{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003596152117234559,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003596152117234559,
      "grad_norm": 8.813926696777344,
      "learning_rate": 2e-05,
      "loss": 15.0108,
      "step": 1
    },
    {
      "epoch": 0.0003596152117234559,
      "eval_loss": 2.9921517372131348,
      "eval_runtime": 188.0494,
      "eval_samples_per_second": 6.227,
      "eval_steps_per_second": 3.116,
      "step": 1
    },
    {
      "epoch": 0.0007192304234469118,
      "grad_norm": 4.008182048797607,
      "learning_rate": 4e-05,
      "loss": 10.4945,
      "step": 2
    },
    {
      "epoch": 0.0010788456351703676,
      "grad_norm": 6.952348232269287,
      "learning_rate": 6e-05,
      "loss": 12.3666,
      "step": 3
    },
    {
      "epoch": 0.0010788456351703676,
      "eval_loss": 2.979651927947998,
      "eval_runtime": 194.1958,
      "eval_samples_per_second": 6.03,
      "eval_steps_per_second": 3.018,
      "step": 3
    },
    {
      "epoch": 0.0014384608468938236,
      "grad_norm": 6.131217956542969,
      "learning_rate": 8e-05,
      "loss": 11.3941,
      "step": 4
    },
    {
      "epoch": 0.0017980760586172794,
      "grad_norm": 8.966681480407715,
      "learning_rate": 0.0001,
      "loss": 12.7776,
      "step": 5
    },
    {
      "epoch": 0.0021576912703407353,
      "grad_norm": 4.6905646324157715,
      "learning_rate": 0.00012,
      "loss": 11.3521,
      "step": 6
    },
    {
      "epoch": 0.0021576912703407353,
      "eval_loss": 2.879966974258423,
      "eval_runtime": 194.3147,
      "eval_samples_per_second": 6.026,
      "eval_steps_per_second": 3.016,
      "step": 6
    },
    {
      "epoch": 0.0025173064820641915,
      "grad_norm": 5.06572151184082,
      "learning_rate": 0.00014,
      "loss": 12.1123,
      "step": 7
    },
    {
      "epoch": 0.0028769216937876473,
      "grad_norm": 61.05796813964844,
      "learning_rate": 0.00016,
      "loss": 15.4283,
      "step": 8
    },
    {
      "epoch": 0.003236536905511103,
      "grad_norm": 10.057729721069336,
      "learning_rate": 0.00018,
      "loss": 10.6844,
      "step": 9
    },
    {
      "epoch": 0.003236536905511103,
      "eval_loss": 2.76363205909729,
      "eval_runtime": 194.0228,
      "eval_samples_per_second": 6.035,
      "eval_steps_per_second": 3.02,
      "step": 9
    },
    {
      "epoch": 0.003596152117234559,
      "grad_norm": 3.328113317489624,
      "learning_rate": 0.0002,
      "loss": 10.3796,
      "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": 3166204172697600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}