trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 6e-06,
      "loss": 2.4875,
      "step": 1
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.3397051914493775,
      "eval_loss": 2.505859375,
      "eval_runtime": 5.7507,
      "eval_samples_per_second": 12.52,
      "eval_steps_per_second": 0.522,
      "step": 1
    },
    {
      "epoch": 0.22,
      "learning_rate": 6e-06,
      "loss": 2.5339,
      "step": 2
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.3397051914493775,
      "eval_loss": 2.505859375,
      "eval_runtime": 6.1033,
      "eval_samples_per_second": 11.797,
      "eval_steps_per_second": 0.492,
      "step": 2
    },
    {
      "epoch": 0.33,
      "learning_rate": 6e-06,
      "loss": 2.5161,
      "step": 3
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.3397051914493775,
      "eval_loss": 2.505859375,
      "eval_runtime": 5.249,
      "eval_samples_per_second": 13.717,
      "eval_steps_per_second": 0.572,
      "step": 3
    },
    {
      "epoch": 0.44,
      "learning_rate": 6e-06,
      "loss": 2.4524,
      "step": 4
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.3397051914493775,
      "eval_loss": 2.505859375,
      "eval_runtime": 5.2566,
      "eval_samples_per_second": 13.697,
      "eval_steps_per_second": 0.571,
      "step": 4
    },
    {
      "epoch": 0.56,
      "learning_rate": 6e-06,
      "loss": 2.554,
      "step": 5
    },
    {
      "epoch": 0.56,
      "eval_accuracy": 0.34155508574113225,
      "eval_loss": 2.478515625,
      "eval_runtime": 6.2098,
      "eval_samples_per_second": 11.595,
      "eval_steps_per_second": 0.483,
      "step": 5
    },
    {
      "epoch": 0.67,
      "learning_rate": 6e-06,
      "loss": 2.4678,
      "step": 6
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.34155508574113225,
      "eval_loss": 2.478515625,
      "eval_runtime": 6.0227,
      "eval_samples_per_second": 11.955,
      "eval_steps_per_second": 0.498,
      "step": 6
    },
    {
      "epoch": 0.78,
      "learning_rate": 6e-06,
      "loss": 2.4836,
      "step": 7
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.34584214235377025,
      "eval_loss": 2.447265625,
      "eval_runtime": 5.1937,
      "eval_samples_per_second": 13.863,
      "eval_steps_per_second": 0.578,
      "step": 7
    },
    {
      "epoch": 0.89,
      "learning_rate": 6e-06,
      "loss": 2.4138,
      "step": 8
    },
    {
      "epoch": 0.89,
      "eval_accuracy": 0.34728094902513507,
      "eval_loss": 2.4296875,
      "eval_runtime": 5.8071,
      "eval_samples_per_second": 12.399,
      "eval_steps_per_second": 0.517,
      "step": 8
    },
    {
      "epoch": 1.0,
      "learning_rate": 6e-06,
      "loss": 2.4551,
      "step": 9
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.348661028893587,
      "eval_loss": 2.412109375,
      "eval_runtime": 6.21,
      "eval_samples_per_second": 11.594,
      "eval_steps_per_second": 0.483,
      "step": 9
    },
    {
      "epoch": 1.0,
      "step": 9,
      "total_flos": 1309654646784.0,
      "train_loss": 2.4849175347222223,
      "train_runtime": 11422.0717,
      "train_samples_per_second": 0.025,
      "train_steps_per_second": 0.001
    }
  ],
  "max_steps": 9,
  "num_train_epochs": 1,
  "total_flos": 1309654646784.0,
  "trial_name": null,
  "trial_params": null
}