{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.025789813023855575,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025789813023855577,
      "grad_norm": 1.1339137554168701,
      "learning_rate": 0.0001,
      "loss": 1.0005,
      "step": 1
    },
    {
      "epoch": 0.0025789813023855577,
      "eval_loss": 1.0008567571640015,
      "eval_runtime": 23.8153,
      "eval_samples_per_second": 6.886,
      "eval_steps_per_second": 3.443,
      "step": 1
    },
    {
      "epoch": 0.0051579626047711154,
      "grad_norm": 1.0735493898391724,
      "learning_rate": 0.0002,
      "loss": 0.9353,
      "step": 2
    },
    {
      "epoch": 0.0051579626047711154,
      "eval_loss": 0.9892755150794983,
      "eval_runtime": 23.8059,
      "eval_samples_per_second": 6.889,
      "eval_steps_per_second": 3.445,
      "step": 2
    },
    {
      "epoch": 0.007736943907156673,
      "grad_norm": 1.1499661207199097,
      "learning_rate": 0.0003,
      "loss": 0.9784,
      "step": 3
    },
    {
      "epoch": 0.007736943907156673,
      "eval_loss": 0.9538405537605286,
      "eval_runtime": 23.8339,
      "eval_samples_per_second": 6.881,
      "eval_steps_per_second": 3.44,
      "step": 3
    },
    {
      "epoch": 0.010315925209542231,
      "grad_norm": 0.8054378032684326,
      "learning_rate": 0.0004,
      "loss": 1.0801,
      "step": 4
    },
    {
      "epoch": 0.010315925209542231,
      "eval_loss": 0.9168704152107239,
      "eval_runtime": 23.8096,
      "eval_samples_per_second": 6.888,
      "eval_steps_per_second": 3.444,
      "step": 4
    },
    {
      "epoch": 0.012894906511927788,
      "grad_norm": 0.5001803636550903,
      "learning_rate": 0.0005,
      "loss": 0.8091,
      "step": 5
    },
    {
      "epoch": 0.012894906511927788,
      "eval_loss": 0.9048398733139038,
      "eval_runtime": 23.8348,
      "eval_samples_per_second": 6.881,
      "eval_steps_per_second": 3.44,
      "step": 5
    },
    {
      "epoch": 0.015473887814313346,
      "grad_norm": 0.6461398601531982,
      "learning_rate": 0.0006,
      "loss": 0.8245,
      "step": 6
    },
    {
      "epoch": 0.015473887814313346,
      "eval_loss": 0.9021034240722656,
      "eval_runtime": 23.8587,
      "eval_samples_per_second": 6.874,
      "eval_steps_per_second": 3.437,
      "step": 6
    },
    {
      "epoch": 0.018052869116698903,
      "grad_norm": 0.6693152785301208,
      "learning_rate": 0.0007,
      "loss": 0.8799,
      "step": 7
    },
    {
      "epoch": 0.018052869116698903,
      "eval_loss": 0.8947257995605469,
      "eval_runtime": 23.8583,
      "eval_samples_per_second": 6.874,
      "eval_steps_per_second": 3.437,
      "step": 7
    },
    {
      "epoch": 0.020631850419084462,
      "grad_norm": 0.8548164367675781,
      "learning_rate": 0.0008,
      "loss": 0.7926,
      "step": 8
    },
    {
      "epoch": 0.020631850419084462,
      "eval_loss": 0.8847903609275818,
      "eval_runtime": 23.8385,
      "eval_samples_per_second": 6.88,
      "eval_steps_per_second": 3.44,
      "step": 8
    },
    {
      "epoch": 0.02321083172147002,
      "grad_norm": 0.6702899932861328,
      "learning_rate": 0.0009000000000000001,
      "loss": 0.9324,
      "step": 9
    },
    {
      "epoch": 0.02321083172147002,
      "eval_loss": 0.8762988448143005,
      "eval_runtime": 23.8478,
      "eval_samples_per_second": 6.877,
      "eval_steps_per_second": 3.438,
      "step": 9
    },
    {
      "epoch": 0.025789813023855575,
      "grad_norm": 0.7006492018699646,
      "learning_rate": 0.001,
      "loss": 0.8441,
      "step": 10
    },
    {
      "epoch": 0.025789813023855575,
      "eval_loss": 0.8688957691192627,
      "eval_runtime": 23.8639,
      "eval_samples_per_second": 6.872,
      "eval_steps_per_second": 3.436,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}