trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1991,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 3.137,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 1.5273,
      "step": 200
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.9383,
      "step": 300
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.7065,
      "step": 400
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 0.6427,
      "step": 500
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.6353,
      "step": 600
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.6162,
      "step": 700
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.4643,
      "step": 800
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.6799,
      "step": 900
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 1000
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.5897,
      "step": 1100
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.5237,
      "step": 1200
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.5258,
      "step": 1300
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.426,
      "step": 1400
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.4769,
      "step": 1500
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.4128,
      "step": 1600
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.4171,
      "step": 1700
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.5292,
      "step": 1800
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 0.3795,
      "step": 1900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.2406361848115921,
      "eval_macro": 0.842884032309874,
      "eval_runtime": 3969.1213,
      "eval_samples_per_second": 1.88,
      "eval_steps_per_second": 1.88,
      "eval_w_f1": 0.9674330747694765,
      "step": 1991
    }
  ],
  "logging_steps": 100,
  "max_steps": 19910,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 3.306411198137549e+17,
  "trial_name": null,
  "trial_params": null
}