,
      "learning_rate": 1.3381653224547635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7327280,
      "step": 26155
    },
    {
      "epoch": 290.6666666666667,
      "grad_norm": 1.6736026964281336e-06,
      "learning_rate": 1.3372961231543086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7328672,
      "step": 26160
    },
    {
      "epoch": 290.72222222222223,
      "grad_norm": 6.469843469858461e-07,
      "learning_rate": 1.3364271031574016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7330128,
      "step": 26165
    },
    {
      "epoch": 290.77777777777777,
      "grad_norm": 5.160300702300447e-07,
      "learning_rate": 1.335558262598059e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7331472,
      "step": 26170
    },
    {
      "epoch": 290.8333333333333,
      "grad_norm": 5.343754878595064e-07,
      "learning_rate": 1.3346896016102645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7332848,
      "step": 26175
    },
    {
      "epoch": 290.8888888888889,
      "grad_norm": 5.484394591803721e-07,
      "learning_rate": 1.3338211203279788e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7334256,
      "step": 26180
    },
    {
      "epoch": 290.94444444444446,
      "grad_norm": 8.389026220356754e-07,
      "learning_rate": 1.3329528188851303e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7335648,
      "step": 26185
    },
    {
      "epoch": 291.0,
      "grad_norm": 5.298878704707022e-07,
      "learning_rate": 1.3320846974156242e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7337056,
      "step": 26190
    },
    {
      "epoch": 291.05555555555554,
      "grad_norm": 1.6303952179441694e-06,
      "learning_rate": 1.3312167560533337e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7338464,
      "step": 26195
    },
    {
      "epoch": 291.1111111111111,
      "grad_norm": 5.276278898236342e-07,
      "learning_rate": 1.3303489949321082e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7339872,
      "step": 26200
    },
    {
      "epoch": 291.1111111111111,
      "eval_loss": 0.3654395043849945,
      "eval_runtime": 1.2889,
      "eval_samples_per_second": 31.035,
      "eval_steps_per_second": 15.518,
      "num_input_tokens_seen": 7339872,
      "step": 26200
    },
    {
      "epoch": 291.1666666666667,
      "grad_norm": 6.159538088468253e-07,
      "learning_rate": 1.3294814141857653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7341216,
      "step": 26205
    },
    {
      "epoch": 291.22222222222223,
      "grad_norm": 2.093539478664752e-06,
      "learning_rate": 1.3286140139480992e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7342592,
      "step": 26210
    },
    {
      "epoch": 291.27777777777777,
      "grad_norm": 5.34997184331587e-07,
      "learning_rate": 1.3277467943528719e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7344000,
      "step": 26215
    },
    {
      "epoch": 291.3333333333333,
      "grad_norm": 5.534618026103999e-07,
      "learning_rate": 1.3268797555338203e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7345440,
      "step": 26220
    },
    {
      "epoch": 291.3888888888889,
      "grad_norm": 5.473439728120866e-07,
      "learning_rate": 1.3260128976246533e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7346864,
      "step": 26225
    },
    {
      "epoch": 291.44444444444446,
      "grad_norm": 5.449236368804122e-07,
      "learning_rate": 1.32514622075905e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7348240,
      "step": 26230
    },
    {
      "epoch": 291.5,
      "grad_norm": 1.5295797766157193e-06,
      "learning_rate": 1.3242797250706638e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7349632,
      "step": 26235
    },
    {
      "epoch": 291.55555555555554,
      "grad_norm": 8.784783744886226e-07,
      "learning_rate": 1.3234134106931195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7351040,
      "step": 26240
    },
    {
      "epoch": 291.6111111111111,
      "grad_norm": 1.6852209228090942e-06,
      "learning_rate": 1.322547277760013e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7352432,
      "step": 26245
    },
    {
      "epoch": 291.6666666666667,
      "grad_norm": 4.869194185630477e-07,
      "learning_rate": 1.3216813264049132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7353824,
      "step": 26250
    },
    {
      "epoch": 291.72222222222223,
      "grad_norm": 6.028634516042075e-07,
      "learning_rate": 1.32081555676136e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7355232,
      "step": 26255
    },
    {
      "epoch": 291.77777777777777,
      "grad_norm": 4.848193384532351e-07,
      "learning_rate": 1.3199499689628674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7356672,
      "step": 26260
    },
    {
      "epoch": 291.8333333333333,
      "grad_norm": 1.0313578968634829e-06,
      "learning_rate": 1.3190845631429192e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7358144,
      "step": 26265
    },
    {
      "epoch": 291.8888888888889,
      "grad_norm": 5.409250434240676e-07,
      "learning_rate": 1.3182193394349704e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7359568,
      "step": 26270
    },
    {
      "epoch": 291.94444444444446,
      "grad_norm": 6.198809501256619e-07,
      "learning_rate": 1.3173542979724507e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7360976,
      "step": 26275
    },
    {
      "epoch": 292.0,
      "grad_norm": 6.187360668263864e-07,
      "learning_rate": 1.3164894388887617e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7362384,
      "step": 26280
    },
    {
      "epoch": 292.05555555555554,
      "grad_norm": 9.621987828722922e-07,
      "learning_rate": 1.3156247623172727e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7363760,
      "step": 26285
    },
    {
      "epoch": 292.1111111111111,
      "grad_norm": 6.24762719780847e-07,
      "learning_rate": 1.3147602683913302e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7365152,
      "step": 26290
    },
    {
      "epoch": 292.1666666666667,
      "grad_norm": 1.6810256511234911e-06,
      "learning_rate": 1.3138959572442481e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7366560,
      "step": 26295
    },
    {
      "epoch": 292.22222222222223,
      "grad_norm": 9.183656288769271e-07,
      "learning_rate": 1.3130318290093146e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7367920,
      "step": 26300
    },
    {
      "epoch": 292.27777777777777,
      "grad_norm": 5.996865866109147e-07,
      "learning_rate": 1.3121678838197909e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7369344,
      "step": 26305
    },
    {
      "epoch": 292.3333333333333,
      "grad_norm": 5.075950753052894e-07,
      "learning_rate": 1.3113041218089056e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7370752,
      "step": 26310
    },
    {
      "epoch": 292.3888888888889,
      "grad_norm": 1.6888403706616373e-06,
      "learning_rate": 1.3104405431098626e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7372176,
      "step": 26315
    },
    {
      "epoch": 292.44444444444446,
      "grad_norm": 4.597806650963321e-07,
      "learning_rate": 1.3095771478558377e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7373568,
      "step": 26320
    },
    {
      "epoch": 292.5,
      "grad_norm": 4.6386236363105127e-07,
      "learning_rate": 1.3087139361799766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7375008,
      "step": 26325
    },
    {
      "epoch": 292.55555555555554,
      "grad_norm": 9.351318794870167e-07,
      "learning_rate": 1.3078509082153964e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7376384,
      "step": 26330
    },
    {
      "epoch": 292.6111111111111,
      "grad_norm": 2.0297966329962946e-06,
      "learning_rate": 1.3069880640951885e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7377776,
      "step": 26335
    },
    {
      "epoch": 292.6666666666667,
      "grad_norm": 4.2430724533915054e-07,
      "learning_rate": 1.3061254039524123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7379200,
      "step": 26340
    },
    {
      "epoch": 292.72222222222223,
      "grad_norm": 5.753445861955697e-07,
      "learning_rate": 1.3052629279201028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7380608,
      "step": 26345
    },
    {
      "epoch": 292.77777777777777,
      "grad_norm": 9.61208115768386e-07,
      "learning_rate": 1.3044006361312633e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7381984,
      "step": 26350
    },
    {
      "epoch": 292.8333333333333,
      "grad_norm": 6.069441269573872e-07,
      "learning_rate": 1.30353852871887e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7383344,
      "step": 26355
    },
    {
      "epoch": 292.8888888888889,
      "grad_norm": 4.782960445481876e-07,
      "learning_rate": 1.302676605815873e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7384752,
      "step": 26360
    },
    {
      "epoch": 292.94444444444446,
      "grad_norm": 5.315558837537537e-07,
      "learning_rate": 1.3018148675551884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7386160,
      "step": 26365
    },
    {
      "epoch": 293.0,
      "grad_norm": 5.754196763518848e-07,
      "learning_rate": 1.3009533140697094e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7387504,
      "step": 26370
    },
    {
      "epoch": 293.05555555555554,
      "grad_norm": 9.83391032605141e-07,
      "learning_rate": 1.3000919454922966e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7388864,
      "step": 26375
    },
    {
      "epoch": 293.1111111111111,
      "grad_norm": 3.5205448511987925e-06,
      "learning_rate": 1.299230761955785e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7390288,
      "step": 26380
    },
    {
      "epoch": 293.1666666666667,
      "grad_norm": 5.650189791595039e-07,
      "learning_rate": 1.2983697635929807e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7391648,
      "step": 26385
    },
    {
      "epoch": 293.22222222222223,
      "grad_norm": 1.4755970596525003e-06,
      "learning_rate": 1.2975089505366584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7393056,
      "step": 26390
    },
    {
      "epoch": 293.27777777777777,
      "grad_norm": 4.868493874710111e-07,
      "learning_rate": 1.2966483229195683e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7394448,
      "step": 26395
    },
    {
      "epoch": 293.3333333333333,
      "grad_norm": 6.028166126270662e-07,
      "learning_rate": 1.2957878808744283e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7395808,
      "step": 26400
    },
    {
      "epoch": 293.3333333333333,
      "eval_loss": 0.32258859276771545,
      "eval_runtime": 1.2896,
      "eval_samples_per_second": 31.018,
      "eval_steps_per_second": 15.509,
      "num_input_tokens_seen": 7395808,
      "step": 26400
    },
    {
      "epoch": 293.3888888888889,
      "grad_norm": 9.521360198050388e-07,
      "learning_rate": 1.294927624533931e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7397216,
      "step": 26405
    },
    {
      "epoch": 293.44444444444446,
      "grad_norm": 5.505184503817873e-07,
      "learning_rate": 1.2940675540307378e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7398688,
      "step": 26410
    },
    {
      "epoch": 293.5,
      "grad_norm": 6.878927933939849e-07,
      "learning_rate": 1.2932076694974814e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7400080,
      "step": 26415
    },
    {
      "epoch": 293.55555555555554,
      "grad_norm": 9.445673754271411e-07,
      "learning_rate": 1.2923479710667682e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7401488,
      "step": 26420
    },
    {
      "epoch": 293.6111111111111,
      "grad_norm": 3.850960297313577e-07,
      "learning_rate": 1.2914884588711751e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7402848,
      "step": 26425
    },
    {
      "epoch": 293.6666666666667,
      "grad_norm": 1.494518301115022e-06,
      "learning_rate": 1.2906291330432475e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7404272,
      "step": 26430
    },
    {
      "epoch": 293.72222222222223,
      "grad_norm": 1.6823850046421285e-06,
      "learning_rate": 1.2897699937155055e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7405680,
      "step": 26435
    },
    {
      "epoch": 293.77777777777777,
      "grad_norm": 5.788274961560091e-07,
      "learning_rate": 1.2889110410204403e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7407104,
      "step": 26440
    },
    {
      "epoch": 293.8333333333333,
      "grad_norm": 9.183843872051511e-07,
      "learning_rate": 1.2880522750905111e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7408496,
      "step": 26445
    },
    {
      "epoch": 293.8888888888889,
      "grad_norm": 3.26342001244484e-06,
      "learning_rate": 1.2871936960581523e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7409904,
      "step": 26450
    },
    {
      "epoch": 293.94444444444446,
      "grad_norm": 6.119601039245026e-07,
      "learning_rate": 1.2863353040557658e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7411296,
      "step": 26455
    },
    {
      "epoch": 294.0,
      "grad_norm": 5.989670057715557e-07,
      "learning_rate": 1.2854770992157273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7412736,
      "step": 26460
    },
    {
      "epoch": 294.05555555555554,
      "grad_norm": 1.695819719316205e-06,
      "learning_rate": 1.2846190816703835e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7414144,
      "step": 26465
    },
    {
      "epoch": 294.1111111111111,
      "grad_norm": 2.1953076156933093e-06,
      "learning_rate": 1.2837612515520498e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7415504,
      "step": 26470
    },
    {
      "epoch": 294.1666666666667,
      "grad_norm": 5.730162229156122e-07,
      "learning_rate": 1.2829036089930163e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7416976,
      "step": 26475
    },
    {
      "epoch": 294.22222222222223,
      "grad_norm": 1.7315746845270041e-06,
      "learning_rate": 1.2820461541255412e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7418352,
      "step": 26480
    },
    {
      "epoch": 294.27777777777777,
      "grad_norm": 5.339086328604026e-07,
      "learning_rate": 1.2811888870818543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7419824,
      "step": 26485
    },
    {
      "epoch": 294.3333333333333,
      "grad_norm": 9.976869250749587e-07,
      "learning_rate": 1.2803318079941581e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7421248,
      "step": 26490
    },
    {
      "epoch": 294.3888888888889,
      "grad_norm": 6.12747726336238e-07,
      "learning_rate": 1.2794749169946235e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7422704,
      "step": 26495
    },
    {
      "epoch": 294.44444444444446,
      "grad_norm": 8.926512009566068e-07,
      "learning_rate": 1.2786182142153952e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7424064,
      "step": 26500
    },
    {
      "epoch": 294.5,
      "grad_norm": 2.2708916276314994e-06,
      "learning_rate": 1.2777616997885878e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7425440,
      "step": 26505
    },
    {
      "epoch": 294.55555555555554,
      "grad_norm": 5.667349114446552e-07,
      "learning_rate": 1.2769053738462847e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7426832,
      "step": 26510
    },
    {
      "epoch": 294.6111111111111,
      "grad_norm": 5.071918280918908e-07,
      "learning_rate": 1.2760492365205434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7428192,
      "step": 26515
    },
    {
      "epoch": 294.6666666666667,
      "grad_norm": 1.989552174563869e-06,
      "learning_rate": 1.2751932879433919e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7429552,
      "step": 26520
    },
    {
      "epoch": 294.72222222222223,
      "grad_norm": 1.6860268488017027e-06,
      "learning_rate": 1.2743375282468267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7430912,
      "step": 26525
    },
    {
      "epoch": 294.77777777777777,
      "grad_norm": 5.846916906193655e-07,
      "learning_rate": 1.2734819575628182e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7432288,
      "step": 26530
    },
    {
      "epoch": 294.8333333333333,
      "grad_norm": 4.4312361069387407e-07,
      "learning_rate": 1.2726265760233039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7433664,
      "step": 26535
    },
    {
      "epoch": 294.8888888888889,
      "grad_norm": 4.796351049662917e-07,
      "learning_rate": 1.271771383760197e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7435056,
      "step": 26540
    },
    {
      "epoch": 294.94444444444446,
      "grad_norm": 5.04121942412894e-07,
      "learning_rate": 1.2709163809053764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7436496,
      "step": 26545
    },
    {
      "epoch": 295.0,
      "grad_norm": 5.45243494798342e-07,
      "learning_rate": 1.2700615675906963e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7437888,
      "step": 26550
    },
    {
      "epoch": 295.05555555555554,
      "grad_norm": 5.694676019629696e-07,
      "learning_rate": 1.269206943947978e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7439280,
      "step": 26555
    },
    {
      "epoch": 295.1111111111111,
      "grad_norm": 5.394756499299547e-07,
      "learning_rate": 1.2683525101090177e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7440688,
      "step": 26560
    },
    {
      "epoch": 295.1666666666667,
      "grad_norm": 5.344681994756684e-07,
      "learning_rate": 1.2674982662055765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7442112,
      "step": 26565
    },
    {
      "epoch": 295.22222222222223,
      "grad_norm": 5.118576495988236e-07,
      "learning_rate": 1.2666442123693922e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7443472,
      "step": 26570
    },
    {
      "epoch": 295.27777777777777,
      "grad_norm": 9.293483458350238e-07,
      "learning_rate": 1.265790348732169e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7444816,
      "step": 26575
    },
    {
      "epoch": 295.3333333333333,
      "grad_norm": 5.358304520086676e-07,
      "learning_rate": 1.264936675425584e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7446208,
      "step": 26580
    },
    {
      "epoch": 295.3888888888889,
      "grad_norm": 1.659445160839823e-06,
      "learning_rate": 1.2640831925812852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7447616,
      "step": 26585
    },
    {
      "epoch": 295.44444444444446,
      "grad_norm": 1.6546235883652116e-06,
      "learning_rate": 1.263229900330889e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7449072,
      "step": 26590
    },
    {
      "epoch": 295.5,
      "grad_norm": 5.713939685847436e-07,
      "learning_rate": 1.2623767988059843e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7450464,
      "step": 26595
    },
    {
      "epoch": 295.55555555555554,
      "grad_norm": 6.160985890346637e-07,
      "learning_rate": 1.2615238881381309e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7451904,
      "step": 26600
    },
    {
      "epoch": 295.55555555555554,
      "eval_loss": 0.32041311264038086,
      "eval_runtime": 1.2902,
      "eval_samples_per_second": 31.003,
      "eval_steps_per_second": 15.502,
      "num_input_tokens_seen": 7451904,
      "step": 26600
    },
    {
      "epoch": 295.6111111111111,
      "grad_norm": 2.012328423006693e-06,
      "learning_rate": 1.2606711684588568e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7453328,
      "step": 26605
    },
    {
      "epoch": 295.6666666666667,
      "grad_norm": 5.197099994802556e-07,
      "learning_rate": 1.2598186398996636e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7454704,
      "step": 26610
    },
    {
      "epoch": 295.72222222222223,
      "grad_norm": 4.930816430714913e-07,
      "learning_rate": 1.2589663025920207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7456096,
      "step": 26615
    },
    {
      "epoch": 295.77777777777777,
      "grad_norm": 5.798002007395553e-07,
      "learning_rate": 1.2581141566673705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7457504,
      "step": 26620
    },
    {
      "epoch": 295.8333333333333,
      "grad_norm": 5.936309435128351e-07,
      "learning_rate": 1.257262202257124e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7458928,
      "step": 26625
    },
    {
      "epoch": 295.8888888888889,
      "grad_norm": 5.279207471176051e-07,
      "learning_rate": 1.2564104394926618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7460320,
      "step": 26630
    },
    {
      "epoch": 295.94444444444446,
      "grad_norm": 8.138352427522477e-07,
      "learning_rate": 1.2555588685053383e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7461728,
      "step": 26635
    },
    {
      "epoch": 296.0,
      "grad_norm": 7.26577923160221e-07,
      "learning_rate": 1.2547074894264762e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7463072,
      "step": 26640
    },
    {
      "epoch": 296.05555555555554,
      "grad_norm": 5.526208042283542e-07,
      "learning_rate": 1.2538563023873679e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7464480,
      "step": 26645
    },
    {
      "epoch": 296.1111111111111,
      "grad_norm": 5.750885634370206e-07,
      "learning_rate": 1.2530053075192789e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7465872,
      "step": 26650
    },
    {
      "epoch": 296.1666666666667,
      "grad_norm": 4.803571869160805e-07,
      "learning_rate": 1.252154504953441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7467248,
      "step": 26655
    },
    {
      "epoch": 296.22222222222223,
      "grad_norm": 4.845288685828564e-07,
      "learning_rate": 1.25130389482106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7468592,
      "step": 26660
    },
    {
      "epoch": 296.27777777777777,
      "grad_norm": 5.676019441125391e-07,
      "learning_rate": 1.2504534772533116e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7469984,
      "step": 26665
    },
    {
      "epoch": 296.3333333333333,
      "grad_norm": 8.272504032902361e-07,
      "learning_rate": 1.2496032523813387e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7471392,
      "step": 26670
    },
    {
      "epoch": 296.3888888888889,
      "grad_norm": 1.6826993487484287e-06,
      "learning_rate": 1.2487532203362576e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7472816,
      "step": 26675
    },
    {
      "epoch": 296.44444444444446,
      "grad_norm": 5.285610313876532e-07,
      "learning_rate": 1.247903381249155e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7474224,
      "step": 26680
    },
    {
      "epoch": 296.5,
      "grad_norm": 1.000811721496575e-06,
      "learning_rate": 1.2470537352510853e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7475648,
      "step": 26685
    },
    {
      "epoch": 296.55555555555554,
      "grad_norm": 2.346776454942301e-06,
      "learning_rate": 1.2462042824730758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7477072,
      "step": 26690
    },
    {
      "epoch": 296.6111111111111,
      "grad_norm": 5.394664981395181e-07,
      "learning_rate": 1.245355023046122e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7478432,
      "step": 26695
    },
    {
      "epoch": 296.6666666666667,
      "grad_norm": 6.668154242106539e-07,
      "learning_rate": 1.2445059571011896e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7479840,
      "step": 26700
    },
    {
      "epoch": 296.72222222222223,
      "grad_norm": 1.6922284657994169e-06,
      "learning_rate": 1.2436570847692173e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7481200,
      "step": 26705
    },
    {
      "epoch": 296.77777777777777,
      "grad_norm": 5.698620952898636e-07,
      "learning_rate": 1.2428084061811096e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7482640,
      "step": 26710
    },
    {
      "epoch": 296.8333333333333,
      "grad_norm": 4.927362056150741e-07,
      "learning_rate": 1.2419599214677447e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7484064,
      "step": 26715
    },
    {
      "epoch": 296.8888888888889,
      "grad_norm": 3.2382315566792386e-06,
      "learning_rate": 1.2411116307599702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7485456,
      "step": 26720
    },
    {
      "epoch": 296.94444444444446,
      "grad_norm": 5.622915750791435e-07,
      "learning_rate": 1.2402635341886016e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7486864,
      "step": 26725
    },
    {
      "epoch": 297.0,
      "grad_norm": 5.861136287421687e-07,
      "learning_rate": 1.2394156318844278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7488272,
      "step": 26730
    },
    {
      "epoch": 297.05555555555554,
      "grad_norm": 4.461033142888482e-07,
      "learning_rate": 1.2385679239782039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7489664,
      "step": 26735
    },
    {
      "epoch": 297.1111111111111,
      "grad_norm": 2.1551154532062355e-06,
      "learning_rate": 1.2377204106006585e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7491056,
      "step": 26740
    },
    {
      "epoch": 297.1666666666667,
      "grad_norm": 1.6978168559944606e-06,
      "learning_rate": 1.2368730918824891e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7492432,
      "step": 26745
    },
    {
      "epoch": 297.22222222222223,
      "grad_norm": 5.373328235691588e-07,
      "learning_rate": 1.236025967954362e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7493872,
      "step": 26750
    },
    {
      "epoch": 297.27777777777777,
      "grad_norm": 6.01525414367643e-07,
      "learning_rate": 1.2351790389469153e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7495248,
      "step": 26755
    },
    {
      "epoch": 297.3333333333333,
      "grad_norm": 4.878182267020748e-07,
      "learning_rate": 1.234332304990755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7496624,
      "step": 26760
    },
    {
      "epoch": 297.3888888888889,
      "grad_norm": 6.119300905993441e-07,
      "learning_rate": 1.2334857662164593e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7498032,
      "step": 26765
    },
    {
      "epoch": 297.44444444444446,
      "grad_norm": 1.0019272167482995e-06,
      "learning_rate": 1.2326394227545743e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7499440,
      "step": 26770
    },
    {
      "epoch": 297.5,
      "grad_norm": 5.622849812425557e-07,
      "learning_rate": 1.2317932747356162e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7500816,
      "step": 26775
    },
    {
      "epoch": 297.55555555555554,
      "grad_norm": 6.156608947094355e-07,
      "learning_rate": 1.2309473222900726e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7502240,
      "step": 26780
    },
    {
      "epoch": 297.6111111111111,
      "grad_norm": 6.964023100408667e-07,
      "learning_rate": 1.2301015655484006e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7503584,
      "step": 26785
    },
    {
      "epoch": 297.6666666666667,
      "grad_norm": 2.292353883603937e-06,
      "learning_rate": 1.2292560046410245e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7504976,
      "step": 26790
    },
    {
      "epoch": 297.72222222222223,
      "grad_norm": 5.273440706332622e-07,
      "learning_rate": 1.228410639698343e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7506368,
      "step": 26795
    },
    {
      "epoch": 297.77777777777777,
      "grad_norm": 1.4826565575276618e-06,
      "learning_rate": 1.2275654708507195e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7507792,
      "step": 26800
    },
    {
      "epoch": 297.77777777777777,
      "eval_loss": 0.31429359316825867,
      "eval_runtime": 1.3055,
      "eval_samples_per_second": 30.64,
      "eval_steps_per_second": 15.32,
      "num_input_tokens_seen": 7507792,
      "step": 26800
    },
    {
      "epoch": 297.8333333333333,
      "grad_norm": 4.480414474983263e-07,
      "learning_rate": 1.2267204982284908e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7509232,
      "step": 26805
    },
    {
      "epoch": 297.8888888888889,
      "grad_norm": 4.7097384481276094e-07,
      "learning_rate": 1.2258757219619635e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7510608,
      "step": 26810
    },
    {
      "epoch": 297.94444444444446,
      "grad_norm": 6.505007377199945e-07,
      "learning_rate": 1.2250311421814104e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7512000,
      "step": 26815
    },
    {
      "epoch": 298.0,
      "grad_norm": 5.411491770246357e-07,
      "learning_rate": 1.2241867590170772e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7513456,
      "step": 26820
    },
    {
      "epoch": 298.05555555555554,
      "grad_norm": 1.727633048176358e-06,
      "learning_rate": 1.2233425725991799e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7514800,
      "step": 26825
    },
    {
      "epoch": 298.1111111111111,
      "grad_norm": 5.367169819692208e-07,
      "learning_rate": 1.2224985830579003e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7516192,
      "step": 26830
    },
    {
      "epoch": 298.1666666666667,
      "grad_norm": 4.6291054900393647e-07,
      "learning_rate": 1.2216547905233944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7517600,
      "step": 26835
    },
    {
      "epoch": 298.22222222222223,
      "grad_norm": 4.850516575061192e-07,
      "learning_rate": 1.2208111951257842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7519024,
      "step": 26840
    },
    {
      "epoch": 298.27777777777777,
      "grad_norm": 2.2982367227086797e-06,
      "learning_rate": 1.2199677969951622e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7520416,
      "step": 26845
    },
    {
      "epoch": 298.3333333333333,
      "grad_norm": 5.780436254099186e-07,
      "learning_rate": 1.2191245962615927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7521872,
      "step": 26850
    },
    {
      "epoch": 298.3888888888889,
      "grad_norm": 8.744240744817944e-07,
      "learning_rate": 1.218281593055106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7523232,
      "step": 26855
    },
    {
      "epoch": 298.44444444444446,
      "grad_norm": 1.5068122820593999e-06,
      "learning_rate": 1.217438787505705e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7524672,
      "step": 26860
    },
    {
      "epoch": 298.5,
      "grad_norm": 5.266506377665792e-07,
      "learning_rate": 1.2165961797433615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7526064,
      "step": 26865
    },
    {
      "epoch": 298.55555555555554,
      "grad_norm": 1.9539991171768634e-06,
      "learning_rate": 1.215753769898014e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7527488,
      "step": 26870
    },
    {
      "epoch": 298.6111111111111,
      "grad_norm": 5.207298841014563e-07,
      "learning_rate": 1.2149115580995755e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7528816,
      "step": 26875
    },
    {
      "epoch": 298.6666666666667,
      "grad_norm": 1.0342935183871305e-06,
      "learning_rate": 1.2140695444779227e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7530224,
      "step": 26880
    },
    {
      "epoch": 298.72222222222223,
      "grad_norm": 5.694889750884613e-07,
      "learning_rate": 1.2132277291629066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7531600,
      "step": 26885
    },
    {
      "epoch": 298.77777777777777,
      "grad_norm": 9.548652997182216e-07,
      "learning_rate": 1.2123861122843458e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7533008,
      "step": 26890
    },
    {
      "epoch": 298.8333333333333,
      "grad_norm": 5.118274088999897e-07,
      "learning_rate": 1.2115446939720271e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7534400,
      "step": 26895
    },
    {
      "epoch": 298.8888888888889,
      "grad_norm": 4.975360639036808e-07,
      "learning_rate": 1.210703474355708e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7535776,
      "step": 26900
    },
    {
      "epoch": 298.94444444444446,
      "grad_norm": 5.95915878420783e-07,
      "learning_rate": 1.2098624535651164e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7537184,
      "step": 26905
    },
    {
      "epoch": 299.0,
      "grad_norm": 6.379732440109365e-07,
      "learning_rate": 1.2090216317299477e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7538640,
      "step": 26910
    },
    {
      "epoch": 299.05555555555554,
      "grad_norm": 3.5172233765479177e-06,
      "learning_rate": 1.2081810089798668e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7540048,
      "step": 26915
    },
    {
      "epoch": 299.1111111111111,
      "grad_norm": 5.656102644024941e-07,
      "learning_rate": 1.2073405854445072e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7541424,
      "step": 26920
    },
    {
      "epoch": 299.1666666666667,
      "grad_norm": 5.638145808006811e-07,
      "learning_rate": 1.206500361253474e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7542832,
      "step": 26925
    },
    {
      "epoch": 299.22222222222223,
      "grad_norm": 4.648365745651972e-07,
      "learning_rate": 1.2056603365363409e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7544256,
      "step": 26930
    },
    {
      "epoch": 299.27777777777777,
      "grad_norm": 9.09125219550333e-07,
      "learning_rate": 1.2048205114226487e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7545600,
      "step": 26935
    },
    {
      "epoch": 299.3333333333333,
      "grad_norm": 5.623937795462552e-07,
      "learning_rate": 1.2039808860419102e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7547024,
      "step": 26940
    },
    {
      "epoch": 299.3888888888889,
      "grad_norm": 1.493469198976527e-06,
      "learning_rate": 1.2031414605236066e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7548432,
      "step": 26945
    },
    {
      "epoch": 299.44444444444446,
      "grad_norm": 5.612940867649741e-07,
      "learning_rate": 1.2023022349971862e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7549840,
      "step": 26950
    },
    {
      "epoch": 299.5,
      "grad_norm": 5.427878591035551e-07,
      "learning_rate": 1.20146320959207e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7551280,
      "step": 26955
    },
    {
      "epoch": 299.55555555555554,
      "grad_norm": 4.923340952700528e-07,
      "learning_rate": 1.2006243844376445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7552640,
      "step": 26960
    },
    {
      "epoch": 299.6111111111111,
      "grad_norm": 5.737363721891597e-07,
      "learning_rate": 1.1997857596632678e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7553984,
      "step": 26965
    },
    {
      "epoch": 299.6666666666667,
      "grad_norm": 3.519410938679357e-06,
      "learning_rate": 1.1989473353982672e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7555408,
      "step": 26970
    },
    {
      "epoch": 299.72222222222223,
      "grad_norm": 5.087662202640786e-07,
      "learning_rate": 1.198109111771937e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7556784,
      "step": 26975
    },
    {
      "epoch": 299.77777777777777,
      "grad_norm": 4.937681978844921e-07,
      "learning_rate": 1.197271088913543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7558176,
      "step": 26980
    },
    {
      "epoch": 299.8333333333333,
      "grad_norm": 5.053787504039065e-07,
      "learning_rate": 1.1964332669523182e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7559648,
      "step": 26985
    },
    {
      "epoch": 299.8888888888889,
      "grad_norm": 5.808994387734856e-07,
      "learning_rate": 1.1955956460174645e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7561056,
      "step": 26990
    },
    {
      "epoch": 299.94444444444446,
      "grad_norm": 4.914608098260942e-07,
      "learning_rate": 1.1947582262381552e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7562464,
      "step": 26995
    },
    {
      "epoch": 300.0,
      "grad_norm": 1.7046269249476609e-06,
      "learning_rate": 1.1939210077435293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7563888,
      "step": 27000
    },
    {
      "epoch": 300.0,
      "eval_loss": 0.3090466856956482,
      "eval_runtime": 1.2841,
      "eval_samples_per_second": 31.15,
      "eval_steps_per_second": 15.575,
      "num_input_tokens_seen": 7563888,
      "step": 27000
    },
    {
      "epoch": 300.05555555555554,
      "grad_norm": 2.0295560716476757e-06,
      "learning_rate": 1.193083990662697e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7565312,
      "step": 27005
    },
    {
      "epoch": 300.1111111111111,
      "grad_norm": 5.34877528934885e-07,
      "learning_rate": 1.192247175124738e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7566688,
      "step": 27010
    },
    {
      "epoch": 300.1666666666667,
      "grad_norm": 5.299136205394461e-07,
      "learning_rate": 1.191410561258698e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7568096,
      "step": 27015
    },
    {
      "epoch": 300.22222222222223,
      "grad_norm": 5.13415898240055e-07,
      "learning_rate": 1.1905741491935944e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7569472,
      "step": 27020
    },
    {
      "epoch": 300.27777777777777,
      "grad_norm": 5.262523927740403e-07,
      "learning_rate": 1.1897379390584129e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7570944,
      "step": 27025
    },
    {
      "epoch": 300.3333333333333,
      "grad_norm": 2.0035658963024616e-06,
      "learning_rate": 1.1889019309821062e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7572384,
      "step": 27030
    },
    {
      "epoch": 300.3888888888889,
      "grad_norm": 6.185455845297838e-07,
      "learning_rate": 1.188066125093599e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7573776,
      "step": 27035
    },
    {
      "epoch": 300.44444444444446,
      "grad_norm": 5.027608267482719e-07,
      "learning_rate": 1.1872305215217811e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7575216,
      "step": 27040
    },
    {
      "epoch": 300.5,
      "grad_norm": 4.959622970091004e-07,
      "learning_rate": 1.186395120395514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7576656,
      "step": 27045
    },
    {
      "epoch": 300.55555555555554,
      "grad_norm": 5.542790404433617e-07,
      "learning_rate": 1.1855599218436283e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7578048,
      "step": 27050
    },
    {
      "epoch": 300.6111111111111,
      "grad_norm": 2.010609023272991e-06,
      "learning_rate": 1.1847249259949209e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7579392,
      "step": 27055
    },
    {
      "epoch": 300.6666666666667,
      "grad_norm": 5.142158556736831e-07,
      "learning_rate": 1.1838901329781574e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7580752,
      "step": 27060
    },
    {
      "epoch": 300.72222222222223,
      "grad_norm": 1.7407497807653272e-06,
      "learning_rate": 1.1830555429220758e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7582144,
      "step": 27065
    },
    {
      "epoch": 300.77777777777777,
      "grad_norm": 4.7520001089651487e-07,
      "learning_rate": 1.1822211559553784e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7583488,
      "step": 27070
    },
    {
      "epoch": 300.8333333333333,
      "grad_norm": 4.5924912228656467e-07,
      "learning_rate": 1.18138697220674e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7584912,
      "step": 27075
    },
    {
      "epoch": 300.8888888888889,
      "grad_norm": 4.6376277396120713e-07,
      "learning_rate": 1.1805529918048e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7586256,
      "step": 27080
    },
    {
      "epoch": 300.94444444444446,
      "grad_norm": 4.7380666501339874e-07,
      "learning_rate": 1.1797192148781702e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7587648,
      "step": 27085
    },
    {
      "epoch": 301.0,
      "grad_norm": 1.9579179024731275e-06,
      "learning_rate": 1.1788856415554297e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7589088,
      "step": 27090
    },
    {
      "epoch": 301.05555555555554,
      "grad_norm": 6.500005156340194e-07,
      "learning_rate": 1.1780522719651249e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7590512,
      "step": 27095
    },
    {
      "epoch": 301.1111111111111,
      "grad_norm": 1.4869997357891407e-06,
      "learning_rate": 1.1772191062357721e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7591920,
      "step": 27100
    },
    {
      "epoch": 301.1666666666667,
      "grad_norm": 5.518021453099209e-07,
      "learning_rate": 1.1763861444958573e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7593296,
      "step": 27105
    },
    {
      "epoch": 301.22222222222223,
      "grad_norm": 1.0402698080724804e-06,
      "learning_rate": 1.1755533868738317e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7594688,
      "step": 27110
    },
    {
      "epoch": 301.27777777777777,
      "grad_norm": 9.39195956561889e-07,
      "learning_rate": 1.1747208334981185e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7596032,
      "step": 27115
    },
    {
      "epoch": 301.3333333333333,
      "grad_norm": 9.705526053949143e-07,
      "learning_rate": 1.1738884844971067e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7597472,
      "step": 27120
    },
    {
      "epoch": 301.3888888888889,
      "grad_norm": 5.372160671868187e-07,
      "learning_rate": 1.1730563399991563e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7598896,
      "step": 27125
    },
    {
      "epoch": 301.44444444444446,
      "grad_norm": 3.5920086247642757e-06,
      "learning_rate": 1.1722244001325938e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7600336,
      "step": 27130
    },
    {
      "epoch": 301.5,
      "grad_norm": 6.151901175144303e-07,
      "learning_rate": 1.1713926650257137e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7601776,
      "step": 27135
    },
    {
      "epoch": 301.55555555555554,
      "grad_norm": 6.25378959284717e-07,
      "learning_rate": 1.170561134806781e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7603168,
      "step": 27140
    },
    {
      "epoch": 301.6111111111111,
      "grad_norm": 9.014612487590057e-07,
      "learning_rate": 1.1697298096040287e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7604544,
      "step": 27145
    },
    {
      "epoch": 301.6666666666667,
      "grad_norm": 4.830865236726822e-07,
      "learning_rate": 1.1688986895456567e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7605904,
      "step": 27150
    },
    {
      "epoch": 301.72222222222223,
      "grad_norm": 9.664424851507647e-07,
      "learning_rate": 1.1680677747598349e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7607280,
      "step": 27155
    },
    {
      "epoch": 301.77777777777777,
      "grad_norm": 2.173213943024166e-06,
      "learning_rate": 1.1672370653746995e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7608672,
      "step": 27160
    },
    {
      "epoch": 301.8333333333333,
      "grad_norm": 9.99533540380071e-07,
      "learning_rate": 1.166406561518357e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7610064,
      "step": 27165
    },
    {
      "epoch": 301.8888888888889,
      "grad_norm": 9.140453016698302e-07,
      "learning_rate": 1.1655762633188826e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7611488,
      "step": 27170
    },
    {
      "epoch": 301.94444444444446,
      "grad_norm": 6.049554599485418e-07,
      "learning_rate": 1.1647461709043172e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7612896,
      "step": 27175
    },
    {
      "epoch": 302.0,
      "grad_norm": 5.251470156508731e-07,
      "learning_rate": 1.1639162844026722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7614288,
      "step": 27180
    },
    {
      "epoch": 302.05555555555554,
      "grad_norm": 5.377695515562664e-07,
      "learning_rate": 1.163086603941927e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7615712,
      "step": 27185
    },
    {
      "epoch": 302.1111111111111,
      "grad_norm": 1.6877091866263072e-06,
      "learning_rate": 1.1622571296500273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7617072,
      "step": 27190
    },
    {
      "epoch": 302.1666666666667,
      "grad_norm": 5.801322231491213e-07,
      "learning_rate": 1.1614278616548904e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7618464,
      "step": 27195
    },
    {
      "epoch": 302.22222222222223,
      "grad_norm": 4.978665515409375e-07,
      "learning_rate": 1.1605988000843986e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7619872,
      "step": 27200
    },
    {
      "epoch": 302.22222222222223,
      "eval_loss": 0.3612271845340729,
      "eval_runtime": 1.3005,
      "eval_samples_per_second": 30.759,
      "eval_steps_per_second": 15.379,
      "num_input_tokens_seen": 7619872,
      "step": 27200
    },
    {
      "epoch": 302.27777777777777,
      "grad_norm": 5.205465072322113e-07,
      "learning_rate": 1.1597699450664028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7621296,
      "step": 27205
    },
    {
      "epoch": 302.3333333333333,
      "grad_norm": 5.763631634181365e-07,
      "learning_rate": 1.1589412967287252e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7622752,
      "step": 27210
    },
    {
      "epoch": 302.3888888888889,
      "grad_norm": 2.023536808337667e-06,
      "learning_rate": 1.1581128551991514e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7624144,
      "step": 27215
    },
    {
      "epoch": 302.44444444444446,
      "grad_norm": 5.45583247912873e-07,
      "learning_rate": 1.1572846206054383e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7625536,
      "step": 27220
    },
    {
      "epoch": 302.5,
      "grad_norm": 4.072622061812581e-07,
      "learning_rate": 1.1564565930753113e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7626928,
      "step": 27225
    },
    {
      "epoch": 302.55555555555554,
      "grad_norm": 5.861267595719255e-07,
      "learning_rate": 1.1556287727364606e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7628272,
      "step": 27230
    },
    {
      "epoch": 302.6111111111111,
      "grad_norm": 1.5163391253736336e-06,
      "learning_rate": 1.1548011597165489e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7629664,
      "step": 27235
    },
    {
      "epoch": 302.6666666666667,
      "grad_norm": 3.485256002022652e-06,
      "learning_rate": 1.1539737541432019e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7631088,
      "step": 27240
    },
    {
      "epoch": 302.72222222222223,
      "grad_norm": 3.7712995890615275e-06,
      "learning_rate": 1.1531465561440174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7632528,
      "step": 27245
    },
    {
      "epoch": 302.77777777777777,
      "grad_norm": 9.939259371094522e-07,
      "learning_rate": 1.1523195658465605e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7633904,
      "step": 27250
    },
    {
      "epoch": 302.8333333333333,
      "grad_norm": 5.93325921727228e-07,
      "learning_rate": 1.1514927833783618e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7635296,
      "step": 27255
    },
    {
      "epoch": 302.8888888888889,
      "grad_norm": 5.194074219616596e-07,
      "learning_rate": 1.150666208866922e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7636640,
      "step": 27260
    },
    {
      "epoch": 302.94444444444446,
      "grad_norm": 3.686490344989579e-06,
      "learning_rate": 1.1498398424397106e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7638080,
      "step": 27265
    },
    {
      "epoch": 303.0,
      "grad_norm": 8.983543011709116e-07,
      "learning_rate": 1.1490136842241628e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7639472,
      "step": 27270
    },
    {
      "epoch": 303.05555555555554,
      "grad_norm": 8.552109420634224e-07,
      "learning_rate": 1.1481877343476813e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7640864,
      "step": 27275
    },
    {
      "epoch": 303.1111111111111,
      "grad_norm": 5.838579113515152e-07,
      "learning_rate": 1.14736199293764e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7642208,
      "step": 27280
    },
    {
      "epoch": 303.1666666666667,
      "grad_norm": 5.1472147788445e-07,
      "learning_rate": 1.1465364601213771e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7643584,
      "step": 27285
    },
    {
      "epoch": 303.22222222222223,
      "grad_norm": 4.4116080744061037e-07,
      "learning_rate": 1.1457111360262012e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7644976,
      "step": 27290
    },
    {
      "epoch": 303.27777777777777,
      "grad_norm": 5.266974199003016e-07,
      "learning_rate": 1.1448860207793869e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7646400,
      "step": 27295
    },
    {
      "epoch": 303.3333333333333,
      "grad_norm": 1.5097429013621877e-06,
      "learning_rate": 1.144061114508177e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7647824,
      "step": 27300
    },
    {
      "epoch": 303.3888888888889,
      "grad_norm": 9.055906389221491e-07,
      "learning_rate": 1.1432364173397842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7649232,
      "step": 27305
    },
    {
      "epoch": 303.44444444444446,
      "grad_norm": 9.624768608773593e-07,
      "learning_rate": 1.1424119294013852e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7650656,
      "step": 27310
    },
    {
      "epoch": 303.5,
      "grad_norm": 3.357468187914492e-07,
      "learning_rate": 1.1415876508201279e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7652080,
      "step": 27315
    },
    {
      "epoch": 303.55555555555554,
      "grad_norm": 4.991619562133565e-07,
      "learning_rate": 1.140763581723125e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7653520,
      "step": 27320
    },
    {
      "epoch": 303.6111111111111,
      "grad_norm": 5.187719125387957e-07,
      "learning_rate": 1.1399397222374588e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7654896,
      "step": 27325
    },
    {
      "epoch": 303.6666666666667,
      "grad_norm": 5.803570388707158e-07,
      "learning_rate": 1.1391160724901804e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7656272,
      "step": 27330
    },
    {
      "epoch": 303.72222222222223,
      "grad_norm": 5.189781404624227e-07,
      "learning_rate": 1.138292632608304e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7657680,
      "step": 27335
    },
    {
      "epoch": 303.77777777777777,
      "grad_norm": 6.135247190286464e-07,
      "learning_rate": 1.1374694027188174e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7659136,
      "step": 27340
    },
    {
      "epoch": 303.8333333333333,
      "grad_norm": 1.987015593840624e-06,
      "learning_rate": 1.1366463829486711e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7660592,
      "step": 27345
    },
    {
      "epoch": 303.8888888888889,
      "grad_norm": 4.836538209929131e-07,
      "learning_rate": 1.1358235734247849e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7662000,
      "step": 27350
    },
    {
      "epoch": 303.94444444444446,
      "grad_norm": 5.410568633124058e-07,
      "learning_rate": 1.1350009742740478e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7663392,
      "step": 27355
    },
    {
      "epoch": 304.0,
      "grad_norm": 5.683465360561968e-07,
      "learning_rate": 1.134178585623313e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7664784,
      "step": 27360
    },
    {
      "epoch": 304.05555555555554,
      "grad_norm": 5.74028661048942e-07,
      "learning_rate": 1.1333564075994047e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7666192,
      "step": 27365
    },
    {
      "epoch": 304.1111111111111,
      "grad_norm": 9.623580581319402e-07,
      "learning_rate": 1.1325344403291133e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7667616,
      "step": 27370
    },
    {
      "epoch": 304.1666666666667,
      "grad_norm": 5.772924964730919e-07,
      "learning_rate": 1.1317126839391951e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7669008,
      "step": 27375
    },
    {
      "epoch": 304.22222222222223,
      "grad_norm": 5.397338895818393e-07,
      "learning_rate": 1.1308911385563766e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7670432,
      "step": 27380
    },
    {
      "epoch": 304.27777777777777,
      "grad_norm": 1.025463234327617e-06,
      "learning_rate": 1.1300698043073494e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7671824,
      "step": 27385
    },
    {
      "epoch": 304.3333333333333,
      "grad_norm": 3.0406461064558243e-06,
      "learning_rate": 1.1292486813187736e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7673216,
      "step": 27390
    },
    {
      "epoch": 304.3888888888889,
      "grad_norm": 5.681795300915837e-07,
      "learning_rate": 1.1284277697172782e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7674608,
      "step": 27395
    },
    {
      "epoch": 304.44444444444446,
      "grad_norm": 6.078858518776542e-07,
      "learning_rate": 1.127607069629456e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7676016,
      "step": 27400
    },
    {
      "epoch": 304.44444444444446,
      "eval_loss": 0.3266785740852356,
      "eval_runtime": 1.2903,
      "eval_samples_per_second": 31.0,
      "eval_steps_per_second": 15.5,
      "num_input_tokens_seen": 7676016,
      "step": 27400
    },
    {
      "epoch": 304.5,
      "grad_norm": 5.567513312598749e-07,
      "learning_rate": 1.1267865811818701e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7677376,
      "step": 27405
    },
    {
      "epoch": 304.55555555555554,
      "grad_norm": 8.769919190854125e-07,
      "learning_rate": 1.1259663045010513e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7678720,
      "step": 27410
    },
    {
      "epoch": 304.6111111111111,
      "grad_norm": 4.855500606026908e-07,
      "learning_rate": 1.1251462397134957e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7680144,
      "step": 27415
    },
    {
      "epoch": 304.6666666666667,
      "grad_norm": 4.1990301724581514e-07,
      "learning_rate": 1.1243263869456664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7681536,
      "step": 27420
    },
    {
      "epoch": 304.72222222222223,
      "grad_norm": 4.416937713358493e-07,
      "learning_rate": 1.1235067463239967e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7682944,
      "step": 27425
    },
    {
      "epoch": 304.77777777777777,
      "grad_norm": 1.7916222532221582e-06,
      "learning_rate": 1.122687317974884e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7684336,
      "step": 27430
    },
    {
      "epoch": 304.8333333333333,
      "grad_norm": 5.043232249590801e-07,
      "learning_rate": 1.1218681020246963e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7685744,
      "step": 27435
    },
    {
      "epoch": 304.8888888888889,
      "grad_norm": 5.131219040777069e-07,
      "learning_rate": 1.1210490985997652e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7687120,
      "step": 27440
    },
    {
      "epoch": 304.94444444444446,
      "grad_norm": 6.316291774055571e-07,
      "learning_rate": 1.1202303078263917e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7688560,
      "step": 27445
    },
    {
      "epoch": 305.0,
      "grad_norm": 5.981181629977073e-07,
      "learning_rate": 1.1194117298308451e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7689952,
      "step": 27450
    },
    {
      "epoch": 305.05555555555554,
      "grad_norm": 2.05451783585886e-06,
      "learning_rate": 1.1185933647393585e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7691360,
      "step": 27455
    },
    {
      "epoch": 305.1111111111111,
      "grad_norm": 9.487615670877858e-07,
      "learning_rate": 1.1177752126781354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7692784,
      "step": 27460
    },
    {
      "epoch": 305.1666666666667,
      "grad_norm": 6.264973535508034e-07,
      "learning_rate": 1.1169572737733441e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7694144,
      "step": 27465
    },
    {
      "epoch": 305.22222222222223,
      "grad_norm": 9.731077170727076e-07,
      "learning_rate": 1.1161395481511216e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7695536,
      "step": 27470
    },
    {
      "epoch": 305.27777777777777,
      "grad_norm": 8.605987886767252e-07,
      "learning_rate": 1.1153220359375722e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7696928,
      "step": 27475
    },
    {
      "epoch": 305.3333333333333,
      "grad_norm": 6.721879231008643e-07,
      "learning_rate": 1.114504737258765e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7698368,
      "step": 27480
    },
    {
      "epoch": 305.3888888888889,
      "grad_norm": 4.923122105537914e-07,
      "learning_rate": 1.1136876522407393e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7699776,
      "step": 27485
    },
    {
      "epoch": 305.44444444444446,
      "grad_norm": 5.125127131577756e-07,
      "learning_rate": 1.1128707810094985e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7701200,
      "step": 27490
    },
    {
      "epoch": 305.5,
      "grad_norm": 9.78265802586975e-07,
      "learning_rate": 1.1120541236910157e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7702576,
      "step": 27495
    },
    {
      "epoch": 305.55555555555554,
      "grad_norm": 2.2035785605112324e-06,
      "learning_rate": 1.111237680411229e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7703984,
      "step": 27500
    },
    {
      "epoch": 305.6111111111111,
      "grad_norm": 8.698058877598669e-07,
      "learning_rate": 1.1104214512960433e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7705360,
      "step": 27505
    },
    {
      "epoch": 305.6666666666667,
      "grad_norm": 4.869235681326245e-07,
      "learning_rate": 1.1096054364713327e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7706752,
      "step": 27510
    },
    {
      "epoch": 305.72222222222223,
      "grad_norm": 5.730183829655289e-07,
      "learning_rate": 1.1087896360629371e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7708112,
      "step": 27515
    },
    {
      "epoch": 305.77777777777777,
      "grad_norm": 6.76858689985238e-07,
      "learning_rate": 1.107974050196662e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7709504,
      "step": 27520
    },
    {
      "epoch": 305.8333333333333,
      "grad_norm": 4.4558015588336275e-07,
      "learning_rate": 1.1071586789982816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7710912,
      "step": 27525
    },
    {
      "epoch": 305.8888888888889,
      "grad_norm": 5.562031901718001e-07,
      "learning_rate": 1.1063435225935373e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7712320,
      "step": 27530
    },
    {
      "epoch": 305.94444444444446,
      "grad_norm": 5.788950261376158e-07,
      "learning_rate": 1.1055285811081348e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7713712,
      "step": 27535
    },
    {
      "epoch": 306.0,
      "grad_norm": 2.0517088614724344e-06,
      "learning_rate": 1.1047138546677499e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7715104,
      "step": 27540
    },
    {
      "epoch": 306.05555555555554,
      "grad_norm": 5.639324740513985e-07,
      "learning_rate": 1.1038993433980219e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7716528,
      "step": 27545
    },
    {
      "epoch": 306.1111111111111,
      "grad_norm": 5.223163270784426e-07,
      "learning_rate": 1.1030850474245597e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7717968,
      "step": 27550
    },
    {
      "epoch": 306.1666666666667,
      "grad_norm": 9.195653660754033e-07,
      "learning_rate": 1.102270966872939e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7719360,
      "step": 27555
    },
    {
      "epoch": 306.22222222222223,
      "grad_norm": 5.885068503630464e-07,
      "learning_rate": 1.1014571018687e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7720768,
      "step": 27560
    },
    {
      "epoch": 306.27777777777777,
      "grad_norm": 3.775359573410242e-06,
      "learning_rate": 1.1006434525373502e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7722160,
      "step": 27565
    },
    {
      "epoch": 306.3333333333333,
      "grad_norm": 4.820956291951006e-07,
      "learning_rate": 1.0998300190043664e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7723552,
      "step": 27570
    },
    {
      "epoch": 306.3888888888889,
      "grad_norm": 5.479373044181557e-07,
      "learning_rate": 1.0990168013951882e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7724944,
      "step": 27575
    },
    {
      "epoch": 306.44444444444446,
      "grad_norm": 9.485378313911497e-07,
      "learning_rate": 1.0982037998352263e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7726320,
      "step": 27580
    },
    {
      "epoch": 306.5,
      "grad_norm": 3.0812444151706586e-07,
      "learning_rate": 1.0973910144498534e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7727728,
      "step": 27585
    },
    {
      "epoch": 306.55555555555554,
      "grad_norm": 5.461515115712245e-07,
      "learning_rate": 1.0965784453644123e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7729104,
      "step": 27590
    },
    {
      "epoch": 306.6111111111111,
      "grad_norm": 4.821891366191267e-07,
      "learning_rate": 1.0957660927042127e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7730464,
      "step": 27595
    },
    {
      "epoch": 306.6666666666667,
      "grad_norm": 5.67838810638932e-07,
      "learning_rate": 1.094953956594527e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7731872,
      "step": 27600
    },
    {
      "epoch": 306.6666666666667,
      "eval_loss": 0.30818554759025574,
      "eval_runtime": 1.2943,
      "eval_samples_per_second": 30.904,
      "eval_steps_per_second": 15.452,
      "num_input_tokens_seen": 7731872,
      "step": 27600
    },
    {
      "epoch": 306.72222222222223,
      "grad_norm": 3.704822688632703e-07,
      "learning_rate": 1.0941420371605981e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7733312,
      "step": 27605
    },
    {
      "epoch": 306.77777777777777,
      "grad_norm": 5.186539624446596e-07,
      "learning_rate": 1.0933303345276354e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7734736,
      "step": 27610
    },
    {
      "epoch": 306.8333333333333,
      "grad_norm": 9.750577874001465e-07,
      "learning_rate": 1.0925188488208112e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7736112,
      "step": 27615
    },
    {
      "epoch": 306.8888888888889,
      "grad_norm": 5.77103776322474e-07,
      "learning_rate": 1.0917075801652694e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7737520,
      "step": 27620
    },
    {
      "epoch": 306.94444444444446,
      "grad_norm": 1.5112277651496697e-06,
      "learning_rate": 1.0908965286861151e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7738928,
      "step": 27625
    },
    {
      "epoch": 307.0,
      "grad_norm": 2.1627631667797687e-06,
      "learning_rate": 1.090085694508425e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7740304,
      "step": 27630
    },
    {
      "epoch": 307.05555555555554,
      "grad_norm": 6.231739462236874e-07,
      "learning_rate": 1.089275077757238e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7741680,
      "step": 27635
    },
    {
      "epoch": 307.1111111111111,
      "grad_norm": 9.079363394448592e-07,
      "learning_rate": 1.0884646785575633e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7743104,
      "step": 27640
    },
    {
      "epoch": 307.1666666666667,
      "grad_norm": 3.9247808558684483e-07,
      "learning_rate": 1.0876544970343728e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7744528,
      "step": 27645
    },
    {
      "epoch": 307.22222222222223,
      "grad_norm": 4.9055836370826e-07,
      "learning_rate": 1.0868445333126082e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7745952,
      "step": 27650
    },
    {
      "epoch": 307.27777777777777,
      "grad_norm": 9.084834005079756e-07,
      "learning_rate": 1.0860347875171745e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7747392,
      "step": 27655
    },
    {
      "epoch": 307.3333333333333,
      "grad_norm": 6.829707217548275e-07,
      "learning_rate": 1.0852252597729465e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7748784,
      "step": 27660
    },
    {
      "epoch": 307.3888888888889,
      "grad_norm": 5.24731717632676e-07,
      "learning_rate": 1.0844159502047615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7750160,
      "step": 27665
    },
    {
      "epoch": 307.44444444444446,
      "grad_norm": 5.657219048771367e-07,
      "learning_rate": 1.0836068589374265e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7751568,
      "step": 27670
    },
    {
      "epoch": 307.5,
      "grad_norm": 4.4546879962581443e-07,
      "learning_rate": 1.0827979860957144e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7752976,
      "step": 27675
    },
    {
      "epoch": 307.55555555555554,
      "grad_norm": 1.7505254845673335e-06,
      "learning_rate": 1.0819893318043615e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7754368,
      "step": 27680
    },
    {
      "epoch": 307.6111111111111,
      "grad_norm": 2.376621296207304e-06,
      "learning_rate": 1.0811808961880734e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7755744,
      "step": 27685
    },
    {
      "epoch": 307.6666666666667,
      "grad_norm": 5.761550596616871e-07,
      "learning_rate": 1.080372679371522e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7757168,
      "step": 27690
    },
    {
      "epoch": 307.72222222222223,
      "grad_norm": 5.533406124413887e-07,
      "learning_rate": 1.0795646814793428e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7758544,
      "step": 27695
    },
    {
      "epoch": 307.77777777777777,
      "grad_norm": 6.02418538164784e-07,
      "learning_rate": 1.078756902636141e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7760000,
      "step": 27700
    },
    {
      "epoch": 307.8333333333333,
      "grad_norm": 1.5672311519665527e-06,
      "learning_rate": 1.077949342966485e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7761376,
      "step": 27705
    },
    {
      "epoch": 307.8888888888889,
      "grad_norm": 6.583348977073911e-07,
      "learning_rate": 1.0771420025949103e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7762784,
      "step": 27710
    },
    {
      "epoch": 307.94444444444446,
      "grad_norm": 3.682880787891918e-06,
      "learning_rate": 1.0763348816459204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7764128,
      "step": 27715
    },
    {
      "epoch": 308.0,
      "grad_norm": 5.006650098948739e-07,
      "learning_rate": 1.0755279802439816e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7765584,
      "step": 27720
    },
    {
      "epoch": 308.05555555555554,
      "grad_norm": 5.059791305939143e-07,
      "learning_rate": 1.0747212985135293e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7767008,
      "step": 27725
    },
    {
      "epoch": 308.1111111111111,
      "grad_norm": 5.272155476632179e-07,
      "learning_rate": 1.073914836578965e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7768400,
      "step": 27730
    },
    {
      "epoch": 308.1666666666667,
      "grad_norm": 5.23434721344529e-07,
      "learning_rate": 1.0731085945646529e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7769792,
      "step": 27735
    },
    {
      "epoch": 308.22222222222223,
      "grad_norm": 4.2005839873127115e-07,
      "learning_rate": 1.0723025725949285e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7771184,
      "step": 27740
    },
    {
      "epoch": 308.27777777777777,
      "grad_norm": 5.437763661575445e-07,
      "learning_rate": 1.0714967707940875e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7772544,
      "step": 27745
    },
    {
      "epoch": 308.3333333333333,
      "grad_norm": 1.521449803476571e-06,
      "learning_rate": 1.0706911892863963e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7773952,
      "step": 27750
    },
    {
      "epoch": 308.3888888888889,
      "grad_norm": 3.6684258475361275e-07,
      "learning_rate": 1.0698858281960866e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7775312,
      "step": 27755
    },
    {
      "epoch": 308.44444444444446,
      "grad_norm": 3.628257161381043e-07,
      "learning_rate": 1.069080687647353e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7776672,
      "step": 27760
    },
    {
      "epoch": 308.5,
      "grad_norm": 8.744095794099849e-07,
      "learning_rate": 1.0682757677643596e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7778080,
      "step": 27765
    },
    {
      "epoch": 308.55555555555554,
      "grad_norm": 4.6903028305678163e-07,
      "learning_rate": 1.0674710686712359e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7779504,
      "step": 27770
    },
    {
      "epoch": 308.6111111111111,
      "grad_norm": 5.800900453323266e-07,
      "learning_rate": 1.0666665904920756e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7780896,
      "step": 27775
    },
    {
      "epoch": 308.6666666666667,
      "grad_norm": 6.14077805494162e-07,
      "learning_rate": 1.0658623333509385e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7782320,
      "step": 27780
    },
    {
      "epoch": 308.72222222222223,
      "grad_norm": 1.721926309983246e-06,
      "learning_rate": 1.0650582973718532e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7783760,
      "step": 27785
    },
    {
      "epoch": 308.77777777777777,
      "grad_norm": 3.998857209808193e-07,
      "learning_rate": 1.0642544826788098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7785152,
      "step": 27790
    },
    {
      "epoch": 308.8333333333333,
      "grad_norm": 5.488291208166629e-07,
      "learning_rate": 1.063450889395769e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7786560,
      "step": 27795
    },
    {
      "epoch": 308.8888888888889,
      "grad_norm": 4.789845320374297e-07,
      "learning_rate": 1.062647517646653e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7787920,
      "step": 27800
    },
    {
      "epoch": 308.8888888888889,
      "eval_loss": 0.3292129337787628,
      "eval_runtime": 1.2916,
      "eval_samples_per_second": 30.969,
      "eval_steps_per_second": 15.485,
      "num_input_tokens_seen": 7787920,
      "step": 27800
    },
    {
      "epoch": 308.94444444444446,
      "grad_norm": 1.031195324685541e-06,
      "learning_rate": 1.0618443675553527e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7789312,
      "step": 27805
    },
    {
      "epoch": 309.0,
      "grad_norm": 1.4762623550268472e-06,
      "learning_rate": 1.0610414392457247e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7790736,
      "step": 27810
    },
    {
      "epoch": 309.05555555555554,
      "grad_norm": 8.926591590352473e-07,
      "learning_rate": 1.0602387328415888e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7792096,
      "step": 27815
    },
    {
      "epoch": 309.1111111111111,
      "grad_norm": 5.234675768406305e-07,
      "learning_rate": 1.0594362484667347e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7793520,
      "step": 27820
    },
    {
      "epoch": 309.1666666666667,
      "grad_norm": 5.684991037924192e-07,
      "learning_rate": 1.0586339862449132e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7794944,
      "step": 27825
    },
    {
      "epoch": 309.22222222222223,
      "grad_norm": 5.290203262120485e-07,
      "learning_rate": 1.0578319462998445e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7796352,
      "step": 27830
    },
    {
      "epoch": 309.27777777777777,
      "grad_norm": 5.633516479974787e-07,
      "learning_rate": 1.057030128755214e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7797760,
      "step": 27835
    },
    {
      "epoch": 309.3333333333333,
      "grad_norm": 5.309273092279909e-07,
      "learning_rate": 1.0562285337346703e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7799200,
      "step": 27840
    },
    {
      "epoch": 309.3888888888889,
      "grad_norm": 1.7024642602336826e-06,
      "learning_rate": 1.0554271613618308e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7800592,
      "step": 27845
    },
    {
      "epoch": 309.44444444444446,
      "grad_norm": 5.957026587566361e-07,
      "learning_rate": 1.054626011760276e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7802000,
      "step": 27850
    },
    {
      "epoch": 309.5,
      "grad_norm": 8.647937193018151e-07,
      "learning_rate": 1.0538250850535549e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7803408,
      "step": 27855
    },
    {
      "epoch": 309.55555555555554,
      "grad_norm": 5.664046511810739e-07,
      "learning_rate": 1.0530243813651794e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7804784,
      "step": 27860
    },
    {
      "epoch": 309.6111111111111,
      "grad_norm": 3.2372163332183845e-06,
      "learning_rate": 1.0522239008186271e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7806160,
      "step": 27865
    },
    {
      "epoch": 309.6666666666667,
      "grad_norm": 4.7462302177336824e-07,
      "learning_rate": 1.0514236435373434e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7807536,
      "step": 27870
    },
    {
      "epoch": 309.72222222222223,
      "grad_norm": 5.745228577325179e-07,
      "learning_rate": 1.0506236096447386e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7808928,
      "step": 27875
    },
    {
      "epoch": 309.77777777777777,
      "grad_norm": 6.325585673039313e-07,
      "learning_rate": 1.049823799264186e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7810352,
      "step": 27880
    },
    {
      "epoch": 309.8333333333333,
      "grad_norm": 5.850913566973759e-07,
      "learning_rate": 1.049024212519028e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7811760,
      "step": 27885
    },
    {
      "epoch": 309.8888888888889,
      "grad_norm": 5.902450084249722e-07,
      "learning_rate": 1.0482248495325713e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7813184,
      "step": 27890
    },
    {
      "epoch": 309.94444444444446,
      "grad_norm": 1.6846204289322486e-06,
      "learning_rate": 1.047425710428086e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7814640,
      "step": 27895
    },
    {
      "epoch": 310.0,
      "grad_norm": 1.4948906255085603e-06,
      "learning_rate": 1.0466267953288114e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7816016,
      "step": 27900
    },
    {
      "epoch": 310.05555555555554,
      "grad_norm": 5.23777316630003e-07,
      "learning_rate": 1.0458281043579482e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7817392,
      "step": 27905
    },
    {
      "epoch": 310.1111111111111,
      "grad_norm": 9.506194942332513e-07,
      "learning_rate": 1.0450296376386657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7818768,
      "step": 27910
    },
    {
      "epoch": 310.1666666666667,
      "grad_norm": 2.1913058390055085e-06,
      "learning_rate": 1.044231395294098e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7820208,
      "step": 27915
    },
    {
      "epoch": 310.22222222222223,
      "grad_norm": 5.686100621460355e-07,
      "learning_rate": 1.0434333774473435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7821616,
      "step": 27920
    },
    {
      "epoch": 310.27777777777777,
      "grad_norm": 5.377025900088483e-07,
      "learning_rate": 1.0426355842214657e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7823040,
      "step": 27925
    },
    {
      "epoch": 310.3333333333333,
      "grad_norm": 5.788563157693716e-07,
      "learning_rate": 1.0418380157394963e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7824464,
      "step": 27930
    },
    {
      "epoch": 310.3888888888889,
      "grad_norm": 6.503203735519492e-07,
      "learning_rate": 1.0410406721244281e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7825840,
      "step": 27935
    },
    {
      "epoch": 310.44444444444446,
      "grad_norm": 4.6138501375025953e-07,
      "learning_rate": 1.0402435534992238e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7827280,
      "step": 27940
    },
    {
      "epoch": 310.5,
      "grad_norm": 9.269755310015171e-07,
      "learning_rate": 1.0394466599868071e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7828672,
      "step": 27945
    },
    {
      "epoch": 310.55555555555554,
      "grad_norm": 2.230466179753421e-06,
      "learning_rate": 1.0386499917100697e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7830080,
      "step": 27950
    },
    {
      "epoch": 310.6111111111111,
      "grad_norm": 1.680289415162406e-06,
      "learning_rate": 1.0378535487918692e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7831440,
      "step": 27955
    },
    {
      "epoch": 310.6666666666667,
      "grad_norm": 1.6767617125879042e-06,
      "learning_rate": 1.037057331355025e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7832880,
      "step": 27960
    },
    {
      "epoch": 310.72222222222223,
      "grad_norm": 6.529405709443381e-07,
      "learning_rate": 1.0362613395223247e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7834240,
      "step": 27965
    },
    {
      "epoch": 310.77777777777777,
      "grad_norm": 2.269508968311129e-06,
      "learning_rate": 1.0354655734165212e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7835616,
      "step": 27970
    },
    {
      "epoch": 310.8333333333333,
      "grad_norm": 6.009857997923973e-07,
      "learning_rate": 1.03467003316033e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7837056,
      "step": 27975
    },
    {
      "epoch": 310.8888888888889,
      "grad_norm": 2.0299503376008943e-06,
      "learning_rate": 1.033874718876435e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7838448,
      "step": 27980
    },
    {
      "epoch": 310.94444444444446,
      "grad_norm": 5.450111757454579e-07,
      "learning_rate": 1.0330796306874818e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7839856,
      "step": 27985
    },
    {
      "epoch": 311.0,
      "grad_norm": 9.847148021435714e-07,
      "learning_rate": 1.032284768716085e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7841264,
      "step": 27990
    },
    {
      "epoch": 311.05555555555554,
      "grad_norm": 5.354916083888384e-07,
      "learning_rate": 1.0314901330848206e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7842672,
      "step": 27995
    },
    {
      "epoch": 311.1111111111111,
      "grad_norm": 4.979401637683623e-07,
      "learning_rate": 1.030695723916233e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7844080,
      "step": 28000
    },
    {
      "epoch": 311.1111111111111,
      "eval_loss": 0.315041720867157,
      "eval_runtime": 1.2877,
      "eval_samples_per_second": 31.064,
      "eval_steps_per_second": 15.532,
      "num_input_tokens_seen": 7844080,
      "step": 28000
    },
    {
      "epoch": 311.1666666666667,
      "grad_norm": 6.543059498653747e-07,
      "learning_rate": 1.0299015413328289e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7845488,
      "step": 28005
    },
    {
      "epoch": 311.22222222222223,
      "grad_norm": 5.033031698076229e-07,
      "learning_rate": 1.0291075854570809e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7846928,
      "step": 28010
    },
    {
      "epoch": 311.27777777777777,
      "grad_norm": 5.770675670646597e-07,
      "learning_rate": 1.0283138564114275e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7848368,
      "step": 28015
    },
    {
      "epoch": 311.3333333333333,
      "grad_norm": 5.642455107590649e-07,
      "learning_rate": 1.027520354318273e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7849744,
      "step": 28020
    },
    {
      "epoch": 311.3888888888889,
      "grad_norm": 4.951158416588441e-07,
      "learning_rate": 1.0267270792999828e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7851120,
      "step": 28025
    },
    {
      "epoch": 311.44444444444446,
      "grad_norm": 1.6335316104232334e-06,
      "learning_rate": 1.0259340314788919e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7852560,
      "step": 28030
    },
    {
      "epoch": 311.5,
      "grad_norm": 5.232951139078068e-07,
      "learning_rate": 1.0251412109772979e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7854000,
      "step": 28035
    },
    {
      "epoch": 311.55555555555554,
      "grad_norm": 9.563490266373265e-07,
      "learning_rate": 1.0243486179174627e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7855408,
      "step": 28040
    },
    {
      "epoch": 311.6111111111111,
      "grad_norm": 9.383735459778109e-07,
      "learning_rate": 1.0235562524216158e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7856800,
      "step": 28045
    },
    {
      "epoch": 311.6666666666667,
      "grad_norm": 1.0392790272817365e-06,
      "learning_rate": 1.022764114611948e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7858192,
      "step": 28050
    },
    {
      "epoch": 311.72222222222223,
      "grad_norm": 4.0551719848735956e-07,
      "learning_rate": 1.0219722046106178e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7859616,
      "step": 28055
    },
    {
      "epoch": 311.77777777777777,
      "grad_norm": 9.56597091317235e-07,
      "learning_rate": 1.0211805225397486e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7861008,
      "step": 28060
    },
    {
      "epoch": 311.8333333333333,
      "grad_norm": 6.765633315808373e-07,
      "learning_rate": 1.020389068521426e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7862400,
      "step": 28065
    },
    {
      "epoch": 311.8888888888889,
      "grad_norm": 5.728687142436684e-07,
      "learning_rate": 1.0195978426777039e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7863776,
      "step": 28070
    },
    {
      "epoch": 311.94444444444446,
      "grad_norm": 1.0643684618116822e-06,
      "learning_rate": 1.0188068451305982e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7865152,
      "step": 28075
    },
    {
      "epoch": 312.0,
      "grad_norm": 1.6567109923926182e-06,
      "learning_rate": 1.0180160760020902e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7866496,
      "step": 28080
    },
    {
      "epoch": 312.05555555555554,
      "grad_norm": 1.6933851156863966e-06,
      "learning_rate": 1.0172255354141278e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7867888,
      "step": 28085
    },
    {
      "epoch": 312.1111111111111,
      "grad_norm": 7.142290883166424e-07,
      "learning_rate": 1.0164352234886205e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7869264,
      "step": 28090
    },
    {
      "epoch": 312.1666666666667,
      "grad_norm": 1.660793259361526e-06,
      "learning_rate": 1.0156451403474454e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7870624,
      "step": 28095
    },
    {
      "epoch": 312.22222222222223,
      "grad_norm": 5.143468229107384e-07,
      "learning_rate": 1.0148552861124443e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7872016,
      "step": 28100
    },
    {
      "epoch": 312.27777777777777,
      "grad_norm": 6.102193310653092e-07,
      "learning_rate": 1.0140656609054205e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7873408,
      "step": 28105
    },
    {
      "epoch": 312.3333333333333,
      "grad_norm": 5.992064302517974e-07,
      "learning_rate": 1.0132762648481455e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7874832,
      "step": 28110
    },
    {
      "epoch": 312.3888888888889,
      "grad_norm": 5.914803864470741e-07,
      "learning_rate": 1.0124870980623543e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7876240,
      "step": 28115
    },
    {
      "epoch": 312.44444444444446,
      "grad_norm": 5.332106525202107e-07,
      "learning_rate": 1.0116981606697453e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7877616,
      "step": 28120
    },
    {
      "epoch": 312.5,
      "grad_norm": 5.453015887724177e-07,
      "learning_rate": 1.0109094527919838e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7878992,
      "step": 28125
    },
    {
      "epoch": 312.55555555555554,
      "grad_norm": 1.6375821587644168e-06,
      "learning_rate": 1.010120974550697e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7880352,
      "step": 28130
    },
    {
      "epoch": 312.6111111111111,
      "grad_norm": 9.695620519778458e-07,
      "learning_rate": 1.0093327260674795e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7881744,
      "step": 28135
    },
    {
      "epoch": 312.6666666666667,
      "grad_norm": 4.834829496758175e-07,
      "learning_rate": 1.0085447074638878e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7883120,
      "step": 28140
    },
    {
      "epoch": 312.72222222222223,
      "grad_norm": 4.606708046139829e-07,
      "learning_rate": 1.0077569188614461e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7884544,
      "step": 28145
    },
    {
      "epoch": 312.77777777777777,
      "grad_norm": 2.9872992399759823e-06,
      "learning_rate": 1.0069693603816393e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7885984,
      "step": 28150
    },
    {
      "epoch": 312.8333333333333,
      "grad_norm": 5.719650744140381e-07,
      "learning_rate": 1.0061820321459204e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7887392,
      "step": 28155
    },
    {
      "epoch": 312.8888888888889,
      "grad_norm": 8.79192498359771e-07,
      "learning_rate": 1.0053949342757038e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7888816,
      "step": 28160
    },
    {
      "epoch": 312.94444444444446,
      "grad_norm": 5.499118742591236e-07,
      "learning_rate": 1.0046080668923717e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7890272,
      "step": 28165
    },
    {
      "epoch": 313.0,
      "grad_norm": 6.126070388745575e-07,
      "learning_rate": 1.003821430117267e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7891648,
      "step": 28170
    },
    {
      "epoch": 313.05555555555554,
      "grad_norm": 5.50761967588187e-07,
      "learning_rate": 1.0030350240716999e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7893056,
      "step": 28175
    },
    {
      "epoch": 313.1111111111111,
      "grad_norm": 1.0004761179516208e-06,
      "learning_rate": 1.0022488488769449e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7894400,
      "step": 28180
    },
    {
      "epoch": 313.1666666666667,
      "grad_norm": 4.272779108305258e-07,
      "learning_rate": 1.0014629046542387e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7895824,
      "step": 28185
    },
    {
      "epoch": 313.22222222222223,
      "grad_norm": 5.492823333952401e-07,
      "learning_rate": 1.0006771915247842e-05,
      "loss": 0.0,
      "num_input_tokens_seen": 7897248,
      "step": 28190
    },
    {
      "epoch": 313.27777777777777,
      "grad_norm": 6.454497452068608e-07,
      "learning_rate": 9.998917096097495e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7898624,
      "step": 28195
    },
    {
      "epoch": 313.3333333333333,
      "grad_norm": 2.8561396447912557e-06,
      "learning_rate": 9.991064590302638e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7900064,
      "step": 28200
    },
    {
      "epoch": 313.3333333333333,
      "eval_loss": 0.3051114082336426,
      "eval_runtime": 1.2945,
      "eval_samples_per_second": 30.901,
      "eval_steps_per_second": 15.45,
      "num_input_tokens_seen": 7900064,
      "step": 28200
    },
    {
      "epoch": 313.3888888888889,
      "grad_norm": 1.6312266097884276e-06,
      "learning_rate": 9.983214399074241e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7901472,
      "step": 28205
    },
    {
      "epoch": 313.44444444444446,
      "grad_norm": 5.45905891158327e-07,
      "learning_rate": 9.975366523622893e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7902880,
      "step": 28210
    },
    {
      "epoch": 313.5,
      "grad_norm": 5.88225645969942e-07,
      "learning_rate": 9.967520965158841e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7904256,
      "step": 28215
    },
    {
      "epoch": 313.55555555555554,
      "grad_norm": 5.346261673366826e-07,
      "learning_rate": 9.95967772489197e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7905680,
      "step": 28220
    },
    {
      "epoch": 313.6111111111111,
      "grad_norm": 2.0078462057426805e-06,
      "learning_rate": 9.951836804031794e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7907072,
      "step": 28225
    },
    {
      "epoch": 313.6666666666667,
      "grad_norm": 1.4839520190434996e-06,
      "learning_rate": 9.943998203787489e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7908496,
      "step": 28230
    },
    {
      "epoch": 313.72222222222223,
      "grad_norm": 6.043815687917231e-07,
      "learning_rate": 9.936161925367874e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7909904,
      "step": 28235
    },
    {
      "epoch": 313.77777777777777,
      "grad_norm": 1.7506046106063877e-06,
      "learning_rate": 9.928327969981386e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7911328,
      "step": 28240
    },
    {
      "epoch": 313.8333333333333,
      "grad_norm": 6.185812821968284e-07,
      "learning_rate": 9.920496338836135e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7912720,
      "step": 28245
    },
    {
      "epoch": 313.8888888888889,
      "grad_norm": 5.230497208685847e-07,
      "learning_rate": 9.912667033139844e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7914064,
      "step": 28250
    },
    {
      "epoch": 313.94444444444446,
      "grad_norm": 5.077195055491757e-07,
      "learning_rate": 9.904840054099893e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7915456,
      "step": 28255
    },
    {
      "epoch": 314.0,
      "grad_norm": 5.859782277184422e-07,
      "learning_rate": 9.897015402923312e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7916784,
      "step": 28260
    },
    {
      "epoch": 314.05555555555554,
      "grad_norm": 1.0390569968876662e-06,
      "learning_rate": 9.889193080816744e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7918176,
      "step": 28265
    },
    {
      "epoch": 314.1111111111111,
      "grad_norm": 1.9844860617013182e-06,
      "learning_rate": 9.881373088986498e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7919584,
      "step": 28270
    },
    {
      "epoch": 314.1666666666667,
      "grad_norm": 5.215819669501798e-07,
      "learning_rate": 9.873555428638523e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7920960,
      "step": 28275
    },
    {
      "epoch": 314.22222222222223,
      "grad_norm": 4.937136850458046e-07,
      "learning_rate": 9.865740100978383e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7922384,
      "step": 28280
    },
    {
      "epoch": 314.27777777777777,
      "grad_norm": 6.040534117346397e-07,
      "learning_rate": 9.857927107211315e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7923744,
      "step": 28285
    },
    {
      "epoch": 314.3333333333333,
      "grad_norm": 1.022063088385039e-06,
      "learning_rate": 9.850116448542177e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7925104,
      "step": 28290
    },
    {
      "epoch": 314.3888888888889,
      "grad_norm": 9.120597610490222e-07,
      "learning_rate": 9.842308126175457e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7926496,
      "step": 28295
    },
    {
      "epoch": 314.44444444444446,
      "grad_norm": 5.717264457416604e-07,
      "learning_rate": 9.834502141315315e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7927904,
      "step": 28300
    },
    {
      "epoch": 314.5,
      "grad_norm": 5.971970722384867e-07,
      "learning_rate": 9.82669849516552e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7929328,
      "step": 28305
    },
    {
      "epoch": 314.55555555555554,
      "grad_norm": 5.790458317278535e-07,
      "learning_rate": 9.818897188929493e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7930736,
      "step": 28310
    },
    {
      "epoch": 314.6111111111111,
      "grad_norm": 1.7424943052901654e-06,
      "learning_rate": 9.811098223810309e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7932112,
      "step": 28315
    },
    {
      "epoch": 314.6666666666667,
      "grad_norm": 1.6586577658017632e-06,
      "learning_rate": 9.803301601010641e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7933536,
      "step": 28320
    },
    {
      "epoch": 314.72222222222223,
      "grad_norm": 5.603554882327444e-07,
      "learning_rate": 9.795507321732853e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7934928,
      "step": 28325
    },
    {
      "epoch": 314.77777777777777,
      "grad_norm": 2.2951478513277834e-06,
      "learning_rate": 9.787715387178898e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7936400,
      "step": 28330
    },
    {
      "epoch": 314.8333333333333,
      "grad_norm": 5.526715085579781e-07,
      "learning_rate": 9.779925798550399e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7937792,
      "step": 28335
    },
    {
      "epoch": 314.8888888888889,
      "grad_norm": 5.235132789493946e-07,
      "learning_rate": 9.772138557048619e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7939184,
      "step": 28340
    },
    {
      "epoch": 314.94444444444446,
      "grad_norm": 3.8486706444018637e-07,
      "learning_rate": 9.764353663874426e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7940624,
      "step": 28345
    },
    {
      "epoch": 315.0,
      "grad_norm": 5.512377470040519e-07,
      "learning_rate": 9.756571120228375e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7942016,
      "step": 28350
    },
    {
      "epoch": 315.05555555555554,
      "grad_norm": 5.554250606110145e-07,
      "learning_rate": 9.748790927310605e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7943392,
      "step": 28355
    },
    {
      "epoch": 315.1111111111111,
      "grad_norm": 4.960070896231628e-07,
      "learning_rate": 9.741013086320946e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7944784,
      "step": 28360
    },
    {
      "epoch": 315.1666666666667,
      "grad_norm": 3.705333483594586e-06,
      "learning_rate": 9.733237598458821e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7946176,
      "step": 28365
    },
    {
      "epoch": 315.22222222222223,
      "grad_norm": 5.898145332139393e-07,
      "learning_rate": 9.725464464923308e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7947568,
      "step": 28370
    },
    {
      "epoch": 315.27777777777777,
      "grad_norm": 6.332034558909072e-07,
      "learning_rate": 9.717693686913123e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7948976,
      "step": 28375
    },
    {
      "epoch": 315.3333333333333,
      "grad_norm": 9.70079440776317e-07,
      "learning_rate": 9.709925265626632e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7950320,
      "step": 28380
    },
    {
      "epoch": 315.3888888888889,
      "grad_norm": 6.006835064908955e-07,
      "learning_rate": 9.702159202261801e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7951728,
      "step": 28385
    },
    {
      "epoch": 315.44444444444446,
      "grad_norm": 5.953956474513689e-07,
      "learning_rate": 9.694395498016268e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7953152,
      "step": 28390
    },
    {
      "epoch": 315.5,
      "grad_norm": 6.303581017164106e-07,
      "learning_rate": 9.686634154087298e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7954624,
      "step": 28395
    },
    {
      "epoch": 315.55555555555554,
      "grad_norm": 3.71167084267654e-06,
      "learning_rate": 9.678875171671776e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7956016,
      "step": 28400
    },
    {
      "epoch": 315.55555555555554,
      "eval_loss": 0.3159722685813904,
      "eval_runtime": 1.291,
      "eval_samples_per_second": 30.983,
      "eval_steps_per_second": 15.492,
      "num_input_tokens_seen": 7956016,
      "step": 28400
    },
    {
      "epoch": 315.6111111111111,
      "grad_norm": 2.196558170908247e-06,
      "learning_rate": 9.671118551966246e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7957440,
      "step": 28405
    },
    {
      "epoch": 315.6666666666667,
      "grad_norm": 4.471098122849071e-07,
      "learning_rate": 9.66336429616686e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7958864,
      "step": 28410
    },
    {
      "epoch": 315.72222222222223,
      "grad_norm": 5.156324505151133e-07,
      "learning_rate": 9.655612405469436e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7960272,
      "step": 28415
    },
    {
      "epoch": 315.77777777777777,
      "grad_norm": 5.325221650309686e-07,
      "learning_rate": 9.647862881069413e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7961680,
      "step": 28420
    },
    {
      "epoch": 315.8333333333333,
      "grad_norm": 6.650971045019105e-07,
      "learning_rate": 9.640115724161855e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7963088,
      "step": 28425
    },
    {
      "epoch": 315.8888888888889,
      "grad_norm": 1.6591397979937028e-06,
      "learning_rate": 9.632370935941483e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7964464,
      "step": 28430
    },
    {
      "epoch": 315.94444444444446,
      "grad_norm": 5.479866445057269e-07,
      "learning_rate": 9.624628517602634e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7965872,
      "step": 28435
    },
    {
      "epoch": 316.0,
      "grad_norm": 5.107183369545965e-07,
      "learning_rate": 9.61688847033928e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7967264,
      "step": 28440
    },
    {
      "epoch": 316.05555555555554,
      "grad_norm": 5.748769922320207e-07,
      "learning_rate": 9.609150795345051e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7968720,
      "step": 28445
    },
    {
      "epoch": 316.1111111111111,
      "grad_norm": 9.743777127368958e-07,
      "learning_rate": 9.601415493813171e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7970112,
      "step": 28450
    },
    {
      "epoch": 316.1666666666667,
      "grad_norm": 4.591057631841977e-07,
      "learning_rate": 9.593682566936533e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7971520,
      "step": 28455
    },
    {
      "epoch": 316.22222222222223,
      "grad_norm": 1.6941610283538466e-06,
      "learning_rate": 9.58595201590766e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7972896,
      "step": 28460
    },
    {
      "epoch": 316.27777777777777,
      "grad_norm": 1.0124629170604749e-06,
      "learning_rate": 9.578223841918681e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7974320,
      "step": 28465
    },
    {
      "epoch": 316.3333333333333,
      "grad_norm": 1.4684667348774383e-06,
      "learning_rate": 9.570498046161389e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7975760,
      "step": 28470
    },
    {
      "epoch": 316.3888888888889,
      "grad_norm": 8.341487500729272e-07,
      "learning_rate": 9.562774629827206e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7977184,
      "step": 28475
    },
    {
      "epoch": 316.44444444444446,
      "grad_norm": 5.245888701210788e-07,
      "learning_rate": 9.555053594107163e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7978576,
      "step": 28480
    },
    {
      "epoch": 316.5,
      "grad_norm": 5.156637143954867e-07,
      "learning_rate": 9.547334940191957e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7979952,
      "step": 28485
    },
    {
      "epoch": 316.55555555555554,
      "grad_norm": 4.635125776530913e-07,
      "learning_rate": 9.539618669271886e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7981376,
      "step": 28490
    },
    {
      "epoch": 316.6111111111111,
      "grad_norm": 9.524140978101059e-07,
      "learning_rate": 9.531904782536904e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7982720,
      "step": 28495
    },
    {
      "epoch": 316.6666666666667,
      "grad_norm": 5.032575245422777e-07,
      "learning_rate": 9.524193281176597e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7984096,
      "step": 28500
    },
    {
      "epoch": 316.72222222222223,
      "grad_norm": 4.586574959830614e-07,
      "learning_rate": 9.516484166380165e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7985472,
      "step": 28505
    },
    {
      "epoch": 316.77777777777777,
      "grad_norm": 2.3174768557510106e-06,
      "learning_rate": 9.508777439336447e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7986832,
      "step": 28510
    },
    {
      "epoch": 316.8333333333333,
      "grad_norm": 5.911026050853252e-07,
      "learning_rate": 9.50107310123393e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7988224,
      "step": 28515
    },
    {
      "epoch": 316.8888888888889,
      "grad_norm": 5.37509151854465e-07,
      "learning_rate": 9.493371153260702e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7989680,
      "step": 28520
    },
    {
      "epoch": 316.94444444444446,
      "grad_norm": 6.099438110140909e-07,
      "learning_rate": 9.485671596604523e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7991056,
      "step": 28525
    },
    {
      "epoch": 317.0,
      "grad_norm": 1.5061219755807542e-06,
      "learning_rate": 9.477974432452738e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7992464,
      "step": 28530
    },
    {
      "epoch": 317.05555555555554,
      "grad_norm": 1.654160769248847e-06,
      "learning_rate": 9.470279661992356e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7993856,
      "step": 28535
    },
    {
      "epoch": 317.1111111111111,
      "grad_norm": 9.357416956845555e-07,
      "learning_rate": 9.462587286410021e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7995264,
      "step": 28540
    },
    {
      "epoch": 317.1666666666667,
      "grad_norm": 5.491813794833433e-07,
      "learning_rate": 9.454897306891972e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7996624,
      "step": 28545
    },
    {
      "epoch": 317.22222222222223,
      "grad_norm": 9.68774202192435e-07,
      "learning_rate": 9.44720972462411e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7998096,
      "step": 28550
    },
    {
      "epoch": 317.27777777777777,
      "grad_norm": 1.6590101949987002e-06,
      "learning_rate": 9.439524540791964e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 7999472,
      "step": 28555
    },
    {
      "epoch": 317.3333333333333,
      "grad_norm": 8.744650017433742e-07,
      "learning_rate": 9.431841756580673e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8000864,
      "step": 28560
    },
    {
      "epoch": 317.3888888888889,
      "grad_norm": 5.244748990662629e-07,
      "learning_rate": 9.42416137317503e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8002272,
      "step": 28565
    },
    {
      "epoch": 317.44444444444446,
      "grad_norm": 6.31000716566632e-07,
      "learning_rate": 9.416483391759437e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8003632,
      "step": 28570
    },
    {
      "epoch": 317.5,
      "grad_norm": 2.2548572360392427e-06,
      "learning_rate": 9.408807813517945e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8005008,
      "step": 28575
    },
    {
      "epoch": 317.55555555555554,
      "grad_norm": 9.763907655724324e-07,
      "learning_rate": 9.401134639634221e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8006432,
      "step": 28580
    },
    {
      "epoch": 317.6111111111111,
      "grad_norm": 5.612120617115579e-07,
      "learning_rate": 9.393463871291555e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8007840,
      "step": 28585
    },
    {
      "epoch": 317.6666666666667,
      "grad_norm": 9.512913834441861e-07,
      "learning_rate": 9.385795509672881e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8009264,
      "step": 28590
    },
    {
      "epoch": 317.72222222222223,
      "grad_norm": 5.637299977934163e-07,
      "learning_rate": 9.378129555960771e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8010720,
      "step": 28595
    },
    {
      "epoch": 317.77777777777777,
      "grad_norm": 5.517932208931597e-07,
      "learning_rate": 9.370466011337392e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8012160,
      "step": 28600
    },
    {
      "epoch": 317.77777777777777,
      "eval_loss": 0.3321463465690613,
      "eval_runtime": 1.2923,
      "eval_samples_per_second": 30.953,
      "eval_steps_per_second": 15.477,
      "num_input_tokens_seen": 8012160,
      "step": 28600
    },
    {
      "epoch": 317.8333333333333,
      "grad_norm": 1.0221614274996682e-06,
      "learning_rate": 9.362804876984573e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8013584,
      "step": 28605
    },
    {
      "epoch": 317.8888888888889,
      "grad_norm": 2.8508879950095434e-06,
      "learning_rate": 9.355146154083747e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8014992,
      "step": 28610
    },
    {
      "epoch": 317.94444444444446,
      "grad_norm": 5.403148293225968e-07,
      "learning_rate": 9.347489843815987e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8016384,
      "step": 28615
    },
    {
      "epoch": 318.0,
      "grad_norm": 8.963700111053186e-07,
      "learning_rate": 9.339835947362002e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8017776,
      "step": 28620
    },
    {
      "epoch": 318.05555555555554,
      "grad_norm": 4.7249591261788737e-07,
      "learning_rate": 9.332184465902105e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8019168,
      "step": 28625
    },
    {
      "epoch": 318.1111111111111,
      "grad_norm": 5.841628194502846e-07,
      "learning_rate": 9.324535400616266e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8020592,
      "step": 28630
    },
    {
      "epoch": 318.1666666666667,
      "grad_norm": 1.9634521777334157e-06,
      "learning_rate": 9.31688875268405e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8021984,
      "step": 28635
    },
    {
      "epoch": 318.22222222222223,
      "grad_norm": 5.991710168018471e-07,
      "learning_rate": 9.309244523284674e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8023376,
      "step": 28640
    },
    {
      "epoch": 318.27777777777777,
      "grad_norm": 5.316340434546873e-07,
      "learning_rate": 9.301602713596982e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8024816,
      "step": 28645
    },
    {
      "epoch": 318.3333333333333,
      "grad_norm": 5.283676500766887e-07,
      "learning_rate": 9.293963324799432e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8026160,
      "step": 28650
    },
    {
      "epoch": 318.3888888888889,
      "grad_norm": 1.0168507742491784e-06,
      "learning_rate": 9.286326358070104e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8027600,
      "step": 28655
    },
    {
      "epoch": 318.44444444444446,
      "grad_norm": 9.392257425133721e-07,
      "learning_rate": 9.278691814586729e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8029024,
      "step": 28660
    },
    {
      "epoch": 318.5,
      "grad_norm": 5.498803261616558e-07,
      "learning_rate": 9.271059695526635e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8030448,
      "step": 28665
    },
    {
      "epoch": 318.55555555555554,
      "grad_norm": 5.285381803332712e-07,
      "learning_rate": 9.263430002066805e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8031792,
      "step": 28670
    },
    {
      "epoch": 318.6111111111111,
      "grad_norm": 5.439065375867358e-07,
      "learning_rate": 9.25580273538382e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8033200,
      "step": 28675
    },
    {
      "epoch": 318.6666666666667,
      "grad_norm": 5.30565444023523e-07,
      "learning_rate": 9.248177896653907e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8034624,
      "step": 28680
    },
    {
      "epoch": 318.72222222222223,
      "grad_norm": 9.906789273372851e-07,
      "learning_rate": 9.240555487052918e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8036048,
      "step": 28685
    },
    {
      "epoch": 318.77777777777777,
      "grad_norm": 5.268922222967376e-07,
      "learning_rate": 9.232935507756313e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8037392,
      "step": 28690
    },
    {
      "epoch": 318.8333333333333,
      "grad_norm": 5.984384756629879e-07,
      "learning_rate": 9.225317959939193e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8038816,
      "step": 28695
    },
    {
      "epoch": 318.8888888888889,
      "grad_norm": 5.807111733702186e-07,
      "learning_rate": 9.217702844776287e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8040240,
      "step": 28700
    },
    {
      "epoch": 318.94444444444446,
      "grad_norm": 5.551153208216419e-07,
      "learning_rate": 9.210090163441929e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8041568,
      "step": 28705
    },
    {
      "epoch": 319.0,
      "grad_norm": 5.100942530589236e-07,
      "learning_rate": 9.202479917110105e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8042944,
      "step": 28710
    },
    {
      "epoch": 319.05555555555554,
      "grad_norm": 8.886340765457135e-07,
      "learning_rate": 9.194872106954392e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8044320,
      "step": 28715
    },
    {
      "epoch": 319.1111111111111,
      "grad_norm": 1.027980147227936e-06,
      "learning_rate": 9.187266734148029e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8045712,
      "step": 28720
    },
    {
      "epoch": 319.1666666666667,
      "grad_norm": 4.7043812401170726e-07,
      "learning_rate": 9.179663799863849e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8047104,
      "step": 28725
    },
    {
      "epoch": 319.22222222222223,
      "grad_norm": 9.587109843778308e-07,
      "learning_rate": 9.172063305274317e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8048496,
      "step": 28730
    },
    {
      "epoch": 319.27777777777777,
      "grad_norm": 6.206898888194701e-07,
      "learning_rate": 9.164465251551527e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8049872,
      "step": 28735
    },
    {
      "epoch": 319.3333333333333,
      "grad_norm": 5.45178977517935e-07,
      "learning_rate": 9.156869639867205e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8051296,
      "step": 28740
    },
    {
      "epoch": 319.3888888888889,
      "grad_norm": 9.121188782046374e-07,
      "learning_rate": 9.149276471392677e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8052720,
      "step": 28745
    },
    {
      "epoch": 319.44444444444446,
      "grad_norm": 2.204568545494112e-06,
      "learning_rate": 9.141685747298914e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8054160,
      "step": 28750
    },
    {
      "epoch": 319.5,
      "grad_norm": 4.7117669055296574e-07,
      "learning_rate": 9.13409746875649e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8055552,
      "step": 28755
    },
    {
      "epoch": 319.55555555555554,
      "grad_norm": 5.595040306616283e-07,
      "learning_rate": 9.12651163693562e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8057008,
      "step": 28760
    },
    {
      "epoch": 319.6111111111111,
      "grad_norm": 5.638999027723912e-07,
      "learning_rate": 9.11892825300614e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8058448,
      "step": 28765
    },
    {
      "epoch": 319.6666666666667,
      "grad_norm": 5.114353598401067e-07,
      "learning_rate": 9.111347318137491e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8059840,
      "step": 28770
    },
    {
      "epoch": 319.72222222222223,
      "grad_norm": 1.5196957292573643e-06,
      "learning_rate": 9.103768833498755e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8061248,
      "step": 28775
    },
    {
      "epoch": 319.77777777777777,
      "grad_norm": 2.1901448690186953e-06,
      "learning_rate": 9.096192800258639e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8062608,
      "step": 28780
    },
    {
      "epoch": 319.8333333333333,
      "grad_norm": 6.132555085969216e-07,
      "learning_rate": 9.088619219585443e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8064032,
      "step": 28785
    },
    {
      "epoch": 319.8888888888889,
      "grad_norm": 5.47680315321486e-07,
      "learning_rate": 9.081048092647127e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8065440,
      "step": 28790
    },
    {
      "epoch": 319.94444444444446,
      "grad_norm": 5.50231447959959e-07,
      "learning_rate": 9.073479420611245e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8066864,
      "step": 28795
    },
    {
      "epoch": 320.0,
      "grad_norm": 2.171562755393097e-06,
      "learning_rate": 9.065913204644974e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8068256,
      "step": 28800
    },
    {
      "epoch": 320.0,
      "eval_loss": 0.355111300945282,
      "eval_runtime": 1.2849,
      "eval_samples_per_second": 31.13,
      "eval_steps_per_second": 15.565,
      "num_input_tokens_seen": 8068256,
      "step": 28800
    },
    {
      "epoch": 320.05555555555554,
      "grad_norm": 5.931413511461869e-07,
      "learning_rate": 9.058349445915135e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8069664,
      "step": 28805
    },
    {
      "epoch": 320.1111111111111,
      "grad_norm": 5.495919026543561e-07,
      "learning_rate": 9.050788145588138e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8071072,
      "step": 28810
    },
    {
      "epoch": 320.1666666666667,
      "grad_norm": 5.444524049380561e-07,
      "learning_rate": 9.043229304830039e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8072528,
      "step": 28815
    },
    {
      "epoch": 320.22222222222223,
      "grad_norm": 9.227297823599656e-07,
      "learning_rate": 9.035672924806515e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8073904,
      "step": 28820
    },
    {
      "epoch": 320.27777777777777,
      "grad_norm": 5.26453845850483e-07,
      "learning_rate": 9.028119006682839e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8075296,
      "step": 28825
    },
    {
      "epoch": 320.3333333333333,
      "grad_norm": 1.4959605323383585e-06,
      "learning_rate": 9.020567551623935e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8076640,
      "step": 28830
    },
    {
      "epoch": 320.3888888888889,
      "grad_norm": 4.885549742539297e-07,
      "learning_rate": 9.013018560794318e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8078000,
      "step": 28835
    },
    {
      "epoch": 320.44444444444446,
      "grad_norm": 5.579656772169983e-07,
      "learning_rate": 9.005472035358139e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8079408,
      "step": 28840
    },
    {
      "epoch": 320.5,
      "grad_norm": 5.137543439559522e-07,
      "learning_rate": 8.997927976479185e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8080784,
      "step": 28845
    },
    {
      "epoch": 320.55555555555554,
      "grad_norm": 5.368697770791186e-07,
      "learning_rate": 8.99038638532082e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8082192,
      "step": 28850
    },
    {
      "epoch": 320.6111111111111,
      "grad_norm": 5.433292358247854e-07,
      "learning_rate": 8.982847263046065e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8083632,
      "step": 28855
    },
    {
      "epoch": 320.6666666666667,
      "grad_norm": 6.131504619588668e-07,
      "learning_rate": 8.975310610817555e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8085024,
      "step": 28860
    },
    {
      "epoch": 320.72222222222223,
      "grad_norm": 4.750815776333184e-07,
      "learning_rate": 8.967776429797528e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8086448,
      "step": 28865
    },
    {
      "epoch": 320.77777777777777,
      "grad_norm": 5.255733412923291e-07,
      "learning_rate": 8.960244721147842e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8087840,
      "step": 28870
    },
    {
      "epoch": 320.8333333333333,
      "grad_norm": 6.419732585527527e-07,
      "learning_rate": 8.952715486029995e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8089248,
      "step": 28875
    },
    {
      "epoch": 320.8888888888889,
      "grad_norm": 2.829622417266364e-06,
      "learning_rate": 8.945188725605075e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8090624,
      "step": 28880
    },
    {
      "epoch": 320.94444444444446,
      "grad_norm": 9.969262464437634e-07,
      "learning_rate": 8.937664441033817e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8092000,
      "step": 28885
    },
    {
      "epoch": 321.0,
      "grad_norm": 8.227134458138607e-07,
      "learning_rate": 8.930142633476549e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8093408,
      "step": 28890
    },
    {
      "epoch": 321.05555555555554,
      "grad_norm": 5.76624358927802e-07,
      "learning_rate": 8.92262330409323e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8094768,
      "step": 28895
    },
    {
      "epoch": 321.1111111111111,
      "grad_norm": 6.004356123412435e-07,
      "learning_rate": 8.915106454043448e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8096176,
      "step": 28900
    },
    {
      "epoch": 321.1666666666667,
      "grad_norm": 1.6774235973571194e-06,
      "learning_rate": 8.90759208448638e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8097536,
      "step": 28905
    },
    {
      "epoch": 321.22222222222223,
      "grad_norm": 5.25655480032583e-07,
      "learning_rate": 8.900080196580848e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8098928,
      "step": 28910
    },
    {
      "epoch": 321.27777777777777,
      "grad_norm": 5.352446237338881e-07,
      "learning_rate": 8.892570791485267e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8100416,
      "step": 28915
    },
    {
      "epoch": 321.3333333333333,
      "grad_norm": 5.230352257967752e-07,
      "learning_rate": 8.885063870357688e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8101856,
      "step": 28920
    },
    {
      "epoch": 321.3888888888889,
      "grad_norm": 7.986388936842559e-07,
      "learning_rate": 8.87755943435578e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8103248,
      "step": 28925
    },
    {
      "epoch": 321.44444444444446,
      "grad_norm": 4.726628048956627e-07,
      "learning_rate": 8.87005748463681e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8104640,
      "step": 28930
    },
    {
      "epoch": 321.5,
      "grad_norm": 5.736130788136506e-07,
      "learning_rate": 8.862558022357681e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8106032,
      "step": 28935
    },
    {
      "epoch": 321.55555555555554,
      "grad_norm": 6.063413025003683e-07,
      "learning_rate": 8.855061048674903e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8107392,
      "step": 28940
    },
    {
      "epoch": 321.6111111111111,
      "grad_norm": 5.674412477674196e-07,
      "learning_rate": 8.847566564744595e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8108816,
      "step": 28945
    },
    {
      "epoch": 321.6666666666667,
      "grad_norm": 5.947631507297046e-07,
      "learning_rate": 8.840074571722512e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8110224,
      "step": 28950
    },
    {
      "epoch": 321.72222222222223,
      "grad_norm": 2.280052285641432e-06,
      "learning_rate": 8.832585070764002e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8111584,
      "step": 28955
    },
    {
      "epoch": 321.77777777777777,
      "grad_norm": 1.0155773679798585e-06,
      "learning_rate": 8.825098063024045e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8113008,
      "step": 28960
    },
    {
      "epoch": 321.8333333333333,
      "grad_norm": 4.0079700625028636e-07,
      "learning_rate": 8.817613549657244e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8114416,
      "step": 28965
    },
    {
      "epoch": 321.8888888888889,
      "grad_norm": 5.085830139250902e-07,
      "learning_rate": 8.810131531817783e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8115792,
      "step": 28970
    },
    {
      "epoch": 321.94444444444446,
      "grad_norm": 2.0258528365957318e-06,
      "learning_rate": 8.802652010659496e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8117184,
      "step": 28975
    },
    {
      "epoch": 322.0,
      "grad_norm": 6.182806941978924e-07,
      "learning_rate": 8.795174987335827e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8118592,
      "step": 28980
    },
    {
      "epoch": 322.05555555555554,
      "grad_norm": 5.965029572507774e-07,
      "learning_rate": 8.787700462999807e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8120000,
      "step": 28985
    },
    {
      "epoch": 322.1111111111111,
      "grad_norm": 9.821661706155282e-07,
      "learning_rate": 8.780228438804122e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8121392,
      "step": 28990
    },
    {
      "epoch": 322.1666666666667,
      "grad_norm": 9.120803383666498e-07,
      "learning_rate": 8.772758915901032e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8122784,
      "step": 28995
    },
    {
      "epoch": 322.22222222222223,
      "grad_norm": 6.361702276080905e-07,
      "learning_rate": 8.765291895442443e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8124112,
      "step": 29000
    },
    {
      "epoch": 322.22222222222223,
      "eval_loss": 0.3725336790084839,
      "eval_runtime": 1.2899,
      "eval_samples_per_second": 31.011,
      "eval_steps_per_second": 15.506,
      "num_input_tokens_seen": 8124112,
      "step": 29000
    },
    {
      "epoch": 322.27777777777777,
      "grad_norm": 4.7436921590815473e-07,
      "learning_rate": 8.75782737857987e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8125536,
      "step": 29005
    },
    {
      "epoch": 322.3333333333333,
      "grad_norm": 5.081006975160562e-07,
      "learning_rate": 8.750365366464425e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8126992,
      "step": 29010
    },
    {
      "epoch": 322.3888888888889,
      "grad_norm": 4.952573249283887e-07,
      "learning_rate": 8.742905860246838e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8128368,
      "step": 29015
    },
    {
      "epoch": 322.44444444444446,
      "grad_norm": 5.154862492418033e-07,
      "learning_rate": 8.735448861077478e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8129792,
      "step": 29020
    },
    {
      "epoch": 322.5,
      "grad_norm": 8.993237656795827e-07,
      "learning_rate": 8.727994370106288e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8131136,
      "step": 29025
    },
    {
      "epoch": 322.55555555555554,
      "grad_norm": 4.92116328132397e-07,
      "learning_rate": 8.720542388482861e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8132528,
      "step": 29030
    },
    {
      "epoch": 322.6111111111111,
      "grad_norm": 4.845047101298405e-07,
      "learning_rate": 8.71309291735637e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8133872,
      "step": 29035
    },
    {
      "epoch": 322.6666666666667,
      "grad_norm": 1.5210702031254186e-06,
      "learning_rate": 8.705645957875621e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8135264,
      "step": 29040
    },
    {
      "epoch": 322.72222222222223,
      "grad_norm": 1.4773788734601112e-06,
      "learning_rate": 8.698201511189048e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8136640,
      "step": 29045
    },
    {
      "epoch": 322.77777777777777,
      "grad_norm": 5.43890507742617e-07,
      "learning_rate": 8.690759578444649e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8138096,
      "step": 29050
    },
    {
      "epoch": 322.8333333333333,
      "grad_norm": 5.290643230182468e-07,
      "learning_rate": 8.68332016079008e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8139552,
      "step": 29055
    },
    {
      "epoch": 322.8888888888889,
      "grad_norm": 4.772431339006289e-07,
      "learning_rate": 8.6758832593726e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8140976,
      "step": 29060
    },
    {
      "epoch": 322.94444444444446,
      "grad_norm": 1.6451164128739038e-06,
      "learning_rate": 8.668448875339053e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8142384,
      "step": 29065
    },
    {
      "epoch": 323.0,
      "grad_norm": 5.65811603792099e-07,
      "learning_rate": 8.661017009835933e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8143760,
      "step": 29070
    },
    {
      "epoch": 323.05555555555554,
      "grad_norm": 4.844035629503196e-06,
      "learning_rate": 8.653587664009311e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8145152,
      "step": 29075
    },
    {
      "epoch": 323.1111111111111,
      "grad_norm": 1.7152706277556717e-06,
      "learning_rate": 8.646160839004902e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8146544,
      "step": 29080
    },
    {
      "epoch": 323.1666666666667,
      "grad_norm": 5.494835590980074e-07,
      "learning_rate": 8.638736535967998e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8147920,
      "step": 29085
    },
    {
      "epoch": 323.22222222222223,
      "grad_norm": 9.733765864439192e-07,
      "learning_rate": 8.631314756043535e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8149312,
      "step": 29090
    },
    {
      "epoch": 323.27777777777777,
      "grad_norm": 5.754540666202956e-07,
      "learning_rate": 8.62389550037603e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8150736,
      "step": 29095
    },
    {
      "epoch": 323.3333333333333,
      "grad_norm": 5.669611482517212e-07,
      "learning_rate": 8.616478770109646e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8152128,
      "step": 29100
    },
    {
      "epoch": 323.3888888888889,
      "grad_norm": 1.4905322132108267e-06,
      "learning_rate": 8.609064566388111e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8153504,
      "step": 29105
    },
    {
      "epoch": 323.44444444444446,
      "grad_norm": 5.326933205651585e-07,
      "learning_rate": 8.601652890354815e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8154928,
      "step": 29110
    },
    {
      "epoch": 323.5,
      "grad_norm": 5.871411303814966e-07,
      "learning_rate": 8.594243743152705e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8156320,
      "step": 29115
    },
    {
      "epoch": 323.55555555555554,
      "grad_norm": 2.203663598265848e-06,
      "learning_rate": 8.58683712592438e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8157696,
      "step": 29120
    },
    {
      "epoch": 323.6111111111111,
      "grad_norm": 8.795830126473447e-07,
      "learning_rate": 8.579433039812037e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8159104,
      "step": 29125
    },
    {
      "epoch": 323.6666666666667,
      "grad_norm": 4.992169237993949e-07,
      "learning_rate": 8.572031485957466e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8160528,
      "step": 29130
    },
    {
      "epoch": 323.72222222222223,
      "grad_norm": 5.223242283136642e-07,
      "learning_rate": 8.564632465502084e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8161904,
      "step": 29135
    },
    {
      "epoch": 323.77777777777777,
      "grad_norm": 8.432683102910232e-07,
      "learning_rate": 8.557235979586928e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8163312,
      "step": 29140
    },
    {
      "epoch": 323.8333333333333,
      "grad_norm": 6.352357786454377e-07,
      "learning_rate": 8.549842029352606e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8164736,
      "step": 29145
    },
    {
      "epoch": 323.8888888888889,
      "grad_norm": 9.935696425600327e-07,
      "learning_rate": 8.542450615939376e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8166144,
      "step": 29150
    },
    {
      "epoch": 323.94444444444446,
      "grad_norm": 2.2894651010574307e-06,
      "learning_rate": 8.535061740487082e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8167552,
      "step": 29155
    },
    {
      "epoch": 324.0,
      "grad_norm": 5.55322742457065e-07,
      "learning_rate": 8.527675404135168e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8168976,
      "step": 29160
    },
    {
      "epoch": 324.05555555555554,
      "grad_norm": 1.0581943570286967e-06,
      "learning_rate": 8.520291608022724e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8170336,
      "step": 29165
    },
    {
      "epoch": 324.1111111111111,
      "grad_norm": 5.462063654704252e-07,
      "learning_rate": 8.512910353288398e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8171712,
      "step": 29170
    },
    {
      "epoch": 324.1666666666667,
      "grad_norm": 4.940708890899259e-07,
      "learning_rate": 8.505531641070486e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8173088,
      "step": 29175
    },
    {
      "epoch": 324.22222222222223,
      "grad_norm": 5.275389867165359e-07,
      "learning_rate": 8.498155472506885e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8174528,
      "step": 29180
    },
    {
      "epoch": 324.27777777777777,
      "grad_norm": 5.25373309301358e-07,
      "learning_rate": 8.49078184873508e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8175936,
      "step": 29185
    },
    {
      "epoch": 324.3333333333333,
      "grad_norm": 5.113489578434383e-07,
      "learning_rate": 8.483410770892188e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8177408,
      "step": 29190
    },
    {
      "epoch": 324.3888888888889,
      "grad_norm": 5.880559115212236e-07,
      "learning_rate": 8.476042240114909e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8178816,
      "step": 29195
    },
    {
      "epoch": 324.44444444444446,
      "grad_norm": 5.56008444618783e-07,
      "learning_rate": 8.468676257539568e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8180192,
      "step": 29200
    },
    {
      "epoch": 324.44444444444446,
      "eval_loss": 0.3379303514957428,
      "eval_runtime": 1.2928,
      "eval_samples_per_second": 30.941,
      "eval_steps_per_second": 15.47,
      "num_input_tokens_seen": 8180192,
      "step": 29200
    },
    {
      "epoch": 324.5,
      "grad_norm": 4.0514643728783994e-07,
      "learning_rate": 8.4613128243021e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8181632,
      "step": 29205
    },
    {
      "epoch": 324.55555555555554,
      "grad_norm": 1.00117722467985e-06,
      "learning_rate": 8.453951941538028e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8183008,
      "step": 29210
    },
    {
      "epoch": 324.6111111111111,
      "grad_norm": 8.835840503707004e-07,
      "learning_rate": 8.446593610382495e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8184416,
      "step": 29215
    },
    {
      "epoch": 324.6666666666667,
      "grad_norm": 5.343431439541746e-07,
      "learning_rate": 8.439237831970259e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8185824,
      "step": 29220
    },
    {
      "epoch": 324.72222222222223,
      "grad_norm": 5.340968414202507e-07,
      "learning_rate": 8.431884607435667e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8187216,
      "step": 29225
    },
    {
      "epoch": 324.77777777777777,
      "grad_norm": 1.0019103910963167e-06,
      "learning_rate": 8.424533937912665e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8188576,
      "step": 29230
    },
    {
      "epoch": 324.8333333333333,
      "grad_norm": 5.84692315896973e-07,
      "learning_rate": 8.41718582453484e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8189968,
      "step": 29235
    },
    {
      "epoch": 324.8888888888889,
      "grad_norm": 5.789575538983627e-07,
      "learning_rate": 8.409840268435346e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8191376,
      "step": 29240
    },
    {
      "epoch": 324.94444444444446,
      "grad_norm": 5.969497465230234e-07,
      "learning_rate": 8.402497270746976e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8192832,
      "step": 29245
    },
    {
      "epoch": 325.0,
      "grad_norm": 4.869892222814087e-07,
      "learning_rate": 8.395156832602095e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8194208,
      "step": 29250
    },
    {
      "epoch": 325.05555555555554,
      "grad_norm": 5.398690632318903e-07,
      "learning_rate": 8.387818955132707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8195664,
      "step": 29255
    },
    {
      "epoch": 325.1111111111111,
      "grad_norm": 2.4059415864030598e-06,
      "learning_rate": 8.38048363947039e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8197040,
      "step": 29260
    },
    {
      "epoch": 325.1666666666667,
      "grad_norm": 5.917530074839306e-07,
      "learning_rate": 8.373150886746351e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8198416,
      "step": 29265
    },
    {
      "epoch": 325.22222222222223,
      "grad_norm": 5.026248572903569e-07,
      "learning_rate": 8.365820698091397e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8199840,
      "step": 29270
    },
    {
      "epoch": 325.27777777777777,
      "grad_norm": 6.110776098466886e-07,
      "learning_rate": 8.358493074635922e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8201232,
      "step": 29275
    },
    {
      "epoch": 325.3333333333333,
      "grad_norm": 6.354301262945228e-07,
      "learning_rate": 8.351168017509948e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8202624,
      "step": 29280
    },
    {
      "epoch": 325.3888888888889,
      "grad_norm": 6.091681257203163e-07,
      "learning_rate": 8.343845527843094e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8204064,
      "step": 29285
    },
    {
      "epoch": 325.44444444444446,
      "grad_norm": 5.598144525720272e-07,
      "learning_rate": 8.336525606764566e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8205456,
      "step": 29290
    },
    {
      "epoch": 325.5,
      "grad_norm": 5.176283934815729e-07,
      "learning_rate": 8.329208255403204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8206896,
      "step": 29295
    },
    {
      "epoch": 325.55555555555554,
      "grad_norm": 1.6973109495665994e-06,
      "learning_rate": 8.321893474887426e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8208320,
      "step": 29300
    },
    {
      "epoch": 325.6111111111111,
      "grad_norm": 1.0680878403945826e-06,
      "learning_rate": 8.31458126634526e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8209712,
      "step": 29305
    },
    {
      "epoch": 325.6666666666667,
      "grad_norm": 6.661585416622984e-07,
      "learning_rate": 8.30727163090435e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8211136,
      "step": 29310
    },
    {
      "epoch": 325.72222222222223,
      "grad_norm": 6.382195465448603e-07,
      "learning_rate": 8.29996456969192e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8212528,
      "step": 29315
    },
    {
      "epoch": 325.77777777777777,
      "grad_norm": 6.489065071946243e-07,
      "learning_rate": 8.292660083834818e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8213936,
      "step": 29320
    },
    {
      "epoch": 325.8333333333333,
      "grad_norm": 2.1950866084807785e-06,
      "learning_rate": 8.2853581744595e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8215264,
      "step": 29325
    },
    {
      "epoch": 325.8888888888889,
      "grad_norm": 5.360509476304287e-07,
      "learning_rate": 8.278058842691991e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8216688,
      "step": 29330
    },
    {
      "epoch": 325.94444444444446,
      "grad_norm": 5.623923016173649e-07,
      "learning_rate": 8.27076208965796e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8218096,
      "step": 29335
    },
    {
      "epoch": 326.0,
      "grad_norm": 4.87821807837463e-07,
      "learning_rate": 8.263467916482637e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8219488,
      "step": 29340
    },
    {
      "epoch": 326.05555555555554,
      "grad_norm": 5.36403263140528e-07,
      "learning_rate": 8.256176324290885e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8220864,
      "step": 29345
    },
    {
      "epoch": 326.1111111111111,
      "grad_norm": 1.1137032061014907e-06,
      "learning_rate": 8.248887314207168e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8222240,
      "step": 29350
    },
    {
      "epoch": 326.1666666666667,
      "grad_norm": 4.5220835431791784e-07,
      "learning_rate": 8.24160088735553e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8223664,
      "step": 29355
    },
    {
      "epoch": 326.22222222222223,
      "grad_norm": 9.866918162515503e-07,
      "learning_rate": 8.234317044859629e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8225056,
      "step": 29360
    },
    {
      "epoch": 326.27777777777777,
      "grad_norm": 1.0547223610046785e-06,
      "learning_rate": 8.227035787842744e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8226464,
      "step": 29365
    },
    {
      "epoch": 326.3333333333333,
      "grad_norm": 6.070397375879111e-07,
      "learning_rate": 8.219757117427721e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8227888,
      "step": 29370
    },
    {
      "epoch": 326.3888888888889,
      "grad_norm": 5.201941348786931e-07,
      "learning_rate": 8.212481034737014e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8229232,
      "step": 29375
    },
    {
      "epoch": 326.44444444444446,
      "grad_norm": 5.184741667108028e-07,
      "learning_rate": 8.205207540892707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8230640,
      "step": 29380
    },
    {
      "epoch": 326.5,
      "grad_norm": 1.5011246432550251e-06,
      "learning_rate": 8.197936637016442e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8232096,
      "step": 29385
    },
    {
      "epoch": 326.55555555555554,
      "grad_norm": 9.473463364884083e-07,
      "learning_rate": 8.190668324229508e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8233504,
      "step": 29390
    },
    {
      "epoch": 326.6111111111111,
      "grad_norm": 5.841028496433864e-07,
      "learning_rate": 8.183402603652749e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8234896,
      "step": 29395
    },
    {
      "epoch": 326.6666666666667,
      "grad_norm": 9.13740734631574e-07,
      "learning_rate": 8.176139476406635e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8236304,
      "step": 29400
    },
    {
      "epoch": 326.6666666666667,
      "eval_loss": 0.3741936683654785,
      "eval_runtime": 1.2907,
      "eval_samples_per_second": 30.99,
      "eval_steps_per_second": 15.495,
      "num_input_tokens_seen": 8236304,
      "step": 29400
    },
    {
      "epoch": 326.72222222222223,
      "grad_norm": 4.89095953071228e-07,
      "learning_rate": 8.16887894361125e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8237680,
      "step": 29405
    },
    {
      "epoch": 326.77777777777777,
      "grad_norm": 5.885684686290915e-07,
      "learning_rate": 8.161621006386233e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8239088,
      "step": 29410
    },
    {
      "epoch": 326.8333333333333,
      "grad_norm": 1.0545356872171396e-06,
      "learning_rate": 8.154365665850869e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8240496,
      "step": 29415
    },
    {
      "epoch": 326.8888888888889,
      "grad_norm": 5.064334231974499e-07,
      "learning_rate": 8.147112923124005e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8241904,
      "step": 29420
    },
    {
      "epoch": 326.94444444444446,
      "grad_norm": 4.895330221188487e-07,
      "learning_rate": 8.13986277932412e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8243296,
      "step": 29425
    },
    {
      "epoch": 327.0,
      "grad_norm": 5.282697657094104e-07,
      "learning_rate": 8.132615235569277e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8244688,
      "step": 29430
    },
    {
      "epoch": 327.05555555555554,
      "grad_norm": 6.309265359050187e-07,
      "learning_rate": 8.125370292977124e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8246064,
      "step": 29435
    },
    {
      "epoch": 327.1111111111111,
      "grad_norm": 2.089466306642862e-06,
      "learning_rate": 8.118127952664944e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8247488,
      "step": 29440
    },
    {
      "epoch": 327.1666666666667,
      "grad_norm": 1.6360794461434125e-06,
      "learning_rate": 8.110888215749574e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8248880,
      "step": 29445
    },
    {
      "epoch": 327.22222222222223,
      "grad_norm": 4.917661158287956e-07,
      "learning_rate": 8.10365108334749e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8250304,
      "step": 29450
    },
    {
      "epoch": 327.27777777777777,
      "grad_norm": 9.006254231280764e-07,
      "learning_rate": 8.096416556574743e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8251696,
      "step": 29455
    },
    {
      "epoch": 327.3333333333333,
      "grad_norm": 5.238047720013128e-07,
      "learning_rate": 8.08918463654698e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8253088,
      "step": 29460
    },
    {
      "epoch": 327.3888888888889,
      "grad_norm": 5.979866273264633e-07,
      "learning_rate": 8.081955324379458e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8254496,
      "step": 29465
    },
    {
      "epoch": 327.44444444444446,
      "grad_norm": 1.6939812894634088e-06,
      "learning_rate": 8.074728621187039e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8255856,
      "step": 29470
    },
    {
      "epoch": 327.5,
      "grad_norm": 5.353586516321229e-07,
      "learning_rate": 8.067504528084158e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8257264,
      "step": 29475
    },
    {
      "epoch": 327.55555555555554,
      "grad_norm": 5.983573601042735e-07,
      "learning_rate": 8.060283046184861e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8258656,
      "step": 29480
    },
    {
      "epoch": 327.6111111111111,
      "grad_norm": 9.916064982462558e-07,
      "learning_rate": 8.053064176602806e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8260080,
      "step": 29485
    },
    {
      "epoch": 327.6666666666667,
      "grad_norm": 2.021110958594363e-06,
      "learning_rate": 8.045847920451216e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8261488,
      "step": 29490
    },
    {
      "epoch": 327.72222222222223,
      "grad_norm": 4.853744144384109e-07,
      "learning_rate": 8.038634278842944e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8262832,
      "step": 29495
    },
    {
      "epoch": 327.77777777777777,
      "grad_norm": 5.559685973821615e-07,
      "learning_rate": 8.031423252890408e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8264240,
      "step": 29500
    },
    {
      "epoch": 327.8333333333333,
      "grad_norm": 3.6870881103823194e-07,
      "learning_rate": 8.024214843705646e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8265616,
      "step": 29505
    },
    {
      "epoch": 327.8888888888889,
      "grad_norm": 5.131111038281233e-07,
      "learning_rate": 8.017009052400295e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8267024,
      "step": 29510
    },
    {
      "epoch": 327.94444444444446,
      "grad_norm": 4.444903254352539e-07,
      "learning_rate": 8.00980588008557e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8268432,
      "step": 29515
    },
    {
      "epoch": 328.0,
      "grad_norm": 6.019563443260267e-07,
      "learning_rate": 8.002605327872282e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8269856,
      "step": 29520
    },
    {
      "epoch": 328.05555555555554,
      "grad_norm": 4.72605506729451e-07,
      "learning_rate": 7.995407396870862e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8271264,
      "step": 29525
    },
    {
      "epoch": 328.1111111111111,
      "grad_norm": 5.26276608070475e-07,
      "learning_rate": 7.988212088191307e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8272672,
      "step": 29530
    },
    {
      "epoch": 328.1666666666667,
      "grad_norm": 4.7385668722199625e-07,
      "learning_rate": 7.98101940294324e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8274112,
      "step": 29535
    },
    {
      "epoch": 328.22222222222223,
      "grad_norm": 5.164063736629032e-07,
      "learning_rate": 7.973829342235847e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8275536,
      "step": 29540
    },
    {
      "epoch": 328.27777777777777,
      "grad_norm": 6.042466793587664e-07,
      "learning_rate": 7.966641907177936e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8276944,
      "step": 29545
    },
    {
      "epoch": 328.3333333333333,
      "grad_norm": 5.354424956749426e-07,
      "learning_rate": 7.959457098877901e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8278336,
      "step": 29550
    },
    {
      "epoch": 328.3888888888889,
      "grad_norm": 8.826337420941854e-07,
      "learning_rate": 7.952274918443719e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8279712,
      "step": 29555
    },
    {
      "epoch": 328.44444444444446,
      "grad_norm": 5.787389909528429e-07,
      "learning_rate": 7.945095366982983e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8281104,
      "step": 29560
    },
    {
      "epoch": 328.5,
      "grad_norm": 1.7148020106105832e-06,
      "learning_rate": 7.937918445602871e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8282544,
      "step": 29565
    },
    {
      "epoch": 328.55555555555554,
      "grad_norm": 1.4909966239429195e-06,
      "learning_rate": 7.930744155410145e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8283920,
      "step": 29570
    },
    {
      "epoch": 328.6111111111111,
      "grad_norm": 9.174714818982466e-07,
      "learning_rate": 7.923572497511181e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8285296,
      "step": 29575
    },
    {
      "epoch": 328.6666666666667,
      "grad_norm": 5.732295562665968e-07,
      "learning_rate": 7.916403473011927e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8286704,
      "step": 29580
    },
    {
      "epoch": 328.72222222222223,
      "grad_norm": 5.075874014437431e-07,
      "learning_rate": 7.909237083017953e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8288112,
      "step": 29585
    },
    {
      "epoch": 328.77777777777777,
      "grad_norm": 1.018900547933299e-06,
      "learning_rate": 7.902073328634389e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8289472,
      "step": 29590
    },
    {
      "epoch": 328.8333333333333,
      "grad_norm": 1.4710698224007501e-06,
      "learning_rate": 7.894912210965987e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8290896,
      "step": 29595
    },
    {
      "epoch": 328.8888888888889,
      "grad_norm": 5.05717082432966e-07,
      "learning_rate": 7.887753731117075e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8292272,
      "step": 29600
    },
    {
      "epoch": 328.8888888888889,
      "eval_loss": 0.3082268238067627,
      "eval_runtime": 1.3006,
      "eval_samples_per_second": 30.755,
      "eval_steps_per_second": 15.378,
      "num_input_tokens_seen": 8292272,
      "step": 29600
    },
    {
      "epoch": 328.94444444444446,
      "grad_norm": 4.745281216855801e-07,
      "learning_rate": 7.880597890191587e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8293712,
      "step": 29605
    },
    {
      "epoch": 329.0,
      "grad_norm": 5.177917614673788e-07,
      "learning_rate": 7.873444689293036e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8295152,
      "step": 29610
    },
    {
      "epoch": 329.05555555555554,
      "grad_norm": 9.906680134008639e-07,
      "learning_rate": 7.866294129524548e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8296512,
      "step": 29615
    },
    {
      "epoch": 329.1111111111111,
      "grad_norm": 1.4989630017225863e-06,
      "learning_rate": 7.859146211988811e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8297888,
      "step": 29620
    },
    {
      "epoch": 329.1666666666667,
      "grad_norm": 7.431505082422518e-07,
      "learning_rate": 7.852000937788134e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8299264,
      "step": 29625
    },
    {
      "epoch": 329.22222222222223,
      "grad_norm": 5.845126906933729e-07,
      "learning_rate": 7.844858308024416e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8300720,
      "step": 29630
    },
    {
      "epoch": 329.27777777777777,
      "grad_norm": 5.688240207746276e-07,
      "learning_rate": 7.837718323799122e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8302096,
      "step": 29635
    },
    {
      "epoch": 329.3333333333333,
      "grad_norm": 9.547644594931626e-07,
      "learning_rate": 7.83058098621334e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8303488,
      "step": 29640
    },
    {
      "epoch": 329.3888888888889,
      "grad_norm": 8.322667213178647e-07,
      "learning_rate": 7.823446296367739e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8304912,
      "step": 29645
    },
    {
      "epoch": 329.44444444444446,
      "grad_norm": 7.099259278220416e-07,
      "learning_rate": 7.81631425536257e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8306320,
      "step": 29650
    },
    {
      "epoch": 329.5,
      "grad_norm": 1.4880052958687884e-06,
      "learning_rate": 7.809184864297689e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8307728,
      "step": 29655
    },
    {
      "epoch": 329.55555555555554,
      "grad_norm": 4.87527756831696e-07,
      "learning_rate": 7.802058124272532e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8309136,
      "step": 29660
    },
    {
      "epoch": 329.6111111111111,
      "grad_norm": 5.66387029721227e-07,
      "learning_rate": 7.79493403638614e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8310496,
      "step": 29665
    },
    {
      "epoch": 329.6666666666667,
      "grad_norm": 5.43546263997996e-07,
      "learning_rate": 7.787812601737132e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8311904,
      "step": 29670
    },
    {
      "epoch": 329.72222222222223,
      "grad_norm": 5.884713800696773e-07,
      "learning_rate": 7.780693821423715e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8313328,
      "step": 29675
    },
    {
      "epoch": 329.77777777777777,
      "grad_norm": 5.140898906574876e-07,
      "learning_rate": 7.773577696543705e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8314752,
      "step": 29680
    },
    {
      "epoch": 329.8333333333333,
      "grad_norm": 4.98706810958538e-07,
      "learning_rate": 7.7664642281945e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8316112,
      "step": 29685
    },
    {
      "epoch": 329.8888888888889,
      "grad_norm": 9.263150104743545e-07,
      "learning_rate": 7.759353417473072e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8317552,
      "step": 29690
    },
    {
      "epoch": 329.94444444444446,
      "grad_norm": 5.042965653956344e-07,
      "learning_rate": 7.752245265476016e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8319024,
      "step": 29695
    },
    {
      "epoch": 330.0,
      "grad_norm": 9.557071507515502e-07,
      "learning_rate": 7.745139773299481e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8320448,
      "step": 29700
    },
    {
      "epoch": 330.05555555555554,
      "grad_norm": 5.418231125986495e-07,
      "learning_rate": 7.738036942039232e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8321872,
      "step": 29705
    },
    {
      "epoch": 330.1111111111111,
      "grad_norm": 6.284441838033672e-07,
      "learning_rate": 7.73093677279062e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8323232,
      "step": 29710
    },
    {
      "epoch": 330.1666666666667,
      "grad_norm": 6.023724381520879e-07,
      "learning_rate": 7.72383926664857e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8324656,
      "step": 29715
    },
    {
      "epoch": 330.22222222222223,
      "grad_norm": 9.856630640570074e-07,
      "learning_rate": 7.716744424707606e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8326048,
      "step": 29720
    },
    {
      "epoch": 330.27777777777777,
      "grad_norm": 4.764884806718328e-07,
      "learning_rate": 7.709652248061858e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8327408,
      "step": 29725
    },
    {
      "epoch": 330.3333333333333,
      "grad_norm": 3.849012841783406e-07,
      "learning_rate": 7.702562737805017e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8328768,
      "step": 29730
    },
    {
      "epoch": 330.3888888888889,
      "grad_norm": 4.153282304741879e-07,
      "learning_rate": 7.695475895030365e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8330256,
      "step": 29735
    },
    {
      "epoch": 330.44444444444446,
      "grad_norm": 1.9711906134034507e-06,
      "learning_rate": 7.6883917208308e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8331728,
      "step": 29740
    },
    {
      "epoch": 330.5,
      "grad_norm": 5.231722752796486e-07,
      "learning_rate": 7.681310216298778e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8333104,
      "step": 29745
    },
    {
      "epoch": 330.55555555555554,
      "grad_norm": 1.6968973568509682e-06,
      "learning_rate": 7.674231382526367e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8334528,
      "step": 29750
    },
    {
      "epoch": 330.6111111111111,
      "grad_norm": 5.454242000269005e-07,
      "learning_rate": 7.667155220605198e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8335920,
      "step": 29755
    },
    {
      "epoch": 330.6666666666667,
      "grad_norm": 5.689988142876246e-07,
      "learning_rate": 7.660081731626515e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8337344,
      "step": 29760
    },
    {
      "epoch": 330.72222222222223,
      "grad_norm": 1.6457304354844382e-06,
      "learning_rate": 7.653010916681141e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8338720,
      "step": 29765
    },
    {
      "epoch": 330.77777777777777,
      "grad_norm": 4.5464662434824277e-07,
      "learning_rate": 7.645942776859472e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8340112,
      "step": 29770
    },
    {
      "epoch": 330.8333333333333,
      "grad_norm": 5.732504178013187e-07,
      "learning_rate": 7.63887731325152e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8341488,
      "step": 29775
    },
    {
      "epoch": 330.8888888888889,
      "grad_norm": 8.222361884691054e-07,
      "learning_rate": 7.63181452694685e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8342864,
      "step": 29780
    },
    {
      "epoch": 330.94444444444446,
      "grad_norm": 6.213282972566958e-07,
      "learning_rate": 7.624754419034644e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8344256,
      "step": 29785
    },
    {
      "epoch": 331.0,
      "grad_norm": 5.128628686179582e-07,
      "learning_rate": 7.6176969906036645e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8345648,
      "step": 29790
    },
    {
      "epoch": 331.05555555555554,
      "grad_norm": 5.230177748671849e-07,
      "learning_rate": 7.610642242742242e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8347040,
      "step": 29795
    },
    {
      "epoch": 331.1111111111111,
      "grad_norm": 5.880377216271881e-07,
      "learning_rate": 7.603590176538322e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8348416,
      "step": 29800
    },
    {
      "epoch": 331.1111111111111,
      "eval_loss": 0.38023608922958374,
      "eval_runtime": 1.2924,
      "eval_samples_per_second": 30.95,
      "eval_steps_per_second": 15.475,
      "num_input_tokens_seen": 8348416,
      "step": 29800
    },
    {
      "epoch": 331.1666666666667,
      "grad_norm": 2.2886263195687206e-06,
      "learning_rate": 7.596540793079404e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8349872,
      "step": 29805
    },
    {
      "epoch": 331.22222222222223,
      "grad_norm": 6.321165528788697e-07,
      "learning_rate": 7.5894940934526125e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8351296,
      "step": 29810
    },
    {
      "epoch": 331.27777777777777,
      "grad_norm": 6.185093184285506e-07,
      "learning_rate": 7.582450078744621e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8352688,
      "step": 29815
    },
    {
      "epoch": 331.3333333333333,
      "grad_norm": 9.525171549285005e-07,
      "learning_rate": 7.575408750041707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8354064,
      "step": 29820
    },
    {
      "epoch": 331.3888888888889,
      "grad_norm": 4.551523886675568e-07,
      "learning_rate": 7.568370108429732e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8355504,
      "step": 29825
    },
    {
      "epoch": 331.44444444444446,
      "grad_norm": 1.6365697774745058e-06,
      "learning_rate": 7.561334154994154e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8356912,
      "step": 29830
    },
    {
      "epoch": 331.5,
      "grad_norm": 5.344792839423462e-07,
      "learning_rate": 7.55430089081999e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8358288,
      "step": 29835
    },
    {
      "epoch": 331.55555555555554,
      "grad_norm": 1.5033543832032592e-06,
      "learning_rate": 7.547270316991864e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8359680,
      "step": 29840
    },
    {
      "epoch": 331.6111111111111,
      "grad_norm": 4.854702524426102e-07,
      "learning_rate": 7.5402424345939884e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8361040,
      "step": 29845
    },
    {
      "epoch": 331.6666666666667,
      "grad_norm": 5.145791988070414e-07,
      "learning_rate": 7.533217244710133e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8362448,
      "step": 29850
    },
    {
      "epoch": 331.72222222222223,
      "grad_norm": 1.021647335619491e-06,
      "learning_rate": 7.52619474842369e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8363872,
      "step": 29855
    },
    {
      "epoch": 331.77777777777777,
      "grad_norm": 5.437610184344521e-07,
      "learning_rate": 7.519174946817597e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8365264,
      "step": 29860
    },
    {
      "epoch": 331.8333333333333,
      "grad_norm": 5.710678010473202e-07,
      "learning_rate": 7.512157840974407e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8366704,
      "step": 29865
    },
    {
      "epoch": 331.8888888888889,
      "grad_norm": 6.22459026544675e-07,
      "learning_rate": 7.5051434319762496e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8368112,
      "step": 29870
    },
    {
      "epoch": 331.94444444444446,
      "grad_norm": 4.4002109689245117e-07,
      "learning_rate": 7.498131720904822e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8369536,
      "step": 29875
    },
    {
      "epoch": 332.0,
      "grad_norm": 9.258926070287998e-07,
      "learning_rate": 7.491122708841433e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8370896,
      "step": 29880
    },
    {
      "epoch": 332.05555555555554,
      "grad_norm": 9.139544090430718e-07,
      "learning_rate": 7.4841163968669524e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8372320,
      "step": 29885
    },
    {
      "epoch": 332.1111111111111,
      "grad_norm": 1.6813996808195952e-06,
      "learning_rate": 7.4771127860618355e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8373680,
      "step": 29890
    },
    {
      "epoch": 332.1666666666667,
      "grad_norm": 5.050180220678158e-07,
      "learning_rate": 7.470111877506139e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8375072,
      "step": 29895
    },
    {
      "epoch": 332.22222222222223,
      "grad_norm": 5.532502314054e-07,
      "learning_rate": 7.463113672279479e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8376464,
      "step": 29900
    },
    {
      "epoch": 332.27777777777777,
      "grad_norm": 5.254407255961269e-07,
      "learning_rate": 7.456118171461071e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8377856,
      "step": 29905
    },
    {
      "epoch": 332.3333333333333,
      "grad_norm": 3.186363755958155e-06,
      "learning_rate": 7.449125376129721e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8379296,
      "step": 29910
    },
    {
      "epoch": 332.3888888888889,
      "grad_norm": 9.531697173770226e-07,
      "learning_rate": 7.442135287363788e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8380672,
      "step": 29915
    },
    {
      "epoch": 332.44444444444446,
      "grad_norm": 1.497049083809543e-06,
      "learning_rate": 7.435147906241247e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8382048,
      "step": 29920
    },
    {
      "epoch": 332.5,
      "grad_norm": 8.876816082192818e-07,
      "learning_rate": 7.428163233839624e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8383440,
      "step": 29925
    },
    {
      "epoch": 332.55555555555554,
      "grad_norm": 5.378673790801258e-07,
      "learning_rate": 7.4211812712360525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8384848,
      "step": 29930
    },
    {
      "epoch": 332.6111111111111,
      "grad_norm": 5.036055767959624e-07,
      "learning_rate": 7.4142020195072464e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8386256,
      "step": 29935
    },
    {
      "epoch": 332.6666666666667,
      "grad_norm": 4.7468557795582456e-07,
      "learning_rate": 7.407225479729479e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8387696,
      "step": 29940
    },
    {
      "epoch": 332.72222222222223,
      "grad_norm": 9.604034403309925e-07,
      "learning_rate": 7.400251652978632e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8389088,
      "step": 29945
    },
    {
      "epoch": 332.77777777777777,
      "grad_norm": 5.776179818894889e-07,
      "learning_rate": 7.393280540330147e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8390480,
      "step": 29950
    },
    {
      "epoch": 332.8333333333333,
      "grad_norm": 5.964979550299176e-07,
      "learning_rate": 7.386312142859069e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8391888,
      "step": 29955
    },
    {
      "epoch": 332.8888888888889,
      "grad_norm": 1.5643387314412394e-06,
      "learning_rate": 7.379346461640008e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8393264,
      "step": 29960
    },
    {
      "epoch": 332.94444444444446,
      "grad_norm": 5.908928528697288e-07,
      "learning_rate": 7.372383497747149e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8394640,
      "step": 29965
    },
    {
      "epoch": 333.0,
      "grad_norm": 5.581421760325611e-07,
      "learning_rate": 7.3654232522542775e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8396048,
      "step": 29970
    },
    {
      "epoch": 333.05555555555554,
      "grad_norm": 1.665199306444265e-06,
      "learning_rate": 7.358465726234756e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8397424,
      "step": 29975
    },
    {
      "epoch": 333.1111111111111,
      "grad_norm": 8.529052024641715e-07,
      "learning_rate": 7.351510920761512e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8398816,
      "step": 29980
    },
    {
      "epoch": 333.1666666666667,
      "grad_norm": 1.4730885595781729e-06,
      "learning_rate": 7.344558836907067e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8400240,
      "step": 29985
    },
    {
      "epoch": 333.22222222222223,
      "grad_norm": 5.488353167493187e-07,
      "learning_rate": 7.3376094757435285e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8401648,
      "step": 29990
    },
    {
      "epoch": 333.27777777777777,
      "grad_norm": 4.435351570464263e-07,
      "learning_rate": 7.330662838342561e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8403040,
      "step": 29995
    },
    {
      "epoch": 333.3333333333333,
      "grad_norm": 1.4835355841569253e-06,
      "learning_rate": 7.323718925775438e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8404432,
      "step": 30000
    },
    {
      "epoch": 333.3333333333333,
      "eval_loss": 0.3238731026649475,
      "eval_runtime": 1.302,
      "eval_samples_per_second": 30.721,
      "eval_steps_per_second": 15.361,
      "num_input_tokens_seen": 8404432,
      "step": 30000
    },
    {
      "epoch": 333.3888888888889,
      "grad_norm": 5.448582101053034e-07,
      "learning_rate": 7.316777739112985e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8405792,
      "step": 30005
    },
    {
      "epoch": 333.44444444444446,
      "grad_norm": 1.4550164451065939e-06,
      "learning_rate": 7.309839279425626e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8407200,
      "step": 30010
    },
    {
      "epoch": 333.5,
      "grad_norm": 5.50086895145796e-07,
      "learning_rate": 7.302903547783366e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8408544,
      "step": 30015
    },
    {
      "epoch": 333.55555555555554,
      "grad_norm": 5.834928629155911e-07,
      "learning_rate": 7.2959705452557644e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8409984,
      "step": 30020
    },
    {
      "epoch": 333.6111111111111,
      "grad_norm": 1.707298906694632e-06,
      "learning_rate": 7.289040272911996e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8411376,
      "step": 30025
    },
    {
      "epoch": 333.6666666666667,
      "grad_norm": 6.504105272142624e-07,
      "learning_rate": 7.282112731820789e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8412800,
      "step": 30030
    },
    {
      "epoch": 333.72222222222223,
      "grad_norm": 4.935479864798253e-07,
      "learning_rate": 7.275187923050447e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8414176,
      "step": 30035
    },
    {
      "epoch": 333.77777777777777,
      "grad_norm": 2.194791932197404e-06,
      "learning_rate": 7.268265847668879e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8415600,
      "step": 30040
    },
    {
      "epoch": 333.8333333333333,
      "grad_norm": 2.0031109215778997e-06,
      "learning_rate": 7.261346506743538e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8416976,
      "step": 30045
    },
    {
      "epoch": 333.8888888888889,
      "grad_norm": 5.50971037682757e-07,
      "learning_rate": 7.254429901341486e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8418368,
      "step": 30050
    },
    {
      "epoch": 333.94444444444446,
      "grad_norm": 5.077799869468436e-07,
      "learning_rate": 7.247516032529356e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8419776,
      "step": 30055
    },
    {
      "epoch": 334.0,
      "grad_norm": 3.2199091037909966e-06,
      "learning_rate": 7.240604901373338e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8421216,
      "step": 30060
    },
    {
      "epoch": 334.05555555555554,
      "grad_norm": 1.6651557643854176e-06,
      "learning_rate": 7.233696508939223e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8422656,
      "step": 30065
    },
    {
      "epoch": 334.1111111111111,
      "grad_norm": 2.0790755570487818e-06,
      "learning_rate": 7.226790856292376e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8424048,
      "step": 30070
    },
    {
      "epoch": 334.1666666666667,
      "grad_norm": 9.73429791883973e-07,
      "learning_rate": 7.219887944497727e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8425440,
      "step": 30075
    },
    {
      "epoch": 334.22222222222223,
      "grad_norm": 4.0857148064787907e-07,
      "learning_rate": 7.2129877746198e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8426832,
      "step": 30080
    },
    {
      "epoch": 334.27777777777777,
      "grad_norm": 5.724705260945484e-07,
      "learning_rate": 7.20609034772268e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8428272,
      "step": 30085
    },
    {
      "epoch": 334.3333333333333,
      "grad_norm": 5.109539529257745e-07,
      "learning_rate": 7.19919566487004e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8429648,
      "step": 30090
    },
    {
      "epoch": 334.3888888888889,
      "grad_norm": 5.671383291883103e-07,
      "learning_rate": 7.192303727125132e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8431056,
      "step": 30095
    },
    {
      "epoch": 334.44444444444446,
      "grad_norm": 5.744490181314177e-07,
      "learning_rate": 7.185414535550777e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8432432,
      "step": 30100
    },
    {
      "epoch": 334.5,
      "grad_norm": 1.4728334463143256e-06,
      "learning_rate": 7.178528091209363e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8433792,
      "step": 30105
    },
    {
      "epoch": 334.55555555555554,
      "grad_norm": 1.6487679204146843e-06,
      "learning_rate": 7.171644395162888e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8435152,
      "step": 30110
    },
    {
      "epoch": 334.6111111111111,
      "grad_norm": 5.798721645078331e-07,
      "learning_rate": 7.164763448472881e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8436528,
      "step": 30115
    },
    {
      "epoch": 334.6666666666667,
      "grad_norm": 5.895803951716516e-07,
      "learning_rate": 7.157885252200491e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8437968,
      "step": 30120
    },
    {
      "epoch": 334.72222222222223,
      "grad_norm": 5.247954959486378e-07,
      "learning_rate": 7.151009807406403e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8439328,
      "step": 30125
    },
    {
      "epoch": 334.77777777777777,
      "grad_norm": 5.365810693547246e-07,
      "learning_rate": 7.144137115150909e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8440736,
      "step": 30130
    },
    {
      "epoch": 334.8333333333333,
      "grad_norm": 4.569571956380969e-07,
      "learning_rate": 7.1372671764938725e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8442160,
      "step": 30135
    },
    {
      "epoch": 334.8888888888889,
      "grad_norm": 2.1795010525238467e-06,
      "learning_rate": 7.130399992494705e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8443584,
      "step": 30140
    },
    {
      "epoch": 334.94444444444446,
      "grad_norm": 8.931178285820351e-07,
      "learning_rate": 7.123535564212419e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8445024,
      "step": 30145
    },
    {
      "epoch": 335.0,
      "grad_norm": 4.861155389335181e-07,
      "learning_rate": 7.116673892705611e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8446416,
      "step": 30150
    },
    {
      "epoch": 335.05555555555554,
      "grad_norm": 5.311429731591488e-07,
      "learning_rate": 7.109814979032415e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8447840,
      "step": 30155
    },
    {
      "epoch": 335.1111111111111,
      "grad_norm": 5.667584446200635e-07,
      "learning_rate": 7.102958824250577e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8449184,
      "step": 30160
    },
    {
      "epoch": 335.1666666666667,
      "grad_norm": 5.860565579496324e-07,
      "learning_rate": 7.096105429417393e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8450608,
      "step": 30165
    },
    {
      "epoch": 335.22222222222223,
      "grad_norm": 4.480913844417955e-07,
      "learning_rate": 7.0892547955897506e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8452080,
      "step": 30170
    },
    {
      "epoch": 335.27777777777777,
      "grad_norm": 5.444024964162963e-07,
      "learning_rate": 7.0824069238241e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8453504,
      "step": 30175
    },
    {
      "epoch": 335.3333333333333,
      "grad_norm": 5.954925654805265e-07,
      "learning_rate": 7.075561815176462e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8454848,
      "step": 30180
    },
    {
      "epoch": 335.3888888888889,
      "grad_norm": 9.583958444636664e-07,
      "learning_rate": 7.068719470702445e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8456272,
      "step": 30185
    },
    {
      "epoch": 335.44444444444446,
      "grad_norm": 9.522868253952765e-07,
      "learning_rate": 7.061879891457229e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8457632,
      "step": 30190
    },
    {
      "epoch": 335.5,
      "grad_norm": 1.658486326050479e-06,
      "learning_rate": 7.0550430784955515e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8459008,
      "step": 30195
    },
    {
      "epoch": 335.55555555555554,
      "grad_norm": 6.408347985598084e-07,
      "learning_rate": 7.048209032871752e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8460384,
      "step": 30200
    },
    {
      "epoch": 335.55555555555554,
      "eval_loss": 0.34168726205825806,
      "eval_runtime": 1.2992,
      "eval_samples_per_second": 30.787,
      "eval_steps_per_second": 15.394,
      "num_input_tokens_seen": 8460384,
      "step": 30200
    },
    {
      "epoch": 335.6111111111111,
      "grad_norm": 8.60929674217914e-07,
      "learning_rate": 7.0413777556397055e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8461840,
      "step": 30205
    },
    {
      "epoch": 335.6666666666667,
      "grad_norm": 5.83364283102128e-07,
      "learning_rate": 7.0345492478528925e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8463200,
      "step": 30210
    },
    {
      "epoch": 335.72222222222223,
      "grad_norm": 4.7534715008623607e-07,
      "learning_rate": 7.02772351056436e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8464576,
      "step": 30215
    },
    {
      "epoch": 335.77777777777777,
      "grad_norm": 5.133047693561821e-07,
      "learning_rate": 7.020900544826709e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8465952,
      "step": 30220
    },
    {
      "epoch": 335.8333333333333,
      "grad_norm": 1.5222803995129652e-06,
      "learning_rate": 7.014080351692134e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8467360,
      "step": 30225
    },
    {
      "epoch": 335.8888888888889,
      "grad_norm": 4.4954444433642493e-07,
      "learning_rate": 7.0072629322124024e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8468768,
      "step": 30230
    },
    {
      "epoch": 335.94444444444446,
      "grad_norm": 4.944942020301824e-07,
      "learning_rate": 7.000448287438827e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8470224,
      "step": 30235
    },
    {
      "epoch": 336.0,
      "grad_norm": 5.148368131813186e-07,
      "learning_rate": 6.993636418422331e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8471600,
      "step": 30240
    },
    {
      "epoch": 336.05555555555554,
      "grad_norm": 5.77278171931539e-07,
      "learning_rate": 6.986827326213383e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8473056,
      "step": 30245
    },
    {
      "epoch": 336.1111111111111,
      "grad_norm": 6.312508276096196e-07,
      "learning_rate": 6.9800210118620205e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8474448,
      "step": 30250
    },
    {
      "epoch": 336.1666666666667,
      "grad_norm": 9.98692257780931e-07,
      "learning_rate": 6.973217476417876e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8475856,
      "step": 30255
    },
    {
      "epoch": 336.22222222222223,
      "grad_norm": 1.6551815633647493e-06,
      "learning_rate": 6.96641672093013e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8477232,
      "step": 30260
    },
    {
      "epoch": 336.27777777777777,
      "grad_norm": 5.763099579780828e-07,
      "learning_rate": 6.95961874644755e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8478608,
      "step": 30265
    },
    {
      "epoch": 336.3333333333333,
      "grad_norm": 4.988539785699686e-07,
      "learning_rate": 6.952823554018476e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8480064,
      "step": 30270
    },
    {
      "epoch": 336.3888888888889,
      "grad_norm": 5.093571076031367e-07,
      "learning_rate": 6.946031144690798e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8481472,
      "step": 30275
    },
    {
      "epoch": 336.44444444444446,
      "grad_norm": 8.641145541332662e-07,
      "learning_rate": 6.939241519512005e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8482848,
      "step": 30280
    },
    {
      "epoch": 336.5,
      "grad_norm": 9.960017450794112e-07,
      "learning_rate": 6.932454679529129e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8484272,
      "step": 30285
    },
    {
      "epoch": 336.55555555555554,
      "grad_norm": 9.972337693398003e-07,
      "learning_rate": 6.925670625788791e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8485680,
      "step": 30290
    },
    {
      "epoch": 336.6111111111111,
      "grad_norm": 5.945864245404664e-07,
      "learning_rate": 6.918889359337186e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8487088,
      "step": 30295
    },
    {
      "epoch": 336.6666666666667,
      "grad_norm": 9.866735126706772e-07,
      "learning_rate": 6.912110881220058e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8488448,
      "step": 30300
    },
    {
      "epoch": 336.72222222222223,
      "grad_norm": 5.471226245390426e-07,
      "learning_rate": 6.905335192482735e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8489856,
      "step": 30305
    },
    {
      "epoch": 336.77777777777777,
      "grad_norm": 4.5558599026662705e-07,
      "learning_rate": 6.8985622941701275e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8491248,
      "step": 30310
    },
    {
      "epoch": 336.8333333333333,
      "grad_norm": 1.6828829529913492e-06,
      "learning_rate": 6.89179218732669e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8492592,
      "step": 30315
    },
    {
      "epoch": 336.8888888888889,
      "grad_norm": 6.121140359027777e-07,
      "learning_rate": 6.8850248729964595e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8493968,
      "step": 30320
    },
    {
      "epoch": 336.94444444444446,
      "grad_norm": 9.241713314622757e-07,
      "learning_rate": 6.8782603522230314e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8495376,
      "step": 30325
    },
    {
      "epoch": 337.0,
      "grad_norm": 5.534440106202965e-07,
      "learning_rate": 6.871498626049591e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8496752,
      "step": 30330
    },
    {
      "epoch": 337.05555555555554,
      "grad_norm": 4.2610133732523536e-07,
      "learning_rate": 6.8647396955188875e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8498160,
      "step": 30335
    },
    {
      "epoch": 337.1111111111111,
      "grad_norm": 3.460935658949893e-06,
      "learning_rate": 6.857983561673218e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8499568,
      "step": 30340
    },
    {
      "epoch": 337.1666666666667,
      "grad_norm": 5.309796620167617e-07,
      "learning_rate": 6.851230225554467e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8500992,
      "step": 30345
    },
    {
      "epoch": 337.22222222222223,
      "grad_norm": 4.143012688473391e-07,
      "learning_rate": 6.8444796882040946e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8502416,
      "step": 30350
    },
    {
      "epoch": 337.27777777777777,
      "grad_norm": 1.6746719211369054e-06,
      "learning_rate": 6.837731950663106e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8503840,
      "step": 30355
    },
    {
      "epoch": 337.3333333333333,
      "grad_norm": 1.4806456647420418e-06,
      "learning_rate": 6.830987013972098e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8505232,
      "step": 30360
    },
    {
      "epoch": 337.3888888888889,
      "grad_norm": 6.927512004040182e-07,
      "learning_rate": 6.82424487917121e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8506640,
      "step": 30365
    },
    {
      "epoch": 337.44444444444446,
      "grad_norm": 9.730151759868022e-07,
      "learning_rate": 6.8175055473001735e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8508048,
      "step": 30370
    },
    {
      "epoch": 337.5,
      "grad_norm": 5.276683054944442e-07,
      "learning_rate": 6.8107690193982855e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8509392,
      "step": 30375
    },
    {
      "epoch": 337.55555555555554,
      "grad_norm": 5.840229277964681e-07,
      "learning_rate": 6.804035296504385e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8510784,
      "step": 30380
    },
    {
      "epoch": 337.6111111111111,
      "grad_norm": 6.093598585721338e-07,
      "learning_rate": 6.797304379656916e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8512208,
      "step": 30385
    },
    {
      "epoch": 337.6666666666667,
      "grad_norm": 1.6278094108201913e-06,
      "learning_rate": 6.790576269893861e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8513600,
      "step": 30390
    },
    {
      "epoch": 337.72222222222223,
      "grad_norm": 1.4937496644051862e-06,
      "learning_rate": 6.783850968252772e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8514992,
      "step": 30395
    },
    {
      "epoch": 337.77777777777777,
      "grad_norm": 5.724720608668576e-07,
      "learning_rate": 6.777128475770789e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8516432,
      "step": 30400
    },
    {
      "epoch": 337.77777777777777,
      "eval_loss": 0.3461856544017792,
      "eval_runtime": 1.293,
      "eval_samples_per_second": 30.935,
      "eval_steps_per_second": 15.467,
      "num_input_tokens_seen": 8516432,
      "step": 30400
    },
    {
      "epoch": 337.8333333333333,
      "grad_norm": 2.0471766219998244e-06,
      "learning_rate": 6.77040879348459e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8517840,
      "step": 30405
    },
    {
      "epoch": 337.8888888888889,
      "grad_norm": 6.400908318937581e-07,
      "learning_rate": 6.763691922430443e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8519248,
      "step": 30410
    },
    {
      "epoch": 337.94444444444446,
      "grad_norm": 5.615009399662085e-07,
      "learning_rate": 6.756977863644178e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8520640,
      "step": 30415
    },
    {
      "epoch": 338.0,
      "grad_norm": 3.5090222354483558e-06,
      "learning_rate": 6.7502666181611804e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8522032,
      "step": 30420
    },
    {
      "epoch": 338.05555555555554,
      "grad_norm": 5.421599098553997e-07,
      "learning_rate": 6.743558187016405e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8523456,
      "step": 30425
    },
    {
      "epoch": 338.1111111111111,
      "grad_norm": 5.749456590820046e-07,
      "learning_rate": 6.7368525712443925e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8524864,
      "step": 30430
    },
    {
      "epoch": 338.1666666666667,
      "grad_norm": 3.1534900699625723e-06,
      "learning_rate": 6.7301497718792155e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8526288,
      "step": 30435
    },
    {
      "epoch": 338.22222222222223,
      "grad_norm": 2.0167390175629407e-06,
      "learning_rate": 6.723449789954544e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8527664,
      "step": 30440
    },
    {
      "epoch": 338.27777777777777,
      "grad_norm": 4.948599325871328e-07,
      "learning_rate": 6.716752626503586e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8529088,
      "step": 30445
    },
    {
      "epoch": 338.3333333333333,
      "grad_norm": 5.320649734130711e-07,
      "learning_rate": 6.710058282559131e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8530480,
      "step": 30450
    },
    {
      "epoch": 338.3888888888889,
      "grad_norm": 5.791219450657081e-07,
      "learning_rate": 6.703366759153545e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8531840,
      "step": 30455
    },
    {
      "epoch": 338.44444444444446,
      "grad_norm": 4.2451262061149464e-07,
      "learning_rate": 6.6966780573187335e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8533216,
      "step": 30460
    },
    {
      "epoch": 338.5,
      "grad_norm": 5.997000585011847e-07,
      "learning_rate": 6.689992178086174e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8534640,
      "step": 30465
    },
    {
      "epoch": 338.55555555555554,
      "grad_norm": 1.688214410933142e-06,
      "learning_rate": 6.683309122486925e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8535968,
      "step": 30470
    },
    {
      "epoch": 338.6111111111111,
      "grad_norm": 5.716073019357282e-07,
      "learning_rate": 6.676628891551584e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8537360,
      "step": 30475
    },
    {
      "epoch": 338.6666666666667,
      "grad_norm": 5.356319547900057e-07,
      "learning_rate": 6.6699514863103385e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8538752,
      "step": 30480
    },
    {
      "epoch": 338.72222222222223,
      "grad_norm": 9.993565299737384e-07,
      "learning_rate": 6.663276907792921e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8540176,
      "step": 30485
    },
    {
      "epoch": 338.77777777777777,
      "grad_norm": 1.051830054166203e-06,
      "learning_rate": 6.656605157028634e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8541648,
      "step": 30490
    },
    {
      "epoch": 338.8333333333333,
      "grad_norm": 4.84751183194021e-07,
      "learning_rate": 6.649936235046358e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8543040,
      "step": 30495
    },
    {
      "epoch": 338.8888888888889,
      "grad_norm": 1.9975855138909537e-06,
      "learning_rate": 6.643270142874508e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8544496,
      "step": 30500
    },
    {
      "epoch": 338.94444444444446,
      "grad_norm": 5.692230047316116e-07,
      "learning_rate": 6.636606881541094e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8545888,
      "step": 30505
    },
    {
      "epoch": 339.0,
      "grad_norm": 5.395182824941003e-07,
      "learning_rate": 6.629946452073662e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8547280,
      "step": 30510
    },
    {
      "epoch": 339.05555555555554,
      "grad_norm": 1.686681343926466e-06,
      "learning_rate": 6.6232888554993375e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8548672,
      "step": 30515
    },
    {
      "epoch": 339.1111111111111,
      "grad_norm": 2.227391405540402e-06,
      "learning_rate": 6.616634092844817e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8550080,
      "step": 30520
    },
    {
      "epoch": 339.1666666666667,
      "grad_norm": 1.4681922948511783e-06,
      "learning_rate": 6.609982165136331e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8551456,
      "step": 30525
    },
    {
      "epoch": 339.22222222222223,
      "grad_norm": 9.81966536528489e-07,
      "learning_rate": 6.603333073399706e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8552880,
      "step": 30530
    },
    {
      "epoch": 339.27777777777777,
      "grad_norm": 6.592055683540821e-07,
      "learning_rate": 6.596686818660308e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8554240,
      "step": 30535
    },
    {
      "epoch": 339.3333333333333,
      "grad_norm": 6.281403557295562e-07,
      "learning_rate": 6.590043401943066e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8555664,
      "step": 30540
    },
    {
      "epoch": 339.3888888888889,
      "grad_norm": 4.1104203774011694e-07,
      "learning_rate": 6.583402824272494e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8557056,
      "step": 30545
    },
    {
      "epoch": 339.44444444444446,
      "grad_norm": 5.340185111890605e-07,
      "learning_rate": 6.576765086672634e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8558448,
      "step": 30550
    },
    {
      "epoch": 339.5,
      "grad_norm": 4.5035710627416847e-07,
      "learning_rate": 6.57013019016712e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8559920,
      "step": 30555
    },
    {
      "epoch": 339.55555555555554,
      "grad_norm": 2.183254764531739e-06,
      "learning_rate": 6.563498135779142e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8561328,
      "step": 30560
    },
    {
      "epoch": 339.6111111111111,
      "grad_norm": 6.317696374935622e-07,
      "learning_rate": 6.556868924531431e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8562704,
      "step": 30565
    },
    {
      "epoch": 339.6666666666667,
      "grad_norm": 5.011630719309323e-07,
      "learning_rate": 6.550242557446304e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8564080,
      "step": 30570
    },
    {
      "epoch": 339.72222222222223,
      "grad_norm": 5.466075663207448e-07,
      "learning_rate": 6.543619035545634e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8565472,
      "step": 30575
    },
    {
      "epoch": 339.77777777777777,
      "grad_norm": 4.7225069010892184e-07,
      "learning_rate": 6.53699835985084e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8566896,
      "step": 30580
    },
    {
      "epoch": 339.8333333333333,
      "grad_norm": 2.1285213733790442e-06,
      "learning_rate": 6.530380531382927e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8568272,
      "step": 30585
    },
    {
      "epoch": 339.8888888888889,
      "grad_norm": 9.807640708459076e-07,
      "learning_rate": 6.523765551162433e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8569664,
      "step": 30590
    },
    {
      "epoch": 339.94444444444446,
      "grad_norm": 5.748840408159595e-07,
      "learning_rate": 6.517153420209476e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8571056,
      "step": 30595
    },
    {
      "epoch": 340.0,
      "grad_norm": 5.718094939766161e-07,
      "learning_rate": 6.510544139543739e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8572496,
      "step": 30600
    },
    {
      "epoch": 340.0,
      "eval_loss": 0.35483676195144653,
      "eval_runtime": 1.2844,
      "eval_samples_per_second": 31.142,
      "eval_steps_per_second": 15.571,
      "num_input_tokens_seen": 8572496,
      "step": 30600
    },
    {
      "epoch": 340.05555555555554,
      "grad_norm": 5.068861241852574e-07,
      "learning_rate": 6.503937710184452e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8573872,
      "step": 30605
    },
    {
      "epoch": 340.1111111111111,
      "grad_norm": 5.798609663543175e-07,
      "learning_rate": 6.4973341331503954e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8575280,
      "step": 30610
    },
    {
      "epoch": 340.1666666666667,
      "grad_norm": 5.35253263933555e-07,
      "learning_rate": 6.490733409459942e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8576672,
      "step": 30615
    },
    {
      "epoch": 340.22222222222223,
      "grad_norm": 4.897801773040555e-07,
      "learning_rate": 6.484135540130995e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8578112,
      "step": 30620
    },
    {
      "epoch": 340.27777777777777,
      "grad_norm": 9.710134918350377e-07,
      "learning_rate": 6.4775405261810364e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8579520,
      "step": 30625
    },
    {
      "epoch": 340.3333333333333,
      "grad_norm": 4.4714977320836624e-07,
      "learning_rate": 6.470948368627092e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8580912,
      "step": 30630
    },
    {
      "epoch": 340.3888888888889,
      "grad_norm": 5.042802513344213e-07,
      "learning_rate": 6.464359068485756e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8582304,
      "step": 30635
    },
    {
      "epoch": 340.44444444444446,
      "grad_norm": 5.894377750337298e-07,
      "learning_rate": 6.457772626773195e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8583744,
      "step": 30640
    },
    {
      "epoch": 340.5,
      "grad_norm": 6.1438777265721e-07,
      "learning_rate": 6.451189044505104e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8585120,
      "step": 30645
    },
    {
      "epoch": 340.55555555555554,
      "grad_norm": 9.544235126668354e-07,
      "learning_rate": 6.44460832269676e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8586560,
      "step": 30650
    },
    {
      "epoch": 340.6111111111111,
      "grad_norm": 5.447315061246627e-07,
      "learning_rate": 6.438030462363001e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8587936,
      "step": 30655
    },
    {
      "epoch": 340.6666666666667,
      "grad_norm": 8.18951320979977e-07,
      "learning_rate": 6.431455464518205e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8589264,
      "step": 30660
    },
    {
      "epoch": 340.72222222222223,
      "grad_norm": 6.258002258618944e-07,
      "learning_rate": 6.424883330176326e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8590688,
      "step": 30665
    },
    {
      "epoch": 340.77777777777777,
      "grad_norm": 5.443284294415207e-07,
      "learning_rate": 6.418314060350864e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8592080,
      "step": 30670
    },
    {
      "epoch": 340.8333333333333,
      "grad_norm": 2.9999450816831086e-06,
      "learning_rate": 6.4117476560548895e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8593456,
      "step": 30675
    },
    {
      "epoch": 340.8888888888889,
      "grad_norm": 5.626959023175004e-07,
      "learning_rate": 6.405184118301016e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8594896,
      "step": 30680
    },
    {
      "epoch": 340.94444444444446,
      "grad_norm": 1.6605962400717544e-06,
      "learning_rate": 6.398623448101434e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8596256,
      "step": 30685
    },
    {
      "epoch": 341.0,
      "grad_norm": 5.889747853871086e-07,
      "learning_rate": 6.392065646467871e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8597664,
      "step": 30690
    },
    {
      "epoch": 341.05555555555554,
      "grad_norm": 5.323456662154058e-07,
      "learning_rate": 6.385510714411632e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8599088,
      "step": 30695
    },
    {
      "epoch": 341.1111111111111,
      "grad_norm": 5.473770556818636e-07,
      "learning_rate": 6.378958652943559e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8600496,
      "step": 30700
    },
    {
      "epoch": 341.1666666666667,
      "grad_norm": 9.871768043012707e-07,
      "learning_rate": 6.3724094630740776e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8601904,
      "step": 30705
    },
    {
      "epoch": 341.22222222222223,
      "grad_norm": 1.4748724197488627e-06,
      "learning_rate": 6.365863145813136e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8603328,
      "step": 30710
    },
    {
      "epoch": 341.27777777777777,
      "grad_norm": 9.69149141383241e-07,
      "learning_rate": 6.359319702170269e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8604720,
      "step": 30715
    },
    {
      "epoch": 341.3333333333333,
      "grad_norm": 2.1415826267912053e-06,
      "learning_rate": 6.352779133154566e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8606144,
      "step": 30720
    },
    {
      "epoch": 341.3888888888889,
      "grad_norm": 5.825035600537376e-07,
      "learning_rate": 6.346241439774648e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8607568,
      "step": 30725
    },
    {
      "epoch": 341.44444444444446,
      "grad_norm": 5.921862680224876e-07,
      "learning_rate": 6.339706623038716e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8608960,
      "step": 30730
    },
    {
      "epoch": 341.5,
      "grad_norm": 1.6712616570657701e-06,
      "learning_rate": 6.333174683954532e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8610320,
      "step": 30735
    },
    {
      "epoch": 341.55555555555554,
      "grad_norm": 6.022337970534863e-07,
      "learning_rate": 6.326645623529387e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8611696,
      "step": 30740
    },
    {
      "epoch": 341.6111111111111,
      "grad_norm": 9.613087286197697e-07,
      "learning_rate": 6.320119442770156e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8613136,
      "step": 30745
    },
    {
      "epoch": 341.6666666666667,
      "grad_norm": 9.686633575256565e-07,
      "learning_rate": 6.313596142683254e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8614544,
      "step": 30750
    },
    {
      "epoch": 341.72222222222223,
      "grad_norm": 9.954134156942018e-07,
      "learning_rate": 6.307075724274647e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8615920,
      "step": 30755
    },
    {
      "epoch": 341.77777777777777,
      "grad_norm": 5.609463187283836e-07,
      "learning_rate": 6.300558188549882e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8617312,
      "step": 30760
    },
    {
      "epoch": 341.8333333333333,
      "grad_norm": 5.995413516757253e-07,
      "learning_rate": 6.29404353651403e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8618688,
      "step": 30765
    },
    {
      "epoch": 341.8888888888889,
      "grad_norm": 5.879239211026288e-07,
      "learning_rate": 6.287531769171737e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8620064,
      "step": 30770
    },
    {
      "epoch": 341.94444444444446,
      "grad_norm": 6.105682928136957e-07,
      "learning_rate": 6.2810228875272045e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8621424,
      "step": 30775
    },
    {
      "epoch": 342.0,
      "grad_norm": 1.478060994486441e-06,
      "learning_rate": 6.274516892584179e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8622864,
      "step": 30780
    },
    {
      "epoch": 342.05555555555554,
      "grad_norm": 2.208269734182977e-06,
      "learning_rate": 6.268013785345969e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8624288,
      "step": 30785
    },
    {
      "epoch": 342.1111111111111,
      "grad_norm": 5.367663789002108e-07,
      "learning_rate": 6.26151356681543e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8625680,
      "step": 30790
    },
    {
      "epoch": 342.1666666666667,
      "grad_norm": 4.918589411317953e-07,
      "learning_rate": 6.255016237994981e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8627056,
      "step": 30795
    },
    {
      "epoch": 342.22222222222223,
      "grad_norm": 9.358547572446696e-07,
      "learning_rate": 6.248521799886603e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8628448,
      "step": 30800
    },
    {
      "epoch": 342.22222222222223,
      "eval_loss": 0.31406450271606445,
      "eval_runtime": 1.2911,
      "eval_samples_per_second": 30.981,
      "eval_steps_per_second": 15.491,
      "num_input_tokens_seen": 8628448,
      "step": 30800
    },
    {
      "epoch": 342.27777777777777,
      "grad_norm": 6.053366519154224e-07,
      "learning_rate": 6.242030253491798e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8629840,
      "step": 30805
    },
    {
      "epoch": 342.3333333333333,
      "grad_norm": 9.227197779182461e-07,
      "learning_rate": 6.235541599811656e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8631264,
      "step": 30810
    },
    {
      "epoch": 342.3888888888889,
      "grad_norm": 9.575753665558295e-07,
      "learning_rate": 6.229055839846814e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8632624,
      "step": 30815
    },
    {
      "epoch": 342.44444444444446,
      "grad_norm": 5.278103571981774e-07,
      "learning_rate": 6.222572974597455e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8634000,
      "step": 30820
    },
    {
      "epoch": 342.5,
      "grad_norm": 5.312483608577168e-07,
      "learning_rate": 6.216093005063306e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8635440,
      "step": 30825
    },
    {
      "epoch": 342.55555555555554,
      "grad_norm": 1.1445639529483742e-06,
      "learning_rate": 6.209615932243678e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8636816,
      "step": 30830
    },
    {
      "epoch": 342.6111111111111,
      "grad_norm": 1.11321173790202e-06,
      "learning_rate": 6.203141757137399e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8638224,
      "step": 30835
    },
    {
      "epoch": 342.6666666666667,
      "grad_norm": 5.56390261863271e-07,
      "learning_rate": 6.196670480742886e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8639664,
      "step": 30840
    },
    {
      "epoch": 342.72222222222223,
      "grad_norm": 3.148393261653837e-06,
      "learning_rate": 6.190202104058074e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8641072,
      "step": 30845
    },
    {
      "epoch": 342.77777777777777,
      "grad_norm": 1.0470104143678327e-06,
      "learning_rate": 6.183736628080475e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8642480,
      "step": 30850
    },
    {
      "epoch": 342.8333333333333,
      "grad_norm": 5.357798045224627e-07,
      "learning_rate": 6.177274053807155e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8643888,
      "step": 30855
    },
    {
      "epoch": 342.8888888888889,
      "grad_norm": 5.453539415611885e-07,
      "learning_rate": 6.170814382234713e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8645344,
      "step": 30860
    },
    {
      "epoch": 342.94444444444446,
      "grad_norm": 9.085784995477297e-07,
      "learning_rate": 6.16435761435932e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8646752,
      "step": 30865
    },
    {
      "epoch": 343.0,
      "grad_norm": 4.896019731859269e-07,
      "learning_rate": 6.157903751176681e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8648192,
      "step": 30870
    },
    {
      "epoch": 343.05555555555554,
      "grad_norm": 6.304158546299732e-07,
      "learning_rate": 6.151452793682066e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8649584,
      "step": 30875
    },
    {
      "epoch": 343.1111111111111,
      "grad_norm": 6.188561201270204e-07,
      "learning_rate": 6.145004742870305e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8650992,
      "step": 30880
    },
    {
      "epoch": 343.1666666666667,
      "grad_norm": 5.210137601352471e-07,
      "learning_rate": 6.138559599735752e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8652448,
      "step": 30885
    },
    {
      "epoch": 343.22222222222223,
      "grad_norm": 4.961073045706144e-07,
      "learning_rate": 6.132117365272344e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8653872,
      "step": 30890
    },
    {
      "epoch": 343.27777777777777,
      "grad_norm": 2.139102207365795e-06,
      "learning_rate": 6.125678040473545e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8655280,
      "step": 30895
    },
    {
      "epoch": 343.3333333333333,
      "grad_norm": 4.677422111853957e-07,
      "learning_rate": 6.1192416263323755e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8656656,
      "step": 30900
    },
    {
      "epoch": 343.3888888888889,
      "grad_norm": 5.143144790054066e-07,
      "learning_rate": 6.112808123841424e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8658048,
      "step": 30905
    },
    {
      "epoch": 343.44444444444446,
      "grad_norm": 5.910627578487038e-07,
      "learning_rate": 6.106377533992805e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8659424,
      "step": 30910
    },
    {
      "epoch": 343.5,
      "grad_norm": 2.306749365743599e-06,
      "learning_rate": 6.099949857778204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8660784,
      "step": 30915
    },
    {
      "epoch": 343.55555555555554,
      "grad_norm": 5.042060138293891e-07,
      "learning_rate": 6.093525096188852e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8662160,
      "step": 30920
    },
    {
      "epoch": 343.6111111111111,
      "grad_norm": 5.014634893996117e-07,
      "learning_rate": 6.087103250215518e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8663584,
      "step": 30925
    },
    {
      "epoch": 343.6666666666667,
      "grad_norm": 1.0317820624550222e-06,
      "learning_rate": 6.080684320848537e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8664992,
      "step": 30930
    },
    {
      "epoch": 343.72222222222223,
      "grad_norm": 9.556771374263917e-07,
      "learning_rate": 6.074268309077794e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8666400,
      "step": 30935
    },
    {
      "epoch": 343.77777777777777,
      "grad_norm": 9.166251970782469e-07,
      "learning_rate": 6.067855215892709e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8667840,
      "step": 30940
    },
    {
      "epoch": 343.8333333333333,
      "grad_norm": 5.053639142715838e-07,
      "learning_rate": 6.061445042282271e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8669248,
      "step": 30945
    },
    {
      "epoch": 343.8888888888889,
      "grad_norm": 6.31016234819981e-07,
      "learning_rate": 6.055037789234999e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8670688,
      "step": 30950
    },
    {
      "epoch": 343.94444444444446,
      "grad_norm": 9.7990221092914e-07,
      "learning_rate": 6.048633457738975e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8672080,
      "step": 30955
    },
    {
      "epoch": 344.0,
      "grad_norm": 4.781555276167637e-07,
      "learning_rate": 6.042232048781837e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8673456,
      "step": 30960
    },
    {
      "epoch": 344.05555555555554,
      "grad_norm": 9.349327001473284e-07,
      "learning_rate": 6.035833563350757e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8674784,
      "step": 30965
    },
    {
      "epoch": 344.1111111111111,
      "grad_norm": 5.309972834766086e-07,
      "learning_rate": 6.0294380024324525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8676224,
      "step": 30970
    },
    {
      "epoch": 344.1666666666667,
      "grad_norm": 1.0284111340297386e-06,
      "learning_rate": 6.023045367013213e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8677600,
      "step": 30975
    },
    {
      "epoch": 344.22222222222223,
      "grad_norm": 9.727128826853004e-07,
      "learning_rate": 6.016655658078851e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8678960,
      "step": 30980
    },
    {
      "epoch": 344.27777777777777,
      "grad_norm": 3.726408522197744e-06,
      "learning_rate": 6.010268876614753e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8680368,
      "step": 30985
    },
    {
      "epoch": 344.3333333333333,
      "grad_norm": 5.007731829209661e-07,
      "learning_rate": 6.0038850236058266e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8681824,
      "step": 30990
    },
    {
      "epoch": 344.3888888888889,
      "grad_norm": 5.347461069504789e-07,
      "learning_rate": 5.997504100036549e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8683264,
      "step": 30995
    },
    {
      "epoch": 344.44444444444446,
      "grad_norm": 6.388262931977806e-07,
      "learning_rate": 5.991126106890949e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8684672,
      "step": 31000
    },
    {
      "epoch": 344.44444444444446,
      "eval_loss": 0.3563522696495056,
      "eval_runtime": 1.2916,
      "eval_samples_per_second": 30.97,
      "eval_steps_per_second": 15.485,
      "num_input_tokens_seen": 8684672,
      "step": 31000
    },
    {
      "epoch": 344.5,
      "grad_norm": 9.461376748731709e-07,
      "learning_rate": 5.984751045152576e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8686096,
      "step": 31005
    },
    {
      "epoch": 344.55555555555554,
      "grad_norm": 6.141316930552421e-07,
      "learning_rate": 5.978378915804553e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8687472,
      "step": 31010
    },
    {
      "epoch": 344.6111111111111,
      "grad_norm": 5.967581842014624e-07,
      "learning_rate": 5.972009719829547e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8688848,
      "step": 31015
    },
    {
      "epoch": 344.6666666666667,
      "grad_norm": 5.287545832288743e-07,
      "learning_rate": 5.965643458209755e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8690272,
      "step": 31020
    },
    {
      "epoch": 344.72222222222223,
      "grad_norm": 5.859206453351362e-07,
      "learning_rate": 5.95928013192695e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8691680,
      "step": 31025
    },
    {
      "epoch": 344.77777777777777,
      "grad_norm": 2.8362699140416225e-06,
      "learning_rate": 5.952919741962423e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8693104,
      "step": 31030
    },
    {
      "epoch": 344.8333333333333,
      "grad_norm": 1.6759307754909969e-06,
      "learning_rate": 5.946562289297042e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8694512,
      "step": 31035
    },
    {
      "epoch": 344.8888888888889,
      "grad_norm": 4.956791030963359e-07,
      "learning_rate": 5.9402077749111855e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8695920,
      "step": 31040
    },
    {
      "epoch": 344.94444444444446,
      "grad_norm": 1.5156554127315758e-06,
      "learning_rate": 5.933856199784821e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8697328,
      "step": 31045
    },
    {
      "epoch": 345.0,
      "grad_norm": 5.489070531439211e-07,
      "learning_rate": 5.927507564897419e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8698720,
      "step": 31050
    },
    {
      "epoch": 345.05555555555554,
      "grad_norm": 5.012599331166712e-07,
      "learning_rate": 5.9211618712280395e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8700112,
      "step": 31055
    },
    {
      "epoch": 345.1111111111111,
      "grad_norm": 9.079102483156021e-07,
      "learning_rate": 5.914819119755255e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8701488,
      "step": 31060
    },
    {
      "epoch": 345.1666666666667,
      "grad_norm": 2.013049652305199e-06,
      "learning_rate": 5.908479311457205e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8702880,
      "step": 31065
    },
    {
      "epoch": 345.22222222222223,
      "grad_norm": 5.681205834662251e-07,
      "learning_rate": 5.902142447311559e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8704320,
      "step": 31070
    },
    {
      "epoch": 345.27777777777777,
      "grad_norm": 5.018173965254391e-07,
      "learning_rate": 5.895808528295546e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8705776,
      "step": 31075
    },
    {
      "epoch": 345.3333333333333,
      "grad_norm": 5.751694516220596e-07,
      "learning_rate": 5.889477555385941e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8707168,
      "step": 31080
    },
    {
      "epoch": 345.3888888888889,
      "grad_norm": 1.6809389080663095e-06,
      "learning_rate": 5.883149529559051e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8708576,
      "step": 31085
    },
    {
      "epoch": 345.44444444444446,
      "grad_norm": 9.090422281587962e-07,
      "learning_rate": 5.876824451790738e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8709952,
      "step": 31090
    },
    {
      "epoch": 345.5,
      "grad_norm": 9.932708735505003e-07,
      "learning_rate": 5.87050232305642e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8711328,
      "step": 31095
    },
    {
      "epoch": 345.55555555555554,
      "grad_norm": 1.0206532579104532e-06,
      "learning_rate": 5.864183144331034e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8712720,
      "step": 31100
    },
    {
      "epoch": 345.6111111111111,
      "grad_norm": 5.018650881538633e-07,
      "learning_rate": 5.857866916589089e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8714112,
      "step": 31105
    },
    {
      "epoch": 345.6666666666667,
      "grad_norm": 4.7448241957681603e-07,
      "learning_rate": 5.8515536408046216e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8715568,
      "step": 31110
    },
    {
      "epoch": 345.72222222222223,
      "grad_norm": 5.638371476379689e-07,
      "learning_rate": 5.845243317951208e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8717008,
      "step": 31115
    },
    {
      "epoch": 345.77777777777777,
      "grad_norm": 4.6813272547296947e-07,
      "learning_rate": 5.838935949001997e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8718352,
      "step": 31120
    },
    {
      "epoch": 345.8333333333333,
      "grad_norm": 5.44184956652316e-07,
      "learning_rate": 5.8326315349296476e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8719728,
      "step": 31125
    },
    {
      "epoch": 345.8888888888889,
      "grad_norm": 9.119971764448564e-07,
      "learning_rate": 5.826330076706396e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8721168,
      "step": 31130
    },
    {
      "epoch": 345.94444444444446,
      "grad_norm": 1.493519789619313e-06,
      "learning_rate": 5.820031575303988e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8722544,
      "step": 31135
    },
    {
      "epoch": 346.0,
      "grad_norm": 2.1554458271566546e-06,
      "learning_rate": 5.813736031693745e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8723936,
      "step": 31140
    },
    {
      "epoch": 346.05555555555554,
      "grad_norm": 8.837548648443772e-07,
      "learning_rate": 5.807443446846522e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8725408,
      "step": 31145
    },
    {
      "epoch": 346.1111111111111,
      "grad_norm": 6.346411964841536e-07,
      "learning_rate": 5.801153821732699e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8726816,
      "step": 31150
    },
    {
      "epoch": 346.1666666666667,
      "grad_norm": 1.66401048318221e-06,
      "learning_rate": 5.794867157322229e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8728240,
      "step": 31155
    },
    {
      "epoch": 346.22222222222223,
      "grad_norm": 5.065022605776903e-07,
      "learning_rate": 5.788583454584593e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8729600,
      "step": 31160
    },
    {
      "epoch": 346.27777777777777,
      "grad_norm": 2.190953637182247e-06,
      "learning_rate": 5.7823027144888075e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8731024,
      "step": 31165
    },
    {
      "epoch": 346.3333333333333,
      "grad_norm": 6.468583819696505e-07,
      "learning_rate": 5.776024938003455e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8732464,
      "step": 31170
    },
    {
      "epoch": 346.3888888888889,
      "grad_norm": 1.6849570556587423e-06,
      "learning_rate": 5.7697501260966345e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8733872,
      "step": 31175
    },
    {
      "epoch": 346.44444444444446,
      "grad_norm": 2.7373093871574383e-06,
      "learning_rate": 5.7634782797360145e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8735264,
      "step": 31180
    },
    {
      "epoch": 346.5,
      "grad_norm": 4.749179254304181e-07,
      "learning_rate": 5.757209399888777e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8736672,
      "step": 31185
    },
    {
      "epoch": 346.55555555555554,
      "grad_norm": 5.89336025313969e-07,
      "learning_rate": 5.750943487521679e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8738048,
      "step": 31190
    },
    {
      "epoch": 346.6111111111111,
      "grad_norm": 4.688497483584797e-07,
      "learning_rate": 5.744680543600986e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8739408,
      "step": 31195
    },
    {
      "epoch": 346.6666666666667,
      "grad_norm": 1.6976524648271152e-06,
      "learning_rate": 5.738420569092537e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8740800,
      "step": 31200
    },
    {
      "epoch": 346.6666666666667,
      "eval_loss": 0.30873173475265503,
      "eval_runtime": 1.2913,
      "eval_samples_per_second": 30.975,
      "eval_steps_per_second": 15.488,
      "num_input_tokens_seen": 8740800,
      "step": 31200
    },
    {
      "epoch": 346.72222222222223,
      "grad_norm": 2.1059586288174614e-06,
      "learning_rate": 5.732163564961684e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8742240,
      "step": 31205
    },
    {
      "epoch": 346.77777777777777,
      "grad_norm": 5.688666533387732e-07,
      "learning_rate": 5.725909532173354e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8743600,
      "step": 31210
    },
    {
      "epoch": 346.8333333333333,
      "grad_norm": 5.734819410463388e-07,
      "learning_rate": 5.719658471691977e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8744992,
      "step": 31215
    },
    {
      "epoch": 346.8888888888889,
      "grad_norm": 5.62838181394909e-07,
      "learning_rate": 5.71341038448156e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8746352,
      "step": 31220
    },
    {
      "epoch": 346.94444444444446,
      "grad_norm": 2.0762329313583905e-06,
      "learning_rate": 5.707165271505635e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8747728,
      "step": 31225
    },
    {
      "epoch": 347.0,
      "grad_norm": 9.503881983619067e-07,
      "learning_rate": 5.700923133727271e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8749152,
      "step": 31230
    },
    {
      "epoch": 347.05555555555554,
      "grad_norm": 6.336626938718837e-07,
      "learning_rate": 5.694683972109083e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8750560,
      "step": 31235
    },
    {
      "epoch": 347.1111111111111,
      "grad_norm": 1.7327474779449403e-06,
      "learning_rate": 5.688447787613241e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8751936,
      "step": 31240
    },
    {
      "epoch": 347.1666666666667,
      "grad_norm": 5.880942239855358e-07,
      "learning_rate": 5.6822145812014285e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8753328,
      "step": 31245
    },
    {
      "epoch": 347.22222222222223,
      "grad_norm": 5.646294312100508e-07,
      "learning_rate": 5.675984353834896e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8754784,
      "step": 31250
    },
    {
      "epoch": 347.27777777777777,
      "grad_norm": 5.286522082315059e-07,
      "learning_rate": 5.66975710647441e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8756192,
      "step": 31255
    },
    {
      "epoch": 347.3333333333333,
      "grad_norm": 2.1292123619787162e-06,
      "learning_rate": 5.663532840080304e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8757568,
      "step": 31260
    },
    {
      "epoch": 347.3888888888889,
      "grad_norm": 5.763236572420283e-07,
      "learning_rate": 5.6573115556124325e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8758976,
      "step": 31265
    },
    {
      "epoch": 347.44444444444446,
      "grad_norm": 5.003703336114995e-07,
      "learning_rate": 5.651093254030185e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8760368,
      "step": 31270
    },
    {
      "epoch": 347.5,
      "grad_norm": 5.783626306765655e-07,
      "learning_rate": 5.644877936292514e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8761680,
      "step": 31275
    },
    {
      "epoch": 347.55555555555554,
      "grad_norm": 4.667508335387538e-07,
      "learning_rate": 5.638665603357901e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8763120,
      "step": 31280
    },
    {
      "epoch": 347.6111111111111,
      "grad_norm": 4.5476213017536793e-07,
      "learning_rate": 5.632456256184357e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8764576,
      "step": 31285
    },
    {
      "epoch": 347.6666666666667,
      "grad_norm": 1.4841484698990826e-06,
      "learning_rate": 5.626249895729452e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8766000,
      "step": 31290
    },
    {
      "epoch": 347.72222222222223,
      "grad_norm": 1.4872734936943743e-06,
      "learning_rate": 5.620046522950273e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8767440,
      "step": 31295
    },
    {
      "epoch": 347.77777777777777,
      "grad_norm": 4.6747973669880594e-07,
      "learning_rate": 5.613846138803464e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8768832,
      "step": 31300
    },
    {
      "epoch": 347.8333333333333,
      "grad_norm": 9.69785332927131e-07,
      "learning_rate": 5.607648744245206e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8770240,
      "step": 31305
    },
    {
      "epoch": 347.8888888888889,
      "grad_norm": 6.315514156085555e-07,
      "learning_rate": 5.601454340231207e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8771632,
      "step": 31310
    },
    {
      "epoch": 347.94444444444446,
      "grad_norm": 4.870746010965377e-07,
      "learning_rate": 5.595262927716724e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8773008,
      "step": 31315
    },
    {
      "epoch": 348.0,
      "grad_norm": 8.803013429314888e-07,
      "learning_rate": 5.589074507656561e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8774384,
      "step": 31320
    },
    {
      "epoch": 348.05555555555554,
      "grad_norm": 9.743288273966755e-07,
      "learning_rate": 5.582889081005044e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8775744,
      "step": 31325
    },
    {
      "epoch": 348.1111111111111,
      "grad_norm": 1.4707087530041463e-06,
      "learning_rate": 5.5767066487160316e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8777168,
      "step": 31330
    },
    {
      "epoch": 348.1666666666667,
      "grad_norm": 5.325769052433316e-07,
      "learning_rate": 5.570527211742949e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8778576,
      "step": 31335
    },
    {
      "epoch": 348.22222222222223,
      "grad_norm": 4.5247227831168857e-07,
      "learning_rate": 5.564350771038731e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8780016,
      "step": 31340
    },
    {
      "epoch": 348.27777777777777,
      "grad_norm": 1.5229528571580886e-06,
      "learning_rate": 5.558177327555875e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8781472,
      "step": 31345
    },
    {
      "epoch": 348.3333333333333,
      "grad_norm": 6.007379624861642e-07,
      "learning_rate": 5.552006882246388e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8782832,
      "step": 31350
    },
    {
      "epoch": 348.3888888888889,
      "grad_norm": 1.0377576700193458e-06,
      "learning_rate": 5.545839436061839e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8784240,
      "step": 31355
    },
    {
      "epoch": 348.44444444444446,
      "grad_norm": 5.066711992185446e-07,
      "learning_rate": 5.539674989953331e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8785664,
      "step": 31360
    },
    {
      "epoch": 348.5,
      "grad_norm": 2.987282641697675e-06,
      "learning_rate": 5.533513544871488e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8787072,
      "step": 31365
    },
    {
      "epoch": 348.55555555555554,
      "grad_norm": 5.436767764877004e-07,
      "learning_rate": 5.527355101766493e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8788480,
      "step": 31370
    },
    {
      "epoch": 348.6111111111111,
      "grad_norm": 5.878312663298857e-07,
      "learning_rate": 5.521199661588044e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8789840,
      "step": 31375
    },
    {
      "epoch": 348.6666666666667,
      "grad_norm": 6.010074571349833e-07,
      "learning_rate": 5.5150472252853944e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8791280,
      "step": 31380
    },
    {
      "epoch": 348.72222222222223,
      "grad_norm": 5.79173445203196e-07,
      "learning_rate": 5.50889779380733e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8792656,
      "step": 31385
    },
    {
      "epoch": 348.77777777777777,
      "grad_norm": 1.6679604186720098e-06,
      "learning_rate": 5.5027513681021605e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8794000,
      "step": 31390
    },
    {
      "epoch": 348.8333333333333,
      "grad_norm": 1.9479493857943453e-06,
      "learning_rate": 5.4966079491177545e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8795408,
      "step": 31395
    },
    {
      "epoch": 348.8888888888889,
      "grad_norm": 8.2463805028965e-07,
      "learning_rate": 5.490467537801491e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8796784,
      "step": 31400
    },
    {
      "epoch": 348.8888888888889,
      "eval_loss": 0.32893458008766174,
      "eval_runtime": 1.3026,
      "eval_samples_per_second": 30.708,
      "eval_steps_per_second": 15.354,
      "num_input_tokens_seen": 8796784,
      "step": 31400
    },
    {
      "epoch": 348.94444444444446,
      "grad_norm": 5.066249855190108e-07,
      "learning_rate": 5.484330135100313e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8798192,
      "step": 31405
    },
    {
      "epoch": 349.0,
      "grad_norm": 3.1843292163102888e-06,
      "learning_rate": 5.4781957419606785e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8799552,
      "step": 31410
    },
    {
      "epoch": 349.05555555555554,
      "grad_norm": 4.672760951507371e-07,
      "learning_rate": 5.472064359328577e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8800928,
      "step": 31415
    },
    {
      "epoch": 349.1111111111111,
      "grad_norm": 4.516406875154644e-07,
      "learning_rate": 5.4659359881495565e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8802320,
      "step": 31420
    },
    {
      "epoch": 349.1666666666667,
      "grad_norm": 4.4703085677610943e-07,
      "learning_rate": 5.4598106293686916e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8803744,
      "step": 31425
    },
    {
      "epoch": 349.22222222222223,
      "grad_norm": 5.844506176799769e-07,
      "learning_rate": 5.45368828393058e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8805152,
      "step": 31430
    },
    {
      "epoch": 349.27777777777777,
      "grad_norm": 6.020385967531183e-07,
      "learning_rate": 5.44756895277937e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8806528,
      "step": 31435
    },
    {
      "epoch": 349.3333333333333,
      "grad_norm": 5.183293865229643e-07,
      "learning_rate": 5.441452636858746e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8807936,
      "step": 31440
    },
    {
      "epoch": 349.3888888888889,
      "grad_norm": 2.8611682409973582e-06,
      "learning_rate": 5.435339337111905e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8809344,
      "step": 31445
    },
    {
      "epoch": 349.44444444444446,
      "grad_norm": 6.152918103907723e-07,
      "learning_rate": 5.42922905448161e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8810752,
      "step": 31450
    },
    {
      "epoch": 349.5,
      "grad_norm": 5.916328973398777e-07,
      "learning_rate": 5.423121789910129e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8812144,
      "step": 31455
    },
    {
      "epoch": 349.55555555555554,
      "grad_norm": 8.598606200393988e-07,
      "learning_rate": 5.417017544339287e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8813552,
      "step": 31460
    },
    {
      "epoch": 349.6111111111111,
      "grad_norm": 5.202536499382404e-07,
      "learning_rate": 5.410916318710443e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8814944,
      "step": 31465
    },
    {
      "epoch": 349.6666666666667,
      "grad_norm": 1.488356247136835e-06,
      "learning_rate": 5.404818113964466e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8816368,
      "step": 31470
    },
    {
      "epoch": 349.72222222222223,
      "grad_norm": 4.5831026795895013e-07,
      "learning_rate": 5.398722931041792e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8817744,
      "step": 31475
    },
    {
      "epoch": 349.77777777777777,
      "grad_norm": 6.469028335231997e-07,
      "learning_rate": 5.392630770882367e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8819136,
      "step": 31480
    },
    {
      "epoch": 349.8333333333333,
      "grad_norm": 5.753015557274921e-07,
      "learning_rate": 5.3865416344256705e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8820576,
      "step": 31485
    },
    {
      "epoch": 349.8888888888889,
      "grad_norm": 3.5412656416156096e-06,
      "learning_rate": 5.380455522610742e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8822000,
      "step": 31490
    },
    {
      "epoch": 349.94444444444446,
      "grad_norm": 6.033011459294357e-07,
      "learning_rate": 5.374372436376116e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8823376,
      "step": 31495
    },
    {
      "epoch": 350.0,
      "grad_norm": 9.459022862756683e-07,
      "learning_rate": 5.368292376659895e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8824784,
      "step": 31500
    },
    {
      "epoch": 350.05555555555554,
      "grad_norm": 1.6469333559143706e-06,
      "learning_rate": 5.362215344399701e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8826192,
      "step": 31505
    },
    {
      "epoch": 350.1111111111111,
      "grad_norm": 5.201716248848243e-07,
      "learning_rate": 5.356141340532678e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8827568,
      "step": 31510
    },
    {
      "epoch": 350.1666666666667,
      "grad_norm": 5.845981831953395e-07,
      "learning_rate": 5.350070365995522e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8828976,
      "step": 31515
    },
    {
      "epoch": 350.22222222222223,
      "grad_norm": 1.0537619345996063e-06,
      "learning_rate": 5.344002421724459e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8830336,
      "step": 31520
    },
    {
      "epoch": 350.27777777777777,
      "grad_norm": 4.58048560858515e-07,
      "learning_rate": 5.337937508655228e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8831712,
      "step": 31525
    },
    {
      "epoch": 350.3333333333333,
      "grad_norm": 5.58796443783649e-07,
      "learning_rate": 5.331875627723126e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8833120,
      "step": 31530
    },
    {
      "epoch": 350.3888888888889,
      "grad_norm": 6.132197540864581e-07,
      "learning_rate": 5.325816779862963e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8834528,
      "step": 31535
    },
    {
      "epoch": 350.44444444444446,
      "grad_norm": 6.697154049106757e-07,
      "learning_rate": 5.319760966009102e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8835920,
      "step": 31540
    },
    {
      "epoch": 350.5,
      "grad_norm": 4.962212187820114e-07,
      "learning_rate": 5.3137081870954096e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8837376,
      "step": 31545
    },
    {
      "epoch": 350.55555555555554,
      "grad_norm": 2.0344130007288186e-06,
      "learning_rate": 5.307658444055313e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8838816,
      "step": 31550
    },
    {
      "epoch": 350.6111111111111,
      "grad_norm": 1.4723553931617062e-06,
      "learning_rate": 5.301611737821749e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8840160,
      "step": 31555
    },
    {
      "epoch": 350.6666666666667,
      "grad_norm": 1.122410594689427e-06,
      "learning_rate": 5.295568069327206e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8841520,
      "step": 31560
    },
    {
      "epoch": 350.72222222222223,
      "grad_norm": 6.022240199854423e-07,
      "learning_rate": 5.289527439503683e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8842912,
      "step": 31565
    },
    {
      "epoch": 350.77777777777777,
      "grad_norm": 5.833406930833007e-07,
      "learning_rate": 5.28348984928273e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8844304,
      "step": 31570
    },
    {
      "epoch": 350.8333333333333,
      "grad_norm": 6.420568752218969e-07,
      "learning_rate": 5.27745529959541e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8845728,
      "step": 31575
    },
    {
      "epoch": 350.8888888888889,
      "grad_norm": 9.351439871352341e-07,
      "learning_rate": 5.271423791372335e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8847168,
      "step": 31580
    },
    {
      "epoch": 350.94444444444446,
      "grad_norm": 4.94188896027481e-07,
      "learning_rate": 5.26539532554364e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8848592,
      "step": 31585
    },
    {
      "epoch": 351.0,
      "grad_norm": 1.4789517308599898e-06,
      "learning_rate": 5.25936990303898e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8849984,
      "step": 31590
    },
    {
      "epoch": 351.05555555555554,
      "grad_norm": 5.331976922207105e-07,
      "learning_rate": 5.253347524787555e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8851344,
      "step": 31595
    },
    {
      "epoch": 351.1111111111111,
      "grad_norm": 5.082644065623754e-07,
      "learning_rate": 5.2473281917181035e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8852784,
      "step": 31600
    },
    {
      "epoch": 351.1111111111111,
      "eval_loss": 0.32816341519355774,
      "eval_runtime": 1.2901,
      "eval_samples_per_second": 31.005,
      "eval_steps_per_second": 15.502,
      "num_input_tokens_seen": 8852784,
      "step": 31600
    },
    {
      "epoch": 351.1666666666667,
      "grad_norm": 5.173697559257562e-07,
      "learning_rate": 5.241311904758864e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8854192,
      "step": 31605
    },
    {
      "epoch": 351.22222222222223,
      "grad_norm": 3.122022690149606e-06,
      "learning_rate": 5.23529866483764e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8855568,
      "step": 31610
    },
    {
      "epoch": 351.27777777777777,
      "grad_norm": 5.612758400275197e-07,
      "learning_rate": 5.229288472881732e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8856976,
      "step": 31615
    },
    {
      "epoch": 351.3333333333333,
      "grad_norm": 6.156265044410247e-07,
      "learning_rate": 5.2232813298180025e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8858400,
      "step": 31620
    },
    {
      "epoch": 351.3888888888889,
      "grad_norm": 1.6910129261304974e-06,
      "learning_rate": 5.217277236572824e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8859792,
      "step": 31625
    },
    {
      "epoch": 351.44444444444446,
      "grad_norm": 1.6493154362251516e-06,
      "learning_rate": 5.211276194072093e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8861184,
      "step": 31630
    },
    {
      "epoch": 351.5,
      "grad_norm": 2.1898854356550146e-06,
      "learning_rate": 5.205278203241254e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8862592,
      "step": 31635
    },
    {
      "epoch": 351.55555555555554,
      "grad_norm": 5.943993528489955e-07,
      "learning_rate": 5.199283265005278e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8863984,
      "step": 31640
    },
    {
      "epoch": 351.6111111111111,
      "grad_norm": 3.566727627912769e-06,
      "learning_rate": 5.193291380288648e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8865376,
      "step": 31645
    },
    {
      "epoch": 351.6666666666667,
      "grad_norm": 1.7417056596968905e-06,
      "learning_rate": 5.1873025500153995e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8866768,
      "step": 31650
    },
    {
      "epoch": 351.72222222222223,
      "grad_norm": 4.704272953404143e-07,
      "learning_rate": 5.181316775109071e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8868160,
      "step": 31655
    },
    {
      "epoch": 351.77777777777777,
      "grad_norm": 1.4629850966230151e-06,
      "learning_rate": 5.1753340564927564e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8869584,
      "step": 31660
    },
    {
      "epoch": 351.8333333333333,
      "grad_norm": 9.094848678614653e-07,
      "learning_rate": 5.169354395089068e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8870960,
      "step": 31665
    },
    {
      "epoch": 351.8888888888889,
      "grad_norm": 1.658913447499799e-06,
      "learning_rate": 5.1633777918201346e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8872384,
      "step": 31670
    },
    {
      "epoch": 351.94444444444446,
      "grad_norm": 6.269493724175845e-07,
      "learning_rate": 5.157404247607625e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8873840,
      "step": 31675
    },
    {
      "epoch": 352.0,
      "grad_norm": 2.3112199869501637e-06,
      "learning_rate": 5.1514337633727454e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8875232,
      "step": 31680
    },
    {
      "epoch": 352.05555555555554,
      "grad_norm": 5.77997298023547e-07,
      "learning_rate": 5.145466340036206e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8876640,
      "step": 31685
    },
    {
      "epoch": 352.1111111111111,
      "grad_norm": 5.733735974899901e-07,
      "learning_rate": 5.139501978518274e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8878000,
      "step": 31690
    },
    {
      "epoch": 352.1666666666667,
      "grad_norm": 4.792598815583915e-07,
      "learning_rate": 5.133540679738716e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8879472,
      "step": 31695
    },
    {
      "epoch": 352.22222222222223,
      "grad_norm": 1.6740051478336682e-06,
      "learning_rate": 5.127582444616838e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8880864,
      "step": 31700
    },
    {
      "epoch": 352.27777777777777,
      "grad_norm": 6.445568487833953e-07,
      "learning_rate": 5.121627274071486e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8882256,
      "step": 31705
    },
    {
      "epoch": 352.3333333333333,
      "grad_norm": 9.878600621959777e-07,
      "learning_rate": 5.115675169021009e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8883696,
      "step": 31710
    },
    {
      "epoch": 352.3888888888889,
      "grad_norm": 1.6620075484752306e-06,
      "learning_rate": 5.1097261303832994e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8885088,
      "step": 31715
    },
    {
      "epoch": 352.44444444444446,
      "grad_norm": 4.12819701978151e-07,
      "learning_rate": 5.103780159075788e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8886432,
      "step": 31720
    },
    {
      "epoch": 352.5,
      "grad_norm": 5.404071998782456e-07,
      "learning_rate": 5.0978372560154e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8887872,
      "step": 31725
    },
    {
      "epoch": 352.55555555555554,
      "grad_norm": 7.058952178340405e-07,
      "learning_rate": 5.091897422118619e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8889328,
      "step": 31730
    },
    {
      "epoch": 352.6111111111111,
      "grad_norm": 9.81993139248516e-07,
      "learning_rate": 5.0859606583014305e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8890768,
      "step": 31735
    },
    {
      "epoch": 352.6666666666667,
      "grad_norm": 9.714427733342745e-07,
      "learning_rate": 5.080026965479365e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8892144,
      "step": 31740
    },
    {
      "epoch": 352.72222222222223,
      "grad_norm": 6.668767014161858e-07,
      "learning_rate": 5.074096344567475e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8893568,
      "step": 31745
    },
    {
      "epoch": 352.77777777777777,
      "grad_norm": 5.254638608676032e-07,
      "learning_rate": 5.0681687964803294e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8894960,
      "step": 31750
    },
    {
      "epoch": 352.8333333333333,
      "grad_norm": 1.5122614058782347e-06,
      "learning_rate": 5.06224432213204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8896368,
      "step": 31755
    },
    {
      "epoch": 352.8888888888889,
      "grad_norm": 5.196889674152771e-07,
      "learning_rate": 5.056322922436224e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8897776,
      "step": 31760
    },
    {
      "epoch": 352.94444444444446,
      "grad_norm": 1.0309921663065325e-06,
      "learning_rate": 5.0504045983060465e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8899216,
      "step": 31765
    },
    {
      "epoch": 353.0,
      "grad_norm": 6.074030807212694e-07,
      "learning_rate": 5.044489350654183e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8900592,
      "step": 31770
    },
    {
      "epoch": 353.05555555555554,
      "grad_norm": 2.1052260308351833e-06,
      "learning_rate": 5.038577180392831e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8902032,
      "step": 31775
    },
    {
      "epoch": 353.1111111111111,
      "grad_norm": 1.6556737136852462e-06,
      "learning_rate": 5.032668088433729e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8903440,
      "step": 31780
    },
    {
      "epoch": 353.1666666666667,
      "grad_norm": 1.4939532775315456e-06,
      "learning_rate": 5.02676207568814e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8904864,
      "step": 31785
    },
    {
      "epoch": 353.22222222222223,
      "grad_norm": 4.912152462566155e-07,
      "learning_rate": 5.02085914306683e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8906288,
      "step": 31790
    },
    {
      "epoch": 353.27777777777777,
      "grad_norm": 4.92833066800813e-07,
      "learning_rate": 5.014959291480123e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8907664,
      "step": 31795
    },
    {
      "epoch": 353.3333333333333,
      "grad_norm": 5.502393491951807e-07,
      "learning_rate": 5.009062521837835e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8909040,
      "step": 31800
    },
    {
      "epoch": 353.3333333333333,
      "eval_loss": 0.38202881813049316,
      "eval_runtime": 1.2967,
      "eval_samples_per_second": 30.848,
      "eval_steps_per_second": 15.424,
      "num_input_tokens_seen": 8909040,
      "step": 31800
    },
    {
      "epoch": 353.3888888888889,
      "grad_norm": 5.853913762621232e-07,
      "learning_rate": 5.003168835049324e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8910432,
      "step": 31805
    },
    {
      "epoch": 353.44444444444446,
      "grad_norm": 4.610684527506237e-07,
      "learning_rate": 4.997278232023483e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8911840,
      "step": 31810
    },
    {
      "epoch": 353.5,
      "grad_norm": 9.205303399539844e-07,
      "learning_rate": 4.9913907136687036e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8913264,
      "step": 31815
    },
    {
      "epoch": 353.55555555555554,
      "grad_norm": 5.545046519728203e-07,
      "learning_rate": 4.985506280892918e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8914640,
      "step": 31820
    },
    {
      "epoch": 353.6111111111111,
      "grad_norm": 9.242568808076612e-07,
      "learning_rate": 4.979624934603589e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8916048,
      "step": 31825
    },
    {
      "epoch": 353.6666666666667,
      "grad_norm": 1.7395260556440917e-06,
      "learning_rate": 4.97374667570768e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8917456,
      "step": 31830
    },
    {
      "epoch": 353.72222222222223,
      "grad_norm": 8.894256211533502e-07,
      "learning_rate": 4.967871505111704e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8918848,
      "step": 31835
    },
    {
      "epoch": 353.77777777777777,
      "grad_norm": 6.077497687329014e-07,
      "learning_rate": 4.961999423721686e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8920256,
      "step": 31840
    },
    {
      "epoch": 353.8333333333333,
      "grad_norm": 2.1204250515438616e-06,
      "learning_rate": 4.956130432443159e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8921680,
      "step": 31845
    },
    {
      "epoch": 353.8888888888889,
      "grad_norm": 1.0354660844313912e-06,
      "learning_rate": 4.950264532181215e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8923040,
      "step": 31850
    },
    {
      "epoch": 353.94444444444446,
      "grad_norm": 8.913179385672265e-07,
      "learning_rate": 4.944401723840433e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8924448,
      "step": 31855
    },
    {
      "epoch": 354.0,
      "grad_norm": 4.924334575662215e-07,
      "learning_rate": 4.938542008324942e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8925856,
      "step": 31860
    },
    {
      "epoch": 354.05555555555554,
      "grad_norm": 8.940065754359239e-07,
      "learning_rate": 4.9326853865383855e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8927232,
      "step": 31865
    },
    {
      "epoch": 354.1111111111111,
      "grad_norm": 6.275129749155894e-07,
      "learning_rate": 4.926831859383918e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8928640,
      "step": 31870
    },
    {
      "epoch": 354.1666666666667,
      "grad_norm": 1.6867767271833145e-06,
      "learning_rate": 4.92098142776424e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8930032,
      "step": 31875
    },
    {
      "epoch": 354.22222222222223,
      "grad_norm": 5.007259460398927e-07,
      "learning_rate": 4.91513409258155e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8931376,
      "step": 31880
    },
    {
      "epoch": 354.27777777777777,
      "grad_norm": 5.408354013525241e-07,
      "learning_rate": 4.909289854737581e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8932768,
      "step": 31885
    },
    {
      "epoch": 354.3333333333333,
      "grad_norm": 4.5110820678928576e-07,
      "learning_rate": 4.903448715133602e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8934176,
      "step": 31890
    },
    {
      "epoch": 354.3888888888889,
      "grad_norm": 6.000537950967555e-07,
      "learning_rate": 4.897610674670372e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8935584,
      "step": 31895
    },
    {
      "epoch": 354.44444444444446,
      "grad_norm": 5.192113690100086e-07,
      "learning_rate": 4.8917757342482e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8936976,
      "step": 31900
    },
    {
      "epoch": 354.5,
      "grad_norm": 5.464182208925195e-07,
      "learning_rate": 4.885943894766909e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8938368,
      "step": 31905
    },
    {
      "epoch": 354.55555555555554,
      "grad_norm": 1.6742953903303714e-06,
      "learning_rate": 4.880115157125842e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8939792,
      "step": 31910
    },
    {
      "epoch": 354.6111111111111,
      "grad_norm": 1.503042085460038e-06,
      "learning_rate": 4.874289522223857e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8941232,
      "step": 31915
    },
    {
      "epoch": 354.6666666666667,
      "grad_norm": 9.874753459371277e-07,
      "learning_rate": 4.868466990959339e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8942656,
      "step": 31920
    },
    {
      "epoch": 354.72222222222223,
      "grad_norm": 6.474600695582922e-07,
      "learning_rate": 4.8626475642301964e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8944064,
      "step": 31925
    },
    {
      "epoch": 354.77777777777777,
      "grad_norm": 5.78638889692229e-07,
      "learning_rate": 4.856831242933871e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8945456,
      "step": 31930
    },
    {
      "epoch": 354.8333333333333,
      "grad_norm": 6.033486670276034e-07,
      "learning_rate": 4.851018027967294e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8946864,
      "step": 31935
    },
    {
      "epoch": 354.8888888888889,
      "grad_norm": 2.240965613964363e-06,
      "learning_rate": 4.845207920226946e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8948256,
      "step": 31940
    },
    {
      "epoch": 354.94444444444446,
      "grad_norm": 1.0966181207550108e-06,
      "learning_rate": 4.839400920608825e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8949664,
      "step": 31945
    },
    {
      "epoch": 355.0,
      "grad_norm": 5.775430622634303e-07,
      "learning_rate": 4.83359703000843e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8951120,
      "step": 31950
    },
    {
      "epoch": 355.05555555555554,
      "grad_norm": 5.803631779599527e-07,
      "learning_rate": 4.827796249320804e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8952496,
      "step": 31955
    },
    {
      "epoch": 355.1111111111111,
      "grad_norm": 4.960572823620168e-07,
      "learning_rate": 4.82199857944049e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8953936,
      "step": 31960
    },
    {
      "epoch": 355.1666666666667,
      "grad_norm": 5.288569013828237e-07,
      "learning_rate": 4.8162040212615695e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8955360,
      "step": 31965
    },
    {
      "epoch": 355.22222222222223,
      "grad_norm": 1.6473727555421647e-06,
      "learning_rate": 4.810412575677639e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8956736,
      "step": 31970
    },
    {
      "epoch": 355.27777777777777,
      "grad_norm": 5.404828016253305e-07,
      "learning_rate": 4.804624243581801e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8958128,
      "step": 31975
    },
    {
      "epoch": 355.3333333333333,
      "grad_norm": 9.974555723601952e-07,
      "learning_rate": 4.798839025866703e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8959552,
      "step": 31980
    },
    {
      "epoch": 355.3888888888889,
      "grad_norm": 6.190896328917006e-07,
      "learning_rate": 4.793056923424491e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8960960,
      "step": 31985
    },
    {
      "epoch": 355.44444444444446,
      "grad_norm": 4.833797788705851e-07,
      "learning_rate": 4.78727793714683e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8962320,
      "step": 31990
    },
    {
      "epoch": 355.5,
      "grad_norm": 6.859502832412545e-07,
      "learning_rate": 4.7815020679249285e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8963712,
      "step": 31995
    },
    {
      "epoch": 355.55555555555554,
      "grad_norm": 9.651482741901418e-07,
      "learning_rate": 4.775729316649483e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8965104,
      "step": 32000
    },
    {
      "epoch": 355.55555555555554,
      "eval_loss": 0.351626455783844,
      "eval_runtime": 1.2917,
      "eval_samples_per_second": 30.967,
      "eval_steps_per_second": 15.484,
      "num_input_tokens_seen": 8965104,
      "step": 32000
    },
    {
      "epoch": 355.6111111111111,
      "grad_norm": 9.65041635936359e-07,
      "learning_rate": 4.769959684210728e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8966512,
      "step": 32005
    },
    {
      "epoch": 355.6666666666667,
      "grad_norm": 5.166471055417787e-07,
      "learning_rate": 4.764193171498426e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8967904,
      "step": 32010
    },
    {
      "epoch": 355.72222222222223,
      "grad_norm": 6.404695795936277e-07,
      "learning_rate": 4.75842977940183e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8969344,
      "step": 32015
    },
    {
      "epoch": 355.77777777777777,
      "grad_norm": 5.086919259156275e-07,
      "learning_rate": 4.752669508809729e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8970816,
      "step": 32020
    },
    {
      "epoch": 355.8333333333333,
      "grad_norm": 5.926663106947672e-07,
      "learning_rate": 4.746912360610445e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8972224,
      "step": 32025
    },
    {
      "epoch": 355.8888888888889,
      "grad_norm": 1.7064212443074211e-06,
      "learning_rate": 4.741158335691781e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8973584,
      "step": 32030
    },
    {
      "epoch": 355.94444444444446,
      "grad_norm": 1.690986550784146e-06,
      "learning_rate": 4.7354074349410994e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8975008,
      "step": 32035
    },
    {
      "epoch": 356.0,
      "grad_norm": 5.725647724830196e-07,
      "learning_rate": 4.729659659245245e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8976416,
      "step": 32040
    },
    {
      "epoch": 356.05555555555554,
      "grad_norm": 5.33492709564598e-07,
      "learning_rate": 4.723915009490601e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8977840,
      "step": 32045
    },
    {
      "epoch": 356.1111111111111,
      "grad_norm": 5.74367618355609e-07,
      "learning_rate": 4.718173486563077e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8979264,
      "step": 32050
    },
    {
      "epoch": 356.1666666666667,
      "grad_norm": 2.230440486528096e-06,
      "learning_rate": 4.71243509134808e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8980656,
      "step": 32055
    },
    {
      "epoch": 356.22222222222223,
      "grad_norm": 5.368472102418309e-07,
      "learning_rate": 4.706699824730532e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8982064,
      "step": 32060
    },
    {
      "epoch": 356.27777777777777,
      "grad_norm": 5.690421858162154e-07,
      "learning_rate": 4.700967687594901e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8983472,
      "step": 32065
    },
    {
      "epoch": 356.3333333333333,
      "grad_norm": 6.065833986212965e-07,
      "learning_rate": 4.69523868082514e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8984832,
      "step": 32070
    },
    {
      "epoch": 356.3888888888889,
      "grad_norm": 5.068184236733941e-07,
      "learning_rate": 4.689512805304747e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8986224,
      "step": 32075
    },
    {
      "epoch": 356.44444444444446,
      "grad_norm": 5.970796905785392e-07,
      "learning_rate": 4.683790061916707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8987664,
      "step": 32080
    },
    {
      "epoch": 356.5,
      "grad_norm": 4.999254770154948e-07,
      "learning_rate": 4.678070451543551e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8989088,
      "step": 32085
    },
    {
      "epoch": 356.55555555555554,
      "grad_norm": 6.397444849426392e-07,
      "learning_rate": 4.6723539750673204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8990512,
      "step": 32090
    },
    {
      "epoch": 356.6111111111111,
      "grad_norm": 5.28434497937269e-07,
      "learning_rate": 4.666640633369551e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8991936,
      "step": 32095
    },
    {
      "epoch": 356.6666666666667,
      "grad_norm": 1.989100837818114e-06,
      "learning_rate": 4.660930427331323e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8993328,
      "step": 32100
    },
    {
      "epoch": 356.72222222222223,
      "grad_norm": 8.623081271252886e-07,
      "learning_rate": 4.6552233578332244e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8994704,
      "step": 32105
    },
    {
      "epoch": 356.77777777777777,
      "grad_norm": 1.6447993402834982e-06,
      "learning_rate": 4.649519425755347e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8996128,
      "step": 32110
    },
    {
      "epoch": 356.8333333333333,
      "grad_norm": 5.030561851526727e-07,
      "learning_rate": 4.64381863197732e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8997504,
      "step": 32115
    },
    {
      "epoch": 356.8888888888889,
      "grad_norm": 5.761874035670189e-07,
      "learning_rate": 4.638120977378269e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 8998848,
      "step": 32120
    },
    {
      "epoch": 356.94444444444446,
      "grad_norm": 5.00074861520261e-07,
      "learning_rate": 4.632426462836848e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9000256,
      "step": 32125
    },
    {
      "epoch": 357.0,
      "grad_norm": 5.195594781071122e-07,
      "learning_rate": 4.626735089231224e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9001696,
      "step": 32130
    },
    {
      "epoch": 357.05555555555554,
      "grad_norm": 6.182995662129542e-07,
      "learning_rate": 4.621046857439068e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9003120,
      "step": 32135
    },
    {
      "epoch": 357.1111111111111,
      "grad_norm": 2.319292434549425e-06,
      "learning_rate": 4.615361768337587e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9004544,
      "step": 32140
    },
    {
      "epoch": 357.1666666666667,
      "grad_norm": 1.970158109543263e-06,
      "learning_rate": 4.6096798228034946e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9005920,
      "step": 32145
    },
    {
      "epoch": 357.22222222222223,
      "grad_norm": 5.734702881454723e-07,
      "learning_rate": 4.604001021713008e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9007376,
      "step": 32150
    },
    {
      "epoch": 357.27777777777777,
      "grad_norm": 1.000038651000068e-06,
      "learning_rate": 4.598325365941883e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9008768,
      "step": 32155
    },
    {
      "epoch": 357.3333333333333,
      "grad_norm": 1.4602145483877393e-06,
      "learning_rate": 4.5926528563653645e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9010160,
      "step": 32160
    },
    {
      "epoch": 357.3888888888889,
      "grad_norm": 1.0780116781461402e-06,
      "learning_rate": 4.5869834938582295e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9011520,
      "step": 32165
    },
    {
      "epoch": 357.44444444444446,
      "grad_norm": 5.353959977583145e-07,
      "learning_rate": 4.581317279294772e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9012912,
      "step": 32170
    },
    {
      "epoch": 357.5,
      "grad_norm": 5.845574833074352e-07,
      "learning_rate": 4.57565421354878e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9014352,
      "step": 32175
    },
    {
      "epoch": 357.55555555555554,
      "grad_norm": 1.4872786096020718e-06,
      "learning_rate": 4.569994297493579e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9015792,
      "step": 32180
    },
    {
      "epoch": 357.6111111111111,
      "grad_norm": 9.536329343973193e-07,
      "learning_rate": 4.564337532002002e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9017168,
      "step": 32185
    },
    {
      "epoch": 357.6666666666667,
      "grad_norm": 9.78851062427566e-07,
      "learning_rate": 4.55868391794638e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9018576,
      "step": 32190
    },
    {
      "epoch": 357.72222222222223,
      "grad_norm": 1.0968085462081945e-06,
      "learning_rate": 4.553033456198588e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9019952,
      "step": 32195
    },
    {
      "epoch": 357.77777777777777,
      "grad_norm": 5.918521424064238e-07,
      "learning_rate": 4.54738614762999e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9021344,
      "step": 32200
    },
    {
      "epoch": 357.77777777777777,
      "eval_loss": 0.3088778853416443,
      "eval_runtime": 1.2969,
      "eval_samples_per_second": 30.843,
      "eval_steps_per_second": 15.421,
      "num_input_tokens_seen": 9021344,
      "step": 32200
    },
    {
      "epoch": 357.8333333333333,
      "grad_norm": 4.389805212667852e-07,
      "learning_rate": 4.541741993111465e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9022720,
      "step": 32205
    },
    {
      "epoch": 357.8888888888889,
      "grad_norm": 5.005447292205645e-07,
      "learning_rate": 4.536100993513423e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9024096,
      "step": 32210
    },
    {
      "epoch": 357.94444444444446,
      "grad_norm": 1.9620433704403695e-06,
      "learning_rate": 4.530463149705768e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9025520,
      "step": 32215
    },
    {
      "epoch": 358.0,
      "grad_norm": 1.228070686920546e-06,
      "learning_rate": 4.524828462557934e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9026912,
      "step": 32220
    },
    {
      "epoch": 358.05555555555554,
      "grad_norm": 5.315828843777126e-07,
      "learning_rate": 4.5191969329388625e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9028320,
      "step": 32225
    },
    {
      "epoch": 358.1111111111111,
      "grad_norm": 4.9401080559619e-07,
      "learning_rate": 4.5135685617169965e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9029760,
      "step": 32230
    },
    {
      "epoch": 358.1666666666667,
      "grad_norm": 5.97580424255284e-07,
      "learning_rate": 4.507943349760313e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9031184,
      "step": 32235
    },
    {
      "epoch": 358.22222222222223,
      "grad_norm": 1.9935687305405736e-06,
      "learning_rate": 4.502321297936277e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9032592,
      "step": 32240
    },
    {
      "epoch": 358.27777777777777,
      "grad_norm": 4.811635108126211e-07,
      "learning_rate": 4.496702407111888e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9033968,
      "step": 32245
    },
    {
      "epoch": 358.3333333333333,
      "grad_norm": 5.581279651778459e-07,
      "learning_rate": 4.491086678153653e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9035440,
      "step": 32250
    },
    {
      "epoch": 358.3888888888889,
      "grad_norm": 9.92042146208405e-07,
      "learning_rate": 4.485474111927579e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9036832,
      "step": 32255
    },
    {
      "epoch": 358.44444444444446,
      "grad_norm": 6.302722681539308e-07,
      "learning_rate": 4.479864709299197e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9038240,
      "step": 32260
    },
    {
      "epoch": 358.5,
      "grad_norm": 5.02782029343507e-07,
      "learning_rate": 4.474258471133555e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9039648,
      "step": 32265
    },
    {
      "epoch": 358.55555555555554,
      "grad_norm": 4.900230692328478e-07,
      "learning_rate": 4.4686553982952014e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9041040,
      "step": 32270
    },
    {
      "epoch": 358.6111111111111,
      "grad_norm": 4.847758532378066e-07,
      "learning_rate": 4.463055491648191e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9042448,
      "step": 32275
    },
    {
      "epoch": 358.6666666666667,
      "grad_norm": 9.585825182512053e-07,
      "learning_rate": 4.457458752056112e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9043856,
      "step": 32280
    },
    {
      "epoch": 358.72222222222223,
      "grad_norm": 5.223473635851406e-07,
      "learning_rate": 4.451865180382042e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9045248,
      "step": 32285
    },
    {
      "epoch": 358.77777777777777,
      "grad_norm": 2.1656824173987843e-06,
      "learning_rate": 4.4462747774885936e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9046624,
      "step": 32290
    },
    {
      "epoch": 358.8333333333333,
      "grad_norm": 1.4832920669505256e-06,
      "learning_rate": 4.440687544237859e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9048016,
      "step": 32295
    },
    {
      "epoch": 358.8888888888889,
      "grad_norm": 5.389163106883643e-07,
      "learning_rate": 4.435103481491471e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9049408,
      "step": 32300
    },
    {
      "epoch": 358.94444444444446,
      "grad_norm": 5.09783717461687e-07,
      "learning_rate": 4.429522590110569e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9050816,
      "step": 32305
    },
    {
      "epoch": 359.0,
      "grad_norm": 9.991731531044934e-07,
      "learning_rate": 4.423944870955779e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9052176,
      "step": 32310
    },
    {
      "epoch": 359.05555555555554,
      "grad_norm": 6.396468279490364e-07,
      "learning_rate": 4.418370324887272e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9053616,
      "step": 32315
    },
    {
      "epoch": 359.1111111111111,
      "grad_norm": 1.5691898624936584e-06,
      "learning_rate": 4.412798952764699e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9055056,
      "step": 32320
    },
    {
      "epoch": 359.1666666666667,
      "grad_norm": 1.9909048205590807e-06,
      "learning_rate": 4.407230755447245e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9056448,
      "step": 32325
    },
    {
      "epoch": 359.22222222222223,
      "grad_norm": 1.0541356232351973e-06,
      "learning_rate": 4.401665733793598e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9057824,
      "step": 32330
    },
    {
      "epoch": 359.27777777777777,
      "grad_norm": 1.0063270110549638e-06,
      "learning_rate": 4.3961038886619425e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9059280,
      "step": 32335
    },
    {
      "epoch": 359.3333333333333,
      "grad_norm": 4.443928958153265e-07,
      "learning_rate": 4.39054522091e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9060656,
      "step": 32340
    },
    {
      "epoch": 359.3888888888889,
      "grad_norm": 6.460400072683115e-07,
      "learning_rate": 4.384989731394979e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9062048,
      "step": 32345
    },
    {
      "epoch": 359.44444444444446,
      "grad_norm": 2.784989646897884e-06,
      "learning_rate": 4.379437420973598e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9063440,
      "step": 32350
    },
    {
      "epoch": 359.5,
      "grad_norm": 1.5131648751776083e-06,
      "learning_rate": 4.373888290502107e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9064848,
      "step": 32355
    },
    {
      "epoch": 359.55555555555554,
      "grad_norm": 9.414316082256846e-07,
      "learning_rate": 4.36834234083624e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9066208,
      "step": 32360
    },
    {
      "epoch": 359.6111111111111,
      "grad_norm": 5.472720090438088e-07,
      "learning_rate": 4.362799572831258e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9067600,
      "step": 32365
    },
    {
      "epoch": 359.6666666666667,
      "grad_norm": 1.6782140619397978e-06,
      "learning_rate": 4.35725998734193e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9068976,
      "step": 32370
    },
    {
      "epoch": 359.72222222222223,
      "grad_norm": 5.226409598435566e-07,
      "learning_rate": 4.3517235852225195e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9070368,
      "step": 32375
    },
    {
      "epoch": 359.77777777777777,
      "grad_norm": 6.1224665159898e-07,
      "learning_rate": 4.346190367326822e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9071776,
      "step": 32380
    },
    {
      "epoch": 359.8333333333333,
      "grad_norm": 4.633443211332633e-07,
      "learning_rate": 4.340660334508115e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9073200,
      "step": 32385
    },
    {
      "epoch": 359.8888888888889,
      "grad_norm": 9.034795880324964e-07,
      "learning_rate": 4.335133487619206e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9074576,
      "step": 32390
    },
    {
      "epoch": 359.94444444444446,
      "grad_norm": 2.195861043219338e-06,
      "learning_rate": 4.329609827512409e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9076032,
      "step": 32395
    },
    {
      "epoch": 360.0,
      "grad_norm": 5.98681822339131e-07,
      "learning_rate": 4.324089355039531e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9077456,
      "step": 32400
    },
    {
      "epoch": 360.0,
      "eval_loss": 0.382182776927948,
      "eval_runtime": 1.2825,
      "eval_samples_per_second": 31.188,
      "eval_steps_per_second": 15.594,
      "num_input_tokens_seen": 9077456,
      "step": 32400
    },
    {
      "epoch": 360.05555555555554,
      "grad_norm": 6.086245889491693e-07,
      "learning_rate": 4.3185720710519075e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9078848,
      "step": 32405
    },
    {
      "epoch": 360.1111111111111,
      "grad_norm": 1.6421070085925749e-06,
      "learning_rate": 4.3130579764003724e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9080304,
      "step": 32410
    },
    {
      "epoch": 360.1666666666667,
      "grad_norm": 5.018803790335369e-07,
      "learning_rate": 4.307547071935267e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9081664,
      "step": 32415
    },
    {
      "epoch": 360.22222222222223,
      "grad_norm": 6.25270331511274e-07,
      "learning_rate": 4.302039358506435e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9083072,
      "step": 32420
    },
    {
      "epoch": 360.27777777777777,
      "grad_norm": 9.268878784496337e-07,
      "learning_rate": 4.296534836963245e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9084464,
      "step": 32425
    },
    {
      "epoch": 360.3333333333333,
      "grad_norm": 5.455874543258687e-07,
      "learning_rate": 4.291033508154555e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9085904,
      "step": 32430
    },
    {
      "epoch": 360.3888888888889,
      "grad_norm": 6.651100648014108e-07,
      "learning_rate": 4.285535372928748e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9087296,
      "step": 32435
    },
    {
      "epoch": 360.44444444444446,
      "grad_norm": 3.178258111802279e-06,
      "learning_rate": 4.280040432133695e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9088672,
      "step": 32440
    },
    {
      "epoch": 360.5,
      "grad_norm": 5.578208970291598e-07,
      "learning_rate": 4.274548686616789e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9090064,
      "step": 32445
    },
    {
      "epoch": 360.55555555555554,
      "grad_norm": 5.784204404335469e-07,
      "learning_rate": 4.2690601372249364e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9091504,
      "step": 32450
    },
    {
      "epoch": 360.6111111111111,
      "grad_norm": 9.558010560795083e-07,
      "learning_rate": 4.263574784804525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9092896,
      "step": 32455
    },
    {
      "epoch": 360.6666666666667,
      "grad_norm": 5.420588991000841e-07,
      "learning_rate": 4.258092630201479e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9094256,
      "step": 32460
    },
    {
      "epoch": 360.72222222222223,
      "grad_norm": 5.122971629134554e-07,
      "learning_rate": 4.252613674261202e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9095632,
      "step": 32465
    },
    {
      "epoch": 360.77777777777777,
      "grad_norm": 5.571429824158258e-07,
      "learning_rate": 4.2471379178286224e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9096976,
      "step": 32470
    },
    {
      "epoch": 360.8333333333333,
      "grad_norm": 6.383449431268673e-07,
      "learning_rate": 4.241665361748181e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9098384,
      "step": 32475
    },
    {
      "epoch": 360.8888888888889,
      "grad_norm": 9.435791525902459e-07,
      "learning_rate": 4.2361960068637994e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9099792,
      "step": 32480
    },
    {
      "epoch": 360.94444444444446,
      "grad_norm": 5.793281161459163e-07,
      "learning_rate": 4.230729854018933e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9101232,
      "step": 32485
    },
    {
      "epoch": 361.0,
      "grad_norm": 1.530876147626259e-06,
      "learning_rate": 4.225266904056521e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9102656,
      "step": 32490
    },
    {
      "epoch": 361.05555555555554,
      "grad_norm": 5.88082684771507e-07,
      "learning_rate": 4.21980715781903e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9104000,
      "step": 32495
    },
    {
      "epoch": 361.1111111111111,
      "grad_norm": 1.0556217375778942e-06,
      "learning_rate": 4.214350616148416e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9105408,
      "step": 32500
    },
    {
      "epoch": 361.1666666666667,
      "grad_norm": 4.7137001502051135e-07,
      "learning_rate": 4.20889727988614e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9106800,
      "step": 32505
    },
    {
      "epoch": 361.22222222222223,
      "grad_norm": 4.897609642284806e-07,
      "learning_rate": 4.20344714987318e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9108272,
      "step": 32510
    },
    {
      "epoch": 361.27777777777777,
      "grad_norm": 5.742428470512095e-07,
      "learning_rate": 4.198000226950022e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9109680,
      "step": 32515
    },
    {
      "epoch": 361.3333333333333,
      "grad_norm": 1.0178937372984365e-06,
      "learning_rate": 4.192556511956635e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9111072,
      "step": 32520
    },
    {
      "epoch": 361.3888888888889,
      "grad_norm": 6.128475433797576e-07,
      "learning_rate": 4.18711600573252e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9112480,
      "step": 32525
    },
    {
      "epoch": 361.44444444444446,
      "grad_norm": 9.09792106540408e-07,
      "learning_rate": 4.181678709116671e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9113840,
      "step": 32530
    },
    {
      "epoch": 361.5,
      "grad_norm": 2.210522779932944e-06,
      "learning_rate": 4.1762446229475785e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9115232,
      "step": 32535
    },
    {
      "epoch": 361.55555555555554,
      "grad_norm": 5.199412953516003e-07,
      "learning_rate": 4.17081374806326e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9116656,
      "step": 32540
    },
    {
      "epoch": 361.6111111111111,
      "grad_norm": 9.310314226240735e-07,
      "learning_rate": 4.165386085301212e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9118064,
      "step": 32545
    },
    {
      "epoch": 361.6666666666667,
      "grad_norm": 5.995629521748924e-07,
      "learning_rate": 4.1599616354984525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9119504,
      "step": 32550
    },
    {
      "epoch": 361.72222222222223,
      "grad_norm": 5.596717187472677e-07,
      "learning_rate": 4.154540399491508e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9120928,
      "step": 32555
    },
    {
      "epoch": 361.77777777777777,
      "grad_norm": 4.5206112986306835e-07,
      "learning_rate": 4.149122378116394e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9122272,
      "step": 32560
    },
    {
      "epoch": 361.8333333333333,
      "grad_norm": 1.1812270486188936e-06,
      "learning_rate": 4.14370757220863e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9123680,
      "step": 32565
    },
    {
      "epoch": 361.8888888888889,
      "grad_norm": 9.28657300391933e-07,
      "learning_rate": 4.138295982603263e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9125136,
      "step": 32570
    },
    {
      "epoch": 361.94444444444446,
      "grad_norm": 8.545108016733138e-07,
      "learning_rate": 4.132887610134814e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9126560,
      "step": 32575
    },
    {
      "epoch": 362.0,
      "grad_norm": 5.473513624565385e-07,
      "learning_rate": 4.127482455637335e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9127984,
      "step": 32580
    },
    {
      "epoch": 362.05555555555554,
      "grad_norm": 6.157832785902428e-07,
      "learning_rate": 4.1220805199443545e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9129392,
      "step": 32585
    },
    {
      "epoch": 362.1111111111111,
      "grad_norm": 4.65562351337212e-07,
      "learning_rate": 4.116681803888925e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9130768,
      "step": 32590
    },
    {
      "epoch": 362.1666666666667,
      "grad_norm": 1.5361684972958756e-06,
      "learning_rate": 4.111286308303605e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9132224,
      "step": 32595
    },
    {
      "epoch": 362.22222222222223,
      "grad_norm": 5.290434273774736e-06,
      "learning_rate": 4.105894034020433e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9133648,
      "step": 32600
    },
    {
      "epoch": 362.22222222222223,
      "eval_loss": 0.3347680866718292,
      "eval_runtime": 1.2964,
      "eval_samples_per_second": 30.855,
      "eval_steps_per_second": 15.427,
      "num_input_tokens_seen": 9133648,
      "step": 32600
    },
    {
      "epoch": 362.27777777777777,
      "grad_norm": 5.775939939667296e-07,
      "learning_rate": 4.100504981870975e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9135056,
      "step": 32605
    },
    {
      "epoch": 362.3333333333333,
      "grad_norm": 5.753018399445864e-07,
      "learning_rate": 4.0951191526862915e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9136384,
      "step": 32610
    },
    {
      "epoch": 362.3888888888889,
      "grad_norm": 5.524680659618753e-07,
      "learning_rate": 4.089736547296938e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9137760,
      "step": 32615
    },
    {
      "epoch": 362.44444444444446,
      "grad_norm": 6.551109095198626e-07,
      "learning_rate": 4.08435716653299e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9139088,
      "step": 32620
    },
    {
      "epoch": 362.5,
      "grad_norm": 9.799492772799567e-07,
      "learning_rate": 4.0789810112240005e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9140496,
      "step": 32625
    },
    {
      "epoch": 362.55555555555554,
      "grad_norm": 5.661801196765737e-07,
      "learning_rate": 4.073608082199057e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9141872,
      "step": 32630
    },
    {
      "epoch": 362.6111111111111,
      "grad_norm": 1.965059482245124e-06,
      "learning_rate": 4.068238380286718e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9143264,
      "step": 32635
    },
    {
      "epoch": 362.6666666666667,
      "grad_norm": 5.999092422825925e-07,
      "learning_rate": 4.062871906315072e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9144672,
      "step": 32640
    },
    {
      "epoch": 362.72222222222223,
      "grad_norm": 4.816052978640073e-07,
      "learning_rate": 4.057508661111686e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9145984,
      "step": 32645
    },
    {
      "epoch": 362.77777777777777,
      "grad_norm": 5.7940377473642e-07,
      "learning_rate": 4.052148645503648e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9147424,
      "step": 32650
    },
    {
      "epoch": 362.8333333333333,
      "grad_norm": 5.693899538528058e-07,
      "learning_rate": 4.046791860317531e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9148832,
      "step": 32655
    },
    {
      "epoch": 362.8888888888889,
      "grad_norm": 5.833419436385157e-07,
      "learning_rate": 4.041438306379431e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9150256,
      "step": 32660
    },
    {
      "epoch": 362.94444444444446,
      "grad_norm": 5.531654210244596e-07,
      "learning_rate": 4.036087984514916e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9151696,
      "step": 32665
    },
    {
      "epoch": 363.0,
      "grad_norm": 1.0172492466153926e-06,
      "learning_rate": 4.030740895549084e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9153136,
      "step": 32670
    },
    {
      "epoch": 363.05555555555554,
      "grad_norm": 4.2579085857141763e-07,
      "learning_rate": 4.025397040306531e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9154528,
      "step": 32675
    },
    {
      "epoch": 363.1111111111111,
      "grad_norm": 9.562519380779122e-07,
      "learning_rate": 4.0200564196113285e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9155904,
      "step": 32680
    },
    {
      "epoch": 363.1666666666667,
      "grad_norm": 6.305625674940529e-07,
      "learning_rate": 4.014719034287079e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9157296,
      "step": 32685
    },
    {
      "epoch": 363.22222222222223,
      "grad_norm": 5.584764721788815e-07,
      "learning_rate": 4.0093848851568775e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9158688,
      "step": 32690
    },
    {
      "epoch": 363.27777777777777,
      "grad_norm": 4.021003690013458e-07,
      "learning_rate": 4.004053973043304e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9160080,
      "step": 32695
    },
    {
      "epoch": 363.3333333333333,
      "grad_norm": 5.608031301562733e-07,
      "learning_rate": 3.998726298768465e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9161488,
      "step": 32700
    },
    {
      "epoch": 363.3888888888889,
      "grad_norm": 4.727336602172727e-07,
      "learning_rate": 3.99340186315395e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9162880,
      "step": 32705
    },
    {
      "epoch": 363.44444444444446,
      "grad_norm": 9.51527454162715e-07,
      "learning_rate": 3.988080667020849e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9164320,
      "step": 32710
    },
    {
      "epoch": 363.5,
      "grad_norm": 4.697926669905428e-07,
      "learning_rate": 3.982762711189766e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9165712,
      "step": 32715
    },
    {
      "epoch": 363.55555555555554,
      "grad_norm": 5.953102117928211e-07,
      "learning_rate": 3.977447996480785e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9167072,
      "step": 32720
    },
    {
      "epoch": 363.6111111111111,
      "grad_norm": 2.1720329641539138e-06,
      "learning_rate": 3.97213652371351e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9168448,
      "step": 32725
    },
    {
      "epoch": 363.6666666666667,
      "grad_norm": 9.186507554659329e-07,
      "learning_rate": 3.966828293707042e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9169856,
      "step": 32730
    },
    {
      "epoch": 363.72222222222223,
      "grad_norm": 5.110559300192108e-07,
      "learning_rate": 3.961523307279963e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9171248,
      "step": 32735
    },
    {
      "epoch": 363.77777777777777,
      "grad_norm": 9.942522183337132e-07,
      "learning_rate": 3.956221565250382e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9172656,
      "step": 32740
    },
    {
      "epoch": 363.8333333333333,
      "grad_norm": 5.298376777318481e-07,
      "learning_rate": 3.950923068435883e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9174064,
      "step": 32745
    },
    {
      "epoch": 363.8888888888889,
      "grad_norm": 5.524092330233543e-07,
      "learning_rate": 3.945627817653566e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9175456,
      "step": 32750
    },
    {
      "epoch": 363.94444444444446,
      "grad_norm": 5.68912867038307e-07,
      "learning_rate": 3.9403358137200335e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9176928,
      "step": 32755
    },
    {
      "epoch": 364.0,
      "grad_norm": 2.2917060960025992e-06,
      "learning_rate": 3.9350470574513605e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9178320,
      "step": 32760
    },
    {
      "epoch": 364.05555555555554,
      "grad_norm": 5.993634886181098e-07,
      "learning_rate": 3.9297615496631525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9179728,
      "step": 32765
    },
    {
      "epoch": 364.1111111111111,
      "grad_norm": 1.0206518936684006e-06,
      "learning_rate": 3.924479291170505e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9181216,
      "step": 32770
    },
    {
      "epoch": 364.1666666666667,
      "grad_norm": 5.425589506558026e-07,
      "learning_rate": 3.919200282788002e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9182592,
      "step": 32775
    },
    {
      "epoch": 364.22222222222223,
      "grad_norm": 1.5183443338173674e-06,
      "learning_rate": 3.913924525329726e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9183984,
      "step": 32780
    },
    {
      "epoch": 364.27777777777777,
      "grad_norm": 3.2239570373349125e-06,
      "learning_rate": 3.908652019609279e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9185408,
      "step": 32785
    },
    {
      "epoch": 364.3333333333333,
      "grad_norm": 5.522510946320836e-07,
      "learning_rate": 3.9033827664397364e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9186784,
      "step": 32790
    },
    {
      "epoch": 364.3888888888889,
      "grad_norm": 5.433222440842655e-07,
      "learning_rate": 3.898116766633694e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9188192,
      "step": 32795
    },
    {
      "epoch": 364.44444444444446,
      "grad_norm": 1.6761952110755374e-06,
      "learning_rate": 3.8928540210032225e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9189616,
      "step": 32800
    },
    {
      "epoch": 364.44444444444446,
      "eval_loss": 0.384141206741333,
      "eval_runtime": 1.2928,
      "eval_samples_per_second": 30.941,
      "eval_steps_per_second": 15.471,
      "num_input_tokens_seen": 9189616,
      "step": 32800
    },
    {
      "epoch": 364.5,
      "grad_norm": 6.709349804623344e-07,
      "learning_rate": 3.887594530359909e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9191040,
      "step": 32805
    },
    {
      "epoch": 364.55555555555554,
      "grad_norm": 5.897809955968114e-07,
      "learning_rate": 3.88233829551484e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9192432,
      "step": 32810
    },
    {
      "epoch": 364.6111111111111,
      "grad_norm": 3.531381480570417e-06,
      "learning_rate": 3.877085317278581e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9193808,
      "step": 32815
    },
    {
      "epoch": 364.6666666666667,
      "grad_norm": 5.613552502836683e-07,
      "learning_rate": 3.87183559646122e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9195184,
      "step": 32820
    },
    {
      "epoch": 364.72222222222223,
      "grad_norm": 5.417878128355369e-07,
      "learning_rate": 3.866589133872317e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9196576,
      "step": 32825
    },
    {
      "epoch": 364.77777777777777,
      "grad_norm": 4.711316989869374e-07,
      "learning_rate": 3.861345930320948e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9197952,
      "step": 32830
    },
    {
      "epoch": 364.8333333333333,
      "grad_norm": 8.610105624029529e-07,
      "learning_rate": 3.856105986615688e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9199360,
      "step": 32835
    },
    {
      "epoch": 364.8888888888889,
      "grad_norm": 5.42120176305616e-07,
      "learning_rate": 3.850869303564589e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9200800,
      "step": 32840
    },
    {
      "epoch": 364.94444444444446,
      "grad_norm": 1.039707626659947e-06,
      "learning_rate": 3.845635881975226e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9202144,
      "step": 32845
    },
    {
      "epoch": 365.0,
      "grad_norm": 2.0626905552489916e-06,
      "learning_rate": 3.840405722654647e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9203520,
      "step": 32850
    },
    {
      "epoch": 365.05555555555554,
      "grad_norm": 8.770413728598214e-07,
      "learning_rate": 3.835178826409419e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9204928,
      "step": 32855
    },
    {
      "epoch": 365.1111111111111,
      "grad_norm": 9.434865546609217e-07,
      "learning_rate": 3.8299551940455895e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9206304,
      "step": 32860
    },
    {
      "epoch": 365.1666666666667,
      "grad_norm": 4.842455041398352e-07,
      "learning_rate": 3.824734826368703e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9207680,
      "step": 32865
    },
    {
      "epoch": 365.22222222222223,
      "grad_norm": 2.154621142835822e-06,
      "learning_rate": 3.819517724183813e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9209152,
      "step": 32870
    },
    {
      "epoch": 365.27777777777777,
      "grad_norm": 3.491761162877083e-06,
      "learning_rate": 3.8143038882954648e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9210560,
      "step": 32875
    },
    {
      "epoch": 365.3333333333333,
      "grad_norm": 5.44443082617363e-07,
      "learning_rate": 3.8090933195076867e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9212016,
      "step": 32880
    },
    {
      "epoch": 365.3888888888889,
      "grad_norm": 4.3101206870233e-07,
      "learning_rate": 3.8038860186240198e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9213456,
      "step": 32885
    },
    {
      "epoch": 365.44444444444446,
      "grad_norm": 9.240492886419815e-07,
      "learning_rate": 3.7986819864475026e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9214816,
      "step": 32890
    },
    {
      "epoch": 365.5,
      "grad_norm": 9.419356956641423e-07,
      "learning_rate": 3.793481223780651e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9216240,
      "step": 32895
    },
    {
      "epoch": 365.55555555555554,
      "grad_norm": 2.229784968221793e-06,
      "learning_rate": 3.788283731425496e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9217648,
      "step": 32900
    },
    {
      "epoch": 365.6111111111111,
      "grad_norm": 5.826244091622357e-07,
      "learning_rate": 3.7830895101835488e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9219040,
      "step": 32905
    },
    {
      "epoch": 365.6666666666667,
      "grad_norm": 6.271633310461766e-07,
      "learning_rate": 3.7778985608558274e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9220480,
      "step": 32910
    },
    {
      "epoch": 365.72222222222223,
      "grad_norm": 6.500600875369855e-07,
      "learning_rate": 3.7727108842428443e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9221872,
      "step": 32915
    },
    {
      "epoch": 365.77777777777777,
      "grad_norm": 1.0437022410769714e-06,
      "learning_rate": 3.7675264811446065e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9223264,
      "step": 32920
    },
    {
      "epoch": 365.8333333333333,
      "grad_norm": 6.542838946188567e-07,
      "learning_rate": 3.7623453523605994e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9224656,
      "step": 32925
    },
    {
      "epoch": 365.8888888888889,
      "grad_norm": 1.651495267651626e-06,
      "learning_rate": 3.757167498689834e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9226000,
      "step": 32930
    },
    {
      "epoch": 365.94444444444446,
      "grad_norm": 5.965197260593413e-07,
      "learning_rate": 3.7519929209307914e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9227360,
      "step": 32935
    },
    {
      "epoch": 366.0,
      "grad_norm": 5.706450565412524e-07,
      "learning_rate": 3.746821619881463e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9228736,
      "step": 32940
    },
    {
      "epoch": 366.05555555555554,
      "grad_norm": 1.5338177945523057e-06,
      "learning_rate": 3.74165359633932e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9230144,
      "step": 32945
    },
    {
      "epoch": 366.1111111111111,
      "grad_norm": 1.7004770143103087e-06,
      "learning_rate": 3.736488851101341e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9231552,
      "step": 32950
    },
    {
      "epoch": 366.1666666666667,
      "grad_norm": 5.970721304038307e-07,
      "learning_rate": 3.7313273849640035e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9232928,
      "step": 32955
    },
    {
      "epoch": 366.22222222222223,
      "grad_norm": 9.518793149254634e-07,
      "learning_rate": 3.7261691987232533e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9234320,
      "step": 32960
    },
    {
      "epoch": 366.27777777777777,
      "grad_norm": 5.75052865769976e-07,
      "learning_rate": 3.7210142931745575e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9235664,
      "step": 32965
    },
    {
      "epoch": 366.3333333333333,
      "grad_norm": 5.193483616494632e-07,
      "learning_rate": 3.7158626691128712e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9237056,
      "step": 32970
    },
    {
      "epoch": 366.3888888888889,
      "grad_norm": 5.59344073280954e-07,
      "learning_rate": 3.710714327332629e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9238432,
      "step": 32975
    },
    {
      "epoch": 366.44444444444446,
      "grad_norm": 9.572980843586265e-07,
      "learning_rate": 3.7055692686277815e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9239840,
      "step": 32980
    },
    {
      "epoch": 366.5,
      "grad_norm": 9.001308285405685e-07,
      "learning_rate": 3.70042749379175e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9241232,
      "step": 32985
    },
    {
      "epoch": 366.55555555555554,
      "grad_norm": 6.088245640967216e-07,
      "learning_rate": 3.6952890036174693e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9242640,
      "step": 32990
    },
    {
      "epoch": 366.6111111111111,
      "grad_norm": 6.644433483415924e-07,
      "learning_rate": 3.690153798897353e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9244096,
      "step": 32995
    },
    {
      "epoch": 366.6666666666667,
      "grad_norm": 5.891138243896421e-07,
      "learning_rate": 3.6850218804233225e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9245504,
      "step": 33000
    },
    {
      "epoch": 366.6666666666667,
      "eval_loss": 0.37106671929359436,
      "eval_runtime": 1.2914,
      "eval_samples_per_second": 30.973,
      "eval_steps_per_second": 15.487,
      "num_input_tokens_seen": 9245504,
      "step": 33000
    },
    {
      "epoch": 366.72222222222223,
      "grad_norm": 4.963853825756814e-07,
      "learning_rate": 3.679893248986779e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9246896,
      "step": 33005
    },
    {
      "epoch": 366.77777777777777,
      "grad_norm": 4.7461273311455443e-07,
      "learning_rate": 3.6747679053786147e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9248336,
      "step": 33010
    },
    {
      "epoch": 366.8333333333333,
      "grad_norm": 6.442119229177479e-07,
      "learning_rate": 3.669645850389228e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9249760,
      "step": 33015
    },
    {
      "epoch": 366.8888888888889,
      "grad_norm": 6.13064230492455e-07,
      "learning_rate": 3.664527084808514e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9251136,
      "step": 33020
    },
    {
      "epoch": 366.94444444444446,
      "grad_norm": 4.438419409780181e-07,
      "learning_rate": 3.6594116094258337e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9252512,
      "step": 33025
    },
    {
      "epoch": 367.0,
      "grad_norm": 6.249945840863802e-07,
      "learning_rate": 3.6542994250300665e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9253952,
      "step": 33030
    },
    {
      "epoch": 367.05555555555554,
      "grad_norm": 5.393097808337188e-07,
      "learning_rate": 3.6491905324095825e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9255360,
      "step": 33035
    },
    {
      "epoch": 367.1111111111111,
      "grad_norm": 9.241858833775041e-07,
      "learning_rate": 3.644084932352221e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9256704,
      "step": 33040
    },
    {
      "epoch": 367.1666666666667,
      "grad_norm": 5.384429755395104e-07,
      "learning_rate": 3.6389826256453457e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9258096,
      "step": 33045
    },
    {
      "epoch": 367.22222222222223,
      "grad_norm": 6.217267696229101e-07,
      "learning_rate": 3.633883613075781e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9259488,
      "step": 33050
    },
    {
      "epoch": 367.27777777777777,
      "grad_norm": 2.225131083832821e-06,
      "learning_rate": 3.6287878954298693e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9260880,
      "step": 33055
    },
    {
      "epoch": 367.3333333333333,
      "grad_norm": 8.997363352136745e-07,
      "learning_rate": 3.6236954734934354e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9262320,
      "step": 33060
    },
    {
      "epoch": 367.3888888888889,
      "grad_norm": 6.036686386323709e-07,
      "learning_rate": 3.618606348051784e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9263696,
      "step": 33065
    },
    {
      "epoch": 367.44444444444446,
      "grad_norm": 1.7284953628404764e-06,
      "learning_rate": 3.6135205198897376e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9265072,
      "step": 33070
    },
    {
      "epoch": 367.5,
      "grad_norm": 6.18975946053979e-07,
      "learning_rate": 3.6084379897915854e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9266480,
      "step": 33075
    },
    {
      "epoch": 367.55555555555554,
      "grad_norm": 1.5027228528197156e-06,
      "learning_rate": 3.6033587585411115e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9267920,
      "step": 33080
    },
    {
      "epoch": 367.6111111111111,
      "grad_norm": 1.631236273169634e-06,
      "learning_rate": 3.5982828269216117e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9269328,
      "step": 33085
    },
    {
      "epoch": 367.6666666666667,
      "grad_norm": 4.388095362628519e-07,
      "learning_rate": 3.593210195715843e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9270736,
      "step": 33090
    },
    {
      "epoch": 367.72222222222223,
      "grad_norm": 5.960503699498076e-07,
      "learning_rate": 3.5881408657060773e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9272128,
      "step": 33095
    },
    {
      "epoch": 367.77777777777777,
      "grad_norm": 4.6517780560861866e-07,
      "learning_rate": 3.583074837674075e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9273488,
      "step": 33100
    },
    {
      "epoch": 367.8333333333333,
      "grad_norm": 5.25083351021749e-07,
      "learning_rate": 3.578012112401069e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9274928,
      "step": 33105
    },
    {
      "epoch": 367.8888888888889,
      "grad_norm": 3.0692258405906614e-06,
      "learning_rate": 3.5729526906677996e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9276400,
      "step": 33110
    },
    {
      "epoch": 367.94444444444446,
      "grad_norm": 9.502757052359811e-07,
      "learning_rate": 3.5678965732545007e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9277776,
      "step": 33115
    },
    {
      "epoch": 368.0,
      "grad_norm": 9.212139957526233e-07,
      "learning_rate": 3.562843760940876e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9279200,
      "step": 33120
    },
    {
      "epoch": 368.05555555555554,
      "grad_norm": 5.983713435853133e-07,
      "learning_rate": 3.5577942545061473e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9280608,
      "step": 33125
    },
    {
      "epoch": 368.1111111111111,
      "grad_norm": 5.511926701728953e-07,
      "learning_rate": 3.5527480547289967e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9281984,
      "step": 33130
    },
    {
      "epoch": 368.1666666666667,
      "grad_norm": 1.7177536619783496e-06,
      "learning_rate": 3.547705162387624e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9283408,
      "step": 33135
    },
    {
      "epoch": 368.22222222222223,
      "grad_norm": 4.257476575730834e-07,
      "learning_rate": 3.542665578259699e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9284800,
      "step": 33140
    },
    {
      "epoch": 368.27777777777777,
      "grad_norm": 5.526979975911672e-07,
      "learning_rate": 3.5376293031223945e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9286208,
      "step": 33145
    },
    {
      "epoch": 368.3333333333333,
      "grad_norm": 6.673488428532437e-07,
      "learning_rate": 3.5325963377523614e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9287568,
      "step": 33150
    },
    {
      "epoch": 368.3888888888889,
      "grad_norm": 1.0482933703315211e-06,
      "learning_rate": 3.5275666829257536e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9288992,
      "step": 33155
    },
    {
      "epoch": 368.44444444444446,
      "grad_norm": 6.048048817319795e-07,
      "learning_rate": 3.5225403394181955e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9290384,
      "step": 33160
    },
    {
      "epoch": 368.5,
      "grad_norm": 5.445230613077001e-07,
      "learning_rate": 3.517517308004828e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9291824,
      "step": 33165
    },
    {
      "epoch": 368.55555555555554,
      "grad_norm": 1.62346884735598e-06,
      "learning_rate": 3.512497589460251e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9293248,
      "step": 33170
    },
    {
      "epoch": 368.6111111111111,
      "grad_norm": 1.5192003957054112e-06,
      "learning_rate": 3.5074811845585727e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9294624,
      "step": 33175
    },
    {
      "epoch": 368.6666666666667,
      "grad_norm": 5.462494527819217e-07,
      "learning_rate": 3.5024680940733937e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9295984,
      "step": 33180
    },
    {
      "epoch": 368.72222222222223,
      "grad_norm": 6.034908892615931e-07,
      "learning_rate": 3.4974583187777852e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9297392,
      "step": 33185
    },
    {
      "epoch": 368.77777777777777,
      "grad_norm": 5.565772767113231e-07,
      "learning_rate": 3.4924518594443204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9298752,
      "step": 33190
    },
    {
      "epoch": 368.8333333333333,
      "grad_norm": 5.959176974101865e-07,
      "learning_rate": 3.4874487168450682e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9300112,
      "step": 33195
    },
    {
      "epoch": 368.8888888888889,
      "grad_norm": 5.764037496192032e-07,
      "learning_rate": 3.482448891751558e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9301520,
      "step": 33200
    },
    {
      "epoch": 368.8888888888889,
      "eval_loss": 0.349362313747406,
      "eval_runtime": 1.2908,
      "eval_samples_per_second": 30.988,
      "eval_steps_per_second": 15.494,
      "num_input_tokens_seen": 9301520,
      "step": 33200
    },
    {
      "epoch": 368.94444444444446,
      "grad_norm": 5.941429321865144e-07,
      "learning_rate": 3.477452384934843e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9302976,
      "step": 33205
    },
    {
      "epoch": 369.0,
      "grad_norm": 4.551696974885999e-07,
      "learning_rate": 3.472459197165434e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9304400,
      "step": 33210
    },
    {
      "epoch": 369.05555555555554,
      "grad_norm": 5.728253427150776e-07,
      "learning_rate": 3.4674693292133518e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9305840,
      "step": 33215
    },
    {
      "epoch": 369.1111111111111,
      "grad_norm": 5.568942924583098e-07,
      "learning_rate": 3.4624827818480977e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9307216,
      "step": 33220
    },
    {
      "epoch": 369.1666666666667,
      "grad_norm": 8.912758744372695e-07,
      "learning_rate": 3.4574995558386474e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9308624,
      "step": 33225
    },
    {
      "epoch": 369.22222222222223,
      "grad_norm": 9.574768000675249e-07,
      "learning_rate": 3.452519651953487e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9310032,
      "step": 33230
    },
    {
      "epoch": 369.27777777777777,
      "grad_norm": 5.61778051633155e-07,
      "learning_rate": 3.447543070960585e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9311440,
      "step": 33235
    },
    {
      "epoch": 369.3333333333333,
      "grad_norm": 1.928761321323691e-06,
      "learning_rate": 3.4425698136273778e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9312864,
      "step": 33240
    },
    {
      "epoch": 369.3888888888889,
      "grad_norm": 4.990178581465443e-07,
      "learning_rate": 3.437599880720821e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9314304,
      "step": 33245
    },
    {
      "epoch": 369.44444444444446,
      "grad_norm": 5.868170092071523e-07,
      "learning_rate": 3.4326332730073267e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9315680,
      "step": 33250
    },
    {
      "epoch": 369.5,
      "grad_norm": 6.009639150761359e-07,
      "learning_rate": 3.427669991252813e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9317056,
      "step": 33255
    },
    {
      "epoch": 369.55555555555554,
      "grad_norm": 5.992054639136768e-07,
      "learning_rate": 3.42271003622269e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9318448,
      "step": 33260
    },
    {
      "epoch": 369.6111111111111,
      "grad_norm": 6.032395276633906e-07,
      "learning_rate": 3.4177534086818286e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9319824,
      "step": 33265
    },
    {
      "epoch": 369.6666666666667,
      "grad_norm": 1.0196278026342043e-06,
      "learning_rate": 3.412800109394612e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9321296,
      "step": 33270
    },
    {
      "epoch": 369.72222222222223,
      "grad_norm": 1.6596302430116339e-06,
      "learning_rate": 3.4078501391249044e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9322688,
      "step": 33275
    },
    {
      "epoch": 369.77777777777777,
      "grad_norm": 5.296477638694341e-07,
      "learning_rate": 3.4029034986360453e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9324096,
      "step": 33280
    },
    {
      "epoch": 369.8333333333333,
      "grad_norm": 4.6920558816054836e-07,
      "learning_rate": 3.397960188690877e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9325456,
      "step": 33285
    },
    {
      "epoch": 369.8888888888889,
      "grad_norm": 2.0411109744600253e-06,
      "learning_rate": 3.393020210051717e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9326848,
      "step": 33290
    },
    {
      "epoch": 369.94444444444446,
      "grad_norm": 3.1940019198373193e-06,
      "learning_rate": 3.3880835634803655e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9328288,
      "step": 33295
    },
    {
      "epoch": 370.0,
      "grad_norm": 6.203895850376284e-07,
      "learning_rate": 3.383150249738126e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9329712,
      "step": 33300
    },
    {
      "epoch": 370.05555555555554,
      "grad_norm": 8.942089380070684e-07,
      "learning_rate": 3.3782202695857663e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9331120,
      "step": 33305
    },
    {
      "epoch": 370.1111111111111,
      "grad_norm": 5.541209588955098e-07,
      "learning_rate": 3.373293623783558e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9332528,
      "step": 33310
    },
    {
      "epoch": 370.1666666666667,
      "grad_norm": 1.0381910442447406e-06,
      "learning_rate": 3.368370313091257e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9333968,
      "step": 33315
    },
    {
      "epoch": 370.22222222222223,
      "grad_norm": 5.076952334093221e-07,
      "learning_rate": 3.363450338268087e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9335344,
      "step": 33320
    },
    {
      "epoch": 370.27777777777777,
      "grad_norm": 5.62704656204005e-07,
      "learning_rate": 3.358533700072783e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9336720,
      "step": 33325
    },
    {
      "epoch": 370.3333333333333,
      "grad_norm": 6.197461175361241e-07,
      "learning_rate": 3.3536203992635377e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9338160,
      "step": 33330
    },
    {
      "epoch": 370.3888888888889,
      "grad_norm": 1.641654876038956e-06,
      "learning_rate": 3.348710436598057e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9339584,
      "step": 33335
    },
    {
      "epoch": 370.44444444444446,
      "grad_norm": 8.460508524876786e-07,
      "learning_rate": 3.3438038128335155e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9340992,
      "step": 33340
    },
    {
      "epoch": 370.5,
      "grad_norm": 6.204816713761829e-07,
      "learning_rate": 3.338900528726571e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9342400,
      "step": 33345
    },
    {
      "epoch": 370.55555555555554,
      "grad_norm": 1.6606312556177727e-06,
      "learning_rate": 3.3340005850333812e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9343760,
      "step": 33350
    },
    {
      "epoch": 370.6111111111111,
      "grad_norm": 1.6382279000026756e-06,
      "learning_rate": 3.329103982509568e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9345152,
      "step": 33355
    },
    {
      "epoch": 370.6666666666667,
      "grad_norm": 5.754030780735775e-07,
      "learning_rate": 3.324210721910259e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9346528,
      "step": 33360
    },
    {
      "epoch": 370.72222222222223,
      "grad_norm": 5.289371074468363e-07,
      "learning_rate": 3.319320803990053e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9347920,
      "step": 33365
    },
    {
      "epoch": 370.77777777777777,
      "grad_norm": 4.946551825923962e-07,
      "learning_rate": 3.3144342295030274e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9349296,
      "step": 33370
    },
    {
      "epoch": 370.8333333333333,
      "grad_norm": 1.6976421193248825e-06,
      "learning_rate": 3.309550999202765e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9350656,
      "step": 33375
    },
    {
      "epoch": 370.8888888888889,
      "grad_norm": 5.083767860014632e-07,
      "learning_rate": 3.3046711138423197e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9352064,
      "step": 33380
    },
    {
      "epoch": 370.94444444444446,
      "grad_norm": 3.852666452530684e-07,
      "learning_rate": 3.2997945741742255e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9353472,
      "step": 33385
    },
    {
      "epoch": 371.0,
      "grad_norm": 6.080601337998814e-07,
      "learning_rate": 3.2949213809505082e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9354896,
      "step": 33390
    },
    {
      "epoch": 371.05555555555554,
      "grad_norm": 5.649030185850279e-07,
      "learning_rate": 3.2900515349226834e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9356288,
      "step": 33395
    },
    {
      "epoch": 371.1111111111111,
      "grad_norm": 1.0878781040446484e-06,
      "learning_rate": 3.285185036841731e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9357712,
      "step": 33400
    },
    {
      "epoch": 371.1111111111111,
      "eval_loss": 0.33894291520118713,
      "eval_runtime": 1.2912,
      "eval_samples_per_second": 30.979,
      "eval_steps_per_second": 15.49,
      "num_input_tokens_seen": 9357712,
      "step": 33400
    },
    {
      "epoch": 371.1666666666667,
      "grad_norm": 6.308648039521358e-07,
      "learning_rate": 3.2803218874581377e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9359120,
      "step": 33405
    },
    {
      "epoch": 371.22222222222223,
      "grad_norm": 6.321214414128917e-07,
      "learning_rate": 3.2754620875218494e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9360560,
      "step": 33410
    },
    {
      "epoch": 371.27777777777777,
      "grad_norm": 6.143599193819682e-07,
      "learning_rate": 3.2706056377823146e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9361888,
      "step": 33415
    },
    {
      "epoch": 371.3333333333333,
      "grad_norm": 5.804306510981405e-07,
      "learning_rate": 3.2657525389884647e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9363296,
      "step": 33420
    },
    {
      "epoch": 371.3888888888889,
      "grad_norm": 4.328850593537936e-07,
      "learning_rate": 3.260902791888698e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9364720,
      "step": 33425
    },
    {
      "epoch": 371.44444444444446,
      "grad_norm": 5.188000500311318e-07,
      "learning_rate": 3.2560563972309166e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9366160,
      "step": 33430
    },
    {
      "epoch": 371.5,
      "grad_norm": 3.5105260849377373e-06,
      "learning_rate": 3.251213355762489e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9367568,
      "step": 33435
    },
    {
      "epoch": 371.55555555555554,
      "grad_norm": 7.115372682164889e-07,
      "learning_rate": 3.2463736682302707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9368976,
      "step": 33440
    },
    {
      "epoch": 371.6111111111111,
      "grad_norm": 9.761636192706646e-07,
      "learning_rate": 3.2415373353806124e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9370384,
      "step": 33445
    },
    {
      "epoch": 371.6666666666667,
      "grad_norm": 5.054724852016079e-07,
      "learning_rate": 3.236704357959322e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9371744,
      "step": 33450
    },
    {
      "epoch": 371.72222222222223,
      "grad_norm": 9.129663567364332e-07,
      "learning_rate": 3.2318747367117154e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9373136,
      "step": 33455
    },
    {
      "epoch": 371.77777777777777,
      "grad_norm": 5.93215645494638e-07,
      "learning_rate": 3.227048472382585e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9374512,
      "step": 33460
    },
    {
      "epoch": 371.8333333333333,
      "grad_norm": 6.281664468588133e-07,
      "learning_rate": 3.2222255657161915e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9375936,
      "step": 33465
    },
    {
      "epoch": 371.8888888888889,
      "grad_norm": 1.492723868068424e-06,
      "learning_rate": 3.2174060174562924e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9377296,
      "step": 33470
    },
    {
      "epoch": 371.94444444444446,
      "grad_norm": 1.6461042378068669e-06,
      "learning_rate": 3.2125898283461298e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9378736,
      "step": 33475
    },
    {
      "epoch": 372.0,
      "grad_norm": 8.951116683419968e-07,
      "learning_rate": 3.207776999128406e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9380112,
      "step": 33480
    },
    {
      "epoch": 372.05555555555554,
      "grad_norm": 2.2910608095116913e-06,
      "learning_rate": 3.202967530545331e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9381520,
      "step": 33485
    },
    {
      "epoch": 372.1111111111111,
      "grad_norm": 5.647450507240137e-07,
      "learning_rate": 3.1981614233385778e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9382880,
      "step": 33490
    },
    {
      "epoch": 372.1666666666667,
      "grad_norm": 1.0016677833846188e-06,
      "learning_rate": 3.1933586782493115e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9384256,
      "step": 33495
    },
    {
      "epoch": 372.22222222222223,
      "grad_norm": 3.493775579954672e-07,
      "learning_rate": 3.188559296018184e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9385632,
      "step": 33500
    },
    {
      "epoch": 372.27777777777777,
      "grad_norm": 4.325291627083061e-07,
      "learning_rate": 3.1837632773853098e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9387040,
      "step": 33505
    },
    {
      "epoch": 372.3333333333333,
      "grad_norm": 1.4946340343158226e-06,
      "learning_rate": 3.178970623090294e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9388416,
      "step": 33510
    },
    {
      "epoch": 372.3888888888889,
      "grad_norm": 9.286179079026624e-07,
      "learning_rate": 3.174181333872234e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9389792,
      "step": 33515
    },
    {
      "epoch": 372.44444444444446,
      "grad_norm": 4.059406819578726e-07,
      "learning_rate": 3.169395410469686e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9391216,
      "step": 33520
    },
    {
      "epoch": 372.5,
      "grad_norm": 9.14988333988731e-07,
      "learning_rate": 3.164612853620713e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9392656,
      "step": 33525
    },
    {
      "epoch": 372.55555555555554,
      "grad_norm": 4.905047603642743e-07,
      "learning_rate": 3.1598336640628333e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9394064,
      "step": 33530
    },
    {
      "epoch": 372.6111111111111,
      "grad_norm": 2.066246224785573e-06,
      "learning_rate": 3.155057842533063e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9395488,
      "step": 33535
    },
    {
      "epoch": 372.6666666666667,
      "grad_norm": 1.6304364862662624e-06,
      "learning_rate": 3.1502853897678984e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9396880,
      "step": 33540
    },
    {
      "epoch": 372.72222222222223,
      "grad_norm": 5.568597316596424e-07,
      "learning_rate": 3.1455163065033017e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9398304,
      "step": 33545
    },
    {
      "epoch": 372.77777777777777,
      "grad_norm": 9.274927492697316e-07,
      "learning_rate": 3.140750593474734e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9399680,
      "step": 33550
    },
    {
      "epoch": 372.8333333333333,
      "grad_norm": 5.549226784751227e-07,
      "learning_rate": 3.1359882514171294e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9401040,
      "step": 33555
    },
    {
      "epoch": 372.8888888888889,
      "grad_norm": 1.6428557501058094e-06,
      "learning_rate": 3.1312292810648903e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9402432,
      "step": 33560
    },
    {
      "epoch": 372.94444444444446,
      "grad_norm": 1.6791119605841232e-06,
      "learning_rate": 3.1264736831519204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9403888,
      "step": 33565
    },
    {
      "epoch": 373.0,
      "grad_norm": 9.78053890321462e-07,
      "learning_rate": 3.1217214584115863e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9405296,
      "step": 33570
    },
    {
      "epoch": 373.05555555555554,
      "grad_norm": 5.466832817546674e-07,
      "learning_rate": 3.116972607576746e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9406688,
      "step": 33575
    },
    {
      "epoch": 373.1111111111111,
      "grad_norm": 4.7258552626772143e-07,
      "learning_rate": 3.1122271313797303e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9408064,
      "step": 33580
    },
    {
      "epoch": 373.1666666666667,
      "grad_norm": 1.062161231857317e-06,
      "learning_rate": 3.107485030552343e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9409440,
      "step": 33585
    },
    {
      "epoch": 373.22222222222223,
      "grad_norm": 1.0052876859845128e-06,
      "learning_rate": 3.1027463058258848e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9410864,
      "step": 33590
    },
    {
      "epoch": 373.27777777777777,
      "grad_norm": 5.005283014725137e-07,
      "learning_rate": 3.0980109579311273e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9412256,
      "step": 33595
    },
    {
      "epoch": 373.3333333333333,
      "grad_norm": 5.643078111461364e-07,
      "learning_rate": 3.093278987598314e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9413712,
      "step": 33600
    },
    {
      "epoch": 373.3333333333333,
      "eval_loss": 0.3505513072013855,
      "eval_runtime": 1.2891,
      "eval_samples_per_second": 31.03,
      "eval_steps_per_second": 15.515,
      "num_input_tokens_seen": 9413712,
      "step": 33600
    },
    {
      "epoch": 373.3888888888889,
      "grad_norm": 5.914334337830951e-07,
      "learning_rate": 3.0885503955571826e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9415120,
      "step": 33605
    },
    {
      "epoch": 373.44444444444446,
      "grad_norm": 1.966137915587751e-06,
      "learning_rate": 3.0838251825369313e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9416496,
      "step": 33610
    },
    {
      "epoch": 373.5,
      "grad_norm": 5.414629526967474e-07,
      "learning_rate": 3.0791033492662517e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9417872,
      "step": 33615
    },
    {
      "epoch": 373.55555555555554,
      "grad_norm": 5.757244707638165e-07,
      "learning_rate": 3.0743848964733203e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9419296,
      "step": 33620
    },
    {
      "epoch": 373.6111111111111,
      "grad_norm": 9.474122180108679e-07,
      "learning_rate": 3.0696698248857625e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9420656,
      "step": 33625
    },
    {
      "epoch": 373.6666666666667,
      "grad_norm": 4.733480807317392e-07,
      "learning_rate": 3.0649581352307192e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9422112,
      "step": 33630
    },
    {
      "epoch": 373.72222222222223,
      "grad_norm": 2.077578301395988e-06,
      "learning_rate": 3.060249828234776e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9423488,
      "step": 33635
    },
    {
      "epoch": 373.77777777777777,
      "grad_norm": 6.307088824542006e-07,
      "learning_rate": 3.055544904624025e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9424880,
      "step": 33640
    },
    {
      "epoch": 373.8333333333333,
      "grad_norm": 9.411837140760326e-07,
      "learning_rate": 3.050843365124026e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9426320,
      "step": 33645
    },
    {
      "epoch": 373.8888888888889,
      "grad_norm": 5.424314508672978e-07,
      "learning_rate": 3.0461452104598083e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9427712,
      "step": 33650
    },
    {
      "epoch": 373.94444444444446,
      "grad_norm": 5.670378868671833e-07,
      "learning_rate": 3.0414504413558836e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9429104,
      "step": 33655
    },
    {
      "epoch": 374.0,
      "grad_norm": 6.459781616285909e-07,
      "learning_rate": 3.0367590585362564e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9430544,
      "step": 33660
    },
    {
      "epoch": 374.05555555555554,
      "grad_norm": 1.977038891709526e-06,
      "learning_rate": 3.0320710627243813e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9431984,
      "step": 33665
    },
    {
      "epoch": 374.1111111111111,
      "grad_norm": 1.02268177215592e-06,
      "learning_rate": 3.027386454643222e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9433360,
      "step": 33670
    },
    {
      "epoch": 374.1666666666667,
      "grad_norm": 1.6558509514652542e-06,
      "learning_rate": 3.0227052350151914e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9434720,
      "step": 33675
    },
    {
      "epoch": 374.22222222222223,
      "grad_norm": 5.608941933132883e-07,
      "learning_rate": 3.0180274045621957e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9436112,
      "step": 33680
    },
    {
      "epoch": 374.27777777777777,
      "grad_norm": 6.257802738218743e-07,
      "learning_rate": 3.013352964005625e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9437520,
      "step": 33685
    },
    {
      "epoch": 374.3333333333333,
      "grad_norm": 9.73545752458449e-07,
      "learning_rate": 3.0086819140663218e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9438896,
      "step": 33690
    },
    {
      "epoch": 374.3888888888889,
      "grad_norm": 1.0213306040895986e-06,
      "learning_rate": 3.0040142554646265e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9440256,
      "step": 33695
    },
    {
      "epoch": 374.44444444444446,
      "grad_norm": 9.434605203750834e-07,
      "learning_rate": 2.999349988920361e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9441696,
      "step": 33700
    },
    {
      "epoch": 374.5,
      "grad_norm": 4.844139880333387e-07,
      "learning_rate": 2.994689115152796e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9443088,
      "step": 33705
    },
    {
      "epoch": 374.55555555555554,
      "grad_norm": 1.5520830629611737e-06,
      "learning_rate": 2.9900316348807105e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9444496,
      "step": 33710
    },
    {
      "epoch": 374.6111111111111,
      "grad_norm": 6.582030778190529e-07,
      "learning_rate": 2.985377548822338e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9445904,
      "step": 33715
    },
    {
      "epoch": 374.6666666666667,
      "grad_norm": 1.6612365243418026e-06,
      "learning_rate": 2.980726857695404e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9447296,
      "step": 33720
    },
    {
      "epoch": 374.72222222222223,
      "grad_norm": 5.480218874254206e-07,
      "learning_rate": 2.9760795622171017e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9448688,
      "step": 33725
    },
    {
      "epoch": 374.77777777777777,
      "grad_norm": 1.0007109949583537e-06,
      "learning_rate": 2.971435663104094e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9450112,
      "step": 33730
    },
    {
      "epoch": 374.8333333333333,
      "grad_norm": 1.675328803685261e-06,
      "learning_rate": 2.9667951610725385e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9451504,
      "step": 33735
    },
    {
      "epoch": 374.8888888888889,
      "grad_norm": 9.780632126421551e-07,
      "learning_rate": 2.9621580568380575e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9452816,
      "step": 33740
    },
    {
      "epoch": 374.94444444444446,
      "grad_norm": 1.0226372069155332e-06,
      "learning_rate": 2.9575243511157453e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9454272,
      "step": 33745
    },
    {
      "epoch": 375.0,
      "grad_norm": 7.066716420922603e-07,
      "learning_rate": 2.952894044620186e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9455664,
      "step": 33750
    },
    {
      "epoch": 375.05555555555554,
      "grad_norm": 2.284204583702376e-06,
      "learning_rate": 2.948267138065419e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9457088,
      "step": 33755
    },
    {
      "epoch": 375.1111111111111,
      "grad_norm": 1.6417661754530855e-06,
      "learning_rate": 2.943643632164983e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9458464,
      "step": 33760
    },
    {
      "epoch": 375.1666666666667,
      "grad_norm": 5.95552819504519e-07,
      "learning_rate": 2.939023527631879e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9459936,
      "step": 33765
    },
    {
      "epoch": 375.22222222222223,
      "grad_norm": 9.421446520718746e-07,
      "learning_rate": 2.934406825178576e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9461328,
      "step": 33770
    },
    {
      "epoch": 375.27777777777777,
      "grad_norm": 4.4187666503603396e-07,
      "learning_rate": 2.9297935255170357e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9462752,
      "step": 33775
    },
    {
      "epoch": 375.3333333333333,
      "grad_norm": 5.461291721076122e-07,
      "learning_rate": 2.925183629358691e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9464112,
      "step": 33780
    },
    {
      "epoch": 375.3888888888889,
      "grad_norm": 5.493032517733809e-07,
      "learning_rate": 2.9205771374144346e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9465536,
      "step": 33785
    },
    {
      "epoch": 375.44444444444446,
      "grad_norm": 4.956571046932368e-07,
      "learning_rate": 2.915974050394657e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9466912,
      "step": 33790
    },
    {
      "epoch": 375.5,
      "grad_norm": 3.9871770241006743e-07,
      "learning_rate": 2.9113743690092067e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9468288,
      "step": 33795
    },
    {
      "epoch": 375.55555555555554,
      "grad_norm": 2.094641786243301e-06,
      "learning_rate": 2.906778093967402e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9469696,
      "step": 33800
    },
    {
      "epoch": 375.55555555555554,
      "eval_loss": 0.3593387305736542,
      "eval_runtime": 1.2955,
      "eval_samples_per_second": 30.876,
      "eval_steps_per_second": 15.438,
      "num_input_tokens_seen": 9469696,
      "step": 33800
    },
    {
      "epoch": 375.6111111111111,
      "grad_norm": 9.290279194829054e-07,
      "learning_rate": 2.9021852259780656e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9471072,
      "step": 33805
    },
    {
      "epoch": 375.6666666666667,
      "grad_norm": 5.754180847361567e-07,
      "learning_rate": 2.8975957657494583e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9472496,
      "step": 33810
    },
    {
      "epoch": 375.72222222222223,
      "grad_norm": 5.830635814163543e-07,
      "learning_rate": 2.8930097139893417e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9473888,
      "step": 33815
    },
    {
      "epoch": 375.77777777777777,
      "grad_norm": 1.4885165455780225e-06,
      "learning_rate": 2.888427071404945e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9475280,
      "step": 33820
    },
    {
      "epoch": 375.8333333333333,
      "grad_norm": 6.012074322825356e-07,
      "learning_rate": 2.8838478387029606e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9476688,
      "step": 33825
    },
    {
      "epoch": 375.8888888888889,
      "grad_norm": 6.074678253753518e-07,
      "learning_rate": 2.8792720165895737e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9478064,
      "step": 33830
    },
    {
      "epoch": 375.94444444444446,
      "grad_norm": 6.507721650450549e-07,
      "learning_rate": 2.874699605770423e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9479488,
      "step": 33835
    },
    {
      "epoch": 376.0,
      "grad_norm": 5.527217012968322e-07,
      "learning_rate": 2.8701306069506383e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9480912,
      "step": 33840
    },
    {
      "epoch": 376.05555555555554,
      "grad_norm": 9.697433824840118e-07,
      "learning_rate": 2.8655650208348178e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9482304,
      "step": 33845
    },
    {
      "epoch": 376.1111111111111,
      "grad_norm": 8.846698165143607e-07,
      "learning_rate": 2.8610028481270257e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9483712,
      "step": 33850
    },
    {
      "epoch": 376.1666666666667,
      "grad_norm": 1.9754882032430032e-06,
      "learning_rate": 2.856444089530813e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9485120,
      "step": 33855
    },
    {
      "epoch": 376.22222222222223,
      "grad_norm": 1.4734705473529175e-06,
      "learning_rate": 2.8518887457491955e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9486496,
      "step": 33860
    },
    {
      "epoch": 376.27777777777777,
      "grad_norm": 8.669587714393856e-07,
      "learning_rate": 2.8473368174846666e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9487920,
      "step": 33865
    },
    {
      "epoch": 376.3333333333333,
      "grad_norm": 5.135609626449877e-07,
      "learning_rate": 2.842788305439184e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9489360,
      "step": 33870
    },
    {
      "epoch": 376.3888888888889,
      "grad_norm": 5.4917455827308e-07,
      "learning_rate": 2.8382432103141925e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9490720,
      "step": 33875
    },
    {
      "epoch": 376.44444444444446,
      "grad_norm": 4.817539434043283e-07,
      "learning_rate": 2.833701532810598e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9492080,
      "step": 33880
    },
    {
      "epoch": 376.5,
      "grad_norm": 4.823885433324904e-07,
      "learning_rate": 2.8291632736287877e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9493440,
      "step": 33885
    },
    {
      "epoch": 376.55555555555554,
      "grad_norm": 4.737460699288931e-07,
      "learning_rate": 2.824628433468615e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9494800,
      "step": 33890
    },
    {
      "epoch": 376.6111111111111,
      "grad_norm": 9.111040526477154e-07,
      "learning_rate": 2.8200970130294073e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9496208,
      "step": 33895
    },
    {
      "epoch": 376.6666666666667,
      "grad_norm": 4.68216228455276e-07,
      "learning_rate": 2.8155690130099775e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9497600,
      "step": 33900
    },
    {
      "epoch": 376.72222222222223,
      "grad_norm": 6.328210702122306e-07,
      "learning_rate": 2.8110444341085895e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9499024,
      "step": 33905
    },
    {
      "epoch": 376.77777777777777,
      "grad_norm": 4.627653993338754e-07,
      "learning_rate": 2.806523277022996e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9500416,
      "step": 33910
    },
    {
      "epoch": 376.8333333333333,
      "grad_norm": 6.360547786243842e-07,
      "learning_rate": 2.802005542450409e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9501808,
      "step": 33915
    },
    {
      "epoch": 376.8888888888889,
      "grad_norm": 1.4737375977347256e-06,
      "learning_rate": 2.797491231087526e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9503248,
      "step": 33920
    },
    {
      "epoch": 376.94444444444446,
      "grad_norm": 4.954140422341879e-07,
      "learning_rate": 2.7929803436305137e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9504672,
      "step": 33925
    },
    {
      "epoch": 377.0,
      "grad_norm": 5.403200020737131e-07,
      "learning_rate": 2.788472880774998e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9506128,
      "step": 33930
    },
    {
      "epoch": 377.05555555555554,
      "grad_norm": 6.543833137584443e-07,
      "learning_rate": 2.7839688432160977e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9507568,
      "step": 33935
    },
    {
      "epoch": 377.1111111111111,
      "grad_norm": 6.144254030004959e-07,
      "learning_rate": 2.779468231648383e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9508960,
      "step": 33940
    },
    {
      "epoch": 377.1666666666667,
      "grad_norm": 5.020714297643281e-07,
      "learning_rate": 2.774971046765906e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9510368,
      "step": 33945
    },
    {
      "epoch": 377.22222222222223,
      "grad_norm": 5.731226906391385e-07,
      "learning_rate": 2.770477289262194e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9511728,
      "step": 33950
    },
    {
      "epoch": 377.27777777777777,
      "grad_norm": 9.38421692353586e-07,
      "learning_rate": 2.765986959830233e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9513120,
      "step": 33955
    },
    {
      "epoch": 377.3333333333333,
      "grad_norm": 6.213036840563291e-07,
      "learning_rate": 2.761500059162492e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9514592,
      "step": 33960
    },
    {
      "epoch": 377.3888888888889,
      "grad_norm": 5.846223416483554e-07,
      "learning_rate": 2.757016587950914e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9515936,
      "step": 33965
    },
    {
      "epoch": 377.44444444444446,
      "grad_norm": 4.890822538072825e-07,
      "learning_rate": 2.752536546886897e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9517360,
      "step": 33970
    },
    {
      "epoch": 377.5,
      "grad_norm": 9.292587037634803e-07,
      "learning_rate": 2.7480599366613234e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9518800,
      "step": 33975
    },
    {
      "epoch": 377.55555555555554,
      "grad_norm": 5.959205395811296e-07,
      "learning_rate": 2.7435867579645473e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9520224,
      "step": 33980
    },
    {
      "epoch": 377.6111111111111,
      "grad_norm": 9.8252485258854e-07,
      "learning_rate": 2.739117011486378e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9521600,
      "step": 33985
    },
    {
      "epoch": 377.6666666666667,
      "grad_norm": 1.6693210227458621e-06,
      "learning_rate": 2.7346506979161216e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9522960,
      "step": 33990
    },
    {
      "epoch": 377.72222222222223,
      "grad_norm": 9.587650993125862e-07,
      "learning_rate": 2.7301878179425227e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9524320,
      "step": 33995
    },
    {
      "epoch": 377.77777777777777,
      "grad_norm": 1.5129450048334547e-06,
      "learning_rate": 2.7257283722538244e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9525760,
      "step": 34000
    },
    {
      "epoch": 377.77777777777777,
      "eval_loss": 0.35832586884498596,
      "eval_runtime": 1.2991,
      "eval_samples_per_second": 30.791,
      "eval_steps_per_second": 15.395,
      "num_input_tokens_seen": 9525760,
      "step": 34000
    },
    {
      "epoch": 377.8333333333333,
      "grad_norm": 5.141359906701837e-07,
      "learning_rate": 2.7212723615377326e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9527120,
      "step": 34005
    },
    {
      "epoch": 377.8888888888889,
      "grad_norm": 1.0358216968597844e-06,
      "learning_rate": 2.7168197864814145e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9528512,
      "step": 34010
    },
    {
      "epoch": 377.94444444444446,
      "grad_norm": 2.170387915612082e-06,
      "learning_rate": 2.712370647771509e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9529920,
      "step": 34015
    },
    {
      "epoch": 378.0,
      "grad_norm": 8.906073389880476e-07,
      "learning_rate": 2.707924946094137e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9531264,
      "step": 34020
    },
    {
      "epoch": 378.05555555555554,
      "grad_norm": 2.341322897336795e-06,
      "learning_rate": 2.7034826821348723e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9532656,
      "step": 34025
    },
    {
      "epoch": 378.1111111111111,
      "grad_norm": 5.858386771251389e-07,
      "learning_rate": 2.6990438565787786e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9533984,
      "step": 34030
    },
    {
      "epoch": 378.1666666666667,
      "grad_norm": 4.945216574014921e-07,
      "learning_rate": 2.6946084701103714e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9535360,
      "step": 34035
    },
    {
      "epoch": 378.22222222222223,
      "grad_norm": 5.796251798528829e-07,
      "learning_rate": 2.6901765234136428e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9536784,
      "step": 34040
    },
    {
      "epoch": 378.27777777777777,
      "grad_norm": 5.425872586783953e-07,
      "learning_rate": 2.685748017172063e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9538208,
      "step": 34045
    },
    {
      "epoch": 378.3333333333333,
      "grad_norm": 9.10889013994165e-07,
      "learning_rate": 2.681322952068549e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9539616,
      "step": 34050
    },
    {
      "epoch": 378.3888888888889,
      "grad_norm": 6.207902174537594e-07,
      "learning_rate": 2.6769013287855137e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9541024,
      "step": 34055
    },
    {
      "epoch": 378.44444444444446,
      "grad_norm": 9.175224136015458e-07,
      "learning_rate": 2.6724831480048286e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9542400,
      "step": 34060
    },
    {
      "epoch": 378.5,
      "grad_norm": 5.750518425884366e-07,
      "learning_rate": 2.66806841040782e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9543792,
      "step": 34065
    },
    {
      "epoch": 378.55555555555554,
      "grad_norm": 7.949261089379434e-07,
      "learning_rate": 2.6636571166753083e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9545232,
      "step": 34070
    },
    {
      "epoch": 378.6111111111111,
      "grad_norm": 2.7694325126503827e-06,
      "learning_rate": 2.6592492674875598e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9546640,
      "step": 34075
    },
    {
      "epoch": 378.6666666666667,
      "grad_norm": 6.535189527312468e-07,
      "learning_rate": 2.6548448635243305e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9548080,
      "step": 34080
    },
    {
      "epoch": 378.72222222222223,
      "grad_norm": 5.032882768318814e-07,
      "learning_rate": 2.650443905464828e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9549456,
      "step": 34085
    },
    {
      "epoch": 378.77777777777777,
      "grad_norm": 5.38141762262967e-07,
      "learning_rate": 2.646046393987739e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9550848,
      "step": 34090
    },
    {
      "epoch": 378.8333333333333,
      "grad_norm": 9.176317234960152e-07,
      "learning_rate": 2.64165232977121e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9552256,
      "step": 34095
    },
    {
      "epoch": 378.8888888888889,
      "grad_norm": 1.8830268118108506e-06,
      "learning_rate": 2.6372617134928695e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9553664,
      "step": 34100
    },
    {
      "epoch": 378.94444444444446,
      "grad_norm": 8.041500336730678e-07,
      "learning_rate": 2.6328745458297943e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9555072,
      "step": 34105
    },
    {
      "epoch": 379.0,
      "grad_norm": 6.00030716668698e-07,
      "learning_rate": 2.6284908274585546e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9556464,
      "step": 34110
    },
    {
      "epoch": 379.05555555555554,
      "grad_norm": 1.4957571465856745e-06,
      "learning_rate": 2.6241105590551595e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9557888,
      "step": 34115
    },
    {
      "epoch": 379.1111111111111,
      "grad_norm": 4.4242537455829734e-07,
      "learning_rate": 2.6197337412951105e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9559312,
      "step": 34120
    },
    {
      "epoch": 379.1666666666667,
      "grad_norm": 2.2827980501460843e-06,
      "learning_rate": 2.6153603748533705e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9560720,
      "step": 34125
    },
    {
      "epoch": 379.22222222222223,
      "grad_norm": 5.578356194746448e-07,
      "learning_rate": 2.6109904604043585e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9562144,
      "step": 34130
    },
    {
      "epoch": 379.27777777777777,
      "grad_norm": 5.965974878563429e-07,
      "learning_rate": 2.6066239986219765e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9563552,
      "step": 34135
    },
    {
      "epoch": 379.3333333333333,
      "grad_norm": 5.465276444738265e-07,
      "learning_rate": 2.602260990179592e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9564944,
      "step": 34140
    },
    {
      "epoch": 379.3888888888889,
      "grad_norm": 5.978521926408575e-07,
      "learning_rate": 2.5979014357500248e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9566368,
      "step": 34145
    },
    {
      "epoch": 379.44444444444446,
      "grad_norm": 9.276453738493728e-07,
      "learning_rate": 2.5935453360055844e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9567776,
      "step": 34150
    },
    {
      "epoch": 379.5,
      "grad_norm": 5.776245757260767e-07,
      "learning_rate": 2.5891926916180283e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9569136,
      "step": 34155
    },
    {
      "epoch": 379.55555555555554,
      "grad_norm": 2.0939073692716192e-06,
      "learning_rate": 2.5848435032585883e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9570512,
      "step": 34160
    },
    {
      "epoch": 379.6111111111111,
      "grad_norm": 2.0901877633150434e-06,
      "learning_rate": 2.58049777159797e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9571920,
      "step": 34165
    },
    {
      "epoch": 379.6666666666667,
      "grad_norm": 4.843978445023822e-07,
      "learning_rate": 2.576155497306332e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9573296,
      "step": 34170
    },
    {
      "epoch": 379.72222222222223,
      "grad_norm": 6.48467221253668e-07,
      "learning_rate": 2.57181668105331e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9574672,
      "step": 34175
    },
    {
      "epoch": 379.77777777777777,
      "grad_norm": 5.314994950822438e-07,
      "learning_rate": 2.567481323508014e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9576032,
      "step": 34180
    },
    {
      "epoch": 379.8333333333333,
      "grad_norm": 5.412068162513606e-07,
      "learning_rate": 2.5631494253389954e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9577408,
      "step": 34185
    },
    {
      "epoch": 379.8888888888889,
      "grad_norm": 9.78885736913071e-07,
      "learning_rate": 2.5588209872142997e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9578864,
      "step": 34190
    },
    {
      "epoch": 379.94444444444446,
      "grad_norm": 4.698968041338958e-07,
      "learning_rate": 2.5544960098014186e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9580288,
      "step": 34195
    },
    {
      "epoch": 380.0,
      "grad_norm": 6.334929025797464e-07,
      "learning_rate": 2.550174493767318e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9581648,
      "step": 34200
    },
    {
      "epoch": 380.0,
      "eval_loss": 0.38547393679618835,
      "eval_runtime": 1.2832,
      "eval_samples_per_second": 31.172,
      "eval_steps_per_second": 15.586,
      "num_input_tokens_seen": 9581648,
      "step": 34200
    },
    {
      "epoch": 380.05555555555554,
      "grad_norm": 1.0710274409575504e-06,
      "learning_rate": 2.545856439778438e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9583024,
      "step": 34205
    },
    {
      "epoch": 380.1111111111111,
      "grad_norm": 5.451801712297311e-07,
      "learning_rate": 2.541541848500667e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9584400,
      "step": 34210
    },
    {
      "epoch": 380.1666666666667,
      "grad_norm": 1.6842795957927592e-06,
      "learning_rate": 2.5372307205993733e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9585808,
      "step": 34215
    },
    {
      "epoch": 380.22222222222223,
      "grad_norm": 9.433808827452594e-07,
      "learning_rate": 2.5329230567393917e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9587216,
      "step": 34220
    },
    {
      "epoch": 380.27777777777777,
      "grad_norm": 4.6382945129153086e-07,
      "learning_rate": 2.5286188575850164e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9588624,
      "step": 34225
    },
    {
      "epoch": 380.3333333333333,
      "grad_norm": 6.193796480147284e-07,
      "learning_rate": 2.5243181237999984e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9590048,
      "step": 34230
    },
    {
      "epoch": 380.3888888888889,
      "grad_norm": 5.622636649604829e-07,
      "learning_rate": 2.520020856047578e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9591472,
      "step": 34235
    },
    {
      "epoch": 380.44444444444446,
      "grad_norm": 1.0388934015281848e-06,
      "learning_rate": 2.515727054990438e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9592864,
      "step": 34240
    },
    {
      "epoch": 380.5,
      "grad_norm": 5.491448291650158e-07,
      "learning_rate": 2.511436721290747e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9594288,
      "step": 34245
    },
    {
      "epoch": 380.55555555555554,
      "grad_norm": 1.9870578853442566e-06,
      "learning_rate": 2.5071498556101164e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9595696,
      "step": 34250
    },
    {
      "epoch": 380.6111111111111,
      "grad_norm": 5.467643973133818e-07,
      "learning_rate": 2.5028664586096485e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9597040,
      "step": 34255
    },
    {
      "epoch": 380.6666666666667,
      "grad_norm": 1.0034901833932963e-06,
      "learning_rate": 2.498586530949881e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9598464,
      "step": 34260
    },
    {
      "epoch": 380.72222222222223,
      "grad_norm": 5.723186973227712e-07,
      "learning_rate": 2.4943100732908427e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9599920,
      "step": 34265
    },
    {
      "epoch": 380.77777777777777,
      "grad_norm": 1.469071662540955e-06,
      "learning_rate": 2.4900370862920188e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9601296,
      "step": 34270
    },
    {
      "epoch": 380.8333333333333,
      "grad_norm": 9.485174814471975e-07,
      "learning_rate": 2.4857675706123518e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9602672,
      "step": 34275
    },
    {
      "epoch": 380.8888888888889,
      "grad_norm": 1.643723749111814e-06,
      "learning_rate": 2.4815015269102543e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9604080,
      "step": 34280
    },
    {
      "epoch": 380.94444444444446,
      "grad_norm": 6.118824558143388e-07,
      "learning_rate": 2.477238955843611e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9605504,
      "step": 34285
    },
    {
      "epoch": 381.0,
      "grad_norm": 4.844684440286073e-07,
      "learning_rate": 2.4729798580697573e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9606864,
      "step": 34290
    },
    {
      "epoch": 381.05555555555554,
      "grad_norm": 5.882761229258904e-07,
      "learning_rate": 2.4687242342455034e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9608192,
      "step": 34295
    },
    {
      "epoch": 381.1111111111111,
      "grad_norm": 5.550020887312712e-07,
      "learning_rate": 2.4644720850271196e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9609600,
      "step": 34300
    },
    {
      "epoch": 381.1666666666667,
      "grad_norm": 6.18819115061342e-07,
      "learning_rate": 2.4602234110703364e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9611024,
      "step": 34305
    },
    {
      "epoch": 381.22222222222223,
      "grad_norm": 3.496493491184083e-06,
      "learning_rate": 2.4559782130303576e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9612416,
      "step": 34310
    },
    {
      "epoch": 381.27777777777777,
      "grad_norm": 3.6829246710112784e-06,
      "learning_rate": 2.451736491561843e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9613856,
      "step": 34315
    },
    {
      "epoch": 381.3333333333333,
      "grad_norm": 9.367737447973923e-07,
      "learning_rate": 2.4474982473189163e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9615232,
      "step": 34320
    },
    {
      "epoch": 381.3888888888889,
      "grad_norm": 5.554766744353401e-07,
      "learning_rate": 2.4432634809551796e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9616624,
      "step": 34325
    },
    {
      "epoch": 381.44444444444446,
      "grad_norm": 5.924622996644757e-07,
      "learning_rate": 2.439032193123675e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9618016,
      "step": 34330
    },
    {
      "epoch": 381.5,
      "grad_norm": 5.468638732963882e-07,
      "learning_rate": 2.4348043844769297e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9619408,
      "step": 34335
    },
    {
      "epoch": 381.55555555555554,
      "grad_norm": 6.238457785912033e-07,
      "learning_rate": 2.4305800556669146e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9620800,
      "step": 34340
    },
    {
      "epoch": 381.6111111111111,
      "grad_norm": 1.9817277916445164e-06,
      "learning_rate": 2.426359207345083e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9622224,
      "step": 34345
    },
    {
      "epoch": 381.6666666666667,
      "grad_norm": 9.524230790702859e-07,
      "learning_rate": 2.4221418401623396e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9623616,
      "step": 34350
    },
    {
      "epoch": 381.72222222222223,
      "grad_norm": 4.342033719240135e-07,
      "learning_rate": 2.4179279547690557e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9625024,
      "step": 34355
    },
    {
      "epoch": 381.77777777777777,
      "grad_norm": 5.649492891279806e-07,
      "learning_rate": 2.413717551815062e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9626416,
      "step": 34360
    },
    {
      "epoch": 381.8333333333333,
      "grad_norm": 9.30078840610804e-07,
      "learning_rate": 2.409510631949666e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9627808,
      "step": 34365
    },
    {
      "epoch": 381.8888888888889,
      "grad_norm": 1.9793496903730556e-06,
      "learning_rate": 2.405307195821618e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9629184,
      "step": 34370
    },
    {
      "epoch": 381.94444444444446,
      "grad_norm": 5.522421133719035e-07,
      "learning_rate": 2.4011072440791372e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9630608,
      "step": 34375
    },
    {
      "epoch": 382.0,
      "grad_norm": 6.605393423342321e-07,
      "learning_rate": 2.3969107773699233e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9632016,
      "step": 34380
    },
    {
      "epoch": 382.05555555555554,
      "grad_norm": 5.132808382768417e-07,
      "learning_rate": 2.3927177963411096e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9633456,
      "step": 34385
    },
    {
      "epoch": 382.1111111111111,
      "grad_norm": 4.825052997148305e-07,
      "learning_rate": 2.3885283016393144e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9634800,
      "step": 34390
    },
    {
      "epoch": 382.1666666666667,
      "grad_norm": 5.728152814299392e-07,
      "learning_rate": 2.3843422939106076e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9636176,
      "step": 34395
    },
    {
      "epoch": 382.22222222222223,
      "grad_norm": 2.9247109978314256e-06,
      "learning_rate": 2.380159773800525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9637632,
      "step": 34400
    },
    {
      "epoch": 382.22222222222223,
      "eval_loss": 0.3392062485218048,
      "eval_runtime": 1.2974,
      "eval_samples_per_second": 30.83,
      "eval_steps_per_second": 15.415,
      "num_input_tokens_seen": 9637632,
      "step": 34400
    },
    {
      "epoch": 382.27777777777777,
      "grad_norm": 4.1934643491003953e-07,
      "learning_rate": 2.3759807419540675e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9639056,
      "step": 34405
    },
    {
      "epoch": 382.3333333333333,
      "grad_norm": 2.040515710177715e-06,
      "learning_rate": 2.3718051990156835e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9640496,
      "step": 34410
    },
    {
      "epoch": 382.3888888888889,
      "grad_norm": 5.857073119841516e-07,
      "learning_rate": 2.367633145629311e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9641888,
      "step": 34415
    },
    {
      "epoch": 382.44444444444446,
      "grad_norm": 5.607768116533407e-07,
      "learning_rate": 2.363464582438316e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9643264,
      "step": 34420
    },
    {
      "epoch": 382.5,
      "grad_norm": 4.6366611172743433e-07,
      "learning_rate": 2.3592995100855526e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9644672,
      "step": 34425
    },
    {
      "epoch": 382.55555555555554,
      "grad_norm": 5.518470516108209e-07,
      "learning_rate": 2.3551379292133273e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9646080,
      "step": 34430
    },
    {
      "epoch": 382.6111111111111,
      "grad_norm": 5.1964940439575e-07,
      "learning_rate": 2.3509798404634047e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9647440,
      "step": 34435
    },
    {
      "epoch": 382.6666666666667,
      "grad_norm": 8.821294272820523e-07,
      "learning_rate": 2.346825244477019e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9648880,
      "step": 34440
    },
    {
      "epoch": 382.72222222222223,
      "grad_norm": 6.223605168997892e-07,
      "learning_rate": 2.3426741418948545e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9650288,
      "step": 34445
    },
    {
      "epoch": 382.77777777777777,
      "grad_norm": 6.266102445806609e-07,
      "learning_rate": 2.3385265333570715e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9651664,
      "step": 34450
    },
    {
      "epoch": 382.8333333333333,
      "grad_norm": 1.6735483541197027e-06,
      "learning_rate": 2.334382419503278e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9653040,
      "step": 34455
    },
    {
      "epoch": 382.8888888888889,
      "grad_norm": 8.809029168332927e-07,
      "learning_rate": 2.3302418009725465e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9654432,
      "step": 34460
    },
    {
      "epoch": 382.94444444444446,
      "grad_norm": 9.25858216760389e-07,
      "learning_rate": 2.326104678403415e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9655808,
      "step": 34465
    },
    {
      "epoch": 383.0,
      "grad_norm": 5.262606350697752e-07,
      "learning_rate": 2.321971052433883e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9657216,
      "step": 34470
    },
    {
      "epoch": 383.05555555555554,
      "grad_norm": 5.925305686105276e-07,
      "learning_rate": 2.3178409237014004e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9658640,
      "step": 34475
    },
    {
      "epoch": 383.1111111111111,
      "grad_norm": 5.287242288432026e-07,
      "learning_rate": 2.313714292842889e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9660048,
      "step": 34480
    },
    {
      "epoch": 383.1666666666667,
      "grad_norm": 6.546193276335543e-07,
      "learning_rate": 2.309591160494734e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9661488,
      "step": 34485
    },
    {
      "epoch": 383.22222222222223,
      "grad_norm": 9.821266075960011e-07,
      "learning_rate": 2.305471527292763e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9662880,
      "step": 34490
    },
    {
      "epoch": 383.27777777777777,
      "grad_norm": 6.57616567423247e-07,
      "learning_rate": 2.3013553938722817e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9664288,
      "step": 34495
    },
    {
      "epoch": 383.3333333333333,
      "grad_norm": 5.20493927069765e-07,
      "learning_rate": 2.297242760868043e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9665728,
      "step": 34500
    },
    {
      "epoch": 383.3888888888889,
      "grad_norm": 1.4782629023102345e-06,
      "learning_rate": 2.2931336289142735e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9667120,
      "step": 34505
    },
    {
      "epoch": 383.44444444444446,
      "grad_norm": 7.873344998188259e-07,
      "learning_rate": 2.289027998644655e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9668512,
      "step": 34510
    },
    {
      "epoch": 383.5,
      "grad_norm": 5.828703706356464e-07,
      "learning_rate": 2.2849258706923228e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9669872,
      "step": 34515
    },
    {
      "epoch": 383.55555555555554,
      "grad_norm": 9.030120509123662e-07,
      "learning_rate": 2.2808272456898705e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9671280,
      "step": 34520
    },
    {
      "epoch": 383.6111111111111,
      "grad_norm": 9.576361890140106e-07,
      "learning_rate": 2.2767321242693707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9672672,
      "step": 34525
    },
    {
      "epoch": 383.6666666666667,
      "grad_norm": 5.788838279841002e-07,
      "learning_rate": 2.272640507062329e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9674048,
      "step": 34530
    },
    {
      "epoch": 383.72222222222223,
      "grad_norm": 5.704831664843368e-07,
      "learning_rate": 2.2685523946997382e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9675472,
      "step": 34535
    },
    {
      "epoch": 383.77777777777777,
      "grad_norm": 5.958690394436417e-07,
      "learning_rate": 2.2644677878120245e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9676864,
      "step": 34540
    },
    {
      "epoch": 383.8333333333333,
      "grad_norm": 1.940084530360764e-06,
      "learning_rate": 2.2603866870290897e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9678288,
      "step": 34545
    },
    {
      "epoch": 383.8888888888889,
      "grad_norm": 5.758023462476558e-07,
      "learning_rate": 2.256309092980294e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9679696,
      "step": 34550
    },
    {
      "epoch": 383.94444444444446,
      "grad_norm": 5.970960614831711e-07,
      "learning_rate": 2.252235006294448e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9681104,
      "step": 34555
    },
    {
      "epoch": 384.0,
      "grad_norm": 5.568826964008622e-07,
      "learning_rate": 2.2481644275998333e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9682528,
      "step": 34560
    },
    {
      "epoch": 384.05555555555554,
      "grad_norm": 4.6805280362605117e-07,
      "learning_rate": 2.2440973575241832e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9683920,
      "step": 34565
    },
    {
      "epoch": 384.1111111111111,
      "grad_norm": 6.790445468141115e-07,
      "learning_rate": 2.240033796694685e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9685280,
      "step": 34570
    },
    {
      "epoch": 384.1666666666667,
      "grad_norm": 5.63400533337699e-07,
      "learning_rate": 2.235973745737999e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9686656,
      "step": 34575
    },
    {
      "epoch": 384.22222222222223,
      "grad_norm": 5.690169473382412e-07,
      "learning_rate": 2.2319172052802263e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9688064,
      "step": 34580
    },
    {
      "epoch": 384.27777777777777,
      "grad_norm": 5.361413855098363e-07,
      "learning_rate": 2.2278641759469477e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9689456,
      "step": 34585
    },
    {
      "epoch": 384.3333333333333,
      "grad_norm": 1.0396454399597133e-06,
      "learning_rate": 2.2238146583631825e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9690848,
      "step": 34590
    },
    {
      "epoch": 384.3888888888889,
      "grad_norm": 5.381840537665994e-07,
      "learning_rate": 2.2197686531534256e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9692208,
      "step": 34595
    },
    {
      "epoch": 384.44444444444446,
      "grad_norm": 9.465094308325206e-07,
      "learning_rate": 2.2157261609416087e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9693568,
      "step": 34600
    },
    {
      "epoch": 384.44444444444446,
      "eval_loss": 0.3269561529159546,
      "eval_runtime": 1.2942,
      "eval_samples_per_second": 30.908,
      "eval_steps_per_second": 15.454,
      "num_input_tokens_seen": 9693568,
      "step": 34600
    },
    {
      "epoch": 384.5,
      "grad_norm": 8.922194183469401e-07,
      "learning_rate": 2.211687182351149e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9694960,
      "step": 34605
    },
    {
      "epoch": 384.55555555555554,
      "grad_norm": 3.917575099876558e-07,
      "learning_rate": 2.2076517180048993e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9696400,
      "step": 34610
    },
    {
      "epoch": 384.6111111111111,
      "grad_norm": 5.705772423425515e-07,
      "learning_rate": 2.2036197685251834e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9697808,
      "step": 34615
    },
    {
      "epoch": 384.6666666666667,
      "grad_norm": 1.6653477814543294e-06,
      "learning_rate": 2.199591334533771e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9699216,
      "step": 34620
    },
    {
      "epoch": 384.72222222222223,
      "grad_norm": 5.047016315984365e-07,
      "learning_rate": 2.1955664166519036e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9700656,
      "step": 34625
    },
    {
      "epoch": 384.77777777777777,
      "grad_norm": 1.5053647075546905e-06,
      "learning_rate": 2.1915450155002793e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9702080,
      "step": 34630
    },
    {
      "epoch": 384.8333333333333,
      "grad_norm": 5.67427605346893e-07,
      "learning_rate": 2.187527131699038e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9703520,
      "step": 34635
    },
    {
      "epoch": 384.8888888888889,
      "grad_norm": 5.675368583979434e-07,
      "learning_rate": 2.18351276586779e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9704976,
      "step": 34640
    },
    {
      "epoch": 384.94444444444446,
      "grad_norm": 8.62481101648882e-07,
      "learning_rate": 2.1795019186256092e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9706400,
      "step": 34645
    },
    {
      "epoch": 385.0,
      "grad_norm": 1.6733230268073385e-06,
      "learning_rate": 2.1754945905910094e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9707776,
      "step": 34650
    },
    {
      "epoch": 385.05555555555554,
      "grad_norm": 4.693645223596832e-07,
      "learning_rate": 2.171490782381977e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9709200,
      "step": 34655
    },
    {
      "epoch": 385.1111111111111,
      "grad_norm": 5.264015499051311e-07,
      "learning_rate": 2.1674904946159425e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9710544,
      "step": 34660
    },
    {
      "epoch": 385.1666666666667,
      "grad_norm": 5.51537880255637e-07,
      "learning_rate": 2.16349372790981e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9711904,
      "step": 34665
    },
    {
      "epoch": 385.22222222222223,
      "grad_norm": 9.324856478087895e-07,
      "learning_rate": 2.159500482879928e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9713360,
      "step": 34670
    },
    {
      "epoch": 385.27777777777777,
      "grad_norm": 1.6880647990547004e-06,
      "learning_rate": 2.155510760142096e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9714672,
      "step": 34675
    },
    {
      "epoch": 385.3333333333333,
      "grad_norm": 6.152999389996694e-07,
      "learning_rate": 2.151524560311588e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9716048,
      "step": 34680
    },
    {
      "epoch": 385.3888888888889,
      "grad_norm": 5.29300280049938e-07,
      "learning_rate": 2.147541884003129e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9717456,
      "step": 34685
    },
    {
      "epoch": 385.44444444444446,
      "grad_norm": 8.624966767456499e-07,
      "learning_rate": 2.1435627318308895e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9718832,
      "step": 34690
    },
    {
      "epoch": 385.5,
      "grad_norm": 4.830552597923088e-07,
      "learning_rate": 2.139587104408511e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9720224,
      "step": 34695
    },
    {
      "epoch": 385.55555555555554,
      "grad_norm": 9.146643265012244e-07,
      "learning_rate": 2.1356150023490783e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9721680,
      "step": 34700
    },
    {
      "epoch": 385.6111111111111,
      "grad_norm": 5.785752819065237e-07,
      "learning_rate": 2.1316464262651464e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9723088,
      "step": 34705
    },
    {
      "epoch": 385.6666666666667,
      "grad_norm": 5.900934070268704e-07,
      "learning_rate": 2.1276813767687224e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9724480,
      "step": 34710
    },
    {
      "epoch": 385.72222222222223,
      "grad_norm": 1.6324200942108291e-06,
      "learning_rate": 2.123719854471254e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9725904,
      "step": 34715
    },
    {
      "epoch": 385.77777777777777,
      "grad_norm": 5.546273769141408e-07,
      "learning_rate": 2.119761859983668e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9727296,
      "step": 34720
    },
    {
      "epoch": 385.8333333333333,
      "grad_norm": 1.9180858998879557e-06,
      "learning_rate": 2.1158073939163386e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9728704,
      "step": 34725
    },
    {
      "epoch": 385.8888888888889,
      "grad_norm": 5.412795189840836e-07,
      "learning_rate": 2.111856456879088e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9730096,
      "step": 34730
    },
    {
      "epoch": 385.94444444444446,
      "grad_norm": 5.723236427002121e-07,
      "learning_rate": 2.1079090494811993e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9731536,
      "step": 34735
    },
    {
      "epoch": 386.0,
      "grad_norm": 5.218245746618777e-07,
      "learning_rate": 2.103965172331418e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9732960,
      "step": 34740
    },
    {
      "epoch": 386.05555555555554,
      "grad_norm": 5.129965643391188e-07,
      "learning_rate": 2.100024826037933e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9734320,
      "step": 34745
    },
    {
      "epoch": 386.1111111111111,
      "grad_norm": 5.60303362817649e-07,
      "learning_rate": 2.0960880112084027e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9735728,
      "step": 34750
    },
    {
      "epoch": 386.1666666666667,
      "grad_norm": 5.30226088812924e-07,
      "learning_rate": 2.092154728449927e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9737120,
      "step": 34755
    },
    {
      "epoch": 386.22222222222223,
      "grad_norm": 1.7050745100277709e-06,
      "learning_rate": 2.0882249783690687e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9738560,
      "step": 34760
    },
    {
      "epoch": 386.27777777777777,
      "grad_norm": 5.280432446852501e-07,
      "learning_rate": 2.084298761571851e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9739952,
      "step": 34765
    },
    {
      "epoch": 386.3333333333333,
      "grad_norm": 5.045972102379892e-07,
      "learning_rate": 2.080376078663737e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9741344,
      "step": 34770
    },
    {
      "epoch": 386.3888888888889,
      "grad_norm": 6.014610676174925e-07,
      "learning_rate": 2.0764569302496593e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9742752,
      "step": 34775
    },
    {
      "epoch": 386.44444444444446,
      "grad_norm": 5.417749093794555e-07,
      "learning_rate": 2.0725413169339957e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9744176,
      "step": 34780
    },
    {
      "epoch": 386.5,
      "grad_norm": 1.0270937309542205e-06,
      "learning_rate": 2.068629239320588e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9745536,
      "step": 34785
    },
    {
      "epoch": 386.55555555555554,
      "grad_norm": 4.2479047124288627e-07,
      "learning_rate": 2.064720698012726e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9746976,
      "step": 34790
    },
    {
      "epoch": 386.6111111111111,
      "grad_norm": 1.5300045106414473e-06,
      "learning_rate": 2.0608156936131522e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9748368,
      "step": 34795
    },
    {
      "epoch": 386.6666666666667,
      "grad_norm": 5.311971449373232e-07,
      "learning_rate": 2.056914226724074e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9749792,
      "step": 34800
    },
    {
      "epoch": 386.6666666666667,
      "eval_loss": 0.37162813544273376,
      "eval_runtime": 1.2911,
      "eval_samples_per_second": 30.981,
      "eval_steps_per_second": 15.491,
      "num_input_tokens_seen": 9749792,
      "step": 34800
    },
    {
      "epoch": 386.72222222222223,
      "grad_norm": 9.119476089836098e-07,
      "learning_rate": 2.0530162979471385e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9751200,
      "step": 34805
    },
    {
      "epoch": 386.77777777777777,
      "grad_norm": 9.775271792022977e-07,
      "learning_rate": 2.0491219078834667e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9752576,
      "step": 34810
    },
    {
      "epoch": 386.8333333333333,
      "grad_norm": 5.700366045857663e-07,
      "learning_rate": 2.045231057133612e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9753968,
      "step": 34815
    },
    {
      "epoch": 386.8888888888889,
      "grad_norm": 5.305087711349188e-07,
      "learning_rate": 2.0413437462975944e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9755360,
      "step": 34820
    },
    {
      "epoch": 386.94444444444446,
      "grad_norm": 5.760929298048723e-07,
      "learning_rate": 2.0374599759748843e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9756784,
      "step": 34825
    },
    {
      "epoch": 387.0,
      "grad_norm": 5.450116304928088e-07,
      "learning_rate": 2.033579746764419e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9758160,
      "step": 34830
    },
    {
      "epoch": 387.05555555555554,
      "grad_norm": 1.652459786782856e-06,
      "learning_rate": 2.029703059264565e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9759536,
      "step": 34835
    },
    {
      "epoch": 387.1111111111111,
      "grad_norm": 4.866423068961012e-07,
      "learning_rate": 2.02582991407316e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9760896,
      "step": 34840
    },
    {
      "epoch": 387.1666666666667,
      "grad_norm": 5.372552323024138e-07,
      "learning_rate": 2.0219603117874992e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9762272,
      "step": 34845
    },
    {
      "epoch": 387.22222222222223,
      "grad_norm": 8.60351804021775e-07,
      "learning_rate": 2.0180942530043156e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9763648,
      "step": 34850
    },
    {
      "epoch": 387.27777777777777,
      "grad_norm": 1.015285192806914e-06,
      "learning_rate": 2.0142317383198107e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9765072,
      "step": 34855
    },
    {
      "epoch": 387.3333333333333,
      "grad_norm": 6.488083386102517e-07,
      "learning_rate": 2.0103727683296243e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9766496,
      "step": 34860
    },
    {
      "epoch": 387.3888888888889,
      "grad_norm": 5.514810368367762e-07,
      "learning_rate": 2.0065173436288636e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9767888,
      "step": 34865
    },
    {
      "epoch": 387.44444444444446,
      "grad_norm": 6.178404419188155e-07,
      "learning_rate": 2.002665464812087e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9769312,
      "step": 34870
    },
    {
      "epoch": 387.5,
      "grad_norm": 9.809831453821971e-07,
      "learning_rate": 1.998817132473291e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9770768,
      "step": 34875
    },
    {
      "epoch": 387.55555555555554,
      "grad_norm": 6.290122769314621e-07,
      "learning_rate": 1.9949723472059507e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9772240,
      "step": 34880
    },
    {
      "epoch": 387.6111111111111,
      "grad_norm": 4.542431781828782e-07,
      "learning_rate": 1.9911311096029726e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9773648,
      "step": 34885
    },
    {
      "epoch": 387.6666666666667,
      "grad_norm": 1.0901544555963483e-06,
      "learning_rate": 1.9872934202567224e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9775040,
      "step": 34890
    },
    {
      "epoch": 387.72222222222223,
      "grad_norm": 1.6790122572274413e-06,
      "learning_rate": 1.9834592797590257e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9776448,
      "step": 34895
    },
    {
      "epoch": 387.77777777777777,
      "grad_norm": 5.867094046152488e-07,
      "learning_rate": 1.979628688701149e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9777888,
      "step": 34900
    },
    {
      "epoch": 387.8333333333333,
      "grad_norm": 1.493264562668628e-06,
      "learning_rate": 1.9758016476738193e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9779328,
      "step": 34905
    },
    {
      "epoch": 387.8888888888889,
      "grad_norm": 6.338015623441606e-07,
      "learning_rate": 1.971978157267221e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9780688,
      "step": 34910
    },
    {
      "epoch": 387.94444444444446,
      "grad_norm": 5.377540333029174e-07,
      "learning_rate": 1.968158218070973e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9782064,
      "step": 34915
    },
    {
      "epoch": 388.0,
      "grad_norm": 8.975915193332185e-07,
      "learning_rate": 1.9643418306741682e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9783408,
      "step": 34920
    },
    {
      "epoch": 388.05555555555554,
      "grad_norm": 5.554391009354731e-07,
      "learning_rate": 1.9605289956653337e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9784832,
      "step": 34925
    },
    {
      "epoch": 388.1111111111111,
      "grad_norm": 8.637226756036398e-07,
      "learning_rate": 1.9567197136324626e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9786240,
      "step": 34930
    },
    {
      "epoch": 388.1666666666667,
      "grad_norm": 9.853317806118866e-07,
      "learning_rate": 1.9529139851629935e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9787664,
      "step": 34935
    },
    {
      "epoch": 388.22222222222223,
      "grad_norm": 1.6577808992224163e-06,
      "learning_rate": 1.949111810843812e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9789088,
      "step": 34940
    },
    {
      "epoch": 388.27777777777777,
      "grad_norm": 3.808782764735952e-07,
      "learning_rate": 1.9453131912612694e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9790528,
      "step": 34945
    },
    {
      "epoch": 388.3333333333333,
      "grad_norm": 4.901472152596398e-07,
      "learning_rate": 1.941518127001149e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9791952,
      "step": 34950
    },
    {
      "epoch": 388.3888888888889,
      "grad_norm": 5.273508918435255e-07,
      "learning_rate": 1.9377266186487107e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9793312,
      "step": 34955
    },
    {
      "epoch": 388.44444444444446,
      "grad_norm": 9.740405175762135e-07,
      "learning_rate": 1.9339386667886483e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9794688,
      "step": 34960
    },
    {
      "epoch": 388.5,
      "grad_norm": 1.4734223441337235e-06,
      "learning_rate": 1.9301542720051024e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9796080,
      "step": 34965
    },
    {
      "epoch": 388.55555555555554,
      "grad_norm": 1.6583176147833e-06,
      "learning_rate": 1.926373434881684e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9797440,
      "step": 34970
    },
    {
      "epoch": 388.6111111111111,
      "grad_norm": 9.222825383403688e-07,
      "learning_rate": 1.9225961560014468e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9798832,
      "step": 34975
    },
    {
      "epoch": 388.6666666666667,
      "grad_norm": 5.621706691272266e-07,
      "learning_rate": 1.918822435946885e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9800240,
      "step": 34980
    },
    {
      "epoch": 388.72222222222223,
      "grad_norm": 5.57291173208796e-07,
      "learning_rate": 1.915052275299961e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9801616,
      "step": 34985
    },
    {
      "epoch": 388.77777777777777,
      "grad_norm": 4.808561584468407e-07,
      "learning_rate": 1.9112856746420854e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9803072,
      "step": 34990
    },
    {
      "epoch": 388.8333333333333,
      "grad_norm": 1.032163595482416e-06,
      "learning_rate": 1.907522634554104e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9804448,
      "step": 34995
    },
    {
      "epoch": 388.8888888888889,
      "grad_norm": 1.4924170272934134e-06,
      "learning_rate": 1.9037631556163337e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9805840,
      "step": 35000
    },
    {
      "epoch": 388.8888888888889,
      "eval_loss": 0.34753549098968506,
      "eval_runtime": 1.3034,
      "eval_samples_per_second": 30.689,
      "eval_steps_per_second": 15.345,
      "num_input_tokens_seen": 9805840,
      "step": 35000
    },
    {
      "epoch": 388.94444444444446,
      "grad_norm": 1.0523610853852006e-06,
      "learning_rate": 1.9000072384085272e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9807200,
      "step": 35005
    },
    {
      "epoch": 389.0,
      "grad_norm": 5.854654432368989e-07,
      "learning_rate": 1.8962548835098987e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9808608,
      "step": 35010
    },
    {
      "epoch": 389.05555555555554,
      "grad_norm": 6.58642420603428e-07,
      "learning_rate": 1.8925060914991077e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9810032,
      "step": 35015
    },
    {
      "epoch": 389.1111111111111,
      "grad_norm": 5.106382445774216e-07,
      "learning_rate": 1.888760862954264e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9811424,
      "step": 35020
    },
    {
      "epoch": 389.1666666666667,
      "grad_norm": 4.808892981600366e-07,
      "learning_rate": 1.8850191984529309e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9812816,
      "step": 35025
    },
    {
      "epoch": 389.22222222222223,
      "grad_norm": 1.4698825907544233e-06,
      "learning_rate": 1.8812810985721186e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9814176,
      "step": 35030
    },
    {
      "epoch": 389.27777777777777,
      "grad_norm": 5.154743689672614e-07,
      "learning_rate": 1.8775465638882856e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9815552,
      "step": 35035
    },
    {
      "epoch": 389.3333333333333,
      "grad_norm": 6.477105216617929e-07,
      "learning_rate": 1.8738155949773517e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9816976,
      "step": 35040
    },
    {
      "epoch": 389.3888888888889,
      "grad_norm": 1.6323439240295556e-06,
      "learning_rate": 1.8700881924146707e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9818416,
      "step": 35045
    },
    {
      "epoch": 389.44444444444446,
      "grad_norm": 1.6837348084663972e-06,
      "learning_rate": 1.8663643567750577e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9819840,
      "step": 35050
    },
    {
      "epoch": 389.5,
      "grad_norm": 9.855389180302154e-07,
      "learning_rate": 1.8626440886327813e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9821216,
      "step": 35055
    },
    {
      "epoch": 389.55555555555554,
      "grad_norm": 2.270507138746325e-06,
      "learning_rate": 1.8589273885615432e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9822640,
      "step": 35060
    },
    {
      "epoch": 389.6111111111111,
      "grad_norm": 5.476325668496429e-07,
      "learning_rate": 1.8552142571345133e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9824064,
      "step": 35065
    },
    {
      "epoch": 389.6666666666667,
      "grad_norm": 5.469198072205472e-07,
      "learning_rate": 1.8515046949243025e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9825520,
      "step": 35070
    },
    {
      "epoch": 389.72222222222223,
      "grad_norm": 5.253792778603383e-07,
      "learning_rate": 1.8477987025029674e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9826864,
      "step": 35075
    },
    {
      "epoch": 389.77777777777777,
      "grad_norm": 6.821308033977402e-07,
      "learning_rate": 1.8440962804420232e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9828272,
      "step": 35080
    },
    {
      "epoch": 389.8333333333333,
      "grad_norm": 1.479608272347832e-06,
      "learning_rate": 1.8403974293124265e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9829632,
      "step": 35085
    },
    {
      "epoch": 389.8888888888889,
      "grad_norm": 6.252241178117401e-07,
      "learning_rate": 1.8367021496845854e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9831072,
      "step": 35090
    },
    {
      "epoch": 389.94444444444446,
      "grad_norm": 2.185480070693302e-06,
      "learning_rate": 1.8330104421283662e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9832448,
      "step": 35095
    },
    {
      "epoch": 390.0,
      "grad_norm": 5.059361001258367e-07,
      "learning_rate": 1.8293223072130717e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9833840,
      "step": 35100
    },
    {
      "epoch": 390.05555555555554,
      "grad_norm": 1.6658511867717607e-06,
      "learning_rate": 1.8256377455074525e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9835216,
      "step": 35105
    },
    {
      "epoch": 390.1111111111111,
      "grad_norm": 9.483865142101422e-07,
      "learning_rate": 1.8219567575797263e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9836640,
      "step": 35110
    },
    {
      "epoch": 390.1666666666667,
      "grad_norm": 6.099728580011288e-07,
      "learning_rate": 1.8182793439975365e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9838096,
      "step": 35115
    },
    {
      "epoch": 390.22222222222223,
      "grad_norm": 9.18178216124943e-07,
      "learning_rate": 1.8146055053279958e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9839456,
      "step": 35120
    },
    {
      "epoch": 390.27777777777777,
      "grad_norm": 6.11188511356886e-07,
      "learning_rate": 1.8109352421376486e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9840832,
      "step": 35125
    },
    {
      "epoch": 390.3333333333333,
      "grad_norm": 1.0053366850115708e-06,
      "learning_rate": 1.8072685549924972e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9842256,
      "step": 35130
    },
    {
      "epoch": 390.3888888888889,
      "grad_norm": 1.5107987110241083e-06,
      "learning_rate": 1.8036054444579982e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9843632,
      "step": 35135
    },
    {
      "epoch": 390.44444444444446,
      "grad_norm": 9.63285970101424e-07,
      "learning_rate": 1.7999459110990407e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9845056,
      "step": 35140
    },
    {
      "epoch": 390.5,
      "grad_norm": 4.801815407518006e-07,
      "learning_rate": 1.7962899554799712e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9846416,
      "step": 35145
    },
    {
      "epoch": 390.55555555555554,
      "grad_norm": 6.254358595469967e-07,
      "learning_rate": 1.7926375781645937e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9847808,
      "step": 35150
    },
    {
      "epoch": 390.6111111111111,
      "grad_norm": 5.735550985264126e-07,
      "learning_rate": 1.7889887797161359e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9849184,
      "step": 35155
    },
    {
      "epoch": 390.6666666666667,
      "grad_norm": 4.5777181867379113e-07,
      "learning_rate": 1.7853435606973028e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9850576,
      "step": 35160
    },
    {
      "epoch": 390.72222222222223,
      "grad_norm": 5.84373367473745e-07,
      "learning_rate": 1.781701921670223e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9851920,
      "step": 35165
    },
    {
      "epoch": 390.77777777777777,
      "grad_norm": 4.7577105988239055e-07,
      "learning_rate": 1.7780638631964886e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9853392,
      "step": 35170
    },
    {
      "epoch": 390.8333333333333,
      "grad_norm": 5.580261586146662e-07,
      "learning_rate": 1.7744293858371314e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9854816,
      "step": 35175
    },
    {
      "epoch": 390.8888888888889,
      "grad_norm": 5.097837743051059e-07,
      "learning_rate": 1.770798490152631e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9856240,
      "step": 35180
    },
    {
      "epoch": 390.94444444444446,
      "grad_norm": 1.4906792102920008e-06,
      "learning_rate": 1.767171176702917e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9857616,
      "step": 35185
    },
    {
      "epoch": 391.0,
      "grad_norm": 5.386638122217846e-07,
      "learning_rate": 1.7635474460473755e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9859056,
      "step": 35190
    },
    {
      "epoch": 391.05555555555554,
      "grad_norm": 5.726241170123103e-07,
      "learning_rate": 1.7599272987448206e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9860480,
      "step": 35195
    },
    {
      "epoch": 391.1111111111111,
      "grad_norm": 1.9787037217611214e-06,
      "learning_rate": 1.7563107353535362e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9861856,
      "step": 35200
    },
    {
      "epoch": 391.1111111111111,
      "eval_loss": 0.35917389392852783,
      "eval_runtime": 1.2897,
      "eval_samples_per_second": 31.014,
      "eval_steps_per_second": 15.507,
      "num_input_tokens_seen": 9861856,
      "step": 35200
    },
    {
      "epoch": 391.1666666666667,
      "grad_norm": 1.9521107788023073e-06,
      "learning_rate": 1.7526977564312263e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9863248,
      "step": 35205
    },
    {
      "epoch": 391.22222222222223,
      "grad_norm": 5.576131911766424e-07,
      "learning_rate": 1.7490883625350701e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9864592,
      "step": 35210
    },
    {
      "epoch": 391.27777777777777,
      "grad_norm": 4.76668702731331e-07,
      "learning_rate": 1.7454825542216807e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9866000,
      "step": 35215
    },
    {
      "epoch": 391.3333333333333,
      "grad_norm": 5.925040227339196e-07,
      "learning_rate": 1.7418803320471105e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9867360,
      "step": 35220
    },
    {
      "epoch": 391.3888888888889,
      "grad_norm": 6.189350756358181e-07,
      "learning_rate": 1.7382816965668737e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9868752,
      "step": 35225
    },
    {
      "epoch": 391.44444444444446,
      "grad_norm": 5.422832600743277e-07,
      "learning_rate": 1.7346866483359285e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9870160,
      "step": 35230
    },
    {
      "epoch": 391.5,
      "grad_norm": 5.81890844841837e-07,
      "learning_rate": 1.7310951879086657e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9871552,
      "step": 35235
    },
    {
      "epoch": 391.55555555555554,
      "grad_norm": 5.996004688313405e-07,
      "learning_rate": 1.7275073158389471e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9872960,
      "step": 35240
    },
    {
      "epoch": 391.6111111111111,
      "grad_norm": 9.444406714465003e-07,
      "learning_rate": 1.723923032680061e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9874352,
      "step": 35245
    },
    {
      "epoch": 391.6666666666667,
      "grad_norm": 4.874118531006388e-07,
      "learning_rate": 1.7203423389847428e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9875792,
      "step": 35250
    },
    {
      "epoch": 391.72222222222223,
      "grad_norm": 3.9317224036494736e-06,
      "learning_rate": 1.7167652353051928e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9877216,
      "step": 35255
    },
    {
      "epoch": 391.77777777777777,
      "grad_norm": 6.494476565421792e-07,
      "learning_rate": 1.7131917221930333e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9878656,
      "step": 35260
    },
    {
      "epoch": 391.8333333333333,
      "grad_norm": 2.0625031993404264e-06,
      "learning_rate": 1.7096218001993513e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9880048,
      "step": 35265
    },
    {
      "epoch": 391.8888888888889,
      "grad_norm": 6.490328701147519e-07,
      "learning_rate": 1.706055469874676e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9881488,
      "step": 35270
    },
    {
      "epoch": 391.94444444444446,
      "grad_norm": 9.201384045809391e-07,
      "learning_rate": 1.702492731768976e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9882848,
      "step": 35275
    },
    {
      "epoch": 392.0,
      "grad_norm": 9.473646400692814e-07,
      "learning_rate": 1.6989335864316724e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9884240,
      "step": 35280
    },
    {
      "epoch": 392.05555555555554,
      "grad_norm": 4.842224257117778e-07,
      "learning_rate": 1.6953780344116265e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9885664,
      "step": 35285
    },
    {
      "epoch": 392.1111111111111,
      "grad_norm": 5.442099109131959e-07,
      "learning_rate": 1.6918260762571497e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9887040,
      "step": 35290
    },
    {
      "epoch": 392.1666666666667,
      "grad_norm": 9.394590847477957e-07,
      "learning_rate": 1.6882777125160093e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9888400,
      "step": 35295
    },
    {
      "epoch": 392.22222222222223,
      "grad_norm": 6.241863843570172e-07,
      "learning_rate": 1.6847329437353899e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9889808,
      "step": 35300
    },
    {
      "epoch": 392.27777777777777,
      "grad_norm": 5.975979320282931e-07,
      "learning_rate": 1.6811917704619511e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9891200,
      "step": 35305
    },
    {
      "epoch": 392.3333333333333,
      "grad_norm": 6.45877662464045e-07,
      "learning_rate": 1.67765419324179e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9892592,
      "step": 35310
    },
    {
      "epoch": 392.3888888888889,
      "grad_norm": 5.318493094819132e-07,
      "learning_rate": 1.6741202126204364e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9893984,
      "step": 35315
    },
    {
      "epoch": 392.44444444444446,
      "grad_norm": 9.300774195253325e-07,
      "learning_rate": 1.6705898291428767e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9895376,
      "step": 35320
    },
    {
      "epoch": 392.5,
      "grad_norm": 6.016259703756077e-07,
      "learning_rate": 1.6670630433535395e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9896800,
      "step": 35325
    },
    {
      "epoch": 392.55555555555554,
      "grad_norm": 9.355475754091458e-07,
      "learning_rate": 1.6635398557962979e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9898176,
      "step": 35330
    },
    {
      "epoch": 392.6111111111111,
      "grad_norm": 1.4750984291822533e-06,
      "learning_rate": 1.660020267014481e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9899632,
      "step": 35335
    },
    {
      "epoch": 392.6666666666667,
      "grad_norm": 5.954848916189803e-07,
      "learning_rate": 1.6565042775508438e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9901024,
      "step": 35340
    },
    {
      "epoch": 392.72222222222223,
      "grad_norm": 2.0155359834461706e-06,
      "learning_rate": 1.6529918879475997e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9902448,
      "step": 35345
    },
    {
      "epoch": 392.77777777777777,
      "grad_norm": 2.8865670174127445e-06,
      "learning_rate": 1.6494830987464043e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9903808,
      "step": 35350
    },
    {
      "epoch": 392.8333333333333,
      "grad_norm": 5.527477355826704e-07,
      "learning_rate": 1.6459779104883555e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9905248,
      "step": 35355
    },
    {
      "epoch": 392.8888888888889,
      "grad_norm": 9.288397109230573e-07,
      "learning_rate": 1.6424763237140013e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9906672,
      "step": 35360
    },
    {
      "epoch": 392.94444444444446,
      "grad_norm": 6.065221782591834e-07,
      "learning_rate": 1.6389783389633207e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9908064,
      "step": 35365
    },
    {
      "epoch": 393.0,
      "grad_norm": 6.00291286900756e-07,
      "learning_rate": 1.6354839567757546e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9909488,
      "step": 35370
    },
    {
      "epoch": 393.05555555555554,
      "grad_norm": 1.4954634934838396e-06,
      "learning_rate": 1.6319931776901831e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9910864,
      "step": 35375
    },
    {
      "epoch": 393.1111111111111,
      "grad_norm": 6.070046083550551e-07,
      "learning_rate": 1.6285060022449229e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9912272,
      "step": 35380
    },
    {
      "epoch": 393.1666666666667,
      "grad_norm": 9.468188864047988e-07,
      "learning_rate": 1.6250224309777434e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9913680,
      "step": 35385
    },
    {
      "epoch": 393.22222222222223,
      "grad_norm": 5.61711885893601e-07,
      "learning_rate": 1.6215424644258515e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9915088,
      "step": 35390
    },
    {
      "epoch": 393.27777777777777,
      "grad_norm": 5.380420589062851e-07,
      "learning_rate": 1.6180661031259036e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9916480,
      "step": 35395
    },
    {
      "epoch": 393.3333333333333,
      "grad_norm": 5.876290742889978e-07,
      "learning_rate": 1.614593347613999e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9917904,
      "step": 35400
    },
    {
      "epoch": 393.3333333333333,
      "eval_loss": 0.35188406705856323,
      "eval_runtime": 1.3047,
      "eval_samples_per_second": 30.659,
      "eval_steps_per_second": 15.329,
      "num_input_tokens_seen": 9917904,
      "step": 35400
    },
    {
      "epoch": 393.3888888888889,
      "grad_norm": 6.152305331852403e-07,
      "learning_rate": 1.6111241984256758e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9919264,
      "step": 35405
    },
    {
      "epoch": 393.44444444444446,
      "grad_norm": 1.0344662086936296e-06,
      "learning_rate": 1.6076586560959257e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9920672,
      "step": 35410
    },
    {
      "epoch": 393.5,
      "grad_norm": 4.996040843252558e-07,
      "learning_rate": 1.604196721159182e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9922048,
      "step": 35415
    },
    {
      "epoch": 393.55555555555554,
      "grad_norm": 5.877270723431138e-07,
      "learning_rate": 1.6007383941493092e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9923472,
      "step": 35420
    },
    {
      "epoch": 393.6111111111111,
      "grad_norm": 5.448256388262962e-07,
      "learning_rate": 1.5972836755996285e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9924864,
      "step": 35425
    },
    {
      "epoch": 393.6666666666667,
      "grad_norm": 4.223069254294387e-07,
      "learning_rate": 1.5938325660429076e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9926256,
      "step": 35430
    },
    {
      "epoch": 393.72222222222223,
      "grad_norm": 5.511674316949211e-07,
      "learning_rate": 1.5903850660113378e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9927664,
      "step": 35435
    },
    {
      "epoch": 393.77777777777777,
      "grad_norm": 5.878031288375496e-07,
      "learning_rate": 1.5869411760365826e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9929072,
      "step": 35440
    },
    {
      "epoch": 393.8333333333333,
      "grad_norm": 5.07714048580965e-07,
      "learning_rate": 1.58350089664972e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9930464,
      "step": 35445
    },
    {
      "epoch": 393.8888888888889,
      "grad_norm": 9.847342425928218e-07,
      "learning_rate": 1.5800642283812865e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9931872,
      "step": 35450
    },
    {
      "epoch": 393.94444444444446,
      "grad_norm": 9.671814495959552e-07,
      "learning_rate": 1.5766311717612698e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9933296,
      "step": 35455
    },
    {
      "epoch": 394.0,
      "grad_norm": 5.480602567331516e-07,
      "learning_rate": 1.5732017273190818e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9934640,
      "step": 35460
    },
    {
      "epoch": 394.05555555555554,
      "grad_norm": 3.440635055085295e-06,
      "learning_rate": 1.5697758955835806e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9936064,
      "step": 35465
    },
    {
      "epoch": 394.1111111111111,
      "grad_norm": 9.462314096708724e-07,
      "learning_rate": 1.566353677083085e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9937424,
      "step": 35470
    },
    {
      "epoch": 394.1666666666667,
      "grad_norm": 5.454044753605558e-07,
      "learning_rate": 1.562935072345334e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9938816,
      "step": 35475
    },
    {
      "epoch": 394.22222222222223,
      "grad_norm": 1.020030140352901e-06,
      "learning_rate": 1.5595200818975281e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9940192,
      "step": 35480
    },
    {
      "epoch": 394.27777777777777,
      "grad_norm": 6.286883262873744e-07,
      "learning_rate": 1.5561087062662905e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9941568,
      "step": 35485
    },
    {
      "epoch": 394.3333333333333,
      "grad_norm": 1.5075288501975592e-06,
      "learning_rate": 1.5527009459777087e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9942976,
      "step": 35490
    },
    {
      "epoch": 394.3888888888889,
      "grad_norm": 5.936133220529882e-07,
      "learning_rate": 1.5492968015572984e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9944448,
      "step": 35495
    },
    {
      "epoch": 394.44444444444446,
      "grad_norm": 8.509542226420308e-07,
      "learning_rate": 1.5458962735300203e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9945856,
      "step": 35500
    },
    {
      "epoch": 394.5,
      "grad_norm": 1.6560502444917802e-06,
      "learning_rate": 1.54249936242028e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9947280,
      "step": 35505
    },
    {
      "epoch": 394.55555555555554,
      "grad_norm": 1.9471383438940393e-06,
      "learning_rate": 1.5391060687519222e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9948640,
      "step": 35510
    },
    {
      "epoch": 394.6111111111111,
      "grad_norm": 5.286660211822891e-07,
      "learning_rate": 1.5357163930482367e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9950048,
      "step": 35515
    },
    {
      "epoch": 394.6666666666667,
      "grad_norm": 4.999689053875045e-07,
      "learning_rate": 1.532330335831955e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9951504,
      "step": 35520
    },
    {
      "epoch": 394.72222222222223,
      "grad_norm": 5.889699536965054e-07,
      "learning_rate": 1.5289478976252491e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9952880,
      "step": 35525
    },
    {
      "epoch": 394.77777777777777,
      "grad_norm": 4.2525496724010736e-07,
      "learning_rate": 1.5255690789497345e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9954304,
      "step": 35530
    },
    {
      "epoch": 394.8333333333333,
      "grad_norm": 1.5189018540695542e-06,
      "learning_rate": 1.5221938803264641e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9955728,
      "step": 35535
    },
    {
      "epoch": 394.8888888888889,
      "grad_norm": 5.307948072186264e-07,
      "learning_rate": 1.518822302275938e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9957136,
      "step": 35540
    },
    {
      "epoch": 394.94444444444446,
      "grad_norm": 9.175834065899835e-07,
      "learning_rate": 1.5154543453180958e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9958576,
      "step": 35545
    },
    {
      "epoch": 395.0,
      "grad_norm": 6.602377311537566e-07,
      "learning_rate": 1.5120900099723167e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9959920,
      "step": 35550
    },
    {
      "epoch": 395.05555555555554,
      "grad_norm": 6.15940052739461e-07,
      "learning_rate": 1.5087292967574273e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9961312,
      "step": 35555
    },
    {
      "epoch": 395.1111111111111,
      "grad_norm": 2.108705530190491e-06,
      "learning_rate": 1.5053722061916908e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9962672,
      "step": 35560
    },
    {
      "epoch": 395.1666666666667,
      "grad_norm": 6.038202968738915e-07,
      "learning_rate": 1.5020187387928124e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9964032,
      "step": 35565
    },
    {
      "epoch": 395.22222222222223,
      "grad_norm": 1.9349092781340005e-06,
      "learning_rate": 1.4986688950779343e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9965488,
      "step": 35570
    },
    {
      "epoch": 395.27777777777777,
      "grad_norm": 6.413953315131948e-07,
      "learning_rate": 1.495322675563654e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9966912,
      "step": 35575
    },
    {
      "epoch": 395.3333333333333,
      "grad_norm": 5.556977953347086e-07,
      "learning_rate": 1.4919800807659922e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9968288,
      "step": 35580
    },
    {
      "epoch": 395.3888888888889,
      "grad_norm": 5.988950420032779e-07,
      "learning_rate": 1.4886411112004255e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9969696,
      "step": 35585
    },
    {
      "epoch": 395.44444444444446,
      "grad_norm": 1.0221150432698778e-06,
      "learning_rate": 1.4853057673818588e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9971072,
      "step": 35590
    },
    {
      "epoch": 395.5,
      "grad_norm": 5.648243472933245e-07,
      "learning_rate": 1.481974049824647e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9972464,
      "step": 35595
    },
    {
      "epoch": 395.55555555555554,
      "grad_norm": 5.371300062506634e-07,
      "learning_rate": 1.4786459590425849e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9973888,
      "step": 35600
    },
    {
      "epoch": 395.55555555555554,
      "eval_loss": 0.36891934275627136,
      "eval_runtime": 1.294,
      "eval_samples_per_second": 30.913,
      "eval_steps_per_second": 15.457,
      "num_input_tokens_seen": 9973888,
      "step": 35600
    },
    {
      "epoch": 395.6111111111111,
      "grad_norm": 8.989781008494901e-07,
      "learning_rate": 1.4753214955489036e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9975296,
      "step": 35605
    },
    {
      "epoch": 395.6666666666667,
      "grad_norm": 5.147520028003782e-07,
      "learning_rate": 1.4720006598562737e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9976704,
      "step": 35610
    },
    {
      "epoch": 395.72222222222223,
      "grad_norm": 1.7100315972129465e-06,
      "learning_rate": 1.4686834524768185e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9978112,
      "step": 35615
    },
    {
      "epoch": 395.77777777777777,
      "grad_norm": 6.808083981013624e-07,
      "learning_rate": 1.4653698739220844e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9979520,
      "step": 35620
    },
    {
      "epoch": 395.8333333333333,
      "grad_norm": 4.996255142941664e-07,
      "learning_rate": 1.4620599247030715e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9980896,
      "step": 35625
    },
    {
      "epoch": 395.8888888888889,
      "grad_norm": 5.230037913861452e-07,
      "learning_rate": 1.4587536053302125e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9982320,
      "step": 35630
    },
    {
      "epoch": 395.94444444444446,
      "grad_norm": 1.6973860965663334e-06,
      "learning_rate": 1.4554509163133862e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9983728,
      "step": 35635
    },
    {
      "epoch": 396.0,
      "grad_norm": 5.779332354904909e-07,
      "learning_rate": 1.4521518581619098e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9985136,
      "step": 35640
    },
    {
      "epoch": 396.05555555555554,
      "grad_norm": 1.6935490521063912e-06,
      "learning_rate": 1.4488564313845348e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9986544,
      "step": 35645
    },
    {
      "epoch": 396.1111111111111,
      "grad_norm": 9.701089993541245e-07,
      "learning_rate": 1.4455646364894603e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9987936,
      "step": 35650
    },
    {
      "epoch": 396.1666666666667,
      "grad_norm": 9.80106392489688e-07,
      "learning_rate": 1.4422764739843247e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9989312,
      "step": 35655
    },
    {
      "epoch": 396.22222222222223,
      "grad_norm": 5.375168825594301e-07,
      "learning_rate": 1.4389919443762e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9990704,
      "step": 35660
    },
    {
      "epoch": 396.27777777777777,
      "grad_norm": 4.580152221933531e-07,
      "learning_rate": 1.4357110481716063e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9992144,
      "step": 35665
    },
    {
      "epoch": 396.3333333333333,
      "grad_norm": 9.416602324563428e-07,
      "learning_rate": 1.4324337858764941e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9993552,
      "step": 35670
    },
    {
      "epoch": 396.3888888888889,
      "grad_norm": 9.736785386849078e-07,
      "learning_rate": 1.4291601579962622e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9994992,
      "step": 35675
    },
    {
      "epoch": 396.44444444444446,
      "grad_norm": 4.715194563686964e-07,
      "learning_rate": 1.42589016503574e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9996464,
      "step": 35680
    },
    {
      "epoch": 396.5,
      "grad_norm": 5.961272222521075e-07,
      "learning_rate": 1.4226238074992099e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9997888,
      "step": 35685
    },
    {
      "epoch": 396.55555555555554,
      "grad_norm": 6.060794248696766e-07,
      "learning_rate": 1.4193610858903778e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 9999312,
      "step": 35690
    },
    {
      "epoch": 396.6111111111111,
      "grad_norm": 1.6481766351716942e-06,
      "learning_rate": 1.416102000712402e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10000688,
      "step": 35695
    },
    {
      "epoch": 396.6666666666667,
      "grad_norm": 1.008204662866774e-06,
      "learning_rate": 1.4128465524678668e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10002064,
      "step": 35700
    },
    {
      "epoch": 396.72222222222223,
      "grad_norm": 1.089812712962157e-06,
      "learning_rate": 1.4095947416588124e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10003472,
      "step": 35705
    },
    {
      "epoch": 396.77777777777777,
      "grad_norm": 1.7176488427139702e-06,
      "learning_rate": 1.4063465687866983e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10004880,
      "step": 35710
    },
    {
      "epoch": 396.8333333333333,
      "grad_norm": 6.217580335032835e-07,
      "learning_rate": 1.4031020343524438e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10006320,
      "step": 35715
    },
    {
      "epoch": 396.8888888888889,
      "grad_norm": 5.63646381124272e-07,
      "learning_rate": 1.3998611388563926e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10007712,
      "step": 35720
    },
    {
      "epoch": 396.94444444444446,
      "grad_norm": 5.400956979428884e-07,
      "learning_rate": 1.3966238827983314e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10009088,
      "step": 35725
    },
    {
      "epoch": 397.0,
      "grad_norm": 5.355356620384555e-07,
      "learning_rate": 1.393390266677483e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10010400,
      "step": 35730
    },
    {
      "epoch": 397.05555555555554,
      "grad_norm": 1.940315996762365e-06,
      "learning_rate": 1.3901602909925204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10011808,
      "step": 35735
    },
    {
      "epoch": 397.1111111111111,
      "grad_norm": 1.5220135765048326e-06,
      "learning_rate": 1.3869339562415373e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10013264,
      "step": 35740
    },
    {
      "epoch": 397.1666666666667,
      "grad_norm": 6.287663154580514e-07,
      "learning_rate": 1.38371126292208e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10014688,
      "step": 35745
    },
    {
      "epoch": 397.22222222222223,
      "grad_norm": 5.319872684594884e-07,
      "learning_rate": 1.3804922115311286e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10016096,
      "step": 35750
    },
    {
      "epoch": 397.27777777777777,
      "grad_norm": 6.22817594830849e-07,
      "learning_rate": 1.3772768025650945e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10017456,
      "step": 35755
    },
    {
      "epoch": 397.3333333333333,
      "grad_norm": 5.734542583013535e-07,
      "learning_rate": 1.3740650365198448e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10018832,
      "step": 35760
    },
    {
      "epoch": 397.3888888888889,
      "grad_norm": 5.886896019546839e-07,
      "learning_rate": 1.3708569138906612e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10020240,
      "step": 35765
    },
    {
      "epoch": 397.44444444444446,
      "grad_norm": 5.162039542483399e-07,
      "learning_rate": 1.367652435172287e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10021632,
      "step": 35770
    },
    {
      "epoch": 397.5,
      "grad_norm": 4.882623443336342e-07,
      "learning_rate": 1.364451600858893e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10023056,
      "step": 35775
    },
    {
      "epoch": 397.55555555555554,
      "grad_norm": 9.434330650037737e-07,
      "learning_rate": 1.3612544114440823e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10024496,
      "step": 35780
    },
    {
      "epoch": 397.6111111111111,
      "grad_norm": 5.745372391174897e-07,
      "learning_rate": 1.3580608674209072e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10025888,
      "step": 35785
    },
    {
      "epoch": 397.6666666666667,
      "grad_norm": 6.105570378167613e-07,
      "learning_rate": 1.3548709692818434e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10027296,
      "step": 35790
    },
    {
      "epoch": 397.72222222222223,
      "grad_norm": 2.2770809664507397e-06,
      "learning_rate": 1.3516847175188223e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10028656,
      "step": 35795
    },
    {
      "epoch": 397.77777777777777,
      "grad_norm": 1.0493512263565208e-06,
      "learning_rate": 1.348502112623204e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10030096,
      "step": 35800
    },
    {
      "epoch": 397.77777777777777,
      "eval_loss": 0.33812960982322693,
      "eval_runtime": 1.3169,
      "eval_samples_per_second": 30.373,
      "eval_steps_per_second": 15.187,
      "num_input_tokens_seen": 10030096,
      "step": 35800
    },
    {
      "epoch": 397.8333333333333,
      "grad_norm": 5.830632403558411e-07,
      "learning_rate": 1.3453231550857787e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10031488,
      "step": 35805
    },
    {
      "epoch": 397.8888888888889,
      "grad_norm": 3.4733291158772772e-06,
      "learning_rate": 1.3421478453967878e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10032880,
      "step": 35810
    },
    {
      "epoch": 397.94444444444446,
      "grad_norm": 4.6807633680145955e-07,
      "learning_rate": 1.3389761840459065e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10034320,
      "step": 35815
    },
    {
      "epoch": 398.0,
      "grad_norm": 5.138456344866427e-07,
      "learning_rate": 1.3358081715222376e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10035680,
      "step": 35820
    },
    {
      "epoch": 398.05555555555554,
      "grad_norm": 6.404679311344808e-07,
      "learning_rate": 1.3326438083143295e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10037104,
      "step": 35825
    },
    {
      "epoch": 398.1111111111111,
      "grad_norm": 8.995506277642562e-07,
      "learning_rate": 1.3294830949101723e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10038496,
      "step": 35830
    },
    {
      "epoch": 398.1666666666667,
      "grad_norm": 2.1365431166486815e-06,
      "learning_rate": 1.3263260317971815e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10039904,
      "step": 35835
    },
    {
      "epoch": 398.22222222222223,
      "grad_norm": 2.8028957785863895e-06,
      "learning_rate": 1.3231726194622208e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10041312,
      "step": 35840
    },
    {
      "epoch": 398.27777777777777,
      "grad_norm": 4.898303700429096e-07,
      "learning_rate": 1.3200228583915814e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10042720,
      "step": 35845
    },
    {
      "epoch": 398.3333333333333,
      "grad_norm": 5.551146387006156e-07,
      "learning_rate": 1.3168767490709971e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10044096,
      "step": 35850
    },
    {
      "epoch": 398.3888888888889,
      "grad_norm": 4.818448928745056e-07,
      "learning_rate": 1.3137342919856437e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10045488,
      "step": 35855
    },
    {
      "epoch": 398.44444444444446,
      "grad_norm": 5.228728241490899e-07,
      "learning_rate": 1.310595487620117e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10046896,
      "step": 35860
    },
    {
      "epoch": 398.5,
      "grad_norm": 5.791359853901668e-07,
      "learning_rate": 1.3074603364584715e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10048288,
      "step": 35865
    },
    {
      "epoch": 398.55555555555554,
      "grad_norm": 9.756781764735933e-07,
      "learning_rate": 1.3043288389841758e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10049648,
      "step": 35870
    },
    {
      "epoch": 398.6111111111111,
      "grad_norm": 5.607672619589721e-07,
      "learning_rate": 1.3012009956801546e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10051104,
      "step": 35875
    },
    {
      "epoch": 398.6666666666667,
      "grad_norm": 5.940947858107393e-07,
      "learning_rate": 1.2980768070287586e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10052480,
      "step": 35880
    },
    {
      "epoch": 398.72222222222223,
      "grad_norm": 9.861844318947988e-07,
      "learning_rate": 1.2949562735117716e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10053856,
      "step": 35885
    },
    {
      "epoch": 398.77777777777777,
      "grad_norm": 5.333753279046505e-07,
      "learning_rate": 1.291839395610428e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10055264,
      "step": 35890
    },
    {
      "epoch": 398.8333333333333,
      "grad_norm": 1.5105980537555297e-06,
      "learning_rate": 1.2887261738053852e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10056672,
      "step": 35895
    },
    {
      "epoch": 398.8888888888889,
      "grad_norm": 1.6662817188262125e-06,
      "learning_rate": 1.2856166085767396e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10058032,
      "step": 35900
    },
    {
      "epoch": 398.94444444444446,
      "grad_norm": 1.661857481849438e-06,
      "learning_rate": 1.2825107004040272e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10059440,
      "step": 35905
    },
    {
      "epoch": 399.0,
      "grad_norm": 2.2177089249453275e-06,
      "learning_rate": 1.2794084497662146e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10060880,
      "step": 35910
    },
    {
      "epoch": 399.05555555555554,
      "grad_norm": 4.599372402935842e-07,
      "learning_rate": 1.276309857141711e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10062320,
      "step": 35915
    },
    {
      "epoch": 399.1111111111111,
      "grad_norm": 4.3733743382290413e-07,
      "learning_rate": 1.273214923008359e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10063728,
      "step": 35920
    },
    {
      "epoch": 399.1666666666667,
      "grad_norm": 9.34994545787049e-07,
      "learning_rate": 1.2701236478434352e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10065152,
      "step": 35925
    },
    {
      "epoch": 399.22222222222223,
      "grad_norm": 5.26959013313899e-07,
      "learning_rate": 1.2670360321236502e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10066576,
      "step": 35930
    },
    {
      "epoch": 399.27777777777777,
      "grad_norm": 6.365834792632086e-07,
      "learning_rate": 1.2639520763251617e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10068000,
      "step": 35935
    },
    {
      "epoch": 399.3333333333333,
      "grad_norm": 5.76799948248663e-07,
      "learning_rate": 1.2608717809235448e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10069392,
      "step": 35940
    },
    {
      "epoch": 399.3888888888889,
      "grad_norm": 5.939422749179357e-07,
      "learning_rate": 1.2577951463938282e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10070784,
      "step": 35945
    },
    {
      "epoch": 399.44444444444446,
      "grad_norm": 4.0842675730345945e-07,
      "learning_rate": 1.2547221732104569e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10072192,
      "step": 35950
    },
    {
      "epoch": 399.5,
      "grad_norm": 9.105255003305501e-07,
      "learning_rate": 1.25165286184733e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10073552,
      "step": 35955
    },
    {
      "epoch": 399.55555555555554,
      "grad_norm": 5.01439672007109e-07,
      "learning_rate": 1.248587212777777e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10074976,
      "step": 35960
    },
    {
      "epoch": 399.6111111111111,
      "grad_norm": 6.670824177490431e-07,
      "learning_rate": 1.2455252264745532e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10076384,
      "step": 35965
    },
    {
      "epoch": 399.6666666666667,
      "grad_norm": 5.042545581090963e-07,
      "learning_rate": 1.2424669034098528e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10077776,
      "step": 35970
    },
    {
      "epoch": 399.72222222222223,
      "grad_norm": 5.866958758815599e-07,
      "learning_rate": 1.2394122440553185e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10079168,
      "step": 35975
    },
    {
      "epoch": 399.77777777777777,
      "grad_norm": 1.6547780887776753e-06,
      "learning_rate": 1.2363612488820037e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10080608,
      "step": 35980
    },
    {
      "epoch": 399.8333333333333,
      "grad_norm": 9.831652505454258e-07,
      "learning_rate": 1.2333139183604208e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10082016,
      "step": 35985
    },
    {
      "epoch": 399.8888888888889,
      "grad_norm": 1.6707025451978552e-06,
      "learning_rate": 1.2302702529604998e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10083424,
      "step": 35990
    },
    {
      "epoch": 399.94444444444446,
      "grad_norm": 5.2925577165297e-07,
      "learning_rate": 1.227230253151615e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10084800,
      "step": 35995
    },
    {
      "epoch": 400.0,
      "grad_norm": 5.736004027312447e-07,
      "learning_rate": 1.2241939194025748e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10086192,
      "step": 36000
    },
    {
      "epoch": 400.0,
      "eval_loss": 0.3451782464981079,
      "eval_runtime": 1.2839,
      "eval_samples_per_second": 31.156,
      "eval_steps_per_second": 15.578,
      "num_input_tokens_seen": 10086192,
      "step": 36000
    },
    {
      "epoch": 400.05555555555554,
      "grad_norm": 3.129387096123537e-06,
      "learning_rate": 1.2211612521816156e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10087664,
      "step": 36005
    },
    {
      "epoch": 400.1111111111111,
      "grad_norm": 5.24416861935606e-07,
      "learning_rate": 1.2181322519564137e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10089088,
      "step": 36010
    },
    {
      "epoch": 400.1666666666667,
      "grad_norm": 5.228778832133685e-07,
      "learning_rate": 1.2151069191940839e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10090512,
      "step": 36015
    },
    {
      "epoch": 400.22222222222223,
      "grad_norm": 6.245318786568532e-07,
      "learning_rate": 1.2120852543611644e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10091968,
      "step": 36020
    },
    {
      "epoch": 400.27777777777777,
      "grad_norm": 6.054993946236209e-07,
      "learning_rate": 1.2090672579236379e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10093408,
      "step": 36025
    },
    {
      "epoch": 400.3333333333333,
      "grad_norm": 5.770214670519636e-07,
      "learning_rate": 1.2060529303469126e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10094800,
      "step": 36030
    },
    {
      "epoch": 400.3888888888889,
      "grad_norm": 6.378460852829448e-07,
      "learning_rate": 1.2030422720958445e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10096176,
      "step": 36035
    },
    {
      "epoch": 400.44444444444446,
      "grad_norm": 5.593782930191082e-07,
      "learning_rate": 1.200035283634704e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10097568,
      "step": 36040
    },
    {
      "epoch": 400.5,
      "grad_norm": 1.0461885722179431e-06,
      "learning_rate": 1.1970319654272144e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10098992,
      "step": 36045
    },
    {
      "epoch": 400.55555555555554,
      "grad_norm": 1.6366128647860023e-06,
      "learning_rate": 1.1940323179365192e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10100352,
      "step": 36050
    },
    {
      "epoch": 400.6111111111111,
      "grad_norm": 1.4853221728117205e-06,
      "learning_rate": 1.1910363416252095e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10101744,
      "step": 36055
    },
    {
      "epoch": 400.6666666666667,
      "grad_norm": 3.5618616038846085e-06,
      "learning_rate": 1.1880440369552964e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10103120,
      "step": 36060
    },
    {
      "epoch": 400.72222222222223,
      "grad_norm": 6.173540896270424e-07,
      "learning_rate": 1.1850554043882328e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10104496,
      "step": 36065
    },
    {
      "epoch": 400.77777777777777,
      "grad_norm": 4.823452854907373e-07,
      "learning_rate": 1.1820704443849028e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10105920,
      "step": 36070
    },
    {
      "epoch": 400.8333333333333,
      "grad_norm": 5.795362199023657e-07,
      "learning_rate": 1.1790891574056219e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10107328,
      "step": 36075
    },
    {
      "epoch": 400.8888888888889,
      "grad_norm": 1.6490856751261163e-06,
      "learning_rate": 1.1761115439101523e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10108688,
      "step": 36080
    },
    {
      "epoch": 400.94444444444446,
      "grad_norm": 6.077606826693227e-07,
      "learning_rate": 1.1731376043576659e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10110080,
      "step": 36085
    },
    {
      "epoch": 401.0,
      "grad_norm": 5.591251692749211e-07,
      "learning_rate": 1.1701673392067875e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10111424,
      "step": 36090
    },
    {
      "epoch": 401.05555555555554,
      "grad_norm": 4.936859454574005e-07,
      "learning_rate": 1.1672007489155757e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10112880,
      "step": 36095
    },
    {
      "epoch": 401.1111111111111,
      "grad_norm": 5.041438839725743e-07,
      "learning_rate": 1.164237833941506e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10114320,
      "step": 36100
    },
    {
      "epoch": 401.1666666666667,
      "grad_norm": 3.5496786949806847e-06,
      "learning_rate": 1.1612785947415022e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10115728,
      "step": 36105
    },
    {
      "epoch": 401.22222222222223,
      "grad_norm": 5.265264348963683e-07,
      "learning_rate": 1.1583230317719185e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10117136,
      "step": 36110
    },
    {
      "epoch": 401.27777777777777,
      "grad_norm": 8.987164505924738e-07,
      "learning_rate": 1.1553711454885318e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10118496,
      "step": 36115
    },
    {
      "epoch": 401.3333333333333,
      "grad_norm": 8.918503340282768e-07,
      "learning_rate": 1.152422936346567e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10119856,
      "step": 36120
    },
    {
      "epoch": 401.3888888888889,
      "grad_norm": 5.460875627250061e-07,
      "learning_rate": 1.1494784048006718e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10121232,
      "step": 36125
    },
    {
      "epoch": 401.44444444444446,
      "grad_norm": 5.687892326022848e-07,
      "learning_rate": 1.1465375513049326e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10122624,
      "step": 36130
    },
    {
      "epoch": 401.5,
      "grad_norm": 1.967118578249938e-06,
      "learning_rate": 1.1436003763128616e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10124064,
      "step": 36135
    },
    {
      "epoch": 401.55555555555554,
      "grad_norm": 4.2699329583228973e-07,
      "learning_rate": 1.1406668802774106e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10125456,
      "step": 36140
    },
    {
      "epoch": 401.6111111111111,
      "grad_norm": 5.040965334046632e-07,
      "learning_rate": 1.137737063650965e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10126864,
      "step": 36145
    },
    {
      "epoch": 401.6666666666667,
      "grad_norm": 8.593639790888119e-07,
      "learning_rate": 1.1348109268853323e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10128288,
      "step": 36150
    },
    {
      "epoch": 401.72222222222223,
      "grad_norm": 5.004062586522195e-07,
      "learning_rate": 1.1318884704317634e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10129712,
      "step": 36155
    },
    {
      "epoch": 401.77777777777777,
      "grad_norm": 5.329370083018148e-07,
      "learning_rate": 1.1289696947409417e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10131120,
      "step": 36160
    },
    {
      "epoch": 401.8333333333333,
      "grad_norm": 5.464082164508e-07,
      "learning_rate": 1.126054600262974e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10132512,
      "step": 36165
    },
    {
      "epoch": 401.8888888888889,
      "grad_norm": 1.6757121557020582e-06,
      "learning_rate": 1.1231431874474064e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10133872,
      "step": 36170
    },
    {
      "epoch": 401.94444444444446,
      "grad_norm": 8.289406423500623e-07,
      "learning_rate": 1.12023545674321e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10135280,
      "step": 36175
    },
    {
      "epoch": 402.0,
      "grad_norm": 5.780069614047534e-07,
      "learning_rate": 1.117331408598804e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10136672,
      "step": 36180
    },
    {
      "epoch": 402.05555555555554,
      "grad_norm": 5.859614589098783e-07,
      "learning_rate": 1.1144310434620191e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10138096,
      "step": 36185
    },
    {
      "epoch": 402.1111111111111,
      "grad_norm": 5.591809895122424e-07,
      "learning_rate": 1.1115343617801365e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10139472,
      "step": 36190
    },
    {
      "epoch": 402.1666666666667,
      "grad_norm": 5.0000056717181e-07,
      "learning_rate": 1.1086413639998515e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10140896,
      "step": 36195
    },
    {
      "epoch": 402.22222222222223,
      "grad_norm": 6.027188419466256e-07,
      "learning_rate": 1.1057520505673103e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10142304,
      "step": 36200
    },
    {
      "epoch": 402.22222222222223,
      "eval_loss": 0.33484143018722534,
      "eval_runtime": 1.2967,
      "eval_samples_per_second": 30.848,
      "eval_steps_per_second": 15.424,
      "num_input_tokens_seen": 10142304,
      "step": 36200
    },
    {
      "epoch": 402.27777777777777,
      "grad_norm": 5.220095999902696e-07,
      "learning_rate": 1.1028664219280727e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10143712,
      "step": 36205
    },
    {
      "epoch": 402.3333333333333,
      "grad_norm": 5.719035129914118e-07,
      "learning_rate": 1.0999844785271468e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10145136,
      "step": 36210
    },
    {
      "epoch": 402.3888888888889,
      "grad_norm": 9.542458201394766e-07,
      "learning_rate": 1.097106220808955e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10146512,
      "step": 36215
    },
    {
      "epoch": 402.44444444444446,
      "grad_norm": 5.815646204609948e-07,
      "learning_rate": 1.0942316492173698e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10147920,
      "step": 36220
    },
    {
      "epoch": 402.5,
      "grad_norm": 5.131411171532818e-07,
      "learning_rate": 1.0913607641956841e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10149264,
      "step": 36225
    },
    {
      "epoch": 402.55555555555554,
      "grad_norm": 1.489465830672998e-06,
      "learning_rate": 1.0884935661866213e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10150672,
      "step": 36230
    },
    {
      "epoch": 402.6111111111111,
      "grad_norm": 8.975362675300858e-07,
      "learning_rate": 1.0856300556323418e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10152080,
      "step": 36235
    },
    {
      "epoch": 402.6666666666667,
      "grad_norm": 5.133474019203277e-07,
      "learning_rate": 1.0827702329744365e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10153456,
      "step": 36240
    },
    {
      "epoch": 402.72222222222223,
      "grad_norm": 5.400295322033344e-07,
      "learning_rate": 1.0799140986539197e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10154864,
      "step": 36245
    },
    {
      "epoch": 402.77777777777777,
      "grad_norm": 6.542637152051611e-07,
      "learning_rate": 1.0770616531112526e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10156288,
      "step": 36250
    },
    {
      "epoch": 402.8333333333333,
      "grad_norm": 4.159317370522331e-07,
      "learning_rate": 1.0742128967863085e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10157696,
      "step": 36255
    },
    {
      "epoch": 402.8888888888889,
      "grad_norm": 5.793268087472825e-07,
      "learning_rate": 1.071367830118411e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10159072,
      "step": 36260
    },
    {
      "epoch": 402.94444444444446,
      "grad_norm": 9.080087579604879e-07,
      "learning_rate": 1.068526453546298e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10160464,
      "step": 36265
    },
    {
      "epoch": 403.0,
      "grad_norm": 6.197303150656808e-07,
      "learning_rate": 1.0656887675081467e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10161824,
      "step": 36270
    },
    {
      "epoch": 403.05555555555554,
      "grad_norm": 5.43550754628086e-07,
      "learning_rate": 1.0628547724415628e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10163184,
      "step": 36275
    },
    {
      "epoch": 403.1111111111111,
      "grad_norm": 9.462647199143248e-07,
      "learning_rate": 1.0600244687835881e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10164592,
      "step": 36280
    },
    {
      "epoch": 403.1666666666667,
      "grad_norm": 6.166495154502627e-07,
      "learning_rate": 1.0571978569706876e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10166000,
      "step": 36285
    },
    {
      "epoch": 403.22222222222223,
      "grad_norm": 1.7598080148673034e-06,
      "learning_rate": 1.0543749374387652e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10167360,
      "step": 36290
    },
    {
      "epoch": 403.27777777777777,
      "grad_norm": 6.22336926880962e-07,
      "learning_rate": 1.051555710623142e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10168752,
      "step": 36295
    },
    {
      "epoch": 403.3333333333333,
      "grad_norm": 6.1657630112677e-07,
      "learning_rate": 1.0487401769585847e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10170144,
      "step": 36300
    },
    {
      "epoch": 403.3888888888889,
      "grad_norm": 1.63966524269199e-06,
      "learning_rate": 1.0459283368792845e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10171568,
      "step": 36305
    },
    {
      "epoch": 403.44444444444446,
      "grad_norm": 1.5038730225569452e-06,
      "learning_rate": 1.043120190818858e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10172992,
      "step": 36310
    },
    {
      "epoch": 403.5,
      "grad_norm": 2.7966443667537533e-06,
      "learning_rate": 1.0403157392103596e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10174384,
      "step": 36315
    },
    {
      "epoch": 403.55555555555554,
      "grad_norm": 6.042128006811254e-07,
      "learning_rate": 1.0375149824862735e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10175776,
      "step": 36320
    },
    {
      "epoch": 403.6111111111111,
      "grad_norm": 1.4785874782319297e-06,
      "learning_rate": 1.034717921078507e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10177232,
      "step": 36325
    },
    {
      "epoch": 403.6666666666667,
      "grad_norm": 5.214474185777362e-07,
      "learning_rate": 1.0319245554184009e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10178640,
      "step": 36330
    },
    {
      "epoch": 403.72222222222223,
      "grad_norm": 9.482547511652228e-07,
      "learning_rate": 1.0291348859367361e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10180048,
      "step": 36335
    },
    {
      "epoch": 403.77777777777777,
      "grad_norm": 4.5137733195588225e-07,
      "learning_rate": 1.0263489130637016e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10181488,
      "step": 36340
    },
    {
      "epoch": 403.8333333333333,
      "grad_norm": 2.3293555386771914e-06,
      "learning_rate": 1.0235666372289427e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10182912,
      "step": 36345
    },
    {
      "epoch": 403.8888888888889,
      "grad_norm": 4.618179616500129e-07,
      "learning_rate": 1.0207880588615076e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10184320,
      "step": 36350
    },
    {
      "epoch": 403.94444444444446,
      "grad_norm": 6.009188382449793e-07,
      "learning_rate": 1.0180131783898984e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10185696,
      "step": 36355
    },
    {
      "epoch": 404.0,
      "grad_norm": 6.539347054967948e-07,
      "learning_rate": 1.0152419962420362e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10187088,
      "step": 36360
    },
    {
      "epoch": 404.05555555555554,
      "grad_norm": 9.768154995981604e-07,
      "learning_rate": 1.0124745128452685e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10188496,
      "step": 36365
    },
    {
      "epoch": 404.1111111111111,
      "grad_norm": 3.1622898859495763e-06,
      "learning_rate": 1.0097107286263758e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10189824,
      "step": 36370
    },
    {
      "epoch": 404.1666666666667,
      "grad_norm": 9.049369964486687e-07,
      "learning_rate": 1.00695064401157e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10191280,
      "step": 36375
    },
    {
      "epoch": 404.22222222222223,
      "grad_norm": 8.525009889126522e-07,
      "learning_rate": 1.0041942594264886e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10192672,
      "step": 36380
    },
    {
      "epoch": 404.27777777777777,
      "grad_norm": 6.718436225128244e-07,
      "learning_rate": 1.001441575296208e-06,
      "loss": 0.0,
      "num_input_tokens_seen": 10194096,
      "step": 36385
    },
    {
      "epoch": 404.3333333333333,
      "grad_norm": 5.52630297079304e-07,
      "learning_rate": 9.986925920452139e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10195520,
      "step": 36390
    },
    {
      "epoch": 404.3888888888889,
      "grad_norm": 1.0049056982097682e-06,
      "learning_rate": 9.959473100974475e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10196912,
      "step": 36395
    },
    {
      "epoch": 404.44444444444446,
      "grad_norm": 1.983403990379884e-06,
      "learning_rate": 9.932057298762564e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10198320,
      "step": 36400
    },
    {
      "epoch": 404.44444444444446,
      "eval_loss": 0.3221988081932068,
      "eval_runtime": 1.2942,
      "eval_samples_per_second": 30.907,
      "eval_steps_per_second": 15.454,
      "num_input_tokens_seen": 10198320,
      "step": 36400
    },
    {
      "epoch": 404.5,
      "grad_norm": 1.5087432529981015e-06,
      "learning_rate": 9.90467851804433e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10199744,
      "step": 36405
    },
    {
      "epoch": 404.55555555555554,
      "grad_norm": 6.583383651559416e-07,
      "learning_rate": 9.877336763041895e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10201136,
      "step": 36410
    },
    {
      "epoch": 404.6111111111111,
      "grad_norm": 4.351853135631245e-07,
      "learning_rate": 9.850032037971662e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10202560,
      "step": 36415
    },
    {
      "epoch": 404.6666666666667,
      "grad_norm": 6.890293207106879e-07,
      "learning_rate": 9.822764347044406e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10203968,
      "step": 36420
    },
    {
      "epoch": 404.72222222222223,
      "grad_norm": 5.62996660846693e-07,
      "learning_rate": 9.795533694465175e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10205360,
      "step": 36425
    },
    {
      "epoch": 404.77777777777777,
      "grad_norm": 1.6820689552332624e-06,
      "learning_rate": 9.768340084433197e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10206784,
      "step": 36430
    },
    {
      "epoch": 404.8333333333333,
      "grad_norm": 9.559513500789762e-07,
      "learning_rate": 9.741183521142143e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10208192,
      "step": 36435
    },
    {
      "epoch": 404.8888888888889,
      "grad_norm": 6.584502330042596e-07,
      "learning_rate": 9.714064008779889e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10209536,
      "step": 36440
    },
    {
      "epoch": 404.94444444444446,
      "grad_norm": 3.352795374667039e-07,
      "learning_rate": 9.686981551528584e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10210912,
      "step": 36445
    },
    {
      "epoch": 405.0,
      "grad_norm": 5.613916869151581e-07,
      "learning_rate": 9.65993615356467e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10212320,
      "step": 36450
    },
    {
      "epoch": 405.05555555555554,
      "grad_norm": 5.859732254975825e-07,
      "learning_rate": 9.632927819058917e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10213696,
      "step": 36455
    },
    {
      "epoch": 405.1111111111111,
      "grad_norm": 1.6857221680766088e-06,
      "learning_rate": 9.605956552176305e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10215120,
      "step": 36460
    },
    {
      "epoch": 405.1666666666667,
      "grad_norm": 6.348237775455345e-07,
      "learning_rate": 9.579022357076223e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10216528,
      "step": 36465
    },
    {
      "epoch": 405.22222222222223,
      "grad_norm": 5.47818729046412e-07,
      "learning_rate": 9.552125237912158e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10217904,
      "step": 36470
    },
    {
      "epoch": 405.27777777777777,
      "grad_norm": 1.6823804571686196e-06,
      "learning_rate": 9.525265198832096e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10219264,
      "step": 36475
    },
    {
      "epoch": 405.3333333333333,
      "grad_norm": 9.799061899684602e-07,
      "learning_rate": 9.498442243978112e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10220688,
      "step": 36480
    },
    {
      "epoch": 405.3888888888889,
      "grad_norm": 5.242609404376708e-07,
      "learning_rate": 9.471656377486649e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10222048,
      "step": 36485
    },
    {
      "epoch": 405.44444444444446,
      "grad_norm": 5.886802796339907e-07,
      "learning_rate": 9.444907603488456e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10223504,
      "step": 36490
    },
    {
      "epoch": 405.5,
      "grad_norm": 6.272993573475105e-07,
      "learning_rate": 9.418195926108514e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10224896,
      "step": 36495
    },
    {
      "epoch": 405.55555555555554,
      "grad_norm": 6.475028726526944e-07,
      "learning_rate": 9.391521349466053e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10226336,
      "step": 36500
    },
    {
      "epoch": 405.6111111111111,
      "grad_norm": 5.403438194662158e-07,
      "learning_rate": 9.364883877674758e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10227744,
      "step": 36505
    },
    {
      "epoch": 405.6666666666667,
      "grad_norm": 5.548124590859516e-07,
      "learning_rate": 9.33828351484231e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10229168,
      "step": 36510
    },
    {
      "epoch": 405.72222222222223,
      "grad_norm": 5.499146595866478e-07,
      "learning_rate": 9.311720265070906e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10230512,
      "step": 36515
    },
    {
      "epoch": 405.77777777777777,
      "grad_norm": 5.596353958026157e-07,
      "learning_rate": 9.285194132456931e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10231904,
      "step": 36520
    },
    {
      "epoch": 405.8333333333333,
      "grad_norm": 1.0482356174179586e-06,
      "learning_rate": 9.258705121091032e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10233264,
      "step": 36525
    },
    {
      "epoch": 405.8888888888889,
      "grad_norm": 2.282614786963677e-06,
      "learning_rate": 9.232253235058136e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10234688,
      "step": 36530
    },
    {
      "epoch": 405.94444444444446,
      "grad_norm": 3.228205287086894e-06,
      "learning_rate": 9.205838478437478e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10236096,
      "step": 36535
    },
    {
      "epoch": 406.0,
      "grad_norm": 1.0112415793628315e-06,
      "learning_rate": 9.179460855302524e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10237488,
      "step": 36540
    },
    {
      "epoch": 406.05555555555554,
      "grad_norm": 5.18860815645894e-07,
      "learning_rate": 9.153120369721046e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10238880,
      "step": 36545
    },
    {
      "epoch": 406.1111111111111,
      "grad_norm": 5.38062920441007e-07,
      "learning_rate": 9.126817025755103e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10240304,
      "step": 36550
    },
    {
      "epoch": 406.1666666666667,
      "grad_norm": 6.309726359177148e-07,
      "learning_rate": 9.100550827460947e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10241648,
      "step": 36555
    },
    {
      "epoch": 406.22222222222223,
      "grad_norm": 6.942885875105276e-07,
      "learning_rate": 9.0743217788892e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10243104,
      "step": 36560
    },
    {
      "epoch": 406.27777777777777,
      "grad_norm": 1.6342008848369005e-06,
      "learning_rate": 9.048129884084683e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10244480,
      "step": 36565
    },
    {
      "epoch": 406.3333333333333,
      "grad_norm": 6.586474796677066e-07,
      "learning_rate": 9.021975147086553e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10245872,
      "step": 36570
    },
    {
      "epoch": 406.3888888888889,
      "grad_norm": 6.028682832948107e-07,
      "learning_rate": 8.995857571928141e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10247264,
      "step": 36575
    },
    {
      "epoch": 406.44444444444446,
      "grad_norm": 8.982911481325573e-07,
      "learning_rate": 8.969777162637139e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10248656,
      "step": 36580
    },
    {
      "epoch": 406.5,
      "grad_norm": 9.463068977311195e-07,
      "learning_rate": 8.943733923235525e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10250032,
      "step": 36585
    },
    {
      "epoch": 406.55555555555554,
      "grad_norm": 5.43188093615754e-07,
      "learning_rate": 8.917727857739394e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10251424,
      "step": 36590
    },
    {
      "epoch": 406.6111111111111,
      "grad_norm": 5.814763994749228e-07,
      "learning_rate": 8.891758970159258e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10252864,
      "step": 36595
    },
    {
      "epoch": 406.6666666666667,
      "grad_norm": 9.27325118027511e-07,
      "learning_rate": 8.86582726449986e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10254256,
      "step": 36600
    },
    {
      "epoch": 406.6666666666667,
      "eval_loss": 0.37285032868385315,
      "eval_runtime": 1.3177,
      "eval_samples_per_second": 30.355,
      "eval_steps_per_second": 15.178,
      "num_input_tokens_seen": 10254256,
      "step": 36600
    },
    {
      "epoch": 406.72222222222223,
      "grad_norm": 1.6112383036670508e-06,
      "learning_rate": 8.839932744760165e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10255648,
      "step": 36605
    },
    {
      "epoch": 406.77777777777777,
      "grad_norm": 2.045959035967826e-06,
      "learning_rate": 8.814075414933482e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10257040,
      "step": 36610
    },
    {
      "epoch": 406.8333333333333,
      "grad_norm": 1.6668014950482757e-06,
      "learning_rate": 8.788255279007257e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10258448,
      "step": 36615
    },
    {
      "epoch": 406.8888888888889,
      "grad_norm": 4.490925391564815e-07,
      "learning_rate": 8.762472340963362e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10259872,
      "step": 36620
    },
    {
      "epoch": 406.94444444444446,
      "grad_norm": 1.9921985767723527e-06,
      "learning_rate": 8.736726604777811e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10261216,
      "step": 36625
    },
    {
      "epoch": 407.0,
      "grad_norm": 1.7189585150845232e-06,
      "learning_rate": 8.711018074420901e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10262608,
      "step": 36630
    },
    {
      "epoch": 407.05555555555554,
      "grad_norm": 1.6801972151370137e-06,
      "learning_rate": 8.685346753857209e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10263984,
      "step": 36635
    },
    {
      "epoch": 407.1111111111111,
      "grad_norm": 5.730659040636965e-07,
      "learning_rate": 8.659712647045654e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10265376,
      "step": 36640
    },
    {
      "epoch": 407.1666666666667,
      "grad_norm": 5.317843374541553e-07,
      "learning_rate": 8.634115757939209e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10266752,
      "step": 36645
    },
    {
      "epoch": 407.22222222222223,
      "grad_norm": 9.432228011974075e-07,
      "learning_rate": 8.608556090485387e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10268144,
      "step": 36650
    },
    {
      "epoch": 407.27777777777777,
      "grad_norm": 6.131572831691301e-07,
      "learning_rate": 8.583033648625671e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10269536,
      "step": 36655
    },
    {
      "epoch": 407.3333333333333,
      "grad_norm": 4.935645279147138e-07,
      "learning_rate": 8.557548436295998e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10270896,
      "step": 36660
    },
    {
      "epoch": 407.3888888888889,
      "grad_norm": 1.066956087925064e-06,
      "learning_rate": 8.532100457426556e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10272368,
      "step": 36665
    },
    {
      "epoch": 407.44444444444446,
      "grad_norm": 5.543762426896137e-07,
      "learning_rate": 8.506689715941679e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10273760,
      "step": 36670
    },
    {
      "epoch": 407.5,
      "grad_norm": 9.445622595194436e-07,
      "learning_rate": 8.481316215760011e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10275120,
      "step": 36675
    },
    {
      "epoch": 407.55555555555554,
      "grad_norm": 6.021345484441554e-07,
      "learning_rate": 8.455979960794558e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10276576,
      "step": 36680
    },
    {
      "epoch": 407.6111111111111,
      "grad_norm": 5.547123578253377e-07,
      "learning_rate": 8.430680954952364e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10277936,
      "step": 36685
    },
    {
      "epoch": 407.6666666666667,
      "grad_norm": 1.496443815085513e-06,
      "learning_rate": 8.405419202134974e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10279328,
      "step": 36690
    },
    {
      "epoch": 407.72222222222223,
      "grad_norm": 5.147054480403312e-07,
      "learning_rate": 8.380194706237993e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10280720,
      "step": 36695
    },
    {
      "epoch": 407.77777777777777,
      "grad_norm": 9.674944294602028e-07,
      "learning_rate": 8.355007471151366e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10282160,
      "step": 36700
    },
    {
      "epoch": 407.8333333333333,
      "grad_norm": 9.900857094180537e-07,
      "learning_rate": 8.329857500759292e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10283536,
      "step": 36705
    },
    {
      "epoch": 407.8888888888889,
      "grad_norm": 5.064671313448343e-07,
      "learning_rate": 8.304744798940194e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10284944,
      "step": 36710
    },
    {
      "epoch": 407.94444444444446,
      "grad_norm": 1.005402737064287e-06,
      "learning_rate": 8.279669369566756e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10286304,
      "step": 36715
    },
    {
      "epoch": 408.0,
      "grad_norm": 8.80479319675942e-07,
      "learning_rate": 8.254631216505993e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10287728,
      "step": 36720
    },
    {
      "epoch": 408.05555555555554,
      "grad_norm": 2.2117085336503806e-06,
      "learning_rate": 8.229630343619038e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10289136,
      "step": 36725
    },
    {
      "epoch": 408.1111111111111,
      "grad_norm": 5.459464773593936e-07,
      "learning_rate": 8.204666754761392e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10290528,
      "step": 36730
    },
    {
      "epoch": 408.1666666666667,
      "grad_norm": 6.251397621781507e-07,
      "learning_rate": 8.179740453782669e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10291936,
      "step": 36735
    },
    {
      "epoch": 408.22222222222223,
      "grad_norm": 6.567773311871861e-07,
      "learning_rate": 8.154851444526907e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10293312,
      "step": 36740
    },
    {
      "epoch": 408.27777777777777,
      "grad_norm": 4.153918382598931e-07,
      "learning_rate": 8.129999730832283e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10294656,
      "step": 36745
    },
    {
      "epoch": 408.3333333333333,
      "grad_norm": 5.934222144787782e-07,
      "learning_rate": 8.105185316531178e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10296048,
      "step": 36750
    },
    {
      "epoch": 408.3888888888889,
      "grad_norm": 5.254291863820981e-07,
      "learning_rate": 8.08040820545039e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10297440,
      "step": 36755
    },
    {
      "epoch": 408.44444444444446,
      "grad_norm": 5.371511520024796e-07,
      "learning_rate": 8.055668401410782e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10298880,
      "step": 36760
    },
    {
      "epoch": 408.5,
      "grad_norm": 2.1759105948149227e-06,
      "learning_rate": 8.030965908227578e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10300304,
      "step": 36765
    },
    {
      "epoch": 408.55555555555554,
      "grad_norm": 9.752430969456327e-07,
      "learning_rate": 8.006300729710203e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10301712,
      "step": 36770
    },
    {
      "epoch": 408.6111111111111,
      "grad_norm": 5.480750928654743e-07,
      "learning_rate": 7.981672869662337e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10303104,
      "step": 36775
    },
    {
      "epoch": 408.6666666666667,
      "grad_norm": 9.272865213461046e-07,
      "learning_rate": 7.957082331881888e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10304496,
      "step": 36780
    },
    {
      "epoch": 408.72222222222223,
      "grad_norm": 5.917299858992919e-07,
      "learning_rate": 7.932529120161069e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10305856,
      "step": 36785
    },
    {
      "epoch": 408.77777777777777,
      "grad_norm": 5.417857664724579e-07,
      "learning_rate": 7.908013238286243e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10307312,
      "step": 36790
    },
    {
      "epoch": 408.8333333333333,
      "grad_norm": 9.514595262771763e-07,
      "learning_rate": 7.883534690038136e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10308704,
      "step": 36795
    },
    {
      "epoch": 408.8888888888889,
      "grad_norm": 9.909458640322555e-07,
      "learning_rate": 7.859093479191559e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10310096,
      "step": 36800
    },
    {
      "epoch": 408.8888888888889,
      "eval_loss": 0.3391804099082947,
      "eval_runtime": 1.3055,
      "eval_samples_per_second": 30.64,
      "eval_steps_per_second": 15.32,
      "num_input_tokens_seen": 10310096,
      "step": 36800
    },
    {
      "epoch": 408.94444444444446,
      "grad_norm": 9.586411806594697e-07,
      "learning_rate": 7.834689609515722e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10311536,
      "step": 36805
    },
    {
      "epoch": 409.0,
      "grad_norm": 1.9211238395655528e-06,
      "learning_rate": 7.810323084774002e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10312928,
      "step": 36810
    },
    {
      "epoch": 409.05555555555554,
      "grad_norm": 5.378951186685299e-07,
      "learning_rate": 7.785993908723976e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10314304,
      "step": 36815
    },
    {
      "epoch": 409.1111111111111,
      "grad_norm": 1.0169610504817683e-06,
      "learning_rate": 7.761702085117534e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10315696,
      "step": 36820
    },
    {
      "epoch": 409.1666666666667,
      "grad_norm": 5.985238544781168e-07,
      "learning_rate": 7.737447617700844e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10317104,
      "step": 36825
    },
    {
      "epoch": 409.22222222222223,
      "grad_norm": 6.370761980178941e-07,
      "learning_rate": 7.713230510214136e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10318496,
      "step": 36830
    },
    {
      "epoch": 409.27777777777777,
      "grad_norm": 3.4888769278040854e-06,
      "learning_rate": 7.689050766392092e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10319872,
      "step": 36835
    },
    {
      "epoch": 409.3333333333333,
      "grad_norm": 5.76260049456323e-07,
      "learning_rate": 7.664908389963477e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10321296,
      "step": 36840
    },
    {
      "epoch": 409.3888888888889,
      "grad_norm": 5.082048915028281e-07,
      "learning_rate": 7.64080338465134e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10322704,
      "step": 36845
    },
    {
      "epoch": 409.44444444444446,
      "grad_norm": 9.318953857473389e-07,
      "learning_rate": 7.616735754173043e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10324064,
      "step": 36850
    },
    {
      "epoch": 409.5,
      "grad_norm": 1.7263881773033063e-06,
      "learning_rate": 7.592705502240005e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10325456,
      "step": 36855
    },
    {
      "epoch": 409.55555555555554,
      "grad_norm": 1.0536965646679164e-06,
      "learning_rate": 7.568712632558095e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10326816,
      "step": 36860
    },
    {
      "epoch": 409.6111111111111,
      "grad_norm": 2.8710774131468497e-06,
      "learning_rate": 7.544757148827297e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10328240,
      "step": 36865
    },
    {
      "epoch": 409.6666666666667,
      "grad_norm": 2.8369609026412945e-06,
      "learning_rate": 7.520839054741797e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10329664,
      "step": 36870
    },
    {
      "epoch": 409.72222222222223,
      "grad_norm": 1.0174803719564807e-06,
      "learning_rate": 7.496958353990113e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10331056,
      "step": 36875
    },
    {
      "epoch": 409.77777777777777,
      "grad_norm": 6.702085215692932e-07,
      "learning_rate": 7.473115050254941e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10332528,
      "step": 36880
    },
    {
      "epoch": 409.8333333333333,
      "grad_norm": 5.504031150849187e-07,
      "learning_rate": 7.449309147213173e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10333904,
      "step": 36885
    },
    {
      "epoch": 409.8888888888889,
      "grad_norm": 5.765105584032426e-07,
      "learning_rate": 7.425540648536067e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10335280,
      "step": 36890
    },
    {
      "epoch": 409.94444444444446,
      "grad_norm": 5.862979151061154e-07,
      "learning_rate": 7.40180955788894e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10336656,
      "step": 36895
    },
    {
      "epoch": 410.0,
      "grad_norm": 1.5088660347828409e-06,
      "learning_rate": 7.378115878931474e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10338112,
      "step": 36900
    },
    {
      "epoch": 410.05555555555554,
      "grad_norm": 9.304420700573246e-07,
      "learning_rate": 7.354459615317527e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10339568,
      "step": 36905
    },
    {
      "epoch": 410.1111111111111,
      "grad_norm": 3.1733245577925118e-06,
      "learning_rate": 7.33084077069518e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10340992,
      "step": 36910
    },
    {
      "epoch": 410.1666666666667,
      "grad_norm": 5.823903848067857e-07,
      "learning_rate": 7.307259348706768e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10342384,
      "step": 36915
    },
    {
      "epoch": 410.22222222222223,
      "grad_norm": 5.236004199105082e-07,
      "learning_rate": 7.283715352988801e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10343776,
      "step": 36920
    },
    {
      "epoch": 410.27777777777777,
      "grad_norm": 5.77619971409149e-07,
      "learning_rate": 7.260208787172068e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10345152,
      "step": 36925
    },
    {
      "epoch": 410.3333333333333,
      "grad_norm": 5.773963493993506e-07,
      "learning_rate": 7.23673965488167e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10346576,
      "step": 36930
    },
    {
      "epoch": 410.3888888888889,
      "grad_norm": 6.294091576819483e-07,
      "learning_rate": 7.213307959736709e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10347984,
      "step": 36935
    },
    {
      "epoch": 410.44444444444446,
      "grad_norm": 5.869413826076197e-07,
      "learning_rate": 7.189913705350715e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10349392,
      "step": 36940
    },
    {
      "epoch": 410.5,
      "grad_norm": 1.5002632380856085e-06,
      "learning_rate": 7.166556895331411e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10350768,
      "step": 36945
    },
    {
      "epoch": 410.55555555555554,
      "grad_norm": 6.166550292618922e-07,
      "learning_rate": 7.143237533280639e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10352112,
      "step": 36950
    },
    {
      "epoch": 410.6111111111111,
      "grad_norm": 1.0500774578758865e-06,
      "learning_rate": 7.119955622794578e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10353504,
      "step": 36955
    },
    {
      "epoch": 410.6666666666667,
      "grad_norm": 6.057771315681748e-07,
      "learning_rate": 7.096711167463577e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10354912,
      "step": 36960
    },
    {
      "epoch": 410.72222222222223,
      "grad_norm": 9.55364157562144e-07,
      "learning_rate": 7.073504170872213e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10356288,
      "step": 36965
    },
    {
      "epoch": 410.77777777777777,
      "grad_norm": 3.527313083395711e-06,
      "learning_rate": 7.05033463659932e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10357712,
      "step": 36970
    },
    {
      "epoch": 410.8333333333333,
      "grad_norm": 5.680526555806864e-07,
      "learning_rate": 7.027202568217928e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10359120,
      "step": 36975
    },
    {
      "epoch": 410.8888888888889,
      "grad_norm": 1.6544863683520816e-06,
      "learning_rate": 7.004107969295293e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10360528,
      "step": 36980
    },
    {
      "epoch": 410.94444444444446,
      "grad_norm": 5.424911364571017e-07,
      "learning_rate": 6.9810508433929e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10361936,
      "step": 36985
    },
    {
      "epoch": 411.0,
      "grad_norm": 8.744353863221477e-07,
      "learning_rate": 6.958031194066406e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10363344,
      "step": 36990
    },
    {
      "epoch": 411.05555555555554,
      "grad_norm": 9.09806374238542e-07,
      "learning_rate": 6.935049024865776e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10364752,
      "step": 36995
    },
    {
      "epoch": 411.1111111111111,
      "grad_norm": 1.6988432207654114e-06,
      "learning_rate": 6.912104339335118e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10366160,
      "step": 37000
    },
    {
      "epoch": 411.1111111111111,
      "eval_loss": 0.3407905697822571,
      "eval_runtime": 1.2904,
      "eval_samples_per_second": 30.999,
      "eval_steps_per_second": 15.499,
      "num_input_tokens_seen": 10366160,
      "step": 37000
    },
    {
      "epoch": 411.1666666666667,
      "grad_norm": 5.882420737179928e-07,
      "learning_rate": 6.889197141012799e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10367568,
      "step": 37005
    },
    {
      "epoch": 411.22222222222223,
      "grad_norm": 5.598566303888219e-07,
      "learning_rate": 6.866327433431435e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10368960,
      "step": 37010
    },
    {
      "epoch": 411.27777777777777,
      "grad_norm": 4.6427274469351687e-07,
      "learning_rate": 6.843495220117735e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10370336,
      "step": 37015
    },
    {
      "epoch": 411.3333333333333,
      "grad_norm": 5.858742611053458e-07,
      "learning_rate": 6.820700504592798e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10371728,
      "step": 37020
    },
    {
      "epoch": 411.3888888888889,
      "grad_norm": 1.9365827483852627e-06,
      "learning_rate": 6.797943290371839e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10373136,
      "step": 37025
    },
    {
      "epoch": 411.44444444444446,
      "grad_norm": 4.899028226645896e-06,
      "learning_rate": 6.775223580964274e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10374528,
      "step": 37030
    },
    {
      "epoch": 411.5,
      "grad_norm": 3.7461250030901283e-06,
      "learning_rate": 6.7525413798738e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10375936,
      "step": 37035
    },
    {
      "epoch": 411.55555555555554,
      "grad_norm": 5.769057906945818e-07,
      "learning_rate": 6.729896690598259e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10377376,
      "step": 37040
    },
    {
      "epoch": 411.6111111111111,
      "grad_norm": 1.6640670992273954e-06,
      "learning_rate": 6.707289516629772e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10378752,
      "step": 37045
    },
    {
      "epoch": 411.6666666666667,
      "grad_norm": 5.913153700021212e-07,
      "learning_rate": 6.684719861454692e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10380144,
      "step": 37050
    },
    {
      "epoch": 411.72222222222223,
      "grad_norm": 1.0199381677011843e-06,
      "learning_rate": 6.662187728553481e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10381568,
      "step": 37055
    },
    {
      "epoch": 411.77777777777777,
      "grad_norm": 9.397667781740893e-07,
      "learning_rate": 6.639693121400892e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10382992,
      "step": 37060
    },
    {
      "epoch": 411.8333333333333,
      "grad_norm": 5.457163183564262e-07,
      "learning_rate": 6.617236043465868e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10384416,
      "step": 37065
    },
    {
      "epoch": 411.8888888888889,
      "grad_norm": 5.418528985501325e-07,
      "learning_rate": 6.594816498211587e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10385808,
      "step": 37070
    },
    {
      "epoch": 411.94444444444446,
      "grad_norm": 5.629958081954101e-07,
      "learning_rate": 6.572434489095447e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10387216,
      "step": 37075
    },
    {
      "epoch": 412.0,
      "grad_norm": 5.005005050406908e-07,
      "learning_rate": 6.550090019568994e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10388592,
      "step": 37080
    },
    {
      "epoch": 412.05555555555554,
      "grad_norm": 6.034395596543618e-07,
      "learning_rate": 6.527783093078027e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10389984,
      "step": 37085
    },
    {
      "epoch": 412.1111111111111,
      "grad_norm": 4.815103125110909e-07,
      "learning_rate": 6.5055137130626e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10391392,
      "step": 37090
    },
    {
      "epoch": 412.1666666666667,
      "grad_norm": 1.494383923272835e-06,
      "learning_rate": 6.483281882956854e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10392784,
      "step": 37095
    },
    {
      "epoch": 412.22222222222223,
      "grad_norm": 6.249376269806817e-07,
      "learning_rate": 6.461087606189298e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10394160,
      "step": 37100
    },
    {
      "epoch": 412.27777777777777,
      "grad_norm": 6.216690735527663e-07,
      "learning_rate": 6.438930886182554e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10395568,
      "step": 37105
    },
    {
      "epoch": 412.3333333333333,
      "grad_norm": 5.473258966048888e-07,
      "learning_rate": 6.416811726353417e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10397008,
      "step": 37110
    },
    {
      "epoch": 412.3888888888889,
      "grad_norm": 9.415364843334828e-07,
      "learning_rate": 6.394730130112991e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10398464,
      "step": 37115
    },
    {
      "epoch": 412.44444444444446,
      "grad_norm": 9.466481856179598e-07,
      "learning_rate": 6.372686100866471e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10399824,
      "step": 37120
    },
    {
      "epoch": 412.5,
      "grad_norm": 9.437222274755186e-07,
      "learning_rate": 6.350679642013413e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10401216,
      "step": 37125
    },
    {
      "epoch": 412.55555555555554,
      "grad_norm": 5.915403562539723e-07,
      "learning_rate": 6.328710756947437e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10402624,
      "step": 37130
    },
    {
      "epoch": 412.6111111111111,
      "grad_norm": 1.6156554920598865e-06,
      "learning_rate": 6.306779449056416e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10404016,
      "step": 37135
    },
    {
      "epoch": 412.6666666666667,
      "grad_norm": 5.916661507399112e-07,
      "learning_rate": 6.284885721722422e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10405408,
      "step": 37140
    },
    {
      "epoch": 412.72222222222223,
      "grad_norm": 1.6636387272228603e-06,
      "learning_rate": 6.26302957832181e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10406800,
      "step": 37145
    },
    {
      "epoch": 412.77777777777777,
      "grad_norm": 5.109490075483336e-07,
      "learning_rate": 6.241211022224997e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10408176,
      "step": 37150
    },
    {
      "epoch": 412.8333333333333,
      "grad_norm": 6.176464921736624e-07,
      "learning_rate": 6.219430056796732e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10409584,
      "step": 37155
    },
    {
      "epoch": 412.8888888888889,
      "grad_norm": 2.255896106362343e-06,
      "learning_rate": 6.19768668539586e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10410976,
      "step": 37160
    },
    {
      "epoch": 412.94444444444446,
      "grad_norm": 5.601888801720634e-07,
      "learning_rate": 6.175980911375528e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10412464,
      "step": 37165
    },
    {
      "epoch": 413.0,
      "grad_norm": 5.073877105132851e-07,
      "learning_rate": 6.154312738083034e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10413840,
      "step": 37170
    },
    {
      "epoch": 413.05555555555554,
      "grad_norm": 1.5129393204915687e-06,
      "learning_rate": 6.132682168859843e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10415232,
      "step": 37175
    },
    {
      "epoch": 413.1111111111111,
      "grad_norm": 5.977809678370249e-07,
      "learning_rate": 6.111089207041704e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10416576,
      "step": 37180
    },
    {
      "epoch": 413.1666666666667,
      "grad_norm": 3.6359219848236535e-06,
      "learning_rate": 6.089533855958507e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10417952,
      "step": 37185
    },
    {
      "epoch": 413.22222222222223,
      "grad_norm": 4.7073584141799074e-07,
      "learning_rate": 6.068016118934372e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10419424,
      "step": 37190
    },
    {
      "epoch": 413.27777777777777,
      "grad_norm": 8.749877338232182e-07,
      "learning_rate": 6.04653599928759e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10420800,
      "step": 37195
    },
    {
      "epoch": 413.3333333333333,
      "grad_norm": 6.948570785425545e-07,
      "learning_rate": 6.025093500330675e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10422192,
      "step": 37200
    },
    {
      "epoch": 413.3333333333333,
      "eval_loss": 0.352642685174942,
      "eval_runtime": 1.2973,
      "eval_samples_per_second": 30.833,
      "eval_steps_per_second": 15.416,
      "num_input_tokens_seen": 10422192,
      "step": 37200
    },
    {
      "epoch": 413.3888888888889,
      "grad_norm": 9.27735982259037e-07,
      "learning_rate": 6.003688625370291e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10423584,
      "step": 37205
    },
    {
      "epoch": 413.44444444444446,
      "grad_norm": 6.107550802880723e-07,
      "learning_rate": 5.982321377707406e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10425008,
      "step": 37210
    },
    {
      "epoch": 413.5,
      "grad_norm": 2.1493488020496443e-06,
      "learning_rate": 5.96099176063708e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10426464,
      "step": 37215
    },
    {
      "epoch": 413.55555555555554,
      "grad_norm": 5.428964868769981e-07,
      "learning_rate": 5.93969977744857e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10427856,
      "step": 37220
    },
    {
      "epoch": 413.6111111111111,
      "grad_norm": 3.1327233500633156e-06,
      "learning_rate": 5.918445431425445e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10429248,
      "step": 37225
    },
    {
      "epoch": 413.6666666666667,
      "grad_norm": 9.170877888209361e-07,
      "learning_rate": 5.897228725845333e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10430672,
      "step": 37230
    },
    {
      "epoch": 413.72222222222223,
      "grad_norm": 6.676958719253889e-07,
      "learning_rate": 5.876049663980171e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10432064,
      "step": 37235
    },
    {
      "epoch": 413.77777777777777,
      "grad_norm": 3.5014384138776222e-06,
      "learning_rate": 5.854908249095959e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10433488,
      "step": 37240
    },
    {
      "epoch": 413.8333333333333,
      "grad_norm": 1.6757057892391458e-06,
      "learning_rate": 5.833804484453031e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10434912,
      "step": 37245
    },
    {
      "epoch": 413.8888888888889,
      "grad_norm": 5.622289336315589e-07,
      "learning_rate": 5.81273837330587e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10436336,
      "step": 37250
    },
    {
      "epoch": 413.94444444444446,
      "grad_norm": 9.088901151699247e-07,
      "learning_rate": 5.791709918903071e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10437744,
      "step": 37255
    },
    {
      "epoch": 414.0,
      "grad_norm": 5.661451041305554e-07,
      "learning_rate": 5.770719124487483e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10439136,
      "step": 37260
    },
    {
      "epoch": 414.05555555555554,
      "grad_norm": 5.897543928767846e-07,
      "learning_rate": 5.749765993296241e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10440576,
      "step": 37265
    },
    {
      "epoch": 414.1111111111111,
      "grad_norm": 5.648528258461738e-07,
      "learning_rate": 5.728850528560509e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10441984,
      "step": 37270
    },
    {
      "epoch": 414.1666666666667,
      "grad_norm": 1.6677740859449841e-06,
      "learning_rate": 5.707972733505707e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10443344,
      "step": 37275
    },
    {
      "epoch": 414.22222222222223,
      "grad_norm": 6.097475875321834e-07,
      "learning_rate": 5.687132611351509e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10444720,
      "step": 37280
    },
    {
      "epoch": 414.27777777777777,
      "grad_norm": 9.772552402864676e-07,
      "learning_rate": 5.666330165311651e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10446096,
      "step": 37285
    },
    {
      "epoch": 414.3333333333333,
      "grad_norm": 5.699065468434128e-07,
      "learning_rate": 5.645565398594204e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10447504,
      "step": 37290
    },
    {
      "epoch": 414.3888888888889,
      "grad_norm": 5.821457307320088e-07,
      "learning_rate": 5.624838314401304e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10448896,
      "step": 37295
    },
    {
      "epoch": 414.44444444444446,
      "grad_norm": 5.233499678070075e-07,
      "learning_rate": 5.604148915929336e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10450288,
      "step": 37300
    },
    {
      "epoch": 414.5,
      "grad_norm": 8.41126450268348e-07,
      "learning_rate": 5.583497206368887e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10451648,
      "step": 37305
    },
    {
      "epoch": 414.55555555555554,
      "grad_norm": 5.346473699319176e-07,
      "learning_rate": 5.562883188904688e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10453088,
      "step": 37310
    },
    {
      "epoch": 414.6111111111111,
      "grad_norm": 5.047003241998027e-07,
      "learning_rate": 5.542306866715724e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10454480,
      "step": 37315
    },
    {
      "epoch": 414.6666666666667,
      "grad_norm": 2.810435489664087e-06,
      "learning_rate": 5.52176824297504e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10455872,
      "step": 37320
    },
    {
      "epoch": 414.72222222222223,
      "grad_norm": 2.249660383313312e-06,
      "learning_rate": 5.501267320850018e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10457328,
      "step": 37325
    },
    {
      "epoch": 414.77777777777777,
      "grad_norm": 6.106050136622798e-07,
      "learning_rate": 5.480804103502157e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10458704,
      "step": 37330
    },
    {
      "epoch": 414.8333333333333,
      "grad_norm": 4.390066976611706e-07,
      "learning_rate": 5.460378594087101e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10460112,
      "step": 37335
    },
    {
      "epoch": 414.8888888888889,
      "grad_norm": 9.243097451872018e-07,
      "learning_rate": 5.439990795754773e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10461520,
      "step": 37340
    },
    {
      "epoch": 414.94444444444446,
      "grad_norm": 2.1181472220632713e-06,
      "learning_rate": 5.419640711649188e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10462944,
      "step": 37345
    },
    {
      "epoch": 415.0,
      "grad_norm": 4.856184432355803e-07,
      "learning_rate": 5.399328344908583e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10464384,
      "step": 37350
    },
    {
      "epoch": 415.05555555555554,
      "grad_norm": 5.777140472673636e-07,
      "learning_rate": 5.379053698665399e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10465808,
      "step": 37355
    },
    {
      "epoch": 415.1111111111111,
      "grad_norm": 6.395824811988859e-07,
      "learning_rate": 5.358816776046216e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10467200,
      "step": 37360
    },
    {
      "epoch": 415.1666666666667,
      "grad_norm": 3.1319907520810375e-06,
      "learning_rate": 5.338617580171817e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10468608,
      "step": 37365
    },
    {
      "epoch": 415.22222222222223,
      "grad_norm": 5.487721637109644e-07,
      "learning_rate": 5.318456114157239e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10470016,
      "step": 37370
    },
    {
      "epoch": 415.27777777777777,
      "grad_norm": 9.600078101357212e-07,
      "learning_rate": 5.298332381111576e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10471408,
      "step": 37375
    },
    {
      "epoch": 415.3333333333333,
      "grad_norm": 8.460376648145029e-07,
      "learning_rate": 5.27824638413818e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10472800,
      "step": 37380
    },
    {
      "epoch": 415.3888888888889,
      "grad_norm": 6.195670039232937e-07,
      "learning_rate": 5.258198126334546e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10474176,
      "step": 37385
    },
    {
      "epoch": 415.44444444444446,
      "grad_norm": 5.425407607617672e-07,
      "learning_rate": 5.238187610792367e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10475536,
      "step": 37390
    },
    {
      "epoch": 415.5,
      "grad_norm": 6.600888582397602e-07,
      "learning_rate": 5.218214840597563e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10476928,
      "step": 37395
    },
    {
      "epoch": 415.55555555555554,
      "grad_norm": 1.6517340100108413e-06,
      "learning_rate": 5.198279818830115e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10478368,
      "step": 37400
    },
    {
      "epoch": 415.55555555555554,
      "eval_loss": 0.3385472893714905,
      "eval_runtime": 1.3,
      "eval_samples_per_second": 30.769,
      "eval_steps_per_second": 15.385,
      "num_input_tokens_seen": 10478368,
      "step": 37400
    },
    {
      "epoch": 415.6111111111111,
      "grad_norm": 4.838641416426981e-07,
      "learning_rate": 5.178382548564287e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10479744,
      "step": 37405
    },
    {
      "epoch": 415.6666666666667,
      "grad_norm": 4.997556288799387e-07,
      "learning_rate": 5.15852303286854e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10481152,
      "step": 37410
    },
    {
      "epoch": 415.72222222222223,
      "grad_norm": 9.069367479241919e-07,
      "learning_rate": 5.138701274805396e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10482576,
      "step": 37415
    },
    {
      "epoch": 415.77777777777777,
      "grad_norm": 5.608677042800991e-07,
      "learning_rate": 5.118917277431606e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10483952,
      "step": 37420
    },
    {
      "epoch": 415.8333333333333,
      "grad_norm": 8.901880619305302e-07,
      "learning_rate": 5.099171043798145e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10485344,
      "step": 37425
    },
    {
      "epoch": 415.8888888888889,
      "grad_norm": 3.0494609859488264e-07,
      "learning_rate": 5.079462576950133e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10486736,
      "step": 37430
    },
    {
      "epoch": 415.94444444444446,
      "grad_norm": 5.545367685044766e-07,
      "learning_rate": 5.059791879926862e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10488128,
      "step": 37435
    },
    {
      "epoch": 416.0,
      "grad_norm": 1.637240302443388e-06,
      "learning_rate": 5.040158955761793e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10489552,
      "step": 37440
    },
    {
      "epoch": 416.05555555555554,
      "grad_norm": 4.777359663421521e-07,
      "learning_rate": 5.020563807482559e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10490992,
      "step": 37445
    },
    {
      "epoch": 416.1111111111111,
      "grad_norm": 4.685442718255217e-07,
      "learning_rate": 5.001006438110995e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10492368,
      "step": 37450
    },
    {
      "epoch": 416.1666666666667,
      "grad_norm": 4.798546342499321e-07,
      "learning_rate": 4.981486850663075e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10493728,
      "step": 37455
    },
    {
      "epoch": 416.22222222222223,
      "grad_norm": 4.297345697068522e-07,
      "learning_rate": 4.962005048149005e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10495088,
      "step": 37460
    },
    {
      "epoch": 416.27777777777777,
      "grad_norm": 5.973501515654789e-07,
      "learning_rate": 4.942561033573073e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10496448,
      "step": 37465
    },
    {
      "epoch": 416.3333333333333,
      "grad_norm": 1.9743624761758838e-06,
      "learning_rate": 4.923154809933827e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10497856,
      "step": 37470
    },
    {
      "epoch": 416.3888888888889,
      "grad_norm": 9.778216281119967e-07,
      "learning_rate": 4.903786380223957e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10499280,
      "step": 37475
    },
    {
      "epoch": 416.44444444444446,
      "grad_norm": 5.571968699769059e-07,
      "learning_rate": 4.884455747430266e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10500704,
      "step": 37480
    },
    {
      "epoch": 416.5,
      "grad_norm": 5.775611953140469e-07,
      "learning_rate": 4.865162914533816e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10502096,
      "step": 37485
    },
    {
      "epoch": 416.55555555555554,
      "grad_norm": 2.043850599875441e-06,
      "learning_rate": 4.845907884509809e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10503440,
      "step": 37490
    },
    {
      "epoch": 416.6111111111111,
      "grad_norm": 9.117712238548847e-07,
      "learning_rate": 4.82669066032762e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10504848,
      "step": 37495
    },
    {
      "epoch": 416.6666666666667,
      "grad_norm": 1.6946421510510845e-06,
      "learning_rate": 4.807511244950768e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10506256,
      "step": 37500
    },
    {
      "epoch": 416.72222222222223,
      "grad_norm": 4.5608814502884343e-07,
      "learning_rate": 4.788369641336943e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10507632,
      "step": 37505
    },
    {
      "epoch": 416.77777777777777,
      "grad_norm": 4.36074572007783e-07,
      "learning_rate": 4.769265852438032e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10509056,
      "step": 37510
    },
    {
      "epoch": 416.8333333333333,
      "grad_norm": 6.18792569184734e-07,
      "learning_rate": 4.750199881200124e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10510464,
      "step": 37515
    },
    {
      "epoch": 416.8888888888889,
      "grad_norm": 5.203261252972879e-07,
      "learning_rate": 4.7311717305633664e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10511872,
      "step": 37520
    },
    {
      "epoch": 416.94444444444446,
      "grad_norm": 6.976634381317126e-07,
      "learning_rate": 4.7121814034621623e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10513296,
      "step": 37525
    },
    {
      "epoch": 417.0,
      "grad_norm": 4.320067716889753e-07,
      "learning_rate": 4.693228902825114e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10514720,
      "step": 37530
    },
    {
      "epoch": 417.05555555555554,
      "grad_norm": 8.075576261035167e-07,
      "learning_rate": 4.6743142315748277e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10516048,
      "step": 37535
    },
    {
      "epoch": 417.1111111111111,
      "grad_norm": 5.891492946830112e-07,
      "learning_rate": 4.655437392628276e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10517424,
      "step": 37540
    },
    {
      "epoch": 417.1666666666667,
      "grad_norm": 8.508172300025763e-07,
      "learning_rate": 4.636598388896463e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10518800,
      "step": 37545
    },
    {
      "epoch": 417.22222222222223,
      "grad_norm": 9.216690841640229e-07,
      "learning_rate": 4.6177972232845925e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10520160,
      "step": 37550
    },
    {
      "epoch": 417.27777777777777,
      "grad_norm": 1.473745214752853e-06,
      "learning_rate": 4.5990338986920953e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10521584,
      "step": 37555
    },
    {
      "epoch": 417.3333333333333,
      "grad_norm": 5.051817879575538e-07,
      "learning_rate": 4.5803084180124633e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10522992,
      "step": 37560
    },
    {
      "epoch": 417.3888888888889,
      "grad_norm": 5.19662080478156e-07,
      "learning_rate": 4.561620784133386e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10524368,
      "step": 37565
    },
    {
      "epoch": 417.44444444444446,
      "grad_norm": 9.724295750856982e-07,
      "learning_rate": 4.5429709999367796e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10525792,
      "step": 37570
    },
    {
      "epoch": 417.5,
      "grad_norm": 5.770938287241734e-07,
      "learning_rate": 4.5243590682986223e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10527184,
      "step": 37575
    },
    {
      "epoch": 417.55555555555554,
      "grad_norm": 5.614733140646422e-07,
      "learning_rate": 4.5057849920891735e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10528656,
      "step": 37580
    },
    {
      "epoch": 417.6111111111111,
      "grad_norm": 5.086993724034983e-07,
      "learning_rate": 4.487248774172698e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10530048,
      "step": 37585
    },
    {
      "epoch": 417.6666666666667,
      "grad_norm": 4.748237643070752e-07,
      "learning_rate": 4.4687504174077965e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10531472,
      "step": 37590
    },
    {
      "epoch": 417.72222222222223,
      "grad_norm": 4.315641604080156e-07,
      "learning_rate": 4.450289924647133e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10532864,
      "step": 37595
    },
    {
      "epoch": 417.77777777777777,
      "grad_norm": 2.2447477476816857e-06,
      "learning_rate": 4.431867298737513e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10534240,
      "step": 37600
    },
    {
      "epoch": 417.77777777777777,
      "eval_loss": 0.3754492700099945,
      "eval_runtime": 1.2992,
      "eval_samples_per_second": 30.787,
      "eval_steps_per_second": 15.394,
      "num_input_tokens_seen": 10534240,
      "step": 37600
    },
    {
      "epoch": 417.8333333333333,
      "grad_norm": 4.785758278558205e-07,
      "learning_rate": 4.41348254251997e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10535680,
      "step": 37605
    },
    {
      "epoch": 417.8888888888889,
      "grad_norm": 9.801859732760931e-07,
      "learning_rate": 4.395135658829652e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10537040,
      "step": 37610
    },
    {
      "epoch": 417.94444444444446,
      "grad_norm": 1.6718870483600767e-06,
      "learning_rate": 4.376826650495852e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10538496,
      "step": 37615
    },
    {
      "epoch": 418.0,
      "grad_norm": 1.9369049368833657e-06,
      "learning_rate": 4.358555520342117e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10539888,
      "step": 37620
    },
    {
      "epoch": 418.05555555555554,
      "grad_norm": 5.236358333604585e-07,
      "learning_rate": 4.3403222711860257e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10541312,
      "step": 37625
    },
    {
      "epoch": 418.1111111111111,
      "grad_norm": 5.509601237463357e-07,
      "learning_rate": 4.3221269058394133e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10542672,
      "step": 37630
    },
    {
      "epoch": 418.1666666666667,
      "grad_norm": 1.4631833664680016e-06,
      "learning_rate": 4.303969427108173e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10544112,
      "step": 37635
    },
    {
      "epoch": 418.22222222222223,
      "grad_norm": 4.84357485674991e-07,
      "learning_rate": 4.2858498377924825e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10545472,
      "step": 37640
    },
    {
      "epoch": 418.27777777777777,
      "grad_norm": 5.398751454777084e-07,
      "learning_rate": 4.267768140686579e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10546848,
      "step": 37645
    },
    {
      "epoch": 418.3333333333333,
      "grad_norm": 4.989076387573732e-07,
      "learning_rate": 4.2497243385788975e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10548224,
      "step": 37650
    },
    {
      "epoch": 418.3888888888889,
      "grad_norm": 5.90313277371024e-07,
      "learning_rate": 4.231718434251991e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10549584,
      "step": 37655
    },
    {
      "epoch": 418.44444444444446,
      "grad_norm": 5.404892817750806e-07,
      "learning_rate": 4.213750430482666e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10550960,
      "step": 37660
    },
    {
      "epoch": 418.5,
      "grad_norm": 9.079794267563557e-07,
      "learning_rate": 4.1958203300417054e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10552416,
      "step": 37665
    },
    {
      "epoch": 418.55555555555554,
      "grad_norm": 5.854937512594915e-07,
      "learning_rate": 4.177928135694259e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10553808,
      "step": 37670
    },
    {
      "epoch": 418.6111111111111,
      "grad_norm": 1.6515925835847156e-06,
      "learning_rate": 4.1600738501994807e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10555232,
      "step": 37675
    },
    {
      "epoch": 418.6666666666667,
      "grad_norm": 5.587737064161047e-07,
      "learning_rate": 4.1422574763107237e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10556576,
      "step": 37680
    },
    {
      "epoch": 418.72222222222223,
      "grad_norm": 5.354293080017669e-07,
      "learning_rate": 4.124479016775512e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10557984,
      "step": 37685
    },
    {
      "epoch": 418.77777777777777,
      "grad_norm": 6.089227326810942e-07,
      "learning_rate": 4.106738474335514e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10559376,
      "step": 37690
    },
    {
      "epoch": 418.8333333333333,
      "grad_norm": 5.660920123773394e-07,
      "learning_rate": 4.089035851726486e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10560768,
      "step": 37695
    },
    {
      "epoch": 418.8888888888889,
      "grad_norm": 4.975474894308718e-07,
      "learning_rate": 4.0713711516784937e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10562160,
      "step": 37700
    },
    {
      "epoch": 418.94444444444446,
      "grad_norm": 5.933499664934061e-07,
      "learning_rate": 4.05374437691558e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10563584,
      "step": 37705
    },
    {
      "epoch": 419.0,
      "grad_norm": 1.0679816568881506e-06,
      "learning_rate": 4.036155530156044e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10564960,
      "step": 37710
    },
    {
      "epoch": 419.05555555555554,
      "grad_norm": 5.602926762549032e-07,
      "learning_rate": 4.018604614112298e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10566336,
      "step": 37715
    },
    {
      "epoch": 419.1111111111111,
      "grad_norm": 5.897116466258012e-07,
      "learning_rate": 4.0010916314908996e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10567760,
      "step": 37720
    },
    {
      "epoch": 419.1666666666667,
      "grad_norm": 1.4834062085355981e-06,
      "learning_rate": 3.983616584992578e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10569152,
      "step": 37725
    },
    {
      "epoch": 419.22222222222223,
      "grad_norm": 5.700840688405151e-07,
      "learning_rate": 3.9661794773122595e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10570528,
      "step": 37730
    },
    {
      "epoch": 419.27777777777777,
      "grad_norm": 4.771058002006612e-07,
      "learning_rate": 3.9487803111388777e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10571936,
      "step": 37735
    },
    {
      "epoch": 419.3333333333333,
      "grad_norm": 8.304078278342786e-07,
      "learning_rate": 3.9314190891556747e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10573360,
      "step": 37740
    },
    {
      "epoch": 419.3888888888889,
      "grad_norm": 5.23437563515472e-07,
      "learning_rate": 3.914095814039925e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10574736,
      "step": 37745
    },
    {
      "epoch": 419.44444444444446,
      "grad_norm": 6.933375971129863e-07,
      "learning_rate": 3.896810488463104e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10576176,
      "step": 37750
    },
    {
      "epoch": 419.5,
      "grad_norm": 1.6691061546225683e-06,
      "learning_rate": 3.8795631150908565e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10577600,
      "step": 37755
    },
    {
      "epoch": 419.55555555555554,
      "grad_norm": 5.915133556300134e-07,
      "learning_rate": 3.862353696582888e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10579024,
      "step": 37760
    },
    {
      "epoch": 419.6111111111111,
      "grad_norm": 3.0074838832661044e-06,
      "learning_rate": 3.8451822355931313e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10580400,
      "step": 37765
    },
    {
      "epoch": 419.6666666666667,
      "grad_norm": 1.9296828668302624e-06,
      "learning_rate": 3.82804873476969e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10581792,
      "step": 37770
    },
    {
      "epoch": 419.72222222222223,
      "grad_norm": 5.169982273400819e-07,
      "learning_rate": 3.810953196754702e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10583168,
      "step": 37775
    },
    {
      "epoch": 419.77777777777777,
      "grad_norm": 8.992051903078391e-07,
      "learning_rate": 3.793895624184529e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10584544,
      "step": 37780
    },
    {
      "epoch": 419.8333333333333,
      "grad_norm": 1.6265400972770294e-06,
      "learning_rate": 3.776876019689679e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10585952,
      "step": 37785
    },
    {
      "epoch": 419.8888888888889,
      "grad_norm": 7.632550023117801e-07,
      "learning_rate": 3.7598943858947743e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10587392,
      "step": 37790
    },
    {
      "epoch": 419.94444444444446,
      "grad_norm": 7.824875751794025e-07,
      "learning_rate": 3.742950725418637e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10588784,
      "step": 37795
    },
    {
      "epoch": 420.0,
      "grad_norm": 5.376156195779913e-07,
      "learning_rate": 3.726045040874093e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10590208,
      "step": 37800
    },
    {
      "epoch": 420.0,
      "eval_loss": 0.42338746786117554,
      "eval_runtime": 1.2805,
      "eval_samples_per_second": 31.238,
      "eval_steps_per_second": 15.619,
      "num_input_tokens_seen": 10590208,
      "step": 37800
    },
    {
      "epoch": 420.05555555555554,
      "grad_norm": 8.340273893736594e-07,
      "learning_rate": 3.709177334868308e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10591632,
      "step": 37805
    },
    {
      "epoch": 420.1111111111111,
      "grad_norm": 5.75248520817695e-07,
      "learning_rate": 3.692347610002478e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10593040,
      "step": 37810
    },
    {
      "epoch": 420.1666666666667,
      "grad_norm": 5.553445703299076e-07,
      "learning_rate": 3.675555868871916e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10594464,
      "step": 37815
    },
    {
      "epoch": 420.22222222222223,
      "grad_norm": 4.865204346060636e-07,
      "learning_rate": 3.658802114066162e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10595872,
      "step": 37820
    },
    {
      "epoch": 420.27777777777777,
      "grad_norm": 1.5128075574466493e-06,
      "learning_rate": 3.6420863481688437e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10597264,
      "step": 37825
    },
    {
      "epoch": 420.3333333333333,
      "grad_norm": 6.169842095005151e-07,
      "learning_rate": 3.625408573757705e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10598672,
      "step": 37830
    },
    {
      "epoch": 420.3888888888889,
      "grad_norm": 9.870301482806099e-07,
      "learning_rate": 3.608768793404743e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10600096,
      "step": 37835
    },
    {
      "epoch": 420.44444444444446,
      "grad_norm": 4.007411291695462e-07,
      "learning_rate": 3.592167009675934e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10601472,
      "step": 37840
    },
    {
      "epoch": 420.5,
      "grad_norm": 4.0956589941743005e-07,
      "learning_rate": 3.575603225131563e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10602864,
      "step": 37845
    },
    {
      "epoch": 420.55555555555554,
      "grad_norm": 9.210888833877107e-07,
      "learning_rate": 3.55907744232592e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10604320,
      "step": 37850
    },
    {
      "epoch": 420.6111111111111,
      "grad_norm": 5.754719154538179e-07,
      "learning_rate": 3.5425896638075217e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10605696,
      "step": 37855
    },
    {
      "epoch": 420.6666666666667,
      "grad_norm": 9.293555649492191e-07,
      "learning_rate": 3.5261398921189736e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10607088,
      "step": 37860
    },
    {
      "epoch": 420.72222222222223,
      "grad_norm": 9.117082981902058e-07,
      "learning_rate": 3.509728129797024e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10608528,
      "step": 37865
    },
    {
      "epoch": 420.77777777777777,
      "grad_norm": 9.474758257965732e-07,
      "learning_rate": 3.4933543793725656e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10609936,
      "step": 37870
    },
    {
      "epoch": 420.8333333333333,
      "grad_norm": 9.33529690883006e-07,
      "learning_rate": 3.4770186433707163e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10611312,
      "step": 37875
    },
    {
      "epoch": 420.8888888888889,
      "grad_norm": 5.914279768148845e-07,
      "learning_rate": 3.4607209243105453e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10612704,
      "step": 37880
    },
    {
      "epoch": 420.94444444444446,
      "grad_norm": 6.46063881504233e-07,
      "learning_rate": 3.444461224705431e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10614096,
      "step": 37885
    },
    {
      "epoch": 421.0,
      "grad_norm": 9.570476322551258e-07,
      "learning_rate": 3.4282395470628116e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10615488,
      "step": 37890
    },
    {
      "epoch": 421.05555555555554,
      "grad_norm": 9.751923926160089e-07,
      "learning_rate": 3.4120558938842417e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10616864,
      "step": 37895
    },
    {
      "epoch": 421.1111111111111,
      "grad_norm": 1.0189917247771518e-06,
      "learning_rate": 3.395910267665503e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10618272,
      "step": 37900
    },
    {
      "epoch": 421.1666666666667,
      "grad_norm": 1.67145526575041e-06,
      "learning_rate": 3.3798026708964094e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10619680,
      "step": 37905
    },
    {
      "epoch": 421.22222222222223,
      "grad_norm": 5.408838887888123e-07,
      "learning_rate": 3.3637331060609456e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10621072,
      "step": 37910
    },
    {
      "epoch": 421.27777777777777,
      "grad_norm": 9.599247050573467e-07,
      "learning_rate": 3.3477015756372966e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10622448,
      "step": 37915
    },
    {
      "epoch": 421.3333333333333,
      "grad_norm": 5.421119908533001e-07,
      "learning_rate": 3.3317080820976785e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10623872,
      "step": 37920
    },
    {
      "epoch": 421.3888888888889,
      "grad_norm": 9.565394520905102e-07,
      "learning_rate": 3.315752627908508e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10625280,
      "step": 37925
    },
    {
      "epoch": 421.44444444444446,
      "grad_norm": 6.072142468838138e-07,
      "learning_rate": 3.299835215530317e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10626656,
      "step": 37930
    },
    {
      "epoch": 421.5,
      "grad_norm": 6.252444109122735e-07,
      "learning_rate": 3.2839558474177245e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10628032,
      "step": 37935
    },
    {
      "epoch": 421.55555555555554,
      "grad_norm": 5.176154331820726e-07,
      "learning_rate": 3.2681145260196056e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10629408,
      "step": 37940
    },
    {
      "epoch": 421.6111111111111,
      "grad_norm": 5.417576858235407e-07,
      "learning_rate": 3.252311253778839e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10630800,
      "step": 37945
    },
    {
      "epoch": 421.6666666666667,
      "grad_norm": 5.977224759590172e-07,
      "learning_rate": 3.2365460331325034e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10632240,
      "step": 37950
    },
    {
      "epoch": 421.72222222222223,
      "grad_norm": 6.213655865394685e-07,
      "learning_rate": 3.2208188665117934e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10633600,
      "step": 37955
    },
    {
      "epoch": 421.77777777777777,
      "grad_norm": 2.164371608159854e-06,
      "learning_rate": 3.205129756342018e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10635040,
      "step": 37960
    },
    {
      "epoch": 421.8333333333333,
      "grad_norm": 6.250884325709194e-07,
      "learning_rate": 3.189478705042659e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10636480,
      "step": 37965
    },
    {
      "epoch": 421.8888888888889,
      "grad_norm": 9.145321087089542e-07,
      "learning_rate": 3.173865715027341e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10637872,
      "step": 37970
    },
    {
      "epoch": 421.94444444444446,
      "grad_norm": 1.96307723854261e-06,
      "learning_rate": 3.158290788703694e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10639312,
      "step": 37975
    },
    {
      "epoch": 422.0,
      "grad_norm": 5.443520194603479e-07,
      "learning_rate": 3.1427539284736297e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10640720,
      "step": 37980
    },
    {
      "epoch": 422.05555555555554,
      "grad_norm": 6.161418468764168e-07,
      "learning_rate": 3.127255136733093e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10642176,
      "step": 37985
    },
    {
      "epoch": 422.1111111111111,
      "grad_norm": 1.655817982282315e-06,
      "learning_rate": 3.1117944158722544e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10643568,
      "step": 37990
    },
    {
      "epoch": 422.1666666666667,
      "grad_norm": 5.718674742638541e-07,
      "learning_rate": 3.0963717682752635e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10644976,
      "step": 37995
    },
    {
      "epoch": 422.22222222222223,
      "grad_norm": 5.903519877392682e-07,
      "learning_rate": 3.080987196320578e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10646384,
      "step": 38000
    },
    {
      "epoch": 422.22222222222223,
      "eval_loss": 0.3726119101047516,
      "eval_runtime": 1.2918,
      "eval_samples_per_second": 30.965,
      "eval_steps_per_second": 15.482,
      "num_input_tokens_seen": 10646384,
      "step": 38000
    },
    {
      "epoch": 422.27777777777777,
      "grad_norm": 5.909055857955536e-07,
      "learning_rate": 3.065640702380607e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10647824,
      "step": 38005
    },
    {
      "epoch": 422.3333333333333,
      "grad_norm": 6.724879426656116e-07,
      "learning_rate": 3.050332288822011e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10649232,
      "step": 38010
    },
    {
      "epoch": 422.3888888888889,
      "grad_norm": 5.526358677343524e-07,
      "learning_rate": 3.035061958005542e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10650672,
      "step": 38015
    },
    {
      "epoch": 422.44444444444446,
      "grad_norm": 6.484455070676631e-07,
      "learning_rate": 3.019829712286093e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10652064,
      "step": 38020
    },
    {
      "epoch": 422.5,
      "grad_norm": 1.6812787180242594e-06,
      "learning_rate": 3.004635554012647e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10653456,
      "step": 38025
    },
    {
      "epoch": 422.55555555555554,
      "grad_norm": 6.03528519604879e-07,
      "learning_rate": 2.9894794855283017e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10654832,
      "step": 38030
    },
    {
      "epoch": 422.6111111111111,
      "grad_norm": 5.686777626578987e-07,
      "learning_rate": 2.9743615091703816e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10656240,
      "step": 38035
    },
    {
      "epoch": 422.6666666666667,
      "grad_norm": 9.920529464579886e-07,
      "learning_rate": 2.959281627270216e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10657664,
      "step": 38040
    },
    {
      "epoch": 422.72222222222223,
      "grad_norm": 5.174106263439171e-07,
      "learning_rate": 2.944239842153362e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10659040,
      "step": 38045
    },
    {
      "epoch": 422.77777777777777,
      "grad_norm": 8.69357052124542e-07,
      "learning_rate": 2.929236156139381e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10660480,
      "step": 38050
    },
    {
      "epoch": 422.8333333333333,
      "grad_norm": 1.9749213606701232e-06,
      "learning_rate": 2.9142705715420883e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10661872,
      "step": 38055
    },
    {
      "epoch": 422.8888888888889,
      "grad_norm": 5.765092510046088e-07,
      "learning_rate": 2.8993430906693595e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10663264,
      "step": 38060
    },
    {
      "epoch": 422.94444444444446,
      "grad_norm": 5.110013603371044e-07,
      "learning_rate": 2.88445371582316e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10664608,
      "step": 38065
    },
    {
      "epoch": 423.0,
      "grad_norm": 9.383848009747453e-07,
      "learning_rate": 2.8696024492996796e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10665984,
      "step": 38070
    },
    {
      "epoch": 423.05555555555554,
      "grad_norm": 1.9751635136344703e-06,
      "learning_rate": 2.854789293389115e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10667376,
      "step": 38075
    },
    {
      "epoch": 423.1111111111111,
      "grad_norm": 6.29777616723004e-07,
      "learning_rate": 2.8400142503758606e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10668736,
      "step": 38080
    },
    {
      "epoch": 423.1666666666667,
      "grad_norm": 9.672112355474383e-07,
      "learning_rate": 2.8252773225384276e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10670112,
      "step": 38085
    },
    {
      "epoch": 423.22222222222223,
      "grad_norm": 2.0015231712022796e-06,
      "learning_rate": 2.8105785121494143e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10671568,
      "step": 38090
    },
    {
      "epoch": 423.27777777777777,
      "grad_norm": 5.760196017945418e-07,
      "learning_rate": 2.795917821475563e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10672960,
      "step": 38095
    },
    {
      "epoch": 423.3333333333333,
      "grad_norm": 4.829211093237973e-07,
      "learning_rate": 2.78129525277776e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10674352,
      "step": 38100
    },
    {
      "epoch": 423.3888888888889,
      "grad_norm": 5.345591489458457e-07,
      "learning_rate": 2.766710808310952e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10675760,
      "step": 38105
    },
    {
      "epoch": 423.44444444444446,
      "grad_norm": 5.790429895569105e-07,
      "learning_rate": 2.7521644903242827e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10677184,
      "step": 38110
    },
    {
      "epoch": 423.5,
      "grad_norm": 5.433811338662053e-07,
      "learning_rate": 2.7376563010609593e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10678624,
      "step": 38115
    },
    {
      "epoch": 423.55555555555554,
      "grad_norm": 5.615293048322201e-07,
      "learning_rate": 2.72318624275833e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10679984,
      "step": 38120
    },
    {
      "epoch": 423.6111111111111,
      "grad_norm": 6.400055667654669e-07,
      "learning_rate": 2.7087543176478324e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10681360,
      "step": 38125
    },
    {
      "epoch": 423.6666666666667,
      "grad_norm": 6.812948072365543e-07,
      "learning_rate": 2.694360527955103e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10682816,
      "step": 38130
    },
    {
      "epoch": 423.72222222222223,
      "grad_norm": 6.101370786382176e-07,
      "learning_rate": 2.680004875899811e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10684224,
      "step": 38135
    },
    {
      "epoch": 423.77777777777777,
      "grad_norm": 5.187506531001418e-07,
      "learning_rate": 2.665687363695768e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10685632,
      "step": 38140
    },
    {
      "epoch": 423.8333333333333,
      "grad_norm": 6.132613066256454e-07,
      "learning_rate": 2.6514079935509584e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10687056,
      "step": 38145
    },
    {
      "epoch": 423.8888888888889,
      "grad_norm": 5.990373210806865e-07,
      "learning_rate": 2.6371667676673983e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10688464,
      "step": 38150
    },
    {
      "epoch": 423.94444444444446,
      "grad_norm": 4.693887376561179e-07,
      "learning_rate": 2.6229636882412755e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10689840,
      "step": 38155
    },
    {
      "epoch": 424.0,
      "grad_norm": 5.361554258342949e-07,
      "learning_rate": 2.6087987574628935e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10691216,
      "step": 38160
    },
    {
      "epoch": 424.05555555555554,
      "grad_norm": 6.537110266435775e-07,
      "learning_rate": 2.5946719775166437e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10692544,
      "step": 38165
    },
    {
      "epoch": 424.1111111111111,
      "grad_norm": 1.6642393347865436e-06,
      "learning_rate": 2.5805833505810616e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10693920,
      "step": 38170
    },
    {
      "epoch": 424.1666666666667,
      "grad_norm": 1.498009169154102e-06,
      "learning_rate": 2.566532878828798e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10695376,
      "step": 38175
    },
    {
      "epoch": 424.22222222222223,
      "grad_norm": 4.3120431314491725e-07,
      "learning_rate": 2.552520564426619e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10696752,
      "step": 38180
    },
    {
      "epoch": 424.27777777777777,
      "grad_norm": 1.7129789284808794e-06,
      "learning_rate": 2.5385464095353803e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10698160,
      "step": 38185
    },
    {
      "epoch": 424.3333333333333,
      "grad_norm": 6.216260430846887e-07,
      "learning_rate": 2.5246104163100804e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10699552,
      "step": 38190
    },
    {
      "epoch": 424.3888888888889,
      "grad_norm": 5.064349011263403e-07,
      "learning_rate": 2.510712586899833e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10700912,
      "step": 38195
    },
    {
      "epoch": 424.44444444444446,
      "grad_norm": 2.24892301048385e-06,
      "learning_rate": 2.4968529234478124e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10702336,
      "step": 38200
    },
    {
      "epoch": 424.44444444444446,
      "eval_loss": 0.34964871406555176,
      "eval_runtime": 1.2961,
      "eval_samples_per_second": 30.861,
      "eval_steps_per_second": 15.431,
      "num_input_tokens_seen": 10702336,
      "step": 38200
    },
    {
      "epoch": 424.5,
      "grad_norm": 4.7208578735080664e-07,
      "learning_rate": 2.483031428091448e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10703728,
      "step": 38205
    },
    {
      "epoch": 424.55555555555554,
      "grad_norm": 1.4983296523496392e-06,
      "learning_rate": 2.469248102962091e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10705200,
      "step": 38210
    },
    {
      "epoch": 424.6111111111111,
      "grad_norm": 8.879839583642024e-07,
      "learning_rate": 2.4555029501853455e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10706560,
      "step": 38215
    },
    {
      "epoch": 424.6666666666667,
      "grad_norm": 5.749355409534473e-07,
      "learning_rate": 2.441795971880906e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10707968,
      "step": 38220
    },
    {
      "epoch": 424.72222222222223,
      "grad_norm": 1.9505964701238554e-06,
      "learning_rate": 2.4281271701625255e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10709360,
      "step": 38225
    },
    {
      "epoch": 424.77777777777777,
      "grad_norm": 5.216476779423829e-07,
      "learning_rate": 2.4144965471381007e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10710752,
      "step": 38230
    },
    {
      "epoch": 424.8333333333333,
      "grad_norm": 5.247168246569345e-07,
      "learning_rate": 2.400904104909674e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10712224,
      "step": 38235
    },
    {
      "epoch": 424.8888888888889,
      "grad_norm": 1.4962708974053385e-06,
      "learning_rate": 2.3873498455733725e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10713600,
      "step": 38240
    },
    {
      "epoch": 424.94444444444446,
      "grad_norm": 5.855793574482959e-07,
      "learning_rate": 2.3738337712194137e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10715024,
      "step": 38245
    },
    {
      "epoch": 425.0,
      "grad_norm": 1.4706456568092108e-06,
      "learning_rate": 2.3603558839321305e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10716432,
      "step": 38250
    },
    {
      "epoch": 425.05555555555554,
      "grad_norm": 1.9312894892209442e-06,
      "learning_rate": 2.3469161857900267e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10717840,
      "step": 38255
    },
    {
      "epoch": 425.1111111111111,
      "grad_norm": 1.6806429812277202e-06,
      "learning_rate": 2.3335146788656393e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10719264,
      "step": 38260
    },
    {
      "epoch": 425.1666666666667,
      "grad_norm": 1.0576156910246937e-06,
      "learning_rate": 2.3201513652256757e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10720656,
      "step": 38265
    },
    {
      "epoch": 425.22222222222223,
      "grad_norm": 6.116018198554229e-07,
      "learning_rate": 2.3068262469308766e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10722064,
      "step": 38270
    },
    {
      "epoch": 425.27777777777777,
      "grad_norm": 6.475486316048773e-07,
      "learning_rate": 2.2935393260362093e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10723456,
      "step": 38275
    },
    {
      "epoch": 425.3333333333333,
      "grad_norm": 5.58756823920703e-07,
      "learning_rate": 2.2802906045906458e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10724832,
      "step": 38280
    },
    {
      "epoch": 425.3888888888889,
      "grad_norm": 9.801763098948868e-07,
      "learning_rate": 2.2670800846373018e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10726256,
      "step": 38285
    },
    {
      "epoch": 425.44444444444446,
      "grad_norm": 5.667005211762444e-07,
      "learning_rate": 2.2539077682134367e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10727632,
      "step": 38290
    },
    {
      "epoch": 425.5,
      "grad_norm": 5.499099415828823e-07,
      "learning_rate": 2.2407736573503423e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10729072,
      "step": 38295
    },
    {
      "epoch": 425.55555555555554,
      "grad_norm": 5.779227763014205e-07,
      "learning_rate": 2.2276777540735093e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10730448,
      "step": 38300
    },
    {
      "epoch": 425.6111111111111,
      "grad_norm": 6.371487870637793e-07,
      "learning_rate": 2.2146200604024613e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10731872,
      "step": 38305
    },
    {
      "epoch": 425.6666666666667,
      "grad_norm": 8.855254236550536e-07,
      "learning_rate": 2.2016005783508375e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10733280,
      "step": 38310
    },
    {
      "epoch": 425.72222222222223,
      "grad_norm": 4.74825270657675e-07,
      "learning_rate": 2.1886193099264763e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10734656,
      "step": 38315
    },
    {
      "epoch": 425.77777777777777,
      "grad_norm": 9.733204251460847e-07,
      "learning_rate": 2.175676257131165e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10736064,
      "step": 38320
    },
    {
      "epoch": 425.8333333333333,
      "grad_norm": 6.439701678573329e-07,
      "learning_rate": 2.162771421960974e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10737456,
      "step": 38325
    },
    {
      "epoch": 425.8888888888889,
      "grad_norm": 5.428396434581373e-07,
      "learning_rate": 2.1499048064059224e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10738848,
      "step": 38330
    },
    {
      "epoch": 425.94444444444446,
      "grad_norm": 8.141129228533828e-07,
      "learning_rate": 2.1370764124502285e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10740224,
      "step": 38335
    },
    {
      "epoch": 426.0,
      "grad_norm": 8.262654773716349e-07,
      "learning_rate": 2.1242862420721988e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10741664,
      "step": 38340
    },
    {
      "epoch": 426.05555555555554,
      "grad_norm": 5.738961021961586e-07,
      "learning_rate": 2.1115342972442276e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10743024,
      "step": 38345
    },
    {
      "epoch": 426.1111111111111,
      "grad_norm": 5.73062834519078e-07,
      "learning_rate": 2.0988205799328252e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10744416,
      "step": 38350
    },
    {
      "epoch": 426.1666666666667,
      "grad_norm": 5.519036108125874e-07,
      "learning_rate": 2.0861450920986182e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10745840,
      "step": 38355
    },
    {
      "epoch": 426.22222222222223,
      "grad_norm": 9.794775905902497e-07,
      "learning_rate": 2.07350783569632e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10747200,
      "step": 38360
    },
    {
      "epoch": 426.27777777777777,
      "grad_norm": 9.630415434003226e-07,
      "learning_rate": 2.060908812674761e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10748608,
      "step": 38365
    },
    {
      "epoch": 426.3333333333333,
      "grad_norm": 5.624455639008374e-07,
      "learning_rate": 2.0483480249768317e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10749952,
      "step": 38370
    },
    {
      "epoch": 426.3888888888889,
      "grad_norm": 4.995557105758053e-07,
      "learning_rate": 2.035825474539621e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10751360,
      "step": 38375
    },
    {
      "epoch": 426.44444444444446,
      "grad_norm": 9.078757443603536e-07,
      "learning_rate": 2.0233411632942235e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10752800,
      "step": 38380
    },
    {
      "epoch": 426.5,
      "grad_norm": 6.199373387971718e-07,
      "learning_rate": 2.0108950931658764e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10754144,
      "step": 38385
    },
    {
      "epoch": 426.55555555555554,
      "grad_norm": 4.84159045299748e-07,
      "learning_rate": 1.998487266073934e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10755584,
      "step": 38390
    },
    {
      "epoch": 426.6111111111111,
      "grad_norm": 1.0098842722072732e-06,
      "learning_rate": 1.986117683931865e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10757008,
      "step": 38395
    },
    {
      "epoch": 426.6666666666667,
      "grad_norm": 4.725602309463284e-07,
      "learning_rate": 1.9737863486471442e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10758400,
      "step": 38400
    },
    {
      "epoch": 426.6666666666667,
      "eval_loss": 0.34045541286468506,
      "eval_runtime": 1.2952,
      "eval_samples_per_second": 30.883,
      "eval_steps_per_second": 15.442,
      "num_input_tokens_seen": 10758400,
      "step": 38400
    },
    {
      "epoch": 426.72222222222223,
      "grad_norm": 1.6759330492277513e-06,
      "learning_rate": 1.9614932621215e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10759840,
      "step": 38405
    },
    {
      "epoch": 426.77777777777777,
      "grad_norm": 1.7119239146268228e-06,
      "learning_rate": 1.9492384262506102e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10761264,
      "step": 38410
    },
    {
      "epoch": 426.8333333333333,
      "grad_norm": 5.919242198615393e-07,
      "learning_rate": 1.9370218429243524e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10762688,
      "step": 38415
    },
    {
      "epoch": 426.8888888888889,
      "grad_norm": 5.24931408563134e-07,
      "learning_rate": 1.9248435140267197e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10764096,
      "step": 38420
    },
    {
      "epoch": 426.94444444444446,
      "grad_norm": 4.945214868712355e-07,
      "learning_rate": 1.9127034414356814e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10765504,
      "step": 38425
    },
    {
      "epoch": 427.0,
      "grad_norm": 9.082718861463945e-07,
      "learning_rate": 1.9006016270234627e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10766912,
      "step": 38430
    },
    {
      "epoch": 427.05555555555554,
      "grad_norm": 4.1667414052426466e-07,
      "learning_rate": 1.888538072656293e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10768304,
      "step": 38435
    },
    {
      "epoch": 427.1111111111111,
      "grad_norm": 6.616478458454367e-07,
      "learning_rate": 1.8765127801944893e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10769760,
      "step": 38440
    },
    {
      "epoch": 427.1666666666667,
      "grad_norm": 3.5089565244561527e-06,
      "learning_rate": 1.8645257514925406e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10771168,
      "step": 38445
    },
    {
      "epoch": 427.22222222222223,
      "grad_norm": 9.467052564104961e-07,
      "learning_rate": 1.8525769883989685e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10772544,
      "step": 38450
    },
    {
      "epoch": 427.27777777777777,
      "grad_norm": 6.918816666257044e-07,
      "learning_rate": 1.8406664927564654e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10773952,
      "step": 38455
    },
    {
      "epoch": 427.3333333333333,
      "grad_norm": 5.566255936173548e-07,
      "learning_rate": 1.8287942664017566e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10775344,
      "step": 38460
    },
    {
      "epoch": 427.3888888888889,
      "grad_norm": 9.92548166323104e-07,
      "learning_rate": 1.8169603111656552e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10776736,
      "step": 38465
    },
    {
      "epoch": 427.44444444444446,
      "grad_norm": 5.502597559825517e-07,
      "learning_rate": 1.805164628873146e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10778096,
      "step": 38470
    },
    {
      "epoch": 427.5,
      "grad_norm": 9.42255951486004e-07,
      "learning_rate": 1.793407221343274e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10779504,
      "step": 38475
    },
    {
      "epoch": 427.55555555555554,
      "grad_norm": 9.524279107608891e-07,
      "learning_rate": 1.781688090389172e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10780928,
      "step": 38480
    },
    {
      "epoch": 427.6111111111111,
      "grad_norm": 5.083221026325191e-07,
      "learning_rate": 1.770007237818061e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10782336,
      "step": 38485
    },
    {
      "epoch": 427.6666666666667,
      "grad_norm": 6.450288196901965e-07,
      "learning_rate": 1.7583646654313059e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10783744,
      "step": 38490
    },
    {
      "epoch": 427.72222222222223,
      "grad_norm": 5.30669183262944e-07,
      "learning_rate": 1.7467603750242757e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10785136,
      "step": 38495
    },
    {
      "epoch": 427.77777777777777,
      "grad_norm": 5.294543825584697e-07,
      "learning_rate": 1.7351943683865944e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10786528,
      "step": 38500
    },
    {
      "epoch": 427.8333333333333,
      "grad_norm": 1.5156457493503694e-06,
      "learning_rate": 1.723666647301808e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10787952,
      "step": 38505
    },
    {
      "epoch": 427.8888888888889,
      "grad_norm": 6.329456141429546e-07,
      "learning_rate": 1.712177213547661e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10789312,
      "step": 38510
    },
    {
      "epoch": 427.94444444444446,
      "grad_norm": 1.6342650042133755e-06,
      "learning_rate": 1.7007260688959581e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10790720,
      "step": 38515
    },
    {
      "epoch": 428.0,
      "grad_norm": 9.434324965695851e-07,
      "learning_rate": 1.68931321511262e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10792096,
      "step": 38520
    },
    {
      "epoch": 428.05555555555554,
      "grad_norm": 5.64013532766694e-07,
      "learning_rate": 1.6779386539576835e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10793472,
      "step": 38525
    },
    {
      "epoch": 428.1111111111111,
      "grad_norm": 5.958335123068537e-07,
      "learning_rate": 1.666602387185162e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10794880,
      "step": 38530
    },
    {
      "epoch": 428.1666666666667,
      "grad_norm": 5.803840394946747e-07,
      "learning_rate": 1.655304416543352e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10796224,
      "step": 38535
    },
    {
      "epoch": 428.22222222222223,
      "grad_norm": 4.788357159668521e-07,
      "learning_rate": 1.6440447437744698e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10797648,
      "step": 38540
    },
    {
      "epoch": 428.27777777777777,
      "grad_norm": 1.6625357375232852e-06,
      "learning_rate": 1.6328233706149332e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10799088,
      "step": 38545
    },
    {
      "epoch": 428.3333333333333,
      "grad_norm": 5.89534920436563e-07,
      "learning_rate": 1.6216402987951906e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10800432,
      "step": 38550
    },
    {
      "epoch": 428.3888888888889,
      "grad_norm": 9.771970326255541e-07,
      "learning_rate": 1.6104955300398627e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10801824,
      "step": 38555
    },
    {
      "epoch": 428.44444444444446,
      "grad_norm": 5.944382337474963e-07,
      "learning_rate": 1.5993890660675748e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10803248,
      "step": 38560
    },
    {
      "epoch": 428.5,
      "grad_norm": 2.1572093373833923e-06,
      "learning_rate": 1.5883209085910678e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10804656,
      "step": 38565
    },
    {
      "epoch": 428.55555555555554,
      "grad_norm": 9.436069490220689e-07,
      "learning_rate": 1.5772910593172264e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10806080,
      "step": 38570
    },
    {
      "epoch": 428.6111111111111,
      "grad_norm": 5.413215262706217e-07,
      "learning_rate": 1.5662995199469954e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10807440,
      "step": 38575
    },
    {
      "epoch": 428.6666666666667,
      "grad_norm": 5.195715857553296e-07,
      "learning_rate": 1.5553462921753802e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10808848,
      "step": 38580
    },
    {
      "epoch": 428.72222222222223,
      "grad_norm": 8.456856903649168e-07,
      "learning_rate": 1.544431377691502e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10810272,
      "step": 38585
    },
    {
      "epoch": 428.77777777777777,
      "grad_norm": 6.094348350416112e-07,
      "learning_rate": 1.5335547781785975e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10811664,
      "step": 38590
    },
    {
      "epoch": 428.8333333333333,
      "grad_norm": 1.4695076515636174e-06,
      "learning_rate": 1.5227164953139917e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10813072,
      "step": 38595
    },
    {
      "epoch": 428.8888888888889,
      "grad_norm": 1.477463115406863e-06,
      "learning_rate": 1.511916530769042e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10814480,
      "step": 38600
    },
    {
      "epoch": 428.8888888888889,
      "eval_loss": 0.35227808356285095,
      "eval_runtime": 1.2949,
      "eval_samples_per_second": 30.89,
      "eval_steps_per_second": 15.445,
      "num_input_tokens_seen": 10814480,
      "step": 38600
    },
    {
      "epoch": 428.94444444444446,
      "grad_norm": 6.422237674996722e-07,
      "learning_rate": 1.5011548862092773e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10815872,
      "step": 38605
    },
    {
      "epoch": 429.0,
      "grad_norm": 4.999255907023326e-07,
      "learning_rate": 1.490431563294231e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10817248,
      "step": 38610
    },
    {
      "epoch": 429.05555555555554,
      "grad_norm": 5.676639602825162e-07,
      "learning_rate": 1.4797465636776365e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10818608,
      "step": 38615
    },
    {
      "epoch": 429.1111111111111,
      "grad_norm": 4.778501079272246e-07,
      "learning_rate": 1.4690998890072027e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10819952,
      "step": 38620
    },
    {
      "epoch": 429.1666666666667,
      "grad_norm": 9.504075819677382e-07,
      "learning_rate": 1.4584915409248112e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10821360,
      "step": 38625
    },
    {
      "epoch": 429.22222222222223,
      "grad_norm": 5.234343234405969e-07,
      "learning_rate": 1.4479215210663754e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10822784,
      "step": 38630
    },
    {
      "epoch": 429.27777777777777,
      "grad_norm": 6.207263254509598e-07,
      "learning_rate": 1.4373898310619528e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10824192,
      "step": 38635
    },
    {
      "epoch": 429.3333333333333,
      "grad_norm": 5.452795903693186e-07,
      "learning_rate": 1.4268964725356604e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10825552,
      "step": 38640
    },
    {
      "epoch": 429.3888888888889,
      "grad_norm": 5.01360034377285e-07,
      "learning_rate": 1.4164414471056764e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10826976,
      "step": 38645
    },
    {
      "epoch": 429.44444444444446,
      "grad_norm": 4.878667709817819e-07,
      "learning_rate": 1.4060247563843497e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10828384,
      "step": 38650
    },
    {
      "epoch": 429.5,
      "grad_norm": 1.6791094594736933e-06,
      "learning_rate": 1.3956464019780068e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10829776,
      "step": 38655
    },
    {
      "epoch": 429.55555555555554,
      "grad_norm": 5.375995328904537e-07,
      "learning_rate": 1.385306385487145e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10831168,
      "step": 38660
    },
    {
      "epoch": 429.6111111111111,
      "grad_norm": 9.432911838302971e-07,
      "learning_rate": 1.3750047085063222e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10832576,
      "step": 38665
    },
    {
      "epoch": 429.6666666666667,
      "grad_norm": 2.112441507051699e-06,
      "learning_rate": 1.3647413726242119e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10833984,
      "step": 38670
    },
    {
      "epoch": 429.72222222222223,
      "grad_norm": 1.9756482743105153e-06,
      "learning_rate": 1.3545163794235205e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10835392,
      "step": 38675
    },
    {
      "epoch": 429.77777777777777,
      "grad_norm": 5.426803681984893e-07,
      "learning_rate": 1.3443297304810698e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10836800,
      "step": 38680
    },
    {
      "epoch": 429.8333333333333,
      "grad_norm": 9.874289617073373e-07,
      "learning_rate": 1.3341814273677977e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10838208,
      "step": 38685
    },
    {
      "epoch": 429.8888888888889,
      "grad_norm": 5.862407874701603e-07,
      "learning_rate": 1.324071471648647e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10839632,
      "step": 38690
    },
    {
      "epoch": 429.94444444444446,
      "grad_norm": 5.187463330003084e-07,
      "learning_rate": 1.3139998648827312e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10840992,
      "step": 38695
    },
    {
      "epoch": 430.0,
      "grad_norm": 5.345684712665388e-07,
      "learning_rate": 1.3039666086232526e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10842416,
      "step": 38700
    },
    {
      "epoch": 430.05555555555554,
      "grad_norm": 4.441819214662246e-07,
      "learning_rate": 1.2939717044174183e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10843824,
      "step": 38705
    },
    {
      "epoch": 430.1111111111111,
      "grad_norm": 5.274227987683844e-07,
      "learning_rate": 1.284015153806578e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10845200,
      "step": 38710
    },
    {
      "epoch": 430.1666666666667,
      "grad_norm": 1.6749194173826254e-06,
      "learning_rate": 1.274096958326171e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10846592,
      "step": 38715
    },
    {
      "epoch": 430.22222222222223,
      "grad_norm": 1.4855313565931283e-06,
      "learning_rate": 1.2642171195056952e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10848016,
      "step": 38720
    },
    {
      "epoch": 430.27777777777777,
      "grad_norm": 1.6603157746430952e-06,
      "learning_rate": 1.2543756388687377e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10849408,
      "step": 38725
    },
    {
      "epoch": 430.3333333333333,
      "grad_norm": 1.46873310313822e-06,
      "learning_rate": 1.2445725179330014e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10850816,
      "step": 38730
    },
    {
      "epoch": 430.3888888888889,
      "grad_norm": 9.07232788449619e-07,
      "learning_rate": 1.2348077582102212e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10852256,
      "step": 38735
    },
    {
      "epoch": 430.44444444444446,
      "grad_norm": 1.0025113397205132e-06,
      "learning_rate": 1.2250813612062762e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10853632,
      "step": 38740
    },
    {
      "epoch": 430.5,
      "grad_norm": 1.9334827356942696e-06,
      "learning_rate": 1.215393328421105e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10855024,
      "step": 38745
    },
    {
      "epoch": 430.55555555555554,
      "grad_norm": 5.321010121406289e-07,
      "learning_rate": 1.2057436613486796e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10856368,
      "step": 38750
    },
    {
      "epoch": 430.6111111111111,
      "grad_norm": 5.466965831146808e-07,
      "learning_rate": 1.1961323614771424e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10857792,
      "step": 38755
    },
    {
      "epoch": 430.6666666666667,
      "grad_norm": 9.660406021794188e-07,
      "learning_rate": 1.1865594302886418e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10859200,
      "step": 38760
    },
    {
      "epoch": 430.72222222222223,
      "grad_norm": 9.361046409139817e-07,
      "learning_rate": 1.1770248692594687e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10860560,
      "step": 38765
    },
    {
      "epoch": 430.77777777777777,
      "grad_norm": 1.0630161568769836e-06,
      "learning_rate": 1.167528679859975e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10861984,
      "step": 38770
    },
    {
      "epoch": 430.8333333333333,
      "grad_norm": 6.226413233889616e-07,
      "learning_rate": 1.1580708635545446e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10863440,
      "step": 38775
    },
    {
      "epoch": 430.8888888888889,
      "grad_norm": 5.210287099544075e-07,
      "learning_rate": 1.1486514218017885e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10864816,
      "step": 38780
    },
    {
      "epoch": 430.94444444444446,
      "grad_norm": 5.162345928511058e-07,
      "learning_rate": 1.1392703560542117e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10866208,
      "step": 38785
    },
    {
      "epoch": 431.0,
      "grad_norm": 4.877371111433604e-07,
      "learning_rate": 1.129927667758518e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10867632,
      "step": 38790
    },
    {
      "epoch": 431.05555555555554,
      "grad_norm": 5.203522732699639e-07,
      "learning_rate": 1.1206233583554992e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10869024,
      "step": 38795
    },
    {
      "epoch": 431.1111111111111,
      "grad_norm": 5.5615379324081e-07,
      "learning_rate": 1.1113574292799523e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10870400,
      "step": 38800
    },
    {
      "epoch": 431.1111111111111,
      "eval_loss": 0.37556880712509155,
      "eval_runtime": 1.3032,
      "eval_samples_per_second": 30.694,
      "eval_steps_per_second": 15.347,
      "num_input_tokens_seen": 10870400,
      "step": 38800
    },
    {
      "epoch": 431.1666666666667,
      "grad_norm": 1.6982539818855003e-06,
      "learning_rate": 1.1021298819608449e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10871840,
      "step": 38805
    },
    {
      "epoch": 431.22222222222223,
      "grad_norm": 1.9759670522034867e-06,
      "learning_rate": 1.0929407178211226e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10873232,
      "step": 38810
    },
    {
      "epoch": 431.27777777777777,
      "grad_norm": 1.6594050293861073e-06,
      "learning_rate": 1.0837899382779293e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10874592,
      "step": 38815
    },
    {
      "epoch": 431.3333333333333,
      "grad_norm": 5.590926548393327e-07,
      "learning_rate": 1.0746775447423862e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10876000,
      "step": 38820
    },
    {
      "epoch": 431.3888888888889,
      "grad_norm": 4.6972195377747994e-07,
      "learning_rate": 1.0656035386197583e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10877344,
      "step": 38825
    },
    {
      "epoch": 431.44444444444446,
      "grad_norm": 5.685332666871545e-07,
      "learning_rate": 1.0565679213093982e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10878720,
      "step": 38830
    },
    {
      "epoch": 431.5,
      "grad_norm": 5.832208103129233e-07,
      "learning_rate": 1.0475706942046638e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10880064,
      "step": 38835
    },
    {
      "epoch": 431.55555555555554,
      "grad_norm": 5.485798624249583e-07,
      "learning_rate": 1.0386118586930282e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10881488,
      "step": 38840
    },
    {
      "epoch": 431.6111111111111,
      "grad_norm": 5.58550595997076e-07,
      "learning_rate": 1.0296914161561367e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10882896,
      "step": 38845
    },
    {
      "epoch": 431.6666666666667,
      "grad_norm": 1.1093769671788323e-06,
      "learning_rate": 1.0208093679695552e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10884256,
      "step": 38850
    },
    {
      "epoch": 431.72222222222223,
      "grad_norm": 6.068982543183665e-07,
      "learning_rate": 1.0119657155030493e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10885600,
      "step": 38855
    },
    {
      "epoch": 431.77777777777777,
      "grad_norm": 8.291026460938156e-07,
      "learning_rate": 1.003160460120417e-07,
      "loss": 0.0,
      "num_input_tokens_seen": 10887056,
      "step": 38860
    },
    {
      "epoch": 431.8333333333333,
      "grad_norm": 1.4750717127753887e-06,
      "learning_rate": 9.943936031795165e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10888464,
      "step": 38865
    },
    {
      "epoch": 431.8888888888889,
      "grad_norm": 6.259620022319723e-07,
      "learning_rate": 9.856651460323219e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10889920,
      "step": 38870
    },
    {
      "epoch": 431.94444444444446,
      "grad_norm": 2.865918986572069e-06,
      "learning_rate": 9.769750900248953e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10891312,
      "step": 38875
    },
    {
      "epoch": 432.0,
      "grad_norm": 1.0571668553893687e-06,
      "learning_rate": 9.683234364973038e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10892736,
      "step": 38880
    },
    {
      "epoch": 432.05555555555554,
      "grad_norm": 9.51426159190305e-07,
      "learning_rate": 9.597101867837854e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10894112,
      "step": 38885
    },
    {
      "epoch": 432.1111111111111,
      "grad_norm": 5.803744329568872e-07,
      "learning_rate": 9.511353422125835e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10895504,
      "step": 38890
    },
    {
      "epoch": 432.1666666666667,
      "grad_norm": 5.305396371113602e-07,
      "learning_rate": 9.42598904106029e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10896864,
      "step": 38895
    },
    {
      "epoch": 432.22222222222223,
      "grad_norm": 4.789348508893454e-07,
      "learning_rate": 9.341008737806245e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10898272,
      "step": 38900
    },
    {
      "epoch": 432.27777777777777,
      "grad_norm": 9.24889945963514e-07,
      "learning_rate": 9.256412525467661e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10899680,
      "step": 38905
    },
    {
      "epoch": 432.3333333333333,
      "grad_norm": 1.6821946928757825e-06,
      "learning_rate": 9.172200417091326e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10901088,
      "step": 38910
    },
    {
      "epoch": 432.3888888888889,
      "grad_norm": 6.338563593999424e-07,
      "learning_rate": 9.088372425663239e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10902496,
      "step": 38915
    },
    {
      "epoch": 432.44444444444446,
      "grad_norm": 1.0154066103496007e-06,
      "learning_rate": 9.004928564110837e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10903872,
      "step": 38920
    },
    {
      "epoch": 432.5,
      "grad_norm": 6.777480621167342e-07,
      "learning_rate": 8.92186884530244e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10905232,
      "step": 38925
    },
    {
      "epoch": 432.55555555555554,
      "grad_norm": 7.516247251260211e-07,
      "learning_rate": 8.83919328204641e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10906624,
      "step": 38930
    },
    {
      "epoch": 432.6111111111111,
      "grad_norm": 8.958825787885871e-07,
      "learning_rate": 8.756901887093105e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10907984,
      "step": 38935
    },
    {
      "epoch": 432.6666666666667,
      "grad_norm": 8.507062148055411e-07,
      "learning_rate": 8.674994673132098e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10909392,
      "step": 38940
    },
    {
      "epoch": 432.72222222222223,
      "grad_norm": 9.946389809556422e-07,
      "learning_rate": 8.593471652794949e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10910784,
      "step": 38945
    },
    {
      "epoch": 432.77777777777777,
      "grad_norm": 1.6059751715147286e-06,
      "learning_rate": 8.512332838653548e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10912208,
      "step": 38950
    },
    {
      "epoch": 432.8333333333333,
      "grad_norm": 9.686170869827038e-07,
      "learning_rate": 8.431578243220106e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10913616,
      "step": 38955
    },
    {
      "epoch": 432.8888888888889,
      "grad_norm": 5.153825100023823e-07,
      "learning_rate": 8.351207878948552e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10915040,
      "step": 38960
    },
    {
      "epoch": 432.94444444444446,
      "grad_norm": 5.778118179478042e-07,
      "learning_rate": 8.271221758232583e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10916480,
      "step": 38965
    },
    {
      "epoch": 433.0,
      "grad_norm": 2.175128884118749e-06,
      "learning_rate": 8.191619893407332e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10917888,
      "step": 38970
    },
    {
      "epoch": 433.05555555555554,
      "grad_norm": 8.675934850543854e-07,
      "learning_rate": 8.112402296748534e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10919344,
      "step": 38975
    },
    {
      "epoch": 433.1111111111111,
      "grad_norm": 9.434738217350969e-07,
      "learning_rate": 8.033568980471973e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10920752,
      "step": 38980
    },
    {
      "epoch": 433.1666666666667,
      "grad_norm": 9.574229125064448e-07,
      "learning_rate": 7.955119956735146e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10922112,
      "step": 38985
    },
    {
      "epoch": 433.22222222222223,
      "grad_norm": 5.381252776714973e-07,
      "learning_rate": 7.877055237636155e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10923504,
      "step": 38990
    },
    {
      "epoch": 433.27777777777777,
      "grad_norm": 9.051115057445713e-07,
      "learning_rate": 7.79937483521287e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10924912,
      "step": 38995
    },
    {
      "epoch": 433.3333333333333,
      "grad_norm": 5.219342256168602e-07,
      "learning_rate": 7.722078761444873e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10926320,
      "step": 39000
    },
    {
      "epoch": 433.3333333333333,
      "eval_loss": 0.39856666326522827,
      "eval_runtime": 1.2913,
      "eval_samples_per_second": 30.975,
      "eval_steps_per_second": 15.488,
      "num_input_tokens_seen": 10926320,
      "step": 39000
    },
    {
      "epoch": 433.3888888888889,
      "grad_norm": 1.6207063708861824e-06,
      "learning_rate": 7.645167028252631e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10927680,
      "step": 39005
    },
    {
      "epoch": 433.44444444444446,
      "grad_norm": 5.273286660667509e-07,
      "learning_rate": 7.568639647496379e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10929072,
      "step": 39010
    },
    {
      "epoch": 433.5,
      "grad_norm": 4.912012627755757e-07,
      "learning_rate": 7.492496630977508e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10930464,
      "step": 39015
    },
    {
      "epoch": 433.55555555555554,
      "grad_norm": 1.0276265811626217e-06,
      "learning_rate": 7.416737990438571e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10931872,
      "step": 39020
    },
    {
      "epoch": 433.6111111111111,
      "grad_norm": 5.238013613961812e-07,
      "learning_rate": 7.341363737562445e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10933328,
      "step": 39025
    },
    {
      "epoch": 433.6666666666667,
      "grad_norm": 6.352603350023855e-07,
      "learning_rate": 7.266373883972887e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10934720,
      "step": 39030
    },
    {
      "epoch": 433.72222222222223,
      "grad_norm": 5.616997214019648e-07,
      "learning_rate": 7.191768441233981e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10936144,
      "step": 39035
    },
    {
      "epoch": 433.77777777777777,
      "grad_norm": 4.986248995919595e-07,
      "learning_rate": 7.11754742085069e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10937568,
      "step": 39040
    },
    {
      "epoch": 433.8333333333333,
      "grad_norm": 6.090309625506052e-07,
      "learning_rate": 7.043710834269413e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10938960,
      "step": 39045
    },
    {
      "epoch": 433.8888888888889,
      "grad_norm": 1.0204305453953566e-06,
      "learning_rate": 6.970258692876319e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10940320,
      "step": 39050
    },
    {
      "epoch": 433.94444444444446,
      "grad_norm": 1.959278051799629e-06,
      "learning_rate": 6.897191007998738e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10941712,
      "step": 39055
    },
    {
      "epoch": 434.0,
      "grad_norm": 9.9079295523552e-07,
      "learning_rate": 6.824507790904599e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10943104,
      "step": 39060
    },
    {
      "epoch": 434.05555555555554,
      "grad_norm": 1.0424859056001878e-06,
      "learning_rate": 6.752209052802439e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10944512,
      "step": 39065
    },
    {
      "epoch": 434.1111111111111,
      "grad_norm": 5.347426963453472e-07,
      "learning_rate": 6.680294804841946e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10945872,
      "step": 39070
    },
    {
      "epoch": 434.1666666666667,
      "grad_norm": 6.441811137847253e-07,
      "learning_rate": 6.608765058112865e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10947264,
      "step": 39075
    },
    {
      "epoch": 434.22222222222223,
      "grad_norm": 9.038610073730524e-07,
      "learning_rate": 6.537619823646368e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10948640,
      "step": 39080
    },
    {
      "epoch": 434.27777777777777,
      "grad_norm": 1.5017095620351029e-06,
      "learning_rate": 6.466859112413404e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10950096,
      "step": 39085
    },
    {
      "epoch": 434.3333333333333,
      "grad_norm": 5.683563131242408e-07,
      "learning_rate": 6.39648293532663e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10951504,
      "step": 39090
    },
    {
      "epoch": 434.3888888888889,
      "grad_norm": 5.789456736238208e-07,
      "learning_rate": 6.32649130323848e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10952912,
      "step": 39095
    },
    {
      "epoch": 434.44444444444446,
      "grad_norm": 9.187511409436411e-07,
      "learning_rate": 6.256884226943094e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10954304,
      "step": 39100
    },
    {
      "epoch": 434.5,
      "grad_norm": 6.21198751105112e-07,
      "learning_rate": 6.187661717174386e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10955712,
      "step": 39105
    },
    {
      "epoch": 434.55555555555554,
      "grad_norm": 9.287804232371855e-07,
      "learning_rate": 6.118823784607708e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10957056,
      "step": 39110
    },
    {
      "epoch": 434.6111111111111,
      "grad_norm": 5.367383550947125e-07,
      "learning_rate": 6.050370439858178e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10958432,
      "step": 39115
    },
    {
      "epoch": 434.6666666666667,
      "grad_norm": 2.2528117824549554e-06,
      "learning_rate": 5.98230169348235e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10959824,
      "step": 39120
    },
    {
      "epoch": 434.72222222222223,
      "grad_norm": 5.357805434869078e-07,
      "learning_rate": 5.914617555977664e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10961248,
      "step": 39125
    },
    {
      "epoch": 434.77777777777777,
      "grad_norm": 1.6781108342911466e-06,
      "learning_rate": 5.8473180377816017e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10962640,
      "step": 39130
    },
    {
      "epoch": 434.8333333333333,
      "grad_norm": 5.557810140999209e-07,
      "learning_rate": 5.780403149272251e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10964080,
      "step": 39135
    },
    {
      "epoch": 434.8888888888889,
      "grad_norm": 2.320455450899317e-06,
      "learning_rate": 5.7138729007694126e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10965504,
      "step": 39140
    },
    {
      "epoch": 434.94444444444446,
      "grad_norm": 8.919467973100836e-07,
      "learning_rate": 5.64772730253238e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10966928,
      "step": 39145
    },
    {
      "epoch": 435.0,
      "grad_norm": 6.419459737116995e-07,
      "learning_rate": 5.5819663647618814e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10968336,
      "step": 39150
    },
    {
      "epoch": 435.05555555555554,
      "grad_norm": 1.4921323554517585e-06,
      "learning_rate": 5.5165900975989723e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10969728,
      "step": 39155
    },
    {
      "epoch": 435.1111111111111,
      "grad_norm": 6.415874054255255e-07,
      "learning_rate": 5.451598511125311e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10971168,
      "step": 39160
    },
    {
      "epoch": 435.1666666666667,
      "grad_norm": 9.511255143479502e-07,
      "learning_rate": 5.3869916153637124e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10972512,
      "step": 39165
    },
    {
      "epoch": 435.22222222222223,
      "grad_norm": 8.409901397499198e-07,
      "learning_rate": 5.322769420277318e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10973856,
      "step": 39170
    },
    {
      "epoch": 435.27777777777777,
      "grad_norm": 5.938346134826133e-07,
      "learning_rate": 5.258931935769873e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10975264,
      "step": 39175
    },
    {
      "epoch": 435.3333333333333,
      "grad_norm": 6.219505053195462e-07,
      "learning_rate": 5.19547917168628e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10976608,
      "step": 39180
    },
    {
      "epoch": 435.3888888888889,
      "grad_norm": 9.111198551181587e-07,
      "learning_rate": 5.13241113781121e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10978032,
      "step": 39185
    },
    {
      "epoch": 435.44444444444446,
      "grad_norm": 1.6681852912370232e-06,
      "learning_rate": 5.0697278438707755e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10979440,
      "step": 39190
    },
    {
      "epoch": 435.5,
      "grad_norm": 6.301880830505979e-07,
      "learning_rate": 5.0074292995316854e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10980832,
      "step": 39195
    },
    {
      "epoch": 435.55555555555554,
      "grad_norm": 9.392553579345986e-07,
      "learning_rate": 4.945515514400978e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10982240,
      "step": 39200
    },
    {
      "epoch": 435.55555555555554,
      "eval_loss": 0.35255178809165955,
      "eval_runtime": 1.2907,
      "eval_samples_per_second": 30.99,
      "eval_steps_per_second": 15.495,
      "num_input_tokens_seen": 10982240,
      "step": 39200
    },
    {
      "epoch": 435.6111111111111,
      "grad_norm": 6.497051003861998e-07,
      "learning_rate": 4.883986498026571e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10983568,
      "step": 39205
    },
    {
      "epoch": 435.6666666666667,
      "grad_norm": 9.76076876213483e-07,
      "learning_rate": 4.822842259896987e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10984944,
      "step": 39210
    },
    {
      "epoch": 435.72222222222223,
      "grad_norm": 4.969643896401976e-07,
      "learning_rate": 4.762082809441626e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10986320,
      "step": 39215
    },
    {
      "epoch": 435.77777777777777,
      "grad_norm": 6.380827244356624e-07,
      "learning_rate": 4.7017081560302156e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10987696,
      "step": 39220
    },
    {
      "epoch": 435.8333333333333,
      "grad_norm": 1.7131535514636198e-06,
      "learning_rate": 4.6417183089730866e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10989200,
      "step": 39225
    },
    {
      "epoch": 435.8888888888889,
      "grad_norm": 6.515392669825815e-07,
      "learning_rate": 4.5821132775217265e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10990640,
      "step": 39230
    },
    {
      "epoch": 435.94444444444446,
      "grad_norm": 5.428341296465078e-07,
      "learning_rate": 4.5228930708679504e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10992064,
      "step": 39235
    },
    {
      "epoch": 436.0,
      "grad_norm": 5.870818426956248e-07,
      "learning_rate": 4.464057698144175e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10993520,
      "step": 39240
    },
    {
      "epoch": 436.05555555555554,
      "grad_norm": 8.631293439975707e-07,
      "learning_rate": 4.4056071684236974e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10994944,
      "step": 39245
    },
    {
      "epoch": 436.1111111111111,
      "grad_norm": 1.1279048521828372e-06,
      "learning_rate": 4.347541490719864e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10996368,
      "step": 39250
    },
    {
      "epoch": 436.1666666666667,
      "grad_norm": 9.796401627681917e-07,
      "learning_rate": 4.2898606739877336e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10997792,
      "step": 39255
    },
    {
      "epoch": 436.22222222222223,
      "grad_norm": 6.432531449718226e-07,
      "learning_rate": 4.232564727122135e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 10999216,
      "step": 39260
    },
    {
      "epoch": 436.27777777777777,
      "grad_norm": 1.6653142438372015e-06,
      "learning_rate": 4.1756536589585004e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11000576,
      "step": 39265
    },
    {
      "epoch": 436.3333333333333,
      "grad_norm": 5.604990178653679e-07,
      "learning_rate": 4.119127478273976e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11002032,
      "step": 39270
    },
    {
      "epoch": 436.3888888888889,
      "grad_norm": 5.509544962478685e-07,
      "learning_rate": 4.062986193784923e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11003392,
      "step": 39275
    },
    {
      "epoch": 436.44444444444446,
      "grad_norm": 6.120210969129403e-07,
      "learning_rate": 4.007229814149416e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11004768,
      "step": 39280
    },
    {
      "epoch": 436.5,
      "grad_norm": 5.757600547440234e-07,
      "learning_rate": 3.951858347965576e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11006128,
      "step": 39285
    },
    {
      "epoch": 436.55555555555554,
      "grad_norm": 4.3445183450785407e-07,
      "learning_rate": 3.896871803772684e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11007552,
      "step": 39290
    },
    {
      "epoch": 436.6111111111111,
      "grad_norm": 9.133567004937504e-07,
      "learning_rate": 3.842270190050068e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11008928,
      "step": 39295
    },
    {
      "epoch": 436.6666666666667,
      "grad_norm": 5.940946721239015e-07,
      "learning_rate": 3.7880535152179376e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11010272,
      "step": 39300
    },
    {
      "epoch": 436.72222222222223,
      "grad_norm": 5.762174168921774e-07,
      "learning_rate": 3.734221787637382e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11011664,
      "step": 39305
    },
    {
      "epoch": 436.77777777777777,
      "grad_norm": 2.0230513655405957e-06,
      "learning_rate": 3.680775015609817e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11013024,
      "step": 39310
    },
    {
      "epoch": 436.8333333333333,
      "grad_norm": 4.7375263534377154e-07,
      "learning_rate": 3.627713207377537e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11014480,
      "step": 39315
    },
    {
      "epoch": 436.8888888888889,
      "grad_norm": 2.142582388842129e-06,
      "learning_rate": 3.575036371123164e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11015888,
      "step": 39320
    },
    {
      "epoch": 436.94444444444446,
      "grad_norm": 1.0332440751881222e-06,
      "learning_rate": 3.5227445149704776e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11017328,
      "step": 39325
    },
    {
      "epoch": 437.0,
      "grad_norm": 9.489198191658943e-07,
      "learning_rate": 3.470837646983027e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11018736,
      "step": 39330
    },
    {
      "epoch": 437.05555555555554,
      "grad_norm": 5.276601768855471e-07,
      "learning_rate": 3.419315775165799e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11020080,
      "step": 39335
    },
    {
      "epoch": 437.1111111111111,
      "grad_norm": 8.799224247013626e-07,
      "learning_rate": 3.368178907464103e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11021472,
      "step": 39340
    },
    {
      "epoch": 437.1666666666667,
      "grad_norm": 5.660411943608779e-07,
      "learning_rate": 3.317427051763855e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11022912,
      "step": 39345
    },
    {
      "epoch": 437.22222222222223,
      "grad_norm": 9.370160682919959e-07,
      "learning_rate": 3.267060215891571e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11024304,
      "step": 39350
    },
    {
      "epoch": 437.27777777777777,
      "grad_norm": 5.366406981011096e-07,
      "learning_rate": 3.217078407614649e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11025712,
      "step": 39355
    },
    {
      "epoch": 437.3333333333333,
      "grad_norm": 6.736808586538245e-07,
      "learning_rate": 3.1674816346405345e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11027104,
      "step": 39360
    },
    {
      "epoch": 437.3888888888889,
      "grad_norm": 5.842356927132641e-07,
      "learning_rate": 3.11826990461811e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11028448,
      "step": 39365
    },
    {
      "epoch": 437.44444444444446,
      "grad_norm": 5.845002419846423e-07,
      "learning_rate": 3.069443225136304e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11029856,
      "step": 39370
    },
    {
      "epoch": 437.5,
      "grad_norm": 9.28562940316624e-07,
      "learning_rate": 3.021001603724372e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11031264,
      "step": 39375
    },
    {
      "epoch": 437.55555555555554,
      "grad_norm": 9.308413382314029e-07,
      "learning_rate": 2.9729450478532818e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11032672,
      "step": 39380
    },
    {
      "epoch": 437.6111111111111,
      "grad_norm": 5.312709276950045e-07,
      "learning_rate": 2.9252735649337726e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11034128,
      "step": 39385
    },
    {
      "epoch": 437.6666666666667,
      "grad_norm": 9.047098501469009e-07,
      "learning_rate": 2.8779871623171863e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11035520,
      "step": 39390
    },
    {
      "epoch": 437.72222222222223,
      "grad_norm": 9.976761248253752e-07,
      "learning_rate": 2.8310858472957448e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11036928,
      "step": 39395
    },
    {
      "epoch": 437.77777777777777,
      "grad_norm": 1.639613401493989e-06,
      "learning_rate": 2.784569627101996e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11038352,
      "step": 39400
    },
    {
      "epoch": 437.77777777777777,
      "eval_loss": 0.39003992080688477,
      "eval_runtime": 1.2987,
      "eval_samples_per_second": 30.8,
      "eval_steps_per_second": 15.4,
      "num_input_tokens_seen": 11038352,
      "step": 39400
    },
    {
      "epoch": 437.8333333333333,
      "grad_norm": 6.649417514381639e-07,
      "learning_rate": 2.738438508909924e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11039744,
      "step": 39405
    },
    {
      "epoch": 437.8888888888889,
      "grad_norm": 2.9427403660520213e-06,
      "learning_rate": 2.692692499833005e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11041136,
      "step": 39410
    },
    {
      "epoch": 437.94444444444446,
      "grad_norm": 5.470731139212148e-07,
      "learning_rate": 2.647331606926151e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11042544,
      "step": 39415
    },
    {
      "epoch": 438.0,
      "grad_norm": 1.0440239748277236e-06,
      "learning_rate": 2.6023558371843225e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11043936,
      "step": 39420
    },
    {
      "epoch": 438.05555555555554,
      "grad_norm": 6.044541009941895e-07,
      "learning_rate": 2.557765197543638e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11045312,
      "step": 39425
    },
    {
      "epoch": 438.1111111111111,
      "grad_norm": 8.729813885111071e-07,
      "learning_rate": 2.513559694880263e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11046736,
      "step": 39430
    },
    {
      "epoch": 438.1666666666667,
      "grad_norm": 5.471133022183494e-07,
      "learning_rate": 2.469739336011523e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11048112,
      "step": 39435
    },
    {
      "epoch": 438.22222222222223,
      "grad_norm": 5.717026283491577e-07,
      "learning_rate": 2.4263041276947894e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11049552,
      "step": 39440
    },
    {
      "epoch": 438.27777777777777,
      "grad_norm": 5.400602276495192e-07,
      "learning_rate": 2.3832540766283164e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11050976,
      "step": 39445
    },
    {
      "epoch": 438.3333333333333,
      "grad_norm": 3.4793420127243735e-06,
      "learning_rate": 2.3405891894512366e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11052400,
      "step": 39450
    },
    {
      "epoch": 438.3888888888889,
      "grad_norm": 8.664241590849997e-07,
      "learning_rate": 2.29830947274301e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11053824,
      "step": 39455
    },
    {
      "epoch": 438.44444444444446,
      "grad_norm": 5.076825573269161e-07,
      "learning_rate": 2.2564149330231432e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11055168,
      "step": 39460
    },
    {
      "epoch": 438.5,
      "grad_norm": 1.4784549193791463e-06,
      "learning_rate": 2.2149055767528572e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11056592,
      "step": 39465
    },
    {
      "epoch": 438.55555555555554,
      "grad_norm": 2.235038436992909e-06,
      "learning_rate": 2.1737814103334197e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11058000,
      "step": 39470
    },
    {
      "epoch": 438.6111111111111,
      "grad_norm": 4.955139161211264e-07,
      "learning_rate": 2.1330424401064253e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11059392,
      "step": 39475
    },
    {
      "epoch": 438.6666666666667,
      "grad_norm": 5.60577404939977e-07,
      "learning_rate": 2.092688672354348e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11060784,
      "step": 39480
    },
    {
      "epoch": 438.72222222222223,
      "grad_norm": 9.40890345191292e-07,
      "learning_rate": 2.0527201133005435e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11062128,
      "step": 39485
    },
    {
      "epoch": 438.77777777777777,
      "grad_norm": 6.044313067832263e-07,
      "learning_rate": 2.0131367691084148e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11063552,
      "step": 39490
    },
    {
      "epoch": 438.8333333333333,
      "grad_norm": 5.659372845912003e-07,
      "learning_rate": 1.9739386458819675e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11064992,
      "step": 39495
    },
    {
      "epoch": 438.8888888888889,
      "grad_norm": 5.852655249327654e-07,
      "learning_rate": 1.9351257496666442e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11066368,
      "step": 39500
    },
    {
      "epoch": 438.94444444444446,
      "grad_norm": 1.923691570482333e-06,
      "learning_rate": 1.896698086447657e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11067792,
      "step": 39505
    },
    {
      "epoch": 439.0,
      "grad_norm": 5.871147550351452e-07,
      "learning_rate": 1.8586556621505436e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11069168,
      "step": 39510
    },
    {
      "epoch": 439.05555555555554,
      "grad_norm": 5.173515660317207e-07,
      "learning_rate": 1.820998482642833e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11070560,
      "step": 39515
    },
    {
      "epoch": 439.1111111111111,
      "grad_norm": 4.867230813943024e-07,
      "learning_rate": 1.7837265537309912e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11072000,
      "step": 39520
    },
    {
      "epoch": 439.1666666666667,
      "grad_norm": 5.786570227428456e-07,
      "learning_rate": 1.7468398811629206e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11073360,
      "step": 39525
    },
    {
      "epoch": 439.22222222222223,
      "grad_norm": 5.642266387440031e-07,
      "learning_rate": 1.710338470627404e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11074768,
      "step": 39530
    },
    {
      "epoch": 439.27777777777777,
      "grad_norm": 9.603172657079995e-07,
      "learning_rate": 1.6742223277529945e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11076176,
      "step": 39535
    },
    {
      "epoch": 439.3333333333333,
      "grad_norm": 4.983656367585354e-07,
      "learning_rate": 1.6384914581094036e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11077536,
      "step": 39540
    },
    {
      "epoch": 439.3888888888889,
      "grad_norm": 7.107021815500048e-07,
      "learning_rate": 1.6031458672069455e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11078960,
      "step": 39545
    },
    {
      "epoch": 439.44444444444446,
      "grad_norm": 5.573683097281901e-07,
      "learning_rate": 1.5681855604962602e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11080304,
      "step": 39550
    },
    {
      "epoch": 439.5,
      "grad_norm": 6.332178941192979e-07,
      "learning_rate": 1.5336105433683135e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11081744,
      "step": 39555
    },
    {
      "epoch": 439.55555555555554,
      "grad_norm": 5.633104365188046e-07,
      "learning_rate": 1.499420821155506e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11083120,
      "step": 39560
    },
    {
      "epoch": 439.6111111111111,
      "grad_norm": 5.85248926654458e-07,
      "learning_rate": 1.4656163991302874e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11084512,
      "step": 39565
    },
    {
      "epoch": 439.6666666666667,
      "grad_norm": 5.74951627640985e-07,
      "learning_rate": 1.4321972825051544e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11085904,
      "step": 39570
    },
    {
      "epoch": 439.72222222222223,
      "grad_norm": 1.676965553087939e-06,
      "learning_rate": 1.3991634764345951e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11087344,
      "step": 39575
    },
    {
      "epoch": 439.77777777777777,
      "grad_norm": 1.5000725852587493e-06,
      "learning_rate": 1.3665149860120352e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11088752,
      "step": 39580
    },
    {
      "epoch": 439.8333333333333,
      "grad_norm": 8.812837108962412e-07,
      "learning_rate": 1.3342518162728912e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11090128,
      "step": 39585
    },
    {
      "epoch": 439.8888888888889,
      "grad_norm": 6.635070235461171e-07,
      "learning_rate": 1.30237397219235e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11091552,
      "step": 39590
    },
    {
      "epoch": 439.94444444444446,
      "grad_norm": 5.804938609799137e-07,
      "learning_rate": 1.2708814586862016e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11092912,
      "step": 39595
    },
    {
      "epoch": 440.0,
      "grad_norm": 6.54838345326425e-07,
      "learning_rate": 1.2397742806111168e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11094352,
      "step": 39600
    },
    {
      "epoch": 440.0,
      "eval_loss": 0.3569253385066986,
      "eval_runtime": 1.2823,
      "eval_samples_per_second": 31.194,
      "eval_steps_per_second": 15.597,
      "num_input_tokens_seen": 11094352,
      "step": 39600
    },
    {
      "epoch": 440.05555555555554,
      "grad_norm": 1.4792348110859166e-06,
      "learning_rate": 1.209052442764369e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11095760,
      "step": 39605
    },
    {
      "epoch": 440.1111111111111,
      "grad_norm": 1.9786612028838135e-06,
      "learning_rate": 1.17871594988328e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11097184,
      "step": 39610
    },
    {
      "epoch": 440.1666666666667,
      "grad_norm": 5.801207976219303e-07,
      "learning_rate": 1.1487648066466072e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11098544,
      "step": 39615
    },
    {
      "epoch": 440.22222222222223,
      "grad_norm": 4.597367251335527e-07,
      "learning_rate": 1.1191990176728784e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11099968,
      "step": 39620
    },
    {
      "epoch": 440.27777777777777,
      "grad_norm": 5.023966309636307e-07,
      "learning_rate": 1.0900185875215018e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11101360,
      "step": 39625
    },
    {
      "epoch": 440.3333333333333,
      "grad_norm": 3.6925371205143165e-06,
      "learning_rate": 1.0612235206924891e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11102800,
      "step": 39630
    },
    {
      "epoch": 440.3888888888889,
      "grad_norm": 4.424453550200269e-07,
      "learning_rate": 1.0328138216264549e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11104240,
      "step": 39635
    },
    {
      "epoch": 440.44444444444446,
      "grad_norm": 6.262533247536339e-07,
      "learning_rate": 1.004789494704339e-08,
      "loss": 0.0,
      "num_input_tokens_seen": 11105648,
      "step": 39640
    },
    {
      "epoch": 440.5,
      "grad_norm": 9.0221050186301e-07,
      "learning_rate": 9.771505442482397e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11107072,
      "step": 39645
    },
    {
      "epoch": 440.55555555555554,
      "grad_norm": 4.762387675327773e-07,
      "learning_rate": 9.498969745200259e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11108448,
      "step": 39650
    },
    {
      "epoch": 440.6111111111111,
      "grad_norm": 1.929487325469381e-06,
      "learning_rate": 9.230287897230017e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11109840,
      "step": 39655
    },
    {
      "epoch": 440.6666666666667,
      "grad_norm": 1.9356250504642958e-06,
      "learning_rate": 8.965459940002419e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11111264,
      "step": 39660
    },
    {
      "epoch": 440.72222222222223,
      "grad_norm": 9.05879403489962e-07,
      "learning_rate": 8.704485914357019e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11112704,
      "step": 39665
    },
    {
      "epoch": 440.77777777777777,
      "grad_norm": 1.4809859294473426e-06,
      "learning_rate": 8.447365860539402e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11114112,
      "step": 39670
    },
    {
      "epoch": 440.8333333333333,
      "grad_norm": 4.3777689029411704e-07,
      "learning_rate": 8.194099818201184e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11115488,
      "step": 39675
    },
    {
      "epoch": 440.8888888888889,
      "grad_norm": 1.4760996691620676e-06,
      "learning_rate": 7.944687826400011e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11116880,
      "step": 39680
    },
    {
      "epoch": 440.94444444444446,
      "grad_norm": 6.128959171292081e-07,
      "learning_rate": 7.699129923599557e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11118256,
      "step": 39685
    },
    {
      "epoch": 441.0,
      "grad_norm": 8.157854267665243e-07,
      "learning_rate": 7.457426147663982e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11119632,
      "step": 39690
    },
    {
      "epoch": 441.05555555555554,
      "grad_norm": 5.297986831465096e-07,
      "learning_rate": 7.219576535871797e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11121008,
      "step": 39695
    },
    {
      "epoch": 441.1111111111111,
      "grad_norm": 5.817698820465012e-07,
      "learning_rate": 6.985581124896445e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11122448,
      "step": 39700
    },
    {
      "epoch": 441.1666666666667,
      "grad_norm": 6.348902843456017e-07,
      "learning_rate": 6.755439950828501e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11123856,
      "step": 39705
    },
    {
      "epoch": 441.22222222222223,
      "grad_norm": 1.4876222849125043e-06,
      "learning_rate": 6.5291530491562444e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11125264,
      "step": 39710
    },
    {
      "epoch": 441.27777777777777,
      "grad_norm": 5.182343443266291e-07,
      "learning_rate": 6.3067204547739845e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11126640,
      "step": 39715
    },
    {
      "epoch": 441.3333333333333,
      "grad_norm": 6.284739697548503e-07,
      "learning_rate": 6.088142201987612e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11128048,
      "step": 39720
    },
    {
      "epoch": 441.3888888888889,
      "grad_norm": 1.507362298980297e-06,
      "learning_rate": 5.873418324503499e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11129456,
      "step": 39725
    },
    {
      "epoch": 441.44444444444446,
      "grad_norm": 1.0842940127986367e-06,
      "learning_rate": 5.6625488554340465e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11130880,
      "step": 39730
    },
    {
      "epoch": 441.5,
      "grad_norm": 5.50323363768257e-07,
      "learning_rate": 5.455533827297688e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11132288,
      "step": 39735
    },
    {
      "epoch": 441.55555555555554,
      "grad_norm": 6.258074449760898e-07,
      "learning_rate": 5.252373272018885e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11133696,
      "step": 39740
    },
    {
      "epoch": 441.6111111111111,
      "grad_norm": 4.5151259087106155e-07,
      "learning_rate": 5.053067220925356e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11135104,
      "step": 39745
    },
    {
      "epoch": 441.6666666666667,
      "grad_norm": 5.554437052524008e-07,
      "learning_rate": 4.857615704759177e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11136480,
      "step": 39750
    },
    {
      "epoch": 441.72222222222223,
      "grad_norm": 9.038870416588907e-07,
      "learning_rate": 4.666018753654577e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11137888,
      "step": 39755
    },
    {
      "epoch": 441.77777777777777,
      "grad_norm": 1.5220845170915709e-06,
      "learning_rate": 4.478276397162917e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11139232,
      "step": 39760
    },
    {
      "epoch": 441.8333333333333,
      "grad_norm": 5.675887564393634e-07,
      "learning_rate": 4.294388664233262e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11140608,
      "step": 39765
    },
    {
      "epoch": 441.8888888888889,
      "grad_norm": 5.089227670396212e-07,
      "learning_rate": 4.114355583223484e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11142032,
      "step": 39770
    },
    {
      "epoch": 441.94444444444446,
      "grad_norm": 1.6830712183946162e-06,
      "learning_rate": 3.9381771818974845e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11143440,
      "step": 39775
    },
    {
      "epoch": 442.0,
      "grad_norm": 1.7421790516891633e-06,
      "learning_rate": 3.765853487427973e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11144800,
      "step": 39780
    },
    {
      "epoch": 442.05555555555554,
      "grad_norm": 5.420048410087475e-07,
      "learning_rate": 3.5973845263825857e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11146208,
      "step": 39785
    },
    {
      "epoch": 442.1111111111111,
      "grad_norm": 8.48149397825182e-07,
      "learning_rate": 3.4327703247488684e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11147648,
      "step": 39790
    },
    {
      "epoch": 442.1666666666667,
      "grad_norm": 5.176798367756419e-07,
      "learning_rate": 3.2720109079037443e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11149008,
      "step": 39795
    },
    {
      "epoch": 442.22222222222223,
      "grad_norm": 9.152188908956305e-07,
      "learning_rate": 3.1151063006468193e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11150400,
      "step": 39800
    },
    {
      "epoch": 442.22222222222223,
      "eval_loss": 0.3495562970638275,
      "eval_runtime": 1.2925,
      "eval_samples_per_second": 30.947,
      "eval_steps_per_second": 15.473,
      "num_input_tokens_seen": 11150400,
      "step": 39800
    },
    {
      "epoch": 442.27777777777777,
      "grad_norm": 5.531319402507506e-07,
      "learning_rate": 2.962056527169854e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11151792,
      "step": 39805
    },
    {
      "epoch": 442.3333333333333,
      "grad_norm": 1.5338885077653686e-06,
      "learning_rate": 2.8128616110761898e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11153232,
      "step": 39810
    },
    {
      "epoch": 442.3888888888889,
      "grad_norm": 5.162717684470408e-07,
      "learning_rate": 2.6675215753724223e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11154624,
      "step": 39815
    },
    {
      "epoch": 442.44444444444446,
      "grad_norm": 1.005229592010437e-06,
      "learning_rate": 2.5260364424739557e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11156016,
      "step": 39820
    },
    {
      "epoch": 442.5,
      "grad_norm": 4.1792816318775294e-07,
      "learning_rate": 2.3884062341994475e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11157392,
      "step": 39825
    },
    {
      "epoch": 442.55555555555554,
      "grad_norm": 5.557400299949222e-07,
      "learning_rate": 2.25463097177081e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11158704,
      "step": 39830
    },
    {
      "epoch": 442.6111111111111,
      "grad_norm": 9.433439913664188e-07,
      "learning_rate": 2.1247106758215397e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11160112,
      "step": 39835
    },
    {
      "epoch": 442.6666666666667,
      "grad_norm": 5.122672064317157e-07,
      "learning_rate": 1.998645366382834e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11161520,
      "step": 39840
    },
    {
      "epoch": 442.72222222222223,
      "grad_norm": 5.256492272565083e-07,
      "learning_rate": 1.876435062897475e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11162912,
      "step": 39845
    },
    {
      "epoch": 442.77777777777777,
      "grad_norm": 4.842408998229075e-07,
      "learning_rate": 1.758079784211497e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11164320,
      "step": 39850
    },
    {
      "epoch": 442.8333333333333,
      "grad_norm": 5.763129706792824e-07,
      "learning_rate": 1.6435795485797434e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11165712,
      "step": 39855
    },
    {
      "epoch": 442.8888888888889,
      "grad_norm": 1.009078232527827e-06,
      "learning_rate": 1.5329343736547596e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11167168,
      "step": 39860
    },
    {
      "epoch": 442.94444444444446,
      "grad_norm": 5.859122325091448e-07,
      "learning_rate": 1.4261442765006739e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11168608,
      "step": 39865
    },
    {
      "epoch": 443.0,
      "grad_norm": 1.6417834558524191e-06,
      "learning_rate": 1.3232092735876445e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11170064,
      "step": 39870
    },
    {
      "epoch": 443.05555555555554,
      "grad_norm": 5.632590500681545e-07,
      "learning_rate": 1.2241293807918607e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11171456,
      "step": 39875
    },
    {
      "epoch": 443.1111111111111,
      "grad_norm": 3.1320557809522143e-06,
      "learning_rate": 1.128904613387216e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11172832,
      "step": 39880
    },
    {
      "epoch": 443.1666666666667,
      "grad_norm": 5.263506750452507e-07,
      "learning_rate": 1.0375349860591853e-09,
      "loss": 0.0,
      "num_input_tokens_seen": 11174288,
      "step": 39885
    },
    {
      "epoch": 443.22222222222223,
      "grad_norm": 5.738533559451753e-07,
      "learning_rate": 9.5002051290205e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11175664,
      "step": 39890
    },
    {
      "epoch": 443.27777777777777,
      "grad_norm": 1.6176054487004876e-06,
      "learning_rate": 8.663612074077954e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11177056,
      "step": 39895
    },
    {
      "epoch": 443.3333333333333,
      "grad_norm": 8.832523121782287e-07,
      "learning_rate": 7.865570824799884e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11178480,
      "step": 39900
    },
    {
      "epoch": 443.3888888888889,
      "grad_norm": 6.147605517980992e-07,
      "learning_rate": 7.106081504254514e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11179856,
      "step": 39905
    },
    {
      "epoch": 443.44444444444446,
      "grad_norm": 5.611423148366157e-07,
      "learning_rate": 6.385144229570372e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11181264,
      "step": 39910
    },
    {
      "epoch": 443.5,
      "grad_norm": 1.6465867247461574e-06,
      "learning_rate": 5.70275911190854e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11182624,
      "step": 39915
    },
    {
      "epoch": 443.55555555555554,
      "grad_norm": 6.158369956210663e-07,
      "learning_rate": 5.058926256490403e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11184032,
      "step": 39920
    },
    {
      "epoch": 443.6111111111111,
      "grad_norm": 9.603669468560838e-07,
      "learning_rate": 4.4536457626254134e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11185440,
      "step": 39925
    },
    {
      "epoch": 443.6666666666667,
      "grad_norm": 1.4685721225760062e-06,
      "learning_rate": 3.88691772365557e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11186816,
      "step": 39930
    },
    {
      "epoch": 443.72222222222223,
      "grad_norm": 5.623015226774442e-07,
      "learning_rate": 3.358742226955425e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11188224,
      "step": 39935
    },
    {
      "epoch": 443.77777777777777,
      "grad_norm": 5.969835683572455e-07,
      "learning_rate": 2.8691193539875925e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11189664,
      "step": 39940
    },
    {
      "epoch": 443.8333333333333,
      "grad_norm": 9.882338645184063e-07,
      "learning_rate": 2.418049180274995e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11191072,
      "step": 39945
    },
    {
      "epoch": 443.8888888888889,
      "grad_norm": 4.744655655031238e-07,
      "learning_rate": 2.005531775373104e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11192480,
      "step": 39950
    },
    {
      "epoch": 443.94444444444446,
      "grad_norm": 2.7976279852737207e-06,
      "learning_rate": 1.6315672028699435e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11193888,
      "step": 39955
    },
    {
      "epoch": 444.0,
      "grad_norm": 1.7072936771000968e-06,
      "learning_rate": 1.2961555204693555e-10,
      "loss": 0.0,
      "num_input_tokens_seen": 11195264,
      "step": 39960
    },
    {
      "epoch": 444.05555555555554,
      "grad_norm": 4.4039072122359357e-07,
      "learning_rate": 9.992967798799768e-11,
      "loss": 0.0,
      "num_input_tokens_seen": 11196624,
      "step": 39965
    },
    {
      "epoch": 444.1111111111111,
      "grad_norm": 1.6724402485124301e-06,
      "learning_rate": 7.409910268707521e-11,
      "loss": 0.0,
      "num_input_tokens_seen": 11198016,
      "step": 39970
    },
    {
      "epoch": 444.1666666666667,
      "grad_norm": 1.6577256474192836e-06,
      "learning_rate": 5.212383012986877e-11,
      "loss": 0.0,
      "num_input_tokens_seen": 11199440,
      "step": 39975
    },
    {
      "epoch": 444.22222222222223,
      "grad_norm": 5.586348379438277e-07,
      "learning_rate": 3.400386370533415e-11,
      "loss": 0.0,
      "num_input_tokens_seen": 11200880,
      "step": 39980
    },
    {
      "epoch": 444.27777777777777,
      "grad_norm": 3.586521870602155e-06,
      "learning_rate": 1.9739206205682258e-11,
      "loss": 0.0,
      "num_input_tokens_seen": 11202304,
      "step": 39985
    },
    {
      "epoch": 444.3333333333333,
      "grad_norm": 4.831579758501903e-07,
      "learning_rate": 9.329859829154685e-12,
      "loss": 0.0,
      "num_input_tokens_seen": 11203696,
      "step": 39990
    },
    {
      "epoch": 444.3888888888889,
      "grad_norm": 4.0569395309830725e-07,
      "learning_rate": 2.7758261855748148e-12,
      "loss": 0.0,
      "num_input_tokens_seen": 11205088,
      "step": 39995
    },
    {
      "epoch": 444.44444444444446,
      "grad_norm": 1.7569343526702141e-06,
      "learning_rate": 7.710628524559838e-14,
      "loss": 0.0,
      "num_input_tokens_seen": 11206480,
      "step": 40000
    },
    {
      "epoch": 444.44444444444446,
      "eval_loss": 0.33738812804222107,
      "eval_runtime": 1.2995,
      "eval_samples_per_second": 30.781,
      "eval_steps_per_second": 15.39,
      "num_input_tokens_seen": 11206480,
      "step": 40000
    },
    {
      "epoch": 444.44444444444446,
      "num_input_tokens_seen": 11206480,
      "step": 40000,
      "total_flos": 4.7931140720492544e+17,
      "train_loss": 0.0004821295712202989,
      "train_runtime": 16360.6288,
      "train_samples_per_second": 9.78,
      "train_steps_per_second": 2.445
    }
  ],
  "logging_steps": 5,
  "max_steps": 40000,
  "num_input_tokens_seen": 11206480,
  "num_train_epochs": 445,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7931140720492544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}