{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7407407407407407,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.6574764619767666,
      "epoch": 0.07407407407407407,
      "grad_norm": 0.6482250690460205,
      "learning_rate": 8.032786885245902e-05,
      "loss": 1.4512,
      "mean_token_accuracy": 0.6979378089308739,
      "num_tokens": 408597.0,
      "step": 50
    },
    {
      "entropy": 0.38226877618581057,
      "epoch": 0.14814814814814814,
      "grad_norm": 0.2513386011123657,
      "learning_rate": 9.990765991730485e-05,
      "loss": 0.3105,
      "mean_token_accuracy": 0.92415526881814,
      "num_tokens": 817567.0,
      "step": 100
    },
    {
      "entropy": 0.16286218419671059,
      "epoch": 0.2222222222222222,
      "grad_norm": 0.2887406051158905,
      "learning_rate": 9.950545603782162e-05,
      "loss": 0.1493,
      "mean_token_accuracy": 0.9622085580229759,
      "num_tokens": 1226265.0,
      "step": 150
    },
    {
      "entropy": 0.12771075297147036,
      "epoch": 0.2962962962962963,
      "grad_norm": 0.15249371528625488,
      "learning_rate": 9.878674879048427e-05,
      "loss": 0.1177,
      "mean_token_accuracy": 0.9713320073485374,
      "num_tokens": 1635020.0,
      "step": 200
    },
    {
      "entropy": 0.1111781226657331,
      "epoch": 0.37037037037037035,
      "grad_norm": 0.18299971520900726,
      "learning_rate": 9.775613308830824e-05,
      "loss": 0.1014,
      "mean_token_accuracy": 0.9749903282523156,
      "num_tokens": 2044395.0,
      "step": 250
    },
    {
      "entropy": 0.09641788197681307,
      "epoch": 0.4444444444444444,
      "grad_norm": 0.13050603866577148,
      "learning_rate": 9.642019796948866e-05,
      "loss": 0.0915,
      "mean_token_accuracy": 0.977490707486868,
      "num_tokens": 2453123.0,
      "step": 300
    },
    {
      "entropy": 0.09188288618810475,
      "epoch": 0.5185185185185185,
      "grad_norm": 0.11683323234319687,
      "learning_rate": 9.478748447168449e-05,
      "loss": 0.0883,
      "mean_token_accuracy": 0.9783088724315167,
      "num_tokens": 2862139.0,
      "step": 350
    },
    {
      "entropy": 0.09006990000605583,
      "epoch": 0.5925925925925926,
      "grad_norm": 0.16509227454662323,
      "learning_rate": 9.28684310265789e-05,
      "loss": 0.0874,
      "mean_token_accuracy": 0.9784132435917854,
      "num_tokens": 3270859.0,
      "step": 400
    },
    {
      "entropy": 0.08776539071463048,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.13524411618709564,
      "learning_rate": 9.067530672382544e-05,
      "loss": 0.0866,
      "mean_token_accuracy": 0.9787498603761197,
      "num_tokens": 3680243.0,
      "step": 450
    },
    {
      "entropy": 0.08806963111273944,
      "epoch": 0.7407407407407407,
      "grad_norm": 0.09137360751628876,
      "learning_rate": 8.822213287104348e-05,
      "loss": 0.086,
      "mean_token_accuracy": 0.9788302226364612,
      "num_tokens": 4089386.0,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 2025,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.708245674967982e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}