trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08574858514834505,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.6881,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.5965,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.5403,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.488,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4193,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.5918,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.4684,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.5298,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4885,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.3809,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.534,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4542,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4874,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.4379,
      "step": 140
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2407,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.5581,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.4943,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.4102,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.4299,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.2748,
      "step": 200
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.5647,
      "step": 210
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4367,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.4337,
      "step": 230
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3807,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.2684,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.5007,
      "step": 260
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.3955,
      "step": 270
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.3898,
      "step": 280
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.4153,
      "step": 290
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.1962,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.4459,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.3572,
      "step": 320
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.4047,
      "step": 330
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.3468,
      "step": 340
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.2472,
      "step": 350
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.4912,
      "step": 360
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.3635,
      "step": 370
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.3732,
      "step": 380
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.3813,
      "step": 390
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.0932,
      "step": 400
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.5275,
      "step": 410
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.3711,
      "step": 420
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.364,
      "step": 430
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.3475,
      "step": 440
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.2098,
      "step": 450
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.4563,
      "step": 460
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.385,
      "step": 470
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.3669,
      "step": 480
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.41,
      "step": 490
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.1759,
      "step": 500
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 1,
  "total_flos": 3.806741872341811e+16,
  "trial_name": null,
  "trial_params": null
}