checkpoint-200/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.64,
  "eval_steps": 500,
  "global_step": 200,
  "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": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 145
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 155
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 936,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5.180874638819328e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}