{
  "best_metric": 1.0422136783599854,
  "best_model_checkpoint": "models/deberta-v3-base/1691009101/checkpoint-470",
  "epoch": 4.986737400530504,
  "global_step": 470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.9787234042553193e-05,
      "loss": 2.1681,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9574468085106384e-05,
      "loss": 2.1189,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9361702127659575e-05,
      "loss": 2.163,
      "step": 15
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.914893617021277e-05,
      "loss": 2.111,
      "step": 20
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.893617021276596e-05,
      "loss": 2.1833,
      "step": 25
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.872340425531915e-05,
      "loss": 2.0812,
      "step": 30
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.8510638297872342e-05,
      "loss": 2.1295,
      "step": 35
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8297872340425533e-05,
      "loss": 2.0143,
      "step": 40
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 2.1968,
      "step": 45
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7872340425531915e-05,
      "loss": 1.995,
      "step": 50
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.765957446808511e-05,
      "loss": 2.0799,
      "step": 55
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.74468085106383e-05,
      "loss": 1.9155,
      "step": 60
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.723404255319149e-05,
      "loss": 1.9628,
      "step": 65
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 1.9793,
      "step": 70
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.6808510638297873e-05,
      "loss": 1.8198,
      "step": 75
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.6595744680851064e-05,
      "loss": 1.6043,
      "step": 80
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.6382978723404255e-05,
      "loss": 1.6209,
      "step": 85
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6170212765957446e-05,
      "loss": 1.5354,
      "step": 90
    },
    {
      "epoch": 1.0,
      "eval_dignity_contempt_accuracy": 0.797153024911032,
      "eval_loss": 1.4699641466140747,
      "eval_mae": 0.5818505338078291,
      "eval_n_samples": 670,
      "eval_runtime": 13.4181,
      "eval_samples_per_second": 49.933,
      "eval_scorable_accuracy": 0.8776119402985074,
      "eval_steps_per_second": 6.26,
      "eval_top_1_accuracy": 0.5223880597014925,
      "eval_top_2_accuracy": 0.8843416370106761,
      "step": 94
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.595744680851064e-05,
      "loss": 1.5383,
      "step": 95
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.5744680851063832e-05,
      "loss": 1.5934,
      "step": 100
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.5531914893617023e-05,
      "loss": 1.5562,
      "step": 105
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.5319148936170214e-05,
      "loss": 1.4006,
      "step": 110
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.5106382978723407e-05,
      "loss": 1.4296,
      "step": 115
    },
    {
      "epoch": 1.27,
      "learning_rate": 1.4893617021276596e-05,
      "loss": 1.3508,
      "step": 120
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.4680851063829789e-05,
      "loss": 1.3246,
      "step": 125
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.4468085106382981e-05,
      "loss": 1.2573,
      "step": 130
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.425531914893617e-05,
      "loss": 1.4491,
      "step": 135
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.4042553191489363e-05,
      "loss": 1.2537,
      "step": 140
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.3829787234042556e-05,
      "loss": 1.3947,
      "step": 145
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.3617021276595745e-05,
      "loss": 1.282,
      "step": 150
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.3404255319148938e-05,
      "loss": 1.3167,
      "step": 155
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.3191489361702127e-05,
      "loss": 1.3456,
      "step": 160
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.297872340425532e-05,
      "loss": 1.2924,
      "step": 165
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2765957446808513e-05,
      "loss": 1.4235,
      "step": 170
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.2553191489361702e-05,
      "loss": 1.157,
      "step": 175
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.2340425531914895e-05,
      "loss": 1.1315,
      "step": 180
    },
    {
      "epoch": 1.96,
      "learning_rate": 1.2127659574468087e-05,
      "loss": 1.2265,
      "step": 185
    },
    {
      "epoch": 1.99,
      "eval_dignity_contempt_accuracy": 0.8087248322147651,
      "eval_loss": 1.1996970176696777,
      "eval_mae": 0.5134228187919463,
      "eval_n_samples": 670,
      "eval_runtime": 13.4177,
      "eval_samples_per_second": 49.934,
      "eval_scorable_accuracy": 0.9313432835820895,
      "eval_steps_per_second": 6.26,
      "eval_top_1_accuracy": 0.5492537313432836,
      "eval_top_2_accuracy": 0.9328859060402684,
      "step": 188
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.1914893617021277e-05,
      "loss": 1.1528,
      "step": 190
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.170212765957447e-05,
      "loss": 1.1732,
      "step": 195
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1489361702127662e-05,
      "loss": 1.1946,
      "step": 200
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.1276595744680851e-05,
      "loss": 1.0079,
      "step": 205
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.1063829787234044e-05,
      "loss": 0.9267,
      "step": 210
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.0851063829787233e-05,
      "loss": 1.06,
      "step": 215
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.0638297872340426e-05,
      "loss": 1.0085,
      "step": 220
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.0425531914893619e-05,
      "loss": 1.0053,
      "step": 225
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.0212765957446808e-05,
      "loss": 1.0857,
      "step": 230
    },
    {
      "epoch": 2.49,
      "learning_rate": 1e-05,
      "loss": 0.8903,
      "step": 235
    },
    {
      "epoch": 2.55,
      "learning_rate": 9.787234042553192e-06,
      "loss": 1.1211,
      "step": 240
    },
    {
      "epoch": 2.6,
      "learning_rate": 9.574468085106385e-06,
      "loss": 1.0351,
      "step": 245
    },
    {
      "epoch": 2.65,
      "learning_rate": 9.361702127659576e-06,
      "loss": 0.9636,
      "step": 250
    },
    {
      "epoch": 2.71,
      "learning_rate": 9.148936170212767e-06,
      "loss": 0.9087,
      "step": 255
    },
    {
      "epoch": 2.76,
      "learning_rate": 8.936170212765958e-06,
      "loss": 0.9624,
      "step": 260
    },
    {
      "epoch": 2.81,
      "learning_rate": 8.72340425531915e-06,
      "loss": 0.9403,
      "step": 265
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.510638297872341e-06,
      "loss": 0.9479,
      "step": 270
    },
    {
      "epoch": 2.92,
      "learning_rate": 8.297872340425532e-06,
      "loss": 0.8829,
      "step": 275
    },
    {
      "epoch": 2.97,
      "learning_rate": 8.085106382978723e-06,
      "loss": 0.992,
      "step": 280
    },
    {
      "epoch": 2.99,
      "eval_dignity_contempt_accuracy": 0.8266199649737302,
      "eval_loss": 1.091895580291748,
      "eval_mae": 0.4658493870402802,
      "eval_n_samples": 670,
      "eval_runtime": 13.4128,
      "eval_samples_per_second": 49.952,
      "eval_scorable_accuracy": 0.9059701492537313,
      "eval_steps_per_second": 6.263,
      "eval_top_1_accuracy": 0.5776119402985075,
      "eval_top_2_accuracy": 0.9316987740805605,
      "step": 282
    },
    {
      "epoch": 3.02,
      "learning_rate": 7.872340425531916e-06,
      "loss": 0.9552,
      "step": 285
    },
    {
      "epoch": 3.08,
      "learning_rate": 7.659574468085107e-06,
      "loss": 0.8174,
      "step": 290
    },
    {
      "epoch": 3.13,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.766,
      "step": 295
    },
    {
      "epoch": 3.18,
      "learning_rate": 7.234042553191491e-06,
      "loss": 0.7773,
      "step": 300
    },
    {
      "epoch": 3.24,
      "learning_rate": 7.021276595744682e-06,
      "loss": 0.9016,
      "step": 305
    },
    {
      "epoch": 3.29,
      "learning_rate": 6.808510638297873e-06,
      "loss": 0.8505,
      "step": 310
    },
    {
      "epoch": 3.34,
      "learning_rate": 6.595744680851064e-06,
      "loss": 0.9318,
      "step": 315
    },
    {
      "epoch": 3.4,
      "learning_rate": 6.382978723404256e-06,
      "loss": 0.7373,
      "step": 320
    },
    {
      "epoch": 3.45,
      "learning_rate": 6.170212765957447e-06,
      "loss": 0.7445,
      "step": 325
    },
    {
      "epoch": 3.5,
      "learning_rate": 5.957446808510638e-06,
      "loss": 0.8805,
      "step": 330
    },
    {
      "epoch": 3.55,
      "learning_rate": 5.744680851063831e-06,
      "loss": 0.7931,
      "step": 335
    },
    {
      "epoch": 3.61,
      "learning_rate": 5.531914893617022e-06,
      "loss": 0.8024,
      "step": 340
    },
    {
      "epoch": 3.66,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.7106,
      "step": 345
    },
    {
      "epoch": 3.71,
      "learning_rate": 5.106382978723404e-06,
      "loss": 0.7161,
      "step": 350
    },
    {
      "epoch": 3.77,
      "learning_rate": 4.893617021276596e-06,
      "loss": 0.7998,
      "step": 355
    },
    {
      "epoch": 3.82,
      "learning_rate": 4.680851063829788e-06,
      "loss": 0.6772,
      "step": 360
    },
    {
      "epoch": 3.87,
      "learning_rate": 4.468085106382979e-06,
      "loss": 0.7802,
      "step": 365
    },
    {
      "epoch": 3.93,
      "learning_rate": 4.255319148936171e-06,
      "loss": 0.7525,
      "step": 370
    },
    {
      "epoch": 3.98,
      "learning_rate": 4.042553191489362e-06,
      "loss": 0.7967,
      "step": 375
    },
    {
      "epoch": 4.0,
      "eval_dignity_contempt_accuracy": 0.8305084745762712,
      "eval_loss": 1.0538846254348755,
      "eval_mae": 0.43559322033898307,
      "eval_n_samples": 670,
      "eval_runtime": 13.4019,
      "eval_samples_per_second": 49.993,
      "eval_scorable_accuracy": 0.926865671641791,
      "eval_steps_per_second": 6.268,
      "eval_top_1_accuracy": 0.6044776119402985,
      "eval_top_2_accuracy": 0.9372881355932203,
      "step": 377
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.8297872340425535e-06,
      "loss": 0.7263,
      "step": 380
    },
    {
      "epoch": 4.08,
      "learning_rate": 3.6170212765957453e-06,
      "loss": 0.7746,
      "step": 385
    },
    {
      "epoch": 4.14,
      "learning_rate": 3.4042553191489363e-06,
      "loss": 0.7231,
      "step": 390
    },
    {
      "epoch": 4.19,
      "learning_rate": 3.191489361702128e-06,
      "loss": 0.7129,
      "step": 395
    },
    {
      "epoch": 4.24,
      "learning_rate": 2.978723404255319e-06,
      "loss": 0.7609,
      "step": 400
    },
    {
      "epoch": 4.3,
      "learning_rate": 2.765957446808511e-06,
      "loss": 0.7708,
      "step": 405
    },
    {
      "epoch": 4.35,
      "learning_rate": 2.553191489361702e-06,
      "loss": 0.6699,
      "step": 410
    },
    {
      "epoch": 4.4,
      "learning_rate": 2.340425531914894e-06,
      "loss": 0.5928,
      "step": 415
    },
    {
      "epoch": 4.46,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 0.6845,
      "step": 420
    },
    {
      "epoch": 4.51,
      "learning_rate": 1.9148936170212767e-06,
      "loss": 0.6752,
      "step": 425
    },
    {
      "epoch": 4.56,
      "learning_rate": 1.7021276595744682e-06,
      "loss": 0.5874,
      "step": 430
    },
    {
      "epoch": 4.62,
      "learning_rate": 1.4893617021276596e-06,
      "loss": 0.6781,
      "step": 435
    },
    {
      "epoch": 4.67,
      "learning_rate": 1.276595744680851e-06,
      "loss": 0.6023,
      "step": 440
    },
    {
      "epoch": 4.72,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 0.5626,
      "step": 445
    },
    {
      "epoch": 4.77,
      "learning_rate": 8.510638297872341e-07,
      "loss": 0.6321,
      "step": 450
    },
    {
      "epoch": 4.83,
      "learning_rate": 6.382978723404255e-07,
      "loss": 0.6318,
      "step": 455
    },
    {
      "epoch": 4.88,
      "learning_rate": 4.2553191489361704e-07,
      "loss": 0.5816,
      "step": 460
    },
    {
      "epoch": 4.93,
      "learning_rate": 2.1276595744680852e-07,
      "loss": 0.7118,
      "step": 465
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0,
      "loss": 0.6383,
      "step": 470
    },
    {
      "epoch": 4.99,
      "eval_dignity_contempt_accuracy": 0.8398637137989778,
      "eval_loss": 1.0422136783599854,
      "eval_mae": 0.42759795570698467,
      "eval_n_samples": 670,
      "eval_runtime": 13.4143,
      "eval_samples_per_second": 49.947,
      "eval_scorable_accuracy": 0.9223880597014925,
      "eval_steps_per_second": 6.262,
      "eval_top_1_accuracy": 0.6119402985074627,
      "eval_top_2_accuracy": 0.9369676320272572,
      "step": 470
    }
  ],
  "max_steps": 470,
  "num_train_epochs": 5,
  "total_flos": 7904494608261120.0,
  "trial_name": null,
  "trial_params": null
}