trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7647058823529411,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.672097857935717e-05,
      "loss": 0.8062,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.986771734266245e-05,
      "loss": 0.7465,
      "step": 100
    },
    {
      "epoch": 0.22,
      "learning_rate": 2e-05,
      "loss": 0.7326,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 0.713,
      "step": 200
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.6996,
      "step": 250
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.6924,
      "step": 300
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.6903,
      "step": 350
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.6878,
      "step": 400
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.6903,
      "step": 450
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.6961,
      "step": 500
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.698,
      "step": 550
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 0.6843,
      "step": 600
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.6818,
      "step": 650
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 0.6928,
      "step": 700
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.6792,
      "step": 750
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 0.6894,
      "step": 800
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.6917,
      "step": 850
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.6957,
      "step": 900
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 0.6888,
      "step": 950
    },
    {
      "epoch": 1.47,
      "learning_rate": 2e-05,
      "loss": 0.6976,
      "step": 1000
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.6902,
      "step": 1050
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 0.6921,
      "step": 1100
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.689,
      "step": 1150
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.7036,
      "step": 1200
    }
  ],
  "max_steps": 3400,
  "num_train_epochs": 5,
  "total_flos": 1.5324183002750124e+19,
  "trial_name": null,
  "trial_params": null
}