trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 103,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.0001364038084940016,
      "loss": 3.7165,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001340337156353132,
      "loss": 3.7345,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00013014473739485363,
      "loss": 3.4567,
      "step": 15
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001248271469925082,
      "loss": 3.512,
      "step": 20
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011820437942275874,
      "loss": 3.5706,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00011043016620995614,
      "loss": 3.4168,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010168496690295909,
      "loss": 3.5556,
      "step": 35
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.21717801433564e-05,
      "loss": 3.3815,
      "step": 40
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.211143154318805e-05,
      "loss": 3.2048,
      "step": 45
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.173744775268251e-05,
      "loss": 3.3812,
      "step": 50
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.12906357041245e-05,
      "loss": 3.4762,
      "step": 55
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.101349286159054e-05,
      "loss": 3.2324,
      "step": 60
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.114457822907933e-05,
      "loss": 3.3225,
      "step": 65
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.1912974780463516e-05,
      "loss": 3.5544,
      "step": 70
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.3532971852551605e-05,
      "loss": 3.3748,
      "step": 75
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6199090936639392e-05,
      "loss": 3.3532,
      "step": 80
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.0081570332763395e-05,
      "loss": 3.4422,
      "step": 85
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.322413479482709e-06,
      "loss": 3.556,
      "step": 90
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.032092687651423e-06,
      "loss": 3.3998,
      "step": 95
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.869847930266052e-07,
      "loss": 3.5112,
      "step": 100
    }
  ],
  "max_steps": 103,
  "num_train_epochs": 1,
  "total_flos": 107260379136000.0,
  "trial_name": null,
  "trial_params": null
}