{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.972136222910217,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2476780185758514,
      "grad_norm": 1.7947527170181274,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2896,
      "step": 10
    },
    {
      "epoch": 0.4953560371517028,
      "grad_norm": 1.3205162286758423,
      "learning_rate": 9.865224352899119e-05,
      "loss": 0.846,
      "step": 20
    },
    {
      "epoch": 0.7430340557275542,
      "grad_norm": 0.6289039254188538,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6403,
      "step": 30
    },
    {
      "epoch": 0.9907120743034056,
      "grad_norm": 0.9729762077331543,
      "learning_rate": 8.43120818934367e-05,
      "loss": 0.5799,
      "step": 40
    },
    {
      "epoch": 1.238390092879257,
      "grad_norm": 0.8205918073654175,
      "learning_rate": 7.243995901002312e-05,
      "loss": 0.439,
      "step": 50
    },
    {
      "epoch": 1.4860681114551084,
      "grad_norm": 0.8421332836151123,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.4791,
      "step": 60
    },
    {
      "epoch": 1.7337461300309598,
      "grad_norm": 0.6772934794425964,
      "learning_rate": 4.4195354293738484e-05,
      "loss": 0.3748,
      "step": 70
    },
    {
      "epoch": 1.9814241486068112,
      "grad_norm": 1.1923753023147583,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.437,
      "step": 80
    },
    {
      "epoch": 2.2291021671826625,
      "grad_norm": 0.9291011095046997,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4269,
      "step": 90
    },
    {
      "epoch": 2.476780185758514,
      "grad_norm": 0.708964467048645,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.3449,
      "step": 100
    },
    {
      "epoch": 2.7244582043343653,
      "grad_norm": 0.8045765161514282,
      "learning_rate": 2.100524384225555e-06,
      "loss": 0.3244,
      "step": 110
    },
    {
      "epoch": 2.972136222910217,
      "grad_norm": 0.726122260093689,
      "learning_rate": 0.0,
      "loss": 0.3593,
      "step": 120
    },
    {
      "epoch": 2.972136222910217,
      "step": 120,
      "total_flos": 1389000190033920.0,
      "train_loss": 0.5450925727685293,
      "train_runtime": 1139.6636,
      "train_samples_per_second": 0.85,
      "train_steps_per_second": 0.105
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1389000190033920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}