{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002391886720244929,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.7837734404898585e-05,
      "eval_loss": 5.93709659576416,
      "eval_runtime": 943.8543,
      "eval_samples_per_second": 9.326,
      "eval_steps_per_second": 4.663,
      "step": 1
    },
    {
      "epoch": 0.00023918867202449293,
      "grad_norm": 2.328223466873169,
      "learning_rate": 5e-05,
      "loss": 5.333,
      "step": 5
    },
    {
      "epoch": 0.00047837734404898585,
      "grad_norm": 4.410595893859863,
      "learning_rate": 0.0001,
      "loss": 4.8527,
      "step": 10
    },
    {
      "epoch": 0.00047837734404898585,
      "eval_loss": 4.567225456237793,
      "eval_runtime": 945.1716,
      "eval_samples_per_second": 9.313,
      "eval_steps_per_second": 4.656,
      "step": 10
    },
    {
      "epoch": 0.0007175660160734788,
      "grad_norm": 2.0534868240356445,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.1485,
      "step": 15
    },
    {
      "epoch": 0.0009567546880979717,
      "grad_norm": 0.9618871212005615,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8658,
      "step": 20
    },
    {
      "epoch": 0.0009567546880979717,
      "eval_loss": 1.8261643648147583,
      "eval_runtime": 946.8065,
      "eval_samples_per_second": 9.297,
      "eval_steps_per_second": 4.648,
      "step": 20
    },
    {
      "epoch": 0.0011959433601224645,
      "grad_norm": 1.7864168882369995,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2157,
      "step": 25
    },
    {
      "epoch": 0.0014351320321469576,
      "grad_norm": 1.220751166343689,
      "learning_rate": 5e-05,
      "loss": 0.8402,
      "step": 30
    },
    {
      "epoch": 0.0014351320321469576,
      "eval_loss": 0.9265460968017578,
      "eval_runtime": 945.3293,
      "eval_samples_per_second": 9.311,
      "eval_steps_per_second": 4.656,
      "step": 30
    },
    {
      "epoch": 0.0016743207041714505,
      "grad_norm": 0.9833171963691711,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7063,
      "step": 35
    },
    {
      "epoch": 0.0019135093761959434,
      "grad_norm": 0.7486347556114197,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7917,
      "step": 40
    },
    {
      "epoch": 0.0019135093761959434,
      "eval_loss": 0.8493048548698425,
      "eval_runtime": 946.5996,
      "eval_samples_per_second": 9.299,
      "eval_steps_per_second": 4.649,
      "step": 40
    },
    {
      "epoch": 0.002152698048220436,
      "grad_norm": 0.7290636301040649,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.6596,
      "step": 45
    },
    {
      "epoch": 0.002391886720244929,
      "grad_norm": 0.5923378467559814,
      "learning_rate": 0.0,
      "loss": 0.6751,
      "step": 50
    },
    {
      "epoch": 0.002391886720244929,
      "eval_loss": 0.8390703797340393,
      "eval_runtime": 946.1498,
      "eval_samples_per_second": 9.303,
      "eval_steps_per_second": 4.651,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5160933600985088e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}