trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 300.0,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 10.0,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 1.6943,
      "step": 10
    },
    {
      "epoch": 20.0,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.5664,
      "step": 20
    },
    {
      "epoch": 30.0,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.274,
      "step": 30
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.8583,
      "step": 40
    },
    {
      "epoch": 50.0,
      "learning_rate": 0.00015,
      "loss": 0.2804,
      "step": 50
    },
    {
      "epoch": 60.0,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0656,
      "step": 60
    },
    {
      "epoch": 70.0,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0271,
      "step": 70
    },
    {
      "epoch": 80.0,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0218,
      "step": 80
    },
    {
      "epoch": 90.0,
      "learning_rate": 0.00027,
      "loss": 0.0196,
      "step": 90
    },
    {
      "epoch": 100.0,
      "learning_rate": 0.0003,
      "loss": 0.0142,
      "step": 100
    },
    {
      "epoch": 110.0,
      "learning_rate": 0.000285,
      "loss": 0.0029,
      "step": 110
    },
    {
      "epoch": 120.0,
      "learning_rate": 0.00027,
      "loss": 0.0002,
      "step": 120
    },
    {
      "epoch": 130.0,
      "learning_rate": 0.00025499999999999996,
      "loss": 0.0001,
      "step": 130
    },
    {
      "epoch": 140.0,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.0001,
      "step": 140
    },
    {
      "epoch": 150.0,
      "learning_rate": 0.000225,
      "loss": 0.0001,
      "step": 150
    },
    {
      "epoch": 160.0,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.0001,
      "step": 160
    },
    {
      "epoch": 170.0,
      "learning_rate": 0.000195,
      "loss": 0.0001,
      "step": 170
    },
    {
      "epoch": 180.0,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.0001,
      "step": 180
    },
    {
      "epoch": 190.0,
      "learning_rate": 0.000165,
      "loss": 0.0001,
      "step": 190
    },
    {
      "epoch": 200.0,
      "learning_rate": 0.00015,
      "loss": 0.0001,
      "step": 200
    },
    {
      "epoch": 210.0,
      "learning_rate": 0.000135,
      "loss": 0.0001,
      "step": 210
    },
    {
      "epoch": 220.0,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.0001,
      "step": 220
    },
    {
      "epoch": 230.0,
      "learning_rate": 0.00010499999999999999,
      "loss": 0.0001,
      "step": 230
    },
    {
      "epoch": 240.0,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 250.0,
      "learning_rate": 7.5e-05,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 260.0,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0,
      "step": 260
    },
    {
      "epoch": 270.0,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 0.0,
      "step": 270
    },
    {
      "epoch": 280.0,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.0,
      "step": 280
    },
    {
      "epoch": 290.0,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 300.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_train_epochs": 300,
  "save_steps": 50,
  "total_flos": 6188399493120000.0,
  "trial_name": null,
  "trial_params": null
}