low-shot-task-specific/svamp/best_model/trainer_state.json

{
  "best_metric": 0.5390210151672363,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific/svamp/checkpoint-52",
  "epoch": 2.9714285714285715,
  "eval_steps": 500,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.57,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 4.9058,
      "step": 10
    },
    {
      "epoch": 0.97,
      "eval_loss": 2.449695348739624,
      "eval_runtime": 6.0415,
      "eval_samples_per_second": 23.173,
      "eval_steps_per_second": 2.979,
      "step": 17
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00011999999999999999,
      "loss": 3.0825,
      "step": 20
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.2018,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6993179321289062,
      "eval_runtime": 6.0439,
      "eval_samples_per_second": 23.164,
      "eval_steps_per_second": 2.978,
      "step": 35
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.6819,
      "step": 40
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0003,
      "loss": 0.5012,
      "step": 50
    },
    {
      "epoch": 2.97,
      "eval_loss": 0.5390210151672363,
      "eval_runtime": 6.0418,
      "eval_samples_per_second": 23.172,
      "eval_steps_per_second": 2.979,
      "step": 52
    }
  ],
  "logging_steps": 10,
  "max_steps": 170,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 8725882453032960.0,
  "trial_name": null,
  "trial_params": null
}