{
  "best_metric": 0.5362022519111633,
  "best_model_checkpoint": "newer_model\\checkpoint-1500",
  "epoch": 0.9997037037037036,
  "eval_steps": 500,
  "global_step": 1687,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 4.876801013946533,
      "learning_rate": 4.7095435684647304e-05,
      "loss": 1.0575,
      "step": 100
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 6.375751972198486,
      "learning_rate": 4.413159454653231e-05,
      "loss": 0.8362,
      "step": 200
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 8.8690824508667,
      "learning_rate": 4.1167753408417306e-05,
      "loss": 0.7795,
      "step": 300
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 3.57802414894104,
      "learning_rate": 3.820391227030231e-05,
      "loss": 0.6769,
      "step": 400
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 7.336911201477051,
      "learning_rate": 3.524007113218732e-05,
      "loss": 0.7182,
      "step": 500
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 0.6516097187995911,
      "eval_runtime": 1000.1241,
      "eval_samples_per_second": 3.0,
      "eval_steps_per_second": 0.375,
      "step": 500
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 4.612793445587158,
      "learning_rate": 3.2276229994072324e-05,
      "loss": 0.6576,
      "step": 600
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 9.853538513183594,
      "learning_rate": 2.9342027267338474e-05,
      "loss": 0.6399,
      "step": 700
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 7.267094612121582,
      "learning_rate": 2.6378186129223475e-05,
      "loss": 0.6346,
      "step": 800
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 9.086668968200684,
      "learning_rate": 2.341434499110848e-05,
      "loss": 0.5982,
      "step": 900
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 8.705070495605469,
      "learning_rate": 2.045050385299348e-05,
      "loss": 0.6216,
      "step": 1000
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 0.6586094498634338,
      "eval_runtime": 659.5062,
      "eval_samples_per_second": 4.549,
      "eval_steps_per_second": 0.569,
      "step": 1000
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 8.674996376037598,
      "learning_rate": 1.7486662714878483e-05,
      "loss": 0.5332,
      "step": 1100
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 6.852212905883789,
      "learning_rate": 1.4522821576763487e-05,
      "loss": 0.5707,
      "step": 1200
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 5.364168167114258,
      "learning_rate": 1.155898043864849e-05,
      "loss": 0.5683,
      "step": 1300
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 7.750982761383057,
      "learning_rate": 8.595139300533492e-06,
      "loss": 0.5271,
      "step": 1400
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 8.749728202819824,
      "learning_rate": 5.631298162418495e-06,
      "loss": 0.5368,
      "step": 1500
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.5362022519111633,
      "eval_runtime": 659.3085,
      "eval_samples_per_second": 4.55,
      "eval_steps_per_second": 0.569,
      "step": 1500
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 6.8793230056762695,
      "learning_rate": 2.6674570243034972e-06,
      "loss": 0.5459,
      "step": 1600
    }
  ],
  "logging_steps": 100,
  "max_steps": 1687,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2069541520994304.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}