{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4444444444444444,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 0.6193130612373352,
      "learning_rate": 9.910000000000001e-05,
      "loss": 1.654,
      "mean_token_accuracy": 0.6766653224825859,
      "num_tokens": 23330.0,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.5931444764137268,
      "learning_rate": 9.81e-05,
      "loss": 1.0695,
      "mean_token_accuracy": 0.7898772016167641,
      "num_tokens": 46070.0,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.3904027044773102,
      "learning_rate": 9.71e-05,
      "loss": 0.7556,
      "mean_token_accuracy": 0.8578989505767822,
      "num_tokens": 68719.0,
      "step": 30
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.32560470700263977,
      "learning_rate": 9.61e-05,
      "loss": 0.6186,
      "mean_token_accuracy": 0.8813577085733414,
      "num_tokens": 92126.0,
      "step": 40
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.30384671688079834,
      "learning_rate": 9.51e-05,
      "loss": 0.5761,
      "mean_token_accuracy": 0.8921546742320061,
      "num_tokens": 114738.0,
      "step": 50
    },
    {
      "epoch": 0.1111111111111111,
      "eval_loss": 0.5330827236175537,
      "eval_mean_token_accuracy": 0.9009262701869011,
      "eval_num_tokens": 114738.0,
      "eval_runtime": 40.5094,
      "eval_samples_per_second": 4.937,
      "eval_steps_per_second": 4.937,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.40981799364089966,
      "learning_rate": 9.41e-05,
      "loss": 0.4978,
      "mean_token_accuracy": 0.9065196111798286,
      "num_tokens": 136310.0,
      "step": 60
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 0.5167299509048462,
      "learning_rate": 9.310000000000001e-05,
      "loss": 0.4466,
      "mean_token_accuracy": 0.9203566908836365,
      "num_tokens": 158193.0,
      "step": 70
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.5062010884284973,
      "learning_rate": 9.21e-05,
      "loss": 0.4003,
      "mean_token_accuracy": 0.9284946233034134,
      "num_tokens": 180767.0,
      "step": 80
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.38172802329063416,
      "learning_rate": 9.11e-05,
      "loss": 0.3457,
      "mean_token_accuracy": 0.9404646947979927,
      "num_tokens": 203203.0,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.4985530376434326,
      "learning_rate": 9.010000000000001e-05,
      "loss": 0.3271,
      "mean_token_accuracy": 0.9434564337134361,
      "num_tokens": 226070.0,
      "step": 100
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 0.3216829001903534,
      "eval_mean_token_accuracy": 0.9481457704305649,
      "eval_num_tokens": 226070.0,
      "eval_runtime": 41.0245,
      "eval_samples_per_second": 4.875,
      "eval_steps_per_second": 4.875,
      "step": 100
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 0.3317733108997345,
      "learning_rate": 8.910000000000001e-05,
      "loss": 0.2834,
      "mean_token_accuracy": 0.9527689620852471,
      "num_tokens": 251659.0,
      "step": 110
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.28577539324760437,
      "learning_rate": 8.81e-05,
      "loss": 0.262,
      "mean_token_accuracy": 0.9557135447859764,
      "num_tokens": 276141.0,
      "step": 120
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 0.4030509293079376,
      "learning_rate": 8.71e-05,
      "loss": 0.26,
      "mean_token_accuracy": 0.9594775453209877,
      "num_tokens": 299250.0,
      "step": 130
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.4423465132713318,
      "learning_rate": 8.61e-05,
      "loss": 0.2557,
      "mean_token_accuracy": 0.9583914607763291,
      "num_tokens": 323528.0,
      "step": 140
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.49233391880989075,
      "learning_rate": 8.510000000000001e-05,
      "loss": 0.2444,
      "mean_token_accuracy": 0.9617681756615639,
      "num_tokens": 346496.0,
      "step": 150
    },
    {
      "epoch": 0.3333333333333333,
      "eval_loss": 0.24680288136005402,
      "eval_mean_token_accuracy": 0.963321838080883,
      "eval_num_tokens": 346496.0,
      "eval_runtime": 41.1525,
      "eval_samples_per_second": 4.86,
      "eval_steps_per_second": 4.86,
      "step": 150
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.2696438133716583,
      "learning_rate": 8.41e-05,
      "loss": 0.2196,
      "mean_token_accuracy": 0.9656250089406967,
      "num_tokens": 371258.0,
      "step": 160
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 0.525949239730835,
      "learning_rate": 8.31e-05,
      "loss": 0.2122,
      "mean_token_accuracy": 0.9669450834393502,
      "num_tokens": 395722.0,
      "step": 170
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.38804805278778076,
      "learning_rate": 8.21e-05,
      "loss": 0.2097,
      "mean_token_accuracy": 0.9699977666139603,
      "num_tokens": 418830.0,
      "step": 180
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 0.38709455728530884,
      "learning_rate": 8.11e-05,
      "loss": 0.1914,
      "mean_token_accuracy": 0.9692254871129989,
      "num_tokens": 443015.0,
      "step": 190
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.28362640738487244,
      "learning_rate": 8.010000000000001e-05,
      "loss": 0.2051,
      "mean_token_accuracy": 0.968667496740818,
      "num_tokens": 465941.0,
      "step": 200
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 0.21475830674171448,
      "eval_mean_token_accuracy": 0.9686776822805405,
      "eval_num_tokens": 465941.0,
      "eval_runtime": 40.8312,
      "eval_samples_per_second": 4.898,
      "eval_steps_per_second": 4.898,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2254945698432000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}