checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8475750577367207,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.0758,
      "step": 20
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.0262,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.972,
      "step": 60
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 0.2251,
      "step": 80
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.144,
      "step": 100
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 0.1766,
      "step": 120
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 0.1494,
      "step": 140
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.1483,
      "step": 160
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.1188,
      "step": 180
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 0.0918,
      "step": 200
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 0.1356,
      "step": 220
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.0969,
      "step": 240
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.1145,
      "step": 260
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 0.1058,
      "step": 280
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.0827,
      "step": 300
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.0537,
      "step": 320
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 0.0969,
      "step": 340
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.06,
      "step": 360
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002,
      "loss": 0.0777,
      "step": 380
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0002,
      "loss": 0.071,
      "step": 400
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 0.0487,
      "step": 420
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 0.0871,
      "step": 440
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0002,
      "loss": 0.0577,
      "step": 460
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 0.073,
      "step": 480
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 0.0658,
      "step": 500
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 2,
  "total_flos": 5.366331835972915e+17,
  "trial_name": null,
  "trial_params": null
}