{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8343868520859671,
  "eval_steps": 10,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.116106641292572,
      "epoch": 0.07585335018963338,
      "grad_norm": 1.4921875,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 2.914295959472656,
      "mean_token_accuracy": 0.5410080701112747,
      "num_tokens": 36823.0,
      "step": 10
    },
    {
      "epoch": 0.07585335018963338,
      "eval_entropy": 2.552819073200226,
      "eval_loss": 2.6676909923553467,
      "eval_mean_token_accuracy": 0.5321294479072094,
      "eval_num_tokens": 36823.0,
      "eval_runtime": 14.7674,
      "eval_samples_per_second": 0.542,
      "eval_steps_per_second": 0.542,
      "step": 10
    },
    {
      "entropy": 1.9473248382409414,
      "epoch": 0.15170670037926676,
      "grad_norm": 0.87890625,
      "learning_rate": 9.999152908979117e-05,
      "loss": 1.9090084075927733,
      "mean_token_accuracy": 0.6584314892689387,
      "num_tokens": 65881.0,
      "step": 20
    },
    {
      "epoch": 0.15170670037926676,
      "eval_entropy": 1.8724936991930008,
      "eval_loss": 1.9479429721832275,
      "eval_mean_token_accuracy": 0.6351580396294594,
      "eval_num_tokens": 65881.0,
      "eval_runtime": 14.8467,
      "eval_samples_per_second": 0.539,
      "eval_steps_per_second": 0.539,
      "step": 20
    },
    {
      "entropy": 1.5991886417071024,
      "epoch": 0.22756005056890014,
      "grad_norm": 1.4765625,
      "learning_rate": 9.984101496455829e-05,
      "loss": 1.5578083038330077,
      "mean_token_accuracy": 0.7192381203174592,
      "num_tokens": 89977.0,
      "step": 30
    },
    {
      "epoch": 0.22756005056890014,
      "eval_entropy": 1.6338046044111252,
      "eval_loss": 1.694503903388977,
      "eval_mean_token_accuracy": 0.6637412160634995,
      "eval_num_tokens": 89977.0,
      "eval_runtime": 14.8298,
      "eval_samples_per_second": 0.539,
      "eval_steps_per_second": 0.539,
      "step": 30
    },
    {
      "entropy": 1.6071883370478948,
      "epoch": 0.3034134007585335,
      "grad_norm": 0.71484375,
      "learning_rate": 9.950291051311487e-05,
      "loss": 1.6236091613769532,
      "mean_token_accuracy": 0.6928597639004389,
      "num_tokens": 122672.0,
      "step": 40
    },
    {
      "epoch": 0.3034134007585335,
      "eval_entropy": 1.5961390733718872,
      "eval_loss": 1.5684512853622437,
      "eval_mean_token_accuracy": 0.6787843257188797,
      "eval_num_tokens": 122672.0,
      "eval_runtime": 14.7973,
      "eval_samples_per_second": 0.541,
      "eval_steps_per_second": 0.541,
      "step": 40
    },
    {
      "entropy": 1.3055346330006918,
      "epoch": 0.37926675094816686,
      "grad_norm": 0.9453125,
      "learning_rate": 9.897848828427202e-05,
      "loss": 1.2936326026916505,
      "mean_token_accuracy": 0.7341216415166855,
      "num_tokens": 152626.0,
      "step": 50
    },
    {
      "epoch": 0.37926675094816686,
      "eval_entropy": 1.4331321269273758,
      "eval_loss": 1.410101294517517,
      "eval_mean_token_accuracy": 0.7011745795607567,
      "eval_num_tokens": 152626.0,
      "eval_runtime": 14.7788,
      "eval_samples_per_second": 0.541,
      "eval_steps_per_second": 0.541,
      "step": 50
    },
    {
      "entropy": 1.11328877111276,
      "epoch": 0.45512010113780027,
      "grad_norm": 0.82421875,
      "learning_rate": 9.826972208488447e-05,
      "loss": 1.0861340522766114,
      "mean_token_accuracy": 0.766385022799174,
      "num_tokens": 178156.0,
      "step": 60
    },
    {
      "epoch": 0.45512010113780027,
      "eval_entropy": 1.3111007660627365,
      "eval_loss": 1.2872167825698853,
      "eval_mean_token_accuracy": 0.7273842021822929,
      "eval_num_tokens": 178156.0,
      "eval_runtime": 14.7936,
      "eval_samples_per_second": 0.541,
      "eval_steps_per_second": 0.541,
      "step": 60
    },
    {
      "entropy": 1.3175925850868224,
      "epoch": 0.5309734513274337,
      "grad_norm": 0.625,
      "learning_rate": 9.737927955088705e-05,
      "loss": 1.2941490173339845,
      "mean_token_accuracy": 0.7372792253891627,
      "num_tokens": 209487.0,
      "step": 70
    },
    {
      "epoch": 0.5309734513274337,
      "eval_entropy": 1.2998864650726318,
      "eval_loss": 1.2285542488098145,
      "eval_mean_token_accuracy": 0.7347995787858963,
      "eval_num_tokens": 209487.0,
      "eval_runtime": 14.8531,
      "eval_samples_per_second": 0.539,
      "eval_steps_per_second": 0.539,
      "step": 70
    },
    {
      "entropy": 1.1506140291690827,
      "epoch": 0.606826801517067,
      "grad_norm": 0.828125,
      "learning_rate": 9.631051210691558e-05,
      "loss": 1.134031391143799,
      "mean_token_accuracy": 0.760423094034195,
      "num_tokens": 239555.0,
      "step": 80
    },
    {
      "epoch": 0.606826801517067,
      "eval_entropy": 1.2010595947504044,
      "eval_loss": 1.1256182193756104,
      "eval_mean_token_accuracy": 0.7571268677711487,
      "eval_num_tokens": 239555.0,
      "eval_runtime": 15.6324,
      "eval_samples_per_second": 0.512,
      "eval_steps_per_second": 0.512,
      "step": 80
    },
    {
      "entropy": 0.9923018544912339,
      "epoch": 0.6826801517067004,
      "grad_norm": 1.0078125,
      "learning_rate": 9.50674423523011e-05,
      "loss": 0.9289534568786622,
      "mean_token_accuracy": 0.7951417863368988,
      "num_tokens": 265306.0,
      "step": 90
    },
    {
      "epoch": 0.6826801517067004,
      "eval_entropy": 1.0992150977253914,
      "eval_loss": 1.0379621982574463,
      "eval_mean_token_accuracy": 0.7777058333158493,
      "eval_num_tokens": 265306.0,
      "eval_runtime": 15.7361,
      "eval_samples_per_second": 0.508,
      "eval_steps_per_second": 0.508,
      "step": 90
    },
    {
      "entropy": 1.0375868437190852,
      "epoch": 0.7585335018963337,
      "grad_norm": 0.609375,
      "learning_rate": 9.365474892091451e-05,
      "loss": 1.0106287956237794,
      "mean_token_accuracy": 0.7893585612376531,
      "num_tokens": 292993.0,
      "step": 100
    },
    {
      "epoch": 0.7585335018963337,
      "eval_entropy": 1.072925515472889,
      "eval_loss": 1.0008392333984375,
      "eval_mean_token_accuracy": 0.7823155149817467,
      "eval_num_tokens": 292993.0,
      "eval_runtime": 15.602,
      "eval_samples_per_second": 0.513,
      "eval_steps_per_second": 0.513,
      "step": 100
    },
    {
      "entropy": 1.0960371459523837,
      "epoch": 0.8343868520859671,
      "grad_norm": 0.7890625,
      "learning_rate": 9.207774887184493e-05,
      "loss": 1.0759888648986817,
      "mean_token_accuracy": 0.7768891970316569,
      "num_tokens": 324472.0,
      "step": 110
    },
    {
      "epoch": 0.8343868520859671,
      "eval_entropy": 0.9983096048235893,
      "eval_loss": 0.965083658695221,
      "eval_mean_token_accuracy": 0.7886351868510246,
      "eval_num_tokens": 324472.0,
      "eval_runtime": 15.6552,
      "eval_samples_per_second": 0.511,
      "eval_steps_per_second": 0.511,
      "step": 110
    }
  ],
  "logging_steps": 10,
  "max_steps": 528,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5582297608470528.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}