Instructions to use ulas742/lora-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ulas742/lora-small with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B") model = PeftModel.from_pretrained(base_model, "ulas742/lora-small") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-5000/trainer_state.json from ulas742/lora-small: direct link, hf CLI and curl.
- Browser
- Download file 162 kB
-
https://huggingface.co/ulas742/lora-small/resolve/main/checkpoint-5000/trainer_state.json
- Command line
-
hf download hf://ulas742/lora-small/checkpoint-5000/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/ulas742/lora-small/resolve/main/checkpoint-5000/trainer_state.json
162 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 45.34572219848633,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.578,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 35.23944091796875,
"learning_rate": 3.6e-06,
"loss": 321.7812,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 31.629674911499023,
"learning_rate": 5.600000000000001e-06,
"loss": 321.7244,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 37.21824264526367,
"learning_rate": 7.6e-06,
"loss": 327.2896,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 41.95133972167969,
"learning_rate": 9.600000000000001e-06,
"loss": 327.3718,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 41.561954498291016,
"learning_rate": 1.16e-05,
"loss": 315.5146,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 38.29129409790039,
"learning_rate": 1.3600000000000002e-05,
"loss": 318.5627,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 44.10498046875,
"learning_rate": 1.56e-05,
"loss": 312.3329,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 44.040958404541016,
"learning_rate": 1.76e-05,
"loss": 316.1487,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 48.966148376464844,
"learning_rate": 1.9600000000000002e-05,
"loss": 328.8573,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 48.719276428222656,
"learning_rate": 2.16e-05,
"loss": 314.682,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 56.17375946044922,
"learning_rate": 2.36e-05,
"loss": 315.3329,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 48.65364456176758,
"learning_rate": 2.5600000000000002e-05,
"loss": 320.5187,
"step": 65
},
{
"epoch": 0.014,
"grad_norm": 54.523563385009766,
"learning_rate": 2.7600000000000003e-05,
"loss": 309.5268,
"step": 70
},
{
"epoch": 0.015,
"grad_norm": 55.36623764038086,
"learning_rate": 2.96e-05,
"loss": 303.3225,
"step": 75
},
{
"epoch": 0.016,
"grad_norm": 49.912227630615234,
"learning_rate": 3.16e-05,
"loss": 307.5293,
"step": 80
},
{
"epoch": 0.017,
"grad_norm": 44.767608642578125,
"learning_rate": 3.3600000000000004e-05,
"loss": 321.9792,
"step": 85
},
{
"epoch": 0.018,
"grad_norm": 51.926937103271484,
"learning_rate": 3.56e-05,
"loss": 316.3215,
"step": 90
},
{
"epoch": 0.019,
"grad_norm": 44.54217529296875,
"learning_rate": 3.76e-05,
"loss": 317.4295,
"step": 95
},
{
"epoch": 0.02,
"grad_norm": 55.681034088134766,
"learning_rate": 3.960000000000001e-05,
"loss": 310.2048,
"step": 100
},
{
"epoch": 0.021,
"grad_norm": 49.07088088989258,
"learning_rate": 4.16e-05,
"loss": 314.7998,
"step": 105
},
{
"epoch": 0.022,
"grad_norm": 47.265907287597656,
"learning_rate": 4.36e-05,
"loss": 309.1314,
"step": 110
},
{
"epoch": 0.023,
"grad_norm": 54.9495849609375,
"learning_rate": 4.5600000000000004e-05,
"loss": 311.1284,
"step": 115
},
{
"epoch": 0.024,
"grad_norm": 50.552181243896484,
"learning_rate": 4.76e-05,
"loss": 313.6828,
"step": 120
},
{
"epoch": 0.025,
"grad_norm": 49.1966552734375,
"learning_rate": 4.96e-05,
"loss": 307.6977,
"step": 125
},
{
"epoch": 0.026,
"grad_norm": 51.342525482177734,
"learning_rate": 5.16e-05,
"loss": 310.0091,
"step": 130
},
{
"epoch": 0.027,
"grad_norm": 53.15058517456055,
"learning_rate": 5.360000000000001e-05,
"loss": 309.2304,
"step": 135
},
{
"epoch": 0.028,
"grad_norm": 70.3136978149414,
"learning_rate": 5.560000000000001e-05,
"loss": 305.1431,
"step": 140
},
{
"epoch": 0.029,
"grad_norm": 55.63601303100586,
"learning_rate": 5.76e-05,
"loss": 302.008,
"step": 145
},
{
"epoch": 0.03,
"grad_norm": 51.00766372680664,
"learning_rate": 5.96e-05,
"loss": 310.5994,
"step": 150
},
{
"epoch": 0.031,
"grad_norm": 56.53638458251953,
"learning_rate": 6.16e-05,
"loss": 292.5251,
"step": 155
},
{
"epoch": 0.032,
"grad_norm": 56.440975189208984,
"learning_rate": 6.36e-05,
"loss": 305.7293,
"step": 160
},
{
"epoch": 0.033,
"grad_norm": 59.819984436035156,
"learning_rate": 6.560000000000001e-05,
"loss": 312.4643,
"step": 165
},
{
"epoch": 0.034,
"grad_norm": 75.7228775024414,
"learning_rate": 6.76e-05,
"loss": 245.8394,
"step": 170
},
{
"epoch": 0.035,
"grad_norm": 53.55135726928711,
"learning_rate": 6.96e-05,
"loss": 243.8362,
"step": 175
},
{
"epoch": 0.036,
"grad_norm": 62.67115783691406,
"learning_rate": 7.16e-05,
"loss": 287.5416,
"step": 180
},
{
"epoch": 0.037,
"grad_norm": 52.979793548583984,
"learning_rate": 7.36e-05,
"loss": 293.3803,
"step": 185
},
{
"epoch": 0.038,
"grad_norm": 52.290279388427734,
"learning_rate": 7.560000000000001e-05,
"loss": 306.6807,
"step": 190
},
{
"epoch": 0.039,
"grad_norm": 67.30998992919922,
"learning_rate": 7.76e-05,
"loss": 298.3368,
"step": 195
},
{
"epoch": 0.04,
"grad_norm": 55.25843048095703,
"learning_rate": 7.960000000000001e-05,
"loss": 278.7369,
"step": 200
},
{
"epoch": 0.041,
"grad_norm": 65.67536163330078,
"learning_rate": 8.16e-05,
"loss": 312.0075,
"step": 205
},
{
"epoch": 0.042,
"grad_norm": 63.201416015625,
"learning_rate": 8.36e-05,
"loss": 308.4547,
"step": 210
},
{
"epoch": 0.043,
"grad_norm": 57.8333854675293,
"learning_rate": 8.560000000000001e-05,
"loss": 294.3108,
"step": 215
},
{
"epoch": 0.044,
"grad_norm": 58.91765594482422,
"learning_rate": 8.76e-05,
"loss": 299.3354,
"step": 220
},
{
"epoch": 0.045,
"grad_norm": 52.42339324951172,
"learning_rate": 8.960000000000001e-05,
"loss": 300.8906,
"step": 225
},
{
"epoch": 0.046,
"grad_norm": 54.68716812133789,
"learning_rate": 9.16e-05,
"loss": 310.6755,
"step": 230
},
{
"epoch": 0.047,
"grad_norm": 212.18890380859375,
"learning_rate": 9.360000000000001e-05,
"loss": 311.8085,
"step": 235
},
{
"epoch": 0.048,
"grad_norm": 68.8354263305664,
"learning_rate": 9.56e-05,
"loss": 300.4505,
"step": 240
},
{
"epoch": 0.049,
"grad_norm": 60.16633605957031,
"learning_rate": 9.76e-05,
"loss": 305.0702,
"step": 245
},
{
"epoch": 0.05,
"grad_norm": 68.25749206542969,
"learning_rate": 9.960000000000001e-05,
"loss": 263.8476,
"step": 250
},
{
"epoch": 0.051,
"grad_norm": 78.63923645019531,
"learning_rate": 0.0001016,
"loss": 292.9125,
"step": 255
},
{
"epoch": 0.052,
"grad_norm": 52.39205551147461,
"learning_rate": 0.00010360000000000001,
"loss": 298.1621,
"step": 260
},
{
"epoch": 0.053,
"grad_norm": 71.4918212890625,
"learning_rate": 0.0001056,
"loss": 304.5437,
"step": 265
},
{
"epoch": 0.054,
"grad_norm": 68.6222152709961,
"learning_rate": 0.00010760000000000001,
"loss": 246.9947,
"step": 270
},
{
"epoch": 0.055,
"grad_norm": 84.32728576660156,
"learning_rate": 0.00010960000000000001,
"loss": 306.641,
"step": 275
},
{
"epoch": 0.056,
"grad_norm": 55.64327621459961,
"learning_rate": 0.00011160000000000002,
"loss": 312.2386,
"step": 280
},
{
"epoch": 0.057,
"grad_norm": 61.93655776977539,
"learning_rate": 0.0001136,
"loss": 315.9132,
"step": 285
},
{
"epoch": 0.058,
"grad_norm": 64.90775299072266,
"learning_rate": 0.00011559999999999999,
"loss": 312.8616,
"step": 290
},
{
"epoch": 0.059,
"grad_norm": 60.436927795410156,
"learning_rate": 0.0001176,
"loss": 270.7869,
"step": 295
},
{
"epoch": 0.06,
"grad_norm": 61.79182052612305,
"learning_rate": 0.00011960000000000001,
"loss": 283.6043,
"step": 300
},
{
"epoch": 0.061,
"grad_norm": 67.95398712158203,
"learning_rate": 0.0001216,
"loss": 264.2303,
"step": 305
},
{
"epoch": 0.062,
"grad_norm": 67.74212646484375,
"learning_rate": 0.0001236,
"loss": 310.1396,
"step": 310
},
{
"epoch": 0.063,
"grad_norm": 69.19473266601562,
"learning_rate": 0.00012560000000000002,
"loss": 266.4937,
"step": 315
},
{
"epoch": 0.064,
"grad_norm": 74.57992553710938,
"learning_rate": 0.0001276,
"loss": 246.7177,
"step": 320
},
{
"epoch": 0.065,
"grad_norm": 60.20479965209961,
"learning_rate": 0.0001296,
"loss": 270.1338,
"step": 325
},
{
"epoch": 0.066,
"grad_norm": 60.080810546875,
"learning_rate": 0.0001316,
"loss": 303.0598,
"step": 330
},
{
"epoch": 0.067,
"grad_norm": 76.45138549804688,
"learning_rate": 0.00013360000000000002,
"loss": 270.1677,
"step": 335
},
{
"epoch": 0.068,
"grad_norm": 63.76318359375,
"learning_rate": 0.00013560000000000002,
"loss": 302.7615,
"step": 340
},
{
"epoch": 0.069,
"grad_norm": 62.31223678588867,
"learning_rate": 0.00013759999999999998,
"loss": 304.4131,
"step": 345
},
{
"epoch": 0.07,
"grad_norm": 107.39306640625,
"learning_rate": 0.0001396,
"loss": 289.8084,
"step": 350
},
{
"epoch": 0.071,
"grad_norm": 93.32718658447266,
"learning_rate": 0.0001416,
"loss": 300.6559,
"step": 355
},
{
"epoch": 0.072,
"grad_norm": 62.93545150756836,
"learning_rate": 0.0001436,
"loss": 283.2586,
"step": 360
},
{
"epoch": 0.073,
"grad_norm": 83.80622863769531,
"learning_rate": 0.00014560000000000002,
"loss": 262.5127,
"step": 365
},
{
"epoch": 0.074,
"grad_norm": 73.85086822509766,
"learning_rate": 0.0001476,
"loss": 304.2611,
"step": 370
},
{
"epoch": 0.075,
"grad_norm": 67.023193359375,
"learning_rate": 0.0001496,
"loss": 290.3278,
"step": 375
},
{
"epoch": 0.076,
"grad_norm": 99.57097625732422,
"learning_rate": 0.0001516,
"loss": 296.524,
"step": 380
},
{
"epoch": 0.077,
"grad_norm": 77.39230346679688,
"learning_rate": 0.00015360000000000002,
"loss": 263.7685,
"step": 385
},
{
"epoch": 0.078,
"grad_norm": 62.08967971801758,
"learning_rate": 0.00015560000000000001,
"loss": 289.5857,
"step": 390
},
{
"epoch": 0.079,
"grad_norm": 57.07795333862305,
"learning_rate": 0.0001576,
"loss": 296.4371,
"step": 395
},
{
"epoch": 0.08,
"grad_norm": 67.80342102050781,
"learning_rate": 0.0001596,
"loss": 292.5985,
"step": 400
},
{
"epoch": 0.081,
"grad_norm": 102.50914764404297,
"learning_rate": 0.00016160000000000002,
"loss": 245.5858,
"step": 405
},
{
"epoch": 0.082,
"grad_norm": 73.23768615722656,
"learning_rate": 0.0001636,
"loss": 269.5067,
"step": 410
},
{
"epoch": 0.083,
"grad_norm": 55.31161117553711,
"learning_rate": 0.0001656,
"loss": 284.2472,
"step": 415
},
{
"epoch": 0.084,
"grad_norm": 69.93988037109375,
"learning_rate": 0.0001676,
"loss": 268.031,
"step": 420
},
{
"epoch": 0.085,
"grad_norm": 71.37139129638672,
"learning_rate": 0.0001696,
"loss": 298.9601,
"step": 425
},
{
"epoch": 0.086,
"grad_norm": 71.84090423583984,
"learning_rate": 0.0001716,
"loss": 269.1097,
"step": 430
},
{
"epoch": 0.087,
"grad_norm": 52.79533386230469,
"learning_rate": 0.00017360000000000002,
"loss": 302.7409,
"step": 435
},
{
"epoch": 0.088,
"grad_norm": 59.18761444091797,
"learning_rate": 0.0001756,
"loss": 296.5794,
"step": 440
},
{
"epoch": 0.089,
"grad_norm": 69.19998168945312,
"learning_rate": 0.0001776,
"loss": 295.1216,
"step": 445
},
{
"epoch": 0.09,
"grad_norm": 75.6047134399414,
"learning_rate": 0.0001796,
"loss": 289.3482,
"step": 450
},
{
"epoch": 0.091,
"grad_norm": 63.364139556884766,
"learning_rate": 0.00018160000000000002,
"loss": 292.5362,
"step": 455
},
{
"epoch": 0.092,
"grad_norm": 63.57888412475586,
"learning_rate": 0.00018360000000000002,
"loss": 300.7526,
"step": 460
},
{
"epoch": 0.093,
"grad_norm": 71.47926330566406,
"learning_rate": 0.0001856,
"loss": 310.7431,
"step": 465
},
{
"epoch": 0.094,
"grad_norm": 65.70227813720703,
"learning_rate": 0.0001876,
"loss": 297.2938,
"step": 470
},
{
"epoch": 0.095,
"grad_norm": 59.69890594482422,
"learning_rate": 0.0001896,
"loss": 270.1979,
"step": 475
},
{
"epoch": 0.096,
"grad_norm": 79.22998046875,
"learning_rate": 0.0001916,
"loss": 277.9732,
"step": 480
},
{
"epoch": 0.097,
"grad_norm": 66.13664245605469,
"learning_rate": 0.00019360000000000002,
"loss": 302.6306,
"step": 485
},
{
"epoch": 0.098,
"grad_norm": 57.03192138671875,
"learning_rate": 0.0001956,
"loss": 286.4015,
"step": 490
},
{
"epoch": 0.099,
"grad_norm": 55.27619171142578,
"learning_rate": 0.0001976,
"loss": 298.0568,
"step": 495
},
{
"epoch": 0.1,
"grad_norm": 55.16793441772461,
"learning_rate": 0.0001996,
"loss": 296.1483,
"step": 500
},
{
"epoch": 0.101,
"grad_norm": 58.84857940673828,
"learning_rate": 0.00019999961008995606,
"loss": 309.4064,
"step": 505
},
{
"epoch": 0.102,
"grad_norm": 62.985347747802734,
"learning_rate": 0.0001999980260856137,
"loss": 294.9958,
"step": 510
},
{
"epoch": 0.103,
"grad_norm": 59.40795135498047,
"learning_rate": 0.000199995223636881,
"loss": 281.1267,
"step": 515
},
{
"epoch": 0.104,
"grad_norm": 54.28294372558594,
"learning_rate": 0.00019999120277790477,
"loss": 305.6373,
"step": 520
},
{
"epoch": 0.105,
"grad_norm": 56.23757553100586,
"learning_rate": 0.00019998596355767805,
"loss": 293.8239,
"step": 525
},
{
"epoch": 0.106,
"grad_norm": 52.75642776489258,
"learning_rate": 0.000199979506040039,
"loss": 299.8164,
"step": 530
},
{
"epoch": 0.107,
"grad_norm": 55.38374710083008,
"learning_rate": 0.00019997183030367048,
"loss": 291.3248,
"step": 535
},
{
"epoch": 0.108,
"grad_norm": 57.35643768310547,
"learning_rate": 0.00019996293644209887,
"loss": 296.516,
"step": 540
},
{
"epoch": 0.109,
"grad_norm": 59.5279426574707,
"learning_rate": 0.0001999528245636931,
"loss": 297.022,
"step": 545
},
{
"epoch": 0.11,
"grad_norm": 94.40937805175781,
"learning_rate": 0.00019994149479166324,
"loss": 269.0631,
"step": 550
},
{
"epoch": 0.111,
"grad_norm": 56.67276382446289,
"learning_rate": 0.00019992894726405893,
"loss": 229.5338,
"step": 555
},
{
"epoch": 0.112,
"grad_norm": 65.58580017089844,
"learning_rate": 0.00019991518213376787,
"loss": 299.0329,
"step": 560
},
{
"epoch": 0.113,
"grad_norm": 122.42597198486328,
"learning_rate": 0.00019990019956851382,
"loss": 284.2142,
"step": 565
},
{
"epoch": 0.114,
"grad_norm": 48.66897201538086,
"learning_rate": 0.0001998839997508546,
"loss": 290.9123,
"step": 570
},
{
"epoch": 0.115,
"grad_norm": 52.7710075378418,
"learning_rate": 0.00019986658287817987,
"loss": 282.9158,
"step": 575
},
{
"epoch": 0.116,
"grad_norm": 59.78569412231445,
"learning_rate": 0.00019984794916270876,
"loss": 264.0346,
"step": 580
},
{
"epoch": 0.117,
"grad_norm": 51.239498138427734,
"learning_rate": 0.00019982809883148722,
"loss": 278.2119,
"step": 585
},
{
"epoch": 0.118,
"grad_norm": 45.771385192871094,
"learning_rate": 0.00019980703212638522,
"loss": 256.8016,
"step": 590
},
{
"epoch": 0.119,
"grad_norm": 68.36455535888672,
"learning_rate": 0.00019978474930409395,
"loss": 283.7405,
"step": 595
},
{
"epoch": 0.12,
"grad_norm": 66.43222045898438,
"learning_rate": 0.00019976125063612252,
"loss": 280.3201,
"step": 600
},
{
"epoch": 0.121,
"grad_norm": 47.34906768798828,
"learning_rate": 0.00019973653640879485,
"loss": 286.8456,
"step": 605
},
{
"epoch": 0.122,
"grad_norm": 62.890262603759766,
"learning_rate": 0.00019971060692324598,
"loss": 278.1488,
"step": 610
},
{
"epoch": 0.123,
"grad_norm": 67.57910919189453,
"learning_rate": 0.00019968346249541846,
"loss": 280.0852,
"step": 615
},
{
"epoch": 0.124,
"grad_norm": 67.44754028320312,
"learning_rate": 0.00019965510345605866,
"loss": 273.1637,
"step": 620
},
{
"epoch": 0.125,
"grad_norm": 48.47514724731445,
"learning_rate": 0.0001996255301507125,
"loss": 286.6736,
"step": 625
},
{
"epoch": 0.126,
"grad_norm": 58.169986724853516,
"learning_rate": 0.00019959474293972129,
"loss": 288.5007,
"step": 630
},
{
"epoch": 0.127,
"grad_norm": 55.11975860595703,
"learning_rate": 0.00019956274219821757,
"loss": 269.6669,
"step": 635
},
{
"epoch": 0.128,
"grad_norm": 47.872779846191406,
"learning_rate": 0.00019952952831612026,
"loss": 290.3256,
"step": 640
},
{
"epoch": 0.129,
"grad_norm": 53.464073181152344,
"learning_rate": 0.00019949510169813003,
"loss": 302.1444,
"step": 645
},
{
"epoch": 0.13,
"grad_norm": 44.54434585571289,
"learning_rate": 0.00019945946276372434,
"loss": 274.0604,
"step": 650
},
{
"epoch": 0.131,
"grad_norm": 58.98426055908203,
"learning_rate": 0.00019942261194715236,
"loss": 264.3285,
"step": 655
},
{
"epoch": 0.132,
"grad_norm": 51.247642517089844,
"learning_rate": 0.00019938454969742968,
"loss": 293.6523,
"step": 660
},
{
"epoch": 0.133,
"grad_norm": 53.057464599609375,
"learning_rate": 0.00019934527647833276,
"loss": 286.6662,
"step": 665
},
{
"epoch": 0.134,
"grad_norm": 53.00550842285156,
"learning_rate": 0.00019930479276839344,
"loss": 295.9922,
"step": 670
},
{
"epoch": 0.135,
"grad_norm": 51.69222640991211,
"learning_rate": 0.0001992630990608929,
"loss": 280.5888,
"step": 675
},
{
"epoch": 0.136,
"grad_norm": 47.168575286865234,
"learning_rate": 0.00019922019586385585,
"loss": 282.3569,
"step": 680
},
{
"epoch": 0.137,
"grad_norm": 57.80231857299805,
"learning_rate": 0.00019917608370004417,
"loss": 251.5682,
"step": 685
},
{
"epoch": 0.138,
"grad_norm": 54.561805725097656,
"learning_rate": 0.00019913076310695068,
"loss": 250.5393,
"step": 690
},
{
"epoch": 0.139,
"grad_norm": 46.58423614501953,
"learning_rate": 0.00019908423463679248,
"loss": 279.3385,
"step": 695
},
{
"epoch": 0.14,
"grad_norm": 73.98703002929688,
"learning_rate": 0.0001990364988565043,
"loss": 302.6732,
"step": 700
},
{
"epoch": 0.141,
"grad_norm": 46.092376708984375,
"learning_rate": 0.00019898755634773158,
"loss": 287.1832,
"step": 705
},
{
"epoch": 0.142,
"grad_norm": 73.5405044555664,
"learning_rate": 0.00019893740770682335,
"loss": 286.9068,
"step": 710
},
{
"epoch": 0.143,
"grad_norm": 43.50495529174805,
"learning_rate": 0.0001988860535448249,
"loss": 266.0364,
"step": 715
},
{
"epoch": 0.144,
"grad_norm": 54.091922760009766,
"learning_rate": 0.00019883349448747062,
"loss": 286.2805,
"step": 720
},
{
"epoch": 0.145,
"grad_norm": 69.53164672851562,
"learning_rate": 0.0001987797311751759,
"loss": 286.9355,
"step": 725
},
{
"epoch": 0.146,
"grad_norm": 50.866058349609375,
"learning_rate": 0.00019872476426302982,
"loss": 294.4804,
"step": 730
},
{
"epoch": 0.147,
"grad_norm": 46.98020553588867,
"learning_rate": 0.0001986685944207868,
"loss": 286.8734,
"step": 735
},
{
"epoch": 0.148,
"grad_norm": 47.238983154296875,
"learning_rate": 0.0001986112223328587,
"loss": 291.3399,
"step": 740
},
{
"epoch": 0.149,
"grad_norm": 61.37972640991211,
"learning_rate": 0.00019855264869830629,
"loss": 283.7323,
"step": 745
},
{
"epoch": 0.15,
"grad_norm": 55.343414306640625,
"learning_rate": 0.00019849287423083078,
"loss": 283.7294,
"step": 750
},
{
"epoch": 0.151,
"grad_norm": 73.07318115234375,
"learning_rate": 0.00019843189965876526,
"loss": 278.8252,
"step": 755
},
{
"epoch": 0.152,
"grad_norm": 59.20526123046875,
"learning_rate": 0.00019836972572506557,
"loss": 292.6097,
"step": 760
},
{
"epoch": 0.153,
"grad_norm": 61.79401397705078,
"learning_rate": 0.00019830635318730154,
"loss": 274.8011,
"step": 765
},
{
"epoch": 0.154,
"grad_norm": 51.76266860961914,
"learning_rate": 0.00019824178281764753,
"loss": 296.1988,
"step": 770
},
{
"epoch": 0.155,
"grad_norm": 48.1161994934082,
"learning_rate": 0.00019817601540287306,
"loss": 275.1525,
"step": 775
},
{
"epoch": 0.156,
"grad_norm": 56.47291946411133,
"learning_rate": 0.0001981090517443334,
"loss": 282.4003,
"step": 780
},
{
"epoch": 0.157,
"grad_norm": 45.93486785888672,
"learning_rate": 0.0001980408926579596,
"loss": 271.6085,
"step": 785
},
{
"epoch": 0.158,
"grad_norm": 48.26741409301758,
"learning_rate": 0.00019797153897424852,
"loss": 286.9994,
"step": 790
},
{
"epoch": 0.159,
"grad_norm": 47.9412956237793,
"learning_rate": 0.000197900991538253,
"loss": 273.9757,
"step": 795
},
{
"epoch": 0.16,
"grad_norm": 60.08948516845703,
"learning_rate": 0.00019782925120957124,
"loss": 286.7509,
"step": 800
},
{
"epoch": 0.161,
"grad_norm": 48.55828857421875,
"learning_rate": 0.00019775631886233654,
"loss": 278.9955,
"step": 805
},
{
"epoch": 0.162,
"grad_norm": 57.64690017700195,
"learning_rate": 0.0001976821953852065,
"loss": 276.8143,
"step": 810
},
{
"epoch": 0.163,
"grad_norm": 58.00476837158203,
"learning_rate": 0.00019760688168135232,
"loss": 277.4751,
"step": 815
},
{
"epoch": 0.164,
"grad_norm": 57.093963623046875,
"learning_rate": 0.00019753037866844771,
"loss": 262.7667,
"step": 820
},
{
"epoch": 0.165,
"grad_norm": 56.95517349243164,
"learning_rate": 0.00019745268727865774,
"loss": 269.5826,
"step": 825
},
{
"epoch": 0.166,
"grad_norm": 50.23096466064453,
"learning_rate": 0.00019737380845862745,
"loss": 285.1032,
"step": 830
},
{
"epoch": 0.167,
"grad_norm": 50.731136322021484,
"learning_rate": 0.0001972937431694704,
"loss": 268.6636,
"step": 835
},
{
"epoch": 0.168,
"grad_norm": 58.02402877807617,
"learning_rate": 0.00019721249238675688,
"loss": 275.4251,
"step": 840
},
{
"epoch": 0.169,
"grad_norm": 69.00015258789062,
"learning_rate": 0.000197130057100502,
"loss": 285.3165,
"step": 845
},
{
"epoch": 0.17,
"grad_norm": 46.96028518676758,
"learning_rate": 0.00019704643831515374,
"loss": 285.7622,
"step": 850
},
{
"epoch": 0.171,
"grad_norm": 58.708492279052734,
"learning_rate": 0.0001969616370495806,
"loss": 278.9549,
"step": 855
},
{
"epoch": 0.172,
"grad_norm": 43.957550048828125,
"learning_rate": 0.00019687565433705926,
"loss": 285.4878,
"step": 860
},
{
"epoch": 0.173,
"grad_norm": 47.97303771972656,
"learning_rate": 0.00019678849122526187,
"loss": 264.2698,
"step": 865
},
{
"epoch": 0.174,
"grad_norm": 49.05190658569336,
"learning_rate": 0.00019670014877624353,
"loss": 263.6371,
"step": 870
},
{
"epoch": 0.175,
"grad_norm": 47.07678985595703,
"learning_rate": 0.00019661062806642903,
"loss": 271.3718,
"step": 875
},
{
"epoch": 0.176,
"grad_norm": 59.09493637084961,
"learning_rate": 0.0001965199301866,
"loss": 262.7315,
"step": 880
},
{
"epoch": 0.177,
"grad_norm": 44.131996154785156,
"learning_rate": 0.00019642805624188147,
"loss": 265.7331,
"step": 885
},
{
"epoch": 0.178,
"grad_norm": 61.45351791381836,
"learning_rate": 0.0001963350073517285,
"loss": 255.2025,
"step": 890
},
{
"epoch": 0.179,
"grad_norm": 57.042808532714844,
"learning_rate": 0.0001962407846499124,
"loss": 268.0531,
"step": 895
},
{
"epoch": 0.18,
"grad_norm": 51.4085693359375,
"learning_rate": 0.0001961453892845071,
"loss": 261.5828,
"step": 900
},
{
"epoch": 0.181,
"grad_norm": 51.26783752441406,
"learning_rate": 0.00019604882241787498,
"loss": 262.4921,
"step": 905
},
{
"epoch": 0.182,
"grad_norm": 64.2865982055664,
"learning_rate": 0.0001959510852266529,
"loss": 279.2708,
"step": 910
},
{
"epoch": 0.183,
"grad_norm": 50.644039154052734,
"learning_rate": 0.0001958521789017376,
"loss": 276.3466,
"step": 915
},
{
"epoch": 0.184,
"grad_norm": 51.023094177246094,
"learning_rate": 0.00019575210464827149,
"loss": 288.5591,
"step": 920
},
{
"epoch": 0.185,
"grad_norm": 48.759307861328125,
"learning_rate": 0.0001956508636856278,
"loss": 276.0183,
"step": 925
},
{
"epoch": 0.186,
"grad_norm": 52.664642333984375,
"learning_rate": 0.00019554845724739566,
"loss": 270.6455,
"step": 930
},
{
"epoch": 0.187,
"grad_norm": 48.79008865356445,
"learning_rate": 0.00019544488658136523,
"loss": 284.0267,
"step": 935
},
{
"epoch": 0.188,
"grad_norm": 48.21590042114258,
"learning_rate": 0.00019534015294951233,
"loss": 282.7852,
"step": 940
},
{
"epoch": 0.189,
"grad_norm": 55.6912727355957,
"learning_rate": 0.00019523425762798329,
"loss": 284.7149,
"step": 945
},
{
"epoch": 0.19,
"grad_norm": 76.09707641601562,
"learning_rate": 0.00019512720190707913,
"loss": 266.0458,
"step": 950
},
{
"epoch": 0.191,
"grad_norm": 70.18879699707031,
"learning_rate": 0.00019501898709124008,
"loss": 281.1459,
"step": 955
},
{
"epoch": 0.192,
"grad_norm": 47.123775482177734,
"learning_rate": 0.00019490961449902946,
"loss": 282.8954,
"step": 960
},
{
"epoch": 0.193,
"grad_norm": 46.44071960449219,
"learning_rate": 0.00019479908546311781,
"loss": 283.2815,
"step": 965
},
{
"epoch": 0.194,
"grad_norm": 48.01999282836914,
"learning_rate": 0.0001946874013302666,
"loss": 279.4495,
"step": 970
},
{
"epoch": 0.195,
"grad_norm": 54.30856704711914,
"learning_rate": 0.0001945745634613117,
"loss": 281.8633,
"step": 975
},
{
"epoch": 0.196,
"grad_norm": 60.08113098144531,
"learning_rate": 0.0001944605732311469,
"loss": 284.9872,
"step": 980
},
{
"epoch": 0.197,
"grad_norm": 61.01625442504883,
"learning_rate": 0.00019434543202870725,
"loss": 274.5333,
"step": 985
},
{
"epoch": 0.198,
"grad_norm": 47.403377532958984,
"learning_rate": 0.0001942291412569519,
"loss": 281.1945,
"step": 990
},
{
"epoch": 0.199,
"grad_norm": 42.819091796875,
"learning_rate": 0.00019411170233284727,
"loss": 288.0547,
"step": 995
},
{
"epoch": 0.2,
"grad_norm": 44.18984603881836,
"learning_rate": 0.00019399311668734956,
"loss": 285.208,
"step": 1000
},
{
"epoch": 0.201,
"grad_norm": 46.686588287353516,
"learning_rate": 0.00019387338576538744,
"loss": 289.4717,
"step": 1005
},
{
"epoch": 0.202,
"grad_norm": 54.98046112060547,
"learning_rate": 0.0001937525110258444,
"loss": 280.2115,
"step": 1010
},
{
"epoch": 0.203,
"grad_norm": 45.183387756347656,
"learning_rate": 0.00019363049394154094,
"loss": 285.319,
"step": 1015
},
{
"epoch": 0.204,
"grad_norm": 49.63119888305664,
"learning_rate": 0.00019350733599921683,
"loss": 270.5074,
"step": 1020
},
{
"epoch": 0.205,
"grad_norm": 47.29715347290039,
"learning_rate": 0.00019338303869951269,
"loss": 275.1198,
"step": 1025
},
{
"epoch": 0.206,
"grad_norm": 60.79301834106445,
"learning_rate": 0.00019325760355695188,
"loss": 284.8178,
"step": 1030
},
{
"epoch": 0.207,
"grad_norm": 52.7172966003418,
"learning_rate": 0.00019313103209992204,
"loss": 272.2249,
"step": 1035
},
{
"epoch": 0.208,
"grad_norm": 43.442115783691406,
"learning_rate": 0.0001930033258706564,
"loss": 280.1849,
"step": 1040
},
{
"epoch": 0.209,
"grad_norm": 69.27387237548828,
"learning_rate": 0.00019287448642521513,
"loss": 285.6339,
"step": 1045
},
{
"epoch": 0.21,
"grad_norm": 82.95686340332031,
"learning_rate": 0.00019274451533346615,
"loss": 281.9283,
"step": 1050
},
{
"epoch": 0.211,
"grad_norm": 54.01242446899414,
"learning_rate": 0.00019261341417906621,
"loss": 283.1166,
"step": 1055
},
{
"epoch": 0.212,
"grad_norm": 50.461769104003906,
"learning_rate": 0.0001924811845594415,
"loss": 268.7808,
"step": 1060
},
{
"epoch": 0.213,
"grad_norm": 50.19092559814453,
"learning_rate": 0.00019234782808576824,
"loss": 282.247,
"step": 1065
},
{
"epoch": 0.214,
"grad_norm": 48.89931106567383,
"learning_rate": 0.00019221334638295294,
"loss": 271.4232,
"step": 1070
},
{
"epoch": 0.215,
"grad_norm": 60.72257995605469,
"learning_rate": 0.00019207774108961272,
"loss": 278.4014,
"step": 1075
},
{
"epoch": 0.216,
"grad_norm": 54.485374450683594,
"learning_rate": 0.0001919410138580553,
"loss": 278.6501,
"step": 1080
},
{
"epoch": 0.217,
"grad_norm": 60.64812469482422,
"learning_rate": 0.0001918031663542588,
"loss": 274.0851,
"step": 1085
},
{
"epoch": 0.218,
"grad_norm": 48.138248443603516,
"learning_rate": 0.00019166420025785164,
"loss": 282.6086,
"step": 1090
},
{
"epoch": 0.219,
"grad_norm": 55.088932037353516,
"learning_rate": 0.00019152411726209176,
"loss": 281.5728,
"step": 1095
},
{
"epoch": 0.22,
"grad_norm": 56.48404312133789,
"learning_rate": 0.0001913829190738463,
"loss": 259.0733,
"step": 1100
},
{
"epoch": 0.221,
"grad_norm": 51.37434768676758,
"learning_rate": 0.00019124060741357063,
"loss": 285.3994,
"step": 1105
},
{
"epoch": 0.222,
"grad_norm": 54.788936614990234,
"learning_rate": 0.0001910971840152874,
"loss": 278.9071,
"step": 1110
},
{
"epoch": 0.223,
"grad_norm": 80.36026000976562,
"learning_rate": 0.00019095265062656544,
"loss": 273.4703,
"step": 1115
},
{
"epoch": 0.224,
"grad_norm": 46.11319351196289,
"learning_rate": 0.00019080700900849851,
"loss": 271.8554,
"step": 1120
},
{
"epoch": 0.225,
"grad_norm": 56.28084182739258,
"learning_rate": 0.00019066026093568378,
"loss": 277.7285,
"step": 1125
},
{
"epoch": 0.226,
"grad_norm": 45.574974060058594,
"learning_rate": 0.00019051240819620014,
"loss": 278.846,
"step": 1130
},
{
"epoch": 0.227,
"grad_norm": 46.18704605102539,
"learning_rate": 0.00019036345259158667,
"loss": 278.5995,
"step": 1135
},
{
"epoch": 0.228,
"grad_norm": 45.617332458496094,
"learning_rate": 0.00019021339593682028,
"loss": 277.3522,
"step": 1140
},
{
"epoch": 0.229,
"grad_norm": 55.12424087524414,
"learning_rate": 0.00019006224006029406,
"loss": 265.3224,
"step": 1145
},
{
"epoch": 0.23,
"grad_norm": 52.34011459350586,
"learning_rate": 0.00018990998680379456,
"loss": 277.6808,
"step": 1150
},
{
"epoch": 0.231,
"grad_norm": 61.056175231933594,
"learning_rate": 0.00018975663802247976,
"loss": 291.6425,
"step": 1155
},
{
"epoch": 0.232,
"grad_norm": 57.907012939453125,
"learning_rate": 0.0001896021955848561,
"loss": 275.2473,
"step": 1160
},
{
"epoch": 0.233,
"grad_norm": 67.78964233398438,
"learning_rate": 0.000189446661372756,
"loss": 276.914,
"step": 1165
},
{
"epoch": 0.234,
"grad_norm": 43.24968338012695,
"learning_rate": 0.0001892900372813147,
"loss": 285.2484,
"step": 1170
},
{
"epoch": 0.235,
"grad_norm": 40.49110794067383,
"learning_rate": 0.00018913232521894732,
"loss": 276.8971,
"step": 1175
},
{
"epoch": 0.236,
"grad_norm": 49.47333526611328,
"learning_rate": 0.00018897352710732564,
"loss": 276.965,
"step": 1180
},
{
"epoch": 0.237,
"grad_norm": 102.49535369873047,
"learning_rate": 0.00018881364488135448,
"loss": 285.3501,
"step": 1185
},
{
"epoch": 0.238,
"grad_norm": 59.885005950927734,
"learning_rate": 0.00018865268048914828,
"loss": 272.4432,
"step": 1190
},
{
"epoch": 0.239,
"grad_norm": 48.78818893432617,
"learning_rate": 0.00018849063589200743,
"loss": 280.503,
"step": 1195
},
{
"epoch": 0.24,
"grad_norm": 61.330631256103516,
"learning_rate": 0.00018832751306439418,
"loss": 271.4646,
"step": 1200
},
{
"epoch": 0.241,
"grad_norm": 51.42898178100586,
"learning_rate": 0.0001881633139939087,
"loss": 281.2951,
"step": 1205
},
{
"epoch": 0.242,
"grad_norm": 46.34280014038086,
"learning_rate": 0.00018799804068126485,
"loss": 273.7546,
"step": 1210
},
{
"epoch": 0.243,
"grad_norm": 49.210784912109375,
"learning_rate": 0.00018783169514026578,
"loss": 275.4605,
"step": 1215
},
{
"epoch": 0.244,
"grad_norm": 46.695472717285156,
"learning_rate": 0.00018766427939777945,
"loss": 277.2047,
"step": 1220
},
{
"epoch": 0.245,
"grad_norm": 47.742740631103516,
"learning_rate": 0.0001874957954937138,
"loss": 280.9094,
"step": 1225
},
{
"epoch": 0.246,
"grad_norm": 51.13950729370117,
"learning_rate": 0.00018732624548099204,
"loss": 278.3534,
"step": 1230
},
{
"epoch": 0.247,
"grad_norm": 79.51956939697266,
"learning_rate": 0.00018715563142552758,
"loss": 275.2643,
"step": 1235
},
{
"epoch": 0.248,
"grad_norm": 42.83713912963867,
"learning_rate": 0.0001869839554061988,
"loss": 274.9076,
"step": 1240
},
{
"epoch": 0.249,
"grad_norm": 45.978050231933594,
"learning_rate": 0.00018681121951482393,
"loss": 279.4208,
"step": 1245
},
{
"epoch": 0.25,
"grad_norm": 48.35042190551758,
"learning_rate": 0.00018663742585613518,
"loss": 279.4141,
"step": 1250
},
{
"epoch": 0.251,
"grad_norm": 42.03864669799805,
"learning_rate": 0.0001864625765477535,
"loss": 279.2781,
"step": 1255
},
{
"epoch": 0.252,
"grad_norm": 39.96771240234375,
"learning_rate": 0.0001862866737201625,
"loss": 275.7363,
"step": 1260
},
{
"epoch": 0.253,
"grad_norm": 49.38249588012695,
"learning_rate": 0.00018610971951668265,
"loss": 288.1274,
"step": 1265
},
{
"epoch": 0.254,
"grad_norm": 46.85017395019531,
"learning_rate": 0.00018593171609344503,
"loss": 270.1588,
"step": 1270
},
{
"epoch": 0.255,
"grad_norm": 52.7684211730957,
"learning_rate": 0.00018575266561936523,
"loss": 280.1056,
"step": 1275
},
{
"epoch": 0.256,
"grad_norm": 48.299522399902344,
"learning_rate": 0.00018557257027611675,
"loss": 278.6028,
"step": 1280
},
{
"epoch": 0.257,
"grad_norm": 48.681549072265625,
"learning_rate": 0.0001853914322581045,
"loss": 276.8517,
"step": 1285
},
{
"epoch": 0.258,
"grad_norm": 64.33309936523438,
"learning_rate": 0.0001852092537724381,
"loss": 262.0452,
"step": 1290
},
{
"epoch": 0.259,
"grad_norm": 61.493751525878906,
"learning_rate": 0.00018502603703890488,
"loss": 269.412,
"step": 1295
},
{
"epoch": 0.26,
"grad_norm": 47.19992446899414,
"learning_rate": 0.0001848417842899429,
"loss": 276.7448,
"step": 1300
},
{
"epoch": 0.261,
"grad_norm": 53.078758239746094,
"learning_rate": 0.0001846564977706138,
"loss": 271.0328,
"step": 1305
},
{
"epoch": 0.262,
"grad_norm": 48.62588882446289,
"learning_rate": 0.00018447017973857532,
"loss": 265.8279,
"step": 1310
},
{
"epoch": 0.263,
"grad_norm": 45.19000244140625,
"learning_rate": 0.0001842828324640539,
"loss": 282.4244,
"step": 1315
},
{
"epoch": 0.264,
"grad_norm": 51.99223709106445,
"learning_rate": 0.00018409445822981693,
"loss": 277.7068,
"step": 1320
},
{
"epoch": 0.265,
"grad_norm": 63.16470718383789,
"learning_rate": 0.000183905059331145,
"loss": 275.4358,
"step": 1325
},
{
"epoch": 0.266,
"grad_norm": 62.11888885498047,
"learning_rate": 0.000183714638075804,
"loss": 274.494,
"step": 1330
},
{
"epoch": 0.267,
"grad_norm": 57.818546295166016,
"learning_rate": 0.00018352319678401676,
"loss": 274.5423,
"step": 1335
},
{
"epoch": 0.268,
"grad_norm": 53.74748611450195,
"learning_rate": 0.000183330737788435,
"loss": 278.6121,
"step": 1340
},
{
"epoch": 0.269,
"grad_norm": 50.203853607177734,
"learning_rate": 0.00018313726343411086,
"loss": 271.9252,
"step": 1345
},
{
"epoch": 0.27,
"grad_norm": 65.44813537597656,
"learning_rate": 0.00018294277607846832,
"loss": 267.8632,
"step": 1350
},
{
"epoch": 0.271,
"grad_norm": 48.04423141479492,
"learning_rate": 0.00018274727809127438,
"loss": 267.5536,
"step": 1355
},
{
"epoch": 0.272,
"grad_norm": 59.265811920166016,
"learning_rate": 0.00018255077185461038,
"loss": 268.4268,
"step": 1360
},
{
"epoch": 0.273,
"grad_norm": 47.52214050292969,
"learning_rate": 0.00018235325976284275,
"loss": 265.7156,
"step": 1365
},
{
"epoch": 0.274,
"grad_norm": 49.38442611694336,
"learning_rate": 0.00018215474422259402,
"loss": 262.0943,
"step": 1370
},
{
"epoch": 0.275,
"grad_norm": 49.31957244873047,
"learning_rate": 0.0001819552276527134,
"loss": 264.2624,
"step": 1375
},
{
"epoch": 0.276,
"grad_norm": 46.64031219482422,
"learning_rate": 0.0001817547124842473,
"loss": 271.314,
"step": 1380
},
{
"epoch": 0.277,
"grad_norm": 59.608097076416016,
"learning_rate": 0.00018155320116040982,
"loss": 278.4709,
"step": 1385
},
{
"epoch": 0.278,
"grad_norm": 44.36711120605469,
"learning_rate": 0.0001813506961365528,
"loss": 267.9179,
"step": 1390
},
{
"epoch": 0.279,
"grad_norm": 44.03354263305664,
"learning_rate": 0.00018114719988013612,
"loss": 276.3737,
"step": 1395
},
{
"epoch": 0.28,
"grad_norm": 46.73600387573242,
"learning_rate": 0.00018094271487069735,
"loss": 281.1463,
"step": 1400
},
{
"epoch": 0.281,
"grad_norm": 47.62178421020508,
"learning_rate": 0.00018073724359982186,
"loss": 284.8451,
"step": 1405
},
{
"epoch": 0.282,
"grad_norm": 52.94386291503906,
"learning_rate": 0.0001805307885711122,
"loss": 278.9838,
"step": 1410
},
{
"epoch": 0.283,
"grad_norm": 50.47867965698242,
"learning_rate": 0.0001803233523001578,
"loss": 260.8532,
"step": 1415
},
{
"epoch": 0.284,
"grad_norm": 43.788631439208984,
"learning_rate": 0.00018011493731450413,
"loss": 270.927,
"step": 1420
},
{
"epoch": 0.285,
"grad_norm": 48.58649444580078,
"learning_rate": 0.00017990554615362198,
"loss": 290.5723,
"step": 1425
},
{
"epoch": 0.286,
"grad_norm": 41.595149993896484,
"learning_rate": 0.00017969518136887663,
"loss": 275.7107,
"step": 1430
},
{
"epoch": 0.287,
"grad_norm": 66.20713806152344,
"learning_rate": 0.00017948384552349657,
"loss": 271.6039,
"step": 1435
},
{
"epoch": 0.288,
"grad_norm": 50.655662536621094,
"learning_rate": 0.00017927154119254236,
"loss": 256.8604,
"step": 1440
},
{
"epoch": 0.289,
"grad_norm": 46.8124885559082,
"learning_rate": 0.0001790582709628753,
"loss": 262.3076,
"step": 1445
},
{
"epoch": 0.29,
"grad_norm": 50.67826461791992,
"learning_rate": 0.00017884403743312582,
"loss": 271.3517,
"step": 1450
},
{
"epoch": 0.291,
"grad_norm": 49.34907913208008,
"learning_rate": 0.00017862884321366188,
"loss": 263.9629,
"step": 1455
},
{
"epoch": 0.292,
"grad_norm": 142.8138885498047,
"learning_rate": 0.00017841269092655715,
"loss": 261.0857,
"step": 1460
},
{
"epoch": 0.293,
"grad_norm": 49.53968048095703,
"learning_rate": 0.000178195583205559,
"loss": 254.2599,
"step": 1465
},
{
"epoch": 0.294,
"grad_norm": 46.59897232055664,
"learning_rate": 0.00017797752269605653,
"loss": 256.6566,
"step": 1470
},
{
"epoch": 0.295,
"grad_norm": 57.85300064086914,
"learning_rate": 0.0001777585120550482,
"loss": 271.6792,
"step": 1475
},
{
"epoch": 0.296,
"grad_norm": 46.9395866394043,
"learning_rate": 0.0001775385539511096,
"loss": 248.5841,
"step": 1480
},
{
"epoch": 0.297,
"grad_norm": 52.38425064086914,
"learning_rate": 0.00017731765106436073,
"loss": 256.4067,
"step": 1485
},
{
"epoch": 0.298,
"grad_norm": 56.25849151611328,
"learning_rate": 0.00017709580608643363,
"loss": 258.4175,
"step": 1490
},
{
"epoch": 0.299,
"grad_norm": 44.94255447387695,
"learning_rate": 0.00017687302172043933,
"loss": 260.0202,
"step": 1495
},
{
"epoch": 0.3,
"grad_norm": 48.517120361328125,
"learning_rate": 0.00017664930068093498,
"loss": 265.9558,
"step": 1500
},
{
"epoch": 0.301,
"grad_norm": 48.20281982421875,
"learning_rate": 0.0001764246456938909,
"loss": 278.9301,
"step": 1505
},
{
"epoch": 0.302,
"grad_norm": 58.53182601928711,
"learning_rate": 0.0001761990594966572,
"loss": 283.6035,
"step": 1510
},
{
"epoch": 0.303,
"grad_norm": 53.574710845947266,
"learning_rate": 0.00017597254483793048,
"loss": 273.2,
"step": 1515
},
{
"epoch": 0.304,
"grad_norm": 45.98015213012695,
"learning_rate": 0.00017574510447772039,
"loss": 276.9031,
"step": 1520
},
{
"epoch": 0.305,
"grad_norm": 49.6352424621582,
"learning_rate": 0.00017551674118731591,
"loss": 273.3175,
"step": 1525
},
{
"epoch": 0.306,
"grad_norm": 45.53011703491211,
"learning_rate": 0.00017528745774925172,
"loss": 266.4909,
"step": 1530
},
{
"epoch": 0.307,
"grad_norm": 42.180625915527344,
"learning_rate": 0.00017505725695727412,
"loss": 270.1266,
"step": 1535
},
{
"epoch": 0.308,
"grad_norm": 42.45751953125,
"learning_rate": 0.00017482614161630714,
"loss": 282.3553,
"step": 1540
},
{
"epoch": 0.309,
"grad_norm": 47.69794464111328,
"learning_rate": 0.00017459411454241822,
"loss": 284.4227,
"step": 1545
},
{
"epoch": 0.31,
"grad_norm": 47.662376403808594,
"learning_rate": 0.0001743611785627841,
"loss": 264.2081,
"step": 1550
},
{
"epoch": 0.311,
"grad_norm": 52.77998352050781,
"learning_rate": 0.0001741273365156561,
"loss": 275.133,
"step": 1555
},
{
"epoch": 0.312,
"grad_norm": 61.724395751953125,
"learning_rate": 0.0001738925912503259,
"loss": 278.4467,
"step": 1560
},
{
"epoch": 0.313,
"grad_norm": 69.30736541748047,
"learning_rate": 0.00017365694562709034,
"loss": 265.1142,
"step": 1565
},
{
"epoch": 0.314,
"grad_norm": 54.34204864501953,
"learning_rate": 0.00017342040251721702,
"loss": 273.0908,
"step": 1570
},
{
"epoch": 0.315,
"grad_norm": 47.92331314086914,
"learning_rate": 0.0001731829648029091,
"loss": 280.243,
"step": 1575
},
{
"epoch": 0.316,
"grad_norm": 49.99816131591797,
"learning_rate": 0.00017294463537727024,
"loss": 276.6516,
"step": 1580
},
{
"epoch": 0.317,
"grad_norm": 47.963836669921875,
"learning_rate": 0.0001727054171442692,
"loss": 270.2112,
"step": 1585
},
{
"epoch": 0.318,
"grad_norm": 48.09587478637695,
"learning_rate": 0.0001724653130187047,
"loss": 252.1641,
"step": 1590
},
{
"epoch": 0.319,
"grad_norm": 43.35991287231445,
"learning_rate": 0.0001722243259261697,
"loss": 263.0384,
"step": 1595
},
{
"epoch": 0.32,
"grad_norm": 52.25444793701172,
"learning_rate": 0.0001719824588030159,
"loss": 267.607,
"step": 1600
},
{
"epoch": 0.321,
"grad_norm": 60.11662292480469,
"learning_rate": 0.00017173971459631787,
"loss": 268.7409,
"step": 1605
},
{
"epoch": 0.322,
"grad_norm": 44.59310531616211,
"learning_rate": 0.00017149609626383717,
"loss": 279.788,
"step": 1610
},
{
"epoch": 0.323,
"grad_norm": 47.14988327026367,
"learning_rate": 0.00017125160677398626,
"loss": 275.7,
"step": 1615
},
{
"epoch": 0.324,
"grad_norm": 43.87659454345703,
"learning_rate": 0.0001710062491057925,
"loss": 269.5364,
"step": 1620
},
{
"epoch": 0.325,
"grad_norm": 45.793251037597656,
"learning_rate": 0.00017076002624886154,
"loss": 264.7808,
"step": 1625
},
{
"epoch": 0.326,
"grad_norm": 46.89291763305664,
"learning_rate": 0.00017051294120334125,
"loss": 258.7566,
"step": 1630
},
{
"epoch": 0.327,
"grad_norm": 45.81279754638672,
"learning_rate": 0.00017026499697988493,
"loss": 269.7484,
"step": 1635
},
{
"epoch": 0.328,
"grad_norm": 40.50094223022461,
"learning_rate": 0.00017001619659961467,
"loss": 259.5116,
"step": 1640
},
{
"epoch": 0.329,
"grad_norm": 54.01460266113281,
"learning_rate": 0.00016976654309408464,
"loss": 247.8254,
"step": 1645
},
{
"epoch": 0.33,
"grad_norm": 71.55792236328125,
"learning_rate": 0.000169516039505244,
"loss": 265.0982,
"step": 1650
},
{
"epoch": 0.331,
"grad_norm": 48.39525604248047,
"learning_rate": 0.0001692646888853999,
"loss": 270.6932,
"step": 1655
},
{
"epoch": 0.332,
"grad_norm": 50.999610900878906,
"learning_rate": 0.00016901249429718032,
"loss": 258.0283,
"step": 1660
},
{
"epoch": 0.333,
"grad_norm": 51.788673400878906,
"learning_rate": 0.00016875945881349676,
"loss": 259.6249,
"step": 1665
},
{
"epoch": 0.334,
"grad_norm": 48.77846908569336,
"learning_rate": 0.0001685055855175067,
"loss": 249.0381,
"step": 1670
},
{
"epoch": 0.335,
"grad_norm": 41.93663024902344,
"learning_rate": 0.0001682508775025762,
"loss": 276.623,
"step": 1675
},
{
"epoch": 0.336,
"grad_norm": 42.32875061035156,
"learning_rate": 0.00016799533787224192,
"loss": 270.7933,
"step": 1680
},
{
"epoch": 0.337,
"grad_norm": 43.655128479003906,
"learning_rate": 0.00016773896974017373,
"loss": 267.1175,
"step": 1685
},
{
"epoch": 0.338,
"grad_norm": 46.489009857177734,
"learning_rate": 0.00016748177623013638,
"loss": 255.5338,
"step": 1690
},
{
"epoch": 0.339,
"grad_norm": 42.454551696777344,
"learning_rate": 0.00016722376047595164,
"loss": 263.2208,
"step": 1695
},
{
"epoch": 0.34,
"grad_norm": 43.79629135131836,
"learning_rate": 0.00016696492562145996,
"loss": 266.7905,
"step": 1700
},
{
"epoch": 0.341,
"grad_norm": 67.76934051513672,
"learning_rate": 0.00016670527482048246,
"loss": 262.0689,
"step": 1705
},
{
"epoch": 0.342,
"grad_norm": 46.36932373046875,
"learning_rate": 0.00016644481123678217,
"loss": 257.5991,
"step": 1710
},
{
"epoch": 0.343,
"grad_norm": 48.82585906982422,
"learning_rate": 0.00016618353804402568,
"loss": 248.5159,
"step": 1715
},
{
"epoch": 0.344,
"grad_norm": 39.46201705932617,
"learning_rate": 0.00016592145842574433,
"loss": 260.2951,
"step": 1720
},
{
"epoch": 0.345,
"grad_norm": 43.358558654785156,
"learning_rate": 0.00016565857557529566,
"loss": 278.8751,
"step": 1725
},
{
"epoch": 0.346,
"grad_norm": 38.60557556152344,
"learning_rate": 0.00016539489269582416,
"loss": 272.6581,
"step": 1730
},
{
"epoch": 0.347,
"grad_norm": 48.5496940612793,
"learning_rate": 0.00016513041300022255,
"loss": 267.7874,
"step": 1735
},
{
"epoch": 0.348,
"grad_norm": 43.05610656738281,
"learning_rate": 0.00016486513971109243,
"loss": 276.9668,
"step": 1740
},
{
"epoch": 0.349,
"grad_norm": 39.59821319580078,
"learning_rate": 0.0001645990760607051,
"loss": 257.0475,
"step": 1745
},
{
"epoch": 0.35,
"grad_norm": 39.866703033447266,
"learning_rate": 0.0001643322252909622,
"loss": 268.2825,
"step": 1750
},
{
"epoch": 0.351,
"grad_norm": 42.79712677001953,
"learning_rate": 0.00016406459065335615,
"loss": 250.6996,
"step": 1755
},
{
"epoch": 0.352,
"grad_norm": 45.14170837402344,
"learning_rate": 0.00016379617540893056,
"loss": 253.5547,
"step": 1760
},
{
"epoch": 0.353,
"grad_norm": 42.09737777709961,
"learning_rate": 0.00016352698282824044,
"loss": 258.4789,
"step": 1765
},
{
"epoch": 0.354,
"grad_norm": 42.384578704833984,
"learning_rate": 0.00016325701619131246,
"loss": 263.2515,
"step": 1770
},
{
"epoch": 0.355,
"grad_norm": 41.00054931640625,
"learning_rate": 0.00016298627878760487,
"loss": 256.0611,
"step": 1775
},
{
"epoch": 0.356,
"grad_norm": 47.38276672363281,
"learning_rate": 0.00016271477391596753,
"loss": 273.1083,
"step": 1780
},
{
"epoch": 0.357,
"grad_norm": 41.749542236328125,
"learning_rate": 0.00016244250488460158,
"loss": 267.0974,
"step": 1785
},
{
"epoch": 0.358,
"grad_norm": 64.88787078857422,
"learning_rate": 0.0001621694750110193,
"loss": 267.0445,
"step": 1790
},
{
"epoch": 0.359,
"grad_norm": 39.5011100769043,
"learning_rate": 0.00016189568762200348,
"loss": 252.6451,
"step": 1795
},
{
"epoch": 0.36,
"grad_norm": 85.52110290527344,
"learning_rate": 0.00016162114605356703,
"loss": 258.4725,
"step": 1800
},
{
"epoch": 0.361,
"grad_norm": 43.748374938964844,
"learning_rate": 0.00016134585365091243,
"loss": 255.776,
"step": 1805
},
{
"epoch": 0.362,
"grad_norm": 46.779014587402344,
"learning_rate": 0.00016106981376839066,
"loss": 256.4178,
"step": 1810
},
{
"epoch": 0.363,
"grad_norm": 42.715553283691406,
"learning_rate": 0.00016079302976946055,
"loss": 262.5154,
"step": 1815
},
{
"epoch": 0.364,
"grad_norm": 135.9436492919922,
"learning_rate": 0.0001605155050266478,
"loss": 254.0172,
"step": 1820
},
{
"epoch": 0.365,
"grad_norm": 54.12862014770508,
"learning_rate": 0.00016023724292150385,
"loss": 257.7888,
"step": 1825
},
{
"epoch": 0.366,
"grad_norm": 42.86738204956055,
"learning_rate": 0.00015995824684456465,
"loss": 262.0852,
"step": 1830
},
{
"epoch": 0.367,
"grad_norm": 40.034828186035156,
"learning_rate": 0.00015967852019530926,
"loss": 271.1969,
"step": 1835
},
{
"epoch": 0.368,
"grad_norm": 42.3065071105957,
"learning_rate": 0.0001593980663821187,
"loss": 259.7493,
"step": 1840
},
{
"epoch": 0.369,
"grad_norm": 39.868247985839844,
"learning_rate": 0.0001591168888222342,
"loss": 266.7453,
"step": 1845
},
{
"epoch": 0.37,
"grad_norm": 43.598350524902344,
"learning_rate": 0.00015883499094171554,
"loss": 279.6421,
"step": 1850
},
{
"epoch": 0.371,
"grad_norm": 40.77791976928711,
"learning_rate": 0.0001585523761753994,
"loss": 254.4231,
"step": 1855
},
{
"epoch": 0.372,
"grad_norm": 39.09046936035156,
"learning_rate": 0.00015826904796685762,
"loss": 269.4206,
"step": 1860
},
{
"epoch": 0.373,
"grad_norm": 58.26347732543945,
"learning_rate": 0.00015798500976835493,
"loss": 274.995,
"step": 1865
},
{
"epoch": 0.374,
"grad_norm": 46.25054931640625,
"learning_rate": 0.00015770026504080718,
"loss": 268.3262,
"step": 1870
},
{
"epoch": 0.375,
"grad_norm": 52.09050369262695,
"learning_rate": 0.000157414817253739,
"loss": 255.2382,
"step": 1875
},
{
"epoch": 0.376,
"grad_norm": 50.76063537597656,
"learning_rate": 0.00015712866988524155,
"loss": 269.2449,
"step": 1880
},
{
"epoch": 0.377,
"grad_norm": 49.88444519042969,
"learning_rate": 0.0001568418264219303,
"loss": 258.9195,
"step": 1885
},
{
"epoch": 0.378,
"grad_norm": 39.796630859375,
"learning_rate": 0.0001565542903589023,
"loss": 238.988,
"step": 1890
},
{
"epoch": 0.379,
"grad_norm": 37.72733688354492,
"learning_rate": 0.0001562660651996937,
"loss": 269.7818,
"step": 1895
},
{
"epoch": 0.38,
"grad_norm": 37.415443420410156,
"learning_rate": 0.00015597715445623712,
"loss": 263.4218,
"step": 1900
},
{
"epoch": 0.381,
"grad_norm": 39.50199508666992,
"learning_rate": 0.00015568756164881882,
"loss": 256.9902,
"step": 1905
},
{
"epoch": 0.382,
"grad_norm": 58.79146194458008,
"learning_rate": 0.00015539729030603574,
"loss": 257.8866,
"step": 1910
},
{
"epoch": 0.383,
"grad_norm": 43.52664566040039,
"learning_rate": 0.0001551063439647526,
"loss": 256.392,
"step": 1915
},
{
"epoch": 0.384,
"grad_norm": 38.189552307128906,
"learning_rate": 0.00015481472617005876,
"loss": 257.9,
"step": 1920
},
{
"epoch": 0.385,
"grad_norm": 37.94824981689453,
"learning_rate": 0.00015452244047522502,
"loss": 254.5535,
"step": 1925
},
{
"epoch": 0.386,
"grad_norm": 56.582923889160156,
"learning_rate": 0.0001542294904416603,
"loss": 258.4363,
"step": 1930
},
{
"epoch": 0.387,
"grad_norm": 39.287269592285156,
"learning_rate": 0.00015393587963886835,
"loss": 252.0892,
"step": 1935
},
{
"epoch": 0.388,
"grad_norm": 46.01531982421875,
"learning_rate": 0.0001536416116444041,
"loss": 268.6771,
"step": 1940
},
{
"epoch": 0.389,
"grad_norm": 46.73694610595703,
"learning_rate": 0.0001533466900438303,
"loss": 278.8018,
"step": 1945
},
{
"epoch": 0.39,
"grad_norm": 42.86819839477539,
"learning_rate": 0.0001530511184306734,
"loss": 275.2447,
"step": 1950
},
{
"epoch": 0.391,
"grad_norm": 45.710994720458984,
"learning_rate": 0.00015275490040638038,
"loss": 269.1281,
"step": 1955
},
{
"epoch": 0.392,
"grad_norm": 53.895023345947266,
"learning_rate": 0.00015245803958027434,
"loss": 259.0909,
"step": 1960
},
{
"epoch": 0.393,
"grad_norm": 45.87960433959961,
"learning_rate": 0.0001521605395695108,
"loss": 263.3782,
"step": 1965
},
{
"epoch": 0.394,
"grad_norm": 47.00539016723633,
"learning_rate": 0.00015186240399903342,
"loss": 262.2372,
"step": 1970
},
{
"epoch": 0.395,
"grad_norm": 43.53969192504883,
"learning_rate": 0.00015156363650153012,
"loss": 269.2971,
"step": 1975
},
{
"epoch": 0.396,
"grad_norm": 43.114707946777344,
"learning_rate": 0.0001512642407173885,
"loss": 270.7597,
"step": 1980
},
{
"epoch": 0.397,
"grad_norm": 56.77632141113281,
"learning_rate": 0.00015096422029465178,
"loss": 265.8668,
"step": 1985
},
{
"epoch": 0.398,
"grad_norm": 41.698387145996094,
"learning_rate": 0.0001506635788889741,
"loss": 239.4794,
"step": 1990
},
{
"epoch": 0.399,
"grad_norm": 45.86994934082031,
"learning_rate": 0.0001503623201635761,
"loss": 269.7941,
"step": 1995
},
{
"epoch": 0.4,
"grad_norm": 55.51190948486328,
"learning_rate": 0.0001500604477892003,
"loss": 267.3379,
"step": 2000
},
{
"epoch": 0.401,
"grad_norm": 46.40678024291992,
"learning_rate": 0.00014975796544406625,
"loss": 249.268,
"step": 2005
},
{
"epoch": 0.402,
"grad_norm": 48.44785690307617,
"learning_rate": 0.00014945487681382598,
"loss": 257.6397,
"step": 2010
},
{
"epoch": 0.403,
"grad_norm": 39.55942916870117,
"learning_rate": 0.0001491511855915187,
"loss": 260.7306,
"step": 2015
},
{
"epoch": 0.404,
"grad_norm": 39.36600875854492,
"learning_rate": 0.0001488468954775262,
"loss": 262.7595,
"step": 2020
},
{
"epoch": 0.405,
"grad_norm": 52.9313850402832,
"learning_rate": 0.0001485420101795274,
"loss": 263.257,
"step": 2025
},
{
"epoch": 0.406,
"grad_norm": 42.74100112915039,
"learning_rate": 0.00014823653341245353,
"loss": 275.2946,
"step": 2030
},
{
"epoch": 0.407,
"grad_norm": 44.90149688720703,
"learning_rate": 0.0001479304688984425,
"loss": 274.8642,
"step": 2035
},
{
"epoch": 0.408,
"grad_norm": 45.88239288330078,
"learning_rate": 0.0001476238203667939,
"loss": 276.9828,
"step": 2040
},
{
"epoch": 0.409,
"grad_norm": 41.3275032043457,
"learning_rate": 0.00014731659155392332,
"loss": 266.4131,
"step": 2045
},
{
"epoch": 0.41,
"grad_norm": 44.44849395751953,
"learning_rate": 0.00014700878620331684,
"loss": 257.4841,
"step": 2050
},
{
"epoch": 0.411,
"grad_norm": 39.9067268371582,
"learning_rate": 0.00014670040806548555,
"loss": 255.8938,
"step": 2055
},
{
"epoch": 0.412,
"grad_norm": 46.979976654052734,
"learning_rate": 0.0001463914608979197,
"loss": 269.7252,
"step": 2060
},
{
"epoch": 0.413,
"grad_norm": 41.959922790527344,
"learning_rate": 0.0001460819484650431,
"loss": 262.6385,
"step": 2065
},
{
"epoch": 0.414,
"grad_norm": 40.0914306640625,
"learning_rate": 0.000145771874538167,
"loss": 253.477,
"step": 2070
},
{
"epoch": 0.415,
"grad_norm": 45.21044921875,
"learning_rate": 0.0001454612428954444,
"loss": 271.5422,
"step": 2075
},
{
"epoch": 0.416,
"grad_norm": 42.94995880126953,
"learning_rate": 0.00014515005732182383,
"loss": 254.1815,
"step": 2080
},
{
"epoch": 0.417,
"grad_norm": 44.29420471191406,
"learning_rate": 0.00014483832160900326,
"loss": 259.3287,
"step": 2085
},
{
"epoch": 0.418,
"grad_norm": 45.52935028076172,
"learning_rate": 0.00014452603955538397,
"loss": 273.308,
"step": 2090
},
{
"epoch": 0.419,
"grad_norm": 44.45758056640625,
"learning_rate": 0.00014421321496602428,
"loss": 267.1953,
"step": 2095
},
{
"epoch": 0.42,
"grad_norm": 50.677799224853516,
"learning_rate": 0.00014389985165259308,
"loss": 266.0748,
"step": 2100
},
{
"epoch": 0.421,
"grad_norm": 46.4390754699707,
"learning_rate": 0.00014358595343332342,
"loss": 261.0065,
"step": 2105
},
{
"epoch": 0.422,
"grad_norm": 44.82138442993164,
"learning_rate": 0.00014327152413296608,
"loss": 260.2899,
"step": 2110
},
{
"epoch": 0.423,
"grad_norm": 42.828739166259766,
"learning_rate": 0.00014295656758274284,
"loss": 272.8948,
"step": 2115
},
{
"epoch": 0.424,
"grad_norm": 42.40986251831055,
"learning_rate": 0.0001426410876202999,
"loss": 253.0389,
"step": 2120
},
{
"epoch": 0.425,
"grad_norm": 37.76167678833008,
"learning_rate": 0.00014232508808966098,
"loss": 261.1503,
"step": 2125
},
{
"epoch": 0.426,
"grad_norm": 45.860496520996094,
"learning_rate": 0.00014200857284118066,
"loss": 251.922,
"step": 2130
},
{
"epoch": 0.427,
"grad_norm": 51.91737365722656,
"learning_rate": 0.00014169154573149737,
"loss": 245.9994,
"step": 2135
},
{
"epoch": 0.428,
"grad_norm": 39.74888229370117,
"learning_rate": 0.00014137401062348638,
"loss": 277.4401,
"step": 2140
},
{
"epoch": 0.429,
"grad_norm": 60.26321029663086,
"learning_rate": 0.0001410559713862128,
"loss": 256.6625,
"step": 2145
},
{
"epoch": 0.43,
"grad_norm": 41.04563522338867,
"learning_rate": 0.00014073743189488435,
"loss": 267.464,
"step": 2150
},
{
"epoch": 0.431,
"grad_norm": 41.26578140258789,
"learning_rate": 0.00014041839603080422,
"loss": 268.2872,
"step": 2155
},
{
"epoch": 0.432,
"grad_norm": 43.122657775878906,
"learning_rate": 0.00014009886768132375,
"loss": 243.2352,
"step": 2160
},
{
"epoch": 0.433,
"grad_norm": 57.64035415649414,
"learning_rate": 0.000139778850739795,
"loss": 267.3623,
"step": 2165
},
{
"epoch": 0.434,
"grad_norm": 40.533477783203125,
"learning_rate": 0.0001394583491055234,
"loss": 266.8007,
"step": 2170
},
{
"epoch": 0.435,
"grad_norm": 43.81973648071289,
"learning_rate": 0.00013913736668372026,
"loss": 271.6288,
"step": 2175
},
{
"epoch": 0.436,
"grad_norm": 42.36226272583008,
"learning_rate": 0.00013881590738545508,
"loss": 277.3282,
"step": 2180
},
{
"epoch": 0.437,
"grad_norm": 40.546119689941406,
"learning_rate": 0.00013849397512760795,
"loss": 265.9954,
"step": 2185
},
{
"epoch": 0.438,
"grad_norm": 58.81496810913086,
"learning_rate": 0.00013817157383282184,
"loss": 250.4207,
"step": 2190
},
{
"epoch": 0.439,
"grad_norm": 39.92459487915039,
"learning_rate": 0.00013784870742945482,
"loss": 261.9355,
"step": 2195
},
{
"epoch": 0.44,
"grad_norm": 44.53604507446289,
"learning_rate": 0.0001375253798515321,
"loss": 257.8669,
"step": 2200
},
{
"epoch": 0.441,
"grad_norm": 42.02375030517578,
"learning_rate": 0.00013720159503869815,
"loss": 257.9089,
"step": 2205
},
{
"epoch": 0.442,
"grad_norm": 44.52000045776367,
"learning_rate": 0.00013687735693616876,
"loss": 264.3058,
"step": 2210
},
{
"epoch": 0.443,
"grad_norm": 43.68276596069336,
"learning_rate": 0.0001365526694946829,
"loss": 258.1611,
"step": 2215
},
{
"epoch": 0.444,
"grad_norm": 44.496604919433594,
"learning_rate": 0.00013622753667045457,
"loss": 264.1986,
"step": 2220
},
{
"epoch": 0.445,
"grad_norm": 45.19287109375,
"learning_rate": 0.00013590196242512463,
"loss": 257.4942,
"step": 2225
},
{
"epoch": 0.446,
"grad_norm": 44.563907623291016,
"learning_rate": 0.0001355759507257125,
"loss": 260.0045,
"step": 2230
},
{
"epoch": 0.447,
"grad_norm": 38.62880325317383,
"learning_rate": 0.00013524950554456784,
"loss": 256.7663,
"step": 2235
},
{
"epoch": 0.448,
"grad_norm": 42.39316940307617,
"learning_rate": 0.00013492263085932224,
"loss": 262.3906,
"step": 2240
},
{
"epoch": 0.449,
"grad_norm": 37.33747863769531,
"learning_rate": 0.0001345953306528405,
"loss": 261.1577,
"step": 2245
},
{
"epoch": 0.45,
"grad_norm": 42.38154220581055,
"learning_rate": 0.00013426760891317236,
"loss": 258.2611,
"step": 2250
},
{
"epoch": 0.451,
"grad_norm": 45.666412353515625,
"learning_rate": 0.00013393946963350382,
"loss": 260.3906,
"step": 2255
},
{
"epoch": 0.452,
"grad_norm": 43.84535598754883,
"learning_rate": 0.00013361091681210845,
"loss": 268.4673,
"step": 2260
},
{
"epoch": 0.453,
"grad_norm": 39.42673110961914,
"learning_rate": 0.00013328195445229868,
"loss": 256.571,
"step": 2265
},
{
"epoch": 0.454,
"grad_norm": 43.45452880859375,
"learning_rate": 0.00013295258656237702,
"loss": 255.3156,
"step": 2270
},
{
"epoch": 0.455,
"grad_norm": 43.8148193359375,
"learning_rate": 0.00013262281715558736,
"loss": 272.6897,
"step": 2275
},
{
"epoch": 0.456,
"grad_norm": 36.79037857055664,
"learning_rate": 0.00013229265025006576,
"loss": 264.7511,
"step": 2280
},
{
"epoch": 0.457,
"grad_norm": 39.53091049194336,
"learning_rate": 0.0001319620898687918,
"loss": 276.4025,
"step": 2285
},
{
"epoch": 0.458,
"grad_norm": 38.17203140258789,
"learning_rate": 0.0001316311400395394,
"loss": 261.4093,
"step": 2290
},
{
"epoch": 0.459,
"grad_norm": 66.99674224853516,
"learning_rate": 0.00013129980479482782,
"loss": 268.4529,
"step": 2295
},
{
"epoch": 0.46,
"grad_norm": 43.206600189208984,
"learning_rate": 0.00013096808817187242,
"loss": 264.7954,
"step": 2300
},
{
"epoch": 0.461,
"grad_norm": 43.2386589050293,
"learning_rate": 0.00013063599421253558,
"loss": 256.0279,
"step": 2305
},
{
"epoch": 0.462,
"grad_norm": 45.63770294189453,
"learning_rate": 0.00013030352696327742,
"loss": 260.6356,
"step": 2310
},
{
"epoch": 0.463,
"grad_norm": 39.927799224853516,
"learning_rate": 0.0001299706904751064,
"loss": 259.216,
"step": 2315
},
{
"epoch": 0.464,
"grad_norm": 51.26994323730469,
"learning_rate": 0.00012963748880353011,
"loss": 265.6953,
"step": 2320
},
{
"epoch": 0.465,
"grad_norm": 41.52295684814453,
"learning_rate": 0.00012930392600850573,
"loss": 262.478,
"step": 2325
},
{
"epoch": 0.466,
"grad_norm": 45.509586334228516,
"learning_rate": 0.00012897000615439075,
"loss": 266.892,
"step": 2330
},
{
"epoch": 0.467,
"grad_norm": 40.5629768371582,
"learning_rate": 0.00012863573330989313,
"loss": 257.8486,
"step": 2335
},
{
"epoch": 0.468,
"grad_norm": 66.30706024169922,
"learning_rate": 0.00012830111154802203,
"loss": 264.8887,
"step": 2340
},
{
"epoch": 0.469,
"grad_norm": 43.62724304199219,
"learning_rate": 0.000127966144946038,
"loss": 268.3162,
"step": 2345
},
{
"epoch": 0.47,
"grad_norm": 39.59247589111328,
"learning_rate": 0.00012763083758540337,
"loss": 269.5568,
"step": 2350
},
{
"epoch": 0.471,
"grad_norm": 38.854095458984375,
"learning_rate": 0.00012729519355173254,
"loss": 279.3487,
"step": 2355
},
{
"epoch": 0.472,
"grad_norm": 40.061424255371094,
"learning_rate": 0.00012695921693474212,
"loss": 255.4567,
"step": 2360
},
{
"epoch": 0.473,
"grad_norm": 42.86016845703125,
"learning_rate": 0.00012662291182820114,
"loss": 255.6157,
"step": 2365
},
{
"epoch": 0.474,
"grad_norm": 111.09700012207031,
"learning_rate": 0.0001262862823298812,
"loss": 260.3539,
"step": 2370
},
{
"epoch": 0.475,
"grad_norm": 42.297576904296875,
"learning_rate": 0.00012594933254150655,
"loss": 255.0851,
"step": 2375
},
{
"epoch": 0.476,
"grad_norm": 43.51994323730469,
"learning_rate": 0.00012561206656870396,
"loss": 268.4601,
"step": 2380
},
{
"epoch": 0.477,
"grad_norm": 43.15565490722656,
"learning_rate": 0.00012527448852095295,
"loss": 260.8217,
"step": 2385
},
{
"epoch": 0.478,
"grad_norm": 62.2764892578125,
"learning_rate": 0.0001249366025115354,
"loss": 256.4718,
"step": 2390
},
{
"epoch": 0.479,
"grad_norm": 51.036746978759766,
"learning_rate": 0.0001245984126574858,
"loss": 254.0895,
"step": 2395
},
{
"epoch": 0.48,
"grad_norm": 47.036163330078125,
"learning_rate": 0.00012425992307954075,
"loss": 255.5174,
"step": 2400
},
{
"epoch": 0.481,
"grad_norm": 42.51009750366211,
"learning_rate": 0.00012392113790208895,
"loss": 221.3495,
"step": 2405
},
{
"epoch": 0.482,
"grad_norm": 48.077754974365234,
"learning_rate": 0.00012358206125312083,
"loss": 255.8438,
"step": 2410
},
{
"epoch": 0.483,
"grad_norm": 53.20677947998047,
"learning_rate": 0.0001232426972641784,
"loss": 273.4254,
"step": 2415
},
{
"epoch": 0.484,
"grad_norm": 42.0869140625,
"learning_rate": 0.00012290305007030478,
"loss": 275.1218,
"step": 2420
},
{
"epoch": 0.485,
"grad_norm": 56.51434326171875,
"learning_rate": 0.00012256312380999376,
"loss": 259.3293,
"step": 2425
},
{
"epoch": 0.486,
"grad_norm": 47.111759185791016,
"learning_rate": 0.00012222292262513965,
"loss": 250.6094,
"step": 2430
},
{
"epoch": 0.487,
"grad_norm": 42.47024917602539,
"learning_rate": 0.00012188245066098647,
"loss": 258.4406,
"step": 2435
},
{
"epoch": 0.488,
"grad_norm": 46.04121780395508,
"learning_rate": 0.00012154171206607764,
"loss": 251.4095,
"step": 2440
},
{
"epoch": 0.489,
"grad_norm": 37.413917541503906,
"learning_rate": 0.00012120071099220549,
"loss": 263.7561,
"step": 2445
},
{
"epoch": 0.49,
"grad_norm": 38.14289093017578,
"learning_rate": 0.00012085945159436038,
"loss": 259.9656,
"step": 2450
},
{
"epoch": 0.491,
"grad_norm": 42.38154220581055,
"learning_rate": 0.00012051793803068046,
"loss": 257.4974,
"step": 2455
},
{
"epoch": 0.492,
"grad_norm": 37.19105911254883,
"learning_rate": 0.0001201761744624007,
"loss": 245.0491,
"step": 2460
},
{
"epoch": 0.493,
"grad_norm": 40.53895950317383,
"learning_rate": 0.00011983416505380234,
"loss": 265.8709,
"step": 2465
},
{
"epoch": 0.494,
"grad_norm": 41.050209045410156,
"learning_rate": 0.00011949191397216206,
"loss": 269.7101,
"step": 2470
},
{
"epoch": 0.495,
"grad_norm": 37.79787826538086,
"learning_rate": 0.00011914942538770131,
"loss": 267.1166,
"step": 2475
},
{
"epoch": 0.496,
"grad_norm": 50.62918472290039,
"learning_rate": 0.00011880670347353539,
"loss": 266.1175,
"step": 2480
},
{
"epoch": 0.497,
"grad_norm": 63.609920501708984,
"learning_rate": 0.0001184637524056227,
"loss": 268.239,
"step": 2485
},
{
"epoch": 0.498,
"grad_norm": 48.44621276855469,
"learning_rate": 0.00011812057636271374,
"loss": 250.2449,
"step": 2490
},
{
"epoch": 0.499,
"grad_norm": 45.59789276123047,
"learning_rate": 0.00011777717952630031,
"loss": 275.0825,
"step": 2495
},
{
"epoch": 0.5,
"grad_norm": 38.13023376464844,
"learning_rate": 0.00011743356608056449,
"loss": 260.358,
"step": 2500
},
{
"epoch": 0.501,
"grad_norm": 58.883758544921875,
"learning_rate": 0.00011708974021232769,
"loss": 272.292,
"step": 2505
},
{
"epoch": 0.502,
"grad_norm": 46.26652526855469,
"learning_rate": 0.00011674570611099955,
"loss": 254.0451,
"step": 2510
},
{
"epoch": 0.503,
"grad_norm": 38.81509780883789,
"learning_rate": 0.00011640146796852711,
"loss": 252.5047,
"step": 2515
},
{
"epoch": 0.504,
"grad_norm": 42.22090530395508,
"learning_rate": 0.00011605702997934345,
"loss": 254.5679,
"step": 2520
},
{
"epoch": 0.505,
"grad_norm": 42.911346435546875,
"learning_rate": 0.00011571239634031679,
"loss": 264.0327,
"step": 2525
},
{
"epoch": 0.506,
"grad_norm": 43.037296295166016,
"learning_rate": 0.00011536757125069923,
"loss": 273.553,
"step": 2530
},
{
"epoch": 0.507,
"grad_norm": 39.720943450927734,
"learning_rate": 0.00011502255891207572,
"loss": 266.839,
"step": 2535
},
{
"epoch": 0.508,
"grad_norm": 38.92488479614258,
"learning_rate": 0.00011467736352831266,
"loss": 260.9767,
"step": 2540
},
{
"epoch": 0.509,
"grad_norm": 38.86437225341797,
"learning_rate": 0.00011433198930550695,
"loss": 264.9249,
"step": 2545
},
{
"epoch": 0.51,
"grad_norm": 38.32862854003906,
"learning_rate": 0.00011398644045193444,
"loss": 269.3646,
"step": 2550
},
{
"epoch": 0.511,
"grad_norm": 39.75739669799805,
"learning_rate": 0.00011364072117799885,
"loss": 261.1027,
"step": 2555
},
{
"epoch": 0.512,
"grad_norm": 41.6780891418457,
"learning_rate": 0.00011329483569618045,
"loss": 264.7375,
"step": 2560
},
{
"epoch": 0.513,
"grad_norm": 39.12678527832031,
"learning_rate": 0.00011294878822098469,
"loss": 270.3624,
"step": 2565
},
{
"epoch": 0.514,
"grad_norm": 50.05087661743164,
"learning_rate": 0.00011260258296889086,
"loss": 252.5225,
"step": 2570
},
{
"epoch": 0.515,
"grad_norm": 136.82188415527344,
"learning_rate": 0.00011225622415830068,
"loss": 201.0676,
"step": 2575
},
{
"epoch": 0.516,
"grad_norm": 45.62225341796875,
"learning_rate": 0.00011190971600948699,
"loss": 245.0362,
"step": 2580
},
{
"epoch": 0.517,
"grad_norm": 43.27250289916992,
"learning_rate": 0.00011156306274454218,
"loss": 254.0381,
"step": 2585
},
{
"epoch": 0.518,
"grad_norm": 45.04914855957031,
"learning_rate": 0.0001112162685873269,
"loss": 256.6834,
"step": 2590
},
{
"epoch": 0.519,
"grad_norm": 47.14482116699219,
"learning_rate": 0.00011086933776341852,
"loss": 263.1893,
"step": 2595
},
{
"epoch": 0.52,
"grad_norm": 39.72810745239258,
"learning_rate": 0.00011052227450005967,
"loss": 248.6642,
"step": 2600
},
{
"epoch": 0.521,
"grad_norm": 40.98179626464844,
"learning_rate": 0.00011017508302610664,
"loss": 252.5318,
"step": 2605
},
{
"epoch": 0.522,
"grad_norm": 47.01239776611328,
"learning_rate": 0.00010982776757197799,
"loss": 281.0523,
"step": 2610
},
{
"epoch": 0.523,
"grad_norm": 55.72262954711914,
"learning_rate": 0.00010948033236960294,
"loss": 265.7365,
"step": 2615
},
{
"epoch": 0.524,
"grad_norm": 39.83689880371094,
"learning_rate": 0.00010913278165236978,
"loss": 269.3452,
"step": 2620
},
{
"epoch": 0.525,
"grad_norm": 50.57114791870117,
"learning_rate": 0.00010878511965507434,
"loss": 264.5784,
"step": 2625
},
{
"epoch": 0.526,
"grad_norm": 50.29024124145508,
"learning_rate": 0.00010843735061386828,
"loss": 246.3087,
"step": 2630
},
{
"epoch": 0.527,
"grad_norm": 43.95213317871094,
"learning_rate": 0.00010808947876620767,
"loss": 251.7893,
"step": 2635
},
{
"epoch": 0.528,
"grad_norm": 39.058170318603516,
"learning_rate": 0.00010774150835080119,
"loss": 241.5822,
"step": 2640
},
{
"epoch": 0.529,
"grad_norm": 47.016822814941406,
"learning_rate": 0.00010739344360755852,
"loss": 275.6095,
"step": 2645
},
{
"epoch": 0.53,
"grad_norm": 39.554283142089844,
"learning_rate": 0.0001070452887775387,
"loss": 259.8371,
"step": 2650
},
{
"epoch": 0.531,
"grad_norm": 39.36391830444336,
"learning_rate": 0.00010669704810289851,
"loss": 257.5079,
"step": 2655
},
{
"epoch": 0.532,
"grad_norm": 52.974700927734375,
"learning_rate": 0.00010634872582684061,
"loss": 264.018,
"step": 2660
},
{
"epoch": 0.533,
"grad_norm": 44.6728515625,
"learning_rate": 0.00010600032619356209,
"loss": 263.4835,
"step": 2665
},
{
"epoch": 0.534,
"grad_norm": 39.80046844482422,
"learning_rate": 0.00010565185344820247,
"loss": 266.1423,
"step": 2670
},
{
"epoch": 0.535,
"grad_norm": 36.64481735229492,
"learning_rate": 0.00010530331183679218,
"loss": 261.7118,
"step": 2675
},
{
"epoch": 0.536,
"grad_norm": 39.90692901611328,
"learning_rate": 0.00010495470560620083,
"loss": 264.6565,
"step": 2680
},
{
"epoch": 0.537,
"grad_norm": 37.49492263793945,
"learning_rate": 0.00010460603900408523,
"loss": 262.9902,
"step": 2685
},
{
"epoch": 0.538,
"grad_norm": 40.356319427490234,
"learning_rate": 0.00010425731627883797,
"loss": 259.0453,
"step": 2690
},
{
"epoch": 0.539,
"grad_norm": 38.85243606567383,
"learning_rate": 0.00010390854167953537,
"loss": 260.2315,
"step": 2695
},
{
"epoch": 0.54,
"grad_norm": 38.854793548583984,
"learning_rate": 0.00010355971945588585,
"loss": 264.7388,
"step": 2700
},
{
"epoch": 0.541,
"grad_norm": 40.077762603759766,
"learning_rate": 0.00010321085385817817,
"loss": 248.693,
"step": 2705
},
{
"epoch": 0.542,
"grad_norm": 42.310943603515625,
"learning_rate": 0.00010286194913722948,
"loss": 280.9151,
"step": 2710
},
{
"epoch": 0.543,
"grad_norm": 38.88721466064453,
"learning_rate": 0.00010251300954433376,
"loss": 247.4674,
"step": 2715
},
{
"epoch": 0.544,
"grad_norm": 39.982818603515625,
"learning_rate": 0.00010216403933120979,
"loss": 258.8009,
"step": 2720
},
{
"epoch": 0.545,
"grad_norm": 39.109867095947266,
"learning_rate": 0.00010181504274994948,
"loss": 269.9524,
"step": 2725
},
{
"epoch": 0.546,
"grad_norm": 35.48329544067383,
"learning_rate": 0.00010146602405296607,
"loss": 260.8923,
"step": 2730
},
{
"epoch": 0.547,
"grad_norm": 50.56344985961914,
"learning_rate": 0.00010111698749294223,
"loss": 264.1321,
"step": 2735
},
{
"epoch": 0.548,
"grad_norm": 41.52736282348633,
"learning_rate": 0.00010076793732277829,
"loss": 262.4177,
"step": 2740
},
{
"epoch": 0.549,
"grad_norm": 38.254642486572266,
"learning_rate": 0.0001004188777955404,
"loss": 257.1609,
"step": 2745
},
{
"epoch": 0.55,
"grad_norm": 40.259178161621094,
"learning_rate": 0.00010006981316440875,
"loss": 263.1502,
"step": 2750
},
{
"epoch": 0.551,
"grad_norm": 37.24797058105469,
"learning_rate": 9.972074768262576e-05,
"loss": 267.1995,
"step": 2755
},
{
"epoch": 0.552,
"grad_norm": 37.238441467285156,
"learning_rate": 9.937168560344412e-05,
"loss": 259.7157,
"step": 2760
},
{
"epoch": 0.553,
"grad_norm": 50.60415267944336,
"learning_rate": 9.902263118007513e-05,
"loss": 262.8598,
"step": 2765
},
{
"epoch": 0.554,
"grad_norm": 38.87711715698242,
"learning_rate": 9.867358866563673e-05,
"loss": 251.1438,
"step": 2770
},
{
"epoch": 0.555,
"grad_norm": 43.6115608215332,
"learning_rate": 9.832456231310189e-05,
"loss": 272.077,
"step": 2775
},
{
"epoch": 0.556,
"grad_norm": 43.99259567260742,
"learning_rate": 9.797555637524649e-05,
"loss": 272.5109,
"step": 2780
},
{
"epoch": 0.557,
"grad_norm": 40.357757568359375,
"learning_rate": 9.762657510459783e-05,
"loss": 260.1741,
"step": 2785
},
{
"epoch": 0.558,
"grad_norm": 42.52724075317383,
"learning_rate": 9.727762275338246e-05,
"loss": 264.1492,
"step": 2790
},
{
"epoch": 0.559,
"grad_norm": 151.0966033935547,
"learning_rate": 9.692870357347473e-05,
"loss": 261.9452,
"step": 2795
},
{
"epoch": 0.56,
"grad_norm": 38.09223556518555,
"learning_rate": 9.657982181634475e-05,
"loss": 263.8773,
"step": 2800
},
{
"epoch": 0.561,
"grad_norm": 37.496337890625,
"learning_rate": 9.623098173300654e-05,
"loss": 267.7523,
"step": 2805
},
{
"epoch": 0.562,
"grad_norm": 37.47482681274414,
"learning_rate": 9.588218757396655e-05,
"loss": 261.8609,
"step": 2810
},
{
"epoch": 0.563,
"grad_norm": 38.23861312866211,
"learning_rate": 9.55334435891714e-05,
"loss": 273.2842,
"step": 2815
},
{
"epoch": 0.564,
"grad_norm": 54.279727935791016,
"learning_rate": 9.518475402795661e-05,
"loss": 248.6552,
"step": 2820
},
{
"epoch": 0.565,
"grad_norm": 43.65389633178711,
"learning_rate": 9.483612313899435e-05,
"loss": 245.3415,
"step": 2825
},
{
"epoch": 0.566,
"grad_norm": 38.27533721923828,
"learning_rate": 9.448755517024206e-05,
"loss": 250.5665,
"step": 2830
},
{
"epoch": 0.567,
"grad_norm": 39.547828674316406,
"learning_rate": 9.413905436889035e-05,
"loss": 267.9911,
"step": 2835
},
{
"epoch": 0.568,
"grad_norm": 49.07759094238281,
"learning_rate": 9.37906249813116e-05,
"loss": 252.3524,
"step": 2840
},
{
"epoch": 0.569,
"grad_norm": 64.52811431884766,
"learning_rate": 9.344227125300788e-05,
"loss": 257.7041,
"step": 2845
},
{
"epoch": 0.57,
"grad_norm": 38.99817657470703,
"learning_rate": 9.309399742855942e-05,
"loss": 268.1341,
"step": 2850
},
{
"epoch": 0.571,
"grad_norm": 47.37516403198242,
"learning_rate": 9.274580775157294e-05,
"loss": 272.1344,
"step": 2855
},
{
"epoch": 0.572,
"grad_norm": 41.15652847290039,
"learning_rate": 9.239770646462968e-05,
"loss": 263.8213,
"step": 2860
},
{
"epoch": 0.573,
"grad_norm": 92.29903411865234,
"learning_rate": 9.204969780923403e-05,
"loss": 250.2521,
"step": 2865
},
{
"epoch": 0.574,
"grad_norm": 39.34086227416992,
"learning_rate": 9.17017860257616e-05,
"loss": 253.8077,
"step": 2870
},
{
"epoch": 0.575,
"grad_norm": 43.6414680480957,
"learning_rate": 9.135397535340773e-05,
"loss": 264.8482,
"step": 2875
},
{
"epoch": 0.576,
"grad_norm": 46.1148681640625,
"learning_rate": 9.100627003013562e-05,
"loss": 257.3056,
"step": 2880
},
{
"epoch": 0.577,
"grad_norm": 42.279842376708984,
"learning_rate": 9.065867429262496e-05,
"loss": 261.3003,
"step": 2885
},
{
"epoch": 0.578,
"grad_norm": 42.94358825683594,
"learning_rate": 9.03111923762201e-05,
"loss": 249.0209,
"step": 2890
},
{
"epoch": 0.579,
"grad_norm": 36.43231201171875,
"learning_rate": 8.99638285148785e-05,
"loss": 269.5814,
"step": 2895
},
{
"epoch": 0.58,
"grad_norm": 43.69097900390625,
"learning_rate": 8.961658694111929e-05,
"loss": 264.3022,
"step": 2900
},
{
"epoch": 0.581,
"grad_norm": 42.756011962890625,
"learning_rate": 8.926947188597134e-05,
"loss": 265.849,
"step": 2905
},
{
"epoch": 0.582,
"grad_norm": 36.23428726196289,
"learning_rate": 8.892248757892214e-05,
"loss": 257.55,
"step": 2910
},
{
"epoch": 0.583,
"grad_norm": 39.63174057006836,
"learning_rate": 8.857563824786596e-05,
"loss": 251.9959,
"step": 2915
},
{
"epoch": 0.584,
"grad_norm": 39.31542205810547,
"learning_rate": 8.822892811905237e-05,
"loss": 252.4967,
"step": 2920
},
{
"epoch": 0.585,
"grad_norm": 37.33333206176758,
"learning_rate": 8.788236141703498e-05,
"loss": 256.4792,
"step": 2925
},
{
"epoch": 0.586,
"grad_norm": 103.62459564208984,
"learning_rate": 8.753594236461957e-05,
"loss": 254.6665,
"step": 2930
},
{
"epoch": 0.587,
"grad_norm": 35.646766662597656,
"learning_rate": 8.718967518281307e-05,
"loss": 268.4577,
"step": 2935
},
{
"epoch": 0.588,
"grad_norm": 37.8861083984375,
"learning_rate": 8.684356409077176e-05,
"loss": 252.7815,
"step": 2940
},
{
"epoch": 0.589,
"grad_norm": 37.604679107666016,
"learning_rate": 8.64976133057501e-05,
"loss": 255.5193,
"step": 2945
},
{
"epoch": 0.59,
"grad_norm": 44.07435989379883,
"learning_rate": 8.615182704304918e-05,
"loss": 258.451,
"step": 2950
},
{
"epoch": 0.591,
"grad_norm": 54.42814254760742,
"learning_rate": 8.580620951596557e-05,
"loss": 268.9403,
"step": 2955
},
{
"epoch": 0.592,
"grad_norm": 38.368743896484375,
"learning_rate": 8.546076493573972e-05,
"loss": 267.766,
"step": 2960
},
{
"epoch": 0.593,
"grad_norm": 37.77800369262695,
"learning_rate": 8.511549751150479e-05,
"loss": 256.9156,
"step": 2965
},
{
"epoch": 0.594,
"grad_norm": 82.45809936523438,
"learning_rate": 8.477041145023546e-05,
"loss": 246.7067,
"step": 2970
},
{
"epoch": 0.595,
"grad_norm": 41.70328140258789,
"learning_rate": 8.442551095669639e-05,
"loss": 253.5747,
"step": 2975
},
{
"epoch": 0.596,
"grad_norm": 42.29827880859375,
"learning_rate": 8.408080023339133e-05,
"loss": 263.6176,
"step": 2980
},
{
"epoch": 0.597,
"grad_norm": 60.464542388916016,
"learning_rate": 8.373628348051165e-05,
"loss": 253.2792,
"step": 2985
},
{
"epoch": 0.598,
"grad_norm": 37.77191162109375,
"learning_rate": 8.339196489588523e-05,
"loss": 261.4149,
"step": 2990
},
{
"epoch": 0.599,
"grad_norm": 39.17750930786133,
"learning_rate": 8.30478486749254e-05,
"loss": 262.3409,
"step": 2995
},
{
"epoch": 0.6,
"grad_norm": 86.0202407836914,
"learning_rate": 8.270393901057964e-05,
"loss": 266.7969,
"step": 3000
},
{
"epoch": 0.601,
"grad_norm": 46.726505279541016,
"learning_rate": 8.236024009327879e-05,
"loss": 267.0202,
"step": 3005
},
{
"epoch": 0.602,
"grad_norm": 45.443172454833984,
"learning_rate": 8.201675611088558e-05,
"loss": 265.7428,
"step": 3010
},
{
"epoch": 0.603,
"grad_norm": 40.05506134033203,
"learning_rate": 8.167349124864405e-05,
"loss": 265.6488,
"step": 3015
},
{
"epoch": 0.604,
"grad_norm": 39.430049896240234,
"learning_rate": 8.133044968912811e-05,
"loss": 255.1894,
"step": 3020
},
{
"epoch": 0.605,
"grad_norm": 50.617435455322266,
"learning_rate": 8.0987635612191e-05,
"loss": 270.7121,
"step": 3025
},
{
"epoch": 0.606,
"grad_norm": 39.71659469604492,
"learning_rate": 8.064505319491398e-05,
"loss": 255.0716,
"step": 3030
},
{
"epoch": 0.607,
"grad_norm": 63.42427062988281,
"learning_rate": 8.030270661155574e-05,
"loss": 245.712,
"step": 3035
},
{
"epoch": 0.608,
"grad_norm": 39.74090576171875,
"learning_rate": 7.996060003350139e-05,
"loss": 270.8254,
"step": 3040
},
{
"epoch": 0.609,
"grad_norm": 40.09970474243164,
"learning_rate": 7.961873762921153e-05,
"loss": 254.1872,
"step": 3045
},
{
"epoch": 0.61,
"grad_norm": 40.315521240234375,
"learning_rate": 7.927712356417176e-05,
"loss": 260.551,
"step": 3050
},
{
"epoch": 0.611,
"grad_norm": 38.12311935424805,
"learning_rate": 7.893576200084159e-05,
"loss": 259.6406,
"step": 3055
},
{
"epoch": 0.612,
"grad_norm": 40.54149627685547,
"learning_rate": 7.8594657098604e-05,
"loss": 253.1035,
"step": 3060
},
{
"epoch": 0.613,
"grad_norm": 39.185306549072266,
"learning_rate": 7.825381301371452e-05,
"loss": 251.5984,
"step": 3065
},
{
"epoch": 0.614,
"grad_norm": 43.19792175292969,
"learning_rate": 7.791323389925084e-05,
"loss": 267.4118,
"step": 3070
},
{
"epoch": 0.615,
"grad_norm": 40.695167541503906,
"learning_rate": 7.75729239050619e-05,
"loss": 263.2466,
"step": 3075
},
{
"epoch": 0.616,
"grad_norm": 45.58380889892578,
"learning_rate": 7.723288717771761e-05,
"loss": 258.8287,
"step": 3080
},
{
"epoch": 0.617,
"grad_norm": 35.91655731201172,
"learning_rate": 7.689312786045823e-05,
"loss": 271.715,
"step": 3085
},
{
"epoch": 0.618,
"grad_norm": 39.9389762878418,
"learning_rate": 7.655365009314374e-05,
"loss": 262.5394,
"step": 3090
},
{
"epoch": 0.619,
"grad_norm": 40.34840774536133,
"learning_rate": 7.621445801220371e-05,
"loss": 264.7501,
"step": 3095
},
{
"epoch": 0.62,
"grad_norm": 38.98249053955078,
"learning_rate": 7.587555575058649e-05,
"loss": 251.6992,
"step": 3100
},
{
"epoch": 0.621,
"grad_norm": 40.11667251586914,
"learning_rate": 7.553694743770928e-05,
"loss": 261.6717,
"step": 3105
},
{
"epoch": 0.622,
"grad_norm": 35.13900375366211,
"learning_rate": 7.519863719940748e-05,
"loss": 258.176,
"step": 3110
},
{
"epoch": 0.623,
"grad_norm": 38.65624237060547,
"learning_rate": 7.486062915788452e-05,
"loss": 257.4572,
"step": 3115
},
{
"epoch": 0.624,
"grad_norm": 38.785499572753906,
"learning_rate": 7.45229274316618e-05,
"loss": 253.6056,
"step": 3120
},
{
"epoch": 0.625,
"grad_norm": 38.27753448486328,
"learning_rate": 7.418553613552825e-05,
"loss": 263.7763,
"step": 3125
},
{
"epoch": 0.626,
"grad_norm": 61.69586944580078,
"learning_rate": 7.384845938049031e-05,
"loss": 237.407,
"step": 3130
},
{
"epoch": 0.627,
"grad_norm": 115.49690246582031,
"learning_rate": 7.351170127372191e-05,
"loss": 169.4212,
"step": 3135
},
{
"epoch": 0.628,
"grad_norm": 69.5982894897461,
"learning_rate": 7.317526591851433e-05,
"loss": 144.2144,
"step": 3140
},
{
"epoch": 0.629,
"grad_norm": 63.3367805480957,
"learning_rate": 7.283915741422612e-05,
"loss": 145.3793,
"step": 3145
},
{
"epoch": 0.63,
"grad_norm": 52.025482177734375,
"learning_rate": 7.250337985623342e-05,
"loss": 145.4898,
"step": 3150
},
{
"epoch": 0.631,
"grad_norm": 41.90822219848633,
"learning_rate": 7.216793733587976e-05,
"loss": 200.3819,
"step": 3155
},
{
"epoch": 0.632,
"grad_norm": 47.45818328857422,
"learning_rate": 7.183283394042634e-05,
"loss": 239.0713,
"step": 3160
},
{
"epoch": 0.633,
"grad_norm": 38.797706604003906,
"learning_rate": 7.149807375300239e-05,
"loss": 260.7063,
"step": 3165
},
{
"epoch": 0.634,
"grad_norm": 48.20371627807617,
"learning_rate": 7.11636608525551e-05,
"loss": 259.3726,
"step": 3170
},
{
"epoch": 0.635,
"grad_norm": 44.77751922607422,
"learning_rate": 7.082959931380011e-05,
"loss": 263.1155,
"step": 3175
},
{
"epoch": 0.636,
"grad_norm": 38.651512145996094,
"learning_rate": 7.049589320717186e-05,
"loss": 251.603,
"step": 3180
},
{
"epoch": 0.637,
"grad_norm": 51.91865158081055,
"learning_rate": 7.016254659877398e-05,
"loss": 257.4312,
"step": 3185
},
{
"epoch": 0.638,
"grad_norm": 49.567901611328125,
"learning_rate": 6.982956355032968e-05,
"loss": 253.6835,
"step": 3190
},
{
"epoch": 0.639,
"grad_norm": 41.1312141418457,
"learning_rate": 6.949694811913225e-05,
"loss": 252.9403,
"step": 3195
},
{
"epoch": 0.64,
"grad_norm": 37.49494552612305,
"learning_rate": 6.916470435799587e-05,
"loss": 245.2363,
"step": 3200
},
{
"epoch": 0.641,
"grad_norm": 52.18450927734375,
"learning_rate": 6.883283631520582e-05,
"loss": 243.7648,
"step": 3205
},
{
"epoch": 0.642,
"grad_norm": 38.116153717041016,
"learning_rate": 6.850134803446954e-05,
"loss": 253.5647,
"step": 3210
},
{
"epoch": 0.643,
"grad_norm": 40.90987777709961,
"learning_rate": 6.817024355486706e-05,
"loss": 245.1474,
"step": 3215
},
{
"epoch": 0.644,
"grad_norm": 53.08643341064453,
"learning_rate": 6.783952691080203e-05,
"loss": 255.6519,
"step": 3220
},
{
"epoch": 0.645,
"grad_norm": 37.598731994628906,
"learning_rate": 6.750920213195238e-05,
"loss": 264.1458,
"step": 3225
},
{
"epoch": 0.646,
"grad_norm": 39.50562286376953,
"learning_rate": 6.717927324322124e-05,
"loss": 245.7668,
"step": 3230
},
{
"epoch": 0.647,
"grad_norm": 43.41368103027344,
"learning_rate": 6.684974426468808e-05,
"loss": 273.5278,
"step": 3235
},
{
"epoch": 0.648,
"grad_norm": 45.862911224365234,
"learning_rate": 6.652061921155943e-05,
"loss": 261.577,
"step": 3240
},
{
"epoch": 0.649,
"grad_norm": 39.908111572265625,
"learning_rate": 6.61919020941203e-05,
"loss": 261.3824,
"step": 3245
},
{
"epoch": 0.65,
"grad_norm": 46.08481979370117,
"learning_rate": 6.58635969176849e-05,
"loss": 265.825,
"step": 3250
},
{
"epoch": 0.651,
"grad_norm": 41.879024505615234,
"learning_rate": 6.55357076825483e-05,
"loss": 255.1671,
"step": 3255
},
{
"epoch": 0.652,
"grad_norm": 44.15753173828125,
"learning_rate": 6.520823838393731e-05,
"loss": 252.7175,
"step": 3260
},
{
"epoch": 0.653,
"grad_norm": 36.83877182006836,
"learning_rate": 6.488119301196201e-05,
"loss": 259.6618,
"step": 3265
},
{
"epoch": 0.654,
"grad_norm": 49.46575927734375,
"learning_rate": 6.455457555156705e-05,
"loss": 244.7006,
"step": 3270
},
{
"epoch": 0.655,
"grad_norm": 48.52858352661133,
"learning_rate": 6.422838998248307e-05,
"loss": 248.5214,
"step": 3275
},
{
"epoch": 0.656,
"grad_norm": 39.7501220703125,
"learning_rate": 6.390264027917836e-05,
"loss": 255.4092,
"step": 3280
},
{
"epoch": 0.657,
"grad_norm": 104.92640686035156,
"learning_rate": 6.357733041081018e-05,
"loss": 266.4601,
"step": 3285
},
{
"epoch": 0.658,
"grad_norm": 43.50498962402344,
"learning_rate": 6.325246434117668e-05,
"loss": 250.4321,
"step": 3290
},
{
"epoch": 0.659,
"grad_norm": 44.72059631347656,
"learning_rate": 6.292804602866834e-05,
"loss": 269.8128,
"step": 3295
},
{
"epoch": 0.66,
"grad_norm": 42.671424865722656,
"learning_rate": 6.260407942621998e-05,
"loss": 260.8779,
"step": 3300
},
{
"epoch": 0.661,
"grad_norm": 52.8455696105957,
"learning_rate": 6.228056848126236e-05,
"loss": 260.1772,
"step": 3305
},
{
"epoch": 0.662,
"grad_norm": 37.74003219604492,
"learning_rate": 6.195751713567427e-05,
"loss": 251.0724,
"step": 3310
},
{
"epoch": 0.663,
"grad_norm": 41.658416748046875,
"learning_rate": 6.163492932573438e-05,
"loss": 254.6518,
"step": 3315
},
{
"epoch": 0.664,
"grad_norm": 41.264686584472656,
"learning_rate": 6.131280898207339e-05,
"loss": 260.6244,
"step": 3320
},
{
"epoch": 0.665,
"grad_norm": 44.55626678466797,
"learning_rate": 6.099116002962604e-05,
"loss": 265.9906,
"step": 3325
},
{
"epoch": 0.666,
"grad_norm": 42.659629821777344,
"learning_rate": 6.066998638758326e-05,
"loss": 255.7836,
"step": 3330
},
{
"epoch": 0.667,
"grad_norm": 39.97490692138672,
"learning_rate": 6.034929196934459e-05,
"loss": 252.2421,
"step": 3335
},
{
"epoch": 0.668,
"grad_norm": 39.8810920715332,
"learning_rate": 6.002908068247024e-05,
"loss": 262.0937,
"step": 3340
},
{
"epoch": 0.669,
"grad_norm": 41.694183349609375,
"learning_rate": 5.9709356428633746e-05,
"loss": 276.0104,
"step": 3345
},
{
"epoch": 0.67,
"grad_norm": 40.547630310058594,
"learning_rate": 5.9390123103574215e-05,
"loss": 266.6036,
"step": 3350
},
{
"epoch": 0.671,
"grad_norm": 44.3519401550293,
"learning_rate": 5.907138459704895e-05,
"loss": 260.0076,
"step": 3355
},
{
"epoch": 0.672,
"grad_norm": 38.990447998046875,
"learning_rate": 5.8753144792786096e-05,
"loss": 263.2847,
"step": 3360
},
{
"epoch": 0.673,
"grad_norm": 39.141151428222656,
"learning_rate": 5.8435407568437216e-05,
"loss": 253.4188,
"step": 3365
},
{
"epoch": 0.674,
"grad_norm": 62.34714889526367,
"learning_rate": 5.8118176795530176e-05,
"loss": 265.3321,
"step": 3370
},
{
"epoch": 0.675,
"grad_norm": 42.138999938964844,
"learning_rate": 5.780145633942173e-05,
"loss": 256.3065,
"step": 3375
},
{
"epoch": 0.676,
"grad_norm": 45.7026252746582,
"learning_rate": 5.748525005925074e-05,
"loss": 264.7489,
"step": 3380
},
{
"epoch": 0.677,
"grad_norm": 38.09944534301758,
"learning_rate": 5.716956180789098e-05,
"loss": 259.9945,
"step": 3385
},
{
"epoch": 0.678,
"grad_norm": 42.932376861572266,
"learning_rate": 5.6854395431904094e-05,
"loss": 245.6616,
"step": 3390
},
{
"epoch": 0.679,
"grad_norm": 39.37821960449219,
"learning_rate": 5.653975477149298e-05,
"loss": 257.1524,
"step": 3395
},
{
"epoch": 0.68,
"grad_norm": 42.93898391723633,
"learning_rate": 5.622564366045472e-05,
"loss": 254.5582,
"step": 3400
},
{
"epoch": 0.681,
"grad_norm": 42.979896545410156,
"learning_rate": 5.591206592613416e-05,
"loss": 253.5716,
"step": 3405
},
{
"epoch": 0.682,
"grad_norm": 40.99490737915039,
"learning_rate": 5.5599025389376935e-05,
"loss": 267.5101,
"step": 3410
},
{
"epoch": 0.683,
"grad_norm": 38.44643783569336,
"learning_rate": 5.5286525864483285e-05,
"loss": 257.9088,
"step": 3415
},
{
"epoch": 0.684,
"grad_norm": 43.95431900024414,
"learning_rate": 5.497457115916127e-05,
"loss": 257.9884,
"step": 3420
},
{
"epoch": 0.685,
"grad_norm": 38.33708953857422,
"learning_rate": 5.466316507448048e-05,
"loss": 255.4842,
"step": 3425
},
{
"epoch": 0.686,
"grad_norm": 38.846954345703125,
"learning_rate": 5.435231140482587e-05,
"loss": 252.5897,
"step": 3430
},
{
"epoch": 0.687,
"grad_norm": 42.01698303222656,
"learning_rate": 5.404201393785122e-05,
"loss": 246.008,
"step": 3435
},
{
"epoch": 0.688,
"grad_norm": 46.74819564819336,
"learning_rate": 5.373227645443332e-05,
"loss": 252.7403,
"step": 3440
},
{
"epoch": 0.689,
"grad_norm": 42.5672492980957,
"learning_rate": 5.3423102728625574e-05,
"loss": 250.9112,
"step": 3445
},
{
"epoch": 0.69,
"grad_norm": 47.676334381103516,
"learning_rate": 5.311449652761235e-05,
"loss": 265.1525,
"step": 3450
},
{
"epoch": 0.691,
"grad_norm": 42.83045196533203,
"learning_rate": 5.2806461611662735e-05,
"loss": 264.998,
"step": 3455
},
{
"epoch": 0.692,
"grad_norm": 39.11777877807617,
"learning_rate": 5.2499001734085044e-05,
"loss": 249.4321,
"step": 3460
},
{
"epoch": 0.693,
"grad_norm": 53.95589828491211,
"learning_rate": 5.2192120641180786e-05,
"loss": 240.7245,
"step": 3465
},
{
"epoch": 0.694,
"grad_norm": 43.628509521484375,
"learning_rate": 5.188582207219931e-05,
"loss": 249.6047,
"step": 3470
},
{
"epoch": 0.695,
"grad_norm": 36.41271209716797,
"learning_rate": 5.158010975929193e-05,
"loss": 260.3669,
"step": 3475
},
{
"epoch": 0.696,
"grad_norm": 43.80765151977539,
"learning_rate": 5.127498742746675e-05,
"loss": 272.8111,
"step": 3480
},
{
"epoch": 0.697,
"grad_norm": 71.2214584350586,
"learning_rate": 5.097045879454313e-05,
"loss": 255.1171,
"step": 3485
},
{
"epoch": 0.698,
"grad_norm": 40.30796813964844,
"learning_rate": 5.066652757110628e-05,
"loss": 259.5938,
"step": 3490
},
{
"epoch": 0.699,
"grad_norm": 40.011810302734375,
"learning_rate": 5.036319746046232e-05,
"loss": 264.1131,
"step": 3495
},
{
"epoch": 0.7,
"grad_norm": 45.83029556274414,
"learning_rate": 5.006047215859289e-05,
"loss": 261.6931,
"step": 3500
},
{
"epoch": 0.701,
"grad_norm": 68.0865249633789,
"learning_rate": 4.97583553541102e-05,
"loss": 259.0458,
"step": 3505
},
{
"epoch": 0.702,
"grad_norm": 37.83281707763672,
"learning_rate": 4.945685072821227e-05,
"loss": 235.9054,
"step": 3510
},
{
"epoch": 0.703,
"grad_norm": 45.26643753051758,
"learning_rate": 4.915596195463773e-05,
"loss": 243.8957,
"step": 3515
},
{
"epoch": 0.704,
"grad_norm": 72.13892364501953,
"learning_rate": 4.885569269962142e-05,
"loss": 249.6199,
"step": 3520
},
{
"epoch": 0.705,
"grad_norm": 53.56734085083008,
"learning_rate": 4.8556046621849346e-05,
"loss": 252.4823,
"step": 3525
},
{
"epoch": 0.706,
"grad_norm": 38.96076583862305,
"learning_rate": 4.825702737241452e-05,
"loss": 223.8709,
"step": 3530
},
{
"epoch": 0.707,
"grad_norm": 41.39957809448242,
"learning_rate": 4.7958638594772064e-05,
"loss": 253.6134,
"step": 3535
},
{
"epoch": 0.708,
"grad_norm": 63.26838302612305,
"learning_rate": 4.766088392469506e-05,
"loss": 192.6375,
"step": 3540
},
{
"epoch": 0.709,
"grad_norm": 56.56745147705078,
"learning_rate": 4.736376699023023e-05,
"loss": 201.842,
"step": 3545
},
{
"epoch": 0.71,
"grad_norm": 39.42858123779297,
"learning_rate": 4.706729141165361e-05,
"loss": 272.8633,
"step": 3550
},
{
"epoch": 0.711,
"grad_norm": 40.87665557861328,
"learning_rate": 4.6771460801426635e-05,
"loss": 257.4555,
"step": 3555
},
{
"epoch": 0.712,
"grad_norm": 38.2741584777832,
"learning_rate": 4.647627876415186e-05,
"loss": 270.4158,
"step": 3560
},
{
"epoch": 0.713,
"grad_norm": 58.3974723815918,
"learning_rate": 4.6181748896529273e-05,
"loss": 252.9886,
"step": 3565
},
{
"epoch": 0.714,
"grad_norm": 39.73430633544922,
"learning_rate": 4.588787478731242e-05,
"loss": 259.1499,
"step": 3570
},
{
"epoch": 0.715,
"grad_norm": 40.08724594116211,
"learning_rate": 4.559466001726451e-05,
"loss": 238.2984,
"step": 3575
},
{
"epoch": 0.716,
"grad_norm": 41.74061584472656,
"learning_rate": 4.530210815911504e-05,
"loss": 244.7457,
"step": 3580
},
{
"epoch": 0.717,
"grad_norm": 40.67575454711914,
"learning_rate": 4.501022277751602e-05,
"loss": 247.4829,
"step": 3585
},
{
"epoch": 0.718,
"grad_norm": 39.09025192260742,
"learning_rate": 4.471900742899876e-05,
"loss": 248.77,
"step": 3590
},
{
"epoch": 0.719,
"grad_norm": 41.46986770629883,
"learning_rate": 4.4428465661930343e-05,
"loss": 248.1959,
"step": 3595
},
{
"epoch": 0.72,
"grad_norm": 40.0534782409668,
"learning_rate": 4.413860101647055e-05,
"loss": 263.3911,
"step": 3600
},
{
"epoch": 0.721,
"grad_norm": 35.67971420288086,
"learning_rate": 4.3849417024528564e-05,
"loss": 306.6369,
"step": 3605
},
{
"epoch": 0.722,
"grad_norm": 49.83077621459961,
"learning_rate": 4.356091720972011e-05,
"loss": 263.5932,
"step": 3610
},
{
"epoch": 0.723,
"grad_norm": 39.12168502807617,
"learning_rate": 4.327310508732437e-05,
"loss": 254.8117,
"step": 3615
},
{
"epoch": 0.724,
"grad_norm": 52.56596374511719,
"learning_rate": 4.29859841642412e-05,
"loss": 271.0383,
"step": 3620
},
{
"epoch": 0.725,
"grad_norm": 39.27311325073242,
"learning_rate": 4.26995579389485e-05,
"loss": 247.5798,
"step": 3625
},
{
"epoch": 0.726,
"grad_norm": 43.7979736328125,
"learning_rate": 4.2413829901459344e-05,
"loss": 269.2753,
"step": 3630
},
{
"epoch": 0.727,
"grad_norm": 48.585113525390625,
"learning_rate": 4.212880353327979e-05,
"loss": 262.3543,
"step": 3635
},
{
"epoch": 0.728,
"grad_norm": 40.02567672729492,
"learning_rate": 4.184448230736613e-05,
"loss": 261.9731,
"step": 3640
},
{
"epoch": 0.729,
"grad_norm": 44.60491943359375,
"learning_rate": 4.15608696880828e-05,
"loss": 255.7599,
"step": 3645
},
{
"epoch": 0.73,
"grad_norm": 37.588050842285156,
"learning_rate": 4.1277969131160045e-05,
"loss": 249.9845,
"step": 3650
},
{
"epoch": 0.731,
"grad_norm": 56.560176849365234,
"learning_rate": 4.099578408365191e-05,
"loss": 252.1873,
"step": 3655
},
{
"epoch": 0.732,
"grad_norm": 40.376853942871094,
"learning_rate": 4.071431798389408e-05,
"loss": 253.2732,
"step": 3660
},
{
"epoch": 0.733,
"grad_norm": 40.370140075683594,
"learning_rate": 4.0433574261462206e-05,
"loss": 248.3035,
"step": 3665
},
{
"epoch": 0.734,
"grad_norm": 40.75528335571289,
"learning_rate": 4.015355633712996e-05,
"loss": 260.4456,
"step": 3670
},
{
"epoch": 0.735,
"grad_norm": 40.424930572509766,
"learning_rate": 3.987426762282733e-05,
"loss": 248.4597,
"step": 3675
},
{
"epoch": 0.736,
"grad_norm": 39.80683898925781,
"learning_rate": 3.9595711521599224e-05,
"loss": 267.0541,
"step": 3680
},
{
"epoch": 0.737,
"grad_norm": 41.07396697998047,
"learning_rate": 3.931789142756377e-05,
"loss": 258.9566,
"step": 3685
},
{
"epoch": 0.738,
"grad_norm": 53.07709884643555,
"learning_rate": 3.904081072587119e-05,
"loss": 265.6762,
"step": 3690
},
{
"epoch": 0.739,
"grad_norm": 40.51398468017578,
"learning_rate": 3.876447279266238e-05,
"loss": 257.3493,
"step": 3695
},
{
"epoch": 0.74,
"grad_norm": 38.19279098510742,
"learning_rate": 3.8488880995027786e-05,
"loss": 241.0309,
"step": 3700
},
{
"epoch": 0.741,
"grad_norm": 38.88092803955078,
"learning_rate": 3.821403869096658e-05,
"loss": 259.3728,
"step": 3705
},
{
"epoch": 0.742,
"grad_norm": 56.095191955566406,
"learning_rate": 3.793994922934544e-05,
"loss": 251.3006,
"step": 3710
},
{
"epoch": 0.743,
"grad_norm": 36.113441467285156,
"learning_rate": 3.766661594985801e-05,
"loss": 276.2006,
"step": 3715
},
{
"epoch": 0.744,
"grad_norm": 54.94417953491211,
"learning_rate": 3.739404218298398e-05,
"loss": 262.9567,
"step": 3720
},
{
"epoch": 0.745,
"grad_norm": 38.446964263916016,
"learning_rate": 3.712223124994875e-05,
"loss": 266.0303,
"step": 3725
},
{
"epoch": 0.746,
"grad_norm": 38.46642303466797,
"learning_rate": 3.685118646268272e-05,
"loss": 251.4426,
"step": 3730
},
{
"epoch": 0.747,
"grad_norm": 50.89178466796875,
"learning_rate": 3.6580911123781056e-05,
"loss": 258.4741,
"step": 3735
},
{
"epoch": 0.748,
"grad_norm": 47.903804779052734,
"learning_rate": 3.631140852646355e-05,
"loss": 268.3082,
"step": 3740
},
{
"epoch": 0.749,
"grad_norm": 36.41636276245117,
"learning_rate": 3.604268195453421e-05,
"loss": 273.8859,
"step": 3745
},
{
"epoch": 0.75,
"grad_norm": 43.20536422729492,
"learning_rate": 3.577473468234156e-05,
"loss": 262.7176,
"step": 3750
},
{
"epoch": 0.751,
"grad_norm": 49.615665435791016,
"learning_rate": 3.5507569974738574e-05,
"loss": 272.2414,
"step": 3755
},
{
"epoch": 0.752,
"grad_norm": 44.62723922729492,
"learning_rate": 3.524119108704286e-05,
"loss": 263.3687,
"step": 3760
},
{
"epoch": 0.753,
"grad_norm": 38.35116958618164,
"learning_rate": 3.497560126499709e-05,
"loss": 254.0617,
"step": 3765
},
{
"epoch": 0.754,
"grad_norm": 38.833290100097656,
"learning_rate": 3.4710803744729515e-05,
"loss": 261.7269,
"step": 3770
},
{
"epoch": 0.755,
"grad_norm": 46.218990325927734,
"learning_rate": 3.444680175271428e-05,
"loss": 264.6903,
"step": 3775
},
{
"epoch": 0.756,
"grad_norm": 37.679744720458984,
"learning_rate": 3.418359850573234e-05,
"loss": 261.3971,
"step": 3780
},
{
"epoch": 0.757,
"grad_norm": 36.93716812133789,
"learning_rate": 3.3921197210832235e-05,
"loss": 254.0937,
"step": 3785
},
{
"epoch": 0.758,
"grad_norm": 37.000648498535156,
"learning_rate": 3.3659601065290893e-05,
"loss": 275.8293,
"step": 3790
},
{
"epoch": 0.759,
"grad_norm": 41.63655471801758,
"learning_rate": 3.339881325657484e-05,
"loss": 266.6342,
"step": 3795
},
{
"epoch": 0.76,
"grad_norm": 45.30155944824219,
"learning_rate": 3.313883696230119e-05,
"loss": 253.4443,
"step": 3800
},
{
"epoch": 0.761,
"grad_norm": 38.944618225097656,
"learning_rate": 3.287967535019908e-05,
"loss": 245.3446,
"step": 3805
},
{
"epoch": 0.762,
"grad_norm": 40.4644660949707,
"learning_rate": 3.2621331578070934e-05,
"loss": 276.376,
"step": 3810
},
{
"epoch": 0.763,
"grad_norm": 42.205291748046875,
"learning_rate": 3.236380879375408e-05,
"loss": 266.2379,
"step": 3815
},
{
"epoch": 0.764,
"grad_norm": 39.400848388671875,
"learning_rate": 3.210711013508242e-05,
"loss": 265.028,
"step": 3820
},
{
"epoch": 0.765,
"grad_norm": 37.74625015258789,
"learning_rate": 3.1851238729848034e-05,
"loss": 255.8905,
"step": 3825
},
{
"epoch": 0.766,
"grad_norm": 49.66160202026367,
"learning_rate": 3.159619769576333e-05,
"loss": 234.8752,
"step": 3830
},
{
"epoch": 0.767,
"grad_norm": 41.96841049194336,
"learning_rate": 3.134199014042274e-05,
"loss": 247.8972,
"step": 3835
},
{
"epoch": 0.768,
"grad_norm": 41.085636138916016,
"learning_rate": 3.108861916126518e-05,
"loss": 253.7332,
"step": 3840
},
{
"epoch": 0.769,
"grad_norm": 40.414268493652344,
"learning_rate": 3.0836087845536e-05,
"loss": 258.3927,
"step": 3845
},
{
"epoch": 0.77,
"grad_norm": 44.42462158203125,
"learning_rate": 3.058439927024962e-05,
"loss": 240.4824,
"step": 3850
},
{
"epoch": 0.771,
"grad_norm": 36.66261672973633,
"learning_rate": 3.0333556502151926e-05,
"loss": 260.7343,
"step": 3855
},
{
"epoch": 0.772,
"grad_norm": 44.001564025878906,
"learning_rate": 3.0083562597682847e-05,
"loss": 272.862,
"step": 3860
},
{
"epoch": 0.773,
"grad_norm": 42.986358642578125,
"learning_rate": 2.9834420602939263e-05,
"loss": 259.0933,
"step": 3865
},
{
"epoch": 0.774,
"grad_norm": 47.331729888916016,
"learning_rate": 2.9586133553637683e-05,
"loss": 256.9045,
"step": 3870
},
{
"epoch": 0.775,
"grad_norm": 41.626216888427734,
"learning_rate": 2.933870447507753e-05,
"loss": 256.2642,
"step": 3875
},
{
"epoch": 0.776,
"grad_norm": 38.152557373046875,
"learning_rate": 2.9092136382103973e-05,
"loss": 258.9032,
"step": 3880
},
{
"epoch": 0.777,
"grad_norm": 40.456329345703125,
"learning_rate": 2.8846432279071467e-05,
"loss": 247.0601,
"step": 3885
},
{
"epoch": 0.778,
"grad_norm": 40.76598358154297,
"learning_rate": 2.860159515980695e-05,
"loss": 264.6058,
"step": 3890
},
{
"epoch": 0.779,
"grad_norm": 44.7227668762207,
"learning_rate": 2.835762800757341e-05,
"loss": 251.1074,
"step": 3895
},
{
"epoch": 0.78,
"grad_norm": 49.07013702392578,
"learning_rate": 2.8114533795033683e-05,
"loss": 259.1777,
"step": 3900
},
{
"epoch": 0.781,
"grad_norm": 98.51033020019531,
"learning_rate": 2.7872315484213952e-05,
"loss": 252.7781,
"step": 3905
},
{
"epoch": 0.782,
"grad_norm": 36.13119125366211,
"learning_rate": 2.7630976026467968e-05,
"loss": 253.1699,
"step": 3910
},
{
"epoch": 0.783,
"grad_norm": 53.23884201049805,
"learning_rate": 2.7390518362440808e-05,
"loss": 262.3156,
"step": 3915
},
{
"epoch": 0.784,
"grad_norm": 37.16896057128906,
"learning_rate": 2.715094542203327e-05,
"loss": 230.9953,
"step": 3920
},
{
"epoch": 0.785,
"grad_norm": 39.90071105957031,
"learning_rate": 2.6912260124366006e-05,
"loss": 264.6513,
"step": 3925
},
{
"epoch": 0.786,
"grad_norm": 37.425174713134766,
"learning_rate": 2.6674465377744017e-05,
"loss": 257.6212,
"step": 3930
},
{
"epoch": 0.787,
"grad_norm": 36.34478759765625,
"learning_rate": 2.6437564079621267e-05,
"loss": 266.2025,
"step": 3935
},
{
"epoch": 0.788,
"grad_norm": 40.20833969116211,
"learning_rate": 2.6201559116565345e-05,
"loss": 240.7799,
"step": 3940
},
{
"epoch": 0.789,
"grad_norm": 36.623870849609375,
"learning_rate": 2.5966453364222186e-05,
"loss": 261.1909,
"step": 3945
},
{
"epoch": 0.79,
"grad_norm": 39.4951171875,
"learning_rate": 2.573224968728123e-05,
"loss": 265.2186,
"step": 3950
},
{
"epoch": 0.791,
"grad_norm": 39.477752685546875,
"learning_rate": 2.549895093944039e-05,
"loss": 243.0684,
"step": 3955
},
{
"epoch": 0.792,
"grad_norm": 37.255218505859375,
"learning_rate": 2.5266559963371216e-05,
"loss": 265.4269,
"step": 3960
},
{
"epoch": 0.793,
"grad_norm": 40.87166976928711,
"learning_rate": 2.5035079590684497e-05,
"loss": 260.6802,
"step": 3965
},
{
"epoch": 0.794,
"grad_norm": 45.31010055541992,
"learning_rate": 2.480451264189546e-05,
"loss": 258.0027,
"step": 3970
},
{
"epoch": 0.795,
"grad_norm": 39.18110275268555,
"learning_rate": 2.4574861926389615e-05,
"loss": 264.5426,
"step": 3975
},
{
"epoch": 0.796,
"grad_norm": 41.232994079589844,
"learning_rate": 2.43461302423885e-05,
"loss": 263.8937,
"step": 3980
},
{
"epoch": 0.797,
"grad_norm": 45.59365463256836,
"learning_rate": 2.411832037691545e-05,
"loss": 242.2915,
"step": 3985
},
{
"epoch": 0.798,
"grad_norm": 37.41765213012695,
"learning_rate": 2.389143510576184e-05,
"loss": 251.875,
"step": 3990
},
{
"epoch": 0.799,
"grad_norm": 49.01387023925781,
"learning_rate": 2.3665477193453034e-05,
"loss": 254.8378,
"step": 3995
},
{
"epoch": 0.8,
"grad_norm": 39.30522918701172,
"learning_rate": 2.3440449393214948e-05,
"loss": 256.0667,
"step": 4000
},
{
"epoch": 0.801,
"grad_norm": 36.908485412597656,
"learning_rate": 2.321635444694028e-05,
"loss": 249.5851,
"step": 4005
},
{
"epoch": 0.802,
"grad_norm": 113.0779800415039,
"learning_rate": 2.2993195085155205e-05,
"loss": 270.3869,
"step": 4010
},
{
"epoch": 0.803,
"grad_norm": 42.2454948425293,
"learning_rate": 2.277097402698619e-05,
"loss": 255.6966,
"step": 4015
},
{
"epoch": 0.804,
"grad_norm": 42.46046829223633,
"learning_rate": 2.254969398012663e-05,
"loss": 257.4516,
"step": 4020
},
{
"epoch": 0.805,
"grad_norm": 46.84130096435547,
"learning_rate": 2.2329357640804117e-05,
"loss": 263.0133,
"step": 4025
},
{
"epoch": 0.806,
"grad_norm": 39.72685241699219,
"learning_rate": 2.210996769374737e-05,
"loss": 257.4237,
"step": 4030
},
{
"epoch": 0.807,
"grad_norm": 38.11692428588867,
"learning_rate": 2.1891526812153672e-05,
"loss": 254.8873,
"step": 4035
},
{
"epoch": 0.808,
"grad_norm": 38.06855392456055,
"learning_rate": 2.1674037657656266e-05,
"loss": 260.3844,
"step": 4040
},
{
"epoch": 0.809,
"grad_norm": 50.86600112915039,
"learning_rate": 2.1457502880291812e-05,
"loss": 254.4542,
"step": 4045
},
{
"epoch": 0.81,
"grad_norm": 42.00714111328125,
"learning_rate": 2.1241925118468287e-05,
"loss": 251.0419,
"step": 4050
},
{
"epoch": 0.811,
"grad_norm": 42.913978576660156,
"learning_rate": 2.1027306998932627e-05,
"loss": 266.9853,
"step": 4055
},
{
"epoch": 0.812,
"grad_norm": 35.5350341796875,
"learning_rate": 2.0813651136738954e-05,
"loss": 269.8301,
"step": 4060
},
{
"epoch": 0.813,
"grad_norm": 39.70906066894531,
"learning_rate": 2.0600960135216462e-05,
"loss": 247.8496,
"step": 4065
},
{
"epoch": 0.814,
"grad_norm": 37.79518127441406,
"learning_rate": 2.0389236585937945e-05,
"loss": 243.1816,
"step": 4070
},
{
"epoch": 0.815,
"grad_norm": 38.614803314208984,
"learning_rate": 2.017848306868797e-05,
"loss": 269.2241,
"step": 4075
},
{
"epoch": 0.816,
"grad_norm": 37.76798629760742,
"learning_rate": 1.9968702151431696e-05,
"loss": 263.6142,
"step": 4080
},
{
"epoch": 0.817,
"grad_norm": 45.523902893066406,
"learning_rate": 1.9759896390283362e-05,
"loss": 259.3302,
"step": 4085
},
{
"epoch": 0.818,
"grad_norm": 42.904083251953125,
"learning_rate": 1.955206832947526e-05,
"loss": 255.104,
"step": 4090
},
{
"epoch": 0.819,
"grad_norm": 42.066280364990234,
"learning_rate": 1.9345220501326777e-05,
"loss": 259.8377,
"step": 4095
},
{
"epoch": 0.82,
"grad_norm": 40.68569564819336,
"learning_rate": 1.9139355426213347e-05,
"loss": 255.0549,
"step": 4100
},
{
"epoch": 0.821,
"grad_norm": 38.677242279052734,
"learning_rate": 1.8934475612536017e-05,
"loss": 258.2865,
"step": 4105
},
{
"epoch": 0.822,
"grad_norm": 42.8074836730957,
"learning_rate": 1.8730583556690605e-05,
"loss": 234.6048,
"step": 4110
},
{
"epoch": 0.823,
"grad_norm": 40.076351165771484,
"learning_rate": 1.852768174303752e-05,
"loss": 257.7094,
"step": 4115
},
{
"epoch": 0.824,
"grad_norm": 57.93195343017578,
"learning_rate": 1.8325772643871265e-05,
"loss": 250.8004,
"step": 4120
},
{
"epoch": 0.825,
"grad_norm": 35.33334732055664,
"learning_rate": 1.812485871939056e-05,
"loss": 269.5202,
"step": 4125
},
{
"epoch": 0.826,
"grad_norm": 40.445404052734375,
"learning_rate": 1.792494241766811e-05,
"loss": 263.203,
"step": 4130
},
{
"epoch": 0.827,
"grad_norm": 44.017906188964844,
"learning_rate": 1.7726026174621003e-05,
"loss": 261.8917,
"step": 4135
},
{
"epoch": 0.828,
"grad_norm": 43.33936309814453,
"learning_rate": 1.752811241398089e-05,
"loss": 243.6612,
"step": 4140
},
{
"epoch": 0.829,
"grad_norm": 42.7217903137207,
"learning_rate": 1.7331203547264453e-05,
"loss": 252.7012,
"step": 4145
},
{
"epoch": 0.83,
"grad_norm": 44.460235595703125,
"learning_rate": 1.7135301973744124e-05,
"loss": 249.4634,
"step": 4150
},
{
"epoch": 0.831,
"grad_norm": 46.022769927978516,
"learning_rate": 1.6940410080418723e-05,
"loss": 261.0617,
"step": 4155
},
{
"epoch": 0.832,
"grad_norm": 42.020565032958984,
"learning_rate": 1.6746530241984504e-05,
"loss": 246.9665,
"step": 4160
},
{
"epoch": 0.833,
"grad_norm": 39.0727424621582,
"learning_rate": 1.6553664820806102e-05,
"loss": 250.1572,
"step": 4165
},
{
"epoch": 0.834,
"grad_norm": 72.50296020507812,
"learning_rate": 1.6361816166887768e-05,
"loss": 264.5518,
"step": 4170
},
{
"epoch": 0.835,
"grad_norm": 50.637123107910156,
"learning_rate": 1.6170986617844863e-05,
"loss": 246.5019,
"step": 4175
},
{
"epoch": 0.836,
"grad_norm": 36.076927185058594,
"learning_rate": 1.598117849887518e-05,
"loss": 268.1612,
"step": 4180
},
{
"epoch": 0.837,
"grad_norm": 53.105464935302734,
"learning_rate": 1.579239412273078e-05,
"loss": 261.0002,
"step": 4185
},
{
"epoch": 0.838,
"grad_norm": 43.40309524536133,
"learning_rate": 1.560463578968967e-05,
"loss": 260.1355,
"step": 4190
},
{
"epoch": 0.839,
"grad_norm": 39.313743591308594,
"learning_rate": 1.541790578752794e-05,
"loss": 263.3568,
"step": 4195
},
{
"epoch": 0.84,
"grad_norm": 51.68941879272461,
"learning_rate": 1.5232206391491699e-05,
"loss": 260.2609,
"step": 4200
},
{
"epoch": 0.841,
"grad_norm": 41.127079010009766,
"learning_rate": 1.5047539864269478e-05,
"loss": 248.4744,
"step": 4205
},
{
"epoch": 0.842,
"grad_norm": 46.07831573486328,
"learning_rate": 1.486390845596466e-05,
"loss": 254.4013,
"step": 4210
},
{
"epoch": 0.843,
"grad_norm": 36.880897521972656,
"learning_rate": 1.468131440406798e-05,
"loss": 250.0436,
"step": 4215
},
{
"epoch": 0.844,
"grad_norm": 38.40830612182617,
"learning_rate": 1.4499759933430346e-05,
"loss": 261.3019,
"step": 4220
},
{
"epoch": 0.845,
"grad_norm": 38.050235748291016,
"learning_rate": 1.4319247256235714e-05,
"loss": 251.1153,
"step": 4225
},
{
"epoch": 0.846,
"grad_norm": 43.71001434326172,
"learning_rate": 1.4139778571974049e-05,
"loss": 246.3181,
"step": 4230
},
{
"epoch": 0.847,
"grad_norm": 43.93571472167969,
"learning_rate": 1.3961356067414666e-05,
"loss": 249.1007,
"step": 4235
},
{
"epoch": 0.848,
"grad_norm": 38.746315002441406,
"learning_rate": 1.3783981916579446e-05,
"loss": 258.3322,
"step": 4240
},
{
"epoch": 0.849,
"grad_norm": 38.748046875,
"learning_rate": 1.3607658280716473e-05,
"loss": 256.333,
"step": 4245
},
{
"epoch": 0.85,
"grad_norm": 36.88574981689453,
"learning_rate": 1.3432387308273575e-05,
"loss": 260.3777,
"step": 4250
},
{
"epoch": 0.851,
"grad_norm": 40.78181457519531,
"learning_rate": 1.3258171134872265e-05,
"loss": 253.9064,
"step": 4255
},
{
"epoch": 0.852,
"grad_norm": 36.34745407104492,
"learning_rate": 1.3085011883281606e-05,
"loss": 252.4806,
"step": 4260
},
{
"epoch": 0.853,
"grad_norm": 36.840293884277344,
"learning_rate": 1.2912911663392469e-05,
"loss": 258.0704,
"step": 4265
},
{
"epoch": 0.854,
"grad_norm": 36.13236999511719,
"learning_rate": 1.2741872572191682e-05,
"loss": 221.0204,
"step": 4270
},
{
"epoch": 0.855,
"grad_norm": 37.67177963256836,
"learning_rate": 1.257189669373664e-05,
"loss": 259.7073,
"step": 4275
},
{
"epoch": 0.856,
"grad_norm": 47.06346130371094,
"learning_rate": 1.2402986099129765e-05,
"loss": 268.6031,
"step": 4280
},
{
"epoch": 0.857,
"grad_norm": 38.97346115112305,
"learning_rate": 1.2235142846493308e-05,
"loss": 252.645,
"step": 4285
},
{
"epoch": 0.858,
"grad_norm": 39.149070739746094,
"learning_rate": 1.206836898094439e-05,
"loss": 264.3256,
"step": 4290
},
{
"epoch": 0.859,
"grad_norm": 40.954917907714844,
"learning_rate": 1.1902666534569883e-05,
"loss": 268.8121,
"step": 4295
},
{
"epoch": 0.86,
"grad_norm": 37.766292572021484,
"learning_rate": 1.1738037526401857e-05,
"loss": 252.56,
"step": 4300
},
{
"epoch": 0.861,
"grad_norm": 37.77183532714844,
"learning_rate": 1.1574483962392767e-05,
"loss": 267.0605,
"step": 4305
},
{
"epoch": 0.862,
"grad_norm": 44.07095718383789,
"learning_rate": 1.1412007835391236e-05,
"loss": 250.3679,
"step": 4310
},
{
"epoch": 0.863,
"grad_norm": 38.32337188720703,
"learning_rate": 1.1250611125117527e-05,
"loss": 260.231,
"step": 4315
},
{
"epoch": 0.864,
"grad_norm": 41.917869567871094,
"learning_rate": 1.1090295798139672e-05,
"loss": 266.1937,
"step": 4320
},
{
"epoch": 0.865,
"grad_norm": 91.35490417480469,
"learning_rate": 1.093106380784934e-05,
"loss": 242.6242,
"step": 4325
},
{
"epoch": 0.866,
"grad_norm": 43.455326080322266,
"learning_rate": 1.0772917094438051e-05,
"loss": 266.0179,
"step": 4330
},
{
"epoch": 0.867,
"grad_norm": 43.033599853515625,
"learning_rate": 1.0615857584873623e-05,
"loss": 255.9246,
"step": 4335
},
{
"epoch": 0.868,
"grad_norm": 39.19639587402344,
"learning_rate": 1.0459887192876594e-05,
"loss": 250.1965,
"step": 4340
},
{
"epoch": 0.869,
"grad_norm": 40.74964904785156,
"learning_rate": 1.0305007818897006e-05,
"loss": 237.1111,
"step": 4345
},
{
"epoch": 0.87,
"grad_norm": 44.45502471923828,
"learning_rate": 1.0151221350091134e-05,
"loss": 255.0876,
"step": 4350
},
{
"epoch": 0.871,
"grad_norm": 40.276126861572266,
"learning_rate": 9.998529660298539e-06,
"loss": 259.4555,
"step": 4355
},
{
"epoch": 0.872,
"grad_norm": 37.615684509277344,
"learning_rate": 9.84693461001932e-06,
"loss": 265.8965,
"step": 4360
},
{
"epoch": 0.873,
"grad_norm": 48.69742965698242,
"learning_rate": 9.696438046391288e-06,
"loss": 248.8166,
"step": 4365
},
{
"epoch": 0.874,
"grad_norm": 44.19770812988281,
"learning_rate": 9.5470418031676e-06,
"loss": 260.093,
"step": 4370
},
{
"epoch": 0.875,
"grad_norm": 44.10205078125,
"learning_rate": 9.398747700694322e-06,
"loss": 246.4565,
"step": 4375
},
{
"epoch": 0.876,
"grad_norm": 45.03616714477539,
"learning_rate": 9.251557545888312e-06,
"loss": 243.1274,
"step": 4380
},
{
"epoch": 0.877,
"grad_norm": 48.52793502807617,
"learning_rate": 9.105473132215125e-06,
"loss": 248.354,
"step": 4385
},
{
"epoch": 0.878,
"grad_norm": 36.99675750732422,
"learning_rate": 8.960496239667282e-06,
"loss": 264.2107,
"step": 4390
},
{
"epoch": 0.879,
"grad_norm": 42.750850677490234,
"learning_rate": 8.816628634742441e-06,
"loss": 256.2788,
"step": 4395
},
{
"epoch": 0.88,
"grad_norm": 45.90469741821289,
"learning_rate": 8.67387207042194e-06,
"loss": 247.3613,
"step": 4400
},
{
"epoch": 0.881,
"grad_norm": 37.56058883666992,
"learning_rate": 8.532228286149501e-06,
"loss": 268.0317,
"step": 4405
},
{
"epoch": 0.882,
"grad_norm": 37.7716178894043,
"learning_rate": 8.39169900780995e-06,
"loss": 258.2219,
"step": 4410
},
{
"epoch": 0.883,
"grad_norm": 38.56128692626953,
"learning_rate": 8.252285947708139e-06,
"loss": 256.9367,
"step": 4415
},
{
"epoch": 0.884,
"grad_norm": 47.56509780883789,
"learning_rate": 8.113990804548244e-06,
"loss": 266.1394,
"step": 4420
},
{
"epoch": 0.885,
"grad_norm": 47.41032409667969,
"learning_rate": 7.976815263412963e-06,
"loss": 259.619,
"step": 4425
},
{
"epoch": 0.886,
"grad_norm": 52.97349166870117,
"learning_rate": 7.840760995742946e-06,
"loss": 272.1698,
"step": 4430
},
{
"epoch": 0.887,
"grad_norm": 53.98593521118164,
"learning_rate": 7.7058296593165e-06,
"loss": 269.0591,
"step": 4435
},
{
"epoch": 0.888,
"grad_norm": 37.87742614746094,
"learning_rate": 7.572022898229403e-06,
"loss": 263.6069,
"step": 4440
},
{
"epoch": 0.889,
"grad_norm": 37.33100509643555,
"learning_rate": 7.439342342874789e-06,
"loss": 266.3959,
"step": 4445
},
{
"epoch": 0.89,
"grad_norm": 39.4078483581543,
"learning_rate": 7.3077896099233765e-06,
"loss": 252.6339,
"step": 4450
},
{
"epoch": 0.891,
"grad_norm": 38.39181900024414,
"learning_rate": 7.177366302303667e-06,
"loss": 267.2035,
"step": 4455
},
{
"epoch": 0.892,
"grad_norm": 55.56351852416992,
"learning_rate": 7.048074009182548e-06,
"loss": 248.2377,
"step": 4460
},
{
"epoch": 0.893,
"grad_norm": 41.741329193115234,
"learning_rate": 6.919914305945774e-06,
"loss": 260.8208,
"step": 4465
},
{
"epoch": 0.894,
"grad_norm": 42.143150329589844,
"learning_rate": 6.7928887541789055e-06,
"loss": 263.541,
"step": 4470
},
{
"epoch": 0.895,
"grad_norm": 45.41794967651367,
"learning_rate": 6.666998901648203e-06,
"loss": 272.8168,
"step": 4475
},
{
"epoch": 0.896,
"grad_norm": 43.225955963134766,
"learning_rate": 6.542246282281772e-06,
"loss": 253.7476,
"step": 4480
},
{
"epoch": 0.897,
"grad_norm": 38.11464309692383,
"learning_rate": 6.418632416150927e-06,
"loss": 255.3627,
"step": 4485
},
{
"epoch": 0.898,
"grad_norm": 34.63508987426758,
"learning_rate": 6.296158809451602e-06,
"loss": 259.6055,
"step": 4490
},
{
"epoch": 0.899,
"grad_norm": 60.9337272644043,
"learning_rate": 6.174826954486068e-06,
"loss": 244.1677,
"step": 4495
},
{
"epoch": 0.9,
"grad_norm": 35.18669128417969,
"learning_rate": 6.054638329644657e-06,
"loss": 253.0888,
"step": 4500
},
{
"epoch": 0.901,
"grad_norm": 50.665462493896484,
"learning_rate": 5.935594399387856e-06,
"loss": 259.7753,
"step": 4505
},
{
"epoch": 0.902,
"grad_norm": 53.535987854003906,
"learning_rate": 5.8176966142283965e-06,
"loss": 246.1503,
"step": 4510
},
{
"epoch": 0.903,
"grad_norm": 42.608116149902344,
"learning_rate": 5.700946410713548e-06,
"loss": 258.425,
"step": 4515
},
{
"epoch": 0.904,
"grad_norm": 40.555870056152344,
"learning_rate": 5.585345211407733e-06,
"loss": 207.5773,
"step": 4520
},
{
"epoch": 0.905,
"grad_norm": 94.22760009765625,
"learning_rate": 5.470894424875062e-06,
"loss": 263.021,
"step": 4525
},
{
"epoch": 0.906,
"grad_norm": 39.249366760253906,
"learning_rate": 5.357595445662267e-06,
"loss": 270.8687,
"step": 4530
},
{
"epoch": 0.907,
"grad_norm": 37.268653869628906,
"learning_rate": 5.245449654281631e-06,
"loss": 259.7366,
"step": 4535
},
{
"epoch": 0.908,
"grad_norm": 37.395259857177734,
"learning_rate": 5.134458417194254e-06,
"loss": 254.0296,
"step": 4540
},
{
"epoch": 0.909,
"grad_norm": 44.76549530029297,
"learning_rate": 5.024623086793323e-06,
"loss": 270.3942,
"step": 4545
},
{
"epoch": 0.91,
"grad_norm": 39.78025436401367,
"learning_rate": 4.915945001387667e-06,
"loss": 255.6917,
"step": 4550
},
{
"epoch": 0.911,
"grad_norm": 42.29600524902344,
"learning_rate": 4.808425485185486e-06,
"loss": 262.9055,
"step": 4555
},
{
"epoch": 0.912,
"grad_norm": 43.139976501464844,
"learning_rate": 4.702065848278126e-06,
"loss": 259.3692,
"step": 4560
},
{
"epoch": 0.913,
"grad_norm": 44.60627746582031,
"learning_rate": 4.596867386624215e-06,
"loss": 253.6998,
"step": 4565
},
{
"epoch": 0.914,
"grad_norm": 44.99125289916992,
"learning_rate": 4.492831382033791e-06,
"loss": 252.6491,
"step": 4570
},
{
"epoch": 0.915,
"grad_norm": 37.2318115234375,
"learning_rate": 4.389959102152774e-06,
"loss": 271.8862,
"step": 4575
},
{
"epoch": 0.916,
"grad_norm": 45.15518569946289,
"learning_rate": 4.288251800447385e-06,
"loss": 243.3378,
"step": 4580
},
{
"epoch": 0.917,
"grad_norm": 40.64687728881836,
"learning_rate": 4.187710716189042e-06,
"loss": 260.9743,
"step": 4585
},
{
"epoch": 0.918,
"grad_norm": 34.36521911621094,
"learning_rate": 4.088337074439097e-06,
"loss": 255.274,
"step": 4590
},
{
"epoch": 0.919,
"grad_norm": 40.14622497558594,
"learning_rate": 3.990132086034026e-06,
"loss": 260.487,
"step": 4595
},
{
"epoch": 0.92,
"grad_norm": 50.980133056640625,
"learning_rate": 3.893096947570618e-06,
"loss": 258.2319,
"step": 4600
},
{
"epoch": 0.921,
"grad_norm": 52.429508209228516,
"learning_rate": 3.797232841391407e-06,
"loss": 256.1953,
"step": 4605
},
{
"epoch": 0.922,
"grad_norm": 38.029823303222656,
"learning_rate": 3.7025409355702976e-06,
"loss": 252.3869,
"step": 4610
},
{
"epoch": 0.923,
"grad_norm": 62.06398391723633,
"learning_rate": 3.6090223838982417e-06,
"loss": 255.0028,
"step": 4615
},
{
"epoch": 0.924,
"grad_norm": 37.77223587036133,
"learning_rate": 3.516678325869316e-06,
"loss": 265.305,
"step": 4620
},
{
"epoch": 0.925,
"grad_norm": 37.17695236206055,
"learning_rate": 3.425509886666711e-06,
"loss": 262.0458,
"step": 4625
},
{
"epoch": 0.926,
"grad_norm": 41.86711120605469,
"learning_rate": 3.3355181771490772e-06,
"loss": 266.8221,
"step": 4630
},
{
"epoch": 0.927,
"grad_norm": 39.11123275756836,
"learning_rate": 3.246704293837011e-06,
"loss": 249.548,
"step": 4635
},
{
"epoch": 0.928,
"grad_norm": 54.145565032958984,
"learning_rate": 3.1590693188996323e-06,
"loss": 227.2305,
"step": 4640
},
{
"epoch": 0.929,
"grad_norm": 43.5903205871582,
"learning_rate": 3.072614320141487e-06,
"loss": 256.559,
"step": 4645
},
{
"epoch": 0.93,
"grad_norm": 41.54502487182617,
"learning_rate": 2.9873403509894203e-06,
"loss": 251.1094,
"step": 4650
},
{
"epoch": 0.931,
"grad_norm": 42.24506759643555,
"learning_rate": 2.9032484504798452e-06,
"loss": 248.6529,
"step": 4655
},
{
"epoch": 0.932,
"grad_norm": 38.15921401977539,
"learning_rate": 2.8203396432460506e-06,
"loss": 253.3074,
"step": 4660
},
{
"epoch": 0.933,
"grad_norm": 40.134681701660156,
"learning_rate": 2.738614939505646e-06,
"loss": 245.4101,
"step": 4665
},
{
"epoch": 0.934,
"grad_norm": 59.89959716796875,
"learning_rate": 2.6580753350484046e-06,
"loss": 245.2997,
"step": 4670
},
{
"epoch": 0.935,
"grad_norm": 37.46065902709961,
"learning_rate": 2.5787218112239496e-06,
"loss": 259.8424,
"step": 4675
},
{
"epoch": 0.936,
"grad_norm": 44.80802536010742,
"learning_rate": 2.5005553349299547e-06,
"loss": 260.3636,
"step": 4680
},
{
"epoch": 0.937,
"grad_norm": 37.191802978515625,
"learning_rate": 2.4235768586002517e-06,
"loss": 262.3095,
"step": 4685
},
{
"epoch": 0.938,
"grad_norm": 41.716651916503906,
"learning_rate": 2.3477873201932734e-06,
"loss": 261.4209,
"step": 4690
},
{
"epoch": 0.939,
"grad_norm": 40.65319061279297,
"learning_rate": 2.273187643180652e-06,
"loss": 262.0591,
"step": 4695
},
{
"epoch": 0.94,
"grad_norm": 41.2353515625,
"learning_rate": 2.1997787365358958e-06,
"loss": 261.8104,
"step": 4700
},
{
"epoch": 0.941,
"grad_norm": 42.25737762451172,
"learning_rate": 2.1275614947233624e-06,
"loss": 262.6075,
"step": 4705
},
{
"epoch": 0.942,
"grad_norm": 38.099246978759766,
"learning_rate": 2.0565367976873584e-06,
"loss": 265.5373,
"step": 4710
},
{
"epoch": 0.943,
"grad_norm": 36.257362365722656,
"learning_rate": 1.986705510841402e-06,
"loss": 256.8948,
"step": 4715
},
{
"epoch": 0.944,
"grad_norm": 37.86013412475586,
"learning_rate": 1.918068485057689e-06,
"loss": 254.3568,
"step": 4720
},
{
"epoch": 0.945,
"grad_norm": 40.424285888671875,
"learning_rate": 1.8506265566567094e-06,
"loss": 253.312,
"step": 4725
},
{
"epoch": 0.946,
"grad_norm": 54.601806640625,
"learning_rate": 1.7843805473970798e-06,
"loss": 254.7292,
"step": 4730
},
{
"epoch": 0.947,
"grad_norm": 41.513633728027344,
"learning_rate": 1.719331264465529e-06,
"loss": 272.6708,
"step": 4735
},
{
"epoch": 0.948,
"grad_norm": 47.65037536621094,
"learning_rate": 1.6554795004670388e-06,
"loss": 261.4764,
"step": 4740
},
{
"epoch": 0.949,
"grad_norm": 44.372589111328125,
"learning_rate": 1.5928260334151845e-06,
"loss": 272.646,
"step": 4745
},
{
"epoch": 0.95,
"grad_norm": 43.44160079956055,
"learning_rate": 1.5313716267226996e-06,
"loss": 256.022,
"step": 4750
},
{
"epoch": 0.951,
"grad_norm": 38.6495361328125,
"learning_rate": 1.4711170291921484e-06,
"loss": 256.6988,
"step": 4755
},
{
"epoch": 0.952,
"grad_norm": 42.11634063720703,
"learning_rate": 1.412062975006767e-06,
"loss": 258.3397,
"step": 4760
},
{
"epoch": 0.953,
"grad_norm": 45.68549728393555,
"learning_rate": 1.3542101837215826e-06,
"loss": 266.8495,
"step": 4765
},
{
"epoch": 0.954,
"grad_norm": 48.824134826660156,
"learning_rate": 1.2975593602545965e-06,
"loss": 252.1071,
"step": 4770
},
{
"epoch": 0.955,
"grad_norm": 43.75063705444336,
"learning_rate": 1.2421111948782149e-06,
"loss": 264.1262,
"step": 4775
},
{
"epoch": 0.956,
"grad_norm": 39.52626419067383,
"learning_rate": 1.1878663632108322e-06,
"loss": 262.6142,
"step": 4780
},
{
"epoch": 0.957,
"grad_norm": 40.96241760253906,
"learning_rate": 1.134825526208605e-06,
"loss": 255.4903,
"step": 4785
},
{
"epoch": 0.958,
"grad_norm": 36.851776123046875,
"learning_rate": 1.0829893301573913e-06,
"loss": 252.0685,
"step": 4790
},
{
"epoch": 0.959,
"grad_norm": 43.87605667114258,
"learning_rate": 1.0323584066648795e-06,
"loss": 236.2986,
"step": 4795
},
{
"epoch": 0.96,
"grad_norm": 38.32923889160156,
"learning_rate": 9.829333726529056e-07,
"loss": 243.4744,
"step": 4800
},
{
"epoch": 0.961,
"grad_norm": 37.46969985961914,
"learning_rate": 9.347148303499142e-07,
"loss": 246.6612,
"step": 4805
},
{
"epoch": 0.962,
"grad_norm": 78.73678588867188,
"learning_rate": 8.877033672835988e-07,
"loss": 221.4253,
"step": 4810
},
{
"epoch": 0.963,
"grad_norm": 66.65288543701172,
"learning_rate": 8.418995562738285e-07,
"loss": 168.1778,
"step": 4815
},
{
"epoch": 0.964,
"grad_norm": 73.05755615234375,
"learning_rate": 7.973039554255768e-07,
"loss": 172.9612,
"step": 4820
},
{
"epoch": 0.965,
"grad_norm": 41.94700622558594,
"learning_rate": 7.539171081221596e-07,
"loss": 242.2787,
"step": 4825
},
{
"epoch": 0.966,
"grad_norm": 46.22639465332031,
"learning_rate": 7.117395430186414e-07,
"loss": 263.2662,
"step": 4830
},
{
"epoch": 0.967,
"grad_norm": 47.08068084716797,
"learning_rate": 6.707717740353059e-07,
"loss": 241.7582,
"step": 4835
},
{
"epoch": 0.968,
"grad_norm": 40.754119873046875,
"learning_rate": 6.310143003515179e-07,
"loss": 257.977,
"step": 4840
},
{
"epoch": 0.969,
"grad_norm": 41.96792984008789,
"learning_rate": 5.924676063995382e-07,
"loss": 253.0107,
"step": 4845
},
{
"epoch": 0.97,
"grad_norm": 44.857635498046875,
"learning_rate": 5.551321618586736e-07,
"loss": 260.0565,
"step": 4850
},
{
"epoch": 0.971,
"grad_norm": 36.91495895385742,
"learning_rate": 5.190084216495361e-07,
"loss": 257.19,
"step": 4855
},
{
"epoch": 0.972,
"grad_norm": 39.993370056152344,
"learning_rate": 4.840968259284817e-07,
"loss": 229.8083,
"step": 4860
},
{
"epoch": 0.973,
"grad_norm": 39.71282196044922,
"learning_rate": 4.503978000823028e-07,
"loss": 261.6341,
"step": 4865
},
{
"epoch": 0.974,
"grad_norm": 44.517940521240234,
"learning_rate": 4.179117547229883e-07,
"loss": 250.2828,
"step": 4870
},
{
"epoch": 0.975,
"grad_norm": 45.17426681518555,
"learning_rate": 3.866390856827495e-07,
"loss": 249.7594,
"step": 4875
},
{
"epoch": 0.976,
"grad_norm": 38.93362045288086,
"learning_rate": 3.565801740092023e-07,
"loss": 247.2715,
"step": 4880
},
{
"epoch": 0.977,
"grad_norm": 43.03696823120117,
"learning_rate": 3.277353859606813e-07,
"loss": 261.8643,
"step": 4885
},
{
"epoch": 0.978,
"grad_norm": 40.37131881713867,
"learning_rate": 3.001050730018218e-07,
"loss": 261.9049,
"step": 4890
},
{
"epoch": 0.979,
"grad_norm": 41.421791076660156,
"learning_rate": 2.73689571799296e-07,
"loss": 252.9102,
"step": 4895
},
{
"epoch": 0.98,
"grad_norm": 42.79949188232422,
"learning_rate": 2.484892042176279e-07,
"loss": 256.9695,
"step": 4900
},
{
"epoch": 0.981,
"grad_norm": 47.147674560546875,
"learning_rate": 2.2450427731534053e-07,
"loss": 267.1458,
"step": 4905
},
{
"epoch": 0.982,
"grad_norm": 47.0726203918457,
"learning_rate": 2.017350833412146e-07,
"loss": 277.3694,
"step": 4910
},
{
"epoch": 0.983,
"grad_norm": 39.921356201171875,
"learning_rate": 1.8018189973069143e-07,
"loss": 256.0456,
"step": 4915
},
{
"epoch": 0.984,
"grad_norm": 36.55499267578125,
"learning_rate": 1.598449891024978e-07,
"loss": 263.2622,
"step": 4920
},
{
"epoch": 0.985,
"grad_norm": 41.14494323730469,
"learning_rate": 1.4072459925548177e-07,
"loss": 263.4021,
"step": 4925
},
{
"epoch": 0.986,
"grad_norm": 37.76477813720703,
"learning_rate": 1.2282096316554858e-07,
"loss": 264.6894,
"step": 4930
},
{
"epoch": 0.987,
"grad_norm": 38.58914566040039,
"learning_rate": 1.0613429898287398e-07,
"loss": 268.8848,
"step": 4935
},
{
"epoch": 0.988,
"grad_norm": 51.645572662353516,
"learning_rate": 9.066481002918403e-08,
"loss": 280.8318,
"step": 4940
},
{
"epoch": 0.989,
"grad_norm": 39.02803039550781,
"learning_rate": 7.641268479531283e-08,
"loss": 257.9176,
"step": 4945
},
{
"epoch": 0.99,
"grad_norm": 43.199806213378906,
"learning_rate": 6.337809693891527e-08,
"loss": 250.8048,
"step": 4950
},
{
"epoch": 0.991,
"grad_norm": 55.54723358154297,
"learning_rate": 5.1561205282335547e-08,
"loss": 248.7293,
"step": 4955
},
{
"epoch": 0.992,
"grad_norm": 42.62922286987305,
"learning_rate": 4.096215381066415e-08,
"loss": 228.34,
"step": 4960
},
{
"epoch": 0.993,
"grad_norm": 42.20180130004883,
"learning_rate": 3.1581071670006015e-08,
"loss": 259.0718,
"step": 4965
},
{
"epoch": 0.994,
"grad_norm": 36.09339141845703,
"learning_rate": 2.3418073165870636e-08,
"loss": 249.076,
"step": 4970
},
{
"epoch": 0.995,
"grad_norm": 39.50554275512695,
"learning_rate": 1.6473257761828732e-08,
"loss": 257.3716,
"step": 4975
},
{
"epoch": 0.996,
"grad_norm": 65.08081817626953,
"learning_rate": 1.074671007825767e-08,
"loss": 238.1982,
"step": 4980
},
{
"epoch": 0.997,
"grad_norm": 51.30257034301758,
"learning_rate": 6.238499891353389e-09,
"loss": 253.5564,
"step": 4985
},
{
"epoch": 0.998,
"grad_norm": 77.68270874023438,
"learning_rate": 2.948682132208891e-09,
"loss": 230.3555,
"step": 4990
},
{
"epoch": 0.999,
"grad_norm": 70.24752044677734,
"learning_rate": 8.772968862369446e-10,
"loss": 226.6795,
"step": 4995
},
{
"epoch": 1.0,
"grad_norm": 40.4685173034668,
"learning_rate": 2.4369392592760164e-11,
"loss": 260.2546,
"step": 5000
}
],
"logging_steps": 5,
"max_steps": 5000,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.393697681408e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001,
"grad_norm": 45.34572219848633,
"learning_rate": 1.6000000000000001e-06,
"loss": 319.578,
"step": 5
},
{
"epoch": 0.002,
"grad_norm": 35.23944091796875,
"learning_rate": 3.6e-06,
"loss": 321.7812,
"step": 10
},
{
"epoch": 0.003,
"grad_norm": 31.629674911499023,
"learning_rate": 5.600000000000001e-06,
"loss": 321.7244,
"step": 15
},
{
"epoch": 0.004,
"grad_norm": 37.21824264526367,
"learning_rate": 7.6e-06,
"loss": 327.2896,
"step": 20
},
{
"epoch": 0.005,
"grad_norm": 41.95133972167969,
"learning_rate": 9.600000000000001e-06,
"loss": 327.3718,
"step": 25
},
{
"epoch": 0.006,
"grad_norm": 41.561954498291016,
"learning_rate": 1.16e-05,
"loss": 315.5146,
"step": 30
},
{
"epoch": 0.007,
"grad_norm": 38.29129409790039,
"learning_rate": 1.3600000000000002e-05,
"loss": 318.5627,
"step": 35
},
{
"epoch": 0.008,
"grad_norm": 44.10498046875,
"learning_rate": 1.56e-05,
"loss": 312.3329,
"step": 40
},
{
"epoch": 0.009,
"grad_norm": 44.040958404541016,
"learning_rate": 1.76e-05,
"loss": 316.1487,
"step": 45
},
{
"epoch": 0.01,
"grad_norm": 48.966148376464844,
"learning_rate": 1.9600000000000002e-05,
"loss": 328.8573,
"step": 50
},
{
"epoch": 0.011,
"grad_norm": 48.719276428222656,
"learning_rate": 2.16e-05,
"loss": 314.682,
"step": 55
},
{
"epoch": 0.012,
"grad_norm": 56.17375946044922,
"learning_rate": 2.36e-05,
"loss": 315.3329,
"step": 60
},
{
"epoch": 0.013,
"grad_norm": 48.65364456176758,
"learning_rate": 2.5600000000000002e-05,
"loss": 320.5187,