{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 1.8840750455856323,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 10.773,
      "step": 50
    },
    {
      "epoch": 0.1,
      "grad_norm": 3.636681318283081,
      "learning_rate": 9.900000000000002e-06,
      "loss": 10.751,
      "step": 100
    },
    {
      "epoch": 0.15,
      "grad_norm": 2.9410653114318848,
      "learning_rate": 1.49e-05,
      "loss": 10.1756,
      "step": 150
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.6391408443450928,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 9.222,
      "step": 200
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.7996461391448975,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 8.1145,
      "step": 250
    },
    {
      "epoch": 0.3,
      "grad_norm": 2.6515960693359375,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 6.4262,
      "step": 300
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.3619678020477295,
      "learning_rate": 3.49e-05,
      "loss": 4.0977,
      "step": 350
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6726661920547485,
      "learning_rate": 3.99e-05,
      "loss": 2.6687,
      "step": 400
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4897717237472534,
      "learning_rate": 4.49e-05,
      "loss": 2.4435,
      "step": 450
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.46205028891563416,
      "learning_rate": 4.99e-05,
      "loss": 2.2027,
      "step": 500
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.5643090605735779,
      "learning_rate": 5.4900000000000006e-05,
      "loss": 1.9658,
      "step": 550
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4644372761249542,
      "learning_rate": 5.99e-05,
      "loss": 1.6887,
      "step": 600
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.6230539679527283,
      "learning_rate": 6.49e-05,
      "loss": 1.4829,
      "step": 650
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5066797137260437,
      "learning_rate": 6.99e-05,
      "loss": 1.3053,
      "step": 700
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.4611658453941345,
      "learning_rate": 7.49e-05,
      "loss": 1.1403,
      "step": 750
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3986978828907013,
      "learning_rate": 7.99e-05,
      "loss": 1.098,
      "step": 800
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.375344842672348,
      "learning_rate": 8.49e-05,
      "loss": 1.0219,
      "step": 850
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.34341996908187866,
      "learning_rate": 8.99e-05,
      "loss": 1.0019,
      "step": 900
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.40908634662628174,
      "learning_rate": 9.49e-05,
      "loss": 0.9543,
      "step": 950
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.35558778047561646,
      "learning_rate": 9.99e-05,
      "loss": 0.9663,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "step": 1000,
      "total_flos": 2.199920836608e+16,
      "train_loss": 3.97500887298584,
      "train_runtime": 2211.8953,
      "train_samples_per_second": 14.467,
      "train_steps_per_second": 0.452
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.199920836608e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}