{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 0.14176353812217712,
      "learning_rate": 0.0004,
      "loss": 1.1525,
      "step": 25
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.1460508555173874,
      "learning_rate": 0.0004998852503731983,
      "loss": 1.047,
      "step": 50
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.2368021011352539,
      "learning_rate": 0.0004993848168027977,
      "loss": 0.8529,
      "step": 75
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.14488168060779572,
      "learning_rate": 0.0004984880506341147,
      "loss": 0.9756,
      "step": 100
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.9470569491386414,
      "eval_runtime": 845.9115,
      "eval_samples_per_second": 1.297,
      "eval_steps_per_second": 0.021,
      "step": 100
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.1415175348520279,
      "learning_rate": 0.0004971963770447935,
      "loss": 0.9564,
      "step": 125
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.1751064509153366,
      "learning_rate": 0.0004955118488155782,
      "loss": 0.711,
      "step": 150
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.1439943015575409,
      "learning_rate": 0.0004934371430679492,
      "loss": 0.9409,
      "step": 175
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.15947112441062927,
      "learning_rate": 0.0004909755570095319,
      "loss": 0.8979,
      "step": 200
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.9711233973503113,
      "eval_runtime": 845.6433,
      "eval_samples_per_second": 1.297,
      "eval_steps_per_second": 0.021,
      "step": 200
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.14685837924480438,
      "learning_rate": 0.0004881310026940389,
      "loss": 0.6376,
      "step": 225
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.15040776133537292,
      "learning_rate": 0.0004849080008040734,
      "loss": 0.927,
      "step": 250
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.16087745130062103,
      "learning_rate": 0.00048131167346667446,
      "loss": 0.8456,
      "step": 275
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.15025638043880463,
      "learning_rate": 0.00047734773611302284,
      "loss": 0.6029,
      "step": 300
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.0056413412094116,
      "eval_runtime": 848.447,
      "eval_samples_per_second": 1.293,
      "eval_steps_per_second": 0.021,
      "step": 300
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.15893957018852234,
      "learning_rate": 0.0004730224883952422,
      "loss": 0.9036,
      "step": 325
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.1535714715719223,
      "learning_rate": 0.0004683428041747334,
      "loss": 0.828,
      "step": 350
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.1718970686197281,
      "learning_rate": 0.0004633161205979517,
      "loss": 0.5944,
      "step": 375
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.17664535343647003,
      "learning_rate": 0.0004579504262769877,
      "loss": 0.8654,
      "step": 400
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.0151112079620361,
      "eval_runtime": 839.7482,
      "eval_samples_per_second": 1.306,
      "eval_steps_per_second": 0.021,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.031726173447782e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}