{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.041925974451359316,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002096298722567966,
      "eval_loss": 1.8161089420318604,
      "eval_runtime": 509.8911,
      "eval_samples_per_second": 15.758,
      "eval_steps_per_second": 7.88,
      "step": 1
    },
    {
      "epoch": 0.008385194890271864,
      "grad_norm": 0.8249205350875854,
      "learning_rate": 1e-05,
      "loss": 1.6789,
      "step": 40
    },
    {
      "epoch": 0.008385194890271864,
      "eval_loss": 1.765670657157898,
      "eval_runtime": 510.5563,
      "eval_samples_per_second": 15.738,
      "eval_steps_per_second": 7.87,
      "step": 40
    },
    {
      "epoch": 0.016770389780543727,
      "grad_norm": 0.8328395485877991,
      "learning_rate": 2e-05,
      "loss": 1.4912,
      "step": 80
    },
    {
      "epoch": 0.016770389780543727,
      "eval_loss": 1.425034523010254,
      "eval_runtime": 509.0786,
      "eval_samples_per_second": 15.783,
      "eval_steps_per_second": 7.893,
      "step": 80
    },
    {
      "epoch": 0.025155584670815592,
      "grad_norm": 0.8690986037254333,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.2154,
      "step": 120
    },
    {
      "epoch": 0.025155584670815592,
      "eval_loss": 1.2270913124084473,
      "eval_runtime": 509.6912,
      "eval_samples_per_second": 15.764,
      "eval_steps_per_second": 7.883,
      "step": 120
    },
    {
      "epoch": 0.033540779561087454,
      "grad_norm": 0.8671352863311768,
      "learning_rate": 5.000000000000003e-06,
      "loss": 1.1632,
      "step": 160
    },
    {
      "epoch": 0.033540779561087454,
      "eval_loss": 1.1926395893096924,
      "eval_runtime": 509.61,
      "eval_samples_per_second": 15.767,
      "eval_steps_per_second": 7.884,
      "step": 160
    },
    {
      "epoch": 0.041925974451359316,
      "grad_norm": 0.9359524250030518,
      "learning_rate": 0.0,
      "loss": 1.1496,
      "step": 200
    },
    {
      "epoch": 0.041925974451359316,
      "eval_loss": 1.188537836074829,
      "eval_runtime": 509.1432,
      "eval_samples_per_second": 15.781,
      "eval_steps_per_second": 7.892,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.479651398516736e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}