{
  "best_metric": 0.7091297032684482,
  "best_model_checkpoint": "transformers/checkpoint/vent/linear_probe_ft_cont/vent_bernice_lr1e-5_embdrop0.1_labelsmoothing0.1_42_jointsupcl/checkpoint-11500",
  "epoch": 0.46387802024928404,
  "global_step": 11500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0005,
      "loss": 1.224,
      "step": 500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0005,
      "loss": 1.1917,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "step": 1000,
      "total_flos": 1.6839561117696e+16,
      "train_loss": 1.2078435668945313,
      "train_runtime": 247.7258,
      "train_samples_per_second": 1033.4,
      "train_steps_per_second": 4.037
    },
    {
      "epoch": 0.06,
      "learning_rate": 1e-05,
      "loss": 4.8868,
      "step": 1500
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.6693328022956848,
      "eval_loss": 4.761493682861328,
      "eval_macroPrec": 0.673714797769901,
      "eval_macroRec": 0.6665857187883608,
      "eval_macrof1": 0.6679247692492374,
      "eval_runtime": 599.7459,
      "eval_samples_per_second": 1175.733,
      "eval_steps_per_second": 4.594,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "learning_rate": 1e-05,
      "loss": 4.7865,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.6801448464393616,
      "eval_loss": 4.736236572265625,
      "eval_macroPrec": 0.6789197866299151,
      "eval_macroRec": 0.6820194214808827,
      "eval_macrof1": 0.6792291630889113,
      "eval_runtime": 578.3287,
      "eval_samples_per_second": 1219.274,
      "eval_steps_per_second": 4.764,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 4.7608,
      "step": 2500
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.6877347826957703,
      "eval_loss": 4.717987537384033,
      "eval_macroPrec": 0.6935462320329414,
      "eval_macroRec": 0.684167600736026,
      "eval_macrof1": 0.6858003553695454,
      "eval_runtime": 577.8607,
      "eval_samples_per_second": 1220.261,
      "eval_steps_per_second": 4.768,
      "step": 2500
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 4.7529,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.6885204315185547,
      "eval_loss": 4.716394901275635,
      "eval_macroPrec": 0.6948738613915024,
      "eval_macroRec": 0.6856825977848897,
      "eval_macrof1": 0.6876887565361411,
      "eval_runtime": 577.0236,
      "eval_samples_per_second": 1222.032,
      "eval_steps_per_second": 4.775,
      "step": 3000
    },
    {
      "epoch": 0.14,
      "learning_rate": 1e-05,
      "loss": 4.7382,
      "step": 3500
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.695059597492218,
      "eval_loss": 4.704948902130127,
      "eval_macroPrec": 0.7011306349125166,
      "eval_macroRec": 0.6888804113847884,
      "eval_macrof1": 0.6931494236874167,
      "eval_runtime": 576.8932,
      "eval_samples_per_second": 1222.308,
      "eval_steps_per_second": 4.776,
      "step": 3500
    },
    {
      "epoch": 0.16,
      "learning_rate": 1e-05,
      "loss": 4.7348,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.6983993053436279,
      "eval_loss": 4.708113193511963,
      "eval_macroPrec": 0.7063721040316608,
      "eval_macroRec": 0.6894054446460803,
      "eval_macrof1": 0.6957023053182533,
      "eval_runtime": 577.0472,
      "eval_samples_per_second": 1221.982,
      "eval_steps_per_second": 4.774,
      "step": 4000
    },
    {
      "epoch": 0.18,
      "learning_rate": 1e-05,
      "loss": 4.7271,
      "step": 4500
    },
    {
      "epoch": 0.18,
      "eval_accuracy": 0.6965146064758301,
      "eval_loss": 4.703989505767822,
      "eval_macroPrec": 0.7016966733736484,
      "eval_macroRec": 0.6930968979067849,
      "eval_macrof1": 0.6956711319634581,
      "eval_runtime": 575.3624,
      "eval_samples_per_second": 1225.56,
      "eval_steps_per_second": 4.788,
      "step": 4500
    },
    {
      "epoch": 0.2,
      "learning_rate": 1e-05,
      "loss": 4.7259,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.69874107837677,
      "eval_loss": 4.702021598815918,
      "eval_macroPrec": 0.7016042945042669,
      "eval_macroRec": 0.6974226584847779,
      "eval_macrof1": 0.6986616770403948,
      "eval_runtime": 575.2314,
      "eval_samples_per_second": 1225.839,
      "eval_steps_per_second": 4.789,
      "step": 5000
    },
    {
      "epoch": 0.22,
      "learning_rate": 1e-05,
      "loss": 4.7197,
      "step": 5500
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.6974264979362488,
      "eval_loss": 4.707930564880371,
      "eval_macroPrec": 0.7003383131143052,
      "eval_macroRec": 0.6976402031572404,
      "eval_macrof1": 0.6962975286974858,
      "eval_runtime": 575.3071,
      "eval_samples_per_second": 1225.677,
      "eval_steps_per_second": 4.789,
      "step": 5500
    },
    {
      "epoch": 0.24,
      "learning_rate": 1e-05,
      "loss": 4.7135,
      "step": 6000
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.7048065662384033,
      "eval_loss": 4.693523406982422,
      "eval_macroPrec": 0.7054175910959026,
      "eval_macroRec": 0.7021117345379546,
      "eval_macrof1": 0.7034792144842983,
      "eval_runtime": 575.4054,
      "eval_samples_per_second": 1225.468,
      "eval_steps_per_second": 4.788,
      "step": 6000
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-05,
      "loss": 4.7118,
      "step": 6500
    },
    {
      "epoch": 0.26,
      "eval_accuracy": 0.7045952677726746,
      "eval_loss": 4.700965881347656,
      "eval_macroPrec": 0.7048673550484386,
      "eval_macroRec": 0.7022521214081285,
      "eval_macrof1": 0.703096187006955,
      "eval_runtime": 575.3149,
      "eval_samples_per_second": 1225.661,
      "eval_steps_per_second": 4.789,
      "step": 6500
    },
    {
      "epoch": 0.28,
      "learning_rate": 1e-05,
      "loss": 4.7101,
      "step": 7000
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.7059183716773987,
      "eval_loss": 4.694024562835693,
      "eval_macroPrec": 0.7049601649874102,
      "eval_macroRec": 0.7057936031010754,
      "eval_macrof1": 0.7049956470156717,
      "eval_runtime": 575.6186,
      "eval_samples_per_second": 1225.014,
      "eval_steps_per_second": 4.786,
      "step": 7000
    },
    {
      "epoch": 0.3,
      "learning_rate": 1e-05,
      "loss": 4.7035,
      "step": 7500
    },
    {
      "epoch": 0.3,
      "eval_accuracy": 0.7056205868721008,
      "eval_loss": 4.702441692352295,
      "eval_macroPrec": 0.7058376660421668,
      "eval_macroRec": 0.7052063553135387,
      "eval_macrof1": 0.7050265253043888,
      "eval_runtime": 575.0614,
      "eval_samples_per_second": 1226.201,
      "eval_steps_per_second": 4.791,
      "step": 7500
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-05,
      "loss": 4.7036,
      "step": 8000
    },
    {
      "epoch": 0.32,
      "eval_accuracy": 0.7070202827453613,
      "eval_loss": 4.692503452301025,
      "eval_macroPrec": 0.7096606504418442,
      "eval_macroRec": 0.7034349307228963,
      "eval_macrof1": 0.7056030837342271,
      "eval_runtime": 575.3402,
      "eval_samples_per_second": 1225.607,
      "eval_steps_per_second": 4.788,
      "step": 8000
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 4.7041,
      "step": 8500
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.7082498669624329,
      "eval_loss": 4.698132514953613,
      "eval_macroPrec": 0.7126236486682623,
      "eval_macroRec": 0.7034168237683918,
      "eval_macrof1": 0.7064635115147275,
      "eval_runtime": 575.5597,
      "eval_samples_per_second": 1225.14,
      "eval_steps_per_second": 4.787,
      "step": 8500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1e-05,
      "loss": 4.7032,
      "step": 9000
    },
    {
      "epoch": 0.36,
      "eval_accuracy": 0.7080697417259216,
      "eval_loss": 4.700057029724121,
      "eval_macroPrec": 0.7085243650622768,
      "eval_macroRec": 0.7073288346726845,
      "eval_macrof1": 0.707453549137527,
      "eval_runtime": 575.3159,
      "eval_samples_per_second": 1225.659,
      "eval_steps_per_second": 4.789,
      "step": 9000
    },
    {
      "epoch": 0.38,
      "learning_rate": 1e-05,
      "loss": 4.6971,
      "step": 9500
    },
    {
      "epoch": 0.38,
      "eval_accuracy": 0.7096211910247803,
      "eval_loss": 4.695491790771484,
      "eval_macroPrec": 0.7093534257679457,
      "eval_macroRec": 0.7089873902352126,
      "eval_macrof1": 0.7089231628132355,
      "eval_runtime": 575.2922,
      "eval_samples_per_second": 1225.709,
      "eval_steps_per_second": 4.789,
      "step": 9500
    },
    {
      "epoch": 0.4,
      "learning_rate": 1e-05,
      "loss": 4.697,
      "step": 10000
    },
    {
      "epoch": 0.4,
      "eval_accuracy": 0.7091531753540039,
      "eval_loss": 4.69527530670166,
      "eval_macroPrec": 0.7115081483863327,
      "eval_macroRec": 0.7068199357358054,
      "eval_macrof1": 0.7085571548254068,
      "eval_runtime": 575.5537,
      "eval_samples_per_second": 1225.152,
      "eval_steps_per_second": 4.787,
      "step": 10000
    },
    {
      "epoch": 0.42,
      "learning_rate": 1e-05,
      "loss": 4.6962,
      "step": 10500
    },
    {
      "epoch": 0.42,
      "eval_accuracy": 0.7073847651481628,
      "eval_loss": 4.711122989654541,
      "eval_macroPrec": 0.7123855412743447,
      "eval_macroRec": 0.7031976032088301,
      "eval_macrof1": 0.7063874239625263,
      "eval_runtime": 575.4008,
      "eval_samples_per_second": 1225.478,
      "eval_steps_per_second": 4.788,
      "step": 10500
    },
    {
      "epoch": 0.44,
      "learning_rate": 1e-05,
      "loss": 4.6967,
      "step": 11000
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.7083250284194946,
      "eval_loss": 4.702260494232178,
      "eval_macroPrec": 0.7106193512409639,
      "eval_macroRec": 0.707312062312635,
      "eval_macrof1": 0.7078044182223,
      "eval_runtime": 576.2666,
      "eval_samples_per_second": 1223.637,
      "eval_steps_per_second": 4.781,
      "step": 11000
    },
    {
      "epoch": 0.46,
      "learning_rate": 1e-05,
      "loss": 4.6933,
      "step": 11500
    },
    {
      "epoch": 0.46,
      "eval_accuracy": 0.7103700041770935,
      "eval_loss": 4.70102596282959,
      "eval_macroPrec": 0.7089688659300091,
      "eval_macroRec": 0.7097678048602494,
      "eval_macrof1": 0.7091297032684482,
      "eval_runtime": 570.7047,
      "eval_samples_per_second": 1235.562,
      "eval_steps_per_second": 4.827,
      "step": 11500
    }
  ],
  "max_steps": 123955,
  "num_train_epochs": 5,
  "total_flos": 1.93654952853504e+17,
  "trial_name": null,
  "trial_params": null
}