last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.4461,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.428,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.2611,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.0726,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8897,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7397,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.699,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7029,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.63,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.7011,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5865,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.6309,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.5263,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5052,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5682,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5076,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.5277,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.4567,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4831,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4565,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.4851,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4713,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4407,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.486,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.4523,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4273383195279360.0,
  "trial_name": null,
  "trial_params": null
}