trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990680335507922,
  "eval_steps": 500,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.5126,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.2003,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.757,
      "step": 6
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.6726,
      "step": 8
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.6462,
      "step": 10
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.5562,
      "step": 12
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.9898,
      "step": 14
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.9362,
      "step": 16
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.2908,
      "step": 18
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.9168,
      "step": 20
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.7947,
      "step": 22
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.8443,
      "step": 24
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.5734,
      "step": 26
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.6823,
      "step": 28
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.7899,
      "step": 30
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.8474,
      "step": 32
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 2.0992,
      "step": 34
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.8281,
      "step": 36
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.737,
      "step": 38
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.7205,
      "step": 40
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.5048,
      "step": 42
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.7679,
      "step": 44
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.8433,
      "step": 46
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.6205,
      "step": 48
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 2.5937,
      "step": 50
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.5589,
      "step": 52
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.7151,
      "step": 54
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.7156,
      "step": 56
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.418,
      "step": 58
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.4181,
      "step": 60
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.6132,
      "step": 62
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.4498,
      "step": 64
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.8295,
      "step": 66
    }
  ],
  "logging_steps": 2,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2957918219354112.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}