model/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2171372930866602,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 4.9075899457861016e-05,
      "loss": 2.0374,
      "step": 250
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.753573188762938e-05,
      "loss": 1.6902,
      "step": 500
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.599556431739773e-05,
      "loss": 1.6269,
      "step": 750
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.445539674716609e-05,
      "loss": 1.6167,
      "step": 1000
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.2915229176934454e-05,
      "loss": 1.568,
      "step": 1250
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.137506160670281e-05,
      "loss": 1.5706,
      "step": 1500
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.983489403647117e-05,
      "loss": 1.558,
      "step": 1750
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.829472646623953e-05,
      "loss": 1.5502,
      "step": 2000
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.675455889600789e-05,
      "loss": 1.534,
      "step": 2250
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.5214391325776246e-05,
      "loss": 1.5069,
      "step": 2500
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.367422375554461e-05,
      "loss": 1.5202,
      "step": 2750
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.213405618531297e-05,
      "loss": 1.4854,
      "step": 3000
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.059388861508132e-05,
      "loss": 1.4739,
      "step": 3250
    },
    {
      "epoch": 0.85,
      "learning_rate": 2.905372104484968e-05,
      "loss": 1.4941,
      "step": 3500
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.751355347461804e-05,
      "loss": 1.4642,
      "step": 3750
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.59733859043864e-05,
      "loss": 1.4524,
      "step": 4000
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.4433218334154756e-05,
      "loss": 1.3755,
      "step": 4250
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.2893050763923117e-05,
      "loss": 1.3779,
      "step": 4500
    },
    {
      "epoch": 1.16,
      "learning_rate": 2.1352883193691475e-05,
      "loss": 1.3758,
      "step": 4750
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.9812715623459833e-05,
      "loss": 1.3637,
      "step": 5000
    }
  ],
  "max_steps": 8216,
  "num_train_epochs": 2,
  "total_flos": 2861768122887168.0,
  "trial_name": null,
  "trial_params": null
}