checkpoint-4100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 32.03103782735209,
  "global_step": 4100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 10.1861,
      "step": 100
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 9.3871,
      "step": 200
    },
    {
      "epoch": 2.34,
      "learning_rate": 3e-06,
      "loss": 8.9208,
      "step": 300
    },
    {
      "epoch": 3.12,
      "learning_rate": 4.000000000000001e-06,
      "loss": 8.5062,
      "step": 400
    },
    {
      "epoch": 3.9,
      "learning_rate": 5e-06,
      "loss": 7.9395,
      "step": 500
    },
    {
      "epoch": 4.68,
      "learning_rate": 6e-06,
      "loss": 7.4515,
      "step": 600
    },
    {
      "epoch": 5.47,
      "learning_rate": 7.000000000000001e-06,
      "loss": 6.9286,
      "step": 700
    },
    {
      "epoch": 6.25,
      "learning_rate": 8.000000000000001e-06,
      "loss": 6.5255,
      "step": 800
    },
    {
      "epoch": 7.03,
      "learning_rate": 9e-06,
      "loss": 6.2869,
      "step": 900
    },
    {
      "epoch": 7.81,
      "learning_rate": 1e-05,
      "loss": 6.1101,
      "step": 1000
    },
    {
      "epoch": 8.59,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 6.0904,
      "step": 1100
    },
    {
      "epoch": 9.37,
      "learning_rate": 1.2e-05,
      "loss": 6.0359,
      "step": 1200
    },
    {
      "epoch": 10.16,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 5.9918,
      "step": 1300
    },
    {
      "epoch": 10.93,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 5.9047,
      "step": 1400
    },
    {
      "epoch": 11.71,
      "learning_rate": 1.5e-05,
      "loss": 5.9245,
      "step": 1500
    },
    {
      "epoch": 12.5,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 5.8934,
      "step": 1600
    },
    {
      "epoch": 13.28,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 5.872,
      "step": 1700
    },
    {
      "epoch": 14.06,
      "learning_rate": 1.8e-05,
      "loss": 5.8497,
      "step": 1800
    },
    {
      "epoch": 14.84,
      "learning_rate": 1.9e-05,
      "loss": 5.7714,
      "step": 1900
    },
    {
      "epoch": 15.62,
      "learning_rate": 2e-05,
      "loss": 5.8107,
      "step": 2000
    },
    {
      "epoch": 16.4,
      "learning_rate": 2.1e-05,
      "loss": 5.7927,
      "step": 2100
    },
    {
      "epoch": 17.19,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 5.7739,
      "step": 2200
    },
    {
      "epoch": 17.96,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 5.7129,
      "step": 2300
    },
    {
      "epoch": 18.74,
      "learning_rate": 2.4e-05,
      "loss": 5.7431,
      "step": 2400
    },
    {
      "epoch": 19.53,
      "learning_rate": 2.5e-05,
      "loss": 5.7336,
      "step": 2500
    },
    {
      "epoch": 20.31,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 5.7209,
      "step": 2600
    },
    {
      "epoch": 21.09,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 5.7094,
      "step": 2700
    },
    {
      "epoch": 21.87,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 5.6441,
      "step": 2800
    },
    {
      "epoch": 22.65,
      "learning_rate": 2.9e-05,
      "loss": 5.6845,
      "step": 2900
    },
    {
      "epoch": 23.43,
      "learning_rate": 3e-05,
      "loss": 5.67,
      "step": 3000
    },
    {
      "epoch": 24.22,
      "learning_rate": 3.1e-05,
      "loss": 5.6608,
      "step": 3100
    },
    {
      "epoch": 24.99,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.6013,
      "step": 3200
    },
    {
      "epoch": 25.78,
      "learning_rate": 3.3e-05,
      "loss": 5.6329,
      "step": 3300
    },
    {
      "epoch": 26.56,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 5.6337,
      "step": 3400
    },
    {
      "epoch": 27.34,
      "learning_rate": 3.5e-05,
      "loss": 5.6169,
      "step": 3500
    },
    {
      "epoch": 28.12,
      "learning_rate": 3.6e-05,
      "loss": 5.6096,
      "step": 3600
    },
    {
      "epoch": 28.9,
      "learning_rate": 3.7e-05,
      "loss": 5.5511,
      "step": 3700
    },
    {
      "epoch": 29.68,
      "learning_rate": 3.8e-05,
      "loss": 5.5866,
      "step": 3800
    },
    {
      "epoch": 30.47,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 5.5778,
      "step": 3900
    },
    {
      "epoch": 31.25,
      "learning_rate": 4e-05,
      "loss": 5.5705,
      "step": 4000
    },
    {
      "epoch": 32.03,
      "learning_rate": 4.1e-05,
      "loss": 5.5586,
      "step": 4100
    }
  ],
  "max_steps": 5120,
  "num_train_epochs": 40,
  "total_flos": 2.77949076996096e+17,
  "trial_name": null,
  "trial_params": null
}