trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.666666666666666,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.82,
      "step": 10
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 2.2563,
      "step": 20
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.1476,
      "step": 30
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 2.1418,
      "step": 40
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 2.0863,
      "step": 50
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.9899,
      "step": 60
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 2.0048,
      "step": 70
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 1.9172,
      "step": 80
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0002,
      "loss": 1.8451,
      "step": 90
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 1.9007,
      "step": 100
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0002,
      "loss": 1.8438,
      "step": 110
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0002,
      "loss": 1.7509,
      "step": 120
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0002,
      "loss": 1.6939,
      "step": 130
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0002,
      "loss": 1.6918,
      "step": 140
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0002,
      "loss": 1.7208,
      "step": 150
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0002,
      "loss": 1.5775,
      "step": 160
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.0002,
      "loss": 1.5246,
      "step": 170
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0002,
      "loss": 1.5304,
      "step": 180
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.0002,
      "loss": 1.5009,
      "step": 190
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0002,
      "loss": 1.3492,
      "step": 200
    },
    {
      "epoch": 5.6,
      "learning_rate": 0.0002,
      "loss": 1.39,
      "step": 210
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.0002,
      "loss": 1.39,
      "step": 220
    },
    {
      "epoch": 6.13,
      "learning_rate": 0.0002,
      "loss": 1.2891,
      "step": 230
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0002,
      "loss": 1.2195,
      "step": 240
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0002,
      "loss": 1.2381,
      "step": 250
    },
    {
      "epoch": 6.93,
      "learning_rate": 0.0002,
      "loss": 1.2431,
      "step": 260
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.0002,
      "loss": 1.07,
      "step": 270
    },
    {
      "epoch": 7.47,
      "learning_rate": 0.0002,
      "loss": 1.0858,
      "step": 280
    },
    {
      "epoch": 7.73,
      "learning_rate": 0.0002,
      "loss": 1.0796,
      "step": 290
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0002,
      "loss": 1.107,
      "step": 300
    },
    {
      "epoch": 8.27,
      "learning_rate": 0.0002,
      "loss": 0.882,
      "step": 310
    },
    {
      "epoch": 8.53,
      "learning_rate": 0.0002,
      "loss": 0.9132,
      "step": 320
    },
    {
      "epoch": 8.8,
      "learning_rate": 0.0002,
      "loss": 0.9592,
      "step": 330
    },
    {
      "epoch": 9.07,
      "learning_rate": 0.0002,
      "loss": 0.9249,
      "step": 340
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.0002,
      "loss": 0.7599,
      "step": 350
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.0002,
      "loss": 0.7568,
      "step": 360
    },
    {
      "epoch": 9.87,
      "learning_rate": 0.0002,
      "loss": 0.7966,
      "step": 370
    },
    {
      "epoch": 10.13,
      "learning_rate": 0.0002,
      "loss": 0.7164,
      "step": 380
    },
    {
      "epoch": 10.4,
      "learning_rate": 0.0002,
      "loss": 0.6433,
      "step": 390
    },
    {
      "epoch": 10.67,
      "learning_rate": 0.0002,
      "loss": 0.6312,
      "step": 400
    }
  ],
  "max_steps": 401,
  "num_train_epochs": 11,
  "total_flos": 2.0280759172595712e+17,
  "trial_name": null,
  "trial_params": null
}