checkpoint-72/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7058823529411765,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.8355,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 0.8713,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 0.8682,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 0.9393,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.7962,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 0.812,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 0.7402,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.8024,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 0.7745,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 0.7962,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 0.7168,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 0.7441,
      "step": 24
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.7646,
      "step": 26
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 0.76,
      "step": 28
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.8013,
      "step": 30
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 0.7374,
      "step": 32
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 0.8013,
      "step": 34
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 0.7418,
      "step": 36
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 0.7707,
      "step": 38
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.8057,
      "step": 40
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 0.7133,
      "step": 42
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.7545,
      "step": 44
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.6649,
      "step": 46
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 0.6521,
      "step": 48
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 0.7292,
      "step": 50
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 0.6916,
      "step": 52
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 0.729,
      "step": 54
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 0.7188,
      "step": 56
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.8067,
      "step": 58
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 0.7742,
      "step": 60
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.6993,
      "step": 62
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 0.6729,
      "step": 64
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 0.7793,
      "step": 66
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 0.6627,
      "step": 68
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 0.7312,
      "step": 70
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6635,
      "step": 72
    }
  ],
  "logging_steps": 2,
  "max_steps": 306,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.17304823119872e+16,
  "trial_name": null,
  "trial_params": null
}