{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.310344827586207,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 1.0919902324676514,
      "learning_rate": 0.000511963042168714,
      "loss": 1.1243,
      "step": 100
    },
    {
      "epoch": 0.8620689655172413,
      "eval_loss": 0.3352593779563904,
      "eval_runtime": 21.0273,
      "eval_samples_per_second": 4.898,
      "eval_steps_per_second": 1.236,
      "step": 100
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 0.7907235622406006,
      "learning_rate": 0.0004055258192646154,
      "loss": 0.2577,
      "step": 200
    },
    {
      "epoch": 1.7241379310344827,
      "eval_loss": 0.2866515517234802,
      "eval_runtime": 20.7228,
      "eval_samples_per_second": 4.97,
      "eval_steps_per_second": 1.255,
      "step": 200
    },
    {
      "epoch": 2.586206896551724,
      "grad_norm": 0.10258855670690536,
      "learning_rate": 0.0002990885963605169,
      "loss": 0.1337,
      "step": 300
    },
    {
      "epoch": 2.586206896551724,
      "eval_loss": 0.2725263833999634,
      "eval_runtime": 20.8639,
      "eval_samples_per_second": 4.937,
      "eval_steps_per_second": 1.246,
      "step": 300
    },
    {
      "epoch": 3.4482758620689653,
      "grad_norm": 0.2434462606906891,
      "learning_rate": 0.00019265137345641833,
      "loss": 0.0734,
      "step": 400
    },
    {
      "epoch": 3.4482758620689653,
      "eval_loss": 0.27984029054641724,
      "eval_runtime": 20.7967,
      "eval_samples_per_second": 4.953,
      "eval_steps_per_second": 1.25,
      "step": 400
    },
    {
      "epoch": 4.310344827586207,
      "grad_norm": 0.4092065393924713,
      "learning_rate": 8.621415055231981e-05,
      "loss": 0.0422,
      "step": 500
    },
    {
      "epoch": 4.310344827586207,
      "eval_loss": 0.2786606252193451,
      "eval_runtime": 20.6352,
      "eval_samples_per_second": 4.991,
      "eval_steps_per_second": 1.26,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 580,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.370747847573504e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 0.0005641172813917223,
    "per_device_train_batch_size": 8,
    "weight_decay": 0.0006732813397449721
  }
}