{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.43485013200807576,
  "eval_steps": 1000,
  "global_step": 1750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024848578971890044,
      "grad_norm": 1.1403515692366237,
      "learning_rate": 0.0002475,
      "loss": 0.7727,
      "step": 100
    },
    {
      "epoch": 0.04969715794378009,
      "grad_norm": 2.0321728234236067,
      "learning_rate": 0.0004975,
      "loss": 0.6434,
      "step": 200
    },
    {
      "epoch": 0.07454573691567014,
      "grad_norm": 1.5298185029395692,
      "learning_rate": 0.0004896875,
      "loss": 0.6966,
      "step": 300
    },
    {
      "epoch": 0.09939431588756018,
      "grad_norm": 1.3277644876612467,
      "learning_rate": 0.00047927083333333334,
      "loss": 0.6549,
      "step": 400
    },
    {
      "epoch": 0.12424289485945023,
      "grad_norm": 1.5260941221380562,
      "learning_rate": 0.0004688541666666667,
      "loss": 0.6218,
      "step": 500
    },
    {
      "epoch": 0.14909147383134028,
      "grad_norm": 1.461823959618585,
      "learning_rate": 0.0004584375,
      "loss": 0.6,
      "step": 600
    },
    {
      "epoch": 0.17394005280323033,
      "grad_norm": 1.579155099177269,
      "learning_rate": 0.0004480208333333333,
      "loss": 0.5768,
      "step": 700
    },
    {
      "epoch": 0.19878863177512035,
      "grad_norm": 1.0030257236753515,
      "learning_rate": 0.0004376041666666667,
      "loss": 0.5625,
      "step": 800
    },
    {
      "epoch": 0.2236372107470104,
      "grad_norm": 1.1362089000123636,
      "learning_rate": 0.0004271875,
      "loss": 0.5397,
      "step": 900
    },
    {
      "epoch": 0.24848578971890045,
      "grad_norm": 1.2060122481392086,
      "learning_rate": 0.00041677083333333334,
      "loss": 0.5262,
      "step": 1000
    },
    {
      "epoch": 0.24848578971890045,
      "eval_accuracy": 0.8519274864233807,
      "eval_loss": 0.4272424280643463,
      "eval_runtime": 355.1137,
      "eval_samples_per_second": 76.471,
      "eval_steps_per_second": 9.56,
      "step": 1000
    },
    {
      "epoch": 0.2733343686907905,
      "grad_norm": 1.4939232786831804,
      "learning_rate": 0.0004063541666666667,
      "loss": 0.507,
      "step": 1100
    },
    {
      "epoch": 0.29818294766268055,
      "grad_norm": 1.0210090194207913,
      "learning_rate": 0.0003959375,
      "loss": 0.4923,
      "step": 1200
    },
    {
      "epoch": 0.3230315266345706,
      "grad_norm": 1.5265032617099488,
      "learning_rate": 0.0003855208333333333,
      "loss": 0.485,
      "step": 1300
    },
    {
      "epoch": 0.34788010560646065,
      "grad_norm": 1.5974690542066108,
      "learning_rate": 0.0003751041666666667,
      "loss": 0.4734,
      "step": 1400
    },
    {
      "epoch": 0.3727286845783507,
      "grad_norm": 1.3463235139038994,
      "learning_rate": 0.0003646875,
      "loss": 0.4629,
      "step": 1500
    },
    {
      "epoch": 0.3975772635502407,
      "grad_norm": 0.8545527093751057,
      "learning_rate": 0.00035427083333333334,
      "loss": 0.4504,
      "step": 1600
    },
    {
      "epoch": 0.4224258425221308,
      "grad_norm": 1.1247072555863402,
      "learning_rate": 0.0003438541666666667,
      "loss": 0.4366,
      "step": 1700
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 225213498261504.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}