{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017003188097768332,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001700318809776833,
      "grad_norm": 1.0692028999328613,
      "learning_rate": 2e-05,
      "loss": 1.2256,
      "step": 1
    },
    {
      "epoch": 0.0001700318809776833,
      "eval_loss": 1.1506123542785645,
      "eval_runtime": 375.4934,
      "eval_samples_per_second": 6.597,
      "eval_steps_per_second": 3.3,
      "step": 1
    },
    {
      "epoch": 0.0003400637619553666,
      "grad_norm": 1.705147385597229,
      "learning_rate": 4e-05,
      "loss": 0.9111,
      "step": 2
    },
    {
      "epoch": 0.0005100956429330499,
      "grad_norm": 1.4833035469055176,
      "learning_rate": 6e-05,
      "loss": 1.1934,
      "step": 3
    },
    {
      "epoch": 0.0005100956429330499,
      "eval_loss": 1.1395306587219238,
      "eval_runtime": 376.6512,
      "eval_samples_per_second": 6.576,
      "eval_steps_per_second": 3.29,
      "step": 3
    },
    {
      "epoch": 0.0006801275239107333,
      "grad_norm": 2.3167366981506348,
      "learning_rate": 8e-05,
      "loss": 1.3197,
      "step": 4
    },
    {
      "epoch": 0.0008501594048884166,
      "grad_norm": 1.5329622030258179,
      "learning_rate": 0.0001,
      "loss": 1.2143,
      "step": 5
    },
    {
      "epoch": 0.0010201912858660998,
      "grad_norm": 1.040611743927002,
      "learning_rate": 0.00012,
      "loss": 0.9643,
      "step": 6
    },
    {
      "epoch": 0.0010201912858660998,
      "eval_loss": 1.0490574836730957,
      "eval_runtime": 376.4499,
      "eval_samples_per_second": 6.58,
      "eval_steps_per_second": 3.291,
      "step": 6
    },
    {
      "epoch": 0.0011902231668437832,
      "grad_norm": 1.5477181673049927,
      "learning_rate": 0.00014,
      "loss": 1.2377,
      "step": 7
    },
    {
      "epoch": 0.0013602550478214665,
      "grad_norm": 1.29509699344635,
      "learning_rate": 0.00016,
      "loss": 0.8408,
      "step": 8
    },
    {
      "epoch": 0.0015302869287991498,
      "grad_norm": 1.7048213481903076,
      "learning_rate": 0.00018,
      "loss": 1.0168,
      "step": 9
    },
    {
      "epoch": 0.0015302869287991498,
      "eval_loss": 0.952135443687439,
      "eval_runtime": 376.1474,
      "eval_samples_per_second": 6.585,
      "eval_steps_per_second": 3.294,
      "step": 9
    },
    {
      "epoch": 0.0017003188097768332,
      "grad_norm": 1.1248693466186523,
      "learning_rate": 0.0002,
      "loss": 0.9549,
      "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
}