{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9943502824858759,
  "eval_steps": 500,
  "global_step": 44,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 0.15303204953670502,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.0135,
      "mean_token_accuracy": 0.7157474607229233,
      "step": 1
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 0.10195861756801605,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.9708,
      "mean_token_accuracy": 0.719270593021065,
      "step": 5
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 0.10714796930551529,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.9087,
      "mean_token_accuracy": 0.7353649735450745,
      "step": 10
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.09064473956823349,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.8416,
      "mean_token_accuracy": 0.7480618946254254,
      "step": 15
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 0.08322014659643173,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.8185,
      "mean_token_accuracy": 0.7534565337002277,
      "step": 20
    },
    {
      "epoch": 1.1355932203389831,
      "grad_norm": 0.0759216845035553,
      "learning_rate": 9.597340598905852e-05,
      "loss": 0.811,
      "mean_token_accuracy": 0.7538863693674406,
      "step": 25
    },
    {
      "epoch": 1.3615819209039548,
      "grad_norm": 0.08596349507570267,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.7729,
      "mean_token_accuracy": 0.7635015636682511,
      "step": 30
    },
    {
      "epoch": 1.5875706214689265,
      "grad_norm": 0.07819920778274536,
      "learning_rate": 2.514892518288988e-05,
      "loss": 0.7476,
      "mean_token_accuracy": 0.7687385514378547,
      "step": 35
    },
    {
      "epoch": 1.8135593220338984,
      "grad_norm": 0.07582569867372513,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.7477,
      "mean_token_accuracy": 0.7625166442245245,
      "step": 40
    },
    {
      "epoch": 1.9943502824858759,
      "mean_token_accuracy": 0.7703462559729815,
      "step": 44,
      "total_flos": 4.581572145947443e+16,
      "train_loss": 0.3802848349918019,
      "train_runtime": 844.2371,
      "train_samples_per_second": 0.839,
      "train_steps_per_second": 0.052
    }
  ],
  "logging_steps": 5,
  "max_steps": 44,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.581572145947443e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}