distilbert/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.871395167575994,
  "global_step": 12500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.6662,
      "step": 500
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.797242497972425e-05,
      "loss": 0.6142,
      "step": 1000
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.59448499594485e-05,
      "loss": 0.5878,
      "step": 1500
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.3917274939172754e-05,
      "loss": 0.5643,
      "step": 2000
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.1889699918897e-05,
      "loss": 0.5491,
      "step": 2500
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.986212489862125e-05,
      "loss": 0.4594,
      "step": 3000
    },
    {
      "epoch": 1.36,
      "learning_rate": 3.78345498783455e-05,
      "loss": 0.4472,
      "step": 3500
    },
    {
      "epoch": 1.56,
      "learning_rate": 3.580697485806975e-05,
      "loss": 0.4444,
      "step": 4000
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.3779399837794e-05,
      "loss": 0.4378,
      "step": 4500
    },
    {
      "epoch": 1.95,
      "learning_rate": 3.175182481751825e-05,
      "loss": 0.4435,
      "step": 5000
    },
    {
      "epoch": 2.14,
      "learning_rate": 2.9724249797242497e-05,
      "loss": 0.3289,
      "step": 5500
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.7696674776966745e-05,
      "loss": 0.3034,
      "step": 6000
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.5669099756691e-05,
      "loss": 0.3032,
      "step": 6500
    },
    {
      "epoch": 2.73,
      "learning_rate": 2.3641524736415248e-05,
      "loss": 0.3143,
      "step": 7000
    },
    {
      "epoch": 2.92,
      "learning_rate": 2.1613949716139496e-05,
      "loss": 0.3103,
      "step": 7500
    },
    {
      "epoch": 3.12,
      "learning_rate": 1.9586374695863748e-05,
      "loss": 0.2347,
      "step": 8000
    },
    {
      "epoch": 3.31,
      "learning_rate": 1.7558799675587996e-05,
      "loss": 0.1855,
      "step": 8500
    },
    {
      "epoch": 3.51,
      "learning_rate": 1.5531224655312247e-05,
      "loss": 0.1866,
      "step": 9000
    },
    {
      "epoch": 3.7,
      "learning_rate": 1.3503649635036497e-05,
      "loss": 0.1878,
      "step": 9500
    },
    {
      "epoch": 3.9,
      "learning_rate": 1.1476074614760747e-05,
      "loss": 0.1993,
      "step": 10000
    },
    {
      "epoch": 4.09,
      "learning_rate": 9.448499594484997e-06,
      "loss": 0.1487,
      "step": 10500
    },
    {
      "epoch": 4.29,
      "learning_rate": 7.420924574209247e-06,
      "loss": 0.108,
      "step": 11000
    },
    {
      "epoch": 4.48,
      "learning_rate": 5.393349553933496e-06,
      "loss": 0.107,
      "step": 11500
    },
    {
      "epoch": 4.68,
      "learning_rate": 3.365774533657746e-06,
      "loss": 0.1145,
      "step": 12000
    },
    {
      "epoch": 4.87,
      "learning_rate": 1.3381995133819951e-06,
      "loss": 0.112,
      "step": 12500
    }
  ],
  "max_steps": 12830,
  "num_train_epochs": 5,
  "total_flos": 2.648553168728064e+16,
  "trial_name": null,
  "trial_params": null
}