{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009868989168784388,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.2896630562614627e-05,
      "eval_loss": 2.757450580596924,
      "eval_runtime": 330.1473,
      "eval_samples_per_second": 38.771,
      "eval_steps_per_second": 19.385,
      "step": 1
    },
    {
      "epoch": 9.868989168784387e-05,
      "grad_norm": 2.3541181087493896,
      "learning_rate": 6e-05,
      "loss": 2.9059,
      "step": 3
    },
    {
      "epoch": 0.00019737978337568775,
      "grad_norm": 1.6740833520889282,
      "learning_rate": 0.00012,
      "loss": 2.7077,
      "step": 6
    },
    {
      "epoch": 0.000263173044500917,
      "eval_loss": 2.5687427520751953,
      "eval_runtime": 332.2892,
      "eval_samples_per_second": 38.521,
      "eval_steps_per_second": 19.26,
      "step": 8
    },
    {
      "epoch": 0.0002960696750635316,
      "grad_norm": 1.3266692161560059,
      "learning_rate": 0.00018,
      "loss": 2.7015,
      "step": 9
    },
    {
      "epoch": 0.0003947595667513755,
      "grad_norm": 1.2737700939178467,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.5519,
      "step": 12
    },
    {
      "epoch": 0.0004934494584392194,
      "grad_norm": 1.1872025728225708,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.518,
      "step": 15
    },
    {
      "epoch": 0.000526346089001834,
      "eval_loss": 2.4903249740600586,
      "eval_runtime": 331.946,
      "eval_samples_per_second": 38.56,
      "eval_steps_per_second": 19.28,
      "step": 16
    },
    {
      "epoch": 0.0005921393501270632,
      "grad_norm": 1.1035131216049194,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.645,
      "step": 18
    },
    {
      "epoch": 0.0006908292418149071,
      "grad_norm": 1.0961910486221313,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.3494,
      "step": 21
    },
    {
      "epoch": 0.000789519133502751,
      "grad_norm": 1.122851848602295,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.5578,
      "step": 24
    },
    {
      "epoch": 0.000789519133502751,
      "eval_loss": 2.4727261066436768,
      "eval_runtime": 333.5442,
      "eval_samples_per_second": 38.376,
      "eval_steps_per_second": 19.188,
      "step": 24
    },
    {
      "epoch": 0.0008882090251905949,
      "grad_norm": 1.148537039756775,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.5374,
      "step": 27
    },
    {
      "epoch": 0.0009868989168784388,
      "grad_norm": 1.082649827003479,
      "learning_rate": 0.0,
      "loss": 2.5278,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 465923588751360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}