trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09992006394884093,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9246,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9273,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8793,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.8658,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7721,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.8723,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.7366,
      "step": 175
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.8426,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.7238,
      "step": 225
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.8572,
      "step": 250
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.7551,
      "step": 275
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.793,
      "step": 300
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.7013,
      "step": 325
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.8157,
      "step": 350
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5965,
      "step": 375
    }
  ],
  "max_steps": 3753,
  "num_train_epochs": 1,
  "total_flos": 6702415080751104.0,
  "trial_name": null,
  "trial_params": null
}