{
  "best_metric": 0.4271390736103058,
  "best_model_checkpoint": "bart_lora_outputs\\checkpoint-3000",
  "epoch": 4.893964110929853,
  "eval_steps": 100,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 2.9281,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 4e-05,
      "loss": 2.8201,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 6e-05,
      "loss": 2.579,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 8e-05,
      "loss": 2.4427,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 2.1681,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012,
      "loss": 1.7104,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014000000000000001,
      "loss": 1.4177,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00016,
      "loss": 1.2515,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.1238,
      "step": 90
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.0489,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.8469381928443909,
      "eval_runtime": 5.9601,
      "eval_samples_per_second": 196.474,
      "eval_steps_per_second": 24.664,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00022,
      "loss": 1.0079,
      "step": 110
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00024,
      "loss": 1.0077,
      "step": 120
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00026000000000000003,
      "loss": 0.9416,
      "step": 130
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00028000000000000003,
      "loss": 0.8882,
      "step": 140
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.8595,
      "step": 150
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00032,
      "loss": 0.8853,
      "step": 160
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00034,
      "loss": 0.7678,
      "step": 170
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00035999999999999997,
      "loss": 0.8595,
      "step": 180
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00038,
      "loss": 0.8514,
      "step": 190
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0004,
      "loss": 0.8128,
      "step": 200
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.6850531697273254,
      "eval_runtime": 6.0279,
      "eval_samples_per_second": 194.264,
      "eval_steps_per_second": 24.387,
      "step": 200
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00042,
      "loss": 0.7782,
      "step": 210
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00044,
      "loss": 0.8064,
      "step": 220
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00046,
      "loss": 0.7627,
      "step": 230
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00048,
      "loss": 0.7447,
      "step": 240
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0005,
      "loss": 0.7652,
      "step": 250
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0005200000000000001,
      "loss": 0.7568,
      "step": 260
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00054,
      "loss": 0.7291,
      "step": 270
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0005600000000000001,
      "loss": 0.7118,
      "step": 280
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00058,
      "loss": 0.7462,
      "step": 290
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0006,
      "loss": 0.6866,
      "step": 300
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.629724383354187,
      "eval_runtime": 6.0378,
      "eval_samples_per_second": 193.943,
      "eval_steps_per_second": 24.346,
      "step": 300
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00062,
      "loss": 0.6995,
      "step": 310
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00064,
      "loss": 0.724,
      "step": 320
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00066,
      "loss": 0.6698,
      "step": 330
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00068,
      "loss": 0.6516,
      "step": 340
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0007,
      "loss": 0.6657,
      "step": 350
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0007199999999999999,
      "loss": 0.6765,
      "step": 360
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00074,
      "loss": 0.6596,
      "step": 370
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00076,
      "loss": 0.6884,
      "step": 380
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0007800000000000001,
      "loss": 0.647,
      "step": 390
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0008,
      "loss": 0.713,
      "step": 400
    },
    {
      "epoch": 0.65,
      "eval_loss": 0.5541791319847107,
      "eval_runtime": 6.0716,
      "eval_samples_per_second": 192.864,
      "eval_steps_per_second": 24.211,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00082,
      "loss": 0.6593,
      "step": 410
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00084,
      "loss": 0.62,
      "step": 420
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00086,
      "loss": 0.6912,
      "step": 430
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00088,
      "loss": 0.6407,
      "step": 440
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0009000000000000001,
      "loss": 0.6444,
      "step": 450
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00092,
      "loss": 0.6591,
      "step": 460
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00094,
      "loss": 0.6329,
      "step": 470
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00096,
      "loss": 0.6097,
      "step": 480
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00098,
      "loss": 0.6444,
      "step": 490
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.001,
      "loss": 0.6106,
      "step": 500
    },
    {
      "epoch": 0.82,
      "eval_loss": 0.5469470024108887,
      "eval_runtime": 6.1353,
      "eval_samples_per_second": 190.861,
      "eval_steps_per_second": 23.96,
      "step": 500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0009982238010657195,
      "loss": 0.6725,
      "step": 510
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0009964476021314388,
      "loss": 0.6612,
      "step": 520
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000994671403197158,
      "loss": 0.6202,
      "step": 530
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0009928952042628776,
      "loss": 0.6085,
      "step": 540
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0009911190053285969,
      "loss": 0.6023,
      "step": 550
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0009893428063943162,
      "loss": 0.6209,
      "step": 560
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0009875666074600357,
      "loss": 0.6128,
      "step": 570
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000985790408525755,
      "loss": 0.5971,
      "step": 580
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0009840142095914742,
      "loss": 0.6028,
      "step": 590
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0009822380106571937,
      "loss": 0.6105,
      "step": 600
    },
    {
      "epoch": 0.98,
      "eval_loss": 0.527148425579071,
      "eval_runtime": 6.0982,
      "eval_samples_per_second": 192.024,
      "eval_steps_per_second": 24.105,
      "step": 600
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.000980461811722913,
      "loss": 0.6101,
      "step": 610
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0009786856127886323,
      "loss": 0.5349,
      "step": 620
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0009769094138543518,
      "loss": 0.5903,
      "step": 630
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0009751332149200711,
      "loss": 0.6033,
      "step": 640
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0009733570159857904,
      "loss": 0.544,
      "step": 650
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0009715808170515098,
      "loss": 0.5582,
      "step": 660
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0009698046181172292,
      "loss": 0.5488,
      "step": 670
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0009680284191829485,
      "loss": 0.5799,
      "step": 680
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0009662522202486678,
      "loss": 0.5857,
      "step": 690
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0009644760213143872,
      "loss": 0.5857,
      "step": 700
    },
    {
      "epoch": 1.14,
      "eval_loss": 0.5239382982254028,
      "eval_runtime": 6.2471,
      "eval_samples_per_second": 187.448,
      "eval_steps_per_second": 23.531,
      "step": 700
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0009626998223801065,
      "loss": 0.5289,
      "step": 710
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0009609236234458259,
      "loss": 0.6082,
      "step": 720
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0009591474245115453,
      "loss": 0.5837,
      "step": 730
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0009573712255772646,
      "loss": 0.5571,
      "step": 740
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.000955595026642984,
      "loss": 0.5948,
      "step": 750
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0009538188277087034,
      "loss": 0.5455,
      "step": 760
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0009520426287744227,
      "loss": 0.5858,
      "step": 770
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0009502664298401421,
      "loss": 0.5289,
      "step": 780
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0009484902309058615,
      "loss": 0.6011,
      "step": 790
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0009467140319715807,
      "loss": 0.5841,
      "step": 800
    },
    {
      "epoch": 1.31,
      "eval_loss": 0.5005862712860107,
      "eval_runtime": 5.9494,
      "eval_samples_per_second": 196.827,
      "eval_steps_per_second": 24.708,
      "step": 800
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0009449378330373001,
      "loss": 0.5403,
      "step": 810
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0009431616341030196,
      "loss": 0.558,
      "step": 820
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0009413854351687389,
      "loss": 0.5435,
      "step": 830
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0009396092362344583,
      "loss": 0.5341,
      "step": 840
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0009378330373001777,
      "loss": 0.5398,
      "step": 850
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.000936056838365897,
      "loss": 0.5548,
      "step": 860
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0009342806394316164,
      "loss": 0.5438,
      "step": 870
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0009325044404973358,
      "loss": 0.5845,
      "step": 880
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0009307282415630552,
      "loss": 0.5146,
      "step": 890
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0009289520426287745,
      "loss": 0.5274,
      "step": 900
    },
    {
      "epoch": 1.47,
      "eval_loss": 0.49163827300071716,
      "eval_runtime": 6.0349,
      "eval_samples_per_second": 194.04,
      "eval_steps_per_second": 24.359,
      "step": 900
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0009271758436944939,
      "loss": 0.5999,
      "step": 910
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0009253996447602132,
      "loss": 0.5798,
      "step": 920
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0009236234458259325,
      "loss": 0.5465,
      "step": 930
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0009218472468916519,
      "loss": 0.5752,
      "step": 940
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0009200710479573713,
      "loss": 0.5544,
      "step": 950
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0009182948490230906,
      "loss": 0.5576,
      "step": 960
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00091651865008881,
      "loss": 0.5351,
      "step": 970
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0009147424511545294,
      "loss": 0.5584,
      "step": 980
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0009129662522202487,
      "loss": 0.5191,
      "step": 990
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0009111900532859681,
      "loss": 0.5304,
      "step": 1000
    },
    {
      "epoch": 1.63,
      "eval_loss": 0.48665139079093933,
      "eval_runtime": 5.92,
      "eval_samples_per_second": 197.803,
      "eval_steps_per_second": 24.831,
      "step": 1000
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0009094138543516875,
      "loss": 0.5042,
      "step": 1010
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0009076376554174067,
      "loss": 0.5495,
      "step": 1020
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0009058614564831261,
      "loss": 0.5309,
      "step": 1030
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0009040852575488455,
      "loss": 0.5207,
      "step": 1040
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0009023090586145648,
      "loss": 0.5209,
      "step": 1050
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0009005328596802842,
      "loss": 0.5172,
      "step": 1060
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0008987566607460036,
      "loss": 0.5284,
      "step": 1070
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0008969804618117229,
      "loss": 0.532,
      "step": 1080
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0008952042628774423,
      "loss": 0.534,
      "step": 1090
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0008934280639431617,
      "loss": 0.5299,
      "step": 1100
    },
    {
      "epoch": 1.79,
      "eval_loss": 0.47891008853912354,
      "eval_runtime": 5.951,
      "eval_samples_per_second": 196.772,
      "eval_steps_per_second": 24.702,
      "step": 1100
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.000891651865008881,
      "loss": 0.5213,
      "step": 1110
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0008898756660746004,
      "loss": 0.5443,
      "step": 1120
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0008880994671403197,
      "loss": 0.5367,
      "step": 1130
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0008863232682060391,
      "loss": 0.5393,
      "step": 1140
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0008845470692717584,
      "loss": 0.5286,
      "step": 1150
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0008827708703374778,
      "loss": 0.5363,
      "step": 1160
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0008809946714031972,
      "loss": 0.4707,
      "step": 1170
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0008792184724689165,
      "loss": 0.5414,
      "step": 1180
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0008774422735346359,
      "loss": 0.508,
      "step": 1190
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0008756660746003553,
      "loss": 0.5238,
      "step": 1200
    },
    {
      "epoch": 1.96,
      "eval_loss": 0.47723039984703064,
      "eval_runtime": 11.5341,
      "eval_samples_per_second": 101.525,
      "eval_steps_per_second": 12.745,
      "step": 1200
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0008738898756660746,
      "loss": 0.527,
      "step": 1210
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.000872113676731794,
      "loss": 0.537,
      "step": 1220
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0008703374777975134,
      "loss": 0.5252,
      "step": 1230
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0008685612788632326,
      "loss": 0.5252,
      "step": 1240
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.000866785079928952,
      "loss": 0.501,
      "step": 1250
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0008650088809946714,
      "loss": 0.4979,
      "step": 1260
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0008632326820603907,
      "loss": 0.5041,
      "step": 1270
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0008614564831261101,
      "loss": 0.4837,
      "step": 1280
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0008596802841918295,
      "loss": 0.5124,
      "step": 1290
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0008579040852575488,
      "loss": 0.4876,
      "step": 1300
    },
    {
      "epoch": 2.12,
      "eval_loss": 0.4801134765148163,
      "eval_runtime": 5.9243,
      "eval_samples_per_second": 197.662,
      "eval_steps_per_second": 24.813,
      "step": 1300
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0008561278863232682,
      "loss": 0.4937,
      "step": 1310
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0008543516873889876,
      "loss": 0.4969,
      "step": 1320
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0008525754884547069,
      "loss": 0.4921,
      "step": 1330
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0008507992895204263,
      "loss": 0.5073,
      "step": 1340
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0008490230905861456,
      "loss": 0.4758,
      "step": 1350
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.000847246891651865,
      "loss": 0.5329,
      "step": 1360
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0008454706927175843,
      "loss": 0.4786,
      "step": 1370
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0008436944937833037,
      "loss": 0.4819,
      "step": 1380
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0008419182948490231,
      "loss": 0.5125,
      "step": 1390
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0008401420959147424,
      "loss": 0.5048,
      "step": 1400
    },
    {
      "epoch": 2.28,
      "eval_loss": 0.46734750270843506,
      "eval_runtime": 13.0931,
      "eval_samples_per_second": 89.436,
      "eval_steps_per_second": 11.227,
      "step": 1400
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0008383658969804618,
      "loss": 0.5128,
      "step": 1410
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0008365896980461812,
      "loss": 0.5022,
      "step": 1420
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0008348134991119005,
      "loss": 0.4767,
      "step": 1430
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00083303730017762,
      "loss": 0.4959,
      "step": 1440
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0008312611012433394,
      "loss": 0.5147,
      "step": 1450
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0008294849023090586,
      "loss": 0.4922,
      "step": 1460
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.000827708703374778,
      "loss": 0.4936,
      "step": 1470
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0008259325044404974,
      "loss": 0.5041,
      "step": 1480
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0008241563055062167,
      "loss": 0.491,
      "step": 1490
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0008223801065719361,
      "loss": 0.5096,
      "step": 1500
    },
    {
      "epoch": 2.45,
      "eval_loss": 0.45563551783561707,
      "eval_runtime": 13.1221,
      "eval_samples_per_second": 89.239,
      "eval_steps_per_second": 11.202,
      "step": 1500
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0008206039076376555,
      "loss": 0.4859,
      "step": 1510
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0008188277087033748,
      "loss": 0.5359,
      "step": 1520
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0008170515097690942,
      "loss": 0.4693,
      "step": 1530
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0008152753108348136,
      "loss": 0.4506,
      "step": 1540
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0008134991119005329,
      "loss": 0.4449,
      "step": 1550
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0008117229129662523,
      "loss": 0.4976,
      "step": 1560
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0008099467140319717,
      "loss": 0.4781,
      "step": 1570
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0008081705150976909,
      "loss": 0.4755,
      "step": 1580
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0008063943161634103,
      "loss": 0.5088,
      "step": 1590
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0008046181172291297,
      "loss": 0.4777,
      "step": 1600
    },
    {
      "epoch": 2.61,
      "eval_loss": 0.46053746342658997,
      "eval_runtime": 13.1201,
      "eval_samples_per_second": 89.252,
      "eval_steps_per_second": 11.204,
      "step": 1600
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0008028419182948491,
      "loss": 0.4648,
      "step": 1610
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0008010657193605684,
      "loss": 0.5066,
      "step": 1620
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0007992895204262878,
      "loss": 0.5127,
      "step": 1630
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0007975133214920072,
      "loss": 0.5136,
      "step": 1640
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0007957371225577265,
      "loss": 0.4911,
      "step": 1650
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0007939609236234459,
      "loss": 0.4537,
      "step": 1660
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0007921847246891653,
      "loss": 0.4958,
      "step": 1670
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0007904085257548845,
      "loss": 0.4997,
      "step": 1680
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0007886323268206039,
      "loss": 0.5192,
      "step": 1690
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0007868561278863233,
      "loss": 0.4977,
      "step": 1700
    },
    {
      "epoch": 2.77,
      "eval_loss": 0.4585750102996826,
      "eval_runtime": 13.1101,
      "eval_samples_per_second": 89.32,
      "eval_steps_per_second": 11.213,
      "step": 1700
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0007850799289520426,
      "loss": 0.5044,
      "step": 1710
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.000783303730017762,
      "loss": 0.4839,
      "step": 1720
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0007815275310834814,
      "loss": 0.5234,
      "step": 1730
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0007797513321492007,
      "loss": 0.4835,
      "step": 1740
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0007779751332149201,
      "loss": 0.4939,
      "step": 1750
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0007761989342806395,
      "loss": 0.554,
      "step": 1760
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0007744227353463588,
      "loss": 0.4643,
      "step": 1770
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0007726465364120782,
      "loss": 0.4909,
      "step": 1780
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0007708703374777975,
      "loss": 0.5042,
      "step": 1790
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0007690941385435168,
      "loss": 0.4772,
      "step": 1800
    },
    {
      "epoch": 2.94,
      "eval_loss": 0.44169098138809204,
      "eval_runtime": 13.0107,
      "eval_samples_per_second": 90.003,
      "eval_steps_per_second": 11.298,
      "step": 1800
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0007673179396092362,
      "loss": 0.4529,
      "step": 1810
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0007655417406749556,
      "loss": 0.5058,
      "step": 1820
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0007637655417406749,
      "loss": 0.4794,
      "step": 1830
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0007619893428063943,
      "loss": 0.477,
      "step": 1840
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0007602131438721137,
      "loss": 0.4663,
      "step": 1850
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0007584369449378331,
      "loss": 0.4634,
      "step": 1860
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0007566607460035524,
      "loss": 0.5159,
      "step": 1870
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0007548845470692718,
      "loss": 0.4818,
      "step": 1880
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0007531083481349912,
      "loss": 0.4747,
      "step": 1890
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0007513321492007104,
      "loss": 0.4605,
      "step": 1900
    },
    {
      "epoch": 3.1,
      "eval_loss": 0.4483106732368469,
      "eval_runtime": 13.1231,
      "eval_samples_per_second": 89.232,
      "eval_steps_per_second": 11.202,
      "step": 1900
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0007495559502664298,
      "loss": 0.474,
      "step": 1910
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0007477797513321492,
      "loss": 0.4639,
      "step": 1920
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0007460035523978685,
      "loss": 0.4485,
      "step": 1930
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0007442273534635879,
      "loss": 0.4835,
      "step": 1940
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0007424511545293073,
      "loss": 0.4805,
      "step": 1950
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0007406749555950266,
      "loss": 0.4818,
      "step": 1960
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.000738898756660746,
      "loss": 0.4921,
      "step": 1970
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0007371225577264654,
      "loss": 0.4601,
      "step": 1980
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0007353463587921847,
      "loss": 0.4771,
      "step": 1990
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.000733570159857904,
      "loss": 0.4487,
      "step": 2000
    },
    {
      "epoch": 3.26,
      "eval_loss": 0.46053341031074524,
      "eval_runtime": 12.936,
      "eval_samples_per_second": 90.523,
      "eval_steps_per_second": 11.364,
      "step": 2000
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0007317939609236234,
      "loss": 0.4824,
      "step": 2010
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0007300177619893427,
      "loss": 0.4741,
      "step": 2020
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0007282415630550621,
      "loss": 0.4649,
      "step": 2030
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0007264653641207815,
      "loss": 0.471,
      "step": 2040
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0007246891651865008,
      "loss": 0.4411,
      "step": 2050
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0007229129662522202,
      "loss": 0.4435,
      "step": 2060
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0007211367673179397,
      "loss": 0.4464,
      "step": 2070
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.000719360568383659,
      "loss": 0.4268,
      "step": 2080
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0007175843694493784,
      "loss": 0.4648,
      "step": 2090
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0007158081705150978,
      "loss": 0.4746,
      "step": 2100
    },
    {
      "epoch": 3.43,
      "eval_loss": 0.44933727383613586,
      "eval_runtime": 12.9431,
      "eval_samples_per_second": 90.473,
      "eval_steps_per_second": 11.357,
      "step": 2100
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0007140319715808172,
      "loss": 0.4758,
      "step": 2110
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0007122557726465364,
      "loss": 0.4585,
      "step": 2120
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0007104795737122558,
      "loss": 0.4386,
      "step": 2130
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0007087033747779752,
      "loss": 0.4575,
      "step": 2140
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0007069271758436945,
      "loss": 0.46,
      "step": 2150
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0007051509769094139,
      "loss": 0.4529,
      "step": 2160
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0007033747779751333,
      "loss": 0.4723,
      "step": 2170
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0007015985790408526,
      "loss": 0.47,
      "step": 2180
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.000699822380106572,
      "loss": 0.4952,
      "step": 2190
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0006980461811722914,
      "loss": 0.4488,
      "step": 2200
    },
    {
      "epoch": 3.59,
      "eval_loss": 0.43646687269210815,
      "eval_runtime": 13.2627,
      "eval_samples_per_second": 88.293,
      "eval_steps_per_second": 11.084,
      "step": 2200
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0006962699822380107,
      "loss": 0.4558,
      "step": 2210
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0006944937833037301,
      "loss": 0.4657,
      "step": 2220
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0006927175843694495,
      "loss": 0.4671,
      "step": 2230
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0006909413854351687,
      "loss": 0.5003,
      "step": 2240
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0006891651865008881,
      "loss": 0.4523,
      "step": 2250
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0006873889875666075,
      "loss": 0.4466,
      "step": 2260
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0006856127886323268,
      "loss": 0.4448,
      "step": 2270
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0006838365896980462,
      "loss": 0.4491,
      "step": 2280
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0006820603907637656,
      "loss": 0.4719,
      "step": 2290
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.0006802841918294849,
      "loss": 0.4742,
      "step": 2300
    },
    {
      "epoch": 3.75,
      "eval_loss": 0.43938902020454407,
      "eval_runtime": 13.1019,
      "eval_samples_per_second": 89.376,
      "eval_steps_per_second": 11.22,
      "step": 2300
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0006785079928952043,
      "loss": 0.4709,
      "step": 2310
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0006767317939609237,
      "loss": 0.4575,
      "step": 2320
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.000674955595026643,
      "loss": 0.4688,
      "step": 2330
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0006731793960923623,
      "loss": 0.4552,
      "step": 2340
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0006714031971580817,
      "loss": 0.4515,
      "step": 2350
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0006696269982238011,
      "loss": 0.455,
      "step": 2360
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0006678507992895204,
      "loss": 0.4465,
      "step": 2370
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0006660746003552398,
      "loss": 0.479,
      "step": 2380
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0006642984014209592,
      "loss": 0.4492,
      "step": 2390
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0006625222024866785,
      "loss": 0.4465,
      "step": 2400
    },
    {
      "epoch": 3.92,
      "eval_loss": 0.4411802589893341,
      "eval_runtime": 12.9494,
      "eval_samples_per_second": 90.429,
      "eval_steps_per_second": 11.352,
      "step": 2400
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0006607460035523979,
      "loss": 0.4851,
      "step": 2410
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0006589698046181173,
      "loss": 0.4414,
      "step": 2420
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0006571936056838366,
      "loss": 0.4333,
      "step": 2430
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.000655417406749556,
      "loss": 0.4733,
      "step": 2440
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0006536412078152753,
      "loss": 0.4667,
      "step": 2450
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0006518650088809946,
      "loss": 0.4381,
      "step": 2460
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.000650088809946714,
      "loss": 0.4267,
      "step": 2470
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0006483126110124334,
      "loss": 0.4361,
      "step": 2480
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0006465364120781527,
      "loss": 0.4636,
      "step": 2490
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0006447602131438721,
      "loss": 0.4578,
      "step": 2500
    },
    {
      "epoch": 4.08,
      "eval_loss": 0.4399421811103821,
      "eval_runtime": 13.1521,
      "eval_samples_per_second": 89.035,
      "eval_steps_per_second": 11.177,
      "step": 2500
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0006429840142095915,
      "loss": 0.4375,
      "step": 2510
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0006412078152753108,
      "loss": 0.4485,
      "step": 2520
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0006394316163410302,
      "loss": 0.4633,
      "step": 2530
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0006376554174067496,
      "loss": 0.4457,
      "step": 2540
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0006358792184724689,
      "loss": 0.4504,
      "step": 2550
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.0006341030195381882,
      "loss": 0.4719,
      "step": 2560
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0006323268206039076,
      "loss": 0.4223,
      "step": 2570
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0006305506216696269,
      "loss": 0.4481,
      "step": 2580
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0006287744227353463,
      "loss": 0.4371,
      "step": 2590
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0006269982238010657,
      "loss": 0.4284,
      "step": 2600
    },
    {
      "epoch": 4.24,
      "eval_loss": 0.44260162115097046,
      "eval_runtime": 13.1231,
      "eval_samples_per_second": 89.232,
      "eval_steps_per_second": 11.202,
      "step": 2600
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0006252220248667851,
      "loss": 0.4474,
      "step": 2610
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0006234458259325044,
      "loss": 0.4725,
      "step": 2620
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0006216696269982238,
      "loss": 0.4319,
      "step": 2630
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0006198934280639432,
      "loss": 0.4502,
      "step": 2640
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.0006181172291296625,
      "loss": 0.4378,
      "step": 2650
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0006163410301953819,
      "loss": 0.4333,
      "step": 2660
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0006145648312611012,
      "loss": 0.4206,
      "step": 2670
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0006127886323268205,
      "loss": 0.4314,
      "step": 2680
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.00061101243339254,
      "loss": 0.4083,
      "step": 2690
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0006092362344582594,
      "loss": 0.4416,
      "step": 2700
    },
    {
      "epoch": 4.4,
      "eval_loss": 0.4252881109714508,
      "eval_runtime": 13.1357,
      "eval_samples_per_second": 89.146,
      "eval_steps_per_second": 11.191,
      "step": 2700
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0006074600355239787,
      "loss": 0.452,
      "step": 2710
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0006056838365896981,
      "loss": 0.4075,
      "step": 2720
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0006039076376554175,
      "loss": 0.466,
      "step": 2730
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0006021314387211368,
      "loss": 0.4219,
      "step": 2740
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0006003552397868562,
      "loss": 0.4391,
      "step": 2750
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0005985790408525756,
      "loss": 0.4952,
      "step": 2760
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0005968028419182949,
      "loss": 0.4594,
      "step": 2770
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0005950266429840142,
      "loss": 0.4501,
      "step": 2780
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0005932504440497336,
      "loss": 0.4474,
      "step": 2790
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0005914742451154529,
      "loss": 0.4335,
      "step": 2800
    },
    {
      "epoch": 4.57,
      "eval_loss": 0.43218302726745605,
      "eval_runtime": 12.9197,
      "eval_samples_per_second": 90.637,
      "eval_steps_per_second": 11.378,
      "step": 2800
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.0005896980461811723,
      "loss": 0.4498,
      "step": 2810
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0005879218472468917,
      "loss": 0.4228,
      "step": 2820
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0005861456483126111,
      "loss": 0.4399,
      "step": 2830
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0005843694493783304,
      "loss": 0.4561,
      "step": 2840
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0005825932504440498,
      "loss": 0.4394,
      "step": 2850
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0005808170515097692,
      "loss": 0.4641,
      "step": 2860
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0005790408525754885,
      "loss": 0.4162,
      "step": 2870
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0005772646536412079,
      "loss": 0.4456,
      "step": 2880
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0005754884547069273,
      "loss": 0.4588,
      "step": 2890
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0005737122557726465,
      "loss": 0.4316,
      "step": 2900
    },
    {
      "epoch": 4.73,
      "eval_loss": 0.428786039352417,
      "eval_runtime": 12.9621,
      "eval_samples_per_second": 90.341,
      "eval_steps_per_second": 11.341,
      "step": 2900
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.0005719360568383659,
      "loss": 0.4255,
      "step": 2910
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0005701598579040853,
      "loss": 0.4353,
      "step": 2920
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0005683836589698046,
      "loss": 0.4517,
      "step": 2930
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.000566607460035524,
      "loss": 0.4747,
      "step": 2940
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0005648312611012434,
      "loss": 0.4213,
      "step": 2950
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0005630550621669627,
      "loss": 0.437,
      "step": 2960
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.0005612788632326821,
      "loss": 0.4278,
      "step": 2970
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0005595026642984015,
      "loss": 0.428,
      "step": 2980
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0005577264653641208,
      "loss": 0.4256,
      "step": 2990
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0005559502664298401,
      "loss": 0.4509,
      "step": 3000
    },
    {
      "epoch": 4.89,
      "eval_loss": 0.4271390736103058,
      "eval_runtime": 12.8651,
      "eval_samples_per_second": 91.022,
      "eval_steps_per_second": 11.426,
      "step": 3000
    }
  ],
  "logging_steps": 10,
  "max_steps": 6130,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5664599237689344.0,
  "trial_name": null,
  "trial_params": null
}