{
  "best_metric": 0.26428040862083435,
  "best_model_checkpoint": "YituTech/conv-bert-base/subtaskB/42/checkpoint-1776",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 8880,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.28,
      "learning_rate": 4.718468468468469e-05,
      "loss": 0.6011,
      "step": 500
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.4369369369369375e-05,
      "loss": 0.2811,
      "step": 1000
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.1554054054054055e-05,
      "loss": 0.2427,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.9117274391102351,
      "eval_loss": 0.26428040862083435,
      "eval_runtime": 93.1627,
      "eval_samples_per_second": 152.486,
      "eval_steps_per_second": 4.766,
      "step": 1776
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.873873873873874e-05,
      "loss": 0.1753,
      "step": 2000
    },
    {
      "epoch": 1.41,
      "learning_rate": 3.592342342342343e-05,
      "loss": 0.1239,
      "step": 2500
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.310810810810811e-05,
      "loss": 0.1203,
      "step": 3000
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.0292792792792797e-05,
      "loss": 0.1015,
      "step": 3500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.9108123328171195,
      "eval_loss": 0.3175283372402191,
      "eval_runtime": 93.2571,
      "eval_samples_per_second": 152.332,
      "eval_steps_per_second": 4.761,
      "step": 3552
    },
    {
      "epoch": 2.25,
      "learning_rate": 2.7477477477477483e-05,
      "loss": 0.0539,
      "step": 4000
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.4662162162162162e-05,
      "loss": 0.0475,
      "step": 4500
    },
    {
      "epoch": 2.82,
      "learning_rate": 2.1846846846846845e-05,
      "loss": 0.052,
      "step": 5000
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.9283401379698719,
      "eval_loss": 0.3505339026451111,
      "eval_runtime": 93.5325,
      "eval_samples_per_second": 151.883,
      "eval_steps_per_second": 4.747,
      "step": 5328
    },
    {
      "epoch": 3.1,
      "learning_rate": 1.9031531531531532e-05,
      "loss": 0.0305,
      "step": 5500
    },
    {
      "epoch": 3.38,
      "learning_rate": 1.6216216216216218e-05,
      "loss": 0.018,
      "step": 6000
    },
    {
      "epoch": 3.66,
      "learning_rate": 1.3400900900900901e-05,
      "loss": 0.0187,
      "step": 6500
    },
    {
      "epoch": 3.94,
      "learning_rate": 1.0585585585585586e-05,
      "loss": 0.0136,
      "step": 7000
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.9349570603970153,
      "eval_loss": 0.3897482752799988,
      "eval_runtime": 93.39,
      "eval_samples_per_second": 152.115,
      "eval_steps_per_second": 4.754,
      "step": 7104
    },
    {
      "epoch": 4.22,
      "learning_rate": 7.77027027027027e-06,
      "loss": 0.007,
      "step": 7500
    },
    {
      "epoch": 4.5,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.0024,
      "step": 8000
    },
    {
      "epoch": 4.79,
      "learning_rate": 2.1396396396396396e-06,
      "loss": 0.0035,
      "step": 8500
    },
    {
      "epoch": 5.0,
      "eval_f1": 0.9327748838518936,
      "eval_loss": 0.4131956994533539,
      "eval_runtime": 93.7438,
      "eval_samples_per_second": 151.541,
      "eval_steps_per_second": 4.736,
      "step": 8880
    }
  ],
  "logging_steps": 500,
  "max_steps": 8880,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 7.195127304250368e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}