last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06063411247396436,
  "global_step": 524,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9997685720897943e-05,
      "loss": 2.316,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.969914371673224e-05,
      "loss": 2.907,
      "step": 131
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9398287433464477e-05,
      "loss": 2.8073,
      "step": 262
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9095116871094656e-05,
      "loss": 2.7381,
      "step": 393
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.8791946308724832e-05,
      "loss": 2.6726,
      "step": 524
    }
  ],
  "max_steps": 8642,
  "num_train_epochs": 1,
  "total_flos": 975816804532224.0,
  "trial_name": null,
  "trial_params": null
}