trainer_state.json

{
  "best_metric": 0.8407772378261645,
  "best_model_checkpoint": "checkpoint/CAP_roberta_lr5e-5_embdrop0.1_labelsmoothing0.1_balanced/checkpoint-1100",
  "epoch": 4.522096608427543,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.41,
      "eval_accuracy": 0.7928023934364319,
      "eval_loss": 1.1060333251953125,
      "eval_macroPrec": 0.7617300562957272,
      "eval_macroRec": 0.7804989132215583,
      "eval_macrof1": 0.7624041375292132,
      "eval_runtime": 581.5836,
      "eval_samples_per_second": 53.177,
      "eval_steps_per_second": 3.324,
      "step": 100
    },
    {
      "epoch": 0.82,
      "eval_accuracy": 0.8181200623512268,
      "eval_loss": 1.0196324586868286,
      "eval_macroPrec": 0.7864785109728532,
      "eval_macroRec": 0.8026661148084082,
      "eval_macrof1": 0.7888372448488096,
      "eval_runtime": 581.7036,
      "eval_samples_per_second": 53.166,
      "eval_steps_per_second": 3.323,
      "step": 200
    },
    {
      "epoch": 1.23,
      "eval_accuracy": 0.8291783928871155,
      "eval_loss": 0.999952495098114,
      "eval_macroPrec": 0.8054333366415221,
      "eval_macroRec": 0.810411554185253,
      "eval_macrof1": 0.8048729185022913,
      "eval_runtime": 581.669,
      "eval_samples_per_second": 53.169,
      "eval_steps_per_second": 3.323,
      "step": 300
    },
    {
      "epoch": 1.64,
      "eval_accuracy": 0.83768230676651,
      "eval_loss": 0.9787802696228027,
      "eval_macroPrec": 0.8168532404676263,
      "eval_macroRec": 0.8195910229594843,
      "eval_macrof1": 0.8140468807730719,
      "eval_runtime": 581.6749,
      "eval_samples_per_second": 53.169,
      "eval_steps_per_second": 3.323,
      "step": 400
    },
    {
      "epoch": 2.06,
      "learning_rate": 5e-05,
      "loss": 1.2051,
      "step": 500
    },
    {
      "epoch": 2.06,
      "eval_accuracy": 0.8446018099784851,
      "eval_loss": 0.9603281021118164,
      "eval_macroPrec": 0.8141609394395297,
      "eval_macroRec": 0.8344439496827691,
      "eval_macrof1": 0.8204880440817254,
      "eval_runtime": 581.5182,
      "eval_samples_per_second": 53.183,
      "eval_steps_per_second": 3.324,
      "step": 500
    },
    {
      "epoch": 2.47,
      "eval_accuracy": 0.8457335233688354,
      "eval_loss": 0.9556291699409485,
      "eval_macroPrec": 0.8300101376455962,
      "eval_macroRec": 0.824375780701122,
      "eval_macrof1": 0.8250742223797913,
      "eval_runtime": 581.736,
      "eval_samples_per_second": 53.163,
      "eval_steps_per_second": 3.323,
      "step": 600
    },
    {
      "epoch": 2.88,
      "eval_accuracy": 0.8498399257659912,
      "eval_loss": 0.9379899501800537,
      "eval_macroPrec": 0.8295666021506038,
      "eval_macroRec": 0.8321904717387054,
      "eval_macrof1": 0.8290540592765423,
      "eval_runtime": 581.5277,
      "eval_samples_per_second": 53.182,
      "eval_steps_per_second": 3.324,
      "step": 700
    },
    {
      "epoch": 3.29,
      "eval_accuracy": 0.8535260558128357,
      "eval_loss": 0.9359630942344666,
      "eval_macroPrec": 0.8392464240325657,
      "eval_macroRec": 0.8320164505120938,
      "eval_macrof1": 0.8341211309544266,
      "eval_runtime": 581.7407,
      "eval_samples_per_second": 53.163,
      "eval_steps_per_second": 3.323,
      "step": 800
    },
    {
      "epoch": 3.7,
      "eval_accuracy": 0.8558540940284729,
      "eval_loss": 0.9286991953849792,
      "eval_macroPrec": 0.8406734329096902,
      "eval_macroRec": 0.8328819640638598,
      "eval_macrof1": 0.8359470595652772,
      "eval_runtime": 580.9985,
      "eval_samples_per_second": 53.231,
      "eval_steps_per_second": 3.327,
      "step": 900
    },
    {
      "epoch": 4.11,
      "learning_rate": 5e-05,
      "loss": 0.9523,
      "step": 1000
    },
    {
      "epoch": 4.11,
      "eval_accuracy": 0.8603485822677612,
      "eval_loss": 0.9251722097396851,
      "eval_macroPrec": 0.8421227676571199,
      "eval_macroRec": 0.8363366777340433,
      "eval_macrof1": 0.8383952111763313,
      "eval_runtime": 580.9643,
      "eval_samples_per_second": 53.234,
      "eval_steps_per_second": 3.327,
      "step": 1000
    },
    {
      "epoch": 4.52,
      "eval_accuracy": 0.8593462109565735,
      "eval_loss": 0.9215391874313354,
      "eval_macroPrec": 0.8352280429764268,
      "eval_macroRec": 0.848454411323337,
      "eval_macrof1": 0.8407772378261645,
      "eval_runtime": 580.9576,
      "eval_samples_per_second": 53.235,
      "eval_steps_per_second": 3.327,
      "step": 1100
    }
  ],
  "max_steps": 1215,
  "num_train_epochs": 5,
  "total_flos": 7.40920813179863e+16,
  "trial_name": null,
  "trial_params": null
}