{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 415,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.060350030175015085,
      "grad_norm": 0.17640693485736847,
      "learning_rate": 9.599999999999999e-05,
      "loss": 1.7813,
      "mean_token_accuracy": 0.6300852990150452,
      "num_tokens": 156656.0,
      "step": 25
    },
    {
      "epoch": 0.12070006035003017,
      "grad_norm": 0.24193964898586273,
      "learning_rate": 0.00019599999999999997,
      "loss": 0.9197,
      "mean_token_accuracy": 0.768382026553154,
      "num_tokens": 282982.0,
      "step": 50
    },
    {
      "epoch": 0.18105009052504525,
      "grad_norm": 0.16499435901641846,
      "learning_rate": 0.000296,
      "loss": 0.5906,
      "mean_token_accuracy": 0.8341364151239395,
      "num_tokens": 441181.0,
      "step": 75
    },
    {
      "epoch": 0.24140012070006034,
      "grad_norm": 0.23563049733638763,
      "learning_rate": 0.0002999269005776963,
      "loss": 0.4832,
      "mean_token_accuracy": 0.8592967188358307,
      "num_tokens": 567644.0,
      "step": 100
    },
    {
      "epoch": 0.30175015087507545,
      "grad_norm": 0.22556591033935547,
      "learning_rate": 0.0002996953705789175,
      "loss": 0.3612,
      "mean_token_accuracy": 0.8925437909364701,
      "num_tokens": 725987.0,
      "step": 125
    },
    {
      "epoch": 0.3621001810500905,
      "grad_norm": 0.33429527282714844,
      "learning_rate": 0.00029930552794275785,
      "loss": 0.3126,
      "mean_token_accuracy": 0.9086851555109025,
      "num_tokens": 853185.0,
      "step": 150
    },
    {
      "epoch": 0.4224502112251056,
      "grad_norm": 0.27340370416641235,
      "learning_rate": 0.0002987577849532824,
      "loss": 0.2343,
      "mean_token_accuracy": 0.9301495373249054,
      "num_tokens": 1011232.0,
      "step": 175
    },
    {
      "epoch": 0.4828002414001207,
      "grad_norm": 0.2711191475391388,
      "learning_rate": 0.00029805272088449905,
      "loss": 0.2021,
      "mean_token_accuracy": 0.9406860828399658,
      "num_tokens": 1138074.0,
      "step": 200
    },
    {
      "epoch": 0.5431502715751357,
      "grad_norm": 0.19240038096904755,
      "learning_rate": 0.00029719108138773827,
      "loss": 0.1508,
      "mean_token_accuracy": 0.9550948125123978,
      "num_tokens": 1293601.0,
      "step": 225
    },
    {
      "epoch": 0.6035003017501509,
      "grad_norm": 0.27221739292144775,
      "learning_rate": 0.00029617377770307837,
      "loss": 0.1563,
      "mean_token_accuracy": 0.9542003554105759,
      "num_tokens": 1418074.0,
      "step": 250
    },
    {
      "epoch": 0.663850331925166,
      "grad_norm": 0.25977134704589844,
      "learning_rate": 0.0002950018856956494,
      "loss": 0.1228,
      "mean_token_accuracy": 0.9640595990419388,
      "num_tokens": 1577856.0,
      "step": 275
    },
    {
      "epoch": 0.724200362100181,
      "grad_norm": 0.2311161458492279,
      "learning_rate": 0.0002936766447178356,
      "loss": 0.1229,
      "mean_token_accuracy": 0.9646531140804291,
      "num_tokens": 1704393.0,
      "step": 300
    },
    {
      "epoch": 0.7845503922751962,
      "grad_norm": 0.1375264674425125,
      "learning_rate": 0.0002921994562985788,
      "loss": 0.0972,
      "mean_token_accuracy": 0.9722524845600128,
      "num_tokens": 1860935.0,
      "step": 325
    },
    {
      "epoch": 0.8449004224502112,
      "grad_norm": 0.2860631048679352,
      "learning_rate": 0.0002905718826611708,
      "loss": 0.0853,
      "mean_token_accuracy": 0.9756521546840667,
      "num_tokens": 1988266.0,
      "step": 350
    },
    {
      "epoch": 0.9052504526252263,
      "grad_norm": 0.11123040318489075,
      "learning_rate": 0.00028879564507109946,
      "loss": 0.0814,
      "mean_token_accuracy": 0.9769123244285584,
      "num_tokens": 2146122.0,
      "step": 375
    },
    {
      "epoch": 0.9656004828002414,
      "grad_norm": 0.239139586687088,
      "learning_rate": 0.0002868726220156981,
      "loss": 0.0696,
      "mean_token_accuracy": 0.9802538651227951,
      "num_tokens": 2273996.0,
      "step": 400
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.07211296260356903,
      "eval_mean_token_accuracy": 0.979879263285044,
      "eval_num_tokens": 2354180.0,
      "eval_runtime": 29.4819,
      "eval_samples_per_second": 12.516,
      "eval_steps_per_second": 6.275,
      "step": 415
    }
  ],
  "logging_steps": 25,
  "max_steps": 2490,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 1.998178519084032e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}