{
  "best_metric": 0.0002666182699613273,
  "best_model_checkpoint": "autotrain-3b9gd-7t9lc/checkpoint-494",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 494,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 8.240466117858887,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1781,
      "step": 5
    },
    {
      "epoch": 0.04,
      "grad_norm": 14.987759590148926,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1781,
      "step": 10
    },
    {
      "epoch": 0.06,
      "grad_norm": 8.519774436950684,
      "learning_rate": 1e-05,
      "loss": 1.0057,
      "step": 15
    },
    {
      "epoch": 0.08,
      "grad_norm": 6.639293193817139,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.909,
      "step": 20
    },
    {
      "epoch": 0.1,
      "grad_norm": 8.727118492126465,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8319,
      "step": 25
    },
    {
      "epoch": 0.12,
      "grad_norm": 7.4621148109436035,
      "learning_rate": 2e-05,
      "loss": 0.6461,
      "step": 30
    },
    {
      "epoch": 0.14,
      "grad_norm": 6.218155860900879,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.5342,
      "step": 35
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.2607550621032715,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.3212,
      "step": 40
    },
    {
      "epoch": 0.18,
      "grad_norm": 7.647438049316406,
      "learning_rate": 3e-05,
      "loss": 0.2912,
      "step": 45
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.327169418334961,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.1935,
      "step": 50
    },
    {
      "epoch": 0.22,
      "grad_norm": 10.839067459106445,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.2682,
      "step": 55
    },
    {
      "epoch": 0.24,
      "grad_norm": 5.581568717956543,
      "learning_rate": 4e-05,
      "loss": 0.3104,
      "step": 60
    },
    {
      "epoch": 0.26,
      "grad_norm": 8.139863967895508,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.1683,
      "step": 65
    },
    {
      "epoch": 0.28,
      "grad_norm": 7.741869926452637,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.4055,
      "step": 70
    },
    {
      "epoch": 0.3,
      "grad_norm": 23.573352813720703,
      "learning_rate": 5e-05,
      "loss": 0.3234,
      "step": 75
    },
    {
      "epoch": 0.32,
      "grad_norm": 8.024917602539062,
      "learning_rate": 4.9624624624624625e-05,
      "loss": 0.5331,
      "step": 80
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.1634410321712494,
      "learning_rate": 4.9249249249249253e-05,
      "loss": 0.0505,
      "step": 85
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.8996868133544922,
      "learning_rate": 4.8873873873873876e-05,
      "loss": 0.1691,
      "step": 90
    },
    {
      "epoch": 0.38,
      "grad_norm": 6.981603622436523,
      "learning_rate": 4.8498498498498504e-05,
      "loss": 0.2798,
      "step": 95
    },
    {
      "epoch": 0.4,
      "grad_norm": 5.159909248352051,
      "learning_rate": 4.812312312312313e-05,
      "loss": 0.2114,
      "step": 100
    },
    {
      "epoch": 0.43,
      "grad_norm": 4.676971435546875,
      "learning_rate": 4.774774774774775e-05,
      "loss": 0.2634,
      "step": 105
    },
    {
      "epoch": 0.45,
      "grad_norm": 6.247714042663574,
      "learning_rate": 4.737237237237238e-05,
      "loss": 0.1426,
      "step": 110
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.8779627084732056,
      "learning_rate": 4.6996996996997e-05,
      "loss": 0.4049,
      "step": 115
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.6359833478927612,
      "learning_rate": 4.662162162162162e-05,
      "loss": 0.0321,
      "step": 120
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.4598715007305145,
      "learning_rate": 4.624624624624625e-05,
      "loss": 0.0668,
      "step": 125
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.07359237223863602,
      "learning_rate": 4.587087087087087e-05,
      "loss": 0.2143,
      "step": 130
    },
    {
      "epoch": 0.55,
      "grad_norm": 8.209424018859863,
      "learning_rate": 4.54954954954955e-05,
      "loss": 0.1671,
      "step": 135
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.7971270084381104,
      "learning_rate": 4.5120120120120124e-05,
      "loss": 0.2135,
      "step": 140
    },
    {
      "epoch": 0.59,
      "grad_norm": 12.232625961303711,
      "learning_rate": 4.4744744744744746e-05,
      "loss": 0.1478,
      "step": 145
    },
    {
      "epoch": 0.61,
      "grad_norm": 13.341341972351074,
      "learning_rate": 4.4369369369369375e-05,
      "loss": 0.3675,
      "step": 150
    },
    {
      "epoch": 0.63,
      "grad_norm": 22.468730926513672,
      "learning_rate": 4.3993993993994e-05,
      "loss": 0.1616,
      "step": 155
    },
    {
      "epoch": 0.65,
      "grad_norm": 6.675795078277588,
      "learning_rate": 4.3618618618618626e-05,
      "loss": 0.1661,
      "step": 160
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.265025019645691,
      "learning_rate": 4.324324324324325e-05,
      "loss": 0.1427,
      "step": 165
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.23774471879005432,
      "learning_rate": 4.286786786786787e-05,
      "loss": 0.0339,
      "step": 170
    },
    {
      "epoch": 0.71,
      "grad_norm": 9.141915321350098,
      "learning_rate": 4.24924924924925e-05,
      "loss": 0.4787,
      "step": 175
    },
    {
      "epoch": 0.73,
      "grad_norm": 14.628870964050293,
      "learning_rate": 4.2117117117117115e-05,
      "loss": 0.0911,
      "step": 180
    },
    {
      "epoch": 0.75,
      "grad_norm": 8.062237739562988,
      "learning_rate": 4.1741741741741744e-05,
      "loss": 0.0447,
      "step": 185
    },
    {
      "epoch": 0.77,
      "grad_norm": 16.428728103637695,
      "learning_rate": 4.1366366366366366e-05,
      "loss": 0.3648,
      "step": 190
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.037159789353609085,
      "learning_rate": 4.099099099099099e-05,
      "loss": 0.249,
      "step": 195
    },
    {
      "epoch": 0.81,
      "grad_norm": 8.085445404052734,
      "learning_rate": 4.061561561561562e-05,
      "loss": 0.0837,
      "step": 200
    },
    {
      "epoch": 0.83,
      "grad_norm": 2.010667085647583,
      "learning_rate": 4.024024024024024e-05,
      "loss": 0.0347,
      "step": 205
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.7477858662605286,
      "learning_rate": 3.986486486486487e-05,
      "loss": 0.1399,
      "step": 210
    },
    {
      "epoch": 0.87,
      "grad_norm": 7.963656425476074,
      "learning_rate": 3.948948948948949e-05,
      "loss": 0.09,
      "step": 215
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.43208637833595276,
      "learning_rate": 3.911411411411411e-05,
      "loss": 0.1049,
      "step": 220
    },
    {
      "epoch": 0.91,
      "grad_norm": 5.871271133422852,
      "learning_rate": 3.873873873873874e-05,
      "loss": 0.322,
      "step": 225
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.027932079508900642,
      "learning_rate": 3.836336336336336e-05,
      "loss": 0.0024,
      "step": 230
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.017657727003097534,
      "learning_rate": 3.7987987987987985e-05,
      "loss": 0.1332,
      "step": 235
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.7482669949531555,
      "learning_rate": 3.7612612612612614e-05,
      "loss": 0.0361,
      "step": 240
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.05272696912288666,
      "learning_rate": 3.7237237237237236e-05,
      "loss": 0.0071,
      "step": 245
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9954128440366973,
      "eval_f1_macro": 0.9953370832314339,
      "eval_f1_micro": 0.9954128440366973,
      "eval_f1_weighted": 0.9954123953053728,
      "eval_loss": 0.008562826551496983,
      "eval_precision_macro": 0.9954337899543378,
      "eval_precision_micro": 0.9954128440366973,
      "eval_precision_weighted": 0.9954756817896192,
      "eval_recall_macro": 0.9953051643192489,
      "eval_recall_micro": 0.9954128440366973,
      "eval_recall_weighted": 0.9954128440366973,
      "eval_runtime": 61.5673,
      "eval_samples_per_second": 3.541,
      "eval_steps_per_second": 0.227,
      "step": 247
    },
    {
      "epoch": 1.01,
      "grad_norm": 2.773138999938965,
      "learning_rate": 3.6861861861861865e-05,
      "loss": 0.257,
      "step": 250
    },
    {
      "epoch": 1.03,
      "grad_norm": 4.275286674499512,
      "learning_rate": 3.648648648648649e-05,
      "loss": 0.382,
      "step": 255
    },
    {
      "epoch": 1.05,
      "grad_norm": 24.60214614868164,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.3858,
      "step": 260
    },
    {
      "epoch": 1.07,
      "grad_norm": 8.784448623657227,
      "learning_rate": 3.573573573573574e-05,
      "loss": 0.5298,
      "step": 265
    },
    {
      "epoch": 1.09,
      "grad_norm": 1.1353392601013184,
      "learning_rate": 3.536036036036036e-05,
      "loss": 0.153,
      "step": 270
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.023551814258098602,
      "learning_rate": 3.498498498498499e-05,
      "loss": 0.0052,
      "step": 275
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.15712416172027588,
      "learning_rate": 3.460960960960961e-05,
      "loss": 0.3094,
      "step": 280
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.023001644760370255,
      "learning_rate": 3.4234234234234234e-05,
      "loss": 0.0407,
      "step": 285
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.011525897309184074,
      "learning_rate": 3.385885885885886e-05,
      "loss": 0.0422,
      "step": 290
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.9765132665634155,
      "learning_rate": 3.3483483483483485e-05,
      "loss": 0.1107,
      "step": 295
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.193386971950531,
      "learning_rate": 3.310810810810811e-05,
      "loss": 0.1098,
      "step": 300
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.0348842591047287,
      "learning_rate": 3.2732732732732736e-05,
      "loss": 0.0901,
      "step": 305
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.02413288690149784,
      "learning_rate": 3.235735735735736e-05,
      "loss": 0.0014,
      "step": 310
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.470839023590088,
      "learning_rate": 3.198198198198199e-05,
      "loss": 0.0368,
      "step": 315
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.6575441360473633,
      "learning_rate": 3.160660660660661e-05,
      "loss": 0.3384,
      "step": 320
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.11603262275457382,
      "learning_rate": 3.123123123123123e-05,
      "loss": 0.2287,
      "step": 325
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.09468206018209457,
      "learning_rate": 3.085585585585586e-05,
      "loss": 0.0053,
      "step": 330
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.18447920680046082,
      "learning_rate": 3.0480480480480482e-05,
      "loss": 0.0894,
      "step": 335
    },
    {
      "epoch": 1.38,
      "grad_norm": 22.559310913085938,
      "learning_rate": 3.0105105105105108e-05,
      "loss": 0.2127,
      "step": 340
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.36875221133232117,
      "learning_rate": 2.9729729729729733e-05,
      "loss": 0.0123,
      "step": 345
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.3973434269428253,
      "learning_rate": 2.935435435435436e-05,
      "loss": 0.0268,
      "step": 350
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.054519250988960266,
      "learning_rate": 2.897897897897898e-05,
      "loss": 0.1053,
      "step": 355
    },
    {
      "epoch": 1.46,
      "grad_norm": 5.856131076812744,
      "learning_rate": 2.8603603603603606e-05,
      "loss": 0.105,
      "step": 360
    },
    {
      "epoch": 1.48,
      "grad_norm": 2.6053731441497803,
      "learning_rate": 2.8228228228228232e-05,
      "loss": 0.0072,
      "step": 365
    },
    {
      "epoch": 1.5,
      "grad_norm": 14.849920272827148,
      "learning_rate": 2.7852852852852857e-05,
      "loss": 0.256,
      "step": 370
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.036322303116321564,
      "learning_rate": 2.7477477477477483e-05,
      "loss": 0.1195,
      "step": 375
    },
    {
      "epoch": 1.54,
      "grad_norm": 7.0286431312561035,
      "learning_rate": 2.7102102102102105e-05,
      "loss": 0.2874,
      "step": 380
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.007908895611763,
      "learning_rate": 2.672672672672673e-05,
      "loss": 0.1749,
      "step": 385
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.2694431245326996,
      "learning_rate": 2.635135135135135e-05,
      "loss": 0.0078,
      "step": 390
    },
    {
      "epoch": 1.6,
      "grad_norm": 14.261417388916016,
      "learning_rate": 2.5975975975975975e-05,
      "loss": 0.0251,
      "step": 395
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.8614434003829956,
      "learning_rate": 2.56006006006006e-05,
      "loss": 0.01,
      "step": 400
    },
    {
      "epoch": 1.64,
      "grad_norm": 10.162217140197754,
      "learning_rate": 2.5225225225225222e-05,
      "loss": 0.0645,
      "step": 405
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.010031257756054401,
      "learning_rate": 2.484984984984985e-05,
      "loss": 0.1714,
      "step": 410
    },
    {
      "epoch": 1.68,
      "grad_norm": 1.1147041320800781,
      "learning_rate": 2.4474474474474477e-05,
      "loss": 0.062,
      "step": 415
    },
    {
      "epoch": 1.7,
      "grad_norm": 14.216385841369629,
      "learning_rate": 2.4099099099099102e-05,
      "loss": 0.2521,
      "step": 420
    },
    {
      "epoch": 1.72,
      "grad_norm": 5.073903560638428,
      "learning_rate": 2.3723723723723725e-05,
      "loss": 0.1764,
      "step": 425
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.5860055088996887,
      "learning_rate": 2.334834834834835e-05,
      "loss": 0.0095,
      "step": 430
    },
    {
      "epoch": 1.76,
      "grad_norm": 6.916937828063965,
      "learning_rate": 2.2972972972972976e-05,
      "loss": 0.2236,
      "step": 435
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.4593968689441681,
      "learning_rate": 2.2597597597597598e-05,
      "loss": 0.2062,
      "step": 440
    },
    {
      "epoch": 1.8,
      "grad_norm": 10.855243682861328,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0295,
      "step": 445
    },
    {
      "epoch": 1.82,
      "grad_norm": 8.221331596374512,
      "learning_rate": 2.1846846846846845e-05,
      "loss": 0.2937,
      "step": 450
    },
    {
      "epoch": 1.84,
      "grad_norm": 5.3991265296936035,
      "learning_rate": 2.147147147147147e-05,
      "loss": 0.1518,
      "step": 455
    },
    {
      "epoch": 1.86,
      "grad_norm": 2.2880308628082275,
      "learning_rate": 2.1096096096096096e-05,
      "loss": 0.0107,
      "step": 460
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.38851749897003174,
      "learning_rate": 2.0720720720720722e-05,
      "loss": 0.0047,
      "step": 465
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.007677082903683186,
      "learning_rate": 2.0345345345345344e-05,
      "loss": 0.1443,
      "step": 470
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.004121085163205862,
      "learning_rate": 1.996996996996997e-05,
      "loss": 0.0866,
      "step": 475
    },
    {
      "epoch": 1.94,
      "grad_norm": 4.384052276611328,
      "learning_rate": 1.9594594594594595e-05,
      "loss": 0.1988,
      "step": 480
    },
    {
      "epoch": 1.96,
      "grad_norm": 13.786602973937988,
      "learning_rate": 1.921921921921922e-05,
      "loss": 0.2474,
      "step": 485
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.005240537691861391,
      "learning_rate": 1.8843843843843846e-05,
      "loss": 0.0088,
      "step": 490
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_f1_macro": 1.0,
      "eval_f1_micro": 1.0,
      "eval_f1_weighted": 1.0,
      "eval_loss": 0.0002666182699613273,
      "eval_precision_macro": 1.0,
      "eval_precision_micro": 1.0,
      "eval_precision_weighted": 1.0,
      "eval_recall_macro": 1.0,
      "eval_recall_micro": 1.0,
      "eval_recall_weighted": 1.0,
      "eval_runtime": 57.4601,
      "eval_samples_per_second": 3.794,
      "eval_steps_per_second": 0.244,
      "step": 494
    }
  ],
  "logging_steps": 5,
  "max_steps": 741,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3.0532117555408896e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}