low-shot-task-specific-500-ex/coin_flip/checkpoint-60/trainer_state.json

{
  "best_metric": 0.16547438502311707,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/coin_flip/checkpoint-49",
  "epoch": 9.795918367346939,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.98,
      "eval_loss": 3.1955792903900146,
      "eval_runtime": 1.7606,
      "eval_samples_per_second": 27.832,
      "eval_steps_per_second": 3.976,
      "step": 6
    },
    {
      "epoch": 1.63,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.5618,
      "step": 10
    },
    {
      "epoch": 1.96,
      "eval_loss": 1.2319456338882446,
      "eval_runtime": 1.775,
      "eval_samples_per_second": 27.605,
      "eval_steps_per_second": 3.944,
      "step": 12
    },
    {
      "epoch": 2.94,
      "eval_loss": 0.3878885507583618,
      "eval_runtime": 1.7784,
      "eval_samples_per_second": 27.553,
      "eval_steps_per_second": 3.936,
      "step": 18
    },
    {
      "epoch": 3.27,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.8597,
      "step": 20
    },
    {
      "epoch": 3.92,
      "eval_loss": 0.21831320226192474,
      "eval_runtime": 1.7786,
      "eval_samples_per_second": 27.549,
      "eval_steps_per_second": 3.936,
      "step": 24
    },
    {
      "epoch": 4.9,
      "learning_rate": 4e-05,
      "loss": 0.2398,
      "step": 30
    },
    {
      "epoch": 4.9,
      "eval_loss": 0.18551723659038544,
      "eval_runtime": 1.7792,
      "eval_samples_per_second": 27.54,
      "eval_steps_per_second": 3.934,
      "step": 30
    },
    {
      "epoch": 5.88,
      "eval_loss": 0.1781032681465149,
      "eval_runtime": 1.7761,
      "eval_samples_per_second": 27.588,
      "eval_steps_per_second": 3.941,
      "step": 36
    },
    {
      "epoch": 6.53,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.1729,
      "step": 40
    },
    {
      "epoch": 6.86,
      "eval_loss": 0.17477163672447205,
      "eval_runtime": 1.7765,
      "eval_samples_per_second": 27.583,
      "eval_steps_per_second": 3.94,
      "step": 42
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.16547438502311707,
      "eval_runtime": 1.7731,
      "eval_samples_per_second": 27.635,
      "eval_steps_per_second": 3.948,
      "step": 49
    },
    {
      "epoch": 8.16,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.1579,
      "step": 50
    },
    {
      "epoch": 8.98,
      "eval_loss": 0.18015137314796448,
      "eval_runtime": 1.7751,
      "eval_samples_per_second": 27.604,
      "eval_steps_per_second": 3.943,
      "step": 55
    },
    {
      "epoch": 9.8,
      "learning_rate": 0.0,
      "loss": 0.1442,
      "step": 60
    },
    {
      "epoch": 9.8,
      "eval_loss": 0.1699230819940567,
      "eval_runtime": 1.7773,
      "eval_samples_per_second": 27.57,
      "eval_steps_per_second": 3.939,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7168130697461760.0,
  "trial_name": null,
  "trial_params": null
}