{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04678362573099415,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 1.374222993850708,
      "learning_rate": 2e-05,
      "loss": 1.1689,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 1.1875958442687988,
      "eval_runtime": 2.4949,
      "eval_samples_per_second": 36.074,
      "eval_steps_per_second": 18.037,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 0.7396091222763062,
      "learning_rate": 4e-05,
      "loss": 0.8861,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.972895085811615,
      "learning_rate": 6e-05,
      "loss": 0.8145,
      "step": 3
    },
    {
      "epoch": 0.014035087719298246,
      "eval_loss": 1.1773204803466797,
      "eval_runtime": 2.5194,
      "eval_samples_per_second": 35.722,
      "eval_steps_per_second": 17.861,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 1.4993739128112793,
      "learning_rate": 8e-05,
      "loss": 1.099,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.9818866848945618,
      "learning_rate": 0.0001,
      "loss": 0.9518,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.9982224702835083,
      "learning_rate": 0.00012,
      "loss": 0.8481,
      "step": 6
    },
    {
      "epoch": 0.028070175438596492,
      "eval_loss": 1.0458883047103882,
      "eval_runtime": 2.5468,
      "eval_samples_per_second": 35.338,
      "eval_steps_per_second": 17.669,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 1.0422838926315308,
      "learning_rate": 0.00014,
      "loss": 1.0522,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 0.9016379117965698,
      "learning_rate": 0.00016,
      "loss": 0.7957,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.7024203538894653,
      "learning_rate": 0.00018,
      "loss": 0.6036,
      "step": 9
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 0.8569401502609253,
      "eval_runtime": 2.5192,
      "eval_samples_per_second": 35.726,
      "eval_steps_per_second": 17.863,
      "step": 9
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 1.0091171264648438,
      "learning_rate": 0.0002,
      "loss": 0.7307,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 525102197243904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}