{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1968503937007874,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.437505340576172,
      "epoch": 0.01968503937007874,
      "grad_norm": 0.63671875,
      "learning_rate": 3.91304347826087e-05,
      "loss": 1.657536506652832,
      "mean_token_accuracy": 0.6597658038139343,
      "num_tokens": 115439.0,
      "step": 10
    },
    {
      "entropy": 1.5124324679374694,
      "epoch": 0.03937007874015748,
      "grad_norm": 0.4453125,
      "learning_rate": 8.260869565217392e-05,
      "loss": 1.4648273468017579,
      "mean_token_accuracy": 0.683241218328476,
      "num_tokens": 225264.0,
      "step": 20
    },
    {
      "entropy": 1.2266616582870484,
      "epoch": 0.05905511811023622,
      "grad_norm": 0.6796875,
      "learning_rate": 0.00012608695652173915,
      "loss": 1.113858699798584,
      "mean_token_accuracy": 0.7449506461620331,
      "num_tokens": 330923.0,
      "step": 30
    },
    {
      "entropy": 1.05804543197155,
      "epoch": 0.07874015748031496,
      "grad_norm": 0.47265625,
      "learning_rate": 0.00016956521739130436,
      "loss": 1.076363468170166,
      "mean_token_accuracy": 0.7455369174480438,
      "num_tokens": 437622.0,
      "step": 40
    },
    {
      "entropy": 0.9502384155988693,
      "epoch": 0.0984251968503937,
      "grad_norm": 0.5,
      "learning_rate": 0.00019999796688511753,
      "loss": 0.9587571144104003,
      "mean_token_accuracy": 0.7683711260557174,
      "num_tokens": 551175.0,
      "step": 50
    },
    {
      "epoch": 0.0984251968503937,
      "eval_entropy": 1.0894114132280703,
      "eval_loss": 1.0480613708496094,
      "eval_mean_token_accuracy": 0.745736007337217,
      "eval_num_tokens": 551175.0,
      "eval_runtime": 15.9708,
      "eval_samples_per_second": 26.736,
      "eval_steps_per_second": 3.381,
      "step": 50
    },
    {
      "entropy": 0.9499408066272735,
      "epoch": 0.11811023622047244,
      "grad_norm": 0.5859375,
      "learning_rate": 0.0001999618249203163,
      "loss": 0.9569917678833008,
      "mean_token_accuracy": 0.7686831414699554,
      "num_tokens": 658006.0,
      "step": 60
    },
    {
      "entropy": 1.0497896373271942,
      "epoch": 0.1377952755905512,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00019988052141977201,
      "loss": 0.9973426818847656,
      "mean_token_accuracy": 0.7564341962337494,
      "num_tokens": 771278.0,
      "step": 70
    },
    {
      "entropy": 0.8503248453140259,
      "epoch": 0.15748031496062992,
      "grad_norm": 0.5,
      "learning_rate": 0.0001997540931154166,
      "loss": 0.839632225036621,
      "mean_token_accuracy": 0.7869657546281814,
      "num_tokens": 886071.0,
      "step": 80
    },
    {
      "entropy": 0.9232195496559144,
      "epoch": 0.17716535433070865,
      "grad_norm": 0.482421875,
      "learning_rate": 0.00019958259712601903,
      "loss": 0.8961009025573731,
      "mean_token_accuracy": 0.7736886650323868,
      "num_tokens": 996361.0,
      "step": 90
    },
    {
      "entropy": 0.8409020006656647,
      "epoch": 0.1968503937007874,
      "grad_norm": 0.515625,
      "learning_rate": 0.00019936611093137983,
      "loss": 0.839316463470459,
      "mean_token_accuracy": 0.787284591794014,
      "num_tokens": 1103999.0,
      "step": 100
    },
    {
      "epoch": 0.1968503937007874,
      "eval_entropy": 0.988924115896225,
      "eval_loss": 0.9491098523139954,
      "eval_mean_token_accuracy": 0.7609603978969433,
      "eval_num_tokens": 1103999.0,
      "eval_runtime": 15.8986,
      "eval_samples_per_second": 26.858,
      "eval_steps_per_second": 3.397,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 1524,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5680413745086464e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}