trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.927536231884059,
  "eval_steps": 500,
  "global_step": 660,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 2.1782,
      "step": 20
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.9533,
      "step": 40
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0002,
      "loss": 1.8756,
      "step": 60
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 1.7662,
      "step": 80
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.7196,
      "step": 100
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0002,
      "loss": 1.5842,
      "step": 120
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0002,
      "loss": 1.49,
      "step": 140
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0002,
      "loss": 1.4432,
      "step": 160
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0002,
      "loss": 1.2434,
      "step": 180
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0002,
      "loss": 1.3193,
      "step": 200
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0002,
      "loss": 1.1336,
      "step": 220
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0002,
      "loss": 1.1327,
      "step": 240
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0002,
      "loss": 1.1099,
      "step": 260
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.0002,
      "loss": 0.9778,
      "step": 280
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.0002,
      "loss": 0.9912,
      "step": 300
    },
    {
      "epoch": 6.18,
      "learning_rate": 0.0002,
      "loss": 0.8791,
      "step": 320
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.0002,
      "loss": 0.8689,
      "step": 340
    },
    {
      "epoch": 6.96,
      "learning_rate": 0.0002,
      "loss": 0.7917,
      "step": 360
    },
    {
      "epoch": 7.34,
      "learning_rate": 0.0002,
      "loss": 0.7627,
      "step": 380
    },
    {
      "epoch": 7.73,
      "learning_rate": 0.0002,
      "loss": 0.6916,
      "step": 400
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.0002,
      "loss": 0.717,
      "step": 420
    },
    {
      "epoch": 8.5,
      "learning_rate": 0.0002,
      "loss": 0.5919,
      "step": 440
    },
    {
      "epoch": 8.89,
      "learning_rate": 0.0002,
      "loss": 0.6064,
      "step": 460
    },
    {
      "epoch": 9.28,
      "learning_rate": 0.0002,
      "loss": 0.5224,
      "step": 480
    },
    {
      "epoch": 9.66,
      "learning_rate": 0.0002,
      "loss": 0.5103,
      "step": 500
    },
    {
      "epoch": 10.05,
      "learning_rate": 0.0002,
      "loss": 0.5647,
      "step": 520
    },
    {
      "epoch": 10.43,
      "learning_rate": 0.0002,
      "loss": 0.4083,
      "step": 540
    },
    {
      "epoch": 10.82,
      "learning_rate": 0.0002,
      "loss": 0.472,
      "step": 560
    },
    {
      "epoch": 11.21,
      "learning_rate": 0.0002,
      "loss": 0.3785,
      "step": 580
    },
    {
      "epoch": 11.59,
      "learning_rate": 0.0002,
      "loss": 0.4072,
      "step": 600
    },
    {
      "epoch": 11.98,
      "learning_rate": 0.0002,
      "loss": 0.3689,
      "step": 620
    },
    {
      "epoch": 12.37,
      "learning_rate": 0.0002,
      "loss": 0.3327,
      "step": 640
    },
    {
      "epoch": 12.93,
      "learning_rate": 0.0002,
      "loss": 0.29,
      "step": 660
    }
  ],
  "logging_steps": 20,
  "max_steps": 660,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 13,
  "save_steps": 20,
  "total_flos": 9.918366904902205e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}