last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7863522686673812,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 9.826661901358113e-05,
      "loss": 2.8742,
      "step": 500
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.647962830593282e-05,
      "loss": 1.8355,
      "step": 1000
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.46926375982845e-05,
      "loss": 1.6456,
      "step": 1500
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.290564689063618e-05,
      "loss": 1.5151,
      "step": 2000
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.111865618298785e-05,
      "loss": 1.3961,
      "step": 2500
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.933166547533954e-05,
      "loss": 1.3182,
      "step": 3000
    },
    {
      "epoch": 0.63,
      "learning_rate": 8.754467476769121e-05,
      "loss": 1.2625,
      "step": 3500
    },
    {
      "epoch": 0.71,
      "learning_rate": 8.575768406004289e-05,
      "loss": 1.2033,
      "step": 4000
    },
    {
      "epoch": 0.8,
      "learning_rate": 8.397069335239457e-05,
      "loss": 1.1532,
      "step": 4500
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.218370264474626e-05,
      "loss": 1.1099,
      "step": 5000
    },
    {
      "epoch": 0.98,
      "learning_rate": 8.039671193709793e-05,
      "loss": 1.0695,
      "step": 5500
    },
    {
      "epoch": 1.07,
      "learning_rate": 7.860972122944961e-05,
      "loss": 1.0133,
      "step": 6000
    },
    {
      "epoch": 1.16,
      "learning_rate": 7.682273052180129e-05,
      "loss": 0.964,
      "step": 6500
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.503573981415298e-05,
      "loss": 0.9535,
      "step": 7000
    },
    {
      "epoch": 1.34,
      "learning_rate": 7.324874910650465e-05,
      "loss": 0.9368,
      "step": 7500
    },
    {
      "epoch": 1.43,
      "learning_rate": 7.146175839885633e-05,
      "loss": 0.91,
      "step": 8000
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.9674767691208e-05,
      "loss": 0.8902,
      "step": 8500
    },
    {
      "epoch": 1.61,
      "learning_rate": 6.78877769835597e-05,
      "loss": 0.8761,
      "step": 9000
    },
    {
      "epoch": 1.7,
      "learning_rate": 6.610078627591136e-05,
      "loss": 0.8699,
      "step": 9500
    },
    {
      "epoch": 1.79,
      "learning_rate": 6.431379556826305e-05,
      "loss": 0.8455,
      "step": 10000
    }
  ],
  "max_steps": 27990,
  "num_train_epochs": 5,
  "total_flos": 1.08466293178368e+16,
  "trial_name": null,
  "trial_params": null
}