trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0660980810234542,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 220
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 310
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 320
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 330
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 370
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 380
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 390
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 410
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 420
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 430
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 440
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 460
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 470
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 490
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 6.534086153899868e+17,
  "trial_name": null,
  "trial_params": null
}