last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1966955153422502,
  "global_step": 14500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.0382,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 0.0375,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.0381,
      "step": 1500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.0369,
      "step": 2000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.036,
      "step": 2500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 0.0377,
      "step": 3000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.0373,
      "step": 3500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 0.0373,
      "step": 4000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0,
      "loss": 0.0357,
      "step": 4500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 0.0388,
      "step": 5000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 0.0372,
      "step": 5500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0,
      "loss": 0.0399,
      "step": 6000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 6500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0,
      "loss": 0.0382,
      "step": 7000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0,
      "loss": 0.0361,
      "step": 7500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 0.0358,
      "step": 8000
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.04,
      "step": 8500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0,
      "loss": 0.036,
      "step": 9000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 9500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0362,
      "step": 10000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 10500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 11000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.0385,
      "step": 11500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0,
      "loss": 0.0372,
      "step": 12000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0,
      "loss": 0.0364,
      "step": 12500
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 0.0368,
      "step": 13000
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0,
      "loss": 0.0408,
      "step": 13500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0,
      "loss": 0.0378,
      "step": 14000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0,
      "loss": 0.0376,
      "step": 14500
    }
  ],
  "max_steps": 73718,
  "num_train_epochs": 1,
  "total_flos": 1.5152101302730752e+16,
  "trial_name": null,
  "trial_params": null
}