{
  "best_metric": 0.014762421138584614,
  "best_model_checkpoint": "saves/chess/both/checkpoint-1000",
  "epoch": 1.6260162601626016,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 1.6060084762973008,
      "learning_rate": 1.0162601626016261e-06,
      "loss": 1.0073,
      "step": 100
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 3.0440875723802594,
      "learning_rate": 2.0325203252032523e-06,
      "loss": 0.0302,
      "step": 200
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.9455772942098933,
      "learning_rate": 3.0487804878048782e-06,
      "loss": 0.0229,
      "step": 300
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 0.3831361794753519,
      "learning_rate": 4.0650406504065046e-06,
      "loss": 0.0197,
      "step": 400
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 0.5841201203132319,
      "learning_rate": 4.999959730768458e-06,
      "loss": 0.0183,
      "step": 500
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.36973884839665605,
      "learning_rate": 4.992664502959351e-06,
      "loss": 0.0172,
      "step": 600
    },
    {
      "epoch": 1.1382113821138211,
      "grad_norm": 0.5308905808120226,
      "learning_rate": 4.9728272933003704e-06,
      "loss": 0.0149,
      "step": 700
    },
    {
      "epoch": 1.3008130081300813,
      "grad_norm": 0.3199255336490814,
      "learning_rate": 4.940547913829274e-06,
      "loss": 0.015,
      "step": 800
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.4781960951795096,
      "learning_rate": 4.89598878006206e-06,
      "loss": 0.0147,
      "step": 900
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 0.5141788877979915,
      "learning_rate": 4.839374093790139e-06,
      "loss": 0.0144,
      "step": 1000
    },
    {
      "epoch": 1.6260162601626016,
      "eval_loss": 0.014762421138584614,
      "eval_runtime": 232.6693,
      "eval_samples_per_second": 150.265,
      "eval_steps_per_second": 0.589,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 4920,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 197337053921280.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}