checkpoint-200/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06666666666666667,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 9.4994,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 7.7223,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 7.3713,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 7.2695,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 7.2811,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 7.2291,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 7.1263,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 7.0881,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 6.5989,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 6.0091,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 5.5511,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 5.3413,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 5.1775,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 5.104,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 5.0133,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 4.9843,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 4.9256,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 4.8692,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 4.9233,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 4.9139,
      "step": 200
    }
  ],
  "max_steps": 3000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 83751862272000.0,
  "trial_name": null,
  "trial_params": null
}