trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 2.2461,
      "step": 1
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9888308262251286e-05,
      "loss": 2.0273,
      "step": 2
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.955572805786141e-05,
      "loss": 1.8828,
      "step": 3
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.900968867902419e-05,
      "loss": 1.8164,
      "step": 4
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.826238774315995e-05,
      "loss": 1.6875,
      "step": 5
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7330518718298263e-05,
      "loss": 1.707,
      "step": 6
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 1.8535,
      "step": 7
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.9043,
      "step": 8
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.3653410243663953e-05,
      "loss": 1.6289,
      "step": 9
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 1.9473,
      "step": 10
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0747300935864245e-05,
      "loss": 1.1553,
      "step": 11
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.252699064135759e-06,
      "loss": 0.7178,
      "step": 12
    },
    {
      "epoch": 1.18,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.7715,
      "step": 13
    },
    {
      "epoch": 1.27,
      "learning_rate": 6.34658975633605e-06,
      "loss": 0.8613,
      "step": 14
    },
    {
      "epoch": 1.36,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.7061,
      "step": 15
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.6904,
      "step": 16
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.669481281701739e-06,
      "loss": 0.6143,
      "step": 17
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.7376122568400533e-06,
      "loss": 0.6147,
      "step": 18
    },
    {
      "epoch": 1.73,
      "learning_rate": 9.903113209758098e-07,
      "loss": 0.7466,
      "step": 19
    },
    {
      "epoch": 1.82,
      "learning_rate": 4.4427194213859216e-07,
      "loss": 0.6118,
      "step": 20
    },
    {
      "epoch": 1.82,
      "eval_loss": 2.4375,
      "eval_runtime": 0.6236,
      "eval_samples_per_second": 1.603,
      "eval_steps_per_second": 1.603,
      "step": 20
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.1169173774871478e-07,
      "loss": 0.6118,
      "step": 21
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 0.4739,
      "step": 22
    }
  ],
  "max_steps": 22,
  "num_train_epochs": 2,
  "total_flos": 274810798080.0,
  "trial_name": null,
  "trial_params": null
}