trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14938751120406335,
  "eval_steps": 500,
  "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": 1.0618,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.9484,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.882,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.7933,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 0.6232,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.9928,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8874,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8473,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.7204,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5444,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9667,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8497,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8284,
      "step": 130
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.6822,
      "step": 140
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.5556,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.9517,
      "step": 160
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.8587,
      "step": 170
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 0.8218,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.7056,
      "step": 190
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.5523,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.9718,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.8399,
      "step": 220
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.7947,
      "step": 230
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.6984,
      "step": 240
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.548,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.9692,
      "step": 260
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.8413,
      "step": 270
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.816,
      "step": 280
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 290
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.4823,
      "step": 300
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.9822,
      "step": 310
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8399,
      "step": 320
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.8271,
      "step": 330
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6497,
      "step": 340
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.5488,
      "step": 350
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.9632,
      "step": 360
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.8875,
      "step": 370
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 0.7813,
      "step": 380
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.6623,
      "step": 390
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.5352,
      "step": 400
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.9625,
      "step": 410
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.8437,
      "step": 420
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.765,
      "step": 430
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.6525,
      "step": 440
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 0.5245,
      "step": 450
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.9327,
      "step": 460
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7908,
      "step": 470
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7853,
      "step": 480
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.6868,
      "step": 490
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 0.5026,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 4.892025651291341e+16,
  "trial_name": null,
  "trial_params": null
}