{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007806492659945276,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5612985319890554e-05,
      "eval_loss": 1.5307185649871826,
      "eval_runtime": 3503.1138,
      "eval_samples_per_second": 7.699,
      "eval_steps_per_second": 3.849,
      "step": 1
    },
    {
      "epoch": 7.806492659945277e-05,
      "grad_norm": 1.2548145055770874,
      "learning_rate": 5e-05,
      "loss": 1.5664,
      "step": 5
    },
    {
      "epoch": 0.00015612985319890554,
      "grad_norm": 1.7928839921951294,
      "learning_rate": 0.0001,
      "loss": 1.3714,
      "step": 10
    },
    {
      "epoch": 0.00015612985319890554,
      "eval_loss": 1.3988229036331177,
      "eval_runtime": 3558.3404,
      "eval_samples_per_second": 7.579,
      "eval_steps_per_second": 3.79,
      "step": 10
    },
    {
      "epoch": 0.0002341947797983583,
      "grad_norm": 2.427678108215332,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1713,
      "step": 15
    },
    {
      "epoch": 0.0003122597063978111,
      "grad_norm": 1.928297758102417,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1113,
      "step": 20
    },
    {
      "epoch": 0.0003122597063978111,
      "eval_loss": 1.178857684135437,
      "eval_runtime": 3555.449,
      "eval_samples_per_second": 7.585,
      "eval_steps_per_second": 3.793,
      "step": 20
    },
    {
      "epoch": 0.0003903246329972638,
      "grad_norm": 1.6140434741973877,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0855,
      "step": 25
    },
    {
      "epoch": 0.0004683895595967166,
      "grad_norm": 1.1178323030471802,
      "learning_rate": 5e-05,
      "loss": 1.0627,
      "step": 30
    },
    {
      "epoch": 0.0004683895595967166,
      "eval_loss": 1.0991060733795166,
      "eval_runtime": 3554.2794,
      "eval_samples_per_second": 7.588,
      "eval_steps_per_second": 3.794,
      "step": 30
    },
    {
      "epoch": 0.0005464544861961694,
      "grad_norm": 1.6532901525497437,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.9146,
      "step": 35
    },
    {
      "epoch": 0.0006245194127956221,
      "grad_norm": 1.2385560274124146,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9705,
      "step": 40
    },
    {
      "epoch": 0.0006245194127956221,
      "eval_loss": 1.075425624847412,
      "eval_runtime": 3554.6002,
      "eval_samples_per_second": 7.587,
      "eval_steps_per_second": 3.794,
      "step": 40
    },
    {
      "epoch": 0.0007025843393950749,
      "grad_norm": 1.2929309606552124,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.0751,
      "step": 45
    },
    {
      "epoch": 0.0007806492659945276,
      "grad_norm": 1.0120068788528442,
      "learning_rate": 0.0,
      "loss": 1.0506,
      "step": 50
    },
    {
      "epoch": 0.0007806492659945276,
      "eval_loss": 1.0700223445892334,
      "eval_runtime": 3551.7424,
      "eval_samples_per_second": 7.593,
      "eval_steps_per_second": 3.797,
      "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": 1.364053633007616e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}