trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5555555555555556,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.3698,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.1614,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.1428,
      "step": 30
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.1265,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.1258,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.0623,
      "step": 60
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.0685,
      "step": 70
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.0363,
      "step": 80
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.0749,
      "step": 90
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.9667,
      "step": 100
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 2.015,
      "step": 110
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.99,
      "step": 120
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.0034,
      "step": 130
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.9775,
      "step": 140
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.9822,
      "step": 150
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.975,
      "step": 160
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.9351,
      "step": 170
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.9515,
      "step": 180
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.9296,
      "step": 190
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.9995,
      "step": 200
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.934,
      "step": 210
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.9073,
      "step": 220
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 1.8677,
      "step": 230
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.8251,
      "step": 240
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 1.814,
      "step": 250
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.8077,
      "step": 260
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.7908,
      "step": 270
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 1.7912,
      "step": 280
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 1.8115,
      "step": 290
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.7994,
      "step": 300
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002,
      "loss": 1.7903,
      "step": 310
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.8118,
      "step": 320
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.7894,
      "step": 330
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 1.8182,
      "step": 340
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 1.7409,
      "step": 350
    }
  ],
  "max_steps": 400,
  "num_train_epochs": 2,
  "total_flos": 5.923420480300646e+16,
  "trial_name": null,
  "trial_params": null
}