trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.63768115942029,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.8625,
      "step": 10
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 2.8987,
      "step": 20
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 2.7552,
      "step": 30
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.8627,
      "step": 40
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.6602,
      "step": 50
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 2.8089,
      "step": 60
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 2.7102,
      "step": 70
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 2.772,
      "step": 80
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 2.6953,
      "step": 90
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 2.6401,
      "step": 100
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 2.648,
      "step": 110
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 2.5756,
      "step": 120
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 2.6002,
      "step": 130
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0002,
      "loss": 2.5801,
      "step": 140
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002,
      "loss": 2.6678,
      "step": 150
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 2.5758,
      "step": 160
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 2.6861,
      "step": 170
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0002,
      "loss": 2.4169,
      "step": 180
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0002,
      "loss": 2.3657,
      "step": 190
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0002,
      "loss": 2.3153,
      "step": 200
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 2.3601,
      "step": 210
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0002,
      "loss": 2.3498,
      "step": 220
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 2.4114,
      "step": 230
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0002,
      "loss": 2.3708,
      "step": 240
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0002,
      "loss": 2.4176,
      "step": 250
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0002,
      "loss": 2.3728,
      "step": 260
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0002,
      "loss": 2.1058,
      "step": 270
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0002,
      "loss": 2.0375,
      "step": 280
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0002,
      "loss": 2.0828,
      "step": 290
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0002,
      "loss": 2.081,
      "step": 300
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0002,
      "loss": 2.1004,
      "step": 310
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0002,
      "loss": 2.1472,
      "step": 320
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0002,
      "loss": 2.1437,
      "step": 330
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0002,
      "loss": 2.149,
      "step": 340
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0002,
      "loss": 1.9758,
      "step": 350
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0002,
      "loss": 1.791,
      "step": 360
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0002,
      "loss": 1.7366,
      "step": 370
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0002,
      "loss": 1.8066,
      "step": 380
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0002,
      "loss": 1.7821,
      "step": 390
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0002,
      "loss": 1.8661,
      "step": 400
    }
  ],
  "max_steps": 500,
  "num_train_epochs": 6,
  "total_flos": 1.897304296714445e+16,
  "trial_name": null,
  "trial_params": null
}