{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.6480721473693847,
      "epoch": 0.05,
      "grad_norm": 27.1102352142334,
      "learning_rate": 8e-05,
      "loss": 1.8005,
      "mean_token_accuracy": 0.5941327238082885,
      "num_tokens": 9693.0,
      "step": 25
    },
    {
      "entropy": 1.3281144857406617,
      "epoch": 0.1,
      "grad_norm": 9.47355842590332,
      "learning_rate": 0.00018,
      "loss": 1.2936,
      "mean_token_accuracy": 0.6876855921745301,
      "num_tokens": 19797.0,
      "step": 50
    },
    {
      "entropy": 1.2546486043930054,
      "epoch": 0.15,
      "grad_norm": 7.4732513427734375,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.2329,
      "mean_token_accuracy": 0.691328091621399,
      "num_tokens": 28636.0,
      "step": 75
    },
    {
      "entropy": 1.1987505912780763,
      "epoch": 0.2,
      "grad_norm": 10.677826881408691,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.165,
      "mean_token_accuracy": 0.7062379860877991,
      "num_tokens": 38194.0,
      "step": 100
    },
    {
      "entropy": 1.2390620636940002,
      "epoch": 0.25,
      "grad_norm": 8.650012016296387,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.2323,
      "mean_token_accuracy": 0.686786060333252,
      "num_tokens": 49170.0,
      "step": 125
    },
    {
      "entropy": 1.2445489859580994,
      "epoch": 0.3,
      "grad_norm": 6.545881748199463,
      "learning_rate": 0.00017880107536067218,
      "loss": 1.233,
      "mean_token_accuracy": 0.6857695412635804,
      "num_tokens": 58907.0,
      "step": 150
    },
    {
      "entropy": 1.2420870399475097,
      "epoch": 0.35,
      "grad_norm": 24.16084098815918,
      "learning_rate": 0.00016743023875837233,
      "loss": 1.2297,
      "mean_token_accuracy": 0.6925088000297547,
      "num_tokens": 68206.0,
      "step": 175
    },
    {
      "entropy": 1.2456481051445008,
      "epoch": 0.4,
      "grad_norm": 23.415494918823242,
      "learning_rate": 0.00015358267949789966,
      "loss": 1.2531,
      "mean_token_accuracy": 0.6884878659248352,
      "num_tokens": 77989.0,
      "step": 200
    },
    {
      "entropy": 1.2355119800567627,
      "epoch": 0.45,
      "grad_norm": 7.648189544677734,
      "learning_rate": 0.00013810703763502744,
      "loss": 1.2108,
      "mean_token_accuracy": 0.6975953841209411,
      "num_tokens": 87614.0,
      "step": 225
    },
    {
      "entropy": 1.2422665166854858,
      "epoch": 0.5,
      "grad_norm": 7.272965908050537,
      "learning_rate": 0.00012147353271670634,
      "loss": 1.2552,
      "mean_token_accuracy": 0.687971031665802,
      "num_tokens": 97427.0,
      "step": 250
    },
    {
      "entropy": 1.2536789083480835,
      "epoch": 0.55,
      "grad_norm": 7.070037364959717,
      "learning_rate": 0.00010418756537291996,
      "loss": 1.2526,
      "mean_token_accuracy": 0.6898462009429932,
      "num_tokens": 107088.0,
      "step": 275
    },
    {
      "entropy": 1.2259885239601136,
      "epoch": 0.6,
      "grad_norm": 13.018112182617188,
      "learning_rate": 8.677436097428775e-05,
      "loss": 1.2247,
      "mean_token_accuracy": 0.6857342338562011,
      "num_tokens": 116177.0,
      "step": 300
    },
    {
      "entropy": 1.2294299459457398,
      "epoch": 0.65,
      "grad_norm": 7.353261947631836,
      "learning_rate": 6.976301092495556e-05,
      "loss": 1.2238,
      "mean_token_accuracy": 0.6885941863059998,
      "num_tokens": 126328.0,
      "step": 325
    },
    {
      "entropy": 1.2531250643730163,
      "epoch": 0.7,
      "grad_norm": 7.604862689971924,
      "learning_rate": 5.3670396488013854e-05,
      "loss": 1.2219,
      "mean_token_accuracy": 0.6879838514328003,
      "num_tokens": 135285.0,
      "step": 350
    },
    {
      "entropy": 1.2012500953674317,
      "epoch": 0.75,
      "grad_norm": 7.651504039764404,
      "learning_rate": 3.8985483609873244e-05,
      "loss": 1.2111,
      "mean_token_accuracy": 0.6910693979263306,
      "num_tokens": 145111.0,
      "step": 375
    },
    {
      "entropy": 1.2419355368614198,
      "epoch": 0.8,
      "grad_norm": 8.24601936340332,
      "learning_rate": 2.615446593741161e-05,
      "loss": 1.2345,
      "mean_token_accuracy": 0.685720636844635,
      "num_tokens": 155061.0,
      "step": 400
    },
    {
      "entropy": 1.2203574657440186,
      "epoch": 0.85,
      "grad_norm": 5.648503303527832,
      "learning_rate": 1.5567207449798515e-05,
      "loss": 1.1986,
      "mean_token_accuracy": 0.6945811367034912,
      "num_tokens": 164613.0,
      "step": 425
    },
    {
      "entropy": 1.1166097807884217,
      "epoch": 0.9,
      "grad_norm": 7.915076732635498,
      "learning_rate": 7.545396638768698e-06,
      "loss": 1.1173,
      "mean_token_accuracy": 0.7110410404205322,
      "num_tokens": 174362.0,
      "step": 450
    },
    {
      "entropy": 1.2107400488853455,
      "epoch": 0.95,
      "grad_norm": 8.340585708618164,
      "learning_rate": 2.332772166583208e-06,
      "loss": 1.1966,
      "mean_token_accuracy": 0.7019165325164795,
      "num_tokens": 183648.0,
      "step": 475
    },
    {
      "entropy": 1.2142256331443786,
      "epoch": 1.0,
      "grad_norm": 8.785581588745117,
      "learning_rate": 8.771699011416168e-08,
      "loss": 1.1894,
      "mean_token_accuracy": 0.7058351802825927,
      "num_tokens": 193469.0,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2045157535088640.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}