zephyr-quiklang-3b / trainer_state.json
Walmart-the-bag's picture
Upload folder using huggingface_hub
94e4342
raw
history blame contribute delete
No virus
68.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 2802,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.999960716301628e-05,
"loss": 0.9669,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 4.999842866441079e-05,
"loss": 0.8795,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.9996464541220155e-05,
"loss": 1.1216,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 4.999371485517079e-05,
"loss": 0.6686,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 4.999017969267698e-05,
"loss": 0.8372,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 4.99858591648381e-05,
"loss": 0.7397,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 4.9980753407435234e-05,
"loss": 0.8539,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 4.99748625809268e-05,
"loss": 1.0454,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 4.9968186870443544e-05,
"loss": 0.7646,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 4.9960726485782755e-05,
"loss": 0.8626,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 4.995248166140163e-05,
"loss": 0.8773,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 4.994345265640994e-05,
"loss": 0.5691,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 4.9933639754561824e-05,
"loss": 0.6205,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 4.9923043264246965e-05,
"loss": 0.6391,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 4.9911663518480824e-05,
"loss": 0.5564,
"step": 75
},
{
"epoch": 0.09,
"learning_rate": 4.989950087489419e-05,
"loss": 0.5848,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 4.9886555715721964e-05,
"loss": 0.9124,
"step": 85
},
{
"epoch": 0.1,
"learning_rate": 4.9872828447791135e-05,
"loss": 0.5695,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 4.985831950250798e-05,
"loss": 0.5616,
"step": 95
},
{
"epoch": 0.11,
"learning_rate": 4.9843029335844535e-05,
"loss": 0.6667,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 4.982695842832421e-05,
"loss": 0.7367,
"step": 105
},
{
"epoch": 0.12,
"learning_rate": 4.9810107285006785e-05,
"loss": 0.9258,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 4.979247643547242e-05,
"loss": 0.8087,
"step": 115
},
{
"epoch": 0.13,
"learning_rate": 4.977406643380511e-05,
"loss": 0.8627,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 4.97548778585752e-05,
"loss": 0.633,
"step": 125
},
{
"epoch": 0.14,
"learning_rate": 4.973491131282127e-05,
"loss": 1.0985,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 4.971416742403112e-05,
"loss": 0.9516,
"step": 135
},
{
"epoch": 0.15,
"learning_rate": 4.969264684412208e-05,
"loss": 0.8711,
"step": 140
},
{
"epoch": 0.16,
"learning_rate": 4.967035024942054e-05,
"loss": 0.7193,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 4.9647278340640644e-05,
"loss": 0.8416,
"step": 150
},
{
"epoch": 0.17,
"learning_rate": 4.9623431842862335e-05,
"loss": 0.6761,
"step": 155
},
{
"epoch": 0.17,
"learning_rate": 4.9598811505508504e-05,
"loss": 0.6659,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 4.957341810232147e-05,
"loss": 0.6969,
"step": 165
},
{
"epoch": 0.18,
"learning_rate": 4.954725243133868e-05,
"loss": 0.8674,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 4.952031531486758e-05,
"loss": 0.8668,
"step": 175
},
{
"epoch": 0.19,
"learning_rate": 4.949260759945984e-05,
"loss": 0.7499,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 4.946413015588466e-05,
"loss": 1.0306,
"step": 185
},
{
"epoch": 0.2,
"learning_rate": 4.9434883879101496e-05,
"loss": 0.8853,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 4.940486968823188e-05,
"loss": 0.8703,
"step": 195
},
{
"epoch": 0.21,
"learning_rate": 4.937408852653055e-05,
"loss": 0.8031,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 4.934254136135581e-05,
"loss": 1.2864,
"step": 205
},
{
"epoch": 0.22,
"learning_rate": 4.93102291841391e-05,
"loss": 0.6821,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 4.9277153010353895e-05,
"loss": 0.7472,
"step": 215
},
{
"epoch": 0.24,
"learning_rate": 4.9243313879483734e-05,
"loss": 1.2898,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 4.920871285498958e-05,
"loss": 1.0007,
"step": 225
},
{
"epoch": 0.25,
"learning_rate": 4.917335102427642e-05,
"loss": 0.8147,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 4.913722949865902e-05,
"loss": 0.771,
"step": 235
},
{
"epoch": 0.26,
"learning_rate": 4.91003494133271e-05,
"loss": 0.8844,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 4.9062711927309564e-05,
"loss": 0.7669,
"step": 245
},
{
"epoch": 0.27,
"learning_rate": 4.902431822343813e-05,
"loss": 1.0498,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 4.898516950831015e-05,
"loss": 0.5262,
"step": 255
},
{
"epoch": 0.28,
"learning_rate": 4.894526701225068e-05,
"loss": 0.8268,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 4.8904611989273804e-05,
"loss": 1.1978,
"step": 265
},
{
"epoch": 0.29,
"learning_rate": 4.8863205717043257e-05,
"loss": 0.7573,
"step": 270
},
{
"epoch": 0.29,
"learning_rate": 4.882104949683225e-05,
"loss": 0.9093,
"step": 275
},
{
"epoch": 0.3,
"learning_rate": 4.877814465348256e-05,
"loss": 0.5426,
"step": 280
},
{
"epoch": 0.31,
"learning_rate": 4.873449253536295e-05,
"loss": 0.5552,
"step": 285
},
{
"epoch": 0.31,
"learning_rate": 4.8690094514326713e-05,
"loss": 0.756,
"step": 290
},
{
"epoch": 0.32,
"learning_rate": 4.864495198566863e-05,
"loss": 0.8122,
"step": 295
},
{
"epoch": 0.32,
"learning_rate": 4.859906636808108e-05,
"loss": 0.6565,
"step": 300
},
{
"epoch": 0.33,
"learning_rate": 4.855243910360948e-05,
"loss": 0.7606,
"step": 305
},
{
"epoch": 0.33,
"learning_rate": 4.8505071657606936e-05,
"loss": 0.6584,
"step": 310
},
{
"epoch": 0.34,
"learning_rate": 4.845696551868823e-05,
"loss": 0.8891,
"step": 315
},
{
"epoch": 0.34,
"learning_rate": 4.840812219868299e-05,
"loss": 0.7888,
"step": 320
},
{
"epoch": 0.35,
"learning_rate": 4.835854323258822e-05,
"loss": 0.804,
"step": 325
},
{
"epoch": 0.35,
"learning_rate": 4.830823017852004e-05,
"loss": 0.6016,
"step": 330
},
{
"epoch": 0.36,
"learning_rate": 4.825718461766473e-05,
"loss": 0.7443,
"step": 335
},
{
"epoch": 0.36,
"learning_rate": 4.820540815422901e-05,
"loss": 0.7805,
"step": 340
},
{
"epoch": 0.37,
"learning_rate": 4.815290241538967e-05,
"loss": 0.578,
"step": 345
},
{
"epoch": 0.37,
"learning_rate": 4.809966905124238e-05,
"loss": 0.7461,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 4.804570973474989e-05,
"loss": 0.7009,
"step": 355
},
{
"epoch": 0.39,
"learning_rate": 4.7991026161689414e-05,
"loss": 0.8072,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 4.7935620050599326e-05,
"loss": 0.743,
"step": 365
},
{
"epoch": 0.4,
"learning_rate": 4.787949314272521e-05,
"loss": 0.6266,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 4.782264720196506e-05,
"loss": 0.8777,
"step": 375
},
{
"epoch": 0.41,
"learning_rate": 4.776508401481393e-05,
"loss": 0.653,
"step": 380
},
{
"epoch": 0.41,
"learning_rate": 4.7706805390307716e-05,
"loss": 0.5811,
"step": 385
},
{
"epoch": 0.42,
"learning_rate": 4.764781315996635e-05,
"loss": 0.5695,
"step": 390
},
{
"epoch": 0.42,
"learning_rate": 4.75881091777362e-05,
"loss": 1.009,
"step": 395
},
{
"epoch": 0.43,
"learning_rate": 4.752769531993187e-05,
"loss": 0.9361,
"step": 400
},
{
"epoch": 0.43,
"learning_rate": 4.746657348517716e-05,
"loss": 0.7177,
"step": 405
},
{
"epoch": 0.44,
"learning_rate": 4.7404745594345455e-05,
"loss": 0.783,
"step": 410
},
{
"epoch": 0.44,
"learning_rate": 4.734221359049933e-05,
"loss": 0.7872,
"step": 415
},
{
"epoch": 0.45,
"learning_rate": 4.7278979438829476e-05,
"loss": 0.9596,
"step": 420
},
{
"epoch": 0.46,
"learning_rate": 4.7215045126592975e-05,
"loss": 0.6286,
"step": 425
},
{
"epoch": 0.46,
"learning_rate": 4.7150412663050806e-05,
"loss": 0.6694,
"step": 430
},
{
"epoch": 0.47,
"learning_rate": 4.708508407940474e-05,
"loss": 1.1083,
"step": 435
},
{
"epoch": 0.47,
"learning_rate": 4.701906142873348e-05,
"loss": 0.8941,
"step": 440
},
{
"epoch": 0.48,
"learning_rate": 4.695234678592813e-05,
"loss": 0.5684,
"step": 445
},
{
"epoch": 0.48,
"learning_rate": 4.688494224762703e-05,
"loss": 0.6082,
"step": 450
},
{
"epoch": 0.49,
"learning_rate": 4.68168499321498e-05,
"loss": 0.6237,
"step": 455
},
{
"epoch": 0.49,
"learning_rate": 4.674807197943084e-05,
"loss": 0.7826,
"step": 460
},
{
"epoch": 0.5,
"learning_rate": 4.667861055095204e-05,
"loss": 0.8674,
"step": 465
},
{
"epoch": 0.5,
"learning_rate": 4.660846782967482e-05,
"loss": 0.6158,
"step": 470
},
{
"epoch": 0.51,
"learning_rate": 4.6537646019971606e-05,
"loss": 0.9251,
"step": 475
},
{
"epoch": 0.51,
"learning_rate": 4.6466147347556464e-05,
"loss": 0.3553,
"step": 480
},
{
"epoch": 0.52,
"learning_rate": 4.639397405941523e-05,
"loss": 0.6503,
"step": 485
},
{
"epoch": 0.52,
"learning_rate": 4.632112842373487e-05,
"loss": 0.6233,
"step": 490
},
{
"epoch": 0.53,
"learning_rate": 4.6247612729832136e-05,
"loss": 0.893,
"step": 495
},
{
"epoch": 0.54,
"learning_rate": 4.617342928808171e-05,
"loss": 0.6042,
"step": 500
},
{
"epoch": 0.54,
"learning_rate": 4.609858042984358e-05,
"loss": 0.6552,
"step": 505
},
{
"epoch": 0.55,
"learning_rate": 4.602306850738968e-05,
"loss": 0.7058,
"step": 510
},
{
"epoch": 0.55,
"learning_rate": 4.5946895893830107e-05,
"loss": 0.59,
"step": 515
},
{
"epoch": 0.56,
"learning_rate": 4.587006498303843e-05,
"loss": 0.7338,
"step": 520
},
{
"epoch": 0.56,
"learning_rate": 4.5792578189576517e-05,
"loss": 0.7929,
"step": 525
},
{
"epoch": 0.57,
"learning_rate": 4.5714437948618624e-05,
"loss": 0.5103,
"step": 530
},
{
"epoch": 0.57,
"learning_rate": 4.563564671587487e-05,
"loss": 0.6799,
"step": 535
},
{
"epoch": 0.58,
"learning_rate": 4.555620696751407e-05,
"loss": 1.249,
"step": 540
},
{
"epoch": 0.58,
"learning_rate": 4.5476121200085934e-05,
"loss": 0.7596,
"step": 545
},
{
"epoch": 0.59,
"learning_rate": 4.5395391930442536e-05,
"loss": 0.695,
"step": 550
},
{
"epoch": 0.59,
"learning_rate": 4.531402169565933e-05,
"loss": 0.7904,
"step": 555
},
{
"epoch": 0.6,
"learning_rate": 4.52320130529553e-05,
"loss": 0.5093,
"step": 560
},
{
"epoch": 0.6,
"learning_rate": 4.51493685796127e-05,
"loss": 0.5815,
"step": 565
},
{
"epoch": 0.61,
"learning_rate": 4.5066090872895944e-05,
"loss": 0.7107,
"step": 570
},
{
"epoch": 0.62,
"learning_rate": 4.4982182549970105e-05,
"loss": 0.8838,
"step": 575
},
{
"epoch": 0.62,
"learning_rate": 4.489764624781859e-05,
"loss": 0.6607,
"step": 580
},
{
"epoch": 0.63,
"learning_rate": 4.481248462316026e-05,
"loss": 0.9362,
"step": 585
},
{
"epoch": 0.63,
"learning_rate": 4.472670035236597e-05,
"loss": 0.7114,
"step": 590
},
{
"epoch": 0.64,
"learning_rate": 4.4640296131374474e-05,
"loss": 0.8569,
"step": 595
},
{
"epoch": 0.64,
"learning_rate": 4.4553274675607636e-05,
"loss": 0.8141,
"step": 600
},
{
"epoch": 0.65,
"learning_rate": 4.446563871988517e-05,
"loss": 0.7217,
"step": 605
},
{
"epoch": 0.65,
"learning_rate": 4.4377391018338624e-05,
"loss": 0.5951,
"step": 610
},
{
"epoch": 0.66,
"learning_rate": 4.4288534344324884e-05,
"loss": 0.616,
"step": 615
},
{
"epoch": 0.66,
"learning_rate": 4.419907149033896e-05,
"loss": 0.8424,
"step": 620
},
{
"epoch": 0.67,
"learning_rate": 4.410900526792627e-05,
"loss": 0.6658,
"step": 625
},
{
"epoch": 0.67,
"learning_rate": 4.401833850759428e-05,
"loss": 0.7002,
"step": 630
},
{
"epoch": 0.68,
"learning_rate": 4.392707405872351e-05,
"loss": 0.6905,
"step": 635
},
{
"epoch": 0.69,
"learning_rate": 4.383521478947803e-05,
"loss": 0.759,
"step": 640
},
{
"epoch": 0.69,
"learning_rate": 4.37427635867153e-05,
"loss": 0.6635,
"step": 645
},
{
"epoch": 0.7,
"learning_rate": 4.364972335589544e-05,
"loss": 0.9038,
"step": 650
},
{
"epoch": 0.7,
"learning_rate": 4.355609702098995e-05,
"loss": 0.9281,
"step": 655
},
{
"epoch": 0.71,
"learning_rate": 4.34618875243898e-05,
"loss": 0.6037,
"step": 660
},
{
"epoch": 0.71,
"learning_rate": 4.3367097826812935e-05,
"loss": 0.7123,
"step": 665
},
{
"epoch": 0.72,
"learning_rate": 4.3271730907211274e-05,
"loss": 0.8659,
"step": 670
},
{
"epoch": 0.72,
"learning_rate": 4.3175789762677055e-05,
"loss": 0.885,
"step": 675
},
{
"epoch": 0.73,
"learning_rate": 4.3079277408348665e-05,
"loss": 0.9043,
"step": 680
},
{
"epoch": 0.73,
"learning_rate": 4.298219687731587e-05,
"loss": 0.6392,
"step": 685
},
{
"epoch": 0.74,
"learning_rate": 4.2884551220524525e-05,
"loss": 0.9321,
"step": 690
},
{
"epoch": 0.74,
"learning_rate": 4.278634350668065e-05,
"loss": 0.8969,
"step": 695
},
{
"epoch": 0.75,
"learning_rate": 4.2687576822154e-05,
"loss": 0.5849,
"step": 700
},
{
"epoch": 0.75,
"learning_rate": 4.2588254270881104e-05,
"loss": 0.6908,
"step": 705
},
{
"epoch": 0.76,
"learning_rate": 4.248837897426766e-05,
"loss": 0.8788,
"step": 710
},
{
"epoch": 0.77,
"learning_rate": 4.238795407109052e-05,
"loss": 0.7171,
"step": 715
},
{
"epoch": 0.77,
"learning_rate": 4.228698271739894e-05,
"loss": 0.8489,
"step": 720
},
{
"epoch": 0.78,
"learning_rate": 4.218546808641549e-05,
"loss": 0.7057,
"step": 725
},
{
"epoch": 0.78,
"learning_rate": 4.208341336843629e-05,
"loss": 0.7711,
"step": 730
},
{
"epoch": 0.79,
"learning_rate": 4.198082177073075e-05,
"loss": 0.7608,
"step": 735
},
{
"epoch": 0.79,
"learning_rate": 4.1877696517440755e-05,
"loss": 0.6685,
"step": 740
},
{
"epoch": 0.8,
"learning_rate": 4.17740408494794e-05,
"loss": 1.0127,
"step": 745
},
{
"epoch": 0.8,
"learning_rate": 4.1669858024429085e-05,
"loss": 1.0633,
"step": 750
},
{
"epoch": 0.81,
"learning_rate": 4.156515131643913e-05,
"loss": 0.9283,
"step": 755
},
{
"epoch": 0.81,
"learning_rate": 4.145992401612293e-05,
"loss": 0.8288,
"step": 760
},
{
"epoch": 0.82,
"learning_rate": 4.135417943045451e-05,
"loss": 0.6876,
"step": 765
},
{
"epoch": 0.82,
"learning_rate": 4.12479208826646e-05,
"loss": 0.5607,
"step": 770
},
{
"epoch": 0.83,
"learning_rate": 4.1141151712136185e-05,
"loss": 0.9306,
"step": 775
},
{
"epoch": 0.84,
"learning_rate": 4.103387527429957e-05,
"loss": 0.8383,
"step": 780
},
{
"epoch": 0.84,
"learning_rate": 4.092609494052695e-05,
"loss": 0.6689,
"step": 785
},
{
"epoch": 0.85,
"learning_rate": 4.0817814098026424e-05,
"loss": 0.8616,
"step": 790
},
{
"epoch": 0.85,
"learning_rate": 4.070903614973555e-05,
"loss": 0.9265,
"step": 795
},
{
"epoch": 0.86,
"learning_rate": 4.059976451421441e-05,
"loss": 0.6806,
"step": 800
},
{
"epoch": 0.86,
"learning_rate": 4.0490002625538195e-05,
"loss": 0.7305,
"step": 805
},
{
"epoch": 0.87,
"learning_rate": 4.0379753933189236e-05,
"loss": 0.689,
"step": 810
},
{
"epoch": 0.87,
"learning_rate": 4.026902190194864e-05,
"loss": 0.9028,
"step": 815
},
{
"epoch": 0.88,
"learning_rate": 4.0157810011787376e-05,
"loss": 0.7079,
"step": 820
},
{
"epoch": 0.88,
"learning_rate": 4.004612175775693e-05,
"loss": 0.7397,
"step": 825
},
{
"epoch": 0.89,
"learning_rate": 3.9933960649879434e-05,
"loss": 0.6809,
"step": 830
},
{
"epoch": 0.89,
"learning_rate": 3.98213302130374e-05,
"loss": 0.7632,
"step": 835
},
{
"epoch": 0.9,
"learning_rate": 3.970823398686292e-05,
"loss": 0.8833,
"step": 840
},
{
"epoch": 0.9,
"learning_rate": 3.959467552562642e-05,
"loss": 1.1581,
"step": 845
},
{
"epoch": 0.91,
"learning_rate": 3.948065839812497e-05,
"loss": 0.8152,
"step": 850
},
{
"epoch": 0.92,
"learning_rate": 3.936618618757012e-05,
"loss": 0.7035,
"step": 855
},
{
"epoch": 0.92,
"learning_rate": 3.9251262491475314e-05,
"loss": 0.6862,
"step": 860
},
{
"epoch": 0.93,
"learning_rate": 3.9135890921542795e-05,
"loss": 0.6714,
"step": 865
},
{
"epoch": 0.93,
"learning_rate": 3.902007510355014e-05,
"loss": 0.6129,
"step": 870
},
{
"epoch": 0.94,
"learning_rate": 3.8903818677236256e-05,
"loss": 0.5749,
"step": 875
},
{
"epoch": 0.94,
"learning_rate": 3.878712529618707e-05,
"loss": 0.7528,
"step": 880
},
{
"epoch": 0.95,
"learning_rate": 3.866999862772063e-05,
"loss": 0.8081,
"step": 885
},
{
"epoch": 0.95,
"learning_rate": 3.8552442352771925e-05,
"loss": 0.2889,
"step": 890
},
{
"epoch": 0.96,
"learning_rate": 3.8434460165777145e-05,
"loss": 0.5895,
"step": 895
},
{
"epoch": 0.96,
"learning_rate": 3.831605577455761e-05,
"loss": 0.7995,
"step": 900
},
{
"epoch": 0.97,
"learning_rate": 3.819723290020323e-05,
"loss": 0.8598,
"step": 905
},
{
"epoch": 0.97,
"learning_rate": 3.807799527695557e-05,
"loss": 0.7677,
"step": 910
},
{
"epoch": 0.98,
"learning_rate": 3.79583466520905e-05,
"loss": 0.6112,
"step": 915
},
{
"epoch": 0.99,
"learning_rate": 3.78382907858004e-05,
"loss": 0.701,
"step": 920
},
{
"epoch": 0.99,
"learning_rate": 3.7717831451076024e-05,
"loss": 0.812,
"step": 925
},
{
"epoch": 1.0,
"learning_rate": 3.7596972433587915e-05,
"loss": 0.8178,
"step": 930
},
{
"epoch": 1.0,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.8653,
"step": 935
},
{
"epoch": 1.01,
"learning_rate": 3.737843113344485e-05,
"loss": 0.4592,
"step": 940
},
{
"epoch": 1.01,
"learning_rate": 3.72564732504457e-05,
"loss": 0.1997,
"step": 945
},
{
"epoch": 1.02,
"learning_rate": 3.713413018376795e-05,
"loss": 0.4832,
"step": 950
},
{
"epoch": 1.02,
"learning_rate": 3.701140577828207e-05,
"loss": 0.5203,
"step": 955
},
{
"epoch": 1.03,
"learning_rate": 3.68883038908429e-05,
"loss": 0.3606,
"step": 960
},
{
"epoch": 1.03,
"learning_rate": 3.6764828390168374e-05,
"loss": 0.4231,
"step": 965
},
{
"epoch": 1.04,
"learning_rate": 3.664098315671793e-05,
"loss": 0.4086,
"step": 970
},
{
"epoch": 1.04,
"learning_rate": 3.651677208257063e-05,
"loss": 0.3105,
"step": 975
},
{
"epoch": 1.05,
"learning_rate": 3.639219907130276e-05,
"loss": 0.3642,
"step": 980
},
{
"epoch": 1.05,
"learning_rate": 3.626726803786519e-05,
"loss": 0.4502,
"step": 985
},
{
"epoch": 1.06,
"learning_rate": 3.6141982908460364e-05,
"loss": 0.4569,
"step": 990
},
{
"epoch": 1.07,
"learning_rate": 3.601634762041887e-05,
"loss": 0.45,
"step": 995
},
{
"epoch": 1.07,
"learning_rate": 3.5890366122075694e-05,
"loss": 0.3306,
"step": 1000
},
{
"epoch": 1.08,
"learning_rate": 3.576404237264621e-05,
"loss": 0.3047,
"step": 1005
},
{
"epoch": 1.08,
"learning_rate": 3.5637380342101656e-05,
"loss": 0.3147,
"step": 1010
},
{
"epoch": 1.09,
"learning_rate": 3.5510384011044436e-05,
"loss": 0.2347,
"step": 1015
},
{
"epoch": 1.09,
"learning_rate": 3.5383057370583005e-05,
"loss": 0.2454,
"step": 1020
},
{
"epoch": 1.1,
"learning_rate": 3.525540442220644e-05,
"loss": 0.4466,
"step": 1025
},
{
"epoch": 1.1,
"learning_rate": 3.512742917765866e-05,
"loss": 0.3689,
"step": 1030
},
{
"epoch": 1.11,
"learning_rate": 3.499913565881241e-05,
"loss": 0.4169,
"step": 1035
},
{
"epoch": 1.11,
"learning_rate": 3.487052789754279e-05,
"loss": 0.4434,
"step": 1040
},
{
"epoch": 1.12,
"learning_rate": 3.4741609935600614e-05,
"loss": 0.2953,
"step": 1045
},
{
"epoch": 1.12,
"learning_rate": 3.4612385824485337e-05,
"loss": 0.3711,
"step": 1050
},
{
"epoch": 1.13,
"learning_rate": 3.4482859625317766e-05,
"loss": 0.2047,
"step": 1055
},
{
"epoch": 1.13,
"learning_rate": 3.435303540871242e-05,
"loss": 0.204,
"step": 1060
},
{
"epoch": 1.14,
"learning_rate": 3.422291725464959e-05,
"loss": 0.3836,
"step": 1065
},
{
"epoch": 1.15,
"learning_rate": 3.409250925234712e-05,
"loss": 0.2568,
"step": 1070
},
{
"epoch": 1.15,
"learning_rate": 3.396181550013192e-05,
"loss": 0.4014,
"step": 1075
},
{
"epoch": 1.16,
"learning_rate": 3.383084010531114e-05,
"loss": 0.4951,
"step": 1080
},
{
"epoch": 1.16,
"learning_rate": 3.3699587184043105e-05,
"loss": 0.34,
"step": 1085
},
{
"epoch": 1.17,
"learning_rate": 3.356806086120795e-05,
"loss": 0.3992,
"step": 1090
},
{
"epoch": 1.17,
"learning_rate": 3.343626527027798e-05,
"loss": 0.3924,
"step": 1095
},
{
"epoch": 1.18,
"learning_rate": 3.3304204553187815e-05,
"loss": 0.1872,
"step": 1100
},
{
"epoch": 1.18,
"learning_rate": 3.317188286020413e-05,
"loss": 0.3238,
"step": 1105
},
{
"epoch": 1.19,
"learning_rate": 3.303930434979531e-05,
"loss": 0.2943,
"step": 1110
},
{
"epoch": 1.19,
"learning_rate": 3.290647318850074e-05,
"loss": 0.3754,
"step": 1115
},
{
"epoch": 1.2,
"learning_rate": 3.277339355079983e-05,
"loss": 0.3159,
"step": 1120
},
{
"epoch": 1.2,
"learning_rate": 3.2640069618980854e-05,
"loss": 0.3763,
"step": 1125
},
{
"epoch": 1.21,
"learning_rate": 3.2506505583009516e-05,
"loss": 0.3898,
"step": 1130
},
{
"epoch": 1.22,
"learning_rate": 3.2372705640397264e-05,
"loss": 0.3006,
"step": 1135
},
{
"epoch": 1.22,
"learning_rate": 3.223867399606935e-05,
"loss": 0.3968,
"step": 1140
},
{
"epoch": 1.23,
"learning_rate": 3.210441486223274e-05,
"loss": 0.3107,
"step": 1145
},
{
"epoch": 1.23,
"learning_rate": 3.196993245824368e-05,
"loss": 0.4036,
"step": 1150
},
{
"epoch": 1.24,
"learning_rate": 3.183523101047513e-05,
"loss": 0.3168,
"step": 1155
},
{
"epoch": 1.24,
"learning_rate": 3.170031475218393e-05,
"loss": 0.2956,
"step": 1160
},
{
"epoch": 1.25,
"learning_rate": 3.1565187923377746e-05,
"loss": 0.3462,
"step": 1165
},
{
"epoch": 1.25,
"learning_rate": 3.142985477068185e-05,
"loss": 0.3532,
"step": 1170
},
{
"epoch": 1.26,
"learning_rate": 3.129431954720565e-05,
"loss": 0.3928,
"step": 1175
},
{
"epoch": 1.26,
"learning_rate": 3.1158586512409e-05,
"loss": 0.4801,
"step": 1180
},
{
"epoch": 1.27,
"learning_rate": 3.1022659931968395e-05,
"loss": 0.4299,
"step": 1185
},
{
"epoch": 1.27,
"learning_rate": 3.0886544077642865e-05,
"loss": 0.4258,
"step": 1190
},
{
"epoch": 1.28,
"learning_rate": 3.075024322713972e-05,
"loss": 0.5112,
"step": 1195
},
{
"epoch": 1.28,
"learning_rate": 3.0613761663980184e-05,
"loss": 0.3401,
"step": 1200
},
{
"epoch": 1.29,
"learning_rate": 3.0477103677364694e-05,
"loss": 0.4322,
"step": 1205
},
{
"epoch": 1.3,
"learning_rate": 3.0340273562038146e-05,
"loss": 0.4011,
"step": 1210
},
{
"epoch": 1.3,
"learning_rate": 3.0203275618154935e-05,
"loss": 0.3879,
"step": 1215
},
{
"epoch": 1.31,
"learning_rate": 3.0066114151143775e-05,
"loss": 0.3586,
"step": 1220
},
{
"epoch": 1.31,
"learning_rate": 2.9928793471572432e-05,
"loss": 0.3994,
"step": 1225
},
{
"epoch": 1.32,
"learning_rate": 2.9791317895012234e-05,
"loss": 0.2322,
"step": 1230
},
{
"epoch": 1.32,
"learning_rate": 2.965369174190243e-05,
"loss": 0.3513,
"step": 1235
},
{
"epoch": 1.33,
"learning_rate": 2.9515919337414472e-05,
"loss": 0.307,
"step": 1240
},
{
"epoch": 1.33,
"learning_rate": 2.937800501131601e-05,
"loss": 0.3364,
"step": 1245
},
{
"epoch": 1.34,
"learning_rate": 2.9239953097834876e-05,
"loss": 0.3243,
"step": 1250
},
{
"epoch": 1.34,
"learning_rate": 2.910176793552287e-05,
"loss": 0.4326,
"step": 1255
},
{
"epoch": 1.35,
"learning_rate": 2.8963453867119354e-05,
"loss": 0.3193,
"step": 1260
},
{
"epoch": 1.35,
"learning_rate": 2.8825015239414856e-05,
"loss": 0.3131,
"step": 1265
},
{
"epoch": 1.36,
"learning_rate": 2.8686456403114415e-05,
"loss": 0.3406,
"step": 1270
},
{
"epoch": 1.37,
"learning_rate": 2.854778171270085e-05,
"loss": 0.3749,
"step": 1275
},
{
"epoch": 1.37,
"learning_rate": 2.8408995526297926e-05,
"loss": 0.334,
"step": 1280
},
{
"epoch": 1.38,
"learning_rate": 2.8270102205533406e-05,
"loss": 0.3929,
"step": 1285
},
{
"epoch": 1.38,
"learning_rate": 2.8131106115401933e-05,
"loss": 0.3972,
"step": 1290
},
{
"epoch": 1.39,
"learning_rate": 2.7992011624127888e-05,
"loss": 0.2296,
"step": 1295
},
{
"epoch": 1.39,
"learning_rate": 2.7852823103028116e-05,
"loss": 0.3938,
"step": 1300
},
{
"epoch": 1.4,
"learning_rate": 2.771354492637451e-05,
"loss": 0.3469,
"step": 1305
},
{
"epoch": 1.4,
"learning_rate": 2.7574181471256578e-05,
"loss": 0.3049,
"step": 1310
},
{
"epoch": 1.41,
"learning_rate": 2.743473711744387e-05,
"loss": 0.3872,
"step": 1315
},
{
"epoch": 1.41,
"learning_rate": 2.7295216247248327e-05,
"loss": 0.2893,
"step": 1320
},
{
"epoch": 1.42,
"learning_rate": 2.7155623245386584e-05,
"loss": 0.3781,
"step": 1325
},
{
"epoch": 1.42,
"learning_rate": 2.701596249884214e-05,
"loss": 0.3755,
"step": 1330
},
{
"epoch": 1.43,
"learning_rate": 2.6876238396727504e-05,
"loss": 0.2317,
"step": 1335
},
{
"epoch": 1.43,
"learning_rate": 2.6736455330146278e-05,
"loss": 0.5266,
"step": 1340
},
{
"epoch": 1.44,
"learning_rate": 2.6596617692055105e-05,
"loss": 0.367,
"step": 1345
},
{
"epoch": 1.45,
"learning_rate": 2.6456729877125663e-05,
"loss": 0.3744,
"step": 1350
},
{
"epoch": 1.45,
"learning_rate": 2.631679628160655e-05,
"loss": 0.4376,
"step": 1355
},
{
"epoch": 1.46,
"learning_rate": 2.6176821303185066e-05,
"loss": 0.4219,
"step": 1360
},
{
"epoch": 1.46,
"learning_rate": 2.6036809340849106e-05,
"loss": 0.2541,
"step": 1365
},
{
"epoch": 1.47,
"learning_rate": 2.5896764794748813e-05,
"loss": 0.3705,
"step": 1370
},
{
"epoch": 1.47,
"learning_rate": 2.5756692066058346e-05,
"loss": 0.4607,
"step": 1375
},
{
"epoch": 1.48,
"learning_rate": 2.5616595556837573e-05,
"loss": 0.5631,
"step": 1380
},
{
"epoch": 1.48,
"learning_rate": 2.547647966989371e-05,
"loss": 0.5518,
"step": 1385
},
{
"epoch": 1.49,
"learning_rate": 2.533634880864293e-05,
"loss": 0.3245,
"step": 1390
},
{
"epoch": 1.49,
"learning_rate": 2.519620737697204e-05,
"loss": 0.3764,
"step": 1395
},
{
"epoch": 1.5,
"learning_rate": 2.5056059779100017e-05,
"loss": 0.3896,
"step": 1400
},
{
"epoch": 1.5,
"learning_rate": 2.4915910419439627e-05,
"loss": 0.2681,
"step": 1405
},
{
"epoch": 1.51,
"learning_rate": 2.4775763702459026e-05,
"loss": 0.3076,
"step": 1410
},
{
"epoch": 1.51,
"learning_rate": 2.463562403254327e-05,
"loss": 0.4762,
"step": 1415
},
{
"epoch": 1.52,
"learning_rate": 2.4495495813855994e-05,
"loss": 0.3402,
"step": 1420
},
{
"epoch": 1.53,
"learning_rate": 2.4355383450200957e-05,
"loss": 0.3426,
"step": 1425
},
{
"epoch": 1.53,
"learning_rate": 2.421529134488359e-05,
"loss": 0.323,
"step": 1430
},
{
"epoch": 1.54,
"learning_rate": 2.407522390057272e-05,
"loss": 0.2517,
"step": 1435
},
{
"epoch": 1.54,
"learning_rate": 2.3935185519162133e-05,
"loss": 0.2985,
"step": 1440
},
{
"epoch": 1.55,
"learning_rate": 2.3795180601632257e-05,
"loss": 0.377,
"step": 1445
},
{
"epoch": 1.55,
"learning_rate": 2.3655213547911846e-05,
"loss": 0.3976,
"step": 1450
},
{
"epoch": 1.56,
"learning_rate": 2.3515288756739732e-05,
"loss": 0.5024,
"step": 1455
},
{
"epoch": 1.56,
"learning_rate": 2.3375410625526527e-05,
"loss": 0.3413,
"step": 1460
},
{
"epoch": 1.57,
"learning_rate": 2.3235583550216507e-05,
"loss": 0.2962,
"step": 1465
},
{
"epoch": 1.57,
"learning_rate": 2.309581192514937e-05,
"loss": 0.3109,
"step": 1470
},
{
"epoch": 1.58,
"learning_rate": 2.295610014292221e-05,
"loss": 0.313,
"step": 1475
},
{
"epoch": 1.58,
"learning_rate": 2.2816452594251454e-05,
"loss": 0.4659,
"step": 1480
},
{
"epoch": 1.59,
"learning_rate": 2.2676873667834822e-05,
"loss": 0.3142,
"step": 1485
},
{
"epoch": 1.6,
"learning_rate": 2.253736775021349e-05,
"loss": 0.4029,
"step": 1490
},
{
"epoch": 1.6,
"learning_rate": 2.239793922563415e-05,
"loss": 0.4598,
"step": 1495
},
{
"epoch": 1.61,
"learning_rate": 2.22585924759113e-05,
"loss": 0.3665,
"step": 1500
},
{
"epoch": 1.61,
"learning_rate": 2.2119331880289482e-05,
"loss": 0.3814,
"step": 1505
},
{
"epoch": 1.62,
"learning_rate": 2.1980161815305685e-05,
"loss": 0.3147,
"step": 1510
},
{
"epoch": 1.62,
"learning_rate": 2.1841086654651787e-05,
"loss": 0.4053,
"step": 1515
},
{
"epoch": 1.63,
"learning_rate": 2.1702110769037138e-05,
"loss": 0.3571,
"step": 1520
},
{
"epoch": 1.63,
"learning_rate": 2.1563238526051128e-05,
"loss": 0.4268,
"step": 1525
},
{
"epoch": 1.64,
"learning_rate": 2.1424474290026002e-05,
"loss": 0.2449,
"step": 1530
},
{
"epoch": 1.64,
"learning_rate": 2.128582242189971e-05,
"loss": 0.3293,
"step": 1535
},
{
"epoch": 1.65,
"learning_rate": 2.114728727907875e-05,
"loss": 0.3671,
"step": 1540
},
{
"epoch": 1.65,
"learning_rate": 2.1008873215301346e-05,
"loss": 0.3639,
"step": 1545
},
{
"epoch": 1.66,
"learning_rate": 2.0870584580500555e-05,
"loss": 0.328,
"step": 1550
},
{
"epoch": 1.66,
"learning_rate": 2.0732425720667605e-05,
"loss": 0.3223,
"step": 1555
},
{
"epoch": 1.67,
"learning_rate": 2.0594400977715268e-05,
"loss": 0.4182,
"step": 1560
},
{
"epoch": 1.68,
"learning_rate": 2.045651468934145e-05,
"loss": 0.4449,
"step": 1565
},
{
"epoch": 1.68,
"learning_rate": 2.0318771188892823e-05,
"loss": 0.368,
"step": 1570
},
{
"epoch": 1.69,
"learning_rate": 2.018117480522871e-05,
"loss": 0.237,
"step": 1575
},
{
"epoch": 1.69,
"learning_rate": 2.0043729862584952e-05,
"loss": 0.2892,
"step": 1580
},
{
"epoch": 1.7,
"learning_rate": 1.99064406804381e-05,
"loss": 0.3522,
"step": 1585
},
{
"epoch": 1.7,
"learning_rate": 1.9769311573369613e-05,
"loss": 0.4601,
"step": 1590
},
{
"epoch": 1.71,
"learning_rate": 1.9632346850930265e-05,
"loss": 0.3318,
"step": 1595
},
{
"epoch": 1.71,
"learning_rate": 1.9495550817504742e-05,
"loss": 0.3333,
"step": 1600
},
{
"epoch": 1.72,
"learning_rate": 1.935892777217633e-05,
"loss": 0.3585,
"step": 1605
},
{
"epoch": 1.72,
"learning_rate": 1.922248200859183e-05,
"loss": 0.2718,
"step": 1610
},
{
"epoch": 1.73,
"learning_rate": 1.908621781482662e-05,
"loss": 0.2824,
"step": 1615
},
{
"epoch": 1.73,
"learning_rate": 1.89501394732499e-05,
"loss": 0.2374,
"step": 1620
},
{
"epoch": 1.74,
"learning_rate": 1.8814251260390067e-05,
"loss": 0.3704,
"step": 1625
},
{
"epoch": 1.75,
"learning_rate": 1.8678557446800403e-05,
"loss": 0.3356,
"step": 1630
},
{
"epoch": 1.75,
"learning_rate": 1.854306229692476e-05,
"loss": 0.295,
"step": 1635
},
{
"epoch": 1.76,
"learning_rate": 1.8407770068963615e-05,
"loss": 0.3668,
"step": 1640
},
{
"epoch": 1.76,
"learning_rate": 1.8272685014740258e-05,
"loss": 0.3668,
"step": 1645
},
{
"epoch": 1.77,
"learning_rate": 1.8137811379567076e-05,
"loss": 0.2927,
"step": 1650
},
{
"epoch": 1.77,
"learning_rate": 1.8003153402112248e-05,
"loss": 0.3767,
"step": 1655
},
{
"epoch": 1.78,
"learning_rate": 1.7868715314266464e-05,
"loss": 0.3051,
"step": 1660
},
{
"epoch": 1.78,
"learning_rate": 1.773450134100997e-05,
"loss": 0.2894,
"step": 1665
},
{
"epoch": 1.79,
"learning_rate": 1.760051570027974e-05,
"loss": 0.329,
"step": 1670
},
{
"epoch": 1.79,
"learning_rate": 1.746676260283699e-05,
"loss": 0.3993,
"step": 1675
},
{
"epoch": 1.8,
"learning_rate": 1.7333246252134767e-05,
"loss": 0.2806,
"step": 1680
},
{
"epoch": 1.8,
"learning_rate": 1.7199970844185943e-05,
"loss": 0.359,
"step": 1685
},
{
"epoch": 1.81,
"learning_rate": 1.706694056743122e-05,
"loss": 0.2649,
"step": 1690
},
{
"epoch": 1.81,
"learning_rate": 1.693415960260764e-05,
"loss": 0.3227,
"step": 1695
},
{
"epoch": 1.82,
"learning_rate": 1.6801632122617095e-05,
"loss": 0.2917,
"step": 1700
},
{
"epoch": 1.83,
"learning_rate": 1.6669362292395214e-05,
"loss": 0.4163,
"step": 1705
},
{
"epoch": 1.83,
"learning_rate": 1.6537354268780498e-05,
"loss": 0.4411,
"step": 1710
},
{
"epoch": 1.84,
"learning_rate": 1.6405612200383645e-05,
"loss": 0.2494,
"step": 1715
},
{
"epoch": 1.84,
"learning_rate": 1.6274140227457213e-05,
"loss": 0.5221,
"step": 1720
},
{
"epoch": 1.85,
"learning_rate": 1.6142942481765448e-05,
"loss": 0.3146,
"step": 1725
},
{
"epoch": 1.85,
"learning_rate": 1.6012023086454503e-05,
"loss": 0.3994,
"step": 1730
},
{
"epoch": 1.86,
"learning_rate": 1.588138615592278e-05,
"loss": 0.2006,
"step": 1735
},
{
"epoch": 1.86,
"learning_rate": 1.5751035795691727e-05,
"loss": 0.5552,
"step": 1740
},
{
"epoch": 1.87,
"learning_rate": 1.5620976102276714e-05,
"loss": 0.3602,
"step": 1745
},
{
"epoch": 1.87,
"learning_rate": 1.5491211163058357e-05,
"loss": 0.2798,
"step": 1750
},
{
"epoch": 1.88,
"learning_rate": 1.5361745056154048e-05,
"loss": 0.2709,
"step": 1755
},
{
"epoch": 1.88,
"learning_rate": 1.523258185028977e-05,
"loss": 0.3803,
"step": 1760
},
{
"epoch": 1.89,
"learning_rate": 1.5103725604672275e-05,
"loss": 0.2861,
"step": 1765
},
{
"epoch": 1.9,
"learning_rate": 1.4975180368861458e-05,
"loss": 0.3521,
"step": 1770
},
{
"epoch": 1.9,
"learning_rate": 1.4846950182643143e-05,
"loss": 0.3457,
"step": 1775
},
{
"epoch": 1.91,
"learning_rate": 1.4719039075902091e-05,
"loss": 0.333,
"step": 1780
},
{
"epoch": 1.91,
"learning_rate": 1.4591451068495382e-05,
"loss": 0.2831,
"step": 1785
},
{
"epoch": 1.92,
"learning_rate": 1.4464190170126034e-05,
"loss": 0.3263,
"step": 1790
},
{
"epoch": 1.92,
"learning_rate": 1.433726038021707e-05,
"loss": 0.301,
"step": 1795
},
{
"epoch": 1.93,
"learning_rate": 1.4210665687785734e-05,
"loss": 0.2941,
"step": 1800
},
{
"epoch": 1.93,
"learning_rate": 1.4084410071318201e-05,
"loss": 0.2209,
"step": 1805
},
{
"epoch": 1.94,
"learning_rate": 1.3958497498644529e-05,
"loss": 0.4193,
"step": 1810
},
{
"epoch": 1.94,
"learning_rate": 1.3832931926813907e-05,
"loss": 0.302,
"step": 1815
},
{
"epoch": 1.95,
"learning_rate": 1.3707717301970416e-05,
"loss": 0.3154,
"step": 1820
},
{
"epoch": 1.95,
"learning_rate": 1.3582857559228867e-05,
"loss": 0.548,
"step": 1825
},
{
"epoch": 1.96,
"learning_rate": 1.345835662255126e-05,
"loss": 0.2957,
"step": 1830
},
{
"epoch": 1.96,
"learning_rate": 1.3334218404623373e-05,
"loss": 0.2932,
"step": 1835
},
{
"epoch": 1.97,
"learning_rate": 1.3210446806731857e-05,
"loss": 0.3821,
"step": 1840
},
{
"epoch": 1.98,
"learning_rate": 1.308704571864161e-05,
"loss": 0.3919,
"step": 1845
},
{
"epoch": 1.98,
"learning_rate": 1.2964019018473545e-05,
"loss": 0.2465,
"step": 1850
},
{
"epoch": 1.99,
"learning_rate": 1.2841370572582661e-05,
"loss": 0.4155,
"step": 1855
},
{
"epoch": 1.99,
"learning_rate": 1.2719104235436613e-05,
"loss": 0.379,
"step": 1860
},
{
"epoch": 2.0,
"learning_rate": 1.2597223849494538e-05,
"loss": 0.304,
"step": 1865
},
{
"epoch": 2.0,
"learning_rate": 1.2475733245086263e-05,
"loss": 0.3512,
"step": 1870
},
{
"epoch": 2.01,
"learning_rate": 1.2354636240292031e-05,
"loss": 0.1898,
"step": 1875
},
{
"epoch": 2.01,
"learning_rate": 1.2233936640822385e-05,
"loss": 0.1608,
"step": 1880
},
{
"epoch": 2.02,
"learning_rate": 1.211363823989867e-05,
"loss": 0.1453,
"step": 1885
},
{
"epoch": 2.02,
"learning_rate": 1.1993744818133742e-05,
"loss": 0.1639,
"step": 1890
},
{
"epoch": 2.03,
"learning_rate": 1.187426014341323e-05,
"loss": 0.1394,
"step": 1895
},
{
"epoch": 2.03,
"learning_rate": 1.1755187970777065e-05,
"loss": 0.1596,
"step": 1900
},
{
"epoch": 2.04,
"learning_rate": 1.1636532042301512e-05,
"loss": 0.1185,
"step": 1905
},
{
"epoch": 2.04,
"learning_rate": 1.1518296086981514e-05,
"loss": 0.1359,
"step": 1910
},
{
"epoch": 2.05,
"learning_rate": 1.1400483820613563e-05,
"loss": 0.1435,
"step": 1915
},
{
"epoch": 2.06,
"learning_rate": 1.1283098945678902e-05,
"loss": 0.1491,
"step": 1920
},
{
"epoch": 2.06,
"learning_rate": 1.1166145151227117e-05,
"loss": 0.1697,
"step": 1925
},
{
"epoch": 2.07,
"learning_rate": 1.1049626112760314e-05,
"loss": 0.1224,
"step": 1930
},
{
"epoch": 2.07,
"learning_rate": 1.0933545492117473e-05,
"loss": 0.1467,
"step": 1935
},
{
"epoch": 2.08,
"learning_rate": 1.0817906937359482e-05,
"loss": 0.1813,
"step": 1940
},
{
"epoch": 2.08,
"learning_rate": 1.070271408265441e-05,
"loss": 0.1128,
"step": 1945
},
{
"epoch": 2.09,
"learning_rate": 1.058797054816335e-05,
"loss": 0.1896,
"step": 1950
},
{
"epoch": 2.09,
"learning_rate": 1.0473679939926626e-05,
"loss": 0.1205,
"step": 1955
},
{
"epoch": 2.1,
"learning_rate": 1.0359845849750466e-05,
"loss": 0.1581,
"step": 1960
},
{
"epoch": 2.1,
"learning_rate": 1.0246471855094106e-05,
"loss": 0.1542,
"step": 1965
},
{
"epoch": 2.11,
"learning_rate": 1.0133561518957402e-05,
"loss": 0.1542,
"step": 1970
},
{
"epoch": 2.11,
"learning_rate": 1.0021118389768833e-05,
"loss": 0.0885,
"step": 1975
},
{
"epoch": 2.12,
"learning_rate": 9.909146001273947e-06,
"loss": 0.109,
"step": 1980
},
{
"epoch": 2.13,
"learning_rate": 9.797647872424413e-06,
"loss": 0.1327,
"step": 1985
},
{
"epoch": 2.13,
"learning_rate": 9.686627507267287e-06,
"loss": 0.1584,
"step": 1990
},
{
"epoch": 2.14,
"learning_rate": 9.576088394835023e-06,
"loss": 0.2896,
"step": 1995
},
{
"epoch": 2.14,
"learning_rate": 9.466034009035724e-06,
"loss": 0.2332,
"step": 2000
},
{
"epoch": 2.15,
"learning_rate": 9.356467808544033e-06,
"loss": 0.1039,
"step": 2005
},
{
"epoch": 2.15,
"learning_rate": 9.247393236692412e-06,
"loss": 0.1014,
"step": 2010
},
{
"epoch": 2.16,
"learning_rate": 9.13881372136293e-06,
"loss": 0.0737,
"step": 2015
},
{
"epoch": 2.16,
"learning_rate": 9.030732674879514e-06,
"loss": 0.1649,
"step": 2020
},
{
"epoch": 2.17,
"learning_rate": 8.923153493900757e-06,
"loss": 0.1502,
"step": 2025
},
{
"epoch": 2.17,
"learning_rate": 8.816079559313147e-06,
"loss": 0.2198,
"step": 2030
},
{
"epoch": 2.18,
"learning_rate": 8.709514236124783e-06,
"loss": 0.2312,
"step": 2035
},
{
"epoch": 2.18,
"learning_rate": 8.603460873359687e-06,
"loss": 0.1627,
"step": 2040
},
{
"epoch": 2.19,
"learning_rate": 8.49792280395251e-06,
"loss": 0.0986,
"step": 2045
},
{
"epoch": 2.19,
"learning_rate": 8.392903344643807e-06,
"loss": 0.1889,
"step": 2050
},
{
"epoch": 2.2,
"learning_rate": 8.288405795875773e-06,
"loss": 0.1543,
"step": 2055
},
{
"epoch": 2.21,
"learning_rate": 8.184433441688564e-06,
"loss": 0.0997,
"step": 2060
},
{
"epoch": 2.21,
"learning_rate": 8.08098954961706e-06,
"loss": 0.1241,
"step": 2065
},
{
"epoch": 2.22,
"learning_rate": 7.978077370588196e-06,
"loss": 0.1259,
"step": 2070
},
{
"epoch": 2.22,
"learning_rate": 7.875700138818756e-06,
"loss": 0.1803,
"step": 2075
},
{
"epoch": 2.23,
"learning_rate": 7.773861071713779e-06,
"loss": 0.1437,
"step": 2080
},
{
"epoch": 2.23,
"learning_rate": 7.672563369765429e-06,
"loss": 0.131,
"step": 2085
},
{
"epoch": 2.24,
"learning_rate": 7.571810216452388e-06,
"loss": 0.193,
"step": 2090
},
{
"epoch": 2.24,
"learning_rate": 7.4716047781398485e-06,
"loss": 0.1658,
"step": 2095
},
{
"epoch": 2.25,
"learning_rate": 7.3719502039799856e-06,
"loss": 0.1377,
"step": 2100
},
{
"epoch": 2.25,
"learning_rate": 7.2728496258129915e-06,
"loss": 0.1433,
"step": 2105
},
{
"epoch": 2.26,
"learning_rate": 7.174306158068625e-06,
"loss": 0.1309,
"step": 2110
},
{
"epoch": 2.26,
"learning_rate": 7.0763228976683885e-06,
"loss": 0.149,
"step": 2115
},
{
"epoch": 2.27,
"learning_rate": 6.9789029239281574e-06,
"loss": 0.1573,
"step": 2120
},
{
"epoch": 2.28,
"learning_rate": 6.8820492984614324e-06,
"loss": 0.1268,
"step": 2125
},
{
"epoch": 2.28,
"learning_rate": 6.785765065083083e-06,
"loss": 0.0947,
"step": 2130
},
{
"epoch": 2.29,
"learning_rate": 6.690053249713743e-06,
"loss": 0.1492,
"step": 2135
},
{
"epoch": 2.29,
"learning_rate": 6.594916860284692e-06,
"loss": 0.1955,
"step": 2140
},
{
"epoch": 2.3,
"learning_rate": 6.50035888664329e-06,
"loss": 0.1137,
"step": 2145
},
{
"epoch": 2.3,
"learning_rate": 6.406382300459079e-06,
"loss": 0.1055,
"step": 2150
},
{
"epoch": 2.31,
"learning_rate": 6.312990055130355e-06,
"loss": 0.1119,
"step": 2155
},
{
"epoch": 2.31,
"learning_rate": 6.22018508569136e-06,
"loss": 0.1138,
"step": 2160
},
{
"epoch": 2.32,
"learning_rate": 6.1279703087200186e-06,
"loss": 0.1401,
"step": 2165
},
{
"epoch": 2.32,
"learning_rate": 6.036348622246327e-06,
"loss": 0.1442,
"step": 2170
},
{
"epoch": 2.33,
"learning_rate": 5.945322905661244e-06,
"loss": 0.115,
"step": 2175
},
{
"epoch": 2.33,
"learning_rate": 5.854896019626208e-06,
"loss": 0.1394,
"step": 2180
},
{
"epoch": 2.34,
"learning_rate": 5.765070805983219e-06,
"loss": 0.1419,
"step": 2185
},
{
"epoch": 2.34,
"learning_rate": 5.675850087665563e-06,
"loss": 0.1352,
"step": 2190
},
{
"epoch": 2.35,
"learning_rate": 5.58723666860908e-06,
"loss": 0.1157,
"step": 2195
},
{
"epoch": 2.36,
"learning_rate": 5.4992333336640115e-06,
"loss": 0.1597,
"step": 2200
},
{
"epoch": 2.36,
"learning_rate": 5.411842848507542e-06,
"loss": 0.1668,
"step": 2205
},
{
"epoch": 2.37,
"learning_rate": 5.325067959556834e-06,
"loss": 0.106,
"step": 2210
},
{
"epoch": 2.37,
"learning_rate": 5.238911393882751e-06,
"loss": 0.1626,
"step": 2215
},
{
"epoch": 2.38,
"learning_rate": 5.1533758591241075e-06,
"loss": 0.1001,
"step": 2220
},
{
"epoch": 2.38,
"learning_rate": 5.068464043402632e-06,
"loss": 0.1199,
"step": 2225
},
{
"epoch": 2.39,
"learning_rate": 4.984178615238436e-06,
"loss": 0.1118,
"step": 2230
},
{
"epoch": 2.39,
"learning_rate": 4.900522223466208e-06,
"loss": 0.2024,
"step": 2235
},
{
"epoch": 2.4,
"learning_rate": 4.8174974971519075e-06,
"loss": 0.0992,
"step": 2240
},
{
"epoch": 2.4,
"learning_rate": 4.735107045510179e-06,
"loss": 0.0686,
"step": 2245
},
{
"epoch": 2.41,
"learning_rate": 4.653353457822349e-06,
"loss": 0.2271,
"step": 2250
},
{
"epoch": 2.41,
"learning_rate": 4.572239303355033e-06,
"loss": 0.1831,
"step": 2255
},
{
"epoch": 2.42,
"learning_rate": 4.491767131279414e-06,
"loss": 0.1541,
"step": 2260
},
{
"epoch": 2.43,
"learning_rate": 4.411939470591125e-06,
"loss": 0.2611,
"step": 2265
},
{
"epoch": 2.43,
"learning_rate": 4.332758830030767e-06,
"loss": 0.1216,
"step": 2270
},
{
"epoch": 2.44,
"learning_rate": 4.254227698005048e-06,
"loss": 0.112,
"step": 2275
},
{
"epoch": 2.44,
"learning_rate": 4.176348542508621e-06,
"loss": 0.1712,
"step": 2280
},
{
"epoch": 2.45,
"learning_rate": 4.099123811046471e-06,
"loss": 0.1919,
"step": 2285
},
{
"epoch": 2.45,
"learning_rate": 4.0225559305570676e-06,
"loss": 0.1018,
"step": 2290
},
{
"epoch": 2.46,
"learning_rate": 3.946647307336013e-06,
"loss": 0.1054,
"step": 2295
},
{
"epoch": 2.46,
"learning_rate": 3.871400326960481e-06,
"loss": 0.1212,
"step": 2300
},
{
"epoch": 2.47,
"learning_rate": 3.7968173542142187e-06,
"loss": 0.1063,
"step": 2305
},
{
"epoch": 2.47,
"learning_rate": 3.722900733013221e-06,
"loss": 0.1183,
"step": 2310
},
{
"epoch": 2.48,
"learning_rate": 3.6496527863320916e-06,
"loss": 0.3089,
"step": 2315
},
{
"epoch": 2.48,
"learning_rate": 3.5770758161310288e-06,
"loss": 0.1188,
"step": 2320
},
{
"epoch": 2.49,
"learning_rate": 3.505172103283483e-06,
"loss": 0.1374,
"step": 2325
},
{
"epoch": 2.49,
"learning_rate": 3.4339439075044555e-06,
"loss": 0.2563,
"step": 2330
},
{
"epoch": 2.5,
"learning_rate": 3.3633934672795242e-06,
"loss": 0.0739,
"step": 2335
},
{
"epoch": 2.51,
"learning_rate": 3.293522999794443e-06,
"loss": 0.1082,
"step": 2340
},
{
"epoch": 2.51,
"learning_rate": 3.2243347008655333e-06,
"loss": 0.1598,
"step": 2345
},
{
"epoch": 2.52,
"learning_rate": 3.1558307448705886e-06,
"loss": 0.1337,
"step": 2350
},
{
"epoch": 2.52,
"learning_rate": 3.0880132846806103e-06,
"loss": 0.1227,
"step": 2355
},
{
"epoch": 2.53,
"learning_rate": 3.020884451592126e-06,
"loss": 0.1446,
"step": 2360
},
{
"epoch": 2.53,
"learning_rate": 2.9544463552601875e-06,
"loss": 0.1262,
"step": 2365
},
{
"epoch": 2.54,
"learning_rate": 2.8887010836321087e-06,
"loss": 0.131,
"step": 2370
},
{
"epoch": 2.54,
"learning_rate": 2.8236507028818306e-06,
"loss": 0.3064,
"step": 2375
},
{
"epoch": 2.55,
"learning_rate": 2.759297257344981e-06,
"loss": 0.1329,
"step": 2380
},
{
"epoch": 2.55,
"learning_rate": 2.695642769454629e-06,
"loss": 0.1269,
"step": 2385
},
{
"epoch": 2.56,
"learning_rate": 2.6326892396777465e-06,
"loss": 0.1515,
"step": 2390
},
{
"epoch": 2.56,
"learning_rate": 2.5704386464522946e-06,
"loss": 0.1497,
"step": 2395
},
{
"epoch": 2.57,
"learning_rate": 2.508892946125119e-06,
"loss": 0.1247,
"step": 2400
},
{
"epoch": 2.57,
"learning_rate": 2.4480540728903876e-06,
"loss": 0.1079,
"step": 2405
},
{
"epoch": 2.58,
"learning_rate": 2.3879239387288615e-06,
"loss": 0.0815,
"step": 2410
},
{
"epoch": 2.59,
"learning_rate": 2.3285044333477834e-06,
"loss": 0.0905,
"step": 2415
},
{
"epoch": 2.59,
"learning_rate": 2.269797424121492e-06,
"loss": 0.1124,
"step": 2420
},
{
"epoch": 2.6,
"learning_rate": 2.2118047560327425e-06,
"loss": 0.1781,
"step": 2425
},
{
"epoch": 2.6,
"learning_rate": 2.154528251614721e-06,
"loss": 0.2224,
"step": 2430
},
{
"epoch": 2.61,
"learning_rate": 2.0979697108937685e-06,
"loss": 0.1721,
"step": 2435
},
{
"epoch": 2.61,
"learning_rate": 2.0421309113328042e-06,
"loss": 0.1502,
"step": 2440
},
{
"epoch": 2.62,
"learning_rate": 1.9870136077754787e-06,
"loss": 0.1646,
"step": 2445
},
{
"epoch": 2.62,
"learning_rate": 1.9326195323910082e-06,
"loss": 0.1088,
"step": 2450
},
{
"epoch": 2.63,
"learning_rate": 1.8789503946197579e-06,
"loss": 0.1143,
"step": 2455
},
{
"epoch": 2.63,
"learning_rate": 1.8260078811195041e-06,
"loss": 0.1692,
"step": 2460
},
{
"epoch": 2.64,
"learning_rate": 1.7737936557124301e-06,
"loss": 0.1727,
"step": 2465
},
{
"epoch": 2.64,
"learning_rate": 1.7223093593328494e-06,
"loss": 0.0885,
"step": 2470
},
{
"epoch": 2.65,
"learning_rate": 1.6715566099756024e-06,
"loss": 0.0786,
"step": 2475
},
{
"epoch": 2.66,
"learning_rate": 1.6215370026452598e-06,
"loss": 0.1128,
"step": 2480
},
{
"epoch": 2.66,
"learning_rate": 1.5722521093059496e-06,
"loss": 0.1089,
"step": 2485
},
{
"epoch": 2.67,
"learning_rate": 1.5237034788319837e-06,
"loss": 0.1772,
"step": 2490
},
{
"epoch": 2.67,
"learning_rate": 1.4758926369591614e-06,
"loss": 0.1795,
"step": 2495
},
{
"epoch": 2.68,
"learning_rate": 1.4288210862368395e-06,
"loss": 0.1264,
"step": 2500
},
{
"epoch": 2.68,
"learning_rate": 1.3824903059806937e-06,
"loss": 0.1129,
"step": 2505
},
{
"epoch": 2.69,
"learning_rate": 1.3369017522262438e-06,
"loss": 0.0854,
"step": 2510
},
{
"epoch": 2.69,
"learning_rate": 1.2920568576830882e-06,
"loss": 0.0878,
"step": 2515
},
{
"epoch": 2.7,
"learning_rate": 1.2479570316898726e-06,
"loss": 0.1346,
"step": 2520
},
{
"epoch": 2.7,
"learning_rate": 1.2046036601700146e-06,
"loss": 0.1298,
"step": 2525
},
{
"epoch": 2.71,
"learning_rate": 1.1619981055881162e-06,
"loss": 0.1598,
"step": 2530
},
{
"epoch": 2.71,
"learning_rate": 1.1201417069071934e-06,
"loss": 0.1295,
"step": 2535
},
{
"epoch": 2.72,
"learning_rate": 1.0790357795465527e-06,
"loss": 0.127,
"step": 2540
},
{
"epoch": 2.72,
"learning_rate": 1.038681615340481e-06,
"loss": 0.1714,
"step": 2545
},
{
"epoch": 2.73,
"learning_rate": 9.99080482497622e-07,
"loss": 0.1494,
"step": 2550
},
{
"epoch": 2.74,
"learning_rate": 9.602336255611522e-07,
"loss": 0.0671,
"step": 2555
},
{
"epoch": 2.74,
"learning_rate": 9.221422653696299e-07,
"loss": 0.1641,
"step": 2560
},
{
"epoch": 2.75,
"learning_rate": 8.848075990186639e-07,
"loss": 0.1617,
"step": 2565
},
{
"epoch": 2.75,
"learning_rate": 8.482307998232686e-07,
"loss": 0.1436,
"step": 2570
},
{
"epoch": 2.76,
"learning_rate": 8.12413017281008e-07,
"loss": 0.1328,
"step": 2575
},
{
"epoch": 2.76,
"learning_rate": 7.773553770358488e-07,
"loss": 0.1612,
"step": 2580
},
{
"epoch": 2.77,
"learning_rate": 7.430589808428062e-07,
"loss": 0.141,
"step": 2585
},
{
"epoch": 2.77,
"learning_rate": 7.095249065333016e-07,
"loss": 0.1324,
"step": 2590
},
{
"epoch": 2.78,
"learning_rate": 6.767542079813089e-07,
"loss": 0.2075,
"step": 2595
},
{
"epoch": 2.78,
"learning_rate": 6.447479150702207e-07,
"loss": 0.1804,
"step": 2600
},
{
"epoch": 2.79,
"learning_rate": 6.135070336604737e-07,
"loss": 0.184,
"step": 2605
},
{
"epoch": 2.79,
"learning_rate": 5.830325455579627e-07,
"loss": 0.2522,
"step": 2610
},
{
"epoch": 2.8,
"learning_rate": 5.533254084831657e-07,
"loss": 0.1122,
"step": 2615
},
{
"epoch": 2.81,
"learning_rate": 5.24386556041051e-07,
"loss": 0.1075,
"step": 2620
},
{
"epoch": 2.81,
"learning_rate": 4.962168976917397e-07,
"loss": 0.1535,
"step": 2625
},
{
"epoch": 2.82,
"learning_rate": 4.688173187219258e-07,
"loss": 0.1201,
"step": 2630
},
{
"epoch": 2.82,
"learning_rate": 4.4218868021703996e-07,
"loss": 0.0932,
"step": 2635
},
{
"epoch": 2.83,
"learning_rate": 4.163318190342075e-07,
"loss": 0.1969,
"step": 2640
},
{
"epoch": 2.83,
"learning_rate": 3.912475477759386e-07,
"loss": 0.1997,
"step": 2645
},
{
"epoch": 2.84,
"learning_rate": 3.6693665476458526e-07,
"loss": 0.1271,
"step": 2650
},
{
"epoch": 2.84,
"learning_rate": 3.433999040175828e-07,
"loss": 0.166,
"step": 2655
},
{
"epoch": 2.85,
"learning_rate": 3.206380352234195e-07,
"loss": 0.1474,
"step": 2660
},
{
"epoch": 2.85,
"learning_rate": 2.986517637184133e-07,
"loss": 0.1127,
"step": 2665
},
{
"epoch": 2.86,
"learning_rate": 2.774417804642021e-07,
"loss": 0.1357,
"step": 2670
},
{
"epoch": 2.86,
"learning_rate": 2.570087520260611e-07,
"loss": 0.0642,
"step": 2675
},
{
"epoch": 2.87,
"learning_rate": 2.3735332055192515e-07,
"loss": 0.111,
"step": 2680
},
{
"epoch": 2.87,
"learning_rate": 2.184761037522326e-07,
"loss": 0.1453,
"step": 2685
},
{
"epoch": 2.88,
"learning_rate": 2.0037769488049363e-07,
"loss": 0.2098,
"step": 2690
},
{
"epoch": 2.89,
"learning_rate": 1.8305866271465521e-07,
"loss": 0.1603,
"step": 2695
},
{
"epoch": 2.89,
"learning_rate": 1.665195515392265e-07,
"loss": 0.1162,
"step": 2700
},
{
"epoch": 2.9,
"learning_rate": 1.50760881128173e-07,
"loss": 0.1069,
"step": 2705
},
{
"epoch": 2.9,
"learning_rate": 1.3578314672857972e-07,
"loss": 0.1596,
"step": 2710
},
{
"epoch": 2.91,
"learning_rate": 1.2158681904508306e-07,
"loss": 0.1448,
"step": 2715
},
{
"epoch": 2.91,
"learning_rate": 1.0817234422508815e-07,
"loss": 0.099,
"step": 2720
},
{
"epoch": 2.92,
"learning_rate": 9.554014384474119e-08,
"loss": 0.1657,
"step": 2725
},
{
"epoch": 2.92,
"learning_rate": 8.369061489568453e-08,
"loss": 0.1751,
"step": 2730
},
{
"epoch": 2.93,
"learning_rate": 7.262412977257215e-08,
"loss": 0.1825,
"step": 2735
},
{
"epoch": 2.93,
"learning_rate": 6.234103626137355e-08,
"loss": 0.2671,
"step": 2740
},
{
"epoch": 2.94,
"learning_rate": 5.284165752844905e-08,
"loss": 0.138,
"step": 2745
},
{
"epoch": 2.94,
"learning_rate": 4.412629211037744e-08,
"loss": 0.1538,
"step": 2750
},
{
"epoch": 2.95,
"learning_rate": 3.6195213904588465e-08,
"loss": 0.0941,
"step": 2755
},
{
"epoch": 2.96,
"learning_rate": 2.9048672160750246e-08,
"loss": 0.1369,
"step": 2760
},
{
"epoch": 2.96,
"learning_rate": 2.2686891472933903e-08,
"loss": 0.1327,
"step": 2765
},
{
"epoch": 2.97,
"learning_rate": 1.7110071772560853e-08,
"loss": 0.0837,
"step": 2770
},
{
"epoch": 2.97,
"learning_rate": 1.231838832211063e-08,
"loss": 0.2136,
"step": 2775
},
{
"epoch": 2.98,
"learning_rate": 8.311991709619716e-09,
"loss": 0.1371,
"step": 2780
},
{
"epoch": 2.98,
"learning_rate": 5.091007843954776e-09,
"loss": 0.1605,
"step": 2785
},
{
"epoch": 2.99,
"learning_rate": 2.655537950838061e-09,
"loss": 0.1396,
"step": 2790
},
{
"epoch": 2.99,
"learning_rate": 1.00565856968049e-09,
"loss": 0.0865,
"step": 2795
},
{
"epoch": 3.0,
"learning_rate": 1.414215511780226e-10,
"loss": 0.1582,
"step": 2800
},
{
"epoch": 3.0,
"step": 2802,
"total_flos": 9.781740939681792e+16,
"train_loss": 0.424075347293623,
"train_runtime": 2120.5143,
"train_samples_per_second": 3.964,
"train_steps_per_second": 1.321
}
],
"logging_steps": 5,
"max_steps": 2802,
"num_train_epochs": 3,
"save_steps": 5000,
"total_flos": 9.781740939681792e+16,
"trial_name": null,
"trial_params": null
}