trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9991941982272361,
  "global_step": 465,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 1.2313,
      "step": 20
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 1.1365,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 1.1187,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 2e-05,
      "loss": 1.1067,
      "step": 80
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 1.0958,
      "step": 100
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 1.0903,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 1.0814,
      "step": 140
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 1.0766,
      "step": 160
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 1.0733,
      "step": 180
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 1.0727,
      "step": 200
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 1.0602,
      "step": 220
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 1.0604,
      "step": 240
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 1.058,
      "step": 260
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 1.0519,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 1.0468,
      "step": 300
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 1.0466,
      "step": 320
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 1.0425,
      "step": 340
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 1.0432,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 1.0399,
      "step": 380
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 1.0364,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 1.0309,
      "step": 420
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 1.0274,
      "step": 440
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 1.0269,
      "step": 460
    }
  ],
  "max_steps": 465,
  "num_train_epochs": 1,
  "total_flos": 3639334498467840.0,
  "trial_name": null,
  "trial_params": null
}