trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9567198177676538,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.2205,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.1951,
      "step": 20
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.1806,
      "step": 30
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.2663,
      "step": 40
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.4203,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.1419,
      "step": 60
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.0462,
      "step": 70
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.9591,
      "step": 80
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.9385,
      "step": 90
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.8939,
      "step": 100
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 2.0895,
      "step": 110
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.8045,
      "step": 120
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.8499,
      "step": 130
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.5251,
      "step": 140
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.43,
      "step": 150
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.8088,
      "step": 160
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.563,
      "step": 170
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.5985,
      "step": 180
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.3294,
      "step": 190
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.3141,
      "step": 200
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.5528,
      "step": 210
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "total_flos": 9629736393477120.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}