{
  "best_metric": 2.9716455936431885,
  "best_model_checkpoint": "/root/workspace/mounts/blobs/blob-deeplm2/v-youmohamed/OUTPUT/checkpoint-896",
  "epoch": 1.899688597363016,
  "global_step": 896,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 3.7521,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 3.4722,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 3.3737,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.3422,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 3.2973,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 3.2657,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 3.2831,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 3.2618,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 3.2306,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 3.2366,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 3.2351,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 3.2498,
      "step": 60
    },
    {
      "epoch": 0.14,
      "eval_loss": 3.0548903942108154,
      "eval_runtime": 12.4122,
      "eval_samples_per_second": 9988.553,
      "eval_steps_per_second": 156.137,
      "eval_top3_3_weighted_f1_score ": 0.3635597179689758,
      "eval_top_1_macro_f1_score": 0.12749506628104146,
      "eval_top_1_weighted_f1score": 0.17965168935293338,
      "eval_top_3_macro_f1_score": 0.27169270972798243,
      "step": 64
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 3.2185,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 3.2281,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 3.2107,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 3.1923,
      "step": 80
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 3.2002,
      "step": 85
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 3.1936,
      "step": 90
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 3.1864,
      "step": 95
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 3.1851,
      "step": 100
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 3.2114,
      "step": 105
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 3.1978,
      "step": 110
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 3.2071,
      "step": 115
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 3.1736,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 3.1662,
      "step": 125
    },
    {
      "epoch": 0.27,
      "eval_loss": 3.03450345993042,
      "eval_runtime": 12.3026,
      "eval_samples_per_second": 10077.544,
      "eval_steps_per_second": 157.528,
      "eval_top3_3_weighted_f1_score ": 0.367365798951655,
      "eval_top_1_macro_f1_score": 0.13108849715797372,
      "eval_top_1_weighted_f1score": 0.1856398470154161,
      "eval_top_3_macro_f1_score": 0.2767454300628382,
      "step": 128
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 3.1539,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 3.2208,
      "step": 135
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 3.1691,
      "step": 140
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 3.1579,
      "step": 145
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 3.1827,
      "step": 150
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 3.1546,
      "step": 155
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 3.1561,
      "step": 160
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 3.1529,
      "step": 165
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 3.1775,
      "step": 170
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 3.152,
      "step": 175
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 3.1556,
      "step": 180
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 3.1562,
      "step": 185
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 3.16,
      "step": 190
    },
    {
      "epoch": 0.41,
      "eval_loss": 3.0158042907714844,
      "eval_runtime": 12.5431,
      "eval_samples_per_second": 9884.289,
      "eval_steps_per_second": 154.507,
      "eval_top3_3_weighted_f1_score ": 0.3724159289868765,
      "eval_top_1_macro_f1_score": 0.13421610412877683,
      "eval_top_1_weighted_f1score": 0.18861048252163506,
      "eval_top_3_macro_f1_score": 0.2791788451621761,
      "step": 192
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 3.1525,
      "step": 195
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 3.1471,
      "step": 200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 3.1479,
      "step": 205
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 3.1221,
      "step": 210
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 3.1531,
      "step": 215
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 3.1237,
      "step": 220
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 3.1619,
      "step": 225
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 3.1405,
      "step": 230
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 3.1649,
      "step": 235
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 3.1444,
      "step": 240
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 3.1373,
      "step": 245
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 3.1303,
      "step": 250
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 3.1154,
      "step": 255
    },
    {
      "epoch": 0.54,
      "eval_loss": 3.0033798217773438,
      "eval_runtime": 12.4351,
      "eval_samples_per_second": 9970.191,
      "eval_steps_per_second": 155.85,
      "eval_top3_3_weighted_f1_score ": 0.3769780434228148,
      "eval_top_1_macro_f1_score": 0.13432065892500267,
      "eval_top_1_weighted_f1score": 0.18801869311169406,
      "eval_top_3_macro_f1_score": 0.28440917781504094,
      "step": 256
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 3.1335,
      "step": 260
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 3.1378,
      "step": 265
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 3.1427,
      "step": 270
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 3.1226,
      "step": 275
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 3.126,
      "step": 280
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 3.139,
      "step": 285
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 3.1391,
      "step": 290
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 3.1416,
      "step": 295
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 3.133,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 3.1336,
      "step": 305
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 3.1213,
      "step": 310
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 3.1144,
      "step": 315
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 3.1257,
      "step": 320
    },
    {
      "epoch": 0.68,
      "eval_loss": 2.9847888946533203,
      "eval_runtime": 12.4682,
      "eval_samples_per_second": 9943.722,
      "eval_steps_per_second": 155.436,
      "eval_top3_3_weighted_f1_score ": 0.3782555483193414,
      "eval_top_1_macro_f1_score": 0.1332053681737893,
      "eval_top_1_weighted_f1score": 0.18758504608314192,
      "eval_top_3_macro_f1_score": 0.2819546880264732,
      "step": 320
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 3.1373,
      "step": 325
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 3.1284,
      "step": 330
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 3.1107,
      "step": 335
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 3.1181,
      "step": 340
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 3.145,
      "step": 345
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 3.1185,
      "step": 350
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 3.1189,
      "step": 355
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 3.14,
      "step": 360
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 3.1101,
      "step": 365
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 3.1137,
      "step": 370
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 3.1133,
      "step": 375
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 3.1227,
      "step": 380
    },
    {
      "epoch": 0.81,
      "eval_loss": 2.9721128940582275,
      "eval_runtime": 12.3698,
      "eval_samples_per_second": 10022.814,
      "eval_steps_per_second": 156.672,
      "eval_top3_3_weighted_f1_score ": 0.38056857139903855,
      "eval_top_1_macro_f1_score": 0.13385895070094989,
      "eval_top_1_weighted_f1score": 0.1886778688260468,
      "eval_top_3_macro_f1_score": 0.2843530525848158,
      "step": 384
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 3.1068,
      "step": 385
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 3.1013,
      "step": 390
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 3.1157,
      "step": 395
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 3.1285,
      "step": 400
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 3.1209,
      "step": 405
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 3.1084,
      "step": 410
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 3.1085,
      "step": 415
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 3.0964,
      "step": 420
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 3.0977,
      "step": 425
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 3.1077,
      "step": 430
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 3.1209,
      "step": 435
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 3.1191,
      "step": 440
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 3.1058,
      "step": 445
    },
    {
      "epoch": 0.95,
      "eval_loss": 2.973684549331665,
      "eval_runtime": 12.3568,
      "eval_samples_per_second": 10033.312,
      "eval_steps_per_second": 156.836,
      "eval_top3_3_weighted_f1_score ": 0.3815054842495814,
      "eval_top_1_macro_f1_score": 0.13689945428212444,
      "eval_top_1_weighted_f1score": 0.19158272343260493,
      "eval_top_3_macro_f1_score": 0.28709815898256036,
      "step": 448
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 3.0965,
      "step": 450
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 3.1091,
      "step": 455
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 3.1282,
      "step": 460
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 3.1004,
      "step": 465
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 3.124,
      "step": 470
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 3.0761,
      "step": 475
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 3.0486,
      "step": 480
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 3.0358,
      "step": 485
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 3.0124,
      "step": 490
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 3.0363,
      "step": 495
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0002,
      "loss": 3.0223,
      "step": 500
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 3.0283,
      "step": 505
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002,
      "loss": 3.0411,
      "step": 510
    },
    {
      "epoch": 1.09,
      "eval_loss": 3.0033085346221924,
      "eval_runtime": 12.3385,
      "eval_samples_per_second": 10048.213,
      "eval_steps_per_second": 157.069,
      "eval_top3_3_weighted_f1_score ": 0.38084561975369874,
      "eval_top_1_macro_f1_score": 0.13521743605085645,
      "eval_top_1_weighted_f1score": 0.18797578254383546,
      "eval_top_3_macro_f1_score": 0.2897663126149453,
      "step": 512
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 3.0425,
      "step": 515
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002,
      "loss": 3.0122,
      "step": 520
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 3.0186,
      "step": 525
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 3.034,
      "step": 530
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 3.0444,
      "step": 535
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 3.0289,
      "step": 540
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 3.0539,
      "step": 545
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 3.0165,
      "step": 550
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 3.0315,
      "step": 555
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 3.0457,
      "step": 560
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 3.0518,
      "step": 565
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 3.0271,
      "step": 570
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 3.0259,
      "step": 575
    },
    {
      "epoch": 1.22,
      "eval_loss": 3.003117799758911,
      "eval_runtime": 12.3306,
      "eval_samples_per_second": 10054.688,
      "eval_steps_per_second": 157.17,
      "eval_top3_3_weighted_f1_score ": 0.3808180416513238,
      "eval_top_1_macro_f1_score": 0.1357746878516193,
      "eval_top_1_weighted_f1score": 0.18830594414771443,
      "eval_top_3_macro_f1_score": 0.2872982485151964,
      "step": 576
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 3.0503,
      "step": 580
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 3.0367,
      "step": 585
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 3.0622,
      "step": 590
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 3.0268,
      "step": 595
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 3.0288,
      "step": 600
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 3.0374,
      "step": 605
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 3.0423,
      "step": 610
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002,
      "loss": 3.0421,
      "step": 615
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 3.0486,
      "step": 620
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 3.0581,
      "step": 625
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 3.0522,
      "step": 630
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 3.038,
      "step": 635
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 3.0224,
      "step": 640
    },
    {
      "epoch": 1.36,
      "eval_loss": 2.991966485977173,
      "eval_runtime": 12.3903,
      "eval_samples_per_second": 10006.224,
      "eval_steps_per_second": 156.413,
      "eval_top3_3_weighted_f1_score ": 0.38244182168677654,
      "eval_top_1_macro_f1_score": 0.13697887613478638,
      "eval_top_1_weighted_f1score": 0.19008342397049477,
      "eval_top_3_macro_f1_score": 0.28950530056980883,
      "step": 640
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 3.0515,
      "step": 645
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 3.059,
      "step": 650
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 3.0618,
      "step": 655
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 3.0419,
      "step": 660
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 3.0413,
      "step": 665
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 3.0274,
      "step": 670
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 3.0381,
      "step": 675
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 3.0307,
      "step": 680
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 3.0472,
      "step": 685
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 3.055,
      "step": 690
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 3.0575,
      "step": 695
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 3.0266,
      "step": 700
    },
    {
      "epoch": 1.49,
      "eval_loss": 2.990971088409424,
      "eval_runtime": 12.4127,
      "eval_samples_per_second": 9988.145,
      "eval_steps_per_second": 156.13,
      "eval_top3_3_weighted_f1_score ": 0.38137876299092255,
      "eval_top_1_macro_f1_score": 0.13838382537775124,
      "eval_top_1_weighted_f1score": 0.19131550228883154,
      "eval_top_3_macro_f1_score": 0.28803327800883843,
      "step": 704
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 3.0492,
      "step": 705
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 3.0395,
      "step": 710
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 3.0649,
      "step": 715
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 3.0681,
      "step": 720
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 3.0649,
      "step": 725
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 3.0393,
      "step": 730
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 3.0517,
      "step": 735
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 3.032,
      "step": 740
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 3.0583,
      "step": 745
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 3.0401,
      "step": 750
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 3.0565,
      "step": 755
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 3.0654,
      "step": 760
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 3.0533,
      "step": 765
    },
    {
      "epoch": 1.63,
      "eval_loss": 2.9771080017089844,
      "eval_runtime": 12.6533,
      "eval_samples_per_second": 9798.249,
      "eval_steps_per_second": 153.162,
      "eval_top3_3_weighted_f1_score ": 0.3832560873676479,
      "eval_top_1_macro_f1_score": 0.13752697035489958,
      "eval_top_1_weighted_f1score": 0.18965901401189703,
      "eval_top_3_macro_f1_score": 0.2904255030755513,
      "step": 768
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 3.0475,
      "step": 770
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 3.0636,
      "step": 775
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 3.0349,
      "step": 780
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0002,
      "loss": 3.0396,
      "step": 785
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 3.0486,
      "step": 790
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 3.0499,
      "step": 795
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 3.0419,
      "step": 800
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 3.0155,
      "step": 805
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0002,
      "loss": 3.048,
      "step": 810
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 3.0334,
      "step": 815
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 3.0489,
      "step": 820
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 3.0506,
      "step": 825
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 3.0532,
      "step": 830
    },
    {
      "epoch": 1.76,
      "eval_loss": 2.9731740951538086,
      "eval_runtime": 12.2931,
      "eval_samples_per_second": 10085.346,
      "eval_steps_per_second": 157.65,
      "eval_top3_3_weighted_f1_score ": 0.38454672509114807,
      "eval_top_1_macro_f1_score": 0.13915252180450877,
      "eval_top_1_weighted_f1score": 0.19237329003887355,
      "eval_top_3_macro_f1_score": 0.2905488168931788,
      "step": 832
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 3.0578,
      "step": 835
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 3.0778,
      "step": 840
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 3.0624,
      "step": 845
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 3.0681,
      "step": 850
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 3.0398,
      "step": 855
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 3.0389,
      "step": 860
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 3.0533,
      "step": 865
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0002,
      "loss": 3.0695,
      "step": 870
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 3.0616,
      "step": 875
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 3.0538,
      "step": 880
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 3.0669,
      "step": 885
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 3.043,
      "step": 890
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0002,
      "loss": 3.0493,
      "step": 895
    },
    {
      "epoch": 1.9,
      "eval_loss": 2.9716455936431885,
      "eval_runtime": 12.3359,
      "eval_samples_per_second": 10050.36,
      "eval_steps_per_second": 157.103,
      "eval_top3_3_weighted_f1_score ": 0.3843987215479838,
      "eval_top_1_macro_f1_score": 0.13965577931407566,
      "eval_top_1_weighted_f1score": 0.19375781342563833,
      "eval_top_3_macro_f1_score": 0.2898983574642249,
      "step": 896
    }
  ],
  "max_steps": 942,
  "num_train_epochs": 2,
  "total_flos": 1221880575338496.0,
  "trial_name": null,
  "trial_params": null
}