last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6464646464646465,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.9457994579945803e-05,
      "loss": 4.3763,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.878048780487805e-05,
      "loss": 3.8394,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.81029810298103e-05,
      "loss": 3.639,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7425474254742554e-05,
      "loss": 3.7962,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.6747967479674795e-05,
      "loss": 3.5152,
      "step": 25
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.607046070460705e-05,
      "loss": 3.5752,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.53929539295393e-05,
      "loss": 3.4463,
      "step": 35
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.4715447154471546e-05,
      "loss": 3.5218,
      "step": 40
    },
    {
      "epoch": 0.32,
      "eval_loss": 3.2419066429138184,
      "eval_rouge2_fmeasure": 0.0,
      "eval_rouge2_precision": 0.0,
      "eval_rouge2_recall": 0.0,
      "eval_runtime": 180.4791,
      "eval_samples_per_second": 0.15,
      "eval_steps_per_second": 0.078,
      "step": 40
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.4037940379403794e-05,
      "loss": 3.5264,
      "step": 45
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.336043360433605e-05,
      "loss": 3.6286,
      "step": 50
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.26829268292683e-05,
      "loss": 3.4611,
      "step": 55
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.2005420054200545e-05,
      "loss": 3.9319,
      "step": 60
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.132791327913279e-05,
      "loss": 3.7751,
      "step": 65
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.065040650406504e-05,
      "loss": 3.6241,
      "step": 70
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.9972899728997295e-05,
      "loss": 3.3906,
      "step": 75
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.9295392953929537e-05,
      "loss": 3.1815,
      "step": 80
    },
    {
      "epoch": 0.65,
      "eval_loss": 3.189028739929199,
      "eval_rouge2_fmeasure": 0.0,
      "eval_rouge2_precision": 0.0,
      "eval_rouge2_recall": 0.0,
      "eval_runtime": 265.9332,
      "eval_samples_per_second": 0.102,
      "eval_steps_per_second": 0.053,
      "step": 80
    }
  ],
  "max_steps": 369,
  "num_train_epochs": 3,
  "total_flos": 3121802347806720.0,
  "trial_name": null,
  "trial_params": null
}