checkpoint-20/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10666666666666667,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.9122,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 2.0707,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.9703,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.705882352941177e-05,
      "loss": 2.015,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.119,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.058823529411765e-05,
      "loss": 2.0515,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.23529411764706e-05,
      "loss": 1.7436,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.411764705882353e-05,
      "loss": 1.9326,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010588235294117647,
      "loss": 2.0819,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011764705882352942,
      "loss": 1.9965,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012941176470588237,
      "loss": 2.0543,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001411764705882353,
      "loss": 2.0461,
      "step": 12
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00015294117647058822,
      "loss": 2.311,
      "step": 13
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001647058823529412,
      "loss": 1.8447,
      "step": 14
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017647058823529413,
      "loss": 2.6263,
      "step": 15
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018823529411764707,
      "loss": 2.6179,
      "step": 16
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.535,
      "step": 17
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999833248118322,
      "loss": 2.5924,
      "step": 18
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999332998034514,
      "loss": 2.3562,
      "step": 19
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019998499266432108,
      "loss": 2.2352,
      "step": 20
    }
  ],
  "max_steps": 561,
  "num_train_epochs": 3,
  "total_flos": 5692200019230720.0,
  "trial_name": null,
  "trial_params": null
}