trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018017206432142698,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.00019286154021410173,
      "loss": 1.2716,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017685069172190766,
      "loss": 0.7488,
      "step": 200
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015331716207371888,
      "loss": 0.6891,
      "step": 300
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012456457711924266,
      "loss": 0.6518,
      "step": 400
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.340744020486222e-05,
      "loss": 0.5708,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.289562897629492e-05,
      "loss": 0.5851,
      "step": 600
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.601585210488218e-05,
      "loss": 0.7217,
      "step": 700
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.539928943321579e-05,
      "loss": 0.5756,
      "step": 800
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.064033759637064e-06,
      "loss": 0.6207,
      "step": 900
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.175458542558517e-07,
      "loss": 0.6222,
      "step": 1000
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 1,
  "total_flos": 2797918542102528.0,
  "trial_name": null,
  "trial_params": null
}