checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4914004914004914,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.00025,
      "loss": 0.5873,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0005,
      "loss": 0.18,
      "step": 20
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0004963251406715272,
      "loss": 0.1853,
      "step": 30
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004854085994147815,
      "loss": 0.1675,
      "step": 40
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00046757131025753886,
      "loss": 0.1538,
      "step": 50
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00044333766942743246,
      "loss": 0.1566,
      "step": 60
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0004134201186930015,
      "loss": 0.1319,
      "step": 70
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00037869820037745775,
      "loss": 0.1561,
      "step": 80
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003401926998041959,
      "loss": 0.151,
      "step": 90
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00029903563535704927,
      "loss": 0.1364,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 203,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 2.647116234620928e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}