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

{
  "best_metric": 0.13983282446861267,
  "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific/emotion/checkpoint-150",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 6.4494,
      "step": 10
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00011999999999999999,
      "loss": 5.0703,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.654482126235962,
      "eval_runtime": 6.8374,
      "eval_samples_per_second": 29.251,
      "eval_steps_per_second": 3.656,
      "step": 25
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.9694,
      "step": 30
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.4062,
      "step": 40
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0003,
      "loss": 0.248,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.22630518674850464,
      "eval_runtime": 6.8055,
      "eval_samples_per_second": 29.388,
      "eval_steps_per_second": 3.674,
      "step": 50
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.000285,
      "loss": 0.1644,
      "step": 60
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00027,
      "loss": 0.1532,
      "step": 70
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.17524582147598267,
      "eval_runtime": 6.7943,
      "eval_samples_per_second": 29.437,
      "eval_steps_per_second": 3.68,
      "step": 75
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.00025499999999999996,
      "loss": 0.1291,
      "step": 80
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.082,
      "step": 90
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.000225,
      "loss": 0.0672,
      "step": 100
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.14034521579742432,
      "eval_runtime": 6.8294,
      "eval_samples_per_second": 29.285,
      "eval_steps_per_second": 3.661,
      "step": 100
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0443,
      "step": 110
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.000195,
      "loss": 0.0505,
      "step": 120
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.187747061252594,
      "eval_runtime": 6.8658,
      "eval_samples_per_second": 29.13,
      "eval_steps_per_second": 3.641,
      "step": 125
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.042,
      "step": 130
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.000165,
      "loss": 0.0225,
      "step": 140
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.00015,
      "loss": 0.0131,
      "step": 150
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.13983282446861267,
      "eval_runtime": 6.8662,
      "eval_samples_per_second": 29.128,
      "eval_steps_per_second": 3.641,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.692015121170432e+16,
  "trial_name": null,
  "trial_params": null
}