trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20725388601036268,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.2518,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.08,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.0803,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0389,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.9999,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.0234,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0212,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 2.0067,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0218,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.9615,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.0126,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 2.0325,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.9627,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.9353,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.9652,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.0244,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 2.0159,
      "step": 170
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.998,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.9371,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.9921,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.9473,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.9537,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.0283,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.9755,
      "step": 240
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.9729,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 2.0241,
      "step": 260
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.9208,
      "step": 270
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.0218,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.9854,
      "step": 290
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.9642,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.9665,
      "step": 310
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.9638,
      "step": 320
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.9346,
      "step": 330
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.9077,
      "step": 340
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9674,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9354,
      "step": 360
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.9594,
      "step": 370
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.9699,
      "step": 380
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.9663,
      "step": 390
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.9504,
      "step": 400
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.9155,
      "step": 410
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.8807,
      "step": 420
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.9115,
      "step": 430
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.8983,
      "step": 440
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.8775,
      "step": 450
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.9103,
      "step": 460
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.9505,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.9483,
      "step": 480
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.9128,
      "step": 490
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.8843,
      "step": 500
    }
  ],
  "max_steps": 501,
  "num_train_epochs": 1,
  "total_flos": 8.4635406041088e+16,
  "trial_name": null,
  "trial_params": null
}