trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.991150442477876,
  "global_step": 98,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 2.7205,
      "step": 3
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 2.7244,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 2.7638,
      "step": 9
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 2.7622,
      "step": 12
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 2.7498,
      "step": 15
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 2.7814,
      "step": 18
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 2.7404,
      "step": 21
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 2.8507,
      "step": 24
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 2.7969,
      "step": 27
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 2.7087,
      "step": 30
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 2.6703,
      "step": 33
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 2.7935,
      "step": 36
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 2.6768,
      "step": 39
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 2.7279,
      "step": 42
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 2.7542,
      "step": 45
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001,
      "loss": 2.7718,
      "step": 48
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 3.1325,
      "step": 51
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 2.6908,
      "step": 54
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 2.661,
      "step": 57
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001,
      "loss": 2.6744,
      "step": 60
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 2.7521,
      "step": 63
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 2.7165,
      "step": 66
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001,
      "loss": 2.752,
      "step": 69
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 2.7158,
      "step": 72
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 2.6624,
      "step": 75
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001,
      "loss": 2.7896,
      "step": 78
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001,
      "loss": 2.706,
      "step": 81
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001,
      "loss": 2.7365,
      "step": 84
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001,
      "loss": 2.7428,
      "step": 87
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001,
      "loss": 2.7072,
      "step": 90
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 2.7192,
      "step": 93
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 2.7297,
      "step": 96
    }
  ],
  "max_steps": 294,
  "num_train_epochs": 6,
  "total_flos": 4.665562387762381e+17,
  "trial_name": null,
  "trial_params": null
}