trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.2745098039215685,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.0663,
      "step": 10
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 2.0741,
      "step": 20
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.9687,
      "step": 30
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 1.9634,
      "step": 40
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 1.8635,
      "step": 50
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0002,
      "loss": 1.8845,
      "step": 60
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0002,
      "loss": 1.7803,
      "step": 70
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 1.6615,
      "step": 80
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0002,
      "loss": 1.7173,
      "step": 90
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0002,
      "loss": 1.6624,
      "step": 100
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0002,
      "loss": 1.3819,
      "step": 110
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0002,
      "loss": 1.5122,
      "step": 120
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0002,
      "loss": 1.5129,
      "step": 130
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0002,
      "loss": 1.3089,
      "step": 140
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0002,
      "loss": 1.2554,
      "step": 150
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0002,
      "loss": 1.3004,
      "step": 160
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0002,
      "loss": 1.1838,
      "step": 170
    },
    {
      "epoch": 5.65,
      "learning_rate": 0.0002,
      "loss": 1.0549,
      "step": 180
    },
    {
      "epoch": 5.96,
      "learning_rate": 0.0002,
      "loss": 1.1998,
      "step": 190
    },
    {
      "epoch": 6.27,
      "learning_rate": 0.0002,
      "loss": 0.9754,
      "step": 200
    },
    {
      "epoch": 6.27,
      "step": 200,
      "total_flos": 1.7550743484911616e+17,
      "train_loss": 1.5663859701156617,
      "train_runtime": 4414.9851,
      "train_samples_per_second": 1.45,
      "train_steps_per_second": 0.045
    }
  ],
  "max_steps": 200,
  "num_train_epochs": 7,
  "total_flos": 1.7550743484911616e+17,
  "trial_name": null,
  "trial_params": null
}