trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12195121951219512,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 1.1529,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0,
      "loss": 1.7234,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 1.1025,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 0.8796,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.9621,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.2671,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6072,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.0546,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.12,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.12,
      "step": 20,
      "total_flos": 825752514723840.0,
      "train_loss": 0.38747100830078124,
      "train_runtime": 30.2879,
      "train_samples_per_second": 2.641,
      "train_steps_per_second": 0.66
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 825752514723840.0,
  "trial_name": null,
  "trial_params": null
}