checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.055294442908487694,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.9999895164082156e-05,
      "loss": 1.6349,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999958065720787e-05,
      "loss": 1.6199,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999905648201487e-05,
      "loss": 1.4834,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999832264289934e-05,
      "loss": 1.3882,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999737914601591e-05,
      "loss": 1.3679,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999622599927756e-05,
      "loss": 1.2396,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999486321235559e-05,
      "loss": 1.321,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9993290796679516e-05,
      "loss": 1.2874,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999150876543699e-05,
      "loss": 1.2607,
      "step": 45
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9989517133573694e-05,
      "loss": 1.2454,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9987315917793174e-05,
      "loss": 1.2799,
      "step": 55
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.998490513655676e-05,
      "loss": 1.2575,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.998228481008337e-05,
      "loss": 1.2404,
      "step": 65
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.997945496034934e-05,
      "loss": 1.2219,
      "step": 70
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9976415611088267e-05,
      "loss": 1.2241,
      "step": 75
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.997316678779079e-05,
      "loss": 1.1716,
      "step": 80
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.996970851770438e-05,
      "loss": 1.1883,
      "step": 85
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9966040829833115e-05,
      "loss": 1.205,
      "step": 90
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9962163754937426e-05,
      "loss": 1.1246,
      "step": 95
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.995807732553384e-05,
      "loss": 1.1636,
      "step": 100
    }
  ],
  "max_steps": 5424,
  "num_train_epochs": 3,
  "total_flos": 3.2497031184384e+16,
  "trial_name": null,
  "trial_params": null
}