{
  "best_metric": 0.9186971783638,
  "best_model_checkpoint": "./Finetuned_Classification_model_200k/checkpoint-500",
  "epoch": 0.16,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.037,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.907,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-05,
      "loss": 0.7159,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 0.5758,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.3454,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.997326203208557e-05,
      "loss": 0.1851,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.994652406417113e-05,
      "loss": 0.2821,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9919786096256686e-05,
      "loss": 0.1741,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9893048128342245e-05,
      "loss": 0.1749,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.986631016042781e-05,
      "loss": 0.2407,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.983957219251337e-05,
      "loss": 0.2612,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.981283422459893e-05,
      "loss": 0.1677,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9786096256684495e-05,
      "loss": 0.1123,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.975935828877006e-05,
      "loss": 0.1368,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.973262032085561e-05,
      "loss": 0.1449,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.970588235294118e-05,
      "loss": 0.152,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.967914438502674e-05,
      "loss": 0.2504,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9652406417112304e-05,
      "loss": 0.2578,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.962566844919786e-05,
      "loss": 0.1289,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.959893048128342e-05,
      "loss": 0.1263,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.957219251336899e-05,
      "loss": 0.1031,
      "step": 210
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9545454545454553e-05,
      "loss": 0.2453,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9518716577540106e-05,
      "loss": 0.0675,
      "step": 230
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.949197860962567e-05,
      "loss": 0.1807,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.946524064171123e-05,
      "loss": 0.1493,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9438502673796796e-05,
      "loss": 0.109,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.2148,
      "step": 270
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9385026737967914e-05,
      "loss": 0.2574,
      "step": 280
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.935828877005348e-05,
      "loss": 0.2198,
      "step": 290
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.933155080213904e-05,
      "loss": 0.1574,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.93048128342246e-05,
      "loss": 0.0866,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9278074866310164e-05,
      "loss": 0.1371,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.925133689839572e-05,
      "loss": 0.2074,
      "step": 330
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.922459893048129e-05,
      "loss": 0.3628,
      "step": 340
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.919786096256685e-05,
      "loss": 0.1888,
      "step": 350
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.917112299465241e-05,
      "loss": 0.0934,
      "step": 360
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.914438502673797e-05,
      "loss": 0.1593,
      "step": 370
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.911764705882353e-05,
      "loss": 0.0721,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.909090909090909e-05,
      "loss": 0.1139,
      "step": 390
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.906417112299466e-05,
      "loss": 0.1118,
      "step": 400
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9037433155080216e-05,
      "loss": 0.218,
      "step": 410
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.901069518716578e-05,
      "loss": 0.126,
      "step": 420
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.898395721925134e-05,
      "loss": 0.1057,
      "step": 430
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.89572192513369e-05,
      "loss": 0.1825,
      "step": 440
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8930481283422465e-05,
      "loss": 0.1379,
      "step": 450
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8903743315508024e-05,
      "loss": 0.1311,
      "step": 460
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.8877005347593584e-05,
      "loss": 0.0722,
      "step": 470
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.885026737967915e-05,
      "loss": 0.1286,
      "step": 480
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.882352941176471e-05,
      "loss": 0.1534,
      "step": 490
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.879679144385027e-05,
      "loss": 0.1332,
      "step": 500
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.8395015105740181,
      "eval_f1": 0.8361086180158485,
      "eval_loss": 0.9186971783638,
      "eval_precision": 0.8701532825604937,
      "eval_recall": 0.8395015105740181,
      "eval_runtime": 10.5139,
      "eval_samples_per_second": 251.857,
      "eval_steps_per_second": 3.995,
      "step": 500
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.8770053475935826e-05,
      "loss": 0.1317,
      "step": 510
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.874331550802139e-05,
      "loss": 0.0683,
      "step": 520
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.871657754010696e-05,
      "loss": 0.0474,
      "step": 530
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.868983957219252e-05,
      "loss": 0.2302,
      "step": 540
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8663101604278076e-05,
      "loss": 0.1788,
      "step": 550
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.863636363636364e-05,
      "loss": 0.0917,
      "step": 560
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.86096256684492e-05,
      "loss": 0.2001,
      "step": 570
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.858288770053476e-05,
      "loss": 0.3409,
      "step": 580
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.855614973262032e-05,
      "loss": 0.2044,
      "step": 590
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8529411764705885e-05,
      "loss": 0.1292,
      "step": 600
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.850267379679145e-05,
      "loss": 0.1422,
      "step": 610
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8475935828877e-05,
      "loss": 0.1165,
      "step": 620
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.844919786096257e-05,
      "loss": 0.1115,
      "step": 630
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8422459893048135e-05,
      "loss": 0.0957,
      "step": 640
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8395721925133694e-05,
      "loss": 0.1791,
      "step": 650
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.836898395721925e-05,
      "loss": 0.0691,
      "step": 660
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.834224598930481e-05,
      "loss": 0.2829,
      "step": 670
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.831550802139038e-05,
      "loss": 0.2635,
      "step": 680
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.828877005347594e-05,
      "loss": 0.1722,
      "step": 690
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8262032085561496e-05,
      "loss": 0.0974,
      "step": 700
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.823529411764706e-05,
      "loss": 0.0888,
      "step": 710
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.820855614973262e-05,
      "loss": 0.3148,
      "step": 720
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8181818181818186e-05,
      "loss": 0.3556,
      "step": 730
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8155080213903745e-05,
      "loss": 0.1788,
      "step": 740
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8128342245989304e-05,
      "loss": 0.4376,
      "step": 750
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.810160427807487e-05,
      "loss": 0.2413,
      "step": 760
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.807486631016043e-05,
      "loss": 0.1802,
      "step": 770
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.804812834224599e-05,
      "loss": 0.1364,
      "step": 780
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8021390374331554e-05,
      "loss": 0.0667,
      "step": 790
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.799465240641711e-05,
      "loss": 0.1409,
      "step": 800
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.796791443850268e-05,
      "loss": 0.0897,
      "step": 810
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.794117647058824e-05,
      "loss": 0.0871,
      "step": 820
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.79144385026738e-05,
      "loss": 0.0552,
      "step": 830
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.788770053475936e-05,
      "loss": 0.2569,
      "step": 840
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.786096256684492e-05,
      "loss": 0.2877,
      "step": 850
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.783422459893048e-05,
      "loss": 0.1365,
      "step": 860
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7807486631016047e-05,
      "loss": 0.1604,
      "step": 870
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7780748663101606e-05,
      "loss": 0.2179,
      "step": 880
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7754010695187165e-05,
      "loss": 0.0969,
      "step": 890
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.772727272727273e-05,
      "loss": 0.0953,
      "step": 900
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.770053475935829e-05,
      "loss": 0.0803,
      "step": 910
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7673796791443855e-05,
      "loss": 0.1573,
      "step": 920
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7647058823529414e-05,
      "loss": 0.1388,
      "step": 930
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7620320855614973e-05,
      "loss": 0.1559,
      "step": 940
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.759358288770054e-05,
      "loss": 0.2411,
      "step": 950
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.75668449197861e-05,
      "loss": 0.1119,
      "step": 960
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.754010695187166e-05,
      "loss": 0.1416,
      "step": 970
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.751336898395722e-05,
      "loss": 0.1073,
      "step": 980
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.748663101604278e-05,
      "loss": 0.1799,
      "step": 990
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.745989304812835e-05,
      "loss": 0.127,
      "step": 1000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.847809667673716,
      "eval_f1": 0.8460260531471735,
      "eval_loss": 1.017073392868042,
      "eval_precision": 0.8647086198841812,
      "eval_recall": 0.847809667673716,
      "eval_runtime": 10.5379,
      "eval_samples_per_second": 251.284,
      "eval_steps_per_second": 3.986,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 18750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 8419629367296000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}